=== STARTING NEW TRAINING RUN LOGGING TO training_terminal.log ===
Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured.
[HF] Programmatic login successful using HF_TOKEN.

[GPU] CUDA is available! Using GPU: NVIDIA RTX PRO 6000 Blackwell Server Edition


[Data] Loading BabyLM-2026-Strict-Small ...

README.md:   0%|          | 0.00/2.56k [00:00<?, ?B/s]
README.md: 100%|##########| 2.56k/2.56k [00:00<00:00, 11.2MB/s]

bnc_spoken.train.txt:   0%|          | 0.00/4.06M [00:00<?, ?B/s]
bnc_spoken.train.txt: 100%|##########| 4.06M/4.06M [00:00<00:00, 171MB/s]


childes.train.txt: reconstructing file:   0%|          |  0.00B / 15.2MB            
childes.train.txt: downloading bytes:           |  0.00B            
childes.train.txt: downloading bytes:           | 3.75kB            
childes.train.txt: downloading bytes: 1         |  173kB,   371B/s  
childes.train.txt: downloading bytes: #####1    | 7.75MB, 17.0kB/s  

childes.train.txt: reconstructing file: 100%|##########| 15.2MB / 15.2MB            
childes.train.txt: downloading bytes: ##########| 7.75MB,  761kB/s  
childes.train.txt: downloading bytes: ##########| 7.75MB,  761kB/s  

childes.train.txt: reconstructing file: 100%|##########| 15.2MB / 15.2MB, 1.49MB/s  


gutenberg.train.txt: reconstructing file:   0%|          |  0.00B / 14.0MB            
gutenberg.train.txt: downloading bytes:           |  0.00B            
gutenberg.train.txt: downloading bytes: #1        | 1.57MB            

gutenberg.train.txt: reconstructing file: 100%|##########| 14.0MB / 14.0MB            
gutenberg.train.txt: downloading bytes: ##########| 8.74MB,  864kB/s  
gutenberg.train.txt: downloading bytes: ##########| 8.74MB,  864kB/s  

gutenberg.train.txt: reconstructing file: 100%|##########| 14.0MB / 14.0MB, 1.39MB/s  


open_subtitles.train.txt: reconstructing file:   0%|          |  0.00B / 12.2MB            
open_subtitles.train.txt: downloading bytes:           |  0.00B            
open_subtitles.train.txt: downloading bytes: ######    | 7.33MB            

open_subtitles.train.txt: reconstructing file: 100%|##########| 12.2MB / 12.2MB            
open_subtitles.train.txt: downloading bytes: ##########| 7.33MB,  727kB/s  
open_subtitles.train.txt: downloading bytes: ##########| 7.33MB,  727kB/s  

open_subtitles.train.txt: reconstructing file: 100%|##########| 12.2MB / 12.2MB, 1.20MB/s  

simple_wiki.train.txt:   0%|          | 0.00/8.86M [00:00<?, ?B/s]
simple_wiki.train.txt: 100%|##########| 8.86M/8.86M [00:00<00:00, 165MB/s]

switchboard.train.txt:   0%|          | 0.00/123k [00:00<?, ?B/s]
switchboard.train.txt: 100%|##########| 123k/123k [00:00<00:00, 145MB/s]

Generating train split:   0%|          | 0/1104106 [00:00<?, ? examples/s]
Generating train split:  40%|###9      | 439545/1104106 [00:00<00:00, 2823851.52 examples/s]
Generating train split:  90%|######### | 996363/1104106 [00:00<00:00, 2324270.01 examples/s]
Generating train split: 100%|##########| 1104106/1104106 [00:00<00:00, 2098565.16 examples/s]
[Tokenizer] Generating fresh HuggingFace BPE Tokenizer model with 16384 slots...
[Tokenizer] Tokenizer training completed and saved to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/bpe_vocab_16k.json'.
[DataLoader:train] Tokenising dataset sequences...
[DataLoader:train] Total tokens: 12,688,865 | Epoch steps: 1,548
[Model] torch.compile() successfully verified graph optimizations

[Training] Starting XpertGPT MoEP training for 8 epochs...
/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/_inductor/lowering.py:7095: UserWarning: 
Online softmax is disabled on the fly since Inductor decides to
split the reduction. Cut an issue to PyTorch if this is an
important use case and you want to speed it up with online
softmax.

  warnings.warn(
/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/site-packages/torch/_inductor/lowering.py:7095: UserWarning: 
Online softmax is disabled on the fly since Inductor decides to
split the reduction. Cut an issue to PyTorch if this is an
important use case and you want to speed it up with online
softmax.

  warnings.warn(
[E01     1/1548 G      0|CLM] train=9.8720  mask=20.0%  norm=1.558  lr=3.75e-07  dt=57104.3ms  words=8,192
[E01     2/1548 G      1|CLM] train=9.9017  mask=20.0%  norm=7.906  lr=7.50e-07  dt=  41.2ms  words=16,384
[E01     3/1548 G      2|CLM] train=9.8914  mask=20.0%  norm=6.116  lr=1.13e-06  dt=  37.9ms  words=24,576
[E01     4/1548 G      3|CLM] train=9.8468  mask=20.0%  norm=3.173  lr=1.50e-06  dt=  37.3ms  words=32,768
[E01     5/1548 G      4|CLM] train=9.8455  mask=20.0%  norm=3.602  lr=1.87e-06  dt=  37.5ms  words=40,960
[E01     6/1548 G      5|CLM] train=9.8327  mask=20.0%  norm=2.912  lr=2.25e-06  dt=  37.2ms  words=49,152
[E01     7/1548 G      6|CLM] train=9.8621  mask=20.0%  norm=3.124  lr=2.62e-06  dt=  36.9ms  words=57,344
[E01     8/1548 G      7|CLM] train=9.8572  mask=20.0%  norm=2.837  lr=3.00e-06  dt=  36.8ms  words=65,536
[E01     9/1548 G      8|CLM] train=9.8307  mask=20.0%  norm=2.745  lr=3.37e-06  dt=  37.1ms  words=73,728
[E01    10/1548 G      9|CLM] train=9.8442  mask=20.0%  norm=2.111  lr=3.75e-06  dt=  37.1ms  words=81,920
[E01    11/1548 G     10|CLM] train=9.8717  mask=20.0%  norm=5.845  lr=4.12e-06  dt=  37.3ms  words=90,112
[E01    12/1548 G     11|CLM] train=9.8368  mask=20.0%  norm=2.308  lr=4.50e-06  dt=  37.1ms  words=98,304
[E01    13/1548 G     12|CLM] train=9.7860  mask=20.0%  norm=3.361  lr=4.87e-06  dt=  37.0ms  words=106,496
[E01    14/1548 G     13|CLM] train=9.8762  mask=20.0%  norm=5.432  lr=5.25e-06  dt=  36.9ms  words=114,688
[E01    15/1548 G     14|CLM] train=9.8047  mask=20.0%  norm=7.087  lr=5.62e-06  dt=  37.0ms  words=122,880
[E01    16/1548 G     15|CLM] train=9.8301  mask=20.0%  norm=2.807  lr=6.00e-06  dt=  37.1ms  words=131,072
[E01    17/1548 G     16|CLM] train=9.7771  mask=20.0%  norm=2.610  lr=6.37e-06  dt=  36.9ms  words=139,264
[E01    18/1548 G     17|CLM] train=9.7825  mask=20.0%  norm=3.135  lr=6.75e-06  dt=  37.1ms  words=147,456
[E01    19/1548 G     18|CLM] train=9.8051  mask=20.0%  norm=5.335  lr=7.12e-06  dt=  36.8ms  words=155,648
[E01    20/1548 G     19|CLM] train=9.7865  mask=20.0%  norm=2.922  lr=7.50e-06  dt=  37.0ms  words=163,840
[E01    21/1548 G     20|CLM] train=9.7190  mask=20.0%  norm=3.375  lr=7.87e-06  dt=  36.9ms  words=172,032
[E01    22/1548 G     21|CLM] train=9.8111  mask=20.0%  norm=1.973  lr=8.25e-06  dt=  37.2ms  words=180,224
[E01    23/1548 G     22|CLM] train=9.7989  mask=20.0%  norm=1.992  lr=8.62e-06  dt=  37.3ms  words=188,416
[E01    24/1548 G     23|CLM] train=9.6560  mask=20.0%  norm=5.968  lr=9.00e-06  dt=  37.3ms  words=196,608
[E01    25/1548 G     24|CLM] train=9.6271  mask=20.0%  norm=3.935  lr=9.37e-06  dt=  36.9ms  words=204,800
[E01    26/1548 G     25|CLM] train=9.7700  mask=20.0%  norm=1.983  lr=9.75e-06  dt=  36.9ms  words=212,992
[E01    27/1548 G     26|CLM] train=9.6296  mask=20.0%  norm=6.145  lr=1.01e-05  dt=  37.3ms  words=221,184
[E01    28/1548 G     27|CLM] train=9.6407  mask=20.0%  norm=3.104  lr=1.05e-05  dt=  37.1ms  words=229,376
[E01    29/1548 G     28|CLM] train=9.5260  mask=20.0%  norm=6.768  lr=1.09e-05  dt=  37.2ms  words=237,568
[E01    30/1548 G     29|CLM] train=9.6499  mask=20.0%  norm=2.718  lr=1.12e-05  dt=  37.0ms  words=245,760
[E01    31/1548 G     30|CLM] train=9.7271  mask=20.0%  norm=2.042  lr=1.16e-05  dt=  37.0ms  words=253,952
[E01    32/1548 G     31|CLM] train=9.5515  mask=20.0%  norm=3.319  lr=1.20e-05  dt=  36.9ms  words=262,144
[E01    33/1548 G     32|CLM] train=9.4857  mask=20.0%  norm=5.140  lr=1.24e-05  dt=  36.9ms  words=270,336
[E01    34/1548 G     33|CLM] train=9.5889  mask=20.0%  norm=2.790  lr=1.27e-05  dt=  37.0ms  words=278,528
[E01    35/1548 G     34|CLM] train=9.5104  mask=20.0%  norm=3.336  lr=1.31e-05  dt=  36.7ms  words=286,720
[E01    36/1548 G     35|CLM] train=9.5567  mask=20.0%  norm=3.006  lr=1.35e-05  dt=  36.8ms  words=294,912
[E01    37/1548 G     36|CLM] train=9.7189  mask=20.0%  norm=2.013  lr=1.39e-05  dt=  36.9ms  words=303,104
[E01    38/1548 G     37|CLM] train=9.5940  mask=20.0%  norm=2.465  lr=1.42e-05  dt=  36.9ms  words=311,296
[E01    39/1548 G     38|CLM] train=9.5991  mask=20.0%  norm=2.285  lr=1.46e-05  dt=  36.8ms  words=319,488
[E01    40/1548 G     39|CLM] train=9.5400  mask=20.0%  norm=4.719  lr=1.50e-05  dt=  44.8ms  words=327,680
[E01    41/1548 G     40|CLM] train=9.3261  mask=20.0%  norm=3.525  lr=1.54e-05  dt=  38.6ms  words=335,872
[E01    42/1548 G     41|CLM] train=9.3370  mask=20.0%  norm=3.312  lr=1.57e-05  dt=  37.6ms  words=344,064
[E01    43/1548 G     42|CLM] train=9.4569  mask=20.0%  norm=2.863  lr=1.61e-05  dt=  37.6ms  words=352,256
[E01    44/1548 G     43|CLM] train=9.3938  mask=20.0%  norm=2.855  lr=1.65e-05  dt=  44.8ms  words=360,448
[E01    45/1548 G     44|CLM] train=9.5149  mask=20.0%  norm=2.575  lr=1.69e-05  dt=  39.1ms  words=368,640
[E01    46/1548 G     45|CLM] train=8.9760  mask=20.0%  norm=6.304  lr=1.72e-05  dt=  41.9ms  words=376,832
[E01    47/1548 G     46|CLM] train=9.1424  mask=20.0%  norm=5.122  lr=1.76e-05  dt=  43.5ms  words=385,024
[E01    48/1548 G     47|CLM] train=9.0636  mask=20.0%  norm=5.682  lr=1.80e-05  dt=  45.5ms  words=393,216
[E01    49/1548 G     48|CLM] train=8.9993  mask=20.0%  norm=5.068  lr=1.84e-05  dt=  38.5ms  words=401,408
[E01    50/1548 G     49|CLM] train=8.9478  mask=20.0%  norm=5.596  lr=1.87e-05  dt=  36.8ms  words=409,600
[E01    51/1548 G     50|CLM] train=9.4886  mask=20.0%  norm=2.814  lr=1.91e-05  dt=  43.9ms  words=417,792
[E01    52/1548 G     51|CLM] train=9.5385  mask=20.0%  norm=2.228  lr=1.95e-05  dt=  36.7ms  words=425,984
[E01    53/1548 G     52|CLM] train=9.2022  mask=20.0%  norm=2.535  lr=1.99e-05  dt=  37.0ms  words=434,176
[E01    54/1548 G     53|CLM] train=8.5428  mask=20.0%  norm=6.091  lr=2.02e-05  dt=  36.9ms  words=442,368
[E01    55/1548 G     54|CLM] train=8.7315  mask=20.0%  norm=4.886  lr=2.06e-05  dt=  36.7ms  words=450,560
[E01    56/1548 G     55|CLM] train=9.1218  mask=20.0%  norm=2.324  lr=2.10e-05  dt=  36.6ms  words=458,752
[E01    57/1548 G     56|CLM] train=8.8157  mask=20.0%  norm=3.945  lr=2.14e-05  dt=  36.8ms  words=466,944
[E01    58/1548 G     57|CLM] train=8.5971  mask=20.0%  norm=3.945  lr=2.18e-05  dt=  36.8ms  words=475,136
[E01    59/1548 G     58|CLM] train=8.6565  mask=20.0%  norm=3.780  lr=2.21e-05  dt=  36.7ms  words=483,328
[E01    60/1548 G     59|CLM] train=8.9911  mask=20.0%  norm=2.806  lr=2.25e-05  dt=  36.8ms  words=491,520
[E01    61/1548 G     60|CLM] train=9.2122  mask=20.0%  norm=2.053  lr=2.29e-05  dt=  36.8ms  words=499,712
[E01    62/1548 G     61|CLM] train=9.3891  mask=20.0%  norm=2.138  lr=2.32e-05  dt=  36.8ms  words=507,904
[E01    63/1548 G     62|CLM] train=8.4368  mask=19.9%  norm=3.847  lr=2.36e-05  dt=  36.7ms  words=516,096
[E01    64/1548 G     63|CLM] train=8.5812  mask=19.9%  norm=3.778  lr=2.40e-05  dt=  36.6ms  words=524,288
[E01    65/1548 G     64|CLM] train=8.2668  mask=19.9%  norm=3.652  lr=2.44e-05  dt=  36.7ms  words=532,480
[E01    66/1548 G     65|CLM] train=8.2323  mask=19.9%  norm=3.520  lr=2.47e-05  dt=  37.9ms  words=540,672
[E01    67/1548 G     66|CLM] train=8.3083  mask=19.9%  norm=3.468  lr=2.51e-05  dt=  38.9ms  words=548,864
[E01    68/1548 G     67|CLM] train=8.1669  mask=19.9%  norm=3.321  lr=2.55e-05  dt=  37.1ms  words=557,056
[E01    69/1548 G     68|CLM] train=7.9991  mask=19.9%  norm=3.740  lr=2.59e-05  dt=  38.9ms  words=565,248
[E01    70/1548 G     69|CLM] train=8.9471  mask=19.9%  norm=2.017  lr=2.62e-05  dt=  43.1ms  words=573,440
[E01    71/1548 G     70|CLM] train=8.0685  mask=19.9%  norm=3.431  lr=2.66e-05  dt=  42.8ms  words=581,632
[E01    72/1548 G     71|CLM] train=9.0290  mask=19.9%  norm=1.935  lr=2.70e-05  dt=  38.6ms  words=589,824
[E01    73/1548 G     72|CLM] train=9.2177  mask=19.9%  norm=2.015  lr=2.74e-05  dt=  37.3ms  words=598,016
[E01    74/1548 G     73|CLM] train=8.8329  mask=19.9%  norm=2.121  lr=2.77e-05  dt=  37.3ms  words=606,208
[E01    75/1548 G     74|CLM] train=9.3007  mask=19.9%  norm=2.546  lr=2.81e-05  dt=  38.9ms  words=614,400
[E01    76/1548 G     75|CLM] train=8.0178  mask=19.9%  norm=2.979  lr=2.85e-05  dt=  39.2ms  words=622,592
[E01    77/1548 G     76|CLM] train=8.8936  mask=19.9%  norm=1.987  lr=2.89e-05  dt=  37.7ms  words=630,784
[E01    78/1548 G     77|CLM] train=9.0217  mask=19.9%  norm=2.018  lr=2.92e-05  dt=  37.6ms  words=638,976
[E01    79/1548 G     78|CLM] train=8.4257  mask=19.9%  norm=2.565  lr=2.96e-05  dt=  36.9ms  words=647,168
[E01    80/1548 G     79|CLM] train=8.9960  mask=19.9%  norm=1.940  lr=3.00e-05  dt=  38.0ms  words=655,360
[E01    81/1548 G     80|CLM] train=7.7975  mask=19.9%  norm=3.286  lr=3.04e-05  dt=  36.7ms  words=663,552
[E01    82/1548 G     81|CLM] train=8.2034  mask=19.9%  norm=2.935  lr=3.07e-05  dt=  36.7ms  words=671,744
[E01    83/1548 G     82|CLM] train=8.7066  mask=19.9%  norm=2.035  lr=3.11e-05  dt=  45.2ms  words=679,936
[E01    84/1548 G     83|CLM] train=7.9498  mask=19.9%  norm=3.049  lr=3.15e-05  dt=  38.6ms  words=688,128
[E01    85/1548 G     84|CLM] train=8.8168  mask=19.9%  norm=1.756  lr=3.19e-05  dt=  49.9ms  words=696,320
[E01    86/1548 G     85|CLM] train=8.7463  mask=19.9%  norm=1.960  lr=3.22e-05  dt=  41.5ms  words=704,512
[E01    87/1548 G     86|CLM] train=8.6708  mask=19.9%  norm=1.922  lr=3.26e-05  dt=  39.3ms  words=712,704
[E01    88/1548 G     87|CLM] train=7.8429  mask=19.9%  norm=2.964  lr=3.30e-05  dt=  46.3ms  words=720,896
[E01    89/1548 G     88|CLM] train=7.4825  mask=19.9%  norm=3.464  lr=3.34e-05  dt=  36.7ms  words=729,088
[E01    90/1548 G     89|CLM] train=8.7143  mask=19.9%  norm=1.907  lr=3.37e-05  dt=  36.6ms  words=737,280
[E01    91/1548 G     90|CLM] train=8.6601  mask=19.9%  norm=1.884  lr=3.41e-05  dt=  36.6ms  words=745,472
[E01    92/1548 G     91|CLM] train=8.7108  mask=19.9%  norm=1.816  lr=3.45e-05  dt=  38.6ms  words=753,664
[E01    93/1548 G     92|CLM] train=8.9493  mask=19.9%  norm=1.526  lr=3.49e-05  dt=  36.7ms  words=761,856
[E01    94/1548 G     93|CLM] train=8.7143  mask=19.9%  norm=1.684  lr=3.52e-05  dt=  36.4ms  words=770,048
[E01    95/1548 G     94|CLM] train=8.6647  mask=19.9%  norm=1.816  lr=3.56e-05  dt=  36.4ms  words=778,240
[E01    96/1548 G     95|CLM] train=8.6077  mask=19.9%  norm=1.900  lr=3.60e-05  dt=  36.4ms  words=786,432
[E01    97/1548 G     96|CLM] train=7.3824  mask=19.9%  norm=3.470  lr=3.64e-05  dt=  36.6ms  words=794,624
[E01    98/1548 G     97|CLM] train=8.9539  mask=19.9%  norm=2.005  lr=3.67e-05  dt=  36.4ms  words=802,816
[E01    99/1548 G     98|CLM] train=8.9733  mask=19.9%  norm=1.652  lr=3.71e-05  dt=  36.4ms  words=811,008
[E01   100/1548 G     99|CLM] train=8.5919  mask=19.9%  norm=1.810  lr=3.75e-05  dt=  36.8ms  words=819,200
[E01   101/1548 G    100|CLM] train=7.3853  mask=19.9%  norm=2.964  lr=3.79e-05  dt=  36.4ms  words=827,392
[E01   102/1548 G    101|CLM] train=8.9914  mask=19.9%  norm=1.952  lr=3.83e-05  dt=  36.4ms  words=835,584
[E01   103/1548 G    102|CLM] train=7.4299  mask=19.9%  norm=3.038  lr=3.86e-05  dt=  36.8ms  words=843,776
[E01   104/1548 G    103|CLM] train=7.5648  mask=19.9%  norm=3.223  lr=3.90e-05  dt=  36.6ms  words=851,968
[E01   105/1548 G    104|CLM] train=7.8385  mask=19.9%  norm=3.050  lr=3.94e-05  dt=  36.9ms  words=860,160
[E01   106/1548 G    105|CLM] train=7.2354  mask=19.9%  norm=3.017  lr=3.97e-05  dt=  36.5ms  words=868,352
[E01   107/1548 G    106|CLM] train=8.7896  mask=19.9%  norm=1.718  lr=4.01e-05  dt=  36.6ms  words=876,544
[E01   108/1548 G    107|CLM] train=7.1382  mask=19.9%  norm=3.269  lr=4.05e-05  dt=  36.5ms  words=884,736
[E01   109/1548 G    108|CLM] train=8.5148  mask=19.9%  norm=1.794  lr=4.09e-05  dt=  36.7ms  words=892,928
[E01   110/1548 G    109|CLM] train=8.3082  mask=19.9%  norm=2.246  lr=4.12e-05  dt=  36.6ms  words=901,120
[E01   111/1548 G    110|CLM] train=7.1718  mask=19.9%  norm=4.420  lr=4.16e-05  dt=  36.7ms  words=909,312
[E01   112/1548 G    111|CLM] train=8.5169  mask=19.9%  norm=1.725  lr=4.20e-05  dt=  36.5ms  words=917,504
[E01   113/1548 G    112|CLM] train=8.3891  mask=19.9%  norm=2.014  lr=4.24e-05  dt=  36.6ms  words=925,696
[E01   114/1548 G    113|CLM] train=8.7551  mask=19.9%  norm=1.883  lr=4.27e-05  dt=  36.5ms  words=933,888
[E01   115/1548 G    114|CLM] train=7.5702  mask=19.9%  norm=2.598  lr=4.31e-05  dt=  36.6ms  words=942,080
[E01   116/1548 G    115|CLM] train=8.7104  mask=19.9%  norm=1.674  lr=4.35e-05  dt=  36.8ms  words=950,272
[E01   117/1548 G    116|CLM] train=7.1237  mask=19.9%  norm=3.267  lr=4.39e-05  dt=  36.6ms  words=958,464
[E01   118/1548 G    117|CLM] train=7.0184  mask=19.9%  norm=3.011  lr=4.42e-05  dt=  36.6ms  words=966,656
[E01   119/1548 G    118|CLM] train=8.3692  mask=19.9%  norm=1.746  lr=4.46e-05  dt=  36.6ms  words=974,848
[E01   120/1548 G    119|CLM] train=8.6875  mask=19.9%  norm=1.897  lr=4.50e-05  dt=  36.5ms  words=983,040
[E01   121/1548 G    120|CLM] train=7.0686  mask=19.9%  norm=3.197  lr=4.54e-05  dt=  36.7ms  words=991,232
[E01   122/1548 G    121|CLM] train=7.4745  mask=19.9%  norm=3.916  lr=4.57e-05  dt=  36.6ms  words=999,424
[E01   123/1548 G    122|CLM] train=8.2679  mask=19.9%  norm=1.789  lr=4.61e-05  dt=  36.7ms  words=1,007,616

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_1M'...
[Checkpoint] Checkpoint 'chck_1M' successfully saved.
[E01   124/1548 G    123|CLM] train=8.1910  mask=19.9%  norm=1.927  lr=4.65e-05  dt=  37.3ms  words=1,015,808
[E01   125/1548 G    124|CLM] train=6.5944  mask=19.9%  norm=2.985  lr=4.69e-05  dt=  36.8ms  words=1,024,000
[E01   126/1548 G    125|CLM] train=8.3274  mask=19.9%  norm=1.658  lr=4.72e-05  dt=  36.8ms  words=1,032,192
[E01   127/1548 G    126|CLM] train=6.2149  mask=19.9%  norm=4.424  lr=4.76e-05  dt=  36.6ms  words=1,040,384
[E01   128/1548 G    127|CLM] train=8.2725  mask=19.9%  norm=1.733  lr=4.80e-05  dt=  36.5ms  words=1,048,576
[E01   129/1548 G    128|CLM] train=6.4479  mask=19.9%  norm=3.022  lr=4.84e-05  dt=  36.2ms  words=1,056,768
[E01   130/1548 G    129|CLM] train=6.8979  mask=19.9%  norm=3.178  lr=4.87e-05  dt=  36.6ms  words=1,064,960
[E01   131/1548 G    130|CLM] train=8.4723  mask=19.9%  norm=1.743  lr=4.91e-05  dt=  36.6ms  words=1,073,152
[E01   132/1548 G    131|CLM] train=8.5256  mask=19.9%  norm=1.819  lr=4.95e-05  dt=  36.5ms  words=1,081,344
[E01   133/1548 G    132|CLM] train=6.1940  mask=19.9%  norm=3.054  lr=4.99e-05  dt=  36.7ms  words=1,089,536
[E01   134/1548 G    133|CLM] train=8.0573  mask=19.9%  norm=1.897  lr=5.03e-05  dt=  36.5ms  words=1,097,728
[E01   135/1548 G    134|CLM] train=8.2921  mask=19.9%  norm=1.831  lr=5.06e-05  dt=  36.5ms  words=1,105,920
[E01   136/1548 G    135|CLM] train=7.9866  mask=19.9%  norm=1.983  lr=5.10e-05  dt=  36.4ms  words=1,114,112
[E01   137/1548 G    136|CLM] train=6.1397  mask=19.9%  norm=3.743  lr=5.14e-05  dt=  36.5ms  words=1,122,304
[E01   138/1548 G    137|CLM] train=7.9253  mask=19.9%  norm=1.826  lr=5.17e-05  dt=  36.6ms  words=1,130,496
[E01   139/1548 G    138|CLM] train=8.2705  mask=19.9%  norm=1.727  lr=5.21e-05  dt=  36.7ms  words=1,138,688
[E01   140/1548 G    139|CLM] train=6.1938  mask=19.9%  norm=3.708  lr=5.25e-05  dt=  36.5ms  words=1,146,880
[E01   141/1548 G    140|CLM] train=6.8501  mask=19.9%  norm=2.979  lr=5.29e-05  dt=  36.7ms  words=1,155,072
[E01   142/1548 G    141|CLM] train=8.0193  mask=19.9%  norm=1.852  lr=5.33e-05  dt=  36.5ms  words=1,163,264
[E01   143/1548 G    142|CLM] train=7.8673  mask=19.9%  norm=1.889  lr=5.36e-05  dt=  36.5ms  words=1,171,456
[E01   144/1548 G    143|CLM] train=6.3333  mask=19.9%  norm=5.287  lr=5.40e-05  dt=  36.6ms  words=1,179,648
[E01   145/1548 G    144|CLM] train=8.3771  mask=19.9%  norm=1.564  lr=5.44e-05  dt=  36.6ms  words=1,187,840
[E01   146/1548 G    145|CLM] train=8.5176  mask=19.9%  norm=1.627  lr=5.47e-05  dt=  36.5ms  words=1,196,032
[E01   147/1548 G    146|CLM] train=8.4053  mask=19.9%  norm=1.631  lr=5.51e-05  dt=  36.5ms  words=1,204,224
[E01   148/1548 G    147|CLM] train=6.4515  mask=19.9%  norm=2.905  lr=5.55e-05  dt=  36.4ms  words=1,212,416
[E01   149/1548 G    148|CLM] train=7.9761  mask=19.9%  norm=1.755  lr=5.59e-05  dt=  36.3ms  words=1,220,608
[E01   150/1548 G    149|CLM] train=8.1675  mask=19.9%  norm=1.600  lr=5.62e-05  dt=  36.7ms  words=1,228,800
[E01   151/1548 G    150|CLM] train=7.4297  mask=19.9%  norm=3.833  lr=5.66e-05  dt=  36.6ms  words=1,236,992
[E01   152/1548 G    151|CLM] train=8.1973  mask=19.9%  norm=1.673  lr=5.70e-05  dt=  36.7ms  words=1,245,184
[E01   153/1548 G    152|CLM] train=8.1789  mask=19.9%  norm=1.617  lr=5.74e-05  dt=  36.6ms  words=1,253,376
[E01   154/1548 G    153|CLM] train=7.8639  mask=19.9%  norm=1.785  lr=5.77e-05  dt=  36.4ms  words=1,261,568
[E01   155/1548 G    154|CLM] train=5.9869  mask=19.9%  norm=2.480  lr=5.81e-05  dt=  36.6ms  words=1,269,760
[E01   156/1548 G    155|CLM] train=8.2921  mask=19.9%  norm=1.557  lr=5.85e-05  dt=  36.7ms  words=1,277,952
[E01   157/1548 G    156|CLM] train=8.7732  mask=19.9%  norm=2.411  lr=5.89e-05  dt=  36.5ms  words=1,286,144
[E01   158/1548 G    157|CLM] train=5.4721  mask=19.9%  norm=3.608  lr=5.92e-05  dt=  36.6ms  words=1,294,336
[E01   159/1548 G    158|CLM] train=5.6944  mask=19.9%  norm=3.173  lr=5.96e-05  dt=  36.7ms  words=1,302,528
[E01   160/1548 G    159|CLM] train=7.1153  mask=19.9%  norm=2.105  lr=6.00e-05  dt=  36.5ms  words=1,310,720
[E01   161/1548 G    160|CLM] train=7.8147  mask=19.9%  norm=1.665  lr=6.04e-05  dt=  36.5ms  words=1,318,912
[E01   162/1548 G    161|CLM] train=8.1620  mask=19.9%  norm=1.516  lr=6.07e-05  dt=  36.4ms  words=1,327,104
[E01   163/1548 G    162|CLM] train=7.7524  mask=19.9%  norm=1.629  lr=6.11e-05  dt=  36.7ms  words=1,335,296
[E01   164/1548 G    163|CLM] train=6.5218  mask=19.9%  norm=3.643  lr=6.15e-05  dt=  36.5ms  words=1,343,488
[E01   165/1548 G    164|CLM] train=7.7020  mask=19.9%  norm=1.801  lr=6.19e-05  dt=  36.6ms  words=1,351,680
[E01   166/1548 G    165|CLM] train=7.5148  mask=19.9%  norm=1.816  lr=6.22e-05  dt=  36.5ms  words=1,359,872
[E01   167/1548 G    166|CLM] train=7.7860  mask=19.9%  norm=1.651  lr=6.26e-05  dt=  37.9ms  words=1,368,064
[E01   168/1548 G    167|CLM] train=7.5874  mask=19.9%  norm=1.620  lr=6.30e-05  dt=  47.0ms  words=1,376,256
[E01   169/1548 G    168|CLM] train=7.5097  mask=19.9%  norm=1.705  lr=6.34e-05  dt=  37.9ms  words=1,384,448
[E01   170/1548 G    169|CLM] train=5.7804  mask=19.9%  norm=8.649  lr=6.37e-05  dt=  38.2ms  words=1,392,640
[E01   171/1548 G    170|CLM] train=7.5396  mask=19.9%  norm=1.619  lr=6.41e-05  dt=  37.1ms  words=1,400,832
[E01   172/1548 G    171|CLM] train=5.7661  mask=19.9%  norm=4.786  lr=6.45e-05  dt=  36.9ms  words=1,409,024
[E01   173/1548 G    172|CLM] train=7.5028  mask=19.9%  norm=1.742  lr=6.49e-05  dt=  37.1ms  words=1,417,216
[E01   174/1548 G    173|CLM] train=5.6947  mask=19.9%  norm=2.578  lr=6.53e-05  dt=  36.9ms  words=1,425,408
[E01   175/1548 G    174|CLM] train=5.8627  mask=19.9%  norm=3.073  lr=6.56e-05  dt=  37.7ms  words=1,433,600
[E01   176/1548 G    175|CLM] train=6.1297  mask=19.9%  norm=2.532  lr=6.60e-05  dt=  37.2ms  words=1,441,792
[E01   177/1548 G    176|CLM] train=7.9778  mask=19.9%  norm=1.586  lr=6.64e-05  dt=  36.8ms  words=1,449,984
[E01   178/1548 G    177|CLM] train=8.1559  mask=19.9%  norm=1.401  lr=6.67e-05  dt=  36.9ms  words=1,458,176
[E01   179/1548 G    178|CLM] train=5.8259  mask=19.9%  norm=5.240  lr=6.71e-05  dt=  37.5ms  words=1,466,368
[E01   180/1548 G    179|CLM] train=6.0212  mask=19.9%  norm=3.622  lr=6.75e-05  dt=  37.4ms  words=1,474,560
[E01   181/1548 G    180|CLM] train=8.0234  mask=19.9%  norm=1.435  lr=6.79e-05  dt=  36.5ms  words=1,482,752
[E01   182/1548 G    181|CLM] train=5.7837  mask=19.9%  norm=2.532  lr=6.82e-05  dt=  42.3ms  words=1,490,944
[E01   183/1548 G    182|CLM] train=6.6659  mask=19.9%  norm=2.061  lr=6.86e-05  dt=  39.2ms  words=1,499,136
[E01   184/1548 G    183|CLM] train=7.5367  mask=19.9%  norm=1.581  lr=6.90e-05  dt=  46.8ms  words=1,507,328
[E01   185/1548 G    184|CLM] train=7.2721  mask=19.9%  norm=1.863  lr=6.94e-05  dt=  44.7ms  words=1,515,520
[E01   186/1548 G    185|CLM] train=7.4386  mask=19.9%  norm=1.539  lr=6.97e-05  dt=  42.4ms  words=1,523,712
[E01   187/1548 G    186|CLM] train=7.2027  mask=19.8%  norm=1.625  lr=7.01e-05  dt=  42.7ms  words=1,531,904
[E01   188/1548 G    187|CLM] train=7.7011  mask=19.8%  norm=1.574  lr=7.05e-05  dt=  39.3ms  words=1,540,096
[E01   189/1548 G    188|CLM] train=7.7034  mask=19.8%  norm=1.389  lr=7.09e-05  dt=  36.6ms  words=1,548,288
[E01   190/1548 G    189|CLM] train=7.2675  mask=19.8%  norm=1.614  lr=7.12e-05  dt=  46.3ms  words=1,556,480
[E01   191/1548 G    190|CLM] train=5.8523  mask=19.8%  norm=3.167  lr=7.16e-05  dt=  50.1ms  words=1,564,672
[E01   192/1548 G    191|CLM] train=7.9622  mask=19.8%  norm=3.063  lr=7.20e-05  dt=  36.7ms  words=1,572,864
[E01   193/1548 G    192|CLM] train=5.4350  mask=19.8%  norm=2.400  lr=7.24e-05  dt=  36.6ms  words=1,581,056
[E01   194/1548 G    193|CLM] train=7.7323  mask=19.8%  norm=1.331  lr=7.27e-05  dt=  36.8ms  words=1,589,248
[E01   195/1548 G    194|CLM] train=5.0980  mask=19.8%  norm=2.526  lr=7.31e-05  dt=  36.7ms  words=1,597,440
[E01   196/1548 G    195|CLM] train=7.6413  mask=19.8%  norm=1.533  lr=7.35e-05  dt=  36.9ms  words=1,605,632
[E01   197/1548 G    196|CLM] train=5.7866  mask=19.8%  norm=2.347  lr=7.39e-05  dt=  36.7ms  words=1,613,824
[E01   198/1548 G    197|CLM] train=7.0317  mask=19.8%  norm=2.001  lr=7.42e-05  dt=  36.8ms  words=1,622,016
[E01   199/1548 G    198|CLM] train=8.0200  mask=19.8%  norm=1.228  lr=7.46e-05  dt=  36.6ms  words=1,630,208
[E01   200/1548 G    199|CLM] train=5.7787  mask=19.8%  norm=2.881  lr=7.50e-05  dt=  36.7ms  words=1,638,400
[E01   201/1548 G    200|CLM] train=6.9282  mask=19.8%  norm=1.811  lr=7.54e-05  dt=  36.6ms  words=1,646,592
[E01   202/1548 G    201|CLM] train=5.9938  mask=19.8%  norm=2.339  lr=7.57e-05  dt=  36.8ms  words=1,654,784
[E01   203/1548 G    202|CLM] train=7.2923  mask=19.8%  norm=1.682  lr=7.61e-05  dt=  36.7ms  words=1,662,976
[E01   204/1548 G    203|CLM] train=5.3920  mask=19.8%  norm=2.600  lr=7.65e-05  dt=  36.8ms  words=1,671,168
[E01   205/1548 G    204|CLM] train=5.2617  mask=19.8%  norm=3.411  lr=7.69e-05  dt=  36.6ms  words=1,679,360
[E01   206/1548 G    205|CLM] train=7.4316  mask=19.8%  norm=1.470  lr=7.72e-05  dt=  36.8ms  words=1,687,552
[E01   207/1548 G    206|CLM] train=6.8688  mask=19.8%  norm=1.563  lr=7.76e-05  dt=  36.6ms  words=1,695,744
[E01   208/1548 G    207|CLM] train=6.9989  mask=19.8%  norm=1.487  lr=7.80e-05  dt=  36.7ms  words=1,703,936
[E01   209/1548 G    208|CLM] train=6.9868  mask=19.8%  norm=1.631  lr=7.84e-05  dt=  36.7ms  words=1,712,128
[E01   210/1548 G    209|CLM] train=7.0580  mask=19.8%  norm=1.367  lr=7.88e-05  dt=  36.7ms  words=1,720,320
[E01   211/1548 G    210|CLM] train=7.1421  mask=19.8%  norm=1.548  lr=7.91e-05  dt=  36.7ms  words=1,728,512
[E01   212/1548 G    211|CLM] train=5.3931  mask=19.8%  norm=9.837  lr=7.95e-05  dt=  36.7ms  words=1,736,704
[E01   213/1548 G    212|CLM] train=7.1650  mask=19.8%  norm=1.309  lr=7.99e-05  dt=  36.7ms  words=1,744,896
[E01   214/1548 G    213|CLM] train=7.3879  mask=19.8%  norm=1.355  lr=8.02e-05  dt=  36.7ms  words=1,753,088
[E01   215/1548 G    214|CLM] train=7.0938  mask=19.8%  norm=1.516  lr=8.06e-05  dt=  36.4ms  words=1,761,280
[E01   216/1548 G    215|CLM] train=5.4886  mask=19.8%  norm=2.641  lr=8.10e-05  dt=  36.5ms  words=1,769,472
[E01   217/1548 G    216|CLM] train=7.4624  mask=19.8%  norm=1.248  lr=8.14e-05  dt=  37.1ms  words=1,777,664
[E01   218/1548 G    217|CLM] train=5.2775  mask=19.8%  norm=1.973  lr=8.17e-05  dt=  36.6ms  words=1,785,856
[E01   219/1548 G    218|CLM] train=7.1192  mask=19.8%  norm=1.391  lr=8.21e-05  dt=  36.7ms  words=1,794,048
[E01   220/1548 G    219|CLM] train=6.7919  mask=19.8%  norm=1.546  lr=8.25e-05  dt=  36.5ms  words=1,802,240
[E01   221/1548 G    220|CLM] train=5.5481  mask=19.8%  norm=2.293  lr=8.29e-05  dt=  36.7ms  words=1,810,432
[E01   222/1548 G    221|CLM] train=6.6698  mask=19.8%  norm=1.355  lr=8.32e-05  dt=  36.6ms  words=1,818,624
[E01   223/1548 G    222|CLM] train=6.6544  mask=19.8%  norm=1.323  lr=8.36e-05  dt=  36.6ms  words=1,826,816
[E01   224/1548 G    223|CLM] train=7.5497  mask=19.8%  norm=1.350  lr=8.40e-05  dt=  36.7ms  words=1,835,008
[E01   225/1548 G    224|CLM] train=6.4871  mask=19.8%  norm=1.505  lr=8.44e-05  dt=  36.6ms  words=1,843,200
[E01   226/1548 G    225|CLM] train=5.4740  mask=19.8%  norm=1.817  lr=8.48e-05  dt=  36.7ms  words=1,851,392
[E01   227/1548 G    226|CLM] train=5.0949  mask=19.8%  norm=1.732  lr=8.51e-05  dt=  36.7ms  words=1,859,584
[E01   228/1548 G    227|CLM] train=5.2417  mask=19.8%  norm=1.663  lr=8.55e-05  dt=  36.7ms  words=1,867,776
[E01   229/1548 G    228|CLM] train=7.4102  mask=19.8%  norm=1.253  lr=8.59e-05  dt=  36.8ms  words=1,875,968
[E01   230/1548 G    229|CLM] train=6.9139  mask=19.8%  norm=1.253  lr=8.62e-05  dt=  37.2ms  words=1,884,160
[E01   231/1548 G    230|CLM] train=6.6316  mask=19.8%  norm=1.334  lr=8.66e-05  dt=  36.5ms  words=1,892,352
[E01   232/1548 G    231|CLM] train=6.5340  mask=19.8%  norm=1.345  lr=8.70e-05  dt=  36.7ms  words=1,900,544
[E01   233/1548 G    232|CLM] train=7.2311  mask=19.8%  norm=1.196  lr=8.74e-05  dt=  36.9ms  words=1,908,736
[E01   234/1548 G    233|CLM] train=5.2083  mask=19.8%  norm=4.082  lr=8.77e-05  dt=  36.7ms  words=1,916,928
[E01   235/1548 G    234|CLM] train=6.5591  mask=19.8%  norm=1.184  lr=8.81e-05  dt=  36.6ms  words=1,925,120
[E01   236/1548 G    235|CLM] train=4.8107  mask=19.8%  norm=2.973  lr=8.85e-05  dt=  36.6ms  words=1,933,312
[E01   237/1548 G    236|CLM] train=7.1965  mask=19.8%  norm=1.336  lr=8.89e-05  dt=  36.8ms  words=1,941,504
[E01   238/1548 G    237|CLM] train=5.3199  mask=19.8%  norm=2.773  lr=8.92e-05  dt=  36.6ms  words=1,949,696
[E01   239/1548 G    238|CLM] train=6.4534  mask=19.8%  norm=1.361  lr=8.96e-05  dt=  36.7ms  words=1,957,888
[E01   240/1548 G    239|CLM] train=7.1570  mask=19.8%  norm=1.207  lr=9.00e-05  dt=  36.6ms  words=1,966,080
[E01   241/1548 G    240|CLM] train=7.8432  mask=19.8%  norm=1.648  lr=9.04e-05  dt=  36.5ms  words=1,974,272
[E01   242/1548 G    241|CLM] train=6.9742  mask=19.8%  norm=1.306  lr=9.07e-05  dt=  36.4ms  words=1,982,464
[E01   243/1548 G    242|CLM] train=7.4431  mask=19.8%  norm=1.112  lr=9.11e-05  dt=  36.7ms  words=1,990,656
[E01   244/1548 G    243|CLM] train=6.4750  mask=19.8%  norm=1.412  lr=9.15e-05  dt=  37.1ms  words=1,998,848
[E01   245/1548 G    244|CLM] train=7.3406  mask=19.8%  norm=1.151  lr=9.19e-05  dt=  36.8ms  words=2,007,040

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_2M'...
[Checkpoint] Checkpoint 'chck_2M' successfully saved.
[E01   246/1548 G    245|CLM] train=5.1634  mask=19.8%  norm=8.372  lr=9.22e-05  dt=  37.4ms  words=2,015,232
[E01   247/1548 G    246|CLM] train=6.4209  mask=19.8%  norm=1.220  lr=9.26e-05  dt=  36.6ms  words=2,023,424
[E01   248/1548 G    247|CLM] train=7.7219  mask=19.8%  norm=1.292  lr=9.30e-05  dt=  36.9ms  words=2,031,616
[E01   249/1548 G    248|CLM] train=4.9752  mask=19.8%  norm=2.841  lr=9.34e-05  dt=  36.7ms  words=2,039,808
[E01   250/1548 G    249|CLM] train=6.7021  mask=19.8%  norm=1.206  lr=9.38e-05  dt=  36.6ms  words=2,048,000
[E01   251/1548 G    250|CLM] train=7.3062  mask=19.8%  norm=1.305  lr=9.41e-05  dt=  36.5ms  words=2,056,192
[E01   252/1548 G    251|CLM] train=6.4690  mask=19.8%  norm=1.166  lr=9.45e-05  dt=  36.7ms  words=2,064,384
[E01   253/1548 G    252|CLM] train=6.8805  mask=19.8%  norm=1.170  lr=9.49e-05  dt=  37.0ms  words=2,072,576
[E01   254/1548 G    253|CLM] train=4.7889  mask=19.8%  norm=2.181  lr=9.52e-05  dt=  36.6ms  words=2,080,768
[E01   255/1548 G    254|CLM] train=7.2453  mask=19.8%  norm=1.453  lr=9.56e-05  dt=  36.5ms  words=2,088,960
[E01   256/1548 G    255|CLM] train=6.5835  mask=19.8%  norm=1.277  lr=9.60e-05  dt=  36.6ms  words=2,097,152
[E01   257/1548 G    256|CLM] train=6.0026  mask=19.8%  norm=2.165  lr=9.64e-05  dt=  36.6ms  words=2,105,344
[E01   258/1548 G    257|CLM] train=6.8830  mask=19.8%  norm=1.299  lr=9.67e-05  dt=  36.5ms  words=2,113,536
[E01   259/1548 G    258|CLM] train=7.4235  mask=19.8%  norm=0.854  lr=9.71e-05  dt=  36.8ms  words=2,121,728
[E01   260/1548 G    259|CLM] train=7.0128  mask=19.8%  norm=1.154  lr=9.75e-05  dt=  36.7ms  words=2,129,920
[E01   261/1548 G    260|CLM] train=5.3561  mask=19.8%  norm=1.288  lr=9.79e-05  dt=  36.6ms  words=2,138,112
[E01   262/1548 G    261|CLM] train=6.6394  mask=19.8%  norm=1.274  lr=9.82e-05  dt=  36.5ms  words=2,146,304
[E01   263/1548 G    262|CLM] train=7.4449  mask=19.8%  norm=0.932  lr=9.86e-05  dt=  36.7ms  words=2,154,496
[E01   264/1548 G    263|CLM] train=5.4268  mask=19.8%  norm=2.339  lr=9.90e-05  dt=  36.6ms  words=2,162,688
[E01   265/1548 G    264|CLM] train=4.6700  mask=19.8%  norm=1.459  lr=9.94e-05  dt=  36.7ms  words=2,170,880
[E01   266/1548 G    265|CLM] train=4.5214  mask=19.8%  norm=1.603  lr=9.97e-05  dt=  36.7ms  words=2,179,072
[E01   267/1548 G    266|CLM] train=6.8527  mask=19.8%  norm=1.328  lr=1.00e-04  dt=  36.7ms  words=2,187,264
[E01   268/1548 G    267|CLM] train=6.1995  mask=19.8%  norm=1.765  lr=1.01e-04  dt=  36.6ms  words=2,195,456
[E01   269/1548 G    268|CLM] train=7.6690  mask=19.8%  norm=1.385  lr=1.01e-04  dt=  36.6ms  words=2,203,648
[E01   270/1548 G    269|CLM] train=6.7412  mask=19.8%  norm=0.865  lr=1.01e-04  dt=  36.7ms  words=2,211,840
[E01   271/1548 G    270|CLM] train=6.8275  mask=19.8%  norm=0.933  lr=1.02e-04  dt=  36.7ms  words=2,220,032
[E01   272/1548 G    271|CLM] train=5.1076  mask=19.8%  norm=4.946  lr=1.02e-04  dt=  36.5ms  words=2,228,224
[E01   273/1548 G    272|CLM] train=7.0150  mask=19.8%  norm=1.307  lr=1.02e-04  dt=  36.5ms  words=2,236,416
[E01   274/1548 G    273|CLM] train=4.9429  mask=19.8%  norm=1.882  lr=1.03e-04  dt=  36.6ms  words=2,244,608
[E01   275/1548 G    274|CLM] train=4.7488  mask=19.8%  norm=1.576  lr=1.03e-04  dt=  36.6ms  words=2,252,800
[E01   276/1548 G    275|CLM] train=6.9588  mask=19.8%  norm=0.917  lr=1.03e-04  dt=  36.6ms  words=2,260,992
[E01   277/1548 G    276|CLM] train=5.0421  mask=19.8%  norm=1.509  lr=1.04e-04  dt=  36.6ms  words=2,269,184
[E01   278/1548 G    277|CLM] train=7.7693  mask=19.8%  norm=1.081  lr=1.04e-04  dt=  36.6ms  words=2,277,376
[E01   279/1548 G    278|CLM] train=6.3249  mask=19.8%  norm=1.088  lr=1.05e-04  dt=  36.5ms  words=2,285,568
[E01   280/1548 G    279|CLM] train=6.6611  mask=19.8%  norm=1.198  lr=1.05e-04  dt=  36.8ms  words=2,293,760
[E01   281/1548 G    280|CLM] train=6.4467  mask=19.8%  norm=1.083  lr=1.05e-04  dt=  36.7ms  words=2,301,952
[E01   282/1548 G    281|CLM] train=6.3623  mask=19.8%  norm=0.777  lr=1.06e-04  dt=  36.6ms  words=2,310,144
[E01   283/1548 G    282|CLM] train=6.3373  mask=19.8%  norm=1.331  lr=1.06e-04  dt=  36.6ms  words=2,318,336
[E01   284/1548 G    283|CLM] train=5.5141  mask=19.8%  norm=3.122  lr=1.07e-04  dt=  36.6ms  words=2,326,528
[E01   285/1548 G    284|CLM] train=6.5622  mask=19.8%  norm=1.207  lr=1.07e-04  dt=  36.6ms  words=2,334,720
[E01   286/1548 G    285|CLM] train=6.5397  mask=19.8%  norm=1.205  lr=1.07e-04  dt=  36.6ms  words=2,342,912
[E01   287/1548 G    286|CLM] train=4.9532  mask=19.8%  norm=1.839  lr=1.08e-04  dt=  36.8ms  words=2,351,104
[E01   288/1548 G    287|CLM] train=6.2232  mask=19.8%  norm=1.141  lr=1.08e-04  dt=  36.7ms  words=2,359,296
[E01   289/1548 G    288|CLM] train=6.8492  mask=19.8%  norm=0.938  lr=1.08e-04  dt=  36.6ms  words=2,367,488
[E01   290/1548 G    289|CLM] train=6.7053  mask=19.8%  norm=1.054  lr=1.09e-04  dt=  36.6ms  words=2,375,680
[E01   291/1548 G    290|CLM] train=6.2813  mask=19.8%  norm=0.886  lr=1.09e-04  dt=  36.7ms  words=2,383,872
[E01   292/1548 G    291|CLM] train=6.2782  mask=19.8%  norm=0.788  lr=1.09e-04  dt=  36.7ms  words=2,392,064
[E01   293/1548 G    292|CLM] train=7.7726  mask=19.8%  norm=1.116  lr=1.10e-04  dt=  37.1ms  words=2,400,256
[E01   294/1548 G    293|CLM] train=6.2675  mask=19.8%  norm=0.987  lr=1.10e-04  dt=  36.6ms  words=2,408,448
[E01   295/1548 G    294|CLM] train=6.3316  mask=19.8%  norm=0.683  lr=1.11e-04  dt=  36.5ms  words=2,416,640
[E01   296/1548 G    295|CLM] train=6.0333  mask=19.8%  norm=1.021  lr=1.11e-04  dt=  36.6ms  words=2,424,832
[E01   297/1548 G    296|CLM] train=4.7879  mask=19.8%  norm=1.532  lr=1.11e-04  dt=  36.7ms  words=2,433,024
[E01   298/1548 G    297|CLM] train=4.5845  mask=19.8%  norm=2.010  lr=1.12e-04  dt=  36.6ms  words=2,441,216
[E01   299/1548 G    298|CLM] train=4.9370  mask=19.8%  norm=1.789  lr=1.12e-04  dt=  36.7ms  words=2,449,408
[E01   300/1548 G    299|CLM] train=6.7198  mask=19.8%  norm=1.154  lr=1.12e-04  dt=  36.5ms  words=2,457,600
[E01   301/1548 G    300|CLM] train=6.5236  mask=19.8%  norm=1.030  lr=1.13e-04  dt=  36.6ms  words=2,465,792
[E01   302/1548 G    301|CLM] train=5.0744  mask=19.8%  norm=1.477  lr=1.13e-04  dt=  36.8ms  words=2,473,984
[E01   303/1548 G    302|CLM] train=4.4505  mask=19.8%  norm=2.107  lr=1.14e-04  dt=  36.7ms  words=2,482,176
[E01   304/1548 G    303|CLM] train=6.7927  mask=19.8%  norm=1.187  lr=1.14e-04  dt=  36.6ms  words=2,490,368
[E01   305/1548 G    304|CLM] train=4.7731  mask=19.8%  norm=1.653  lr=1.14e-04  dt=  36.8ms  words=2,498,560
[E01   306/1548 G    305|CLM] train=5.9520  mask=19.8%  norm=1.648  lr=1.15e-04  dt=  36.5ms  words=2,506,752
[E01   307/1548 G    306|CLM] train=5.3805  mask=19.8%  norm=1.690  lr=1.15e-04  dt=  36.8ms  words=2,514,944
[E01   308/1548 G    307|CLM] train=7.1483  mask=19.8%  norm=1.035  lr=1.15e-04  dt=  36.9ms  words=2,523,136
[E01   309/1548 G    308|CLM] train=4.6077  mask=19.8%  norm=1.717  lr=1.16e-04  dt=  36.6ms  words=2,531,328
[E01   310/1548 G    309|CLM] train=4.8779  mask=19.8%  norm=1.198  lr=1.16e-04  dt=  36.6ms  words=2,539,520
[E01   311/1548 G    310|CLM] train=5.0116  mask=19.7%  norm=1.251  lr=1.17e-04  dt=  36.7ms  words=2,547,712
[E01   312/1548 G    311|CLM] train=6.4697  mask=19.7%  norm=1.403  lr=1.17e-04  dt=  36.8ms  words=2,555,904
[E01   313/1548 G    312|CLM] train=4.4621  mask=19.7%  norm=1.268  lr=1.17e-04  dt=  36.7ms  words=2,564,096
[E01   314/1548 G    313|CLM] train=6.9746  mask=19.7%  norm=1.097  lr=1.18e-04  dt=  36.6ms  words=2,572,288
[E01   315/1548 G    314|CLM] train=4.3001  mask=19.7%  norm=1.848  lr=1.18e-04  dt=  36.6ms  words=2,580,480
[E01   316/1548 G    315|CLM] train=4.2166  mask=19.7%  norm=1.455  lr=1.18e-04  dt=  36.5ms  words=2,588,672
[E01   317/1548 G    316|CLM] train=4.4325  mask=19.7%  norm=1.352  lr=1.19e-04  dt=  36.5ms  words=2,596,864
[E01   318/1548 G    317|CLM] train=6.9342  mask=19.7%  norm=1.136  lr=1.19e-04  dt=  36.6ms  words=2,605,056
[E01   319/1548 G    318|CLM] train=4.3620  mask=19.7%  norm=1.660  lr=1.20e-04  dt=  36.6ms  words=2,613,248
[E01   320/1548 G    319|CLM] train=6.2674  mask=19.7%  norm=1.349  lr=1.20e-04  dt=  37.1ms  words=2,621,440
[E01   321/1548 G    320|CLM] train=4.8246  mask=19.7%  norm=1.859  lr=1.20e-04  dt=  36.6ms  words=2,629,632
[E01   322/1548 G    321|CLM] train=5.8326  mask=19.7%  norm=1.025  lr=1.21e-04  dt=  36.5ms  words=2,637,824
[E01   323/1548 G    322|CLM] train=4.5308  mask=19.7%  norm=1.288  lr=1.21e-04  dt=  36.5ms  words=2,646,016
[E01   324/1548 G    323|CLM] train=7.1855  mask=19.7%  norm=0.837  lr=1.21e-04  dt=  36.7ms  words=2,654,208
[E01   325/1548 G    324|CLM] train=5.3923  mask=19.7%  norm=1.525  lr=1.22e-04  dt=  36.7ms  words=2,662,400
[E01   326/1548 G    325|CLM] train=4.8044  mask=19.7%  norm=1.530  lr=1.22e-04  dt=  36.6ms  words=2,670,592
[E01   327/1548 G    326|CLM] train=6.8303  mask=19.7%  norm=1.067  lr=1.23e-04  dt=  36.5ms  words=2,678,784
[E01   328/1548 G    327|CLM] train=7.2212  mask=19.7%  norm=2.321  lr=1.23e-04  dt=  36.5ms  words=2,686,976
[E01   329/1548 G    328|CLM] train=4.2793  mask=19.7%  norm=1.562  lr=1.23e-04  dt=  36.5ms  words=2,695,168
[E01   330/1548 G    329|CLM] train=4.3522  mask=19.7%  norm=1.155  lr=1.24e-04  dt=  36.6ms  words=2,703,360
[E01   331/1548 G    330|CLM] train=4.6551  mask=19.7%  norm=2.035  lr=1.24e-04  dt=  36.7ms  words=2,711,552
[E01   332/1548 G    331|CLM] train=4.7182  mask=19.7%  norm=1.511  lr=1.24e-04  dt=  36.7ms  words=2,719,744
[E01   333/1548 G    332|CLM] train=6.4750  mask=19.7%  norm=1.002  lr=1.25e-04  dt=  36.5ms  words=2,727,936
[E01   334/1548 G    333|CLM] train=6.6213  mask=19.7%  norm=0.744  lr=1.25e-04  dt=  36.9ms  words=2,736,128
[E01   335/1548 G    334|CLM] train=6.6312  mask=19.7%  norm=0.598  lr=1.26e-04  dt=  37.0ms  words=2,744,320
[E01   336/1548 G    335|CLM] train=4.4754  mask=19.7%  norm=1.377  lr=1.26e-04  dt=  36.6ms  words=2,752,512
[E01   337/1548 G    336|CLM] train=4.1617  mask=19.7%  norm=1.523  lr=1.26e-04  dt=  36.6ms  words=2,760,704
[E01   338/1548 G    337|CLM] train=5.9046  mask=19.7%  norm=1.679  lr=1.27e-04  dt=  36.6ms  words=2,768,896
[E01   339/1548 G    338|CLM] train=4.5478  mask=19.7%  norm=1.150  lr=1.27e-04  dt=  36.7ms  words=2,777,088
[E01   340/1548 G    339|CLM] train=6.7640  mask=19.7%  norm=2.369  lr=1.27e-04  dt=  36.6ms  words=2,785,280
[E01   341/1548 G    340|CLM] train=5.9448  mask=19.7%  norm=1.267  lr=1.28e-04  dt=  36.8ms  words=2,793,472
[E01   342/1548 G    341|CLM] train=5.1500  mask=19.7%  norm=1.829  lr=1.28e-04  dt=  36.6ms  words=2,801,664
[E01   343/1548 G    342|CLM] train=4.1334  mask=19.7%  norm=1.290  lr=1.29e-04  dt=  36.5ms  words=2,809,856
[E01   344/1548 G    343|CLM] train=6.6345  mask=19.7%  norm=0.750  lr=1.29e-04  dt=  36.6ms  words=2,818,048
[E01   345/1548 G    344|CLM] train=4.8877  mask=19.7%  norm=1.423  lr=1.29e-04  dt=  36.6ms  words=2,826,240
[E01   346/1548 G    345|CLM] train=6.1980  mask=19.7%  norm=0.933  lr=1.30e-04  dt=  36.6ms  words=2,834,432
[E01   347/1548 G    346|CLM] train=7.3215  mask=19.7%  norm=2.502  lr=1.30e-04  dt=  36.8ms  words=2,842,624
[E01   348/1548 G    347|CLM] train=4.9923  mask=19.7%  norm=1.353  lr=1.31e-04  dt=  36.5ms  words=2,850,816
[E01   349/1548 G    348|CLM] train=5.8449  mask=19.7%  norm=0.947  lr=1.31e-04  dt=  36.6ms  words=2,859,008
[E01   350/1548 G    349|CLM] train=6.1752  mask=19.7%  norm=0.714  lr=1.31e-04  dt=  36.6ms  words=2,867,200
[E01   351/1548 G    350|CLM] train=5.0249  mask=19.7%  norm=1.959  lr=1.32e-04  dt=  36.9ms  words=2,875,392
[E01   352/1548 G    351|CLM] train=5.9224  mask=19.7%  norm=1.493  lr=1.32e-04  dt=  36.6ms  words=2,883,584
[E01   353/1548 G    352|CLM] train=4.4483  mask=19.7%  norm=1.336  lr=1.32e-04  dt=  36.8ms  words=2,891,776
[E01   354/1548 G    353|CLM] train=4.4818  mask=19.7%  norm=0.897  lr=1.33e-04  dt=  36.6ms  words=2,899,968
[E01   355/1548 G    354|CLM] train=6.2129  mask=19.7%  norm=1.413  lr=1.33e-04  dt=  36.6ms  words=2,908,160
[E01   356/1548 G    355|CLM] train=6.4594  mask=19.7%  norm=1.097  lr=1.33e-04  dt=  36.6ms  words=2,916,352
[E01   357/1548 G    356|CLM] train=4.1413  mask=19.7%  norm=1.385  lr=1.34e-04  dt=  36.5ms  words=2,924,544
[E01   358/1548 G    357|CLM] train=4.4313  mask=19.7%  norm=1.643  lr=1.34e-04  dt=  37.2ms  words=2,932,736
[E01   359/1548 G    358|CLM] train=4.0111  mask=19.7%  norm=0.997  lr=1.35e-04  dt=  36.6ms  words=2,940,928
[E01   360/1548 G    359|CLM] train=6.1682  mask=19.7%  norm=0.787  lr=1.35e-04  dt=  36.5ms  words=2,949,120
[E01   361/1548 G    360|CLM] train=4.8378  mask=19.7%  norm=1.073  lr=1.35e-04  dt=  37.7ms  words=2,957,312
[E01   362/1548 G    361|CLM] train=4.1085  mask=19.7%  norm=1.112  lr=1.36e-04  dt=  36.9ms  words=2,965,504
[E01   363/1548 G    362|CLM] train=3.9447  mask=19.7%  norm=0.962  lr=1.36e-04  dt=  36.6ms  words=2,973,696
[E01   364/1548 G    363|CLM] train=5.8593  mask=19.7%  norm=1.457  lr=1.36e-04  dt=  36.9ms  words=2,981,888
[E01   365/1548 G    364|CLM] train=3.7283  mask=19.7%  norm=1.191  lr=1.37e-04  dt=  36.5ms  words=2,990,080
[E01   366/1548 G    365|CLM] train=5.7127  mask=19.7%  norm=0.955  lr=1.37e-04  dt=  36.5ms  words=2,998,272
[E01   367/1548 G    366|CLM] train=6.2739  mask=19.7%  norm=0.957  lr=1.38e-04  dt=  36.7ms  words=3,006,464

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_3M'...
[Checkpoint] Checkpoint 'chck_3M' successfully saved.
[E01   368/1548 G    367|CLM] train=6.1675  mask=19.7%  norm=0.924  lr=1.38e-04  dt=  37.3ms  words=3,014,656
[E01   369/1548 G    368|CLM] train=4.1664  mask=19.7%  norm=1.311  lr=1.38e-04  dt=  37.3ms  words=3,022,848
[E01   370/1548 G    369|CLM] train=6.9440  mask=19.7%  norm=0.745  lr=1.39e-04  dt=  36.7ms  words=3,031,040
[E01   371/1548 G    370|CLM] train=4.1640  mask=19.7%  norm=1.040  lr=1.39e-04  dt=  36.6ms  words=3,039,232
[E01   372/1548 G    371|CLM] train=6.0081  mask=19.7%  norm=1.617  lr=1.39e-04  dt=  36.8ms  words=3,047,424
[E01   373/1548 G    372|CLM] train=6.4356  mask=19.7%  norm=1.450  lr=1.40e-04  dt=  36.7ms  words=3,055,616
[E01   374/1548 G    373|CLM] train=6.0591  mask=19.7%  norm=1.575  lr=1.40e-04  dt=  36.7ms  words=3,063,808
[E01   375/1548 G    374|CLM] train=6.5649  mask=19.7%  norm=0.712  lr=1.41e-04  dt=  36.6ms  words=3,072,000
[E01   376/1548 G    375|CLM] train=4.2991  mask=19.7%  norm=2.042  lr=1.41e-04  dt=  36.7ms  words=3,080,192
[E01   377/1548 G    376|CLM] train=6.3766  mask=19.7%  norm=1.644  lr=1.41e-04  dt=  36.7ms  words=3,088,384
[E01   378/1548 G    377|CLM] train=4.1777  mask=19.7%  norm=1.219  lr=1.42e-04  dt=  36.7ms  words=3,096,576
[E01   379/1548 G    378|CLM] train=5.8273  mask=19.7%  norm=1.315  lr=1.42e-04  dt=  36.8ms  words=3,104,768
[E01   380/1548 G    379|CLM] train=6.0121  mask=19.7%  norm=1.076  lr=1.42e-04  dt=  36.7ms  words=3,112,960
[E01   381/1548 G    380|CLM] train=6.5733  mask=19.7%  norm=0.980  lr=1.43e-04  dt=  36.7ms  words=3,121,152
[E01   382/1548 G    381|CLM] train=5.8240  mask=19.7%  norm=0.839  lr=1.43e-04  dt=  36.6ms  words=3,129,344
[E01   383/1548 G    382|CLM] train=4.0943  mask=19.7%  norm=1.822  lr=1.44e-04  dt=  36.6ms  words=3,137,536
[E01   384/1548 G    383|CLM] train=4.2415  mask=19.7%  norm=1.840  lr=1.44e-04  dt=  36.8ms  words=3,145,728
[E01   385/1548 G    384|CLM] train=6.3387  mask=19.7%  norm=1.171  lr=1.44e-04  dt=  36.8ms  words=3,153,920
[E01   386/1548 G    385|CLM] train=6.3906  mask=19.7%  norm=1.623  lr=1.45e-04  dt=  36.5ms  words=3,162,112
[E01   387/1548 G    386|CLM] train=5.6394  mask=19.7%  norm=2.002  lr=1.45e-04  dt=  36.5ms  words=3,170,304
[E01   388/1548 G    387|CLM] train=6.0700  mask=19.7%  norm=0.862  lr=1.45e-04  dt=  36.7ms  words=3,178,496
[E01   389/1548 G    388|CLM] train=6.0381  mask=19.7%  norm=0.942  lr=1.46e-04  dt=  36.6ms  words=3,186,688
[E01   390/1548 G    389|CLM] train=6.3333  mask=19.7%  norm=0.974  lr=1.46e-04  dt=  36.7ms  words=3,194,880
[E01   391/1548 G    390|CLM] train=5.3098  mask=19.7%  norm=1.366  lr=1.47e-04  dt=  36.5ms  words=3,203,072
[E01   392/1548 G    391|CLM] train=5.0865  mask=19.7%  norm=2.759  lr=1.47e-04  dt=  36.5ms  words=3,211,264
[E01   393/1548 G    392|CLM] train=7.0696  mask=19.7%  norm=0.848  lr=1.47e-04  dt=  36.5ms  words=3,219,456
[E01   394/1548 G    393|CLM] train=4.5863  mask=19.7%  norm=1.392  lr=1.48e-04  dt=  36.6ms  words=3,227,648
[E01   395/1548 G    394|CLM] train=6.1860  mask=19.7%  norm=2.143  lr=1.48e-04  dt=  36.6ms  words=3,235,840
[E01   396/1548 G    395|CLM] train=4.0519  mask=19.7%  norm=1.131  lr=1.48e-04  dt=  36.7ms  words=3,244,032
[E01   397/1548 G    396|CLM] train=6.4012  mask=19.7%  norm=0.854  lr=1.49e-04  dt=  36.6ms  words=3,252,224
[E01   398/1548 G    397|CLM] train=4.3656  mask=19.7%  norm=1.276  lr=1.49e-04  dt=  36.7ms  words=3,260,416
[E01   399/1548 G    398|CLM] train=3.8146  mask=19.7%  norm=0.967  lr=1.50e-04  dt=  36.8ms  words=3,268,608
[E01   400/1548 G    399|CLM] train=5.6637  mask=19.7%  norm=1.086  lr=1.50e-04  dt=  36.7ms  words=3,276,800
[E01   401/1548 G    400|CLM] train=4.8713  mask=19.7%  norm=1.754  lr=1.50e-04  dt=  36.7ms  words=3,284,992
[E01   402/1548 G    401|CLM] train=5.8390  mask=19.7%  norm=0.782  lr=1.51e-04  dt=  36.6ms  words=3,293,184
[E01   403/1548 G    402|CLM] train=6.5355  mask=19.7%  norm=1.373  lr=1.51e-04  dt=  36.5ms  words=3,301,376
[E01   404/1548 G    403|CLM] train=3.8675  mask=19.7%  norm=1.860  lr=1.51e-04  dt=  36.5ms  words=3,309,568
[E01   405/1548 G    404|CLM] train=6.4650  mask=19.7%  norm=1.108  lr=1.52e-04  dt=  36.6ms  words=3,317,760
[E01   406/1548 G    405|CLM] train=4.4892  mask=19.7%  norm=1.243  lr=1.52e-04  dt=  36.6ms  words=3,325,952
[E01   407/1548 G    406|CLM] train=3.7425  mask=19.7%  norm=0.997  lr=1.53e-04  dt=  36.7ms  words=3,334,144
[E01   408/1548 G    407|CLM] train=6.1346  mask=19.7%  norm=1.139  lr=1.53e-04  dt=  36.6ms  words=3,342,336
[E01   409/1548 G    408|CLM] train=7.3482  mask=19.7%  norm=1.245  lr=1.53e-04  dt=  36.5ms  words=3,350,528
[E01   410/1548 G    409|CLM] train=5.5525  mask=19.7%  norm=1.319  lr=1.54e-04  dt=  36.5ms  words=3,358,720
[E01   411/1548 G    410|CLM] train=5.6686  mask=19.7%  norm=0.789  lr=1.54e-04  dt=  36.6ms  words=3,366,912
[E01   412/1548 G    411|CLM] train=7.2275  mask=19.7%  norm=0.899  lr=1.54e-04  dt=  36.8ms  words=3,375,104
[E01   413/1548 G    412|CLM] train=6.4665  mask=19.7%  norm=1.074  lr=1.55e-04  dt=  36.7ms  words=3,383,296
[E01   414/1548 G    413|CLM] train=5.3132  mask=19.7%  norm=3.371  lr=1.55e-04  dt=  36.6ms  words=3,391,488
[E01   415/1548 G    414|CLM] train=6.4984  mask=19.7%  norm=1.010  lr=1.56e-04  dt=  36.5ms  words=3,399,680
[E01   416/1548 G    415|CLM] train=4.2402  mask=19.7%  norm=1.726  lr=1.56e-04  dt=  36.6ms  words=3,407,872
[E01   417/1548 G    416|CLM] train=4.0093  mask=19.7%  norm=1.776  lr=1.56e-04  dt=  36.6ms  words=3,416,064
[E01   418/1548 G    417|CLM] train=3.8841  mask=19.7%  norm=1.467  lr=1.57e-04  dt=  36.8ms  words=3,424,256
[E01   419/1548 G    418|CLM] train=4.0403  mask=19.7%  norm=1.390  lr=1.57e-04  dt=  36.6ms  words=3,432,448
[E01   420/1548 G    419|CLM] train=5.7201  mask=19.7%  norm=2.035  lr=1.58e-04  dt=  36.5ms  words=3,440,640
[E01   421/1548 G    420|CLM] train=5.5767  mask=19.7%  norm=1.672  lr=1.58e-04  dt=  36.5ms  words=3,448,832
[E01   422/1548 G    421|CLM] train=3.9195  mask=19.7%  norm=1.484  lr=1.58e-04  dt=  36.5ms  words=3,457,024
[E01   423/1548 G    422|CLM] train=6.6231  mask=19.7%  norm=1.796  lr=1.59e-04  dt=  36.7ms  words=3,465,216
[E01   424/1548 G    423|CLM] train=6.7795  mask=19.7%  norm=1.087  lr=1.59e-04  dt=  37.0ms  words=3,473,408
[E01   425/1548 G    424|CLM] train=5.5562  mask=19.7%  norm=1.844  lr=1.59e-04  dt=  36.7ms  words=3,481,600
[E01   426/1548 G    425|CLM] train=6.3006  mask=19.7%  norm=1.391  lr=1.60e-04  dt=  36.6ms  words=3,489,792
[E01   427/1548 G    426|CLM] train=4.6546  mask=19.7%  norm=2.565  lr=1.60e-04  dt=  36.7ms  words=3,497,984
[E01   428/1548 G    427|CLM] train=6.5038  mask=19.7%  norm=1.105  lr=1.60e-04  dt=  36.7ms  words=3,506,176
[E01   429/1548 G    428|CLM] train=6.5020  mask=19.7%  norm=0.936  lr=1.61e-04  dt=  36.8ms  words=3,514,368
[E01   430/1548 G    429|CLM] train=5.9576  mask=19.7%  norm=1.062  lr=1.61e-04  dt=  36.8ms  words=3,522,560
[E01   431/1548 G    430|CLM] train=6.4571  mask=19.7%  norm=0.911  lr=1.62e-04  dt=  36.7ms  words=3,530,752
[E01   432/1548 G    431|CLM] train=3.9705  mask=19.7%  norm=1.552  lr=1.62e-04  dt=  36.5ms  words=3,538,944
[E01   433/1548 G    432|CLM] train=4.1351  mask=19.7%  norm=1.375  lr=1.62e-04  dt=  36.9ms  words=3,547,136
[E01   434/1548 G    433|CLM] train=3.9554  mask=19.7%  norm=2.495  lr=1.63e-04  dt=  36.8ms  words=3,555,328
[E01   435/1548 G    434|CLM] train=6.4286  mask=19.6%  norm=1.894  lr=1.63e-04  dt=  36.7ms  words=3,563,520
[E01   436/1548 G    435|CLM] train=5.4482  mask=19.6%  norm=2.742  lr=1.63e-04  dt=  37.8ms  words=3,571,712
[E01   437/1548 G    436|CLM] train=4.2724  mask=19.6%  norm=1.825  lr=1.64e-04  dt=  36.7ms  words=3,579,904
[E01   438/1548 G    437|CLM] train=5.4837  mask=19.6%  norm=1.054  lr=1.64e-04  dt=  37.1ms  words=3,588,096
[E01   439/1548 G    438|CLM] train=6.4571  mask=19.6%  norm=1.269  lr=1.65e-04  dt=  36.7ms  words=3,596,288
[E01   440/1548 G    439|CLM] train=5.3560  mask=19.6%  norm=1.049  lr=1.65e-04  dt=  36.6ms  words=3,604,480
[E01   441/1548 G    440|CLM] train=4.0967  mask=19.6%  norm=1.100  lr=1.65e-04  dt=  36.6ms  words=3,612,672
[E01   442/1548 G    441|CLM] train=3.8865  mask=19.6%  norm=1.244  lr=1.66e-04  dt=  36.8ms  words=3,620,864
[E01   443/1548 G    442|CLM] train=3.6866  mask=19.6%  norm=1.067  lr=1.66e-04  dt=  36.9ms  words=3,629,056
[E01   444/1548 G    443|CLM] train=6.1407  mask=19.6%  norm=1.125  lr=1.66e-04  dt=  36.6ms  words=3,637,248
[E01   445/1548 G    444|CLM] train=6.5400  mask=19.6%  norm=1.000  lr=1.67e-04  dt=  36.7ms  words=3,645,440
[E01   446/1548 G    445|CLM] train=6.6742  mask=19.6%  norm=0.744  lr=1.67e-04  dt=  36.8ms  words=3,653,632
[E01   447/1548 G    446|CLM] train=4.1785  mask=19.6%  norm=1.917  lr=1.68e-04  dt=  36.7ms  words=3,661,824
[E01   448/1548 G    447|CLM] train=7.4396  mask=19.6%  norm=2.429  lr=1.68e-04  dt=  36.7ms  words=3,670,016
[E01   449/1548 G    448|CLM] train=5.5496  mask=19.6%  norm=1.730  lr=1.68e-04  dt=  36.6ms  words=3,678,208
[E01   450/1548 G    449|CLM] train=3.8724  mask=19.6%  norm=1.327  lr=1.69e-04  dt=  36.5ms  words=3,686,400
[E01   451/1548 G    450|CLM] train=7.4067  mask=19.6%  norm=1.166  lr=1.69e-04  dt=  36.6ms  words=3,694,592
[E01   452/1548 G    451|CLM] train=6.9478  mask=19.6%  norm=1.171  lr=1.70e-04  dt=  36.7ms  words=3,702,784
[E01   453/1548 G    452|CLM] train=6.1180  mask=19.6%  norm=1.261  lr=1.70e-04  dt=  36.6ms  words=3,710,976
[E01   454/1548 G    453|CLM] train=6.1582  mask=19.6%  norm=0.840  lr=1.70e-04  dt=  36.7ms  words=3,719,168
[E01   455/1548 G    454|CLM] train=6.3959  mask=19.6%  norm=0.789  lr=1.71e-04  dt=  36.7ms  words=3,727,360
[E01   456/1548 G    455|CLM] train=5.5430  mask=19.6%  norm=1.244  lr=1.71e-04  dt=  36.7ms  words=3,735,552
[E01   457/1548 G    456|CLM] train=5.4809  mask=19.6%  norm=1.144  lr=1.71e-04  dt=  36.6ms  words=3,743,744
[E01   458/1548 G    457|CLM] train=5.5762  mask=19.6%  norm=0.866  lr=1.72e-04  dt=  36.8ms  words=3,751,936
[E01   459/1548 G    458|CLM] train=5.8573  mask=19.6%  norm=1.151  lr=1.72e-04  dt=  36.7ms  words=3,760,128
[E01   460/1548 G    459|CLM] train=5.7403  mask=19.6%  norm=1.385  lr=1.72e-04  dt=  36.6ms  words=3,768,320
[E01   461/1548 G    460|CLM] train=6.1089  mask=19.6%  norm=0.844  lr=1.73e-04  dt=  36.5ms  words=3,776,512
[E01   462/1548 G    461|CLM] train=5.7786  mask=19.6%  norm=1.134  lr=1.73e-04  dt=  36.6ms  words=3,784,704
[E01   463/1548 G    462|CLM] train=5.7899  mask=19.6%  norm=0.941  lr=1.74e-04  dt=  36.7ms  words=3,792,896
[E01   464/1548 G    463|CLM] train=3.9493  mask=19.6%  norm=1.872  lr=1.74e-04  dt=  36.8ms  words=3,801,088
[E01   465/1548 G    464|CLM] train=6.5286  mask=19.6%  norm=0.913  lr=1.74e-04  dt=  36.9ms  words=3,809,280
[E01   466/1548 G    465|CLM] train=4.2383  mask=19.6%  norm=1.269  lr=1.75e-04  dt=  36.5ms  words=3,817,472
[E01   467/1548 G    466|CLM] train=4.3131  mask=19.6%  norm=2.600  lr=1.75e-04  dt=  36.7ms  words=3,825,664
[E01   468/1548 G    467|CLM] train=5.9060  mask=19.6%  norm=0.950  lr=1.75e-04  dt=  36.7ms  words=3,833,856
[E01   469/1548 G    468|CLM] train=3.8403  mask=19.6%  norm=1.043  lr=1.76e-04  dt=  36.6ms  words=3,842,048
[E01   470/1548 G    469|CLM] train=4.1882  mask=19.6%  norm=1.100  lr=1.76e-04  dt=  36.7ms  words=3,850,240
[E01   471/1548 G    470|CLM] train=3.6708  mask=19.6%  norm=0.951  lr=1.77e-04  dt=  36.6ms  words=3,858,432
[E01   472/1548 G    471|CLM] train=6.2838  mask=19.6%  norm=1.056  lr=1.77e-04  dt=  36.6ms  words=3,866,624
[E01   473/1548 G    472|CLM] train=6.0517  mask=19.6%  norm=1.026  lr=1.77e-04  dt=  36.7ms  words=3,874,816
[E01   474/1548 G    473|CLM] train=7.1356  mask=19.6%  norm=9.689  lr=1.78e-04  dt=  36.8ms  words=3,883,008
[E01   475/1548 G    474|CLM] train=3.7880  mask=19.6%  norm=1.643  lr=1.78e-04  dt=  36.7ms  words=3,891,200
[E01   476/1548 G    475|CLM] train=5.3459  mask=19.6%  norm=0.981  lr=1.78e-04  dt=  36.6ms  words=3,899,392
[E01   477/1548 G    476|CLM] train=3.8547  mask=19.6%  norm=1.220  lr=1.79e-04  dt=  36.6ms  words=3,907,584
[E01   478/1548 G    477|CLM] train=8.2619  mask=19.6%  norm=3.132  lr=1.79e-04  dt=  36.7ms  words=3,915,776
[E01   479/1548 G    478|CLM] train=3.7741  mask=19.6%  norm=1.011  lr=1.80e-04  dt=  36.5ms  words=3,923,968
[E01   480/1548 G    479|CLM] train=5.5441  mask=19.6%  norm=0.979  lr=1.80e-04  dt=  36.8ms  words=3,932,160
[E01   481/1548 G    480|CLM] train=3.9960  mask=19.6%  norm=0.875  lr=1.80e-04  dt=  36.6ms  words=3,940,352
[E01   482/1548 G    481|CLM] train=3.9380  mask=19.6%  norm=1.409  lr=1.81e-04  dt=  36.5ms  words=3,948,544
[E01   483/1548 G    482|CLM] train=6.0113  mask=19.6%  norm=0.924  lr=1.81e-04  dt=  36.5ms  words=3,956,736
[E01   484/1548 G    483|CLM] train=3.6911  mask=19.6%  norm=1.011  lr=1.81e-04  dt=  36.8ms  words=3,964,928
[E01   485/1548 G    484|CLM] train=6.5186  mask=19.6%  norm=1.091  lr=1.82e-04  dt=  36.8ms  words=3,973,120
[E01   486/1548 G    485|CLM] train=3.9121  mask=19.6%  norm=1.297  lr=1.82e-04  dt=  36.8ms  words=3,981,312
[E01   487/1548 G    486|CLM] train=5.6990  mask=19.6%  norm=1.223  lr=1.83e-04  dt=  36.6ms  words=3,989,504
[E01   488/1548 G    487|CLM] train=6.5846  mask=19.6%  norm=1.508  lr=1.83e-04  dt=  36.6ms  words=3,997,696
[E01   489/1548 G    488|CLM] train=3.9910  mask=19.6%  norm=1.062  lr=1.83e-04  dt=  36.8ms  words=4,005,888

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_4M'...
[Checkpoint] Checkpoint 'chck_4M' successfully saved.
[E01   490/1548 G    489|CLM] train=7.4420  mask=19.6%  norm=0.798  lr=1.84e-04  dt=  37.4ms  words=4,014,080
[E01   491/1548 G    490|CLM] train=4.1442  mask=19.6%  norm=1.394  lr=1.84e-04  dt=  36.8ms  words=4,022,272
[E01   492/1548 G    491|CLM] train=3.8797  mask=19.6%  norm=0.902  lr=1.84e-04  dt=  37.0ms  words=4,030,464
[E01   493/1548 G    492|CLM] train=3.7593  mask=19.6%  norm=0.789  lr=1.85e-04  dt=  37.0ms  words=4,038,656
[E01   494/1548 G    493|CLM] train=5.5771  mask=19.6%  norm=1.934  lr=1.85e-04  dt=  36.8ms  words=4,046,848
[E01   495/1548 G    494|CLM] train=3.5786  mask=19.6%  norm=0.946  lr=1.86e-04  dt=  36.7ms  words=4,055,040
[E01   496/1548 G    495|CLM] train=4.4508  mask=19.6%  norm=0.973  lr=1.86e-04  dt=  36.7ms  words=4,063,232
[E01   497/1548 G    496|CLM] train=3.8571  mask=19.6%  norm=0.901  lr=1.86e-04  dt=  36.7ms  words=4,071,424
[E01   498/1548 G    497|CLM] train=3.8548  mask=19.6%  norm=0.966  lr=1.87e-04  dt=  36.9ms  words=4,079,616
[E01   499/1548 G    498|CLM] train=5.9925  mask=19.6%  norm=1.341  lr=1.87e-04  dt=  36.9ms  words=4,087,808
[E01   500/1548 G    499|CLM] train=6.5557  mask=19.6%  norm=3.178  lr=1.88e-04  dt=  36.7ms  words=4,096,000
[E01   501/1548 G    500|CLM] train=3.8927  mask=19.6%  norm=1.358  lr=1.88e-04  dt=  36.8ms  words=4,104,192
[E01   502/1548 G    501|CLM] train=3.7998  mask=19.6%  norm=1.034  lr=1.88e-04  dt=  36.6ms  words=4,112,384
[E01   503/1548 G    502|CLM] train=5.8149  mask=19.6%  norm=1.441  lr=1.89e-04  dt=  36.8ms  words=4,120,576
[E01   504/1548 G    503|CLM] train=6.1405  mask=19.6%  norm=1.357  lr=1.89e-04  dt=  36.7ms  words=4,128,768
[E01   505/1548 G    504|CLM] train=5.1266  mask=19.6%  norm=1.727  lr=1.89e-04  dt=  36.7ms  words=4,136,960
[E01   506/1548 G    505|CLM] train=5.6833  mask=19.6%  norm=1.256  lr=1.90e-04  dt=  36.6ms  words=4,145,152
[E01   507/1548 G    506|CLM] train=6.2472  mask=19.6%  norm=1.086  lr=1.90e-04  dt=  36.7ms  words=4,153,344
[E01   508/1548 G    507|CLM] train=5.5645  mask=19.6%  norm=1.079  lr=1.90e-04  dt=  36.8ms  words=4,161,536
[E01   509/1548 G    508|CLM] train=3.8757  mask=19.6%  norm=1.659  lr=1.91e-04  dt=  36.7ms  words=4,169,728
[E01   510/1548 G    509|CLM] train=5.7734  mask=19.6%  norm=1.219  lr=1.91e-04  dt=  36.7ms  words=4,177,920
[E01   511/1548 G    510|CLM] train=5.4044  mask=19.6%  norm=1.036  lr=1.92e-04  dt=  36.7ms  words=4,186,112
[E01   512/1548 G    511|CLM] train=5.6279  mask=19.6%  norm=1.064  lr=1.92e-04  dt=  36.7ms  words=4,194,304
[E01   513/1548 G    512|CLM] train=5.5636  mask=19.6%  norm=0.877  lr=1.92e-04  dt=  36.8ms  words=4,202,496
[E01   514/1548 G    513|CLM] train=5.0272  mask=19.6%  norm=1.158  lr=1.93e-04  dt=  37.0ms  words=4,210,688
[E01   515/1548 G    514|CLM] train=5.5102  mask=19.6%  norm=0.736  lr=1.93e-04  dt=  36.6ms  words=4,218,880
[E01   516/1548 G    515|CLM] train=6.0061  mask=19.6%  norm=0.920  lr=1.93e-04  dt=  36.8ms  words=4,227,072
[E01   517/1548 G    516|CLM] train=3.5957  mask=19.6%  norm=1.741  lr=1.94e-04  dt=  36.9ms  words=4,235,264
[E01   518/1548 G    517|CLM] train=5.5725  mask=19.6%  norm=1.274  lr=1.94e-04  dt=  36.8ms  words=4,243,456
[E01   519/1548 G    518|CLM] train=6.5366  mask=19.6%  norm=0.731  lr=1.95e-04  dt=  36.6ms  words=4,251,648
[E01   520/1548 G    519|CLM] train=4.0196  mask=19.6%  norm=1.547  lr=1.95e-04  dt=  36.5ms  words=4,259,840
[E01   521/1548 G    520|CLM] train=3.9270  mask=19.6%  norm=1.253  lr=1.95e-04  dt=  36.8ms  words=4,268,032
[E01   522/1548 G    521|CLM] train=5.9985  mask=19.6%  norm=1.256  lr=1.96e-04  dt=  36.8ms  words=4,276,224
[E01   523/1548 G    522|CLM] train=3.5697  mask=19.6%  norm=0.890  lr=1.96e-04  dt=  36.8ms  words=4,284,416
[E01   524/1548 G    523|CLM] train=6.5268  mask=19.6%  norm=0.650  lr=1.96e-04  dt=  36.6ms  words=4,292,608
[E01   525/1548 G    524|CLM] train=3.7157  mask=19.6%  norm=0.992  lr=1.97e-04  dt=  36.7ms  words=4,300,800
[E01   526/1548 G    525|CLM] train=5.6675  mask=19.6%  norm=1.093  lr=1.97e-04  dt=  36.6ms  words=4,308,992
[E01   527/1548 G    526|CLM] train=5.7278  mask=19.6%  norm=1.251  lr=1.98e-04  dt=  36.8ms  words=4,317,184
[E01   528/1548 G    527|CLM] train=4.0269  mask=19.6%  norm=1.120  lr=1.98e-04  dt=  36.8ms  words=4,325,376
[E01   529/1548 G    528|CLM] train=5.2952  mask=19.6%  norm=0.887  lr=1.98e-04  dt=  36.6ms  words=4,333,568
[E01   530/1548 G    529|CLM] train=5.5365  mask=19.6%  norm=0.682  lr=1.99e-04  dt=  36.5ms  words=4,341,760
[E01   531/1548 G    530|CLM] train=4.1723  mask=19.6%  norm=1.153  lr=1.99e-04  dt=  36.7ms  words=4,349,952
[E01   532/1548 G    531|CLM] train=6.6055  mask=19.6%  norm=1.212  lr=1.99e-04  dt=  36.6ms  words=4,358,144
[E01   533/1548 G    532|CLM] train=3.7830  mask=19.6%  norm=1.447  lr=2.00e-04  dt=  36.9ms  words=4,366,336
[E01   534/1548 G    533|CLM] train=4.0282  mask=19.6%  norm=1.147  lr=2.00e-04  dt=  36.6ms  words=4,374,528
[E01   535/1548 G    534|CLM] train=5.2985  mask=19.6%  norm=1.235  lr=2.01e-04  dt=  36.7ms  words=4,382,720
[E01   536/1548 G    535|CLM] train=6.0101  mask=19.6%  norm=0.890  lr=2.01e-04  dt=  36.9ms  words=4,390,912
[E01   537/1548 G    536|CLM] train=5.6152  mask=19.6%  norm=1.244  lr=2.01e-04  dt=  36.9ms  words=4,399,104
[E01   538/1548 G    537|CLM] train=3.7345  mask=19.6%  norm=1.065  lr=2.02e-04  dt=  36.7ms  words=4,407,296
[E01   539/1548 G    538|CLM] train=5.6657  mask=19.6%  norm=0.968  lr=2.02e-04  dt=  36.6ms  words=4,415,488
[E01   540/1548 G    539|CLM] train=5.3687  mask=19.6%  norm=0.994  lr=2.02e-04  dt=  36.6ms  words=4,423,680
[E01   541/1548 G    540|CLM] train=3.7673  mask=19.6%  norm=1.028  lr=2.03e-04  dt=  36.8ms  words=4,431,872
[E01   542/1548 G    541|CLM] train=6.3670  mask=19.6%  norm=1.011  lr=2.03e-04  dt=  36.7ms  words=4,440,064
[E01   543/1548 G    542|CLM] train=3.9227  mask=19.6%  norm=0.967  lr=2.04e-04  dt=  36.7ms  words=4,448,256
[E01   544/1548 G    543|CLM] train=7.2812  mask=19.6%  norm=1.280  lr=2.04e-04  dt=  36.6ms  words=4,456,448
[E01   545/1548 G    544|CLM] train=7.1188  mask=19.6%  norm=0.999  lr=2.04e-04  dt=  36.5ms  words=4,464,640
[E01   546/1548 G    545|CLM] train=5.4744  mask=19.6%  norm=1.904  lr=2.05e-04  dt=  36.7ms  words=4,472,832
[E01   547/1548 G    546|CLM] train=3.4630  mask=19.6%  norm=1.149  lr=2.05e-04  dt=  36.7ms  words=4,481,024
[E01   548/1548 G    547|CLM] train=3.6588  mask=19.6%  norm=0.911  lr=2.05e-04  dt=  36.8ms  words=4,489,216
[E01   549/1548 G    548|CLM] train=6.4130  mask=19.6%  norm=3.059  lr=2.06e-04  dt=  36.8ms  words=4,497,408
[E01   550/1548 G    549|CLM] train=4.0524  mask=19.6%  norm=0.802  lr=2.06e-04  dt=  36.6ms  words=4,505,600
[E01   551/1548 G    550|CLM] train=6.5231  mask=19.6%  norm=2.118  lr=2.07e-04  dt=  36.7ms  words=4,513,792
[E01   552/1548 G    551|CLM] train=6.0541  mask=19.6%  norm=0.811  lr=2.07e-04  dt=  36.6ms  words=4,521,984
[E01   553/1548 G    552|CLM] train=6.0643  mask=19.6%  norm=1.037  lr=2.07e-04  dt=  36.8ms  words=4,530,176
[E01   554/1548 G    553|CLM] train=4.9473  mask=19.6%  norm=1.304  lr=2.08e-04  dt=  36.7ms  words=4,538,368
[E01   555/1548 G    554|CLM] train=5.5578  mask=19.6%  norm=0.998  lr=2.08e-04  dt=  36.6ms  words=4,546,560
[E01   556/1548 G    555|CLM] train=3.8382  mask=19.6%  norm=2.014  lr=2.08e-04  dt=  36.5ms  words=4,554,752
[E01   557/1548 G    556|CLM] train=3.9815  mask=19.6%  norm=1.096  lr=2.09e-04  dt=  36.8ms  words=4,562,944
[E01   558/1548 G    557|CLM] train=6.5624  mask=19.6%  norm=0.922  lr=2.09e-04  dt=  36.8ms  words=4,571,136
[E01   559/1548 G    558|CLM] train=3.7023  mask=19.5%  norm=0.980  lr=2.10e-04  dt=  36.9ms  words=4,579,328
[E01   560/1548 G    559|CLM] train=6.1188  mask=19.5%  norm=1.212  lr=2.10e-04  dt=  36.8ms  words=4,587,520
[E01   561/1548 G    560|CLM] train=3.5318  mask=19.5%  norm=1.163  lr=2.10e-04  dt=  36.9ms  words=4,595,712
[E01   562/1548 G    561|CLM] train=6.0305  mask=19.5%  norm=1.335  lr=2.11e-04  dt=  36.7ms  words=4,603,904
[E01   563/1548 G    562|CLM] train=5.6224  mask=19.5%  norm=2.327  lr=2.11e-04  dt=  36.7ms  words=4,612,096
[E01   564/1548 G    563|CLM] train=6.6067  mask=19.5%  norm=1.894  lr=2.11e-04  dt=  36.7ms  words=4,620,288
[E01   565/1548 G    564|CLM] train=5.9274  mask=19.5%  norm=1.065  lr=2.12e-04  dt=  36.7ms  words=4,628,480
[E01   566/1548 G    565|CLM] train=3.5986  mask=19.5%  norm=1.195  lr=2.12e-04  dt=  36.8ms  words=4,636,672
[E01   567/1548 G    566|CLM] train=6.0263  mask=19.5%  norm=0.908  lr=2.13e-04  dt=  37.0ms  words=4,644,864
[E01   568/1548 G    567|CLM] train=4.0002  mask=19.5%  norm=0.875  lr=2.13e-04  dt=  36.8ms  words=4,653,056
[E01   569/1548 G    568|CLM] train=6.2506  mask=19.5%  norm=0.822  lr=2.13e-04  dt=  36.7ms  words=4,661,248
[E01   570/1548 G    569|CLM] train=5.6225  mask=19.5%  norm=1.588  lr=2.14e-04  dt=  36.5ms  words=4,669,440
[E01   571/1548 G    570|CLM] train=3.5477  mask=19.5%  norm=1.117  lr=2.14e-04  dt=  36.8ms  words=4,677,632
[E01   572/1548 G    571|CLM] train=6.2374  mask=19.5%  norm=0.903  lr=2.14e-04  dt=  36.8ms  words=4,685,824
[E01   573/1548 G    572|CLM] train=5.9597  mask=19.5%  norm=0.858  lr=2.15e-04  dt=  36.8ms  words=4,694,016
[E01   574/1548 G    573|CLM] train=3.4624  mask=19.5%  norm=0.801  lr=2.15e-04  dt=  36.6ms  words=4,702,208
[E01   575/1548 G    574|CLM] train=3.5171  mask=19.5%  norm=0.805  lr=2.16e-04  dt=  36.6ms  words=4,710,400
[E01   576/1548 G    575|CLM] train=6.3487  mask=19.5%  norm=0.846  lr=2.16e-04  dt=  36.7ms  words=4,718,592
[E01   577/1548 G    576|CLM] train=5.8727  mask=19.5%  norm=0.872  lr=2.16e-04  dt=  36.7ms  words=4,726,784
[E01   578/1548 G    577|CLM] train=4.8945  mask=19.5%  norm=0.982  lr=2.17e-04  dt=  36.7ms  words=4,734,976
[E01   579/1548 G    578|CLM] train=3.5660  mask=19.5%  norm=0.947  lr=2.17e-04  dt=  36.6ms  words=4,743,168
[E01   580/1548 G    579|CLM] train=5.4762  mask=19.5%  norm=1.079  lr=2.17e-04  dt=  36.5ms  words=4,751,360
[E01   581/1548 G    580|CLM] train=3.5436  mask=19.5%  norm=0.839  lr=2.18e-04  dt=  36.6ms  words=4,759,552
[E01   582/1548 G    581|CLM] train=4.1222  mask=19.5%  norm=1.119  lr=2.18e-04  dt=  36.7ms  words=4,767,744
[E01   583/1548 G    582|CLM] train=4.2698  mask=19.5%  norm=1.064  lr=2.19e-04  dt=  36.8ms  words=4,775,936
[E01   584/1548 G    583|CLM] train=6.1960  mask=19.5%  norm=1.003  lr=2.19e-04  dt=  36.6ms  words=4,784,128
[E01   585/1548 G    584|CLM] train=5.9509  mask=19.5%  norm=0.809  lr=2.19e-04  dt=  36.7ms  words=4,792,320
[E01   586/1548 G    585|CLM] train=5.9914  mask=19.5%  norm=0.936  lr=2.20e-04  dt=  36.5ms  words=4,800,512
[E01   587/1548 G    586|CLM] train=3.5156  mask=19.5%  norm=1.682  lr=2.20e-04  dt=  36.8ms  words=4,808,704
[E01   588/1548 G    587|CLM] train=3.7281  mask=19.5%  norm=1.286  lr=2.20e-04  dt=  36.6ms  words=4,816,896
[E01   589/1548 G    588|CLM] train=3.3796  mask=19.5%  norm=0.873  lr=2.21e-04  dt=  36.7ms  words=4,825,088
[E01   590/1548 G    589|CLM] train=3.6981  mask=19.5%  norm=0.771  lr=2.21e-04  dt=  36.6ms  words=4,833,280
[E01   591/1548 G    590|CLM] train=6.0399  mask=19.5%  norm=1.294  lr=2.22e-04  dt=  36.7ms  words=4,841,472
[E01   592/1548 G    591|CLM] train=3.9171  mask=19.5%  norm=1.250  lr=2.22e-04  dt=  36.6ms  words=4,849,664
[E01   593/1548 G    592|CLM] train=5.8362  mask=19.5%  norm=0.860  lr=2.22e-04  dt=  36.6ms  words=4,857,856
[E01   594/1548 G    593|CLM] train=5.3300  mask=19.5%  norm=1.066  lr=2.23e-04  dt=  36.7ms  words=4,866,048
[E01   595/1548 G    594|CLM] train=3.4150  mask=19.5%  norm=1.300  lr=2.23e-04  dt=  36.7ms  words=4,874,240
[E01   596/1548 G    595|CLM] train=3.7853  mask=19.5%  norm=1.212  lr=2.23e-04  dt=  36.6ms  words=4,882,432
[E01   597/1548 G    596|CLM] train=5.8296  mask=19.5%  norm=1.177  lr=2.24e-04  dt=  36.6ms  words=4,890,624
[E01   598/1548 G    597|CLM] train=5.9955  mask=19.5%  norm=0.868  lr=2.24e-04  dt=  36.6ms  words=4,898,816
[E01   599/1548 G    598|CLM] train=6.5842  mask=19.5%  norm=1.100  lr=2.25e-04  dt=  36.8ms  words=4,907,008
[E01   600/1548 G    599|CLM] train=5.8818  mask=19.5%  norm=0.665  lr=2.25e-04  dt=  36.7ms  words=4,915,200
[E01   601/1548 G    600|CLM] train=6.2622  mask=19.5%  norm=0.698  lr=2.25e-04  dt=  36.6ms  words=4,923,392
[E01   602/1548 G    601|CLM] train=6.2292  mask=19.5%  norm=0.706  lr=2.26e-04  dt=  36.7ms  words=4,931,584
[E01   603/1548 G    602|CLM] train=5.7085  mask=19.5%  norm=1.098  lr=2.26e-04  dt=  36.8ms  words=4,939,776
[E01   604/1548 G    603|CLM] train=5.4036  mask=19.5%  norm=1.011  lr=2.26e-04  dt=  36.6ms  words=4,947,968
[E01   605/1548 G    604|CLM] train=5.3301  mask=19.5%  norm=0.717  lr=2.27e-04  dt=  36.8ms  words=4,956,160
[E01   606/1548 G    605|CLM] train=5.6978  mask=19.5%  norm=0.804  lr=2.27e-04  dt=  36.6ms  words=4,964,352
[E01   607/1548 G    606|CLM] train=5.9338  mask=19.5%  norm=0.728  lr=2.28e-04  dt=  36.7ms  words=4,972,544
[E01   608/1548 G    607|CLM] train=5.1365  mask=19.5%  norm=0.943  lr=2.28e-04  dt=  36.6ms  words=4,980,736
[E01   609/1548 G    608|CLM] train=4.1607  mask=19.5%  norm=6.416  lr=2.28e-04  dt=  36.7ms  words=4,988,928
[E01   610/1548 G    609|CLM] train=6.0572  mask=19.5%  norm=0.855  lr=2.29e-04  dt=  36.8ms  words=4,997,120
[E01   611/1548 G    610|CLM] train=7.6653  mask=19.5%  norm=2.102  lr=2.29e-04  dt=  36.7ms  words=5,005,312

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_5M'...
[Checkpoint] Checkpoint 'chck_5M' successfully saved.
[E01   612/1548 G    611|CLM] train=6.1001  mask=19.5%  norm=2.080  lr=2.29e-04  dt=  36.9ms  words=5,013,504
[E01   613/1548 G    612|CLM] train=5.6533  mask=19.5%  norm=0.764  lr=2.30e-04  dt=  36.5ms  words=5,021,696
[E01   614/1548 G    613|CLM] train=5.8134  mask=19.5%  norm=0.673  lr=2.30e-04  dt=  36.8ms  words=5,029,888
[E01   615/1548 G    614|CLM] train=3.8291  mask=19.5%  norm=3.357  lr=2.31e-04  dt=  36.8ms  words=5,038,080
[E01   616/1548 G    615|CLM] train=3.9121  mask=19.5%  norm=1.042  lr=2.31e-04  dt=  37.2ms  words=5,046,272
[E01   617/1548 G    616|CLM] train=5.5894  mask=19.5%  norm=0.907  lr=2.31e-04  dt=  36.8ms  words=5,054,464
[E01   618/1548 G    617|CLM] train=7.1443  mask=19.5%  norm=1.414  lr=2.32e-04  dt=  36.7ms  words=5,062,656
[E01   619/1548 G    618|CLM] train=5.4445  mask=19.5%  norm=1.084  lr=2.32e-04  dt=  36.5ms  words=5,070,848
[E01   620/1548 G    619|CLM] train=3.6338  mask=19.5%  norm=1.054  lr=2.32e-04  dt=  36.9ms  words=5,079,040
[E01   621/1548 G    620|CLM] train=5.3337  mask=19.5%  norm=1.083  lr=2.33e-04  dt=  36.6ms  words=5,087,232
[E01   622/1548 G    621|CLM] train=5.2511  mask=19.5%  norm=2.554  lr=2.33e-04  dt=  36.5ms  words=5,095,424
[E01   623/1548 G    622|CLM] train=3.5871  mask=19.5%  norm=1.371  lr=2.34e-04  dt=  36.5ms  words=5,103,616
[E01   624/1548 G    623|CLM] train=6.0105  mask=19.5%  norm=0.867  lr=2.34e-04  dt=  36.5ms  words=5,111,808
[E01   625/1548 G    624|CLM] train=4.2222  mask=19.5%  norm=1.086  lr=2.34e-04  dt=  36.8ms  words=5,120,000
[E01   626/1548 G    625|CLM] train=5.3372  mask=19.5%  norm=0.841  lr=2.35e-04  dt=  36.6ms  words=5,128,192
[E01   627/1548 G    626|CLM] train=6.2380  mask=19.5%  norm=0.689  lr=2.35e-04  dt=  36.5ms  words=5,136,384
[E01   628/1548 G    627|CLM] train=3.7460  mask=19.5%  norm=1.040  lr=2.35e-04  dt=  36.6ms  words=5,144,576
[E01   629/1548 G    628|CLM] train=6.2803  mask=19.5%  norm=0.888  lr=2.36e-04  dt=  36.5ms  words=5,152,768
[E01   630/1548 G    629|CLM] train=3.7239  mask=19.5%  norm=0.748  lr=2.36e-04  dt=  36.8ms  words=5,160,960
[E01   631/1548 G    630|CLM] train=3.6189  mask=19.5%  norm=0.905  lr=2.37e-04  dt=  36.7ms  words=5,169,152
[E01   632/1548 G    631|CLM] train=5.7755  mask=19.5%  norm=0.922  lr=2.37e-04  dt=  36.7ms  words=5,177,344
[E01   633/1548 G    632|CLM] train=6.1272  mask=19.5%  norm=0.981  lr=2.37e-04  dt=  36.6ms  words=5,185,536
[E01   634/1548 G    633|CLM] train=3.4549  mask=19.5%  norm=1.095  lr=2.38e-04  dt=  36.5ms  words=5,193,728
[E01   635/1548 G    634|CLM] train=6.1409  mask=19.5%  norm=1.002  lr=2.38e-04  dt=  36.7ms  words=5,201,920
[E01   636/1548 G    635|CLM] train=5.4638  mask=19.5%  norm=1.175  lr=2.38e-04  dt=  36.6ms  words=5,210,112
[E01   637/1548 G    636|CLM] train=3.4247  mask=19.5%  norm=0.802  lr=2.39e-04  dt=  36.7ms  words=5,218,304
[E01   638/1548 G    637|CLM] train=5.5878  mask=19.5%  norm=0.783  lr=2.39e-04  dt=  36.6ms  words=5,226,496
[E01   639/1548 G    638|CLM] train=3.8809  mask=19.5%  norm=1.032  lr=2.40e-04  dt=  36.4ms  words=5,234,688
[E01   640/1548 G    639|CLM] train=5.9949  mask=19.5%  norm=0.797  lr=2.40e-04  dt=  36.6ms  words=5,242,880
[E01   641/1548 G    640|CLM] train=5.5338  mask=19.5%  norm=0.878  lr=2.40e-04  dt=  36.6ms  words=5,251,072
[E01   642/1548 G    641|CLM] train=6.1255  mask=19.5%  norm=0.865  lr=2.41e-04  dt=  36.6ms  words=5,259,264
[E01   643/1548 G    642|CLM] train=5.7936  mask=19.5%  norm=0.961  lr=2.41e-04  dt=  37.0ms  words=5,267,456
[E01   644/1548 G    643|CLM] train=5.9673  mask=19.5%  norm=0.663  lr=2.41e-04  dt=  36.7ms  words=5,275,648
[E01   645/1548 G    644|CLM] train=7.0956  mask=19.5%  norm=1.016  lr=2.42e-04  dt=  36.6ms  words=5,283,840
[E01   646/1548 G    645|CLM] train=5.4534  mask=19.5%  norm=0.818  lr=2.42e-04  dt=  36.7ms  words=5,292,032
[E01   647/1548 G    646|CLM] train=3.4305  mask=19.5%  norm=1.500  lr=2.43e-04  dt=  36.6ms  words=5,300,224
[E01   648/1548 G    647|CLM] train=6.1326  mask=19.5%  norm=1.014  lr=2.43e-04  dt=  36.6ms  words=5,308,416
[E01   649/1548 G    648|CLM] train=6.1322  mask=19.5%  norm=0.782  lr=2.43e-04  dt=  36.8ms  words=5,316,608
[E01   650/1548 G    649|CLM] train=5.2510  mask=19.5%  norm=1.133  lr=2.44e-04  dt=  37.9ms  words=5,324,800
[E01   651/1548 G    650|CLM] train=5.6456  mask=19.5%  norm=0.868  lr=2.44e-04  dt=  36.8ms  words=5,332,992
[E01   652/1548 G    651|CLM] train=3.4635  mask=19.5%  norm=0.600  lr=2.44e-04  dt=  36.7ms  words=5,341,184
[E01   653/1548 G    652|CLM] train=5.5554  mask=19.5%  norm=1.207  lr=2.45e-04  dt=  36.6ms  words=5,349,376
[E01   654/1548 G    653|CLM] train=5.0376  mask=19.5%  norm=1.628  lr=2.45e-04  dt=  36.6ms  words=5,357,568
[E01   655/1548 G    654|CLM] train=3.2416  mask=19.5%  norm=0.919  lr=2.46e-04  dt=  36.8ms  words=5,365,760
[E01   656/1548 G    655|CLM] train=3.6946  mask=19.5%  norm=0.762  lr=2.46e-04  dt=  36.6ms  words=5,373,952
[E01   657/1548 G    656|CLM] train=3.7060  mask=19.5%  norm=0.953  lr=2.46e-04  dt=  37.0ms  words=5,382,144
[E01   658/1548 G    657|CLM] train=5.1885  mask=19.5%  norm=0.857  lr=2.47e-04  dt=  36.5ms  words=5,390,336
[E01   659/1548 G    658|CLM] train=3.4911  mask=19.5%  norm=1.074  lr=2.47e-04  dt=  36.6ms  words=5,398,528
[E01   660/1548 G    659|CLM] train=4.8990  mask=19.5%  norm=1.757  lr=2.47e-04  dt=  36.6ms  words=5,406,720
[E01   661/1548 G    660|CLM] train=3.4499  mask=19.5%  norm=0.942  lr=2.48e-04  dt=  36.7ms  words=5,414,912
[E01   662/1548 G    661|CLM] train=3.5762  mask=19.5%  norm=1.012  lr=2.48e-04  dt=  36.8ms  words=5,423,104
[E01   663/1548 G    662|CLM] train=4.2517  mask=19.5%  norm=1.453  lr=2.49e-04  dt=  36.7ms  words=5,431,296
[E01   664/1548 G    663|CLM] train=6.2009  mask=19.5%  norm=1.971  lr=2.49e-04  dt=  36.5ms  words=5,439,488
[E01   665/1548 G    664|CLM] train=3.8934  mask=19.5%  norm=1.419  lr=2.49e-04  dt=  36.4ms  words=5,447,680
[E01   666/1548 G    665|CLM] train=3.2868  mask=19.5%  norm=1.333  lr=2.50e-04  dt=  36.6ms  words=5,455,872
[E01   667/1548 G    666|CLM] train=3.3332  mask=19.5%  norm=0.814  lr=2.50e-04  dt=  36.5ms  words=5,464,064
[E01   668/1548 G    667|CLM] train=3.3076  mask=19.5%  norm=0.737  lr=2.51e-04  dt=  36.7ms  words=5,472,256
[E01   669/1548 G    668|CLM] train=3.4422  mask=19.5%  norm=0.875  lr=2.51e-04  dt=  36.5ms  words=5,480,448
[E01   670/1548 G    669|CLM] train=5.0670  mask=19.5%  norm=1.645  lr=2.51e-04  dt=  36.6ms  words=5,488,640
[E01   671/1548 G    670|CLM] train=3.3465  mask=19.5%  norm=1.029  lr=2.52e-04  dt=  36.6ms  words=5,496,832
[E01   672/1548 G    671|CLM] train=5.5145  mask=19.5%  norm=0.750  lr=2.52e-04  dt=  36.6ms  words=5,505,024
[E01   673/1548 G    672|CLM] train=3.3235  mask=19.5%  norm=0.878  lr=2.52e-04  dt=  36.6ms  words=5,513,216
[E01   674/1548 G    673|CLM] train=5.8538  mask=19.5%  norm=0.832  lr=2.53e-04  dt=  36.8ms  words=5,521,408
[E01   675/1548 G    674|CLM] train=3.6286  mask=19.5%  norm=1.068  lr=2.53e-04  dt=  36.7ms  words=5,529,600
[E01   676/1548 G    675|CLM] train=3.8864  mask=19.5%  norm=0.907  lr=2.53e-04  dt=  36.5ms  words=5,537,792
[E01   677/1548 G    676|CLM] train=6.2075  mask=19.5%  norm=0.974  lr=2.54e-04  dt=  36.4ms  words=5,545,984
[E01   678/1548 G    677|CLM] train=5.2317  mask=19.5%  norm=1.293  lr=2.54e-04  dt=  36.8ms  words=5,554,176
[E01   679/1548 G    678|CLM] train=3.5701  mask=19.5%  norm=1.278  lr=2.55e-04  dt=  36.6ms  words=5,562,368
[E01   680/1548 G    679|CLM] train=5.8140  mask=19.5%  norm=1.030  lr=2.55e-04  dt=  36.7ms  words=5,570,560
[E01   681/1548 G    680|CLM] train=3.4532  mask=19.5%  norm=1.025  lr=2.55e-04  dt=  36.5ms  words=5,578,752
[E01   682/1548 G    681|CLM] train=3.5588  mask=19.5%  norm=1.047  lr=2.56e-04  dt=  36.7ms  words=5,586,944
[E01   683/1548 G    682|CLM] train=3.3204  mask=19.4%  norm=0.763  lr=2.56e-04  dt=  36.7ms  words=5,595,136
[E01   684/1548 G    683|CLM] train=5.4792  mask=19.4%  norm=1.326  lr=2.57e-04  dt=  36.8ms  words=5,603,328
[E01   685/1548 G    684|CLM] train=2.8289  mask=19.4%  norm=1.207  lr=2.57e-04  dt=  36.7ms  words=5,611,520
[E01   686/1548 G    685|CLM] train=5.7694  mask=19.4%  norm=1.190  lr=2.57e-04  dt=  37.0ms  words=5,619,712
[E01   687/1548 G    686|CLM] train=6.3520  mask=19.4%  norm=1.342  lr=2.58e-04  dt=  36.7ms  words=5,627,904
[E01   688/1548 G    687|CLM] train=3.4529  mask=19.4%  norm=0.932  lr=2.58e-04  dt=  36.8ms  words=5,636,096
[E01   689/1548 G    688|CLM] train=3.2952  mask=19.4%  norm=0.939  lr=2.58e-04  dt=  36.6ms  words=5,644,288
[E01   690/1548 G    689|CLM] train=5.4150  mask=19.4%  norm=1.059  lr=2.59e-04  dt=  36.8ms  words=5,652,480
[E01   691/1548 G    690|CLM] train=3.9342  mask=19.4%  norm=1.097  lr=2.59e-04  dt=  36.6ms  words=5,660,672
[E01   692/1548 G    691|CLM] train=6.0313  mask=19.4%  norm=1.352  lr=2.59e-04  dt=  36.7ms  words=5,668,864
[E01   693/1548 G    692|CLM] train=6.0256  mask=19.4%  norm=1.120  lr=2.60e-04  dt=  36.6ms  words=5,677,056
[E01   694/1548 G    693|CLM] train=6.3423  mask=19.4%  norm=0.785  lr=2.60e-04  dt=  36.7ms  words=5,685,248
[E01   695/1548 G    694|CLM] train=3.9024  mask=19.4%  norm=0.943  lr=2.61e-04  dt=  36.8ms  words=5,693,440
[E01   696/1548 G    695|CLM] train=6.0873  mask=19.4%  norm=1.017  lr=2.61e-04  dt=  36.7ms  words=5,701,632
[E01   697/1548 G    696|CLM] train=3.4492  mask=19.4%  norm=1.036  lr=2.61e-04  dt=  37.0ms  words=5,709,824
[E01   698/1548 G    697|CLM] train=6.0359  mask=19.4%  norm=0.884  lr=2.62e-04  dt=  36.6ms  words=5,718,016
[E01   699/1548 G    698|CLM] train=3.3690  mask=19.4%  norm=1.056  lr=2.62e-04  dt=  37.3ms  words=5,726,208
[E01   700/1548 G    699|CLM] train=5.1378  mask=19.4%  norm=1.328  lr=2.62e-04  dt=  36.7ms  words=5,734,400
[E01   701/1548 G    700|CLM] train=5.4794  mask=19.4%  norm=0.827  lr=2.63e-04  dt=  36.6ms  words=5,742,592
[E01   702/1548 G    701|CLM] train=4.9086  mask=19.4%  norm=0.850  lr=2.63e-04  dt=  36.6ms  words=5,750,784
[E01   703/1548 G    702|CLM] train=6.2478  mask=19.4%  norm=0.809  lr=2.64e-04  dt=  36.7ms  words=5,758,976
[E01   704/1548 G    703|CLM] train=3.3175  mask=19.4%  norm=1.264  lr=2.64e-04  dt=  36.8ms  words=5,767,168
[E01   705/1548 G    704|CLM] train=6.8663  mask=19.4%  norm=1.063  lr=2.64e-04  dt=  36.7ms  words=5,775,360
[E01   706/1548 G    705|CLM] train=5.8445  mask=19.4%  norm=1.212  lr=2.65e-04  dt=  36.6ms  words=5,783,552
[E01   707/1548 G    706|CLM] train=3.3055  mask=19.4%  norm=1.085  lr=2.65e-04  dt=  36.6ms  words=5,791,744
[E01   708/1548 G    707|CLM] train=3.6138  mask=19.4%  norm=1.045  lr=2.65e-04  dt=  36.5ms  words=5,799,936
[E01   709/1548 G    708|CLM] train=6.4108  mask=19.4%  norm=0.783  lr=2.66e-04  dt=  36.6ms  words=5,808,128
[E01   710/1548 G    709|CLM] train=4.7672  mask=19.4%  norm=1.478  lr=2.66e-04  dt=  36.9ms  words=5,816,320
[E01   711/1548 G    710|CLM] train=5.6529  mask=19.4%  norm=0.756  lr=2.67e-04  dt=  37.2ms  words=5,824,512
[E01   712/1548 G    711|CLM] train=3.4383  mask=19.4%  norm=1.602  lr=2.67e-04  dt=  36.5ms  words=5,832,704
[E01   713/1548 G    712|CLM] train=4.8752  mask=19.4%  norm=1.279  lr=2.67e-04  dt=  36.5ms  words=5,840,896
[E01   714/1548 G    713|CLM] train=5.7982  mask=19.4%  norm=0.806  lr=2.68e-04  dt=  36.6ms  words=5,849,088
[E01   715/1548 G    714|CLM] train=3.5845  mask=19.4%  norm=1.245  lr=2.68e-04  dt=  36.6ms  words=5,857,280
[E01   716/1548 G    715|CLM] train=5.5141  mask=19.4%  norm=0.829  lr=2.68e-04  dt=  36.7ms  words=5,865,472
[E01   717/1548 G    716|CLM] train=6.2482  mask=19.4%  norm=0.799  lr=2.69e-04  dt=  36.5ms  words=5,873,664
[E01   718/1548 G    717|CLM] train=4.9421  mask=19.4%  norm=1.147  lr=2.69e-04  dt=  36.7ms  words=5,881,856
[E01   719/1548 G    718|CLM] train=3.6675  mask=19.4%  norm=1.088  lr=2.70e-04  dt=  36.7ms  words=5,890,048
[E01   720/1548 G    719|CLM] train=3.3470  mask=19.4%  norm=0.863  lr=2.70e-04  dt=  36.6ms  words=5,898,240
[E01   721/1548 G    720|CLM] train=5.2792  mask=19.4%  norm=0.787  lr=2.70e-04  dt=  36.7ms  words=5,906,432
[E01   722/1548 G    721|CLM] train=6.9974  mask=19.4%  norm=0.914  lr=2.71e-04  dt=  36.5ms  words=5,914,624
[E01   723/1548 G    722|CLM] train=6.7871  mask=19.4%  norm=2.325  lr=2.71e-04  dt=  36.5ms  words=5,922,816
[E01   724/1548 G    723|CLM] train=5.3407  mask=19.4%  norm=0.829  lr=2.71e-04  dt=  36.5ms  words=5,931,008
[E01   725/1548 G    724|CLM] train=5.8681  mask=19.4%  norm=1.151  lr=2.72e-04  dt=  36.4ms  words=5,939,200
[E01   726/1548 G    725|CLM] train=3.8161  mask=19.4%  norm=2.035  lr=2.72e-04  dt=  36.8ms  words=5,947,392
[E01   727/1548 G    726|CLM] train=5.7499  mask=19.4%  norm=1.063  lr=2.73e-04  dt=  36.6ms  words=5,955,584
[E01   728/1548 G    727|CLM] train=6.6150  mask=19.4%  norm=1.122  lr=2.73e-04  dt=  36.6ms  words=5,963,776
[E01   729/1548 G    728|CLM] train=3.5297  mask=19.4%  norm=1.568  lr=2.73e-04  dt=  36.5ms  words=5,971,968
[E01   730/1548 G    729|CLM] train=3.5072  mask=19.4%  norm=1.065  lr=2.74e-04  dt=  36.5ms  words=5,980,160
[E01   731/1548 G    730|CLM] train=5.5126  mask=19.4%  norm=1.125  lr=2.74e-04  dt=  36.8ms  words=5,988,352
[E01   732/1548 G    731|CLM] train=5.6642  mask=19.4%  norm=0.900  lr=2.75e-04  dt=  36.6ms  words=5,996,544
[E01   733/1548 G    732|CLM] train=5.5597  mask=19.4%  norm=0.703  lr=2.75e-04  dt=  36.6ms  words=6,004,736

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_6M'...
[Checkpoint] Checkpoint 'chck_6M' successfully saved.
[E01   734/1548 G    733|CLM] train=4.9666  mask=19.4%  norm=0.777  lr=2.75e-04  dt=  37.3ms  words=6,012,928
[E01   735/1548 G    734|CLM] train=3.7703  mask=19.4%  norm=1.107  lr=2.76e-04  dt=  36.7ms  words=6,021,120
[E01   736/1548 G    735|CLM] train=5.9734  mask=19.4%  norm=1.004  lr=2.76e-04  dt=  36.8ms  words=6,029,312
[E01   737/1548 G    736|CLM] train=6.2011  mask=19.4%  norm=1.432  lr=2.76e-04  dt=  36.9ms  words=6,037,504
[E01   738/1548 G    737|CLM] train=6.0106  mask=19.4%  norm=0.834  lr=2.77e-04  dt=  36.7ms  words=6,045,696
[E01   739/1548 G    738|CLM] train=5.6252  mask=19.4%  norm=0.723  lr=2.77e-04  dt=  36.6ms  words=6,053,888
[E01   740/1548 G    739|CLM] train=3.3134  mask=19.4%  norm=1.026  lr=2.77e-04  dt=  36.7ms  words=6,062,080
[E01   741/1548 G    740|CLM] train=4.1119  mask=19.4%  norm=1.531  lr=2.78e-04  dt=  36.7ms  words=6,070,272
[E01   742/1548 G    741|CLM] train=5.8806  mask=19.4%  norm=1.059  lr=2.78e-04  dt=  36.6ms  words=6,078,464
[E01   743/1548 G    742|CLM] train=5.9640  mask=19.4%  norm=0.792  lr=2.79e-04  dt=  36.6ms  words=6,086,656
[E01   744/1548 G    743|CLM] train=5.7470  mask=19.4%  norm=1.040  lr=2.79e-04  dt=  36.7ms  words=6,094,848
[E01   745/1548 G    744|CLM] train=5.2895  mask=19.4%  norm=0.949  lr=2.79e-04  dt=  36.6ms  words=6,103,040
[E01   746/1548 G    745|CLM] train=5.8131  mask=19.4%  norm=1.071  lr=2.80e-04  dt=  36.6ms  words=6,111,232
[E01   747/1548 G    746|CLM] train=5.3319  mask=19.4%  norm=0.769  lr=2.80e-04  dt=  36.6ms  words=6,119,424
[E01   748/1548 G    747|CLM] train=3.6191  mask=19.4%  norm=1.585  lr=2.80e-04  dt=  36.9ms  words=6,127,616
[E01   749/1548 G    748|CLM] train=5.7045  mask=19.4%  norm=0.965  lr=2.81e-04  dt=  36.8ms  words=6,135,808
[E01   750/1548 G    749|CLM] train=5.4907  mask=19.4%  norm=1.439  lr=2.81e-04  dt=  36.7ms  words=6,144,000
[E01   751/1548 G    750|CLM] train=5.0470  mask=19.4%  norm=0.781  lr=2.82e-04  dt=  36.5ms  words=6,152,192
[E01   752/1548 G    751|CLM] train=3.4614  mask=19.4%  norm=1.015  lr=2.82e-04  dt=  36.6ms  words=6,160,384
[E01   753/1548 G    752|CLM] train=5.6726  mask=19.4%  norm=0.683  lr=2.82e-04  dt=  36.8ms  words=6,168,576
[E01   754/1548 G    753|CLM] train=4.7110  mask=19.4%  norm=0.934  lr=2.83e-04  dt=  36.7ms  words=6,176,768
[E01   755/1548 G    754|CLM] train=6.3298  mask=19.4%  norm=0.994  lr=2.83e-04  dt=  36.8ms  words=6,184,960
[E01   756/1548 G    755|CLM] train=5.1168  mask=19.4%  norm=0.825  lr=2.83e-04  dt=  36.6ms  words=6,193,152
[E01   757/1548 G    756|CLM] train=3.3737  mask=19.4%  norm=0.889  lr=2.84e-04  dt=  36.6ms  words=6,201,344
[E01   758/1548 G    757|CLM] train=5.6950  mask=19.4%  norm=0.949  lr=2.84e-04  dt=  36.6ms  words=6,209,536
[E01   759/1548 G    758|CLM] train=3.8234  mask=19.4%  norm=0.964  lr=2.85e-04  dt=  36.9ms  words=6,217,728
[E01   760/1548 G    759|CLM] train=5.7651  mask=19.4%  norm=0.802  lr=2.85e-04  dt=  43.5ms  words=6,225,920
[E01   761/1548 G    760|CLM] train=3.6317  mask=19.4%  norm=1.114  lr=2.85e-04  dt=  41.4ms  words=6,234,112
[E01   762/1548 G    761|CLM] train=5.4964  mask=19.4%  norm=0.910  lr=2.86e-04  dt=  41.5ms  words=6,242,304
[E01   763/1548 G    762|CLM] train=3.9764  mask=19.4%  norm=1.492  lr=2.86e-04  dt=  47.5ms  words=6,250,496
[E01   764/1548 G    763|CLM] train=3.3063  mask=19.4%  norm=1.314  lr=2.86e-04  dt=  47.7ms  words=6,258,688
[E01   765/1548 G    764|CLM] train=5.5534  mask=19.4%  norm=0.967  lr=2.87e-04  dt=  43.2ms  words=6,266,880
[E01   766/1548 G    765|CLM] train=6.0242  mask=19.4%  norm=1.184  lr=2.87e-04  dt=  40.4ms  words=6,275,072
[E01   767/1548 G    766|CLM] train=5.2256  mask=19.4%  norm=0.720  lr=2.88e-04  dt=  41.8ms  words=6,283,264
[E01   768/1548 G    767|CLM] train=5.5793  mask=19.4%  norm=1.343  lr=2.88e-04  dt=  42.4ms  words=6,291,456
[E01   769/1548 G    768|CLM] train=3.5516  mask=19.4%  norm=1.536  lr=2.88e-04  dt=  38.8ms  words=6,299,648
[E01   770/1548 G    769|CLM] train=5.1898  mask=19.4%  norm=0.804  lr=2.89e-04  dt=  36.5ms  words=6,307,840
[E01   771/1548 G    770|CLM] train=3.7390  mask=19.4%  norm=2.137  lr=2.89e-04  dt=  36.4ms  words=6,316,032
[E01   772/1548 G    771|CLM] train=5.6882  mask=19.4%  norm=1.236  lr=2.89e-04  dt=  36.4ms  words=6,324,224
[E01   773/1548 G    772|CLM] train=5.6872  mask=19.4%  norm=0.947  lr=2.90e-04  dt=  36.7ms  words=6,332,416
[E01   774/1548 G    773|CLM] train=3.3679  mask=19.4%  norm=0.891  lr=2.90e-04  dt=  38.1ms  words=6,340,608
[E01   775/1548 G    774|CLM] train=5.9396  mask=19.4%  norm=0.841  lr=2.91e-04  dt=  42.0ms  words=6,348,800
[E01   776/1548 G    775|CLM] train=5.0101  mask=19.4%  norm=0.726  lr=2.91e-04  dt=  41.0ms  words=6,356,992
[E01   777/1548 G    776|CLM] train=3.3532  mask=19.4%  norm=0.807  lr=2.91e-04  dt=  39.1ms  words=6,365,184
[E01   778/1548 G    777|CLM] train=3.9212  mask=19.4%  norm=0.883  lr=2.92e-04  dt=  50.1ms  words=6,373,376
[E01   779/1548 G    778|CLM] train=3.2429  mask=19.4%  norm=0.782  lr=2.92e-04  dt=  44.0ms  words=6,381,568
[E01   780/1548 G    779|CLM] train=3.1818  mask=19.4%  norm=0.953  lr=2.93e-04  dt=  36.7ms  words=6,389,760
[E01   781/1548 G    780|CLM] train=3.3906  mask=19.4%  norm=0.807  lr=2.93e-04  dt=  36.6ms  words=6,397,952
[E01   782/1548 G    781|CLM] train=3.7159  mask=19.4%  norm=0.881  lr=2.93e-04  dt=  37.0ms  words=6,406,144
[E01   783/1548 G    782|CLM] train=4.0386  mask=19.4%  norm=1.506  lr=2.94e-04  dt=  36.2ms  words=6,414,336
[E01   784/1548 G    783|CLM] train=5.9685  mask=19.4%  norm=1.106  lr=2.94e-04  dt=  36.7ms  words=6,422,528
[E01   785/1548 G    784|CLM] train=5.3077  mask=19.4%  norm=1.255  lr=2.94e-04  dt=  37.0ms  words=6,430,720
[E01   786/1548 G    785|CLM] train=5.8912  mask=19.4%  norm=1.007  lr=2.95e-04  dt=  36.2ms  words=6,438,912
[E01   787/1548 G    786|CLM] train=7.1136  mask=19.4%  norm=1.080  lr=2.95e-04  dt=  36.2ms  words=6,447,104
[E01   788/1548 G    787|CLM] train=3.3423  mask=19.4%  norm=1.636  lr=2.95e-04  dt=  36.3ms  words=6,455,296
[E01   789/1548 G    788|CLM] train=6.3027  mask=19.4%  norm=0.929  lr=2.96e-04  dt=  36.7ms  words=6,463,488
[E01   790/1548 G    789|CLM] train=5.4951  mask=19.4%  norm=1.012  lr=2.96e-04  dt=  36.7ms  words=6,471,680
[E01   791/1548 G    790|CLM] train=5.0177  mask=19.4%  norm=1.332  lr=2.97e-04  dt=  36.2ms  words=6,479,872
[E01   792/1548 G    791|CLM] train=3.2890  mask=19.4%  norm=1.021  lr=2.97e-04  dt=  36.1ms  words=6,488,064
[E01   793/1548 G    792|CLM] train=3.3192  mask=19.4%  norm=1.022  lr=2.97e-04  dt=  36.2ms  words=6,496,256
[E01   794/1548 G    793|CLM] train=5.2166  mask=19.4%  norm=0.963  lr=2.98e-04  dt=  36.3ms  words=6,504,448
[E01   795/1548 G    794|CLM] train=3.4882  mask=19.4%  norm=0.812  lr=2.98e-04  dt=  36.4ms  words=6,512,640
[E01   796/1548 G    795|CLM] train=3.5297  mask=19.4%  norm=1.258  lr=2.98e-04  dt=  36.2ms  words=6,520,832
[E01   797/1548 G    796|CLM] train=3.4446  mask=19.4%  norm=1.008  lr=2.99e-04  dt=  36.3ms  words=6,529,024
[E01   798/1548 G    797|CLM] train=4.9491  mask=19.4%  norm=1.116  lr=2.99e-04  dt=  36.2ms  words=6,537,216
[E01   799/1548 G    798|CLM] train=3.1774  mask=19.4%  norm=0.840  lr=3.00e-04  dt=  36.4ms  words=6,545,408
[E01   800/1548 G    799|CLM] train=5.8721  mask=19.4%  norm=1.056  lr=3.00e-04  dt=  36.4ms  words=6,553,600
[E01   801/1548 G    800|CLM] train=3.8945  mask=19.4%  norm=1.214  lr=3.00e-04  dt=  36.1ms  words=6,561,792
[E01   802/1548 G    801|CLM] train=3.7343  mask=19.4%  norm=0.609  lr=3.00e-04  dt=  36.1ms  words=6,569,984
[E01   803/1548 G    802|CLM] train=5.9199  mask=19.4%  norm=0.851  lr=3.00e-04  dt=  36.4ms  words=6,578,176
[E01   804/1548 G    803|CLM] train=5.4024  mask=19.4%  norm=1.149  lr=3.00e-04  dt=  36.5ms  words=6,586,368
[E01   805/1548 G    804|CLM] train=4.9875  mask=19.4%  norm=0.727  lr=3.00e-04  dt=  36.3ms  words=6,594,560
[E01   806/1548 G    805|CLM] train=5.9319  mask=19.3%  norm=0.616  lr=3.00e-04  dt=  36.2ms  words=6,602,752
[E01   807/1548 G    806|CLM] train=3.4767  mask=19.3%  norm=1.293  lr=3.00e-04  dt=  36.2ms  words=6,610,944
[E01   808/1548 G    807|CLM] train=4.8116  mask=19.3%  norm=0.736  lr=3.00e-04  dt=  36.3ms  words=6,619,136
[E01   809/1548 G    808|CLM] train=3.4383  mask=19.3%  norm=0.777  lr=3.00e-04  dt=  36.2ms  words=6,627,328
[E01   810/1548 G    809|CLM] train=3.3940  mask=19.3%  norm=0.839  lr=3.00e-04  dt=  36.2ms  words=6,635,520
[E01   811/1548 G    810|CLM] train=3.2447  mask=19.3%  norm=0.696  lr=3.00e-04  dt=  36.2ms  words=6,643,712
[E01   812/1548 G    811|CLM] train=3.1741  mask=19.3%  norm=0.990  lr=3.00e-04  dt=  36.5ms  words=6,651,904
[E01   813/1548 G    812|CLM] train=6.9004  mask=19.3%  norm=1.475  lr=3.00e-04  dt=  39.1ms  words=6,660,096
[E01   814/1548 G    813|CLM] train=5.5065  mask=19.3%  norm=1.045  lr=3.00e-04  dt=  41.7ms  words=6,668,288
[E01   815/1548 G    814|CLM] train=5.6637  mask=19.3%  norm=0.920  lr=3.00e-04  dt=  39.6ms  words=6,676,480
[E01   816/1548 G    815|CLM] train=5.4297  mask=19.3%  norm=0.808  lr=3.00e-04  dt=  42.5ms  words=6,684,672
[E01   817/1548 G    816|CLM] train=5.2954  mask=19.3%  norm=0.928  lr=3.00e-04  dt=  40.7ms  words=6,692,864
[E01   818/1548 G    817|CLM] train=3.4976  mask=19.3%  norm=1.445  lr=3.00e-04  dt=  44.7ms  words=6,701,056
[E01   819/1548 G    818|CLM] train=3.2981  mask=19.3%  norm=1.289  lr=3.00e-04  dt=  39.3ms  words=6,709,248
[E01   820/1548 G    819|CLM] train=3.2311  mask=19.3%  norm=1.006  lr=3.00e-04  dt=  37.0ms  words=6,717,440
[E01   821/1548 G    820|CLM] train=5.3094  mask=19.3%  norm=0.794  lr=3.00e-04  dt=  36.6ms  words=6,725,632
[E01   822/1548 G    821|CLM] train=5.5931  mask=19.3%  norm=0.734  lr=3.00e-04  dt=  36.5ms  words=6,733,824
[E01   823/1548 G    822|CLM] train=3.5347  mask=19.3%  norm=1.104  lr=3.00e-04  dt=  36.6ms  words=6,742,016
[E01   824/1548 G    823|CLM] train=5.9072  mask=19.3%  norm=0.776  lr=3.00e-04  dt=  36.6ms  words=6,750,208
[E01   825/1548 G    824|CLM] train=5.4220  mask=19.3%  norm=0.646  lr=3.00e-04  dt=  36.6ms  words=6,758,400
[E01   826/1548 G    825|CLM] train=3.9574  mask=19.3%  norm=1.070  lr=3.00e-04  dt=  36.7ms  words=6,766,592
[E01   827/1548 G    826|CLM] train=4.9904  mask=19.3%  norm=0.867  lr=3.00e-04  dt=  36.7ms  words=6,774,784
[E01   828/1548 G    827|CLM] train=4.9653  mask=19.3%  norm=0.793  lr=3.00e-04  dt=  36.8ms  words=6,782,976
[E01   829/1548 G    828|CLM] train=5.6375  mask=19.3%  norm=0.692  lr=3.00e-04  dt=  36.5ms  words=6,791,168
[E01   830/1548 G    829|CLM] train=3.3612  mask=19.3%  norm=0.888  lr=3.00e-04  dt=  36.5ms  words=6,799,360
[E01   831/1548 G    830|CLM] train=5.3361  mask=19.3%  norm=1.045  lr=3.00e-04  dt=  36.6ms  words=6,807,552
[E01   832/1548 G    831|CLM] train=3.3422  mask=19.3%  norm=0.700  lr=3.00e-04  dt=  36.7ms  words=6,815,744
[E01   833/1548 G    832|CLM] train=4.8557  mask=19.3%  norm=1.125  lr=3.00e-04  dt=  36.6ms  words=6,823,936
[E01   834/1548 G    833|CLM] train=3.5481  mask=19.3%  norm=0.674  lr=3.00e-04  dt=  36.6ms  words=6,832,128
[E01   835/1548 G    834|CLM] train=3.3985  mask=19.3%  norm=0.918  lr=3.00e-04  dt=  36.6ms  words=6,840,320
[E01   836/1548 G    835|CLM] train=7.1674  mask=19.3%  norm=0.991  lr=3.00e-04  dt=  36.4ms  words=6,848,512
[E01   837/1548 G    836|CLM] train=3.2025  mask=19.3%  norm=0.729  lr=3.00e-04  dt=  36.4ms  words=6,856,704
[E01   838/1548 G    837|CLM] train=5.2499  mask=19.3%  norm=0.858  lr=3.00e-04  dt=  36.3ms  words=6,864,896
[E01   839/1548 G    838|CLM] train=5.5858  mask=19.3%  norm=0.859  lr=3.00e-04  dt=  36.7ms  words=6,873,088
[E01   840/1548 G    839|CLM] train=5.2158  mask=19.3%  norm=0.763  lr=3.00e-04  dt=  36.6ms  words=6,881,280
[E01   841/1548 G    840|CLM] train=3.4058  mask=19.3%  norm=1.169  lr=3.00e-04  dt=  36.6ms  words=6,889,472
[E01   842/1548 G    841|CLM] train=5.9603  mask=19.3%  norm=1.323  lr=3.00e-04  dt=  36.6ms  words=6,897,664
[E01   843/1548 G    842|CLM] train=5.0937  mask=19.3%  norm=0.764  lr=3.00e-04  dt=  36.5ms  words=6,905,856
[E01   844/1548 G    843|CLM] train=3.2615  mask=19.3%  norm=0.916  lr=3.00e-04  dt=  36.5ms  words=6,914,048
[E01   845/1548 G    844|CLM] train=5.5853  mask=19.3%  norm=0.709  lr=3.00e-04  dt=  36.7ms  words=6,922,240
[E01   846/1548 G    845|CLM] train=2.7225  mask=19.3%  norm=0.710  lr=3.00e-04  dt=  36.5ms  words=6,930,432
[E01   847/1548 G    846|CLM] train=5.5698  mask=19.3%  norm=0.631  lr=3.00e-04  dt=  36.6ms  words=6,938,624
[E01   848/1548 G    847|CLM] train=3.4419  mask=19.3%  norm=0.998  lr=3.00e-04  dt=  36.7ms  words=6,946,816
[E01   849/1548 G    848|CLM] train=3.8059  mask=19.3%  norm=1.281  lr=3.00e-04  dt=  36.4ms  words=6,955,008
[E01   850/1548 G    849|CLM] train=5.7164  mask=19.3%  norm=0.945  lr=3.00e-04  dt=  36.4ms  words=6,963,200
[E01   851/1548 G    850|CLM] train=5.6027  mask=19.3%  norm=0.665  lr=3.00e-04  dt=  36.6ms  words=6,971,392
[E01   852/1548 G    851|CLM] train=3.3024  mask=19.3%  norm=0.954  lr=3.00e-04  dt=  36.8ms  words=6,979,584
[E01   853/1548 G    852|CLM] train=5.6005  mask=19.3%  norm=0.963  lr=3.00e-04  dt=  36.7ms  words=6,987,776
[E01   854/1548 G    853|CLM] train=3.4188  mask=19.3%  norm=1.048  lr=3.00e-04  dt=  36.6ms  words=6,995,968
[E01   855/1548 G    854|CLM] train=3.1336  mask=19.3%  norm=0.869  lr=3.00e-04  dt=  36.4ms  words=7,004,160

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_7M'...
[Checkpoint] Checkpoint 'chck_7M' successfully saved.
[E01   856/1548 G    855|CLM] train=3.5271  mask=19.3%  norm=0.993  lr=3.00e-04  dt=  37.0ms  words=7,012,352
[E01   857/1548 G    856|CLM] train=6.2691  mask=19.3%  norm=2.235  lr=3.00e-04  dt=  36.5ms  words=7,020,544
[E01   858/1548 G    857|CLM] train=3.3674  mask=19.3%  norm=1.102  lr=3.00e-04  dt=  36.8ms  words=7,028,736
[E01   859/1548 G    858|CLM] train=3.1764  mask=19.3%  norm=0.900  lr=3.00e-04  dt=  36.8ms  words=7,036,928
[E01   860/1548 G    859|CLM] train=5.5470  mask=19.3%  norm=1.019  lr=3.00e-04  dt=  36.7ms  words=7,045,120
[E01   861/1548 G    860|CLM] train=5.2817  mask=19.3%  norm=0.721  lr=3.00e-04  dt=  36.8ms  words=7,053,312
[E01   862/1548 G    861|CLM] train=5.5573  mask=19.3%  norm=0.735  lr=3.00e-04  dt=  36.7ms  words=7,061,504
[E01   863/1548 G    862|CLM] train=5.2377  mask=19.3%  norm=0.736  lr=3.00e-04  dt=  37.0ms  words=7,069,696
[E01   864/1548 G    863|CLM] train=3.1251  mask=19.3%  norm=0.972  lr=3.00e-04  dt=  37.0ms  words=7,077,888
[E01   865/1548 G    864|CLM] train=3.6362  mask=19.3%  norm=1.240  lr=3.00e-04  dt=  36.5ms  words=7,086,080
[E01   866/1548 G    865|CLM] train=3.4710  mask=19.3%  norm=0.850  lr=3.00e-04  dt=  36.4ms  words=7,094,272
[E01   867/1548 G    866|CLM] train=6.5433  mask=19.3%  norm=1.311  lr=3.00e-04  dt=  36.4ms  words=7,102,464
[E01   868/1548 G    867|CLM] train=5.7939  mask=19.3%  norm=0.978  lr=3.00e-04  dt=  36.7ms  words=7,110,656
[E01   869/1548 G    868|CLM] train=3.1468  mask=19.3%  norm=0.819  lr=3.00e-04  dt=  36.6ms  words=7,118,848
[E01   870/1548 G    869|CLM] train=5.9249  mask=19.3%  norm=1.071  lr=3.00e-04  dt=  36.6ms  words=7,127,040
[E01   871/1548 G    870|CLM] train=3.1581  mask=19.3%  norm=1.289  lr=3.00e-04  dt=  36.9ms  words=7,135,232
[E01   872/1548 G    871|CLM] train=6.2163  mask=19.3%  norm=0.862  lr=3.00e-04  dt=  36.6ms  words=7,143,424
[E01   873/1548 G    872|CLM] train=5.8924  mask=19.3%  norm=0.880  lr=3.00e-04  dt=  36.5ms  words=7,151,616
[E01   874/1548 G    873|CLM] train=6.0376  mask=19.3%  norm=0.820  lr=3.00e-04  dt=  36.7ms  words=7,159,808
[E01   875/1548 G    874|CLM] train=5.5536  mask=19.3%  norm=0.828  lr=3.00e-04  dt=  36.9ms  words=7,168,000
[E01   876/1548 G    875|CLM] train=6.7566  mask=19.3%  norm=1.643  lr=3.00e-04  dt=  36.9ms  words=7,176,192
[E01   877/1548 G    876|CLM] train=4.5495  mask=19.3%  norm=0.812  lr=3.00e-04  dt=  36.5ms  words=7,184,384
[E01   878/1548 G    877|CLM] train=3.2056  mask=19.3%  norm=1.023  lr=3.00e-04  dt=  36.5ms  words=7,192,576
[E01   879/1548 G    878|CLM] train=5.4034  mask=19.3%  norm=1.289  lr=3.00e-04  dt=  36.6ms  words=7,200,768
[E01   880/1548 G    879|CLM] train=5.9429  mask=19.3%  norm=0.942  lr=3.00e-04  dt=  36.7ms  words=7,208,960
[E01   881/1548 G    880|CLM] train=4.9360  mask=19.3%  norm=0.921  lr=3.00e-04  dt=  36.7ms  words=7,217,152
[E01   882/1548 G    881|CLM] train=5.8046  mask=19.3%  norm=0.986  lr=3.00e-04  dt=  36.5ms  words=7,225,344
[E01   883/1548 G    882|CLM] train=3.1196  mask=19.3%  norm=0.996  lr=3.00e-04  dt=  36.6ms  words=7,233,536
[E01   884/1548 G    883|CLM] train=5.6071  mask=19.3%  norm=0.724  lr=3.00e-04  dt=  36.6ms  words=7,241,728
[E01   885/1548 G    884|CLM] train=6.0874  mask=19.3%  norm=0.736  lr=3.00e-04  dt=  36.5ms  words=7,249,920
[E01   886/1548 G    885|CLM] train=3.1119  mask=19.3%  norm=0.876  lr=3.00e-04  dt=  36.6ms  words=7,258,112
[E01   887/1548 G    886|CLM] train=3.1688  mask=19.3%  norm=0.762  lr=3.00e-04  dt=  36.5ms  words=7,266,304
[E01   888/1548 G    887|CLM] train=6.7732  mask=19.3%  norm=1.108  lr=3.00e-04  dt=  36.5ms  words=7,274,496
[E01   889/1548 G    888|CLM] train=5.5760  mask=19.3%  norm=0.924  lr=3.00e-04  dt=  36.5ms  words=7,282,688
[E01   890/1548 G    889|CLM] train=3.0601  mask=19.3%  norm=0.786  lr=3.00e-04  dt=  36.5ms  words=7,290,880
[E01   891/1548 G    890|CLM] train=5.8332  mask=19.3%  norm=0.722  lr=3.00e-04  dt=  36.5ms  words=7,299,072
[E01   892/1548 G    891|CLM] train=5.7918  mask=19.3%  norm=0.660  lr=3.00e-04  dt=  36.5ms  words=7,307,264
[E01   893/1548 G    892|CLM] train=3.2021  mask=19.3%  norm=1.050  lr=3.00e-04  dt=  36.7ms  words=7,315,456
[E01   894/1548 G    893|CLM] train=3.0008  mask=19.3%  norm=0.668  lr=3.00e-04  dt=  36.6ms  words=7,323,648
[E01   895/1548 G    894|CLM] train=3.6688  mask=19.3%  norm=0.724  lr=3.00e-04  dt=  36.5ms  words=7,331,840
[E01   896/1548 G    895|CLM] train=5.3729  mask=19.3%  norm=0.983  lr=3.00e-04  dt=  36.6ms  words=7,340,032
[E01   897/1548 G    896|CLM] train=5.1958  mask=19.3%  norm=4.217  lr=3.00e-04  dt=  36.5ms  words=7,348,224
[E01   898/1548 G    897|CLM] train=4.8460  mask=19.3%  norm=0.821  lr=3.00e-04  dt=  36.5ms  words=7,356,416
[E01   899/1548 G    898|CLM] train=5.0040  mask=19.3%  norm=1.236  lr=3.00e-04  dt=  36.6ms  words=7,364,608
[E01   900/1548 G    899|CLM] train=5.4812  mask=19.3%  norm=1.157  lr=3.00e-04  dt=  36.6ms  words=7,372,800
[E01   901/1548 G    900|CLM] train=4.6105  mask=19.3%  norm=1.042  lr=3.00e-04  dt=  36.6ms  words=7,380,992
[E01   902/1548 G    901|CLM] train=5.5660  mask=19.3%  norm=1.292  lr=3.00e-04  dt=  36.5ms  words=7,389,184
[E01   903/1548 G    902|CLM] train=5.1852  mask=19.3%  norm=1.212  lr=3.00e-04  dt=  36.6ms  words=7,397,376
[E01   904/1548 G    903|CLM] train=6.2476  mask=19.3%  norm=2.376  lr=3.00e-04  dt=  36.6ms  words=7,405,568
[E01   905/1548 G    904|CLM] train=5.1518  mask=19.3%  norm=1.048  lr=3.00e-04  dt=  36.7ms  words=7,413,760
[E01   906/1548 G    905|CLM] train=3.5364  mask=19.3%  norm=1.502  lr=3.00e-04  dt=  36.8ms  words=7,421,952
[E01   907/1548 G    906|CLM] train=4.8324  mask=19.3%  norm=0.675  lr=3.00e-04  dt=  36.7ms  words=7,430,144
[E01   908/1548 G    907|CLM] train=5.2557  mask=19.3%  norm=0.900  lr=3.00e-04  dt=  36.4ms  words=7,438,336
[E01   909/1548 G    908|CLM] train=4.9522  mask=19.3%  norm=0.787  lr=3.00e-04  dt=  36.5ms  words=7,446,528
[E01   910/1548 G    909|CLM] train=5.3041  mask=19.3%  norm=0.718  lr=3.00e-04  dt=  36.5ms  words=7,454,720
[E01   911/1548 G    910|CLM] train=4.0278  mask=19.3%  norm=1.294  lr=3.00e-04  dt=  36.7ms  words=7,462,912
[E01   912/1548 G    911|CLM] train=3.0619  mask=19.3%  norm=0.987  lr=3.00e-04  dt=  36.6ms  words=7,471,104
[E01   913/1548 G    912|CLM] train=4.9608  mask=19.3%  norm=0.915  lr=3.00e-04  dt=  36.7ms  words=7,479,296
[E01   914/1548 G    913|CLM] train=5.5482  mask=19.3%  norm=0.764  lr=3.00e-04  dt=  36.6ms  words=7,487,488
[E01   915/1548 G    914|CLM] train=3.5143  mask=19.3%  norm=1.112  lr=3.00e-04  dt=  36.9ms  words=7,495,680
[E01   916/1548 G    915|CLM] train=4.8207  mask=19.3%  norm=1.196  lr=3.00e-04  dt=  36.5ms  words=7,503,872
[E01   917/1548 G    916|CLM] train=5.2653  mask=19.3%  norm=0.800  lr=3.00e-04  dt=  36.5ms  words=7,512,064
[E01   918/1548 G    917|CLM] train=5.1031  mask=19.3%  norm=1.005  lr=3.00e-04  dt=  36.6ms  words=7,520,256
[E01   919/1548 G    918|CLM] train=3.2865  mask=19.3%  norm=1.010  lr=3.00e-04  dt=  36.5ms  words=7,528,448
[E01   920/1548 G    919|CLM] train=4.8205  mask=19.3%  norm=0.934  lr=3.00e-04  dt=  36.5ms  words=7,536,640
[E01   921/1548 G    920|CLM] train=5.3095  mask=19.3%  norm=0.894  lr=3.00e-04  dt=  36.6ms  words=7,544,832
[E01   922/1548 G    921|CLM] train=4.9725  mask=19.3%  norm=1.105  lr=3.00e-04  dt=  36.7ms  words=7,553,024
[E01   923/1548 G    922|CLM] train=6.5257  mask=19.3%  norm=0.878  lr=3.00e-04  dt=  36.7ms  words=7,561,216
[E01   924/1548 G    923|CLM] train=5.8276  mask=19.3%  norm=0.865  lr=3.00e-04  dt=  36.6ms  words=7,569,408
[E01   925/1548 G    924|CLM] train=5.3855  mask=19.3%  norm=0.715  lr=3.00e-04  dt=  36.4ms  words=7,577,600
[E01   926/1548 G    925|CLM] train=5.5300  mask=19.3%  norm=0.811  lr=3.00e-04  dt=  36.5ms  words=7,585,792
[E01   927/1548 G    926|CLM] train=5.2066  mask=19.3%  norm=1.012  lr=3.00e-04  dt=  36.5ms  words=7,593,984
[E01   928/1548 G    927|CLM] train=4.6768  mask=19.3%  norm=1.501  lr=3.00e-04  dt=  36.5ms  words=7,602,176
[E01   929/1548 G    928|CLM] train=4.5774  mask=19.3%  norm=0.669  lr=3.00e-04  dt=  36.9ms  words=7,610,368
[E01   930/1548 G    929|CLM] train=5.5537  mask=19.2%  norm=0.889  lr=3.00e-04  dt=  36.8ms  words=7,618,560
[E01   931/1548 G    930|CLM] train=3.7054  mask=19.2%  norm=1.495  lr=3.00e-04  dt=  36.6ms  words=7,626,752
[E01   932/1548 G    931|CLM] train=3.2549  mask=19.2%  norm=1.388  lr=3.00e-04  dt=  36.4ms  words=7,634,944
[E01   933/1548 G    932|CLM] train=5.4977  mask=19.2%  norm=0.778  lr=3.00e-04  dt=  36.7ms  words=7,643,136
[E01   934/1548 G    933|CLM] train=4.8613  mask=19.2%  norm=0.927  lr=3.00e-04  dt=  36.5ms  words=7,651,328
[E01   935/1548 G    934|CLM] train=4.8265  mask=19.2%  norm=0.944  lr=3.00e-04  dt=  41.5ms  words=7,659,520
[E01   936/1548 G    935|CLM] train=5.1416  mask=19.2%  norm=0.888  lr=3.00e-04  dt=  43.5ms  words=7,667,712
[E01   937/1548 G    936|CLM] train=5.7284  mask=19.2%  norm=1.125  lr=3.00e-04  dt=  43.4ms  words=7,675,904
[E01   938/1548 G    937|CLM] train=3.3180  mask=19.2%  norm=1.182  lr=3.00e-04  dt=  43.4ms  words=7,684,096
[E01   939/1548 G    938|CLM] train=5.0792  mask=19.2%  norm=1.027  lr=3.00e-04  dt=  43.5ms  words=7,692,288
[E01   940/1548 G    939|CLM] train=5.9894  mask=19.2%  norm=0.879  lr=3.00e-04  dt=  43.7ms  words=7,700,480
[E01   941/1548 G    940|CLM] train=3.4518  mask=19.2%  norm=0.974  lr=3.00e-04  dt=  37.0ms  words=7,708,672
[E01   942/1548 G    941|CLM] train=3.1209  mask=19.2%  norm=0.674  lr=3.00e-04  dt=  36.7ms  words=7,716,864
[E01   943/1548 G    942|CLM] train=5.3382  mask=19.2%  norm=1.017  lr=3.00e-04  dt=  36.9ms  words=7,725,056
[E01   944/1548 G    943|CLM] train=4.8208  mask=19.2%  norm=0.887  lr=3.00e-04  dt=  37.0ms  words=7,733,248
[E01   945/1548 G    944|CLM] train=5.4637  mask=19.2%  norm=0.884  lr=3.00e-04  dt=  36.9ms  words=7,741,440
[E01   946/1548 G    945|CLM] train=3.2396  mask=19.2%  norm=0.798  lr=3.00e-04  dt=  36.6ms  words=7,749,632
[E01   947/1548 G    946|CLM] train=3.0077  mask=19.2%  norm=0.850  lr=3.00e-04  dt=  36.5ms  words=7,757,824
[E01   948/1548 G    947|CLM] train=5.3763  mask=19.2%  norm=0.810  lr=3.00e-04  dt=  36.5ms  words=7,766,016
[E01   949/1548 G    948|CLM] train=4.9608  mask=19.2%  norm=1.086  lr=3.00e-04  dt=  37.0ms  words=7,774,208
[E01   950/1548 G    949|CLM] train=3.2049  mask=19.2%  norm=0.911  lr=3.00e-04  dt=  36.4ms  words=7,782,400
[E01   951/1548 G    950|CLM] train=5.5274  mask=19.2%  norm=0.769  lr=3.00e-04  dt=  36.6ms  words=7,790,592
[E01   952/1548 G    951|CLM] train=3.2492  mask=19.2%  norm=0.995  lr=3.00e-04  dt=  36.6ms  words=7,798,784
[E01   953/1548 G    952|CLM] train=3.0904  mask=19.2%  norm=0.694  lr=3.00e-04  dt=  36.7ms  words=7,806,976
[E01   954/1548 G    953|CLM] train=5.0497  mask=19.2%  norm=0.969  lr=3.00e-04  dt=  36.5ms  words=7,815,168
[E01   955/1548 G    954|CLM] train=2.9436  mask=19.2%  norm=0.749  lr=3.00e-04  dt=  36.8ms  words=7,823,360
[E01   956/1548 G    955|CLM] train=4.7105  mask=19.2%  norm=0.625  lr=3.00e-04  dt=  37.1ms  words=7,831,552
[E01   957/1548 G    956|CLM] train=4.8654  mask=19.2%  norm=1.138  lr=3.00e-04  dt=  36.6ms  words=7,839,744
[E01   958/1548 G    957|CLM] train=3.4885  mask=19.2%  norm=0.804  lr=3.00e-04  dt=  36.4ms  words=7,847,936
[E01   959/1548 G    958|CLM] train=3.4763  mask=19.2%  norm=0.810  lr=3.00e-04  dt=  36.5ms  words=7,856,128
[E01   960/1548 G    959|CLM] train=4.3775  mask=19.2%  norm=0.861  lr=3.00e-04  dt=  36.6ms  words=7,864,320
[E01   961/1548 G    960|CLM] train=5.6809  mask=19.2%  norm=0.833  lr=3.00e-04  dt=  36.5ms  words=7,872,512
[E01   962/1548 G    961|CLM] train=6.7899  mask=19.2%  norm=3.163  lr=3.00e-04  dt=  37.0ms  words=7,880,704
[E01   963/1548 G    962|CLM] train=3.0679  mask=19.2%  norm=0.775  lr=3.00e-04  dt=  36.6ms  words=7,888,896
[E01   964/1548 G    963|CLM] train=3.5956  mask=19.2%  norm=0.829  lr=3.00e-04  dt=  36.6ms  words=7,897,088
[E01   965/1548 G    964|CLM] train=5.1962  mask=19.2%  norm=1.117  lr=3.00e-04  dt=  36.5ms  words=7,905,280
[E01   966/1548 G    965|CLM] train=4.7021  mask=19.2%  norm=0.668  lr=3.00e-04  dt=  36.7ms  words=7,913,472
[E01   967/1548 G    966|CLM] train=3.7581  mask=19.2%  norm=0.877  lr=3.00e-04  dt=  36.6ms  words=7,921,664
[E01   968/1548 G    967|CLM] train=4.6969  mask=19.2%  norm=1.176  lr=3.00e-04  dt=  36.7ms  words=7,929,856
[E01   969/1548 G    968|CLM] train=4.4186  mask=19.2%  norm=0.852  lr=3.00e-04  dt=  36.6ms  words=7,938,048
[E01   970/1548 G    969|CLM] train=5.1858  mask=19.2%  norm=0.740  lr=3.00e-04  dt=  36.7ms  words=7,946,240
[E01   971/1548 G    970|CLM] train=3.4551  mask=19.2%  norm=1.041  lr=3.00e-04  dt=  36.6ms  words=7,954,432
[E01   972/1548 G    971|CLM] train=3.3802  mask=19.2%  norm=0.735  lr=3.00e-04  dt=  36.6ms  words=7,962,624
[E01   973/1548 G    972|CLM] train=5.1028  mask=19.2%  norm=1.270  lr=3.00e-04  dt=  36.6ms  words=7,970,816
[E01   974/1548 G    973|CLM] train=6.0765  mask=19.2%  norm=1.218  lr=3.00e-04  dt=  36.6ms  words=7,979,008
[E01   975/1548 G    974|CLM] train=3.0896  mask=19.2%  norm=1.429  lr=3.00e-04  dt=  36.4ms  words=7,987,200
[E01   976/1548 G    975|CLM] train=3.0185  mask=19.2%  norm=0.903  lr=3.00e-04  dt=  36.4ms  words=7,995,392
[E01   977/1548 G    976|CLM] train=3.6562  mask=19.2%  norm=0.768  lr=3.00e-04  dt=  36.4ms  words=8,003,584

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_8M'...
[Checkpoint] Checkpoint 'chck_8M' successfully saved.
[E01   978/1548 G    977|CLM] train=5.2460  mask=19.2%  norm=0.886  lr=3.00e-04  dt=  37.5ms  words=8,011,776
[E01   979/1548 G    978|CLM] train=3.3064  mask=19.2%  norm=1.219  lr=3.00e-04  dt=  36.6ms  words=8,019,968
[E01   980/1548 G    979|CLM] train=3.1155  mask=19.2%  norm=0.909  lr=3.00e-04  dt=  36.7ms  words=8,028,160
[E01   981/1548 G    980|CLM] train=3.0413  mask=19.2%  norm=0.904  lr=3.00e-04  dt=  36.6ms  words=8,036,352
[E01   982/1548 G    981|CLM] train=4.9673  mask=19.2%  norm=0.893  lr=3.00e-04  dt=  36.5ms  words=8,044,544
[E01   983/1548 G    982|CLM] train=5.6727  mask=19.2%  norm=0.755  lr=3.00e-04  dt=  36.9ms  words=8,052,736
[E01   984/1548 G    983|CLM] train=3.5746  mask=19.2%  norm=0.894  lr=3.00e-04  dt=  36.7ms  words=8,060,928
[E01   985/1548 G    984|CLM] train=5.3417  mask=19.2%  norm=0.797  lr=3.00e-04  dt=  36.5ms  words=8,069,120
[E01   986/1548 G    985|CLM] train=3.3679  mask=19.2%  norm=0.895  lr=3.00e-04  dt=  36.4ms  words=8,077,312
[E01   987/1548 G    986|CLM] train=5.5980  mask=19.2%  norm=0.950  lr=3.00e-04  dt=  36.8ms  words=8,085,504
[E01   988/1548 G    987|CLM] train=5.6261  mask=19.2%  norm=0.852  lr=3.00e-04  dt=  36.9ms  words=8,093,696
[E01   989/1548 G    988|CLM] train=3.4465  mask=19.2%  norm=0.840  lr=3.00e-04  dt=  36.7ms  words=8,101,888
[E01   990/1548 G    989|CLM] train=3.1843  mask=19.2%  norm=1.090  lr=3.00e-04  dt=  36.9ms  words=8,110,080
[E01   991/1548 G    990|CLM] train=3.9426  mask=19.2%  norm=0.732  lr=3.00e-04  dt=  36.6ms  words=8,118,272
[E01   992/1548 G    991|CLM] train=5.5773  mask=19.2%  norm=1.275  lr=3.00e-04  dt=  36.7ms  words=8,126,464
[E01   993/1548 G    992|CLM] train=3.7676  mask=19.2%  norm=1.222  lr=3.00e-04  dt=  36.9ms  words=8,134,656
[E01   994/1548 G    993|CLM] train=5.2806  mask=19.2%  norm=1.055  lr=3.00e-04  dt=  36.7ms  words=8,142,848
[E01   995/1548 G    994|CLM] train=6.4100  mask=19.2%  norm=1.216  lr=3.00e-04  dt=  36.6ms  words=8,151,040
[E01   996/1548 G    995|CLM] train=5.5011  mask=19.2%  norm=0.680  lr=3.00e-04  dt=  36.5ms  words=8,159,232
[E01   997/1548 G    996|CLM] train=3.4722  mask=19.2%  norm=0.856  lr=3.00e-04  dt=  36.8ms  words=8,167,424
[E01   998/1548 G    997|CLM] train=3.0551  mask=19.2%  norm=0.654  lr=3.00e-04  dt=  36.6ms  words=8,175,616
[E01   999/1548 G    998|CLM] train=5.4642  mask=19.2%  norm=0.932  lr=3.00e-04  dt=  36.7ms  words=8,183,808
[E01  1000/1548 G    999|CLM] train=3.2236  mask=19.2%  norm=1.046  lr=3.00e-04  dt=  36.8ms  words=8,192,000
[E01  1001/1548 G   1000|CLM] train=5.9728  mask=19.2%  norm=0.792  lr=3.00e-04  dt=  36.6ms  words=8,200,192
[E01  1002/1548 G   1001|CLM] train=5.3310  mask=19.2%  norm=0.826  lr=3.00e-04  dt=  36.7ms  words=8,208,384
[E01  1003/1548 G   1002|CLM] train=5.8598  mask=19.2%  norm=1.328  lr=3.00e-04  dt=  36.5ms  words=8,216,576
[E01  1004/1548 G   1003|CLM] train=5.4695  mask=19.2%  norm=1.551  lr=3.00e-04  dt=  36.8ms  words=8,224,768
[E01  1005/1548 G   1004|CLM] train=5.6051  mask=19.2%  norm=1.324  lr=3.00e-04  dt=  37.1ms  words=8,232,960
[E01  1006/1548 G   1005|CLM] train=6.8283  mask=19.2%  norm=1.359  lr=3.00e-04  dt=  36.7ms  words=8,241,152
[E01  1007/1548 G   1006|CLM] train=5.0669  mask=19.2%  norm=1.148  lr=3.00e-04  dt=  36.8ms  words=8,249,344
[E01  1008/1548 G   1007|CLM] train=5.2740  mask=19.2%  norm=0.967  lr=3.00e-04  dt=  36.6ms  words=8,257,536
[E01  1009/1548 G   1008|CLM] train=3.2911  mask=19.2%  norm=1.243  lr=3.00e-04  dt=  36.8ms  words=8,265,728
[E01  1010/1548 G   1009|CLM] train=3.2583  mask=19.2%  norm=0.973  lr=3.00e-04  dt=  36.6ms  words=8,273,920
[E01  1011/1548 G   1010|CLM] train=5.0551  mask=19.2%  norm=0.832  lr=3.00e-04  dt=  36.5ms  words=8,282,112
[E01  1012/1548 G   1011|CLM] train=5.2022  mask=19.2%  norm=0.657  lr=3.00e-04  dt=  36.5ms  words=8,290,304
[E01  1013/1548 G   1012|CLM] train=3.1997  mask=19.2%  norm=0.583  lr=3.00e-04  dt=  36.6ms  words=8,298,496
[E01  1014/1548 G   1013|CLM] train=5.1732  mask=19.2%  norm=0.948  lr=3.00e-04  dt=  36.6ms  words=8,306,688
[E01  1015/1548 G   1014|CLM] train=4.0159  mask=19.2%  norm=1.358  lr=3.00e-04  dt=  36.6ms  words=8,314,880
[E01  1016/1548 G   1015|CLM] train=5.4750  mask=19.2%  norm=0.818  lr=3.00e-04  dt=  36.7ms  words=8,323,072
[E01  1017/1548 G   1016|CLM] train=4.6409  mask=19.2%  norm=1.014  lr=3.00e-04  dt=  36.5ms  words=8,331,264
[E01  1018/1548 G   1017|CLM] train=4.9638  mask=19.2%  norm=0.774  lr=3.00e-04  dt=  36.5ms  words=8,339,456
[E01  1019/1548 G   1018|CLM] train=5.2096  mask=19.2%  norm=0.748  lr=3.00e-04  dt=  36.6ms  words=8,347,648
[E01  1020/1548 G   1019|CLM] train=4.9916  mask=19.2%  norm=0.672  lr=3.00e-04  dt=  36.9ms  words=8,355,840
[E01  1021/1548 G   1020|CLM] train=5.6191  mask=19.2%  norm=1.243  lr=3.00e-04  dt=  36.6ms  words=8,364,032
[E01  1022/1548 G   1021|CLM] train=4.7662  mask=19.2%  norm=0.772  lr=3.00e-04  dt=  36.5ms  words=8,372,224
[E01  1023/1548 G   1022|CLM] train=3.2917  mask=19.2%  norm=1.468  lr=3.00e-04  dt=  36.4ms  words=8,380,416
[E01  1024/1548 G   1023|CLM] train=5.4025  mask=19.2%  norm=0.714  lr=3.00e-04  dt=  36.4ms  words=8,388,608
[E01  1025/1548 G   1024|CLM] train=4.7156  mask=19.2%  norm=0.867  lr=3.00e-04  dt=  36.5ms  words=8,396,800
[E01  1026/1548 G   1025|CLM] train=3.3307  mask=19.2%  norm=1.074  lr=3.00e-04  dt=  36.6ms  words=8,404,992
[E01  1027/1548 G   1026|CLM] train=5.5972  mask=19.2%  norm=0.621  lr=3.00e-04  dt=  36.7ms  words=8,413,184
[E01  1028/1548 G   1027|CLM] train=4.9529  mask=19.2%  norm=0.649  lr=3.00e-04  dt=  36.6ms  words=8,421,376
[E01  1029/1548 G   1028|CLM] train=5.2235  mask=19.2%  norm=0.752  lr=3.00e-04  dt=  36.5ms  words=8,429,568
[E01  1030/1548 G   1029|CLM] train=3.4754  mask=19.2%  norm=0.708  lr=3.00e-04  dt=  36.5ms  words=8,437,760
[E01  1031/1548 G   1030|CLM] train=5.7511  mask=19.2%  norm=0.860  lr=3.00e-04  dt=  36.5ms  words=8,445,952
[E01  1032/1548 G   1031|CLM] train=5.7341  mask=19.2%  norm=0.720  lr=3.00e-04  dt=  36.8ms  words=8,454,144
[E01  1033/1548 G   1032|CLM] train=3.5597  mask=19.2%  norm=0.951  lr=3.00e-04  dt=  36.7ms  words=8,462,336
[E01  1034/1548 G   1033|CLM] train=3.1769  mask=19.2%  norm=0.928  lr=3.00e-04  dt=  36.6ms  words=8,470,528
[E01  1035/1548 G   1034|CLM] train=5.7599  mask=19.2%  norm=0.928  lr=3.00e-04  dt=  36.4ms  words=8,478,720
[E01  1036/1548 G   1035|CLM] train=6.0896  mask=19.2%  norm=0.891  lr=3.00e-04  dt=  36.5ms  words=8,486,912
[E01  1037/1548 G   1036|CLM] train=3.1534  mask=19.2%  norm=0.707  lr=3.00e-04  dt=  36.7ms  words=8,495,104
[E01  1038/1548 G   1037|CLM] train=4.8974  mask=19.2%  norm=1.098  lr=3.00e-04  dt=  36.6ms  words=8,503,296
[E01  1039/1548 G   1038|CLM] train=3.2707  mask=19.2%  norm=0.857  lr=3.00e-04  dt=  36.8ms  words=8,511,488
[E01  1040/1548 G   1039|CLM] train=4.8624  mask=19.2%  norm=0.790  lr=3.00e-04  dt=  36.7ms  words=8,519,680
[E01  1041/1548 G   1040|CLM] train=5.4836  mask=19.2%  norm=0.874  lr=3.00e-04  dt=  36.4ms  words=8,527,872
[E01  1042/1548 G   1041|CLM] train=5.3529  mask=19.2%  norm=0.860  lr=3.00e-04  dt=  37.2ms  words=8,536,064
[E01  1043/1548 G   1042|CLM] train=3.5092  mask=19.2%  norm=0.725  lr=3.00e-04  dt=  37.7ms  words=8,544,256
[E01  1044/1548 G   1043|CLM] train=5.4108  mask=19.2%  norm=0.846  lr=3.00e-04  dt=  36.4ms  words=8,552,448
[E01  1045/1548 G   1044|CLM] train=4.8794  mask=19.2%  norm=1.156  lr=3.00e-04  dt=  36.5ms  words=8,560,640
[E01  1046/1548 G   1045|CLM] train=3.0870  mask=19.2%  norm=1.045  lr=3.00e-04  dt=  36.5ms  words=8,568,832
[E01  1047/1548 G   1046|CLM] train=6.1049  mask=19.2%  norm=0.847  lr=3.00e-04  dt=  36.6ms  words=8,577,024
[E01  1048/1548 G   1047|CLM] train=5.7013  mask=19.2%  norm=0.639  lr=3.00e-04  dt=  36.6ms  words=8,585,216
[E01  1049/1548 G   1048|CLM] train=3.2069  mask=19.2%  norm=1.199  lr=3.00e-04  dt=  36.6ms  words=8,593,408
[E01  1050/1548 G   1049|CLM] train=3.1403  mask=19.2%  norm=0.855  lr=3.00e-04  dt=  36.9ms  words=8,601,600
[E01  1051/1548 G   1050|CLM] train=5.6423  mask=19.2%  norm=1.334  lr=3.00e-04  dt=  36.7ms  words=8,609,792
[E01  1052/1548 G   1051|CLM] train=6.0483  mask=19.2%  norm=0.632  lr=3.00e-04  dt=  36.5ms  words=8,617,984
[E01  1053/1548 G   1052|CLM] train=2.7950  mask=19.2%  norm=0.755  lr=3.00e-04  dt=  36.7ms  words=8,626,176
[E01  1054/1548 G   1053|CLM] train=4.7845  mask=19.1%  norm=0.752  lr=3.00e-04  dt=  36.6ms  words=8,634,368
[E01  1055/1548 G   1054|CLM] train=3.0387  mask=19.1%  norm=0.826  lr=3.00e-04  dt=  36.6ms  words=8,642,560
[E01  1056/1548 G   1055|CLM] train=5.4453  mask=19.1%  norm=0.940  lr=3.00e-04  dt=  37.0ms  words=8,650,752
[E01  1057/1548 G   1056|CLM] train=3.0192  mask=19.1%  norm=0.683  lr=3.00e-04  dt=  36.8ms  words=8,658,944
[E01  1058/1548 G   1057|CLM] train=4.9642  mask=19.1%  norm=0.683  lr=3.00e-04  dt=  37.0ms  words=8,667,136
[E01  1059/1548 G   1058|CLM] train=5.1592  mask=19.1%  norm=0.734  lr=3.00e-04  dt=  37.1ms  words=8,675,328
[E01  1060/1548 G   1059|CLM] train=5.1826  mask=19.1%  norm=0.599  lr=3.00e-04  dt=  36.8ms  words=8,683,520
[E01  1061/1548 G   1060|CLM] train=4.8096  mask=19.1%  norm=0.688  lr=3.00e-04  dt=  36.6ms  words=8,691,712
[E01  1062/1548 G   1061|CLM] train=3.0899  mask=19.1%  norm=0.885  lr=3.00e-04  dt=  36.4ms  words=8,699,904
[E01  1063/1548 G   1062|CLM] train=4.8959  mask=19.1%  norm=0.702  lr=3.00e-04  dt=  36.8ms  words=8,708,096
[E01  1064/1548 G   1063|CLM] train=5.9051  mask=19.1%  norm=0.863  lr=3.00e-04  dt=  37.2ms  words=8,716,288
[E01  1065/1548 G   1064|CLM] train=4.7935  mask=19.1%  norm=0.809  lr=3.00e-04  dt=  37.1ms  words=8,724,480
[E01  1066/1548 G   1065|CLM] train=4.7740  mask=19.1%  norm=0.681  lr=3.00e-04  dt=  36.6ms  words=8,732,672
[E01  1067/1548 G   1066|CLM] train=3.1115  mask=19.1%  norm=0.737  lr=3.00e-04  dt=  36.8ms  words=8,740,864
[E01  1068/1548 G   1067|CLM] train=4.8012  mask=19.1%  norm=0.714  lr=3.00e-04  dt=  36.5ms  words=8,749,056
[E01  1069/1548 G   1068|CLM] train=5.7213  mask=19.1%  norm=0.906  lr=3.00e-04  dt=  36.6ms  words=8,757,248
[E01  1070/1548 G   1069|CLM] train=6.0275  mask=19.1%  norm=1.136  lr=3.00e-04  dt=  36.6ms  words=8,765,440
[E01  1071/1548 G   1070|CLM] train=5.2813  mask=19.1%  norm=0.944  lr=3.00e-04  dt=  37.0ms  words=8,773,632
[E01  1072/1548 G   1071|CLM] train=3.1041  mask=19.1%  norm=0.671  lr=3.00e-04  dt=  37.5ms  words=8,781,824
[E01  1073/1548 G   1072|CLM] train=4.9964  mask=19.1%  norm=0.981  lr=3.00e-04  dt=  37.1ms  words=8,790,016
[E01  1074/1548 G   1073|CLM] train=6.8998  mask=19.1%  norm=9.928  lr=3.00e-04  dt=  37.3ms  words=8,798,208
[E01  1075/1548 G   1074|CLM] train=3.9398  mask=19.1%  norm=1.403  lr=3.00e-04  dt=  37.1ms  words=8,806,400
[E01  1076/1548 G   1075|CLM] train=5.8787  mask=19.1%  norm=2.699  lr=3.00e-04  dt=  38.2ms  words=8,814,592
[E01  1077/1548 G   1076|CLM] train=4.8397  mask=19.1%  norm=0.887  lr=3.00e-04  dt=  39.5ms  words=8,822,784
[E01  1078/1548 G   1077|CLM] train=5.0620  mask=19.1%  norm=0.641  lr=3.00e-04  dt=  37.4ms  words=8,830,976
[E01  1079/1548 G   1078|CLM] train=5.3302  mask=19.1%  norm=0.859  lr=3.00e-04  dt=  37.4ms  words=8,839,168
[E01  1080/1548 G   1079|CLM] train=5.5726  mask=19.1%  norm=1.128  lr=3.00e-04  dt=  37.5ms  words=8,847,360
[E01  1081/1548 G   1080|CLM] train=5.7949  mask=19.1%  norm=1.306  lr=3.00e-04  dt=  38.6ms  words=8,855,552
[E01  1082/1548 G   1081|CLM] train=3.6535  mask=19.1%  norm=0.793  lr=3.00e-04  dt=  38.3ms  words=8,863,744
[E01  1083/1548 G   1082|CLM] train=5.9502  mask=19.1%  norm=0.895  lr=3.00e-04  dt=  37.8ms  words=8,871,936
[E01  1084/1548 G   1083|CLM] train=5.7245  mask=19.1%  norm=0.836  lr=3.00e-04  dt=  38.2ms  words=8,880,128
[E01  1085/1548 G   1084|CLM] train=5.7776  mask=19.1%  norm=0.846  lr=3.00e-04  dt=  38.0ms  words=8,888,320
[E01  1086/1548 G   1085|CLM] train=5.9120  mask=19.1%  norm=0.656  lr=3.00e-04  dt=  38.7ms  words=8,896,512
[E01  1087/1548 G   1086|CLM] train=5.1443  mask=19.1%  norm=1.255  lr=3.00e-04  dt=  38.1ms  words=8,904,704
[E01  1088/1548 G   1087|CLM] train=4.9228  mask=19.1%  norm=0.880  lr=3.00e-04  dt=  38.6ms  words=8,912,896
[E01  1089/1548 G   1088|CLM] train=4.3159  mask=19.1%  norm=0.827  lr=3.00e-04  dt=  38.2ms  words=8,921,088
[E01  1090/1548 G   1089|CLM] train=4.8722  mask=19.1%  norm=0.542  lr=3.00e-04  dt=  38.7ms  words=8,929,280
[E01  1091/1548 G   1090|CLM] train=5.6892  mask=19.1%  norm=1.533  lr=3.00e-04  dt=  38.3ms  words=8,937,472
[E01  1092/1548 G   1091|CLM] train=5.5604  mask=19.1%  norm=0.885  lr=3.00e-04  dt=  37.8ms  words=8,945,664
[E01  1093/1548 G   1092|CLM] train=5.6288  mask=19.1%  norm=0.911  lr=3.00e-04  dt=  38.3ms  words=8,953,856
[E01  1094/1548 G   1093|CLM] train=3.1321  mask=19.1%  norm=1.691  lr=3.00e-04  dt=  37.6ms  words=8,962,048
[E01  1095/1548 G   1094|CLM] train=4.9793  mask=19.1%  norm=0.898  lr=3.00e-04  dt=  38.5ms  words=8,970,240
[E01  1096/1548 G   1095|CLM] train=5.4887  mask=19.1%  norm=0.754  lr=3.00e-04  dt=  38.4ms  words=8,978,432
[E01  1097/1548 G   1096|CLM] train=4.3229  mask=19.1%  norm=0.634  lr=3.00e-04  dt=  38.1ms  words=8,986,624
[E01  1098/1548 G   1097|CLM] train=6.4970  mask=19.1%  norm=1.063  lr=3.00e-04  dt=  39.3ms  words=8,994,816
[E01  1099/1548 G   1098|CLM] train=4.9989  mask=19.1%  norm=1.561  lr=3.00e-04  dt=  39.8ms  words=9,003,008

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_9M'...
[Checkpoint] Checkpoint 'chck_9M' successfully saved.
[E01  1100/1548 G   1099|CLM] train=3.3589  mask=19.1%  norm=0.983  lr=3.00e-04  dt=  39.6ms  words=9,011,200
[E01  1101/1548 G   1100|CLM] train=3.5425  mask=19.1%  norm=0.792  lr=3.00e-04  dt=  39.1ms  words=9,019,392
[E01  1102/1548 G   1101|CLM] train=3.3838  mask=19.1%  norm=0.664  lr=3.00e-04  dt=  38.8ms  words=9,027,584
[E01  1103/1548 G   1102|CLM] train=5.4262  mask=19.1%  norm=1.180  lr=3.00e-04  dt=  39.3ms  words=9,035,776
[E01  1104/1548 G   1103|CLM] train=6.0514  mask=19.1%  norm=0.863  lr=3.00e-04  dt=  38.8ms  words=9,043,968
[E01  1105/1548 G   1104|CLM] train=4.6242  mask=19.1%  norm=0.770  lr=3.00e-04  dt=  38.7ms  words=9,052,160
[E01  1106/1548 G   1105|CLM] train=4.8167  mask=19.1%  norm=2.268  lr=3.00e-04  dt=  38.9ms  words=9,060,352
[E01  1107/1548 G   1106|CLM] train=5.1008  mask=19.1%  norm=0.808  lr=3.00e-04  dt=  39.0ms  words=9,068,544
[E01  1108/1548 G   1107|CLM] train=5.0984  mask=19.1%  norm=0.956  lr=3.00e-04  dt=  38.2ms  words=9,076,736
[E01  1109/1548 G   1108|CLM] train=3.5202  mask=19.1%  norm=6.692  lr=3.00e-04  dt=  38.0ms  words=9,084,928
[E01  1110/1548 G   1109|CLM] train=5.4962  mask=19.1%  norm=0.826  lr=2.99e-04  dt=  38.1ms  words=9,093,120
[E01  1111/1548 G   1110|CLM] train=3.4519  mask=19.1%  norm=1.451  lr=2.99e-04  dt=  38.5ms  words=9,101,312
[E01  1112/1548 G   1111|CLM] train=5.0967  mask=19.1%  norm=0.588  lr=2.99e-04  dt=  38.0ms  words=9,109,504
[E01  1113/1548 G   1112|CLM] train=3.2099  mask=19.1%  norm=1.113  lr=2.99e-04  dt=  37.9ms  words=9,117,696
[E01  1114/1548 G   1113|CLM] train=5.8013  mask=19.1%  norm=0.882  lr=2.99e-04  dt=  36.5ms  words=9,125,888
[E01  1115/1548 G   1114|CLM] train=4.9156  mask=19.1%  norm=0.663  lr=2.99e-04  dt=  36.7ms  words=9,134,080
[E01  1116/1548 G   1115|CLM] train=2.8623  mask=19.1%  norm=0.740  lr=2.99e-04  dt=  36.5ms  words=9,142,272
[E01  1117/1548 G   1116|CLM] train=2.8648  mask=19.1%  norm=0.655  lr=2.99e-04  dt=  36.6ms  words=9,150,464
[E01  1118/1548 G   1117|CLM] train=4.8354  mask=19.1%  norm=0.972  lr=2.99e-04  dt=  36.6ms  words=9,158,656
[E01  1119/1548 G   1118|CLM] train=4.8883  mask=19.1%  norm=0.758  lr=2.99e-04  dt=  37.6ms  words=9,166,848
[E01  1120/1548 G   1119|CLM] train=5.0418  mask=19.1%  norm=0.648  lr=2.99e-04  dt=  40.7ms  words=9,175,040
[E01  1121/1548 G   1120|CLM] train=5.0516  mask=19.1%  norm=0.701  lr=2.99e-04  dt=  41.4ms  words=9,183,232
[E01  1122/1548 G   1121|CLM] train=3.2351  mask=19.1%  norm=1.236  lr=2.99e-04  dt=  46.1ms  words=9,191,424
[E01  1123/1548 G   1122|CLM] train=6.5582  mask=19.1%  norm=1.508  lr=2.99e-04  dt=  43.1ms  words=9,199,616
[E01  1124/1548 G   1123|CLM] train=3.4724  mask=19.1%  norm=1.554  lr=2.99e-04  dt=  45.3ms  words=9,207,808
[E01  1125/1548 G   1124|CLM] train=4.6036  mask=19.1%  norm=0.655  lr=2.99e-04  dt=  37.9ms  words=9,216,000
[E01  1126/1548 G   1125|CLM] train=3.0905  mask=19.1%  norm=0.962  lr=2.99e-04  dt=  41.2ms  words=9,224,192
[E01  1127/1548 G   1126|CLM] train=5.5124  mask=19.1%  norm=1.062  lr=2.99e-04  dt=  40.7ms  words=9,232,384
[E01  1128/1548 G   1127|CLM] train=5.4428  mask=19.1%  norm=0.709  lr=2.99e-04  dt=  36.9ms  words=9,240,576
[E01  1129/1548 G   1128|CLM] train=5.8224  mask=19.1%  norm=0.693  lr=2.99e-04  dt=  50.0ms  words=9,248,768
[E01  1130/1548 G   1129|CLM] train=6.0510  mask=19.1%  norm=0.646  lr=2.99e-04  dt=  36.7ms  words=9,256,960
[E01  1131/1548 G   1130|CLM] train=4.9808  mask=19.1%  norm=0.582  lr=2.99e-04  dt=  48.4ms  words=9,265,152
[E01  1132/1548 G   1131|CLM] train=5.4859  mask=19.1%  norm=0.933  lr=2.99e-04  dt=  44.4ms  words=9,273,344
[E01  1133/1548 G   1132|CLM] train=5.8167  mask=19.1%  norm=0.685  lr=2.99e-04  dt=  44.9ms  words=9,281,536
[E01  1134/1548 G   1133|CLM] train=4.1833  mask=19.1%  norm=0.829  lr=2.99e-04  dt=  45.5ms  words=9,289,728
[E01  1135/1548 G   1134|CLM] train=3.5454  mask=19.1%  norm=1.229  lr=2.99e-04  dt=  36.7ms  words=9,297,920
[E01  1136/1548 G   1135|CLM] train=4.9074  mask=19.1%  norm=0.705  lr=2.99e-04  dt=  37.4ms  words=9,306,112
[E01  1137/1548 G   1136|CLM] train=3.3771  mask=19.1%  norm=0.918  lr=2.99e-04  dt=  41.7ms  words=9,314,304
[E01  1138/1548 G   1137|CLM] train=3.1381  mask=19.1%  norm=0.909  lr=2.99e-04  dt=  40.7ms  words=9,322,496
[E01  1139/1548 G   1138|CLM] train=3.0364  mask=19.1%  norm=0.634  lr=2.99e-04  dt=  41.9ms  words=9,330,688
[E01  1140/1548 G   1139|CLM] train=5.8374  mask=19.1%  norm=1.202  lr=2.99e-04  dt=  38.9ms  words=9,338,880
[E01  1141/1548 G   1140|CLM] train=5.4908  mask=19.1%  norm=0.873  lr=2.99e-04  dt=  36.5ms  words=9,347,072
[E01  1142/1548 G   1141|CLM] train=3.1477  mask=19.1%  norm=1.323  lr=2.99e-04  dt=  36.5ms  words=9,355,264
[E01  1143/1548 G   1142|CLM] train=4.8573  mask=19.1%  norm=1.094  lr=2.99e-04  dt=  40.3ms  words=9,363,456
[E01  1144/1548 G   1143|CLM] train=5.2304  mask=19.1%  norm=0.876  lr=2.99e-04  dt=  37.0ms  words=9,371,648
[E01  1145/1548 G   1144|CLM] train=4.8217  mask=19.1%  norm=0.638  lr=2.99e-04  dt=  36.8ms  words=9,379,840
[E01  1146/1548 G   1145|CLM] train=4.6769  mask=19.1%  norm=0.672  lr=2.99e-04  dt=  38.4ms  words=9,388,032
[E01  1147/1548 G   1146|CLM] train=4.7591  mask=19.1%  norm=0.806  lr=2.99e-04  dt=  38.3ms  words=9,396,224
[E01  1148/1548 G   1147|CLM] train=6.8038  mask=19.1%  norm=1.940  lr=2.99e-04  dt=  37.3ms  words=9,404,416
[E01  1149/1548 G   1148|CLM] train=3.5133  mask=19.1%  norm=0.658  lr=2.99e-04  dt=  37.3ms  words=9,412,608
[E01  1150/1548 G   1149|CLM] train=5.7139  mask=19.1%  norm=0.805  lr=2.99e-04  dt=  37.0ms  words=9,420,800
[E01  1151/1548 G   1150|CLM] train=3.0779  mask=19.1%  norm=1.395  lr=2.99e-04  dt=  36.7ms  words=9,428,992
[E01  1152/1548 G   1151|CLM] train=5.3635  mask=19.1%  norm=1.206  lr=2.99e-04  dt=  37.3ms  words=9,437,184
[E01  1153/1548 G   1152|CLM] train=4.9483  mask=19.1%  norm=0.741  lr=2.99e-04  dt=  37.5ms  words=9,445,376
[E01  1154/1548 G   1153|CLM] train=2.9420  mask=19.1%  norm=0.717  lr=2.99e-04  dt=  37.1ms  words=9,453,568
[E01  1155/1548 G   1154|CLM] train=5.7643  mask=19.1%  norm=0.995  lr=2.99e-04  dt=  37.3ms  words=9,461,760
[E01  1156/1548 G   1155|CLM] train=4.1071  mask=19.1%  norm=0.825  lr=2.99e-04  dt=  36.9ms  words=9,469,952
[E01  1157/1548 G   1156|CLM] train=5.6144  mask=19.1%  norm=0.836  lr=2.99e-04  dt=  36.8ms  words=9,478,144
[E01  1158/1548 G   1157|CLM] train=4.9008  mask=19.1%  norm=0.808  lr=2.99e-04  dt=  36.8ms  words=9,486,336
[E01  1159/1548 G   1158|CLM] train=5.7622  mask=19.1%  norm=0.676  lr=2.99e-04  dt=  36.8ms  words=9,494,528
[E01  1160/1548 G   1159|CLM] train=2.9824  mask=19.1%  norm=0.612  lr=2.99e-04  dt=  36.9ms  words=9,502,720
[E01  1161/1548 G   1160|CLM] train=3.4463  mask=19.1%  norm=0.837  lr=2.99e-04  dt=  36.9ms  words=9,510,912
[E01  1162/1548 G   1161|CLM] train=3.3529  mask=19.1%  norm=0.630  lr=2.99e-04  dt=  37.0ms  words=9,519,104
[E01  1163/1548 G   1162|CLM] train=5.4234  mask=19.1%  norm=1.047  lr=2.99e-04  dt=  36.8ms  words=9,527,296
[E01  1164/1548 G   1163|CLM] train=3.6429  mask=19.1%  norm=0.852  lr=2.99e-04  dt=  36.8ms  words=9,535,488
[E01  1165/1548 G   1164|CLM] train=5.6639  mask=19.1%  norm=0.900  lr=2.99e-04  dt=  45.4ms  words=9,543,680
[E01  1166/1548 G   1165|CLM] train=3.3773  mask=19.1%  norm=0.659  lr=2.99e-04  dt=  40.0ms  words=9,551,872
[E01  1167/1548 G   1166|CLM] train=4.5039  mask=19.1%  norm=0.790  lr=2.99e-04  dt=  38.6ms  words=9,560,064
[E01  1168/1548 G   1167|CLM] train=4.9433  mask=19.1%  norm=0.834  lr=2.99e-04  dt=  37.1ms  words=9,568,256
[E01  1169/1548 G   1168|CLM] train=5.0286  mask=19.1%  norm=0.672  lr=2.99e-04  dt=  36.6ms  words=9,576,448
[E01  1170/1548 G   1169|CLM] train=2.9478  mask=19.1%  norm=0.817  lr=2.99e-04  dt=  37.0ms  words=9,584,640
[E01  1171/1548 G   1170|CLM] train=3.1931  mask=19.1%  norm=0.986  lr=2.99e-04  dt=  38.2ms  words=9,592,832
[E01  1172/1548 G   1171|CLM] train=4.8510  mask=19.1%  norm=1.349  lr=2.99e-04  dt=  36.5ms  words=9,601,024
[E01  1173/1548 G   1172|CLM] train=5.3147  mask=19.1%  norm=0.797  lr=2.99e-04  dt=  36.4ms  words=9,609,216
[E01  1174/1548 G   1173|CLM] train=5.2960  mask=19.1%  norm=1.571  lr=2.99e-04  dt=  36.5ms  words=9,617,408
[E01  1175/1548 G   1174|CLM] train=3.1851  mask=19.1%  norm=1.185  lr=2.99e-04  dt=  36.9ms  words=9,625,600
[E01  1176/1548 G   1175|CLM] train=3.0959  mask=19.1%  norm=1.023  lr=2.99e-04  dt=  36.9ms  words=9,633,792
[E01  1177/1548 G   1176|CLM] train=4.8362  mask=19.1%  norm=1.229  lr=2.99e-04  dt=  36.7ms  words=9,641,984
[E01  1178/1548 G   1177|CLM] train=5.1260  mask=19.0%  norm=1.066  lr=2.99e-04  dt=  36.6ms  words=9,650,176
[E01  1179/1548 G   1178|CLM] train=5.8350  mask=19.0%  norm=0.964  lr=2.99e-04  dt=  36.6ms  words=9,658,368
[E01  1180/1548 G   1179|CLM] train=4.5703  mask=19.0%  norm=0.791  lr=2.99e-04  dt=  36.9ms  words=9,666,560
[E01  1181/1548 G   1180|CLM] train=4.8945  mask=19.0%  norm=1.027  lr=2.99e-04  dt=  36.8ms  words=9,674,752
[E01  1182/1548 G   1181|CLM] train=5.4190  mask=19.0%  norm=1.174  lr=2.99e-04  dt=  36.6ms  words=9,682,944
[E01  1183/1548 G   1182|CLM] train=2.8787  mask=19.0%  norm=1.186  lr=2.99e-04  dt=  36.6ms  words=9,691,136
[E01  1184/1548 G   1183|CLM] train=4.5281  mask=19.0%  norm=0.711  lr=2.99e-04  dt=  36.9ms  words=9,699,328
[E01  1185/1548 G   1184|CLM] train=3.2744  mask=19.0%  norm=1.096  lr=2.99e-04  dt=  36.7ms  words=9,707,520
[E01  1186/1548 G   1185|CLM] train=3.6010  mask=19.0%  norm=0.758  lr=2.99e-04  dt=  36.7ms  words=9,715,712
[E01  1187/1548 G   1186|CLM] train=5.2820  mask=19.0%  norm=0.845  lr=2.99e-04  dt=  36.6ms  words=9,723,904
[E01  1188/1548 G   1187|CLM] train=4.9882  mask=19.0%  norm=0.914  lr=2.99e-04  dt=  36.7ms  words=9,732,096
[E01  1189/1548 G   1188|CLM] train=3.0027  mask=19.0%  norm=0.975  lr=2.99e-04  dt=  36.7ms  words=9,740,288
[E01  1190/1548 G   1189|CLM] train=5.6640  mask=19.0%  norm=1.161  lr=2.99e-04  dt=  36.8ms  words=9,748,480
[E01  1191/1548 G   1190|CLM] train=5.3195  mask=19.0%  norm=0.906  lr=2.99e-04  dt=  36.7ms  words=9,756,672
[E01  1192/1548 G   1191|CLM] train=3.0517  mask=19.0%  norm=0.820  lr=2.99e-04  dt=  36.6ms  words=9,764,864
[E01  1193/1548 G   1192|CLM] train=4.8524  mask=19.0%  norm=0.961  lr=2.99e-04  dt=  36.5ms  words=9,773,056
[E01  1194/1548 G   1193|CLM] train=5.3131  mask=19.0%  norm=1.380  lr=2.99e-04  dt=  36.4ms  words=9,781,248
[E01  1195/1548 G   1194|CLM] train=2.9253  mask=19.0%  norm=0.643  lr=2.99e-04  dt=  36.5ms  words=9,789,440
[E01  1196/1548 G   1195|CLM] train=5.3364  mask=19.0%  norm=0.933  lr=2.99e-04  dt=  36.8ms  words=9,797,632
[E01  1197/1548 G   1196|CLM] train=5.1929  mask=19.0%  norm=0.969  lr=2.99e-04  dt=  36.5ms  words=9,805,824
[E01  1198/1548 G   1197|CLM] train=4.3517  mask=19.0%  norm=0.708  lr=2.99e-04  dt=  36.7ms  words=9,814,016
[E01  1199/1548 G   1198|CLM] train=3.1512  mask=19.0%  norm=0.800  lr=2.99e-04  dt=  36.5ms  words=9,822,208
[E01  1200/1548 G   1199|CLM] train=6.7470  mask=19.0%  norm=7.586  lr=2.99e-04  dt=  36.7ms  words=9,830,400
[E01  1201/1548 G   1200|CLM] train=4.9507  mask=19.0%  norm=0.907  lr=2.99e-04  dt=  37.3ms  words=9,838,592
[E01  1202/1548 G   1201|CLM] train=3.5617  mask=19.0%  norm=0.631  lr=2.99e-04  dt=  37.1ms  words=9,846,784
[E01  1203/1548 G   1202|CLM] train=4.9506  mask=19.0%  norm=0.739  lr=2.99e-04  dt=  36.8ms  words=9,854,976
[E01  1204/1548 G   1203|CLM] train=3.1255  mask=19.0%  norm=0.843  lr=2.99e-04  dt=  36.7ms  words=9,863,168
[E01  1205/1548 G   1204|CLM] train=5.4153  mask=19.0%  norm=0.694  lr=2.99e-04  dt=  36.5ms  words=9,871,360
[E01  1206/1548 G   1205|CLM] train=2.9537  mask=19.0%  norm=0.852  lr=2.99e-04  dt=  36.7ms  words=9,879,552
[E01  1207/1548 G   1206|CLM] train=3.3905  mask=19.0%  norm=0.970  lr=2.99e-04  dt=  36.6ms  words=9,887,744
[E01  1208/1548 G   1207|CLM] train=4.6673  mask=19.0%  norm=0.734  lr=2.99e-04  dt=  36.7ms  words=9,895,936
[E01  1209/1548 G   1208|CLM] train=3.6303  mask=19.0%  norm=0.704  lr=2.99e-04  dt=  36.7ms  words=9,904,128
[E01  1210/1548 G   1209|CLM] train=5.2058  mask=19.0%  norm=1.190  lr=2.99e-04  dt=  36.7ms  words=9,912,320
[E01  1211/1548 G   1210|CLM] train=5.1370  mask=19.0%  norm=0.636  lr=2.99e-04  dt=  37.1ms  words=9,920,512
[E01  1212/1548 G   1211|CLM] train=5.3772  mask=19.0%  norm=0.972  lr=2.99e-04  dt=  36.5ms  words=9,928,704
[E01  1213/1548 G   1212|CLM] train=2.9550  mask=19.0%  norm=0.813  lr=2.99e-04  dt=  36.6ms  words=9,936,896
[E01  1214/1548 G   1213|CLM] train=6.6782  mask=19.0%  norm=1.859  lr=2.99e-04  dt=  37.2ms  words=9,945,088
[E01  1215/1548 G   1214|CLM] train=5.9672  mask=19.0%  norm=1.188  lr=2.99e-04  dt=  37.5ms  words=9,953,280
[E01  1216/1548 G   1215|CLM] train=5.1325  mask=19.0%  norm=0.996  lr=2.99e-04  dt=  37.6ms  words=9,961,472
[E01  1217/1548 G   1216|CLM] train=2.8257  mask=19.0%  norm=0.677  lr=2.99e-04  dt=  36.7ms  words=9,969,664
[E01  1218/1548 G   1217|CLM] train=6.4617  mask=19.0%  norm=2.935  lr=2.99e-04  dt=  36.8ms  words=9,977,856
[E01  1219/1548 G   1218|CLM] train=5.1360  mask=19.0%  norm=0.900  lr=2.99e-04  dt=  36.6ms  words=9,986,048
[E01  1220/1548 G   1219|CLM] train=3.2419  mask=19.0%  norm=0.737  lr=2.99e-04  dt=  36.5ms  words=9,994,240
[E01  1221/1548 G   1220|CLM] train=3.3124  mask=19.0%  norm=0.831  lr=2.99e-04  dt=  36.5ms  words=10,002,432

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_10M'...
[Checkpoint] Checkpoint 'chck_10M' successfully saved.
[E01  1222/1548 G   1221|CLM] train=5.5744  mask=19.0%  norm=0.867  lr=2.99e-04  dt=  37.2ms  words=10,010,624
[E01  1223/1548 G   1222|CLM] train=4.9798  mask=19.0%  norm=0.920  lr=2.99e-04  dt=  38.5ms  words=10,018,816
[E01  1224/1548 G   1223|CLM] train=3.0098  mask=19.0%  norm=0.729  lr=2.99e-04  dt=  38.5ms  words=10,027,008
[E01  1225/1548 G   1224|CLM] train=4.5581  mask=19.0%  norm=0.734  lr=2.99e-04  dt=  38.1ms  words=10,035,200
[E01  1226/1548 G   1225|CLM] train=3.2242  mask=19.0%  norm=0.718  lr=2.99e-04  dt=  37.9ms  words=10,043,392
[E01  1227/1548 G   1226|CLM] train=2.9405  mask=19.0%  norm=0.774  lr=2.99e-04  dt=  36.9ms  words=10,051,584
[E01  1228/1548 G   1227|CLM] train=3.3055  mask=19.0%  norm=0.735  lr=2.99e-04  dt=  37.4ms  words=10,059,776
[E01  1229/1548 G   1228|CLM] train=3.1775  mask=19.0%  norm=0.803  lr=2.99e-04  dt=  36.7ms  words=10,067,968
[E01  1230/1548 G   1229|CLM] train=6.0148  mask=19.0%  norm=1.128  lr=2.99e-04  dt=  37.3ms  words=10,076,160
[E01  1231/1548 G   1230|CLM] train=5.0267  mask=19.0%  norm=0.835  lr=2.99e-04  dt=  36.9ms  words=10,084,352
[E01  1232/1548 G   1231|CLM] train=5.0855  mask=19.0%  norm=1.138  lr=2.99e-04  dt=  37.0ms  words=10,092,544
[E01  1233/1548 G   1232|CLM] train=2.9767  mask=19.0%  norm=1.117  lr=2.99e-04  dt=  36.7ms  words=10,100,736
[E01  1234/1548 G   1233|CLM] train=5.4762  mask=19.0%  norm=1.058  lr=2.99e-04  dt=  37.0ms  words=10,108,928
[E01  1235/1548 G   1234|CLM] train=5.1439  mask=19.0%  norm=0.996  lr=2.99e-04  dt=  37.0ms  words=10,117,120
[E01  1236/1548 G   1235|CLM] train=5.6330  mask=19.0%  norm=0.863  lr=2.99e-04  dt=  36.9ms  words=10,125,312
[E01  1237/1548 G   1236|CLM] train=2.8830  mask=19.0%  norm=0.743  lr=2.99e-04  dt=  36.6ms  words=10,133,504
[E01  1238/1548 G   1237|CLM] train=3.0490  mask=19.0%  norm=0.718  lr=2.99e-04  dt=  36.7ms  words=10,141,696
[E01  1239/1548 G   1238|CLM] train=5.4921  mask=19.0%  norm=0.830  lr=2.99e-04  dt=  36.8ms  words=10,149,888
[E01  1240/1548 G   1239|CLM] train=5.3707  mask=19.0%  norm=1.319  lr=2.99e-04  dt=  36.8ms  words=10,158,080
[E01  1241/1548 G   1240|CLM] train=5.1132  mask=19.0%  norm=0.659  lr=2.99e-04  dt=  36.8ms  words=10,166,272
[E01  1242/1548 G   1241|CLM] train=5.3660  mask=19.0%  norm=0.791  lr=2.99e-04  dt=  36.8ms  words=10,174,464
[E01  1243/1548 G   1242|CLM] train=5.1291  mask=19.0%  norm=0.624  lr=2.99e-04  dt=  36.9ms  words=10,182,656
[E01  1244/1548 G   1243|CLM] train=3.0849  mask=19.0%  norm=0.809  lr=2.99e-04  dt=  36.5ms  words=10,190,848
[E01  1245/1548 G   1244|CLM] train=3.7872  mask=19.0%  norm=1.388  lr=2.99e-04  dt=  36.9ms  words=10,199,040
[E01  1246/1548 G   1245|CLM] train=5.6683  mask=19.0%  norm=0.837  lr=2.99e-04  dt=  36.7ms  words=10,207,232
[E01  1247/1548 G   1246|CLM] train=3.1445  mask=19.0%  norm=0.720  lr=2.99e-04  dt=  36.8ms  words=10,215,424
[E01  1248/1548 G   1247|CLM] train=2.8128  mask=19.0%  norm=0.674  lr=2.99e-04  dt=  36.4ms  words=10,223,616
[E01  1249/1548 G   1248|CLM] train=4.6458  mask=19.0%  norm=0.961  lr=2.99e-04  dt=  36.5ms  words=10,231,808
[E01  1250/1548 G   1249|CLM] train=5.2783  mask=19.0%  norm=0.911  lr=2.99e-04  dt=  36.8ms  words=10,240,000
[E01  1251/1548 G   1250|CLM] train=2.9614  mask=19.0%  norm=0.687  lr=2.99e-04  dt=  36.6ms  words=10,248,192
[E01  1252/1548 G   1251|CLM] train=4.9898  mask=19.0%  norm=0.692  lr=2.99e-04  dt=  36.5ms  words=10,256,384
[E01  1253/1548 G   1252|CLM] train=3.1300  mask=19.0%  norm=0.619  lr=2.99e-04  dt=  36.6ms  words=10,264,576
[E01  1254/1548 G   1253|CLM] train=2.8932  mask=19.0%  norm=0.530  lr=2.99e-04  dt=  36.5ms  words=10,272,768
[E01  1255/1548 G   1254|CLM] train=5.9239  mask=19.0%  norm=0.935  lr=2.99e-04  dt=  36.4ms  words=10,280,960
[E01  1256/1548 G   1255|CLM] train=2.9932  mask=19.0%  norm=0.616  lr=2.99e-04  dt=  36.7ms  words=10,289,152
[E01  1257/1548 G   1256|CLM] train=4.9021  mask=19.0%  norm=0.866  lr=2.99e-04  dt=  36.8ms  words=10,297,344
[E01  1258/1548 G   1257|CLM] train=5.2483  mask=19.0%  norm=0.677  lr=2.99e-04  dt=  37.7ms  words=10,305,536
[E01  1259/1548 G   1258|CLM] train=5.8298  mask=19.0%  norm=0.678  lr=2.99e-04  dt=  36.7ms  words=10,313,728
[E01  1260/1548 G   1259|CLM] train=6.3911  mask=19.0%  norm=3.882  lr=2.99e-04  dt=  37.1ms  words=10,321,920
[E01  1261/1548 G   1260|CLM] train=4.8442  mask=19.0%  norm=0.866  lr=2.99e-04  dt=  36.4ms  words=10,330,112
[E01  1262/1548 G   1261|CLM] train=5.5490  mask=19.0%  norm=0.682  lr=2.99e-04  dt=  36.7ms  words=10,338,304
[E01  1263/1548 G   1262|CLM] train=3.4593  mask=19.0%  norm=0.881  lr=2.99e-04  dt=  36.6ms  words=10,346,496
[E01  1264/1548 G   1263|CLM] train=2.9304  mask=19.0%  norm=0.875  lr=2.99e-04  dt=  36.5ms  words=10,354,688
[E01  1265/1548 G   1264|CLM] train=5.2364  mask=19.0%  norm=0.964  lr=2.99e-04  dt=  36.8ms  words=10,362,880
[E01  1266/1548 G   1265|CLM] train=4.7361  mask=19.0%  norm=2.788  lr=2.99e-04  dt=  36.6ms  words=10,371,072
[E01  1267/1548 G   1266|CLM] train=5.3563  mask=19.0%  norm=0.895  lr=2.99e-04  dt=  36.6ms  words=10,379,264
[E01  1268/1548 G   1267|CLM] train=5.5466  mask=19.0%  norm=0.865  lr=2.99e-04  dt=  36.7ms  words=10,387,456
[E01  1269/1548 G   1268|CLM] train=5.1035  mask=19.0%  norm=0.861  lr=2.99e-04  dt=  36.5ms  words=10,395,648
[E01  1270/1548 G   1269|CLM] train=5.1611  mask=19.0%  norm=0.995  lr=2.99e-04  dt=  36.5ms  words=10,403,840
[E01  1271/1548 G   1270|CLM] train=5.6341  mask=19.0%  norm=0.810  lr=2.99e-04  dt=  36.7ms  words=10,412,032
[E01  1272/1548 G   1271|CLM] train=4.7103  mask=19.0%  norm=1.081  lr=2.99e-04  dt=  36.6ms  words=10,420,224
[E01  1273/1548 G   1272|CLM] train=4.3997  mask=19.0%  norm=0.862  lr=2.99e-04  dt=  36.6ms  words=10,428,416
[E01  1274/1548 G   1273|CLM] train=5.9407  mask=19.0%  norm=0.974  lr=2.99e-04  dt=  36.4ms  words=10,436,608
[E01  1275/1548 G   1274|CLM] train=3.0615  mask=19.0%  norm=1.046  lr=2.99e-04  dt=  36.5ms  words=10,444,800
[E01  1276/1548 G   1275|CLM] train=6.5296  mask=19.0%  norm=1.120  lr=2.99e-04  dt=  36.5ms  words=10,452,992
[E01  1277/1548 G   1276|CLM] train=4.6330  mask=19.0%  norm=0.746  lr=2.99e-04  dt=  36.8ms  words=10,461,184
[E01  1278/1548 G   1277|CLM] train=5.4165  mask=19.0%  norm=0.908  lr=2.99e-04  dt=  36.6ms  words=10,469,376
[E01  1279/1548 G   1278|CLM] train=4.9346  mask=19.0%  norm=1.298  lr=2.99e-04  dt=  36.6ms  words=10,477,568
[E01  1280/1548 G   1279|CLM] train=3.1076  mask=19.0%  norm=0.782  lr=2.99e-04  dt=  36.6ms  words=10,485,760
[E01  1281/1548 G   1280|CLM] train=5.5382  mask=19.0%  norm=0.821  lr=2.99e-04  dt=  36.5ms  words=10,493,952
[E01  1282/1548 G   1281|CLM] train=3.3471  mask=19.0%  norm=0.713  lr=2.99e-04  dt=  36.5ms  words=10,502,144
[E01  1283/1548 G   1282|CLM] train=2.9064  mask=19.0%  norm=0.902  lr=2.99e-04  dt=  36.7ms  words=10,510,336
[E01  1284/1548 G   1283|CLM] train=2.9186  mask=19.0%  norm=0.535  lr=2.99e-04  dt=  36.8ms  words=10,518,528
[E01  1285/1548 G   1284|CLM] train=5.2682  mask=19.0%  norm=0.662  lr=2.99e-04  dt=  36.5ms  words=10,526,720
[E01  1286/1548 G   1285|CLM] train=3.4534  mask=19.0%  norm=0.665  lr=2.99e-04  dt=  36.6ms  words=10,534,912
[E01  1287/1548 G   1286|CLM] train=4.3907  mask=19.0%  norm=0.900  lr=2.99e-04  dt=  37.0ms  words=10,543,104
[E01  1288/1548 G   1287|CLM] train=2.9754  mask=19.0%  norm=0.882  lr=2.99e-04  dt=  36.7ms  words=10,551,296
[E01  1289/1548 G   1288|CLM] train=4.3128  mask=19.0%  norm=0.694  lr=2.99e-04  dt=  36.5ms  words=10,559,488
[E01  1290/1548 G   1289|CLM] train=3.2842  mask=19.0%  norm=0.618  lr=2.99e-04  dt=  36.6ms  words=10,567,680
[E01  1291/1548 G   1290|CLM] train=3.3540  mask=19.0%  norm=0.628  lr=2.99e-04  dt=  36.7ms  words=10,575,872
[E01  1292/1548 G   1291|CLM] train=4.7210  mask=19.0%  norm=0.725  lr=2.99e-04  dt=  36.8ms  words=10,584,064
[E01  1293/1548 G   1292|CLM] train=4.5921  mask=19.0%  norm=0.765  lr=2.99e-04  dt=  36.5ms  words=10,592,256
[E01  1294/1548 G   1293|CLM] train=4.6503  mask=19.0%  norm=0.575  lr=2.99e-04  dt=  36.7ms  words=10,600,448
[E01  1295/1548 G   1294|CLM] train=4.7360  mask=19.0%  norm=0.558  lr=2.99e-04  dt=  36.7ms  words=10,608,640
[E01  1296/1548 G   1295|CLM] train=4.7670  mask=19.0%  norm=0.476  lr=2.99e-04  dt=  36.5ms  words=10,616,832
[E01  1297/1548 G   1296|CLM] train=5.1306  mask=19.0%  norm=0.570  lr=2.99e-04  dt=  36.5ms  words=10,625,024
[E01  1298/1548 G   1297|CLM] train=4.5136  mask=19.0%  norm=0.495  lr=2.99e-04  dt=  36.7ms  words=10,633,216
[E01  1299/1548 G   1298|CLM] train=3.1314  mask=19.0%  norm=1.165  lr=2.99e-04  dt=  36.6ms  words=10,641,408
[E01  1300/1548 G   1299|CLM] train=3.0460  mask=19.0%  norm=0.860  lr=2.99e-04  dt=  36.6ms  words=10,649,600
[E01  1301/1548 G   1300|CLM] train=2.8037  mask=19.0%  norm=0.642  lr=2.99e-04  dt=  36.8ms  words=10,657,792
[E01  1302/1548 G   1301|CLM] train=6.8052  mask=18.9%  norm=1.398  lr=2.99e-04  dt=  36.4ms  words=10,665,984
[E01  1303/1548 G   1302|CLM] train=4.9187  mask=18.9%  norm=0.760  lr=2.99e-04  dt=  36.5ms  words=10,674,176
[E01  1304/1548 G   1303|CLM] train=4.6816  mask=18.9%  norm=0.883  lr=2.99e-04  dt=  36.5ms  words=10,682,368
[E01  1305/1548 G   1304|CLM] train=2.9096  mask=18.9%  norm=0.856  lr=2.99e-04  dt=  36.6ms  words=10,690,560
[E01  1306/1548 G   1305|CLM] train=5.1555  mask=18.9%  norm=0.632  lr=2.99e-04  dt=  36.7ms  words=10,698,752
[E01  1307/1548 G   1306|CLM] train=5.0589  mask=18.9%  norm=0.842  lr=2.99e-04  dt=  36.7ms  words=10,706,944
[E01  1308/1548 G   1307|CLM] train=5.2463  mask=18.9%  norm=1.108  lr=2.99e-04  dt=  36.6ms  words=10,715,136
[E01  1309/1548 G   1308|CLM] train=3.2950  mask=18.9%  norm=0.983  lr=2.99e-04  dt= 509.3ms  words=10,723,328
[E01  1310/1548 G   1309|CLM] train=5.9066  mask=18.9%  norm=0.826  lr=2.99e-04  dt=  37.7ms  words=10,731,520
[E01  1311/1548 G   1310|CLM] train=3.0035  mask=18.9%  norm=0.710  lr=2.99e-04  dt=  37.3ms  words=10,739,712
[E01  1312/1548 G   1311|CLM] train=4.8272  mask=18.9%  norm=0.902  lr=2.99e-04  dt=  37.3ms  words=10,747,904
[E01  1313/1548 G   1312|CLM] train=3.2133  mask=18.9%  norm=1.172  lr=2.99e-04  dt=  37.1ms  words=10,756,096
[E01  1314/1548 G   1313|CLM] train=5.3130  mask=18.9%  norm=0.744  lr=2.99e-04  dt=  37.1ms  words=10,764,288
[E01  1315/1548 G   1314|CLM] train=4.6400  mask=18.9%  norm=1.180  lr=2.99e-04  dt=  37.3ms  words=10,772,480
[E01  1316/1548 G   1315|CLM] train=6.2843  mask=18.9%  norm=1.022  lr=2.99e-04  dt=  48.3ms  words=10,780,672
[E01  1317/1548 G   1316|CLM] train=3.0079  mask=18.9%  norm=0.794  lr=2.99e-04  dt=  44.2ms  words=10,788,864
[E01  1318/1548 G   1317|CLM] train=4.6853  mask=18.9%  norm=0.769  lr=2.99e-04  dt=  42.3ms  words=10,797,056
[E01  1319/1548 G   1318|CLM] train=4.8155  mask=18.9%  norm=0.979  lr=2.99e-04  dt=  43.5ms  words=10,805,248
[E01  1320/1548 G   1319|CLM] train=5.4877  mask=18.9%  norm=0.890  lr=2.99e-04  dt=  41.6ms  words=10,813,440
[E01  1321/1548 G   1320|CLM] train=3.3541  mask=18.9%  norm=0.777  lr=2.99e-04  dt=  39.0ms  words=10,821,632
[E01  1322/1548 G   1321|CLM] train=4.2596  mask=18.9%  norm=0.888  lr=2.99e-04  dt=  41.1ms  words=10,829,824
[E01  1323/1548 G   1322|CLM] train=5.5245  mask=18.9%  norm=1.045  lr=2.99e-04  dt=  38.6ms  words=10,838,016
[E01  1324/1548 G   1323|CLM] train=3.4288  mask=18.9%  norm=1.046  lr=2.99e-04  dt=  42.2ms  words=10,846,208
[E01  1325/1548 G   1324|CLM] train=5.1709  mask=18.9%  norm=0.620  lr=2.99e-04  dt=  41.6ms  words=10,854,400
[E01  1326/1548 G   1325|CLM] train=5.1654  mask=18.9%  norm=0.789  lr=2.99e-04  dt=  42.7ms  words=10,862,592
[E01  1327/1548 G   1326|CLM] train=3.1437  mask=18.9%  norm=0.679  lr=2.99e-04  dt=  38.8ms  words=10,870,784
[E01  1328/1548 G   1327|CLM] train=4.7526  mask=18.9%  norm=0.711  lr=2.99e-04  dt=  41.3ms  words=10,878,976
[E01  1329/1548 G   1328|CLM] train=4.6491  mask=18.9%  norm=1.004  lr=2.99e-04  dt=  43.9ms  words=10,887,168
[E01  1330/1548 G   1329|CLM] train=5.4552  mask=18.9%  norm=0.733  lr=2.99e-04  dt=  43.0ms  words=10,895,360
[E01  1331/1548 G   1330|CLM] train=5.3168  mask=18.9%  norm=0.862  lr=2.99e-04  dt=  38.5ms  words=10,903,552
[E01  1332/1548 G   1331|CLM] train=3.2275  mask=18.9%  norm=0.487  lr=2.99e-04  dt=  44.1ms  words=10,911,744
[E01  1333/1548 G   1332|CLM] train=3.0927  mask=18.9%  norm=0.887  lr=2.99e-04  dt=  42.3ms  words=10,919,936
[E01  1334/1548 G   1333|CLM] train=4.5556  mask=18.9%  norm=0.580  lr=2.99e-04  dt=  41.9ms  words=10,928,128
[E01  1335/1548 G   1334|CLM] train=2.8719  mask=18.9%  norm=0.604  lr=2.99e-04  dt=  42.4ms  words=10,936,320
[E01  1336/1548 G   1335|CLM] train=3.0692  mask=18.9%  norm=0.902  lr=2.99e-04  dt=  42.7ms  words=10,944,512
[E01  1337/1548 G   1336|CLM] train=4.4629  mask=18.9%  norm=0.974  lr=2.98e-04  dt=  37.1ms  words=10,952,704
[E01  1338/1548 G   1337|CLM] train=4.9586  mask=18.9%  norm=0.762  lr=2.98e-04  dt=  36.8ms  words=10,960,896
[E01  1339/1548 G   1338|CLM] train=4.2740  mask=18.9%  norm=0.663  lr=2.98e-04  dt=  37.3ms  words=10,969,088
[E01  1340/1548 G   1339|CLM] train=4.8303  mask=18.9%  norm=0.644  lr=2.98e-04  dt=  36.9ms  words=10,977,280
[E01  1341/1548 G   1340|CLM] train=5.0821  mask=18.9%  norm=0.724  lr=2.98e-04  dt=  37.0ms  words=10,985,472
[E01  1342/1548 G   1341|CLM] train=3.3225  mask=18.9%  norm=1.164  lr=2.98e-04  dt=  41.9ms  words=10,993,664
[E01  1343/1548 G   1342|CLM] train=4.5020  mask=18.9%  norm=0.816  lr=2.98e-04  dt=  43.3ms  words=11,001,856
[E01  1344/1548 G   1343|CLM] train=3.1067  mask=18.9%  norm=0.940  lr=2.98e-04  dt=  43.6ms  words=11,010,048
[E01  1345/1548 G   1344|CLM] train=5.5054  mask=18.9%  norm=0.598  lr=2.98e-04  dt=  41.5ms  words=11,018,240
[E01  1346/1548 G   1345|CLM] train=4.7733  mask=18.9%  norm=0.629  lr=2.98e-04  dt=  41.7ms  words=11,026,432
[E01  1347/1548 G   1346|CLM] train=4.5653  mask=18.9%  norm=0.725  lr=2.98e-04  dt=  41.0ms  words=11,034,624
[E01  1348/1548 G   1347|CLM] train=3.3039  mask=18.9%  norm=0.930  lr=2.98e-04  dt=  38.1ms  words=11,042,816
[E01  1349/1548 G   1348|CLM] train=5.1565  mask=18.9%  norm=0.580  lr=2.98e-04  dt=  39.1ms  words=11,051,008
[E01  1350/1548 G   1349|CLM] train=3.0748  mask=18.9%  norm=0.704  lr=2.98e-04  dt=  48.3ms  words=11,059,200
[E01  1351/1548 G   1350|CLM] train=4.7022  mask=18.9%  norm=1.460  lr=2.98e-04  dt=  47.5ms  words=11,067,392
[E01  1352/1548 G   1351|CLM] train=6.7454  mask=18.9%  norm=1.522  lr=2.98e-04  dt=  46.7ms  words=11,075,584
[E01  1353/1548 G   1352|CLM] train=2.8253  mask=18.9%  norm=1.136  lr=2.98e-04  dt=  47.4ms  words=11,083,776
[E01  1354/1548 G   1353|CLM] train=4.6804  mask=18.9%  norm=1.070  lr=2.98e-04  dt=  46.4ms  words=11,091,968
[E01  1355/1548 G   1354|CLM] train=2.8231  mask=18.9%  norm=0.801  lr=2.98e-04  dt=  50.8ms  words=11,100,160
[E01  1356/1548 G   1355|CLM] train=3.1431  mask=18.9%  norm=0.992  lr=2.98e-04  dt=  41.6ms  words=11,108,352
[E01  1357/1548 G   1356|CLM] train=3.2392  mask=18.9%  norm=0.687  lr=2.98e-04  dt=  37.1ms  words=11,116,544
[E01  1358/1548 G   1357|CLM] train=5.3317  mask=18.9%  norm=0.745  lr=2.98e-04  dt=  37.0ms  words=11,124,736
[E01  1359/1548 G   1358|CLM] train=3.2079  mask=18.9%  norm=0.820  lr=2.98e-04  dt=  37.0ms  words=11,132,928
[E01  1360/1548 G   1359|CLM] train=5.4446  mask=18.9%  norm=0.976  lr=2.98e-04  dt=  36.8ms  words=11,141,120
[E01  1361/1548 G   1360|CLM] train=5.8651  mask=18.9%  norm=0.750  lr=2.98e-04  dt=  37.1ms  words=11,149,312
[E01  1362/1548 G   1361|CLM] train=4.4924  mask=18.9%  norm=1.740  lr=2.98e-04  dt=  36.8ms  words=11,157,504
[E01  1363/1548 G   1362|CLM] train=6.3281  mask=18.9%  norm=4.402  lr=2.98e-04  dt=  36.8ms  words=11,165,696
[E01  1364/1548 G   1363|CLM] train=2.9590  mask=18.9%  norm=1.019  lr=2.98e-04  dt=  37.0ms  words=11,173,888
[E01  1365/1548 G   1364|CLM] train=3.0502  mask=18.9%  norm=0.909  lr=2.98e-04  dt=  37.1ms  words=11,182,080
[E01  1366/1548 G   1365|CLM] train=5.5727  mask=18.9%  norm=0.845  lr=2.98e-04  dt=  36.8ms  words=11,190,272
[E01  1367/1548 G   1366|CLM] train=6.0017  mask=18.9%  norm=1.069  lr=2.98e-04  dt=  36.9ms  words=11,198,464
[E01  1368/1548 G   1367|CLM] train=5.0346  mask=18.9%  norm=0.757  lr=2.98e-04  dt=  36.9ms  words=11,206,656
[E01  1369/1548 G   1368|CLM] train=5.0105  mask=18.9%  norm=0.644  lr=2.98e-04  dt=  39.0ms  words=11,214,848
[E01  1370/1548 G   1369|CLM] train=5.0646  mask=18.9%  norm=0.801  lr=2.98e-04  dt=  38.6ms  words=11,223,040
[E01  1371/1548 G   1370|CLM] train=6.7122  mask=18.9%  norm=1.937  lr=2.98e-04  dt=  37.0ms  words=11,231,232
[E01  1372/1548 G   1371|CLM] train=5.6693  mask=18.9%  norm=0.743  lr=2.98e-04  dt=  37.0ms  words=11,239,424
[E01  1373/1548 G   1372|CLM] train=3.4774  mask=18.9%  norm=1.438  lr=2.98e-04  dt=  37.3ms  words=11,247,616
[E01  1374/1548 G   1373|CLM] train=4.5200  mask=18.9%  norm=0.859  lr=2.98e-04  dt=  38.8ms  words=11,255,808
[E01  1375/1548 G   1374|CLM] train=5.6005  mask=18.9%  norm=1.154  lr=2.98e-04  dt=  39.0ms  words=11,264,000
[E01  1376/1548 G   1375|CLM] train=5.4514  mask=18.9%  norm=0.730  lr=2.98e-04  dt=  38.9ms  words=11,272,192
[E01  1377/1548 G   1376|CLM] train=5.6959  mask=18.9%  norm=0.689  lr=2.98e-04  dt=  39.5ms  words=11,280,384
[E01  1378/1548 G   1377|CLM] train=6.6742  mask=18.9%  norm=1.242  lr=2.98e-04  dt=  38.0ms  words=11,288,576
[E01  1379/1548 G   1378|CLM] train=2.8988  mask=18.9%  norm=0.965  lr=2.98e-04  dt=  38.4ms  words=11,296,768
[E01  1380/1548 G   1379|CLM] train=4.3612  mask=18.9%  norm=0.680  lr=2.98e-04  dt=  38.6ms  words=11,304,960
[E01  1381/1548 G   1380|CLM] train=3.3119  mask=18.9%  norm=0.881  lr=2.98e-04  dt=  38.6ms  words=11,313,152
[E01  1382/1548 G   1381|CLM] train=3.4667  mask=18.9%  norm=1.355  lr=2.98e-04  dt=  38.7ms  words=11,321,344
[E01  1383/1548 G   1382|CLM] train=2.9597  mask=18.9%  norm=0.546  lr=2.98e-04  dt=  39.0ms  words=11,329,536
[E01  1384/1548 G   1383|CLM] train=3.4531  mask=18.9%  norm=1.014  lr=2.98e-04  dt=  38.3ms  words=11,337,728
[E01  1385/1548 G   1384|CLM] train=4.7312  mask=18.9%  norm=0.976  lr=2.98e-04  dt=  37.2ms  words=11,345,920
[E01  1386/1548 G   1385|CLM] train=5.5481  mask=18.9%  norm=0.949  lr=2.98e-04  dt=  38.8ms  words=11,354,112
[E01  1387/1548 G   1386|CLM] train=4.8172  mask=18.9%  norm=0.747  lr=2.98e-04  dt=  37.1ms  words=11,362,304
[E01  1388/1548 G   1387|CLM] train=4.7414  mask=18.9%  norm=1.044  lr=2.98e-04  dt=  39.2ms  words=11,370,496
[E01  1389/1548 G   1388|CLM] train=5.2063  mask=18.9%  norm=0.678  lr=2.98e-04  dt=  37.9ms  words=11,378,688
[E01  1390/1548 G   1389|CLM] train=3.1841  mask=18.9%  norm=2.347  lr=2.98e-04  dt=  38.7ms  words=11,386,880
[E01  1391/1548 G   1390|CLM] train=2.8896  mask=18.9%  norm=0.936  lr=2.98e-04  dt=  39.0ms  words=11,395,072
[E01  1392/1548 G   1391|CLM] train=2.9701  mask=18.9%  norm=1.009  lr=2.98e-04  dt=  38.1ms  words=11,403,264
[E01  1393/1548 G   1392|CLM] train=2.9716  mask=18.9%  norm=0.950  lr=2.98e-04  dt=  37.1ms  words=11,411,456
[E01  1394/1548 G   1393|CLM] train=3.1735  mask=18.9%  norm=0.923  lr=2.98e-04  dt=  38.5ms  words=11,419,648
[E01  1395/1548 G   1394|CLM] train=5.5791  mask=18.9%  norm=1.076  lr=2.98e-04  dt=  37.9ms  words=11,427,840
[E01  1396/1548 G   1395|CLM] train=3.0331  mask=18.9%  norm=0.835  lr=2.98e-04  dt=  38.0ms  words=11,436,032
[E01  1397/1548 G   1396|CLM] train=4.9329  mask=18.9%  norm=1.000  lr=2.98e-04  dt=  39.3ms  words=11,444,224
[E01  1398/1548 G   1397|CLM] train=3.0211  mask=18.9%  norm=0.643  lr=2.98e-04  dt=  37.0ms  words=11,452,416
[E01  1399/1548 G   1398|CLM] train=2.9333  mask=18.9%  norm=0.767  lr=2.98e-04  dt=  37.0ms  words=11,460,608
[E01  1400/1548 G   1399|CLM] train=3.3108  mask=18.9%  norm=0.670  lr=2.98e-04  dt=  37.2ms  words=11,468,800
[E01  1401/1548 G   1400|CLM] train=3.3591  mask=18.9%  norm=0.765  lr=2.98e-04  dt=  38.1ms  words=11,476,992
[E01  1402/1548 G   1401|CLM] train=2.6781  mask=18.9%  norm=0.599  lr=2.98e-04  dt=  38.4ms  words=11,485,184
[E01  1403/1548 G   1402|CLM] train=3.4585  mask=18.9%  norm=0.960  lr=2.98e-04  dt=  38.4ms  words=11,493,376
[E01  1404/1548 G   1403|CLM] train=5.7118  mask=18.9%  norm=0.883  lr=2.98e-04  dt=  37.0ms  words=11,501,568
[E01  1405/1548 G   1404|CLM] train=5.2911  mask=18.9%  norm=1.061  lr=2.98e-04  dt=  36.9ms  words=11,509,760
[E01  1406/1548 G   1405|CLM] train=3.0590  mask=18.9%  norm=0.904  lr=2.98e-04  dt=  37.2ms  words=11,517,952
[E01  1407/1548 G   1406|CLM] train=6.0451  mask=18.9%  norm=0.671  lr=2.98e-04  dt=  39.5ms  words=11,526,144
[E01  1408/1548 G   1407|CLM] train=5.4526  mask=18.9%  norm=0.695  lr=2.98e-04  dt=  36.9ms  words=11,534,336
[E01  1409/1548 G   1408|CLM] train=3.0751  mask=18.9%  norm=0.958  lr=2.98e-04  dt=  37.0ms  words=11,542,528
[E01  1410/1548 G   1409|CLM] train=3.2332  mask=18.9%  norm=0.996  lr=2.98e-04  dt=  36.8ms  words=11,550,720
[E01  1411/1548 G   1410|CLM] train=5.1423  mask=18.9%  norm=0.885  lr=2.98e-04  dt=  38.7ms  words=11,558,912
[E01  1412/1548 G   1411|CLM] train=5.4659  mask=18.9%  norm=0.879  lr=2.98e-04  dt=  37.0ms  words=11,567,104
[E01  1413/1548 G   1412|CLM] train=3.2690  mask=18.9%  norm=0.765  lr=2.98e-04  dt=  37.0ms  words=11,575,296
[E01  1414/1548 G   1413|CLM] train=5.4605  mask=18.9%  norm=0.641  lr=2.98e-04  dt=  37.7ms  words=11,583,488
[E01  1415/1548 G   1414|CLM] train=6.0590  mask=18.9%  norm=0.983  lr=2.98e-04  dt=  38.4ms  words=11,591,680
[E01  1416/1548 G   1415|CLM] train=5.4762  mask=18.9%  norm=0.774  lr=2.98e-04  dt=  37.1ms  words=11,599,872
[E01  1417/1548 G   1416|CLM] train=4.1772  mask=18.9%  norm=0.761  lr=2.98e-04  dt=  37.0ms  words=11,608,064
[E01  1418/1548 G   1417|CLM] train=3.0080  mask=18.9%  norm=1.301  lr=2.98e-04  dt=  36.9ms  words=11,616,256
[E01  1419/1548 G   1418|CLM] train=4.8748  mask=18.9%  norm=1.041  lr=2.98e-04  dt=  38.5ms  words=11,624,448
[E01  1420/1548 G   1419|CLM] train=5.6844  mask=18.9%  norm=1.020  lr=2.98e-04  dt=  36.9ms  words=11,632,640
[E01  1421/1548 G   1420|CLM] train=4.7839  mask=18.9%  norm=0.966  lr=2.98e-04  dt=  37.2ms  words=11,640,832
[E01  1422/1548 G   1421|CLM] train=5.3883  mask=18.9%  norm=0.880  lr=2.98e-04  dt=  37.0ms  words=11,649,024
[E01  1423/1548 G   1422|CLM] train=6.1899  mask=18.9%  norm=0.985  lr=2.98e-04  dt=  37.1ms  words=11,657,216
[E01  1424/1548 G   1423|CLM] train=5.3803  mask=18.9%  norm=0.840  lr=2.98e-04  dt=  36.8ms  words=11,665,408
[E01  1425/1548 G   1424|CLM] train=3.2301  mask=18.9%  norm=0.957  lr=2.98e-04  dt=  37.6ms  words=11,673,600
[E01  1426/1548 G   1425|CLM] train=5.0926  mask=18.8%  norm=1.026  lr=2.98e-04  dt=  37.0ms  words=11,681,792
[E01  1427/1548 G   1426|CLM] train=4.5048  mask=18.8%  norm=0.905  lr=2.98e-04  dt=  37.1ms  words=11,689,984
[E01  1428/1548 G   1427|CLM] train=3.1536  mask=18.8%  norm=0.958  lr=2.98e-04  dt=  37.0ms  words=11,698,176
[E01  1429/1548 G   1428|CLM] train=2.7581  mask=18.8%  norm=0.825  lr=2.98e-04  dt=  37.7ms  words=11,706,368
[E01  1430/1548 G   1429|CLM] train=2.7595  mask=18.8%  norm=0.641  lr=2.98e-04  dt=  36.9ms  words=11,714,560
[E01  1431/1548 G   1430|CLM] train=5.9628  mask=18.8%  norm=1.277  lr=2.98e-04  dt=  37.0ms  words=11,722,752
[E01  1432/1548 G   1431|CLM] train=5.8823  mask=18.8%  norm=1.059  lr=2.98e-04  dt=  36.9ms  words=11,730,944
[E01  1433/1548 G   1432|CLM] train=5.5027  mask=18.8%  norm=1.097  lr=2.98e-04  dt=  37.0ms  words=11,739,136
[E01  1434/1548 G   1433|CLM] train=5.2329  mask=18.8%  norm=0.878  lr=2.98e-04  dt=  36.8ms  words=11,747,328
[E01  1435/1548 G   1434|CLM] train=5.0901  mask=18.8%  norm=0.755  lr=2.98e-04  dt=  36.9ms  words=11,755,520
[E01  1436/1548 G   1435|CLM] train=5.0080  mask=18.8%  norm=0.714  lr=2.98e-04  dt=  37.0ms  words=11,763,712
[E01  1437/1548 G   1436|CLM] train=3.2873  mask=18.8%  norm=1.247  lr=2.98e-04  dt=  37.1ms  words=11,771,904
[E01  1438/1548 G   1437|CLM] train=5.1405  mask=18.8%  norm=0.922  lr=2.98e-04  dt=  37.1ms  words=11,780,096
[E01  1439/1548 G   1438|CLM] train=5.7414  mask=18.8%  norm=0.777  lr=2.98e-04  dt=  37.0ms  words=11,788,288
[E01  1440/1548 G   1439|CLM] train=5.3099  mask=18.8%  norm=0.765  lr=2.98e-04  dt=  37.1ms  words=11,796,480
[E01  1441/1548 G   1440|CLM] train=2.8857  mask=18.8%  norm=1.257  lr=2.98e-04  dt=  37.1ms  words=11,804,672
[E01  1442/1548 G   1441|CLM] train=2.7464  mask=18.8%  norm=0.946  lr=2.98e-04  dt=  37.0ms  words=11,812,864
[E01  1443/1548 G   1442|CLM] train=5.3886  mask=18.8%  norm=0.825  lr=2.98e-04  dt=  37.8ms  words=11,821,056
[E01  1444/1548 G   1443|CLM] train=6.9658  mask=18.8%  norm=1.689  lr=2.98e-04  dt=  44.8ms  words=11,829,248
[E01  1445/1548 G   1444|CLM] train=3.4034  mask=18.8%  norm=0.994  lr=2.98e-04  dt=  42.4ms  words=11,837,440
[E01  1446/1548 G   1445|CLM] train=2.7799  mask=18.8%  norm=0.674  lr=2.98e-04  dt=  37.0ms  words=11,845,632
[E01  1447/1548 G   1446|CLM] train=5.2669  mask=18.8%  norm=0.802  lr=2.98e-04  dt=  37.1ms  words=11,853,824
[E01  1448/1548 G   1447|CLM] train=4.9724  mask=18.8%  norm=4.147  lr=2.98e-04  dt=  37.0ms  words=11,862,016
[E01  1449/1548 G   1448|CLM] train=5.1173  mask=18.8%  norm=1.193  lr=2.98e-04  dt=  37.6ms  words=11,870,208
[E01  1450/1548 G   1449|CLM] train=5.9401  mask=18.8%  norm=0.856  lr=2.98e-04  dt=  36.8ms  words=11,878,400
[E01  1451/1548 G   1450|CLM] train=4.6781  mask=18.8%  norm=0.776  lr=2.98e-04  dt=  37.0ms  words=11,886,592
[E01  1452/1548 G   1451|CLM] train=4.7747  mask=18.8%  norm=0.754  lr=2.98e-04  dt=  37.0ms  words=11,894,784
[E01  1453/1548 G   1452|CLM] train=5.5373  mask=18.8%  norm=0.888  lr=2.98e-04  dt=  37.3ms  words=11,902,976
[E01  1454/1548 G   1453|CLM] train=3.6715  mask=18.8%  norm=1.789  lr=2.98e-04  dt=  38.3ms  words=11,911,168
[E01  1455/1548 G   1454|CLM] train=4.6632  mask=18.8%  norm=0.746  lr=2.98e-04  dt=  37.2ms  words=11,919,360
[E01  1456/1548 G   1455|CLM] train=5.4162  mask=18.8%  norm=0.640  lr=2.98e-04  dt=  37.4ms  words=11,927,552
[E01  1457/1548 G   1456|CLM] train=3.1341  mask=18.8%  norm=1.418  lr=2.98e-04  dt=  38.3ms  words=11,935,744
[E01  1458/1548 G   1457|CLM] train=4.3386  mask=18.8%  norm=0.832  lr=2.98e-04  dt=  50.8ms  words=11,943,936
[E01  1459/1548 G   1458|CLM] train=4.9459  mask=18.8%  norm=0.718  lr=2.98e-04  dt=  37.1ms  words=11,952,128
[E01  1460/1548 G   1459|CLM] train=5.0722  mask=18.8%  norm=0.628  lr=2.98e-04  dt=  38.9ms  words=11,960,320
[E01  1461/1548 G   1460|CLM] train=2.9568  mask=18.8%  norm=0.862  lr=2.98e-04  dt=  41.5ms  words=11,968,512
[E01  1462/1548 G   1461|CLM] train=3.2585  mask=18.8%  norm=0.600  lr=2.98e-04  dt=  37.1ms  words=11,976,704
[E01  1463/1548 G   1462|CLM] train=5.0941  mask=18.8%  norm=0.834  lr=2.98e-04  dt=  37.0ms  words=11,984,896
[E01  1464/1548 G   1463|CLM] train=5.9102  mask=18.8%  norm=0.659  lr=2.98e-04  dt=  37.0ms  words=11,993,088
[E01  1465/1548 G   1464|CLM] train=2.8714  mask=18.8%  norm=0.581  lr=2.98e-04  dt=  37.2ms  words=12,001,280
[E01  1466/1548 G   1465|CLM] train=3.3264  mask=18.8%  norm=0.714  lr=2.98e-04  dt=  37.2ms  words=12,009,472
[E01  1467/1548 G   1466|CLM] train=3.1374  mask=18.8%  norm=0.750  lr=2.98e-04  dt=  37.3ms  words=12,017,664
[E01  1468/1548 G   1467|CLM] train=5.6345  mask=18.8%  norm=0.704  lr=2.98e-04  dt=  37.2ms  words=12,025,856
[E01  1469/1548 G   1468|CLM] train=4.7670  mask=18.8%  norm=0.662  lr=2.98e-04  dt=  37.3ms  words=12,034,048
[E01  1470/1548 G   1469|CLM] train=4.8523  mask=18.8%  norm=0.564  lr=2.98e-04  dt=  37.1ms  words=12,042,240
[E01  1471/1548 G   1470|CLM] train=5.2134  mask=18.8%  norm=0.652  lr=2.98e-04  dt=  37.0ms  words=12,050,432
[E01  1472/1548 G   1471|CLM] train=5.9185  mask=18.8%  norm=0.773  lr=2.98e-04  dt=  37.2ms  words=12,058,624
[E01  1473/1548 G   1472|CLM] train=2.7500  mask=18.8%  norm=0.579  lr=2.98e-04  dt=  37.4ms  words=12,066,816
[E01  1474/1548 G   1473|CLM] train=3.0716  mask=18.8%  norm=0.819  lr=2.98e-04  dt=  37.0ms  words=12,075,008
[E01  1475/1548 G   1474|CLM] train=5.5726  mask=18.8%  norm=0.877  lr=2.98e-04  dt=  37.4ms  words=12,083,200
[E01  1476/1548 G   1475|CLM] train=3.3240  mask=18.8%  norm=0.715  lr=2.98e-04  dt=  37.2ms  words=12,091,392
[E01  1477/1548 G   1476|CLM] train=5.8827  mask=18.8%  norm=0.961  lr=2.98e-04  dt=  37.1ms  words=12,099,584
[E01  1478/1548 G   1477|CLM] train=4.7262  mask=18.8%  norm=0.923  lr=2.98e-04  dt=  36.9ms  words=12,107,776
[E01  1479/1548 G   1478|CLM] train=2.7670  mask=18.8%  norm=0.705  lr=2.98e-04  dt=  37.3ms  words=12,115,968
[E01  1480/1548 G   1479|CLM] train=2.9739  mask=18.8%  norm=1.020  lr=2.98e-04  dt=  37.1ms  words=12,124,160
[E01  1481/1548 G   1480|CLM] train=4.3548  mask=18.8%  norm=1.552  lr=2.98e-04  dt=  37.4ms  words=12,132,352
[E01  1482/1548 G   1481|CLM] train=3.1961  mask=18.8%  norm=0.602  lr=2.98e-04  dt=  37.4ms  words=12,140,544
[E01  1483/1548 G   1482|CLM] train=5.1842  mask=18.8%  norm=0.615  lr=2.98e-04  dt=  37.2ms  words=12,148,736
[E01  1484/1548 G   1483|CLM] train=5.9433  mask=18.8%  norm=0.811  lr=2.98e-04  dt=  37.1ms  words=12,156,928
[E01  1485/1548 G   1484|CLM] train=5.4134  mask=18.8%  norm=1.489  lr=2.98e-04  dt=  37.1ms  words=12,165,120
[E01  1486/1548 G   1485|CLM] train=4.6446  mask=18.8%  norm=0.934  lr=2.98e-04  dt=  37.3ms  words=12,173,312
[E01  1487/1548 G   1486|CLM] train=2.6195  mask=18.8%  norm=0.714  lr=2.98e-04  dt=  37.1ms  words=12,181,504
[E01  1488/1548 G   1487|CLM] train=3.2553  mask=18.8%  norm=0.886  lr=2.98e-04  dt=  37.3ms  words=12,189,696
[E01  1489/1548 G   1488|CLM] train=3.1623  mask=18.8%  norm=1.155  lr=2.98e-04  dt=  37.0ms  words=12,197,888
[E01  1490/1548 G   1489|CLM] train=2.8232  mask=18.8%  norm=0.766  lr=2.98e-04  dt=  37.0ms  words=12,206,080
[E01  1491/1548 G   1490|CLM] train=4.7732  mask=18.8%  norm=0.741  lr=2.98e-04  dt=  37.4ms  words=12,214,272
[E01  1492/1548 G   1491|CLM] train=5.4172  mask=18.8%  norm=0.802  lr=2.98e-04  dt=  37.1ms  words=12,222,464
[E01  1493/1548 G   1492|CLM] train=5.0897  mask=18.8%  norm=0.813  lr=2.97e-04  dt=  37.0ms  words=12,230,656
[E01  1494/1548 G   1493|CLM] train=3.2021  mask=18.8%  norm=1.039  lr=2.97e-04  dt=  37.4ms  words=12,238,848
[E01  1495/1548 G   1494|CLM] train=4.4342  mask=18.8%  norm=0.793  lr=2.97e-04  dt=  37.3ms  words=12,247,040
[E01  1496/1548 G   1495|CLM] train=3.5281  mask=18.8%  norm=1.091  lr=2.97e-04  dt=  37.0ms  words=12,255,232
[E01  1497/1548 G   1496|CLM] train=5.5291  mask=18.8%  norm=0.733  lr=2.97e-04  dt=  37.4ms  words=12,263,424
[E01  1498/1548 G   1497|CLM] train=3.2305  mask=18.8%  norm=0.594  lr=2.97e-04  dt=  37.2ms  words=12,271,616
[E01  1499/1548 G   1498|CLM] train=3.1281  mask=18.8%  norm=0.709  lr=2.97e-04  dt=  37.2ms  words=12,279,808
[E01  1500/1548 G   1499|CLM] train=4.9825  mask=18.8%  norm=0.889  lr=2.97e-04  dt=  37.0ms  words=12,288,000
[E01  1501/1548 G   1500|CLM] train=5.8549  mask=18.8%  norm=0.667  lr=2.97e-04  dt=  37.5ms  words=12,296,192
[E01  1502/1548 G   1501|CLM] train=4.9501  mask=18.8%  norm=0.624  lr=2.97e-04  dt=  37.3ms  words=12,304,384
[E01  1503/1548 G   1502|CLM] train=4.8651  mask=18.8%  norm=0.966  lr=2.97e-04  dt=  37.4ms  words=12,312,576
[E01  1504/1548 G   1503|CLM] train=5.0476  mask=18.8%  norm=0.550  lr=2.97e-04  dt=  37.1ms  words=12,320,768
[E01  1505/1548 G   1504|CLM] train=2.6919  mask=18.8%  norm=1.186  lr=2.97e-04  dt=  37.1ms  words=12,328,960
[E01  1506/1548 G   1505|CLM] train=5.3679  mask=18.8%  norm=0.686  lr=2.97e-04  dt=  36.9ms  words=12,337,152
[E01  1507/1548 G   1506|CLM] train=2.9887  mask=18.8%  norm=1.031  lr=2.97e-04  dt=  37.2ms  words=12,345,344
[E01  1508/1548 G   1507|CLM] train=2.9501  mask=18.8%  norm=0.733  lr=2.97e-04  dt=  37.2ms  words=12,353,536
[E01  1509/1548 G   1508|CLM] train=3.3376  mask=18.8%  norm=0.739  lr=2.97e-04  dt=  37.6ms  words=12,361,728
[E01  1510/1548 G   1509|CLM] train=6.4216  mask=18.8%  norm=1.080  lr=2.97e-04  dt=  37.3ms  words=12,369,920
[E01  1511/1548 G   1510|CLM] train=3.1947  mask=18.8%  norm=0.610  lr=2.97e-04  dt=  37.2ms  words=12,378,112
[E01  1512/1548 G   1511|CLM] train=5.5269  mask=18.8%  norm=0.576  lr=2.97e-04  dt=  37.0ms  words=12,386,304
[E01  1513/1548 G   1512|CLM] train=5.1476  mask=18.8%  norm=0.986  lr=2.97e-04  dt=  37.0ms  words=12,394,496
[E01  1514/1548 G   1513|CLM] train=5.6602  mask=18.8%  norm=1.518  lr=2.97e-04  dt=  37.1ms  words=12,402,688
[E01  1515/1548 G   1514|CLM] train=4.9100  mask=18.8%  norm=0.787  lr=2.97e-04  dt=  37.3ms  words=12,410,880
[E01  1516/1548 G   1515|CLM] train=5.3726  mask=18.8%  norm=0.815  lr=2.97e-04  dt=  37.1ms  words=12,419,072
[E01  1517/1548 G   1516|CLM] train=5.4617  mask=18.8%  norm=0.702  lr=2.97e-04  dt=  37.2ms  words=12,427,264
[E01  1518/1548 G   1517|CLM] train=4.0711  mask=18.8%  norm=0.719  lr=2.97e-04  dt=  37.0ms  words=12,435,456
[E01  1519/1548 G   1518|CLM] train=2.8398  mask=18.8%  norm=1.611  lr=2.97e-04  dt=  37.0ms  words=12,443,648
[E01  1520/1548 G   1519|CLM] train=4.8088  mask=18.8%  norm=4.967  lr=2.97e-04  dt=  37.2ms  words=12,451,840
[E01  1521/1548 G   1520|CLM] train=5.9998  mask=18.8%  norm=1.061  lr=2.97e-04  dt=  37.2ms  words=12,460,032
[E01  1522/1548 G   1521|CLM] train=5.2512  mask=18.8%  norm=1.153  lr=2.97e-04  dt=  37.0ms  words=12,468,224
[E01  1523/1548 G   1522|CLM] train=5.4374  mask=18.8%  norm=0.629  lr=2.97e-04  dt=  37.2ms  words=12,476,416
[E01  1524/1548 G   1523|CLM] train=3.1998  mask=18.8%  norm=0.766  lr=2.97e-04  dt=  37.1ms  words=12,484,608
[E01  1525/1548 G   1524|CLM] train=5.4685  mask=18.8%  norm=0.946  lr=2.97e-04  dt=  37.1ms  words=12,492,800
[E01  1526/1548 G   1525|CLM] train=4.8851  mask=18.8%  norm=0.931  lr=2.97e-04  dt=  37.0ms  words=12,500,992
[E01  1527/1548 G   1526|CLM] train=2.9411  mask=18.8%  norm=0.704  lr=2.97e-04  dt=  37.2ms  words=12,509,184
[E01  1528/1548 G   1527|CLM] train=5.2588  mask=18.8%  norm=0.878  lr=2.97e-04  dt=  36.9ms  words=12,517,376
[E01  1529/1548 G   1528|CLM] train=6.0699  mask=18.8%  norm=1.196  lr=2.97e-04  dt=  37.1ms  words=12,525,568
[E01  1530/1548 G   1529|CLM] train=3.0555  mask=18.8%  norm=0.676  lr=2.97e-04  dt=  36.9ms  words=12,533,760
[E01  1531/1548 G   1530|CLM] train=5.3910  mask=18.8%  norm=0.728  lr=2.97e-04  dt=  37.1ms  words=12,541,952
[E01  1532/1548 G   1531|CLM] train=4.7031  mask=18.8%  norm=1.020  lr=2.97e-04  dt=  36.9ms  words=12,550,144
[E01  1533/1548 G   1532|CLM] train=3.0585  mask=18.8%  norm=1.036  lr=2.97e-04  dt=  36.9ms  words=12,558,336
[E01  1534/1548 G   1533|CLM] train=4.1607  mask=18.8%  norm=1.384  lr=2.97e-04  dt=  37.0ms  words=12,566,528
[E01  1535/1548 G   1534|CLM] train=4.4501  mask=18.8%  norm=0.755  lr=2.97e-04  dt=  37.2ms  words=12,574,720
[E01  1536/1548 G   1535|CLM] train=5.2924  mask=18.8%  norm=0.632  lr=2.97e-04  dt=  38.0ms  words=12,582,912
[E01  1537/1548 G   1536|CLM] train=3.1123  mask=18.8%  norm=0.817  lr=2.97e-04  dt=  37.1ms  words=12,591,104
[E01  1538/1548 G   1537|CLM] train=3.0225  mask=18.8%  norm=1.173  lr=2.97e-04  dt=  37.1ms  words=12,599,296
[E01  1539/1548 G   1538|CLM] train=2.6258  mask=18.8%  norm=0.728  lr=2.97e-04  dt=  37.1ms  words=12,607,488
[E01  1540/1548 G   1539|CLM] train=5.0767  mask=18.8%  norm=0.694  lr=2.97e-04  dt=  36.9ms  words=12,615,680
[E01  1541/1548 G   1540|CLM] train=5.2205  mask=18.8%  norm=0.676  lr=2.97e-04  dt=  37.0ms  words=12,623,872
[E01  1542/1548 G   1541|CLM] train=5.4048  mask=18.8%  norm=0.639  lr=2.97e-04  dt=  37.0ms  words=12,632,064
[E01  1543/1548 G   1542|CLM] train=4.9051  mask=18.8%  norm=0.732  lr=2.97e-04  dt=  37.2ms  words=12,640,256
[E01  1544/1548 G   1543|CLM] train=5.4508  mask=18.8%  norm=0.775  lr=2.97e-04  dt=  37.2ms  words=12,648,448
[E01  1545/1548 G   1544|CLM] train=4.8847  mask=18.8%  norm=0.688  lr=2.97e-04  dt=  37.0ms  words=12,656,640
[E01  1546/1548 G   1545|CLM] train=4.2046  mask=18.8%  norm=0.801  lr=2.97e-04  dt=  37.3ms  words=12,664,832
[E01  1547/1548 G   1546|CLM] train=3.4928  mask=18.8%  norm=0.888  lr=2.97e-04  dt=  37.3ms  words=12,673,024
[E01  1548/1548 G   1547|CLM] train=4.1600  mask=18.8%  norm=0.581  lr=2.97e-04  dt=  37.7ms  words=12,681,216
[E02     1/1548 G   1548|CLM] train=2.9840  mask=18.8%  norm=0.848  lr=2.97e-04  dt=  37.1ms  words=12,689,408
[E02     2/1548 G   1549|CLM] train=4.6168  mask=18.7%  norm=0.706  lr=2.97e-04  dt=  37.1ms  words=12,697,600
[E02     3/1548 G   1550|CLM] train=5.0545  mask=18.7%  norm=0.797  lr=2.97e-04  dt=  37.1ms  words=12,705,792
[E02     4/1548 G   1551|CLM] train=5.7594  mask=18.7%  norm=1.327  lr=2.97e-04  dt=  37.1ms  words=12,713,984
[E02     5/1548 G   1552|CLM] train=5.1768  mask=18.7%  norm=0.807  lr=2.97e-04  dt=  37.2ms  words=12,722,176
[E02     6/1548 G   1553|CLM] train=6.4591  mask=18.7%  norm=1.389  lr=2.97e-04  dt=  37.0ms  words=12,730,368
[E02     7/1548 G   1554|CLM] train=4.7842  mask=18.7%  norm=0.678  lr=2.97e-04  dt=  37.0ms  words=12,738,560
[E02     8/1548 G   1555|CLM] train=3.3506  mask=18.7%  norm=1.613  lr=2.97e-04  dt=  36.9ms  words=12,746,752
[E02     9/1548 G   1556|CLM] train=5.2288  mask=18.7%  norm=0.959  lr=2.97e-04  dt=  37.1ms  words=12,754,944
[E02    10/1548 G   1557|CLM] train=4.9936  mask=18.7%  norm=0.723  lr=2.97e-04  dt=  37.0ms  words=12,763,136
[E02    11/1548 G   1558|CLM] train=5.1502  mask=18.7%  norm=0.965  lr=2.97e-04  dt=  37.3ms  words=12,771,328
[E02    12/1548 G   1559|CLM] train=4.8244  mask=18.7%  norm=0.975  lr=2.97e-04  dt=  37.4ms  words=12,779,520
[E02    13/1548 G   1560|CLM] train=2.8388  mask=18.7%  norm=0.734  lr=2.97e-04  dt=  37.3ms  words=12,787,712
[E02    14/1548 G   1561|CLM] train=5.3882  mask=18.7%  norm=0.984  lr=2.97e-04  dt=  37.2ms  words=12,795,904
[E02    15/1548 G   1562|CLM] train=5.3804  mask=18.7%  norm=0.824  lr=2.97e-04  dt=  37.4ms  words=12,804,096
[E02    16/1548 G   1563|CLM] train=4.4985  mask=18.7%  norm=0.799  lr=2.97e-04  dt=  38.0ms  words=12,812,288
[E02    17/1548 G   1564|CLM] train=4.8546  mask=18.7%  norm=0.609  lr=2.97e-04  dt=  37.8ms  words=12,820,480
[E02    18/1548 G   1565|CLM] train=4.6872  mask=18.7%  norm=0.624  lr=2.97e-04  dt=  37.9ms  words=12,828,672
[E02    19/1548 G   1566|CLM] train=3.0273  mask=18.7%  norm=0.992  lr=2.97e-04  dt=  37.5ms  words=12,836,864
[E02    20/1548 G   1567|CLM] train=4.9852  mask=18.7%  norm=0.670  lr=2.97e-04  dt=  37.1ms  words=12,845,056
[E02    21/1548 G   1568|CLM] train=4.7890  mask=18.7%  norm=0.600  lr=2.97e-04  dt=  37.1ms  words=12,853,248
[E02    22/1548 G   1569|CLM] train=4.9567  mask=18.7%  norm=0.684  lr=2.97e-04  dt=  37.0ms  words=12,861,440
[E02    23/1548 G   1570|CLM] train=4.5332  mask=18.7%  norm=0.688  lr=2.97e-04  dt=  37.2ms  words=12,869,632
[E02    24/1548 G   1571|CLM] train=5.0310  mask=18.7%  norm=0.769  lr=2.97e-04  dt=  37.2ms  words=12,877,824
[E02    25/1548 G   1572|CLM] train=2.8248  mask=18.7%  norm=0.721  lr=2.97e-04  dt=  37.1ms  words=12,886,016
[E02    26/1548 G   1573|CLM] train=4.2001  mask=18.7%  norm=0.741  lr=2.97e-04  dt=  37.2ms  words=12,894,208
[E02    27/1548 G   1574|CLM] train=4.1026  mask=18.7%  norm=0.644  lr=2.97e-04  dt=  37.8ms  words=12,902,400
[E02    28/1548 G   1575|CLM] train=3.3099  mask=18.7%  norm=2.270  lr=2.97e-04  dt=  37.0ms  words=12,910,592
[E02    29/1548 G   1576|CLM] train=4.9159  mask=18.7%  norm=0.824  lr=2.97e-04  dt=  39.6ms  words=12,918,784
[E02    30/1548 G   1577|CLM] train=2.9681  mask=18.7%  norm=0.707  lr=2.97e-04  dt=  41.3ms  words=12,926,976
[E02    31/1548 G   1578|CLM] train=5.7499  mask=18.7%  norm=0.915  lr=2.97e-04  dt=  37.0ms  words=12,935,168
[E02    32/1548 G   1579|CLM] train=3.0264  mask=18.7%  norm=0.654  lr=2.97e-04  dt=  38.2ms  words=12,943,360
[E02    33/1548 G   1580|CLM] train=2.7315  mask=18.7%  norm=0.655  lr=2.97e-04  dt=  38.7ms  words=12,951,552
[E02    34/1548 G   1581|CLM] train=4.5878  mask=18.7%  norm=0.951  lr=2.97e-04  dt=  37.3ms  words=12,959,744
[E02    35/1548 G   1582|CLM] train=3.4522  mask=18.7%  norm=0.881  lr=2.97e-04  dt=  37.9ms  words=12,967,936
[E02    36/1548 G   1583|CLM] train=3.0910  mask=18.7%  norm=0.608  lr=2.97e-04  dt=  37.8ms  words=12,976,128
[E02    37/1548 G   1584|CLM] train=5.2700  mask=18.7%  norm=1.175  lr=2.97e-04  dt=  37.4ms  words=12,984,320
[E02    38/1548 G   1585|CLM] train=4.6472  mask=18.7%  norm=4.291  lr=2.97e-04  dt=  37.2ms  words=12,992,512
[E02    39/1548 G   1586|CLM] train=3.0389  mask=18.7%  norm=1.121  lr=2.97e-04  dt=  37.5ms  words=13,000,704
[E02    40/1548 G   1587|CLM] train=5.4397  mask=18.7%  norm=0.776  lr=2.97e-04  dt=  37.5ms  words=13,008,896
[E02    41/1548 G   1588|CLM] train=3.2481  mask=18.7%  norm=1.431  lr=2.97e-04  dt=  37.6ms  words=13,017,088
[E02    42/1548 G   1589|CLM] train=4.9155  mask=18.7%  norm=0.906  lr=2.97e-04  dt=  37.1ms  words=13,025,280
[E02    43/1548 G   1590|CLM] train=4.7846  mask=18.7%  norm=0.874  lr=2.97e-04  dt=  37.3ms  words=13,033,472
[E02    44/1548 G   1591|CLM] train=2.9387  mask=18.7%  norm=0.932  lr=2.97e-04  dt=  37.2ms  words=13,041,664
[E02    45/1548 G   1592|CLM] train=3.6934  mask=18.7%  norm=0.851  lr=2.97e-04  dt=  41.4ms  words=13,049,856
[E02    46/1548 G   1593|CLM] train=4.9276  mask=18.7%  norm=0.779  lr=2.97e-04  dt=  45.6ms  words=13,058,048
[E02    47/1548 G   1594|CLM] train=5.1377  mask=18.7%  norm=0.628  lr=2.97e-04  dt=  40.2ms  words=13,066,240
[E02    48/1548 G   1595|CLM] train=2.9265  mask=18.7%  norm=0.687  lr=2.97e-04  dt=  37.2ms  words=13,074,432
[E02    49/1548 G   1596|CLM] train=5.3646  mask=18.7%  norm=0.793  lr=2.97e-04  dt=  37.0ms  words=13,082,624
[E02    50/1548 G   1597|CLM] train=2.8795  mask=18.7%  norm=0.758  lr=2.97e-04  dt=  37.0ms  words=13,090,816
[E02    51/1548 G   1598|CLM] train=2.8464  mask=18.7%  norm=0.770  lr=2.97e-04  dt=  37.1ms  words=13,099,008
[E02    52/1548 G   1599|CLM] train=5.1354  mask=18.7%  norm=0.768  lr=2.97e-04  dt=  36.9ms  words=13,107,200
[E02    53/1548 G   1600|CLM] train=4.5522  mask=18.7%  norm=0.754  lr=2.97e-04  dt=  37.4ms  words=13,115,392
[E02    54/1548 G   1601|CLM] train=4.7971  mask=18.7%  norm=0.718  lr=2.97e-04  dt=  37.1ms  words=13,123,584
[E02    55/1548 G   1602|CLM] train=3.5925  mask=18.7%  norm=0.940  lr=2.97e-04  dt=  37.3ms  words=13,131,776
[E02    56/1548 G   1603|CLM] train=4.4024  mask=18.7%  norm=0.599  lr=2.97e-04  dt=  37.7ms  words=13,139,968
[E02    57/1548 G   1604|CLM] train=5.7483  mask=18.7%  norm=1.127  lr=2.97e-04  dt=  37.8ms  words=13,148,160
[E02    58/1548 G   1605|CLM] train=4.3087  mask=18.7%  norm=0.760  lr=2.97e-04  dt=  37.2ms  words=13,156,352
[E02    59/1548 G   1606|CLM] train=4.6326  mask=18.7%  norm=0.805  lr=2.97e-04  dt=  37.1ms  words=13,164,544
[E02    60/1548 G   1607|CLM] train=5.3892  mask=18.7%  norm=0.927  lr=2.97e-04  dt=  38.0ms  words=13,172,736
[E02    61/1548 G   1608|CLM] train=4.7450  mask=18.7%  norm=0.759  lr=2.97e-04  dt=  37.8ms  words=13,180,928
[E02    62/1548 G   1609|CLM] train=3.1340  mask=18.7%  norm=0.982  lr=2.97e-04  dt=  39.4ms  words=13,189,120
[E02    63/1548 G   1610|CLM] train=3.1929  mask=18.7%  norm=1.057  lr=2.97e-04  dt=  42.0ms  words=13,197,312
[E02    64/1548 G   1611|CLM] train=3.2059  mask=18.7%  norm=1.154  lr=2.97e-04  dt=  38.6ms  words=13,205,504
[E02    65/1548 G   1612|CLM] train=5.8398  mask=18.7%  norm=2.532  lr=2.97e-04  dt=  43.5ms  words=13,213,696
[E02    66/1548 G   1613|CLM] train=5.2616  mask=18.7%  norm=0.913  lr=2.97e-04  dt=  42.2ms  words=13,221,888
[E02    67/1548 G   1614|CLM] train=5.2990  mask=18.7%  norm=0.896  lr=2.97e-04  dt=  39.6ms  words=13,230,080
[E02    68/1548 G   1615|CLM] train=3.2288  mask=18.7%  norm=0.979  lr=2.97e-04  dt=  52.0ms  words=13,238,272
[E02    69/1548 G   1616|CLM] train=4.5338  mask=18.7%  norm=0.649  lr=2.97e-04  dt=  41.4ms  words=13,246,464
[E02    70/1548 G   1617|CLM] train=6.0060  mask=18.7%  norm=1.646  lr=2.97e-04  dt=  38.5ms  words=13,254,656
[E02    71/1548 G   1618|CLM] train=4.8899  mask=18.7%  norm=0.984  lr=2.97e-04  dt=  37.4ms  words=13,262,848
[E02    72/1548 G   1619|CLM] train=5.0644  mask=18.7%  norm=0.716  lr=2.96e-04  dt=  41.0ms  words=13,271,040
[E02    73/1548 G   1620|CLM] train=5.6740  mask=18.7%  norm=0.657  lr=2.96e-04  dt=  40.4ms  words=13,279,232
[E02    74/1548 G   1621|CLM] train=2.9995  mask=18.7%  norm=1.098  lr=2.96e-04  dt=  43.6ms  words=13,287,424
[E02    75/1548 G   1622|CLM] train=4.9640  mask=18.7%  norm=0.774  lr=2.96e-04  dt=  47.7ms  words=13,295,616
[E02    76/1548 G   1623|CLM] train=5.0654  mask=18.7%  norm=0.658  lr=2.96e-04  dt=  42.8ms  words=13,303,808
[E02    77/1548 G   1624|CLM] train=5.4753  mask=18.7%  norm=1.001  lr=2.96e-04  dt=  41.5ms  words=13,312,000
[E02    78/1548 G   1625|CLM] train=4.9031  mask=18.7%  norm=0.629  lr=2.96e-04  dt=  37.2ms  words=13,320,192
[E02    79/1548 G   1626|CLM] train=2.8235  mask=18.7%  norm=0.617  lr=2.96e-04  dt=  37.1ms  words=13,328,384
[E02    80/1548 G   1627|CLM] train=5.5946  mask=18.7%  norm=1.173  lr=2.96e-04  dt=  38.3ms  words=13,336,576
[E02    81/1548 G   1628|CLM] train=4.9665  mask=18.7%  norm=0.964  lr=2.96e-04  dt=  38.5ms  words=13,344,768
[E02    82/1548 G   1629|CLM] train=4.6366  mask=18.7%  norm=0.819  lr=2.96e-04  dt=  37.1ms  words=13,352,960
[E02    83/1548 G   1630|CLM] train=5.1680  mask=18.7%  norm=0.910  lr=2.96e-04  dt=  38.0ms  words=13,361,152
[E02    84/1548 G   1631|CLM] train=4.5782  mask=18.7%  norm=2.299  lr=2.96e-04  dt=  38.4ms  words=13,369,344
[E02    85/1548 G   1632|CLM] train=5.2599  mask=18.7%  norm=0.905  lr=2.96e-04  dt=  39.3ms  words=13,377,536
[E02    86/1548 G   1633|CLM] train=2.9357  mask=18.7%  norm=1.118  lr=2.96e-04  dt=  39.6ms  words=13,385,728
[E02    87/1548 G   1634|CLM] train=5.6650  mask=18.7%  norm=0.751  lr=2.96e-04  dt=  38.0ms  words=13,393,920
[E02    88/1548 G   1635|CLM] train=4.6992  mask=18.7%  norm=0.686  lr=2.96e-04  dt=  38.0ms  words=13,402,112
[E02    89/1548 G   1636|CLM] train=2.8937  mask=18.7%  norm=0.834  lr=2.96e-04  dt=  37.3ms  words=13,410,304
[E02    90/1548 G   1637|CLM] train=4.8561  mask=18.7%  norm=0.623  lr=2.96e-04  dt=  39.0ms  words=13,418,496
[E02    91/1548 G   1638|CLM] train=5.2628  mask=18.7%  norm=0.629  lr=2.96e-04  dt=  37.0ms  words=13,426,688
[E02    92/1548 G   1639|CLM] train=3.0024  mask=18.7%  norm=0.795  lr=2.96e-04  dt=  39.0ms  words=13,434,880
[E02    93/1548 G   1640|CLM] train=4.8838  mask=18.7%  norm=0.691  lr=2.96e-04  dt=  36.8ms  words=13,443,072
[E02    94/1548 G   1641|CLM] train=4.5862  mask=18.7%  norm=0.691  lr=2.96e-04  dt=  37.7ms  words=13,451,264
[E02    95/1548 G   1642|CLM] train=2.5775  mask=18.7%  norm=0.782  lr=2.96e-04  dt=  37.5ms  words=13,459,456
[E02    96/1548 G   1643|CLM] train=4.2433  mask=18.7%  norm=0.661  lr=2.96e-04  dt=  37.3ms  words=13,467,648
[E02    97/1548 G   1644|CLM] train=4.8749  mask=18.7%  norm=0.772  lr=2.96e-04  dt=  37.3ms  words=13,475,840
[E02    98/1548 G   1645|CLM] train=5.0239  mask=18.7%  norm=0.741  lr=2.96e-04  dt=  37.3ms  words=13,484,032
[E02    99/1548 G   1646|CLM] train=4.0580  mask=18.7%  norm=0.679  lr=2.96e-04  dt=  37.4ms  words=13,492,224
[E02   100/1548 G   1647|CLM] train=4.2940  mask=18.7%  norm=0.628  lr=2.96e-04  dt=  37.5ms  words=13,500,416
[E02   101/1548 G   1648|CLM] train=6.1857  mask=18.7%  norm=0.969  lr=2.96e-04  dt=  37.0ms  words=13,508,608
[E02   102/1548 G   1649|CLM] train=3.2612  mask=18.7%  norm=0.935  lr=2.96e-04  dt=  37.1ms  words=13,516,800
[E02   103/1548 G   1650|CLM] train=5.3997  mask=18.7%  norm=0.695  lr=2.96e-04  dt=  37.2ms  words=13,524,992
[E02   104/1548 G   1651|CLM] train=4.8152  mask=18.7%  norm=0.680  lr=2.96e-04  dt=  37.1ms  words=13,533,184
[E02   105/1548 G   1652|CLM] train=2.7216  mask=18.7%  norm=0.909  lr=2.96e-04  dt=  37.4ms  words=13,541,376
[E02   106/1548 G   1653|CLM] train=4.8884  mask=18.7%  norm=0.550  lr=2.96e-04  dt=  37.6ms  words=13,549,568
[E02   107/1548 G   1654|CLM] train=2.9018  mask=18.7%  norm=0.892  lr=2.96e-04  dt=  37.7ms  words=13,557,760
[E02   108/1548 G   1655|CLM] train=4.9543  mask=18.7%  norm=0.737  lr=2.96e-04  dt=  37.6ms  words=13,565,952
[E02   109/1548 G   1656|CLM] train=3.4395  mask=18.7%  norm=1.461  lr=2.96e-04  dt=  37.9ms  words=13,574,144
[E02   110/1548 G   1657|CLM] train=2.7479  mask=18.7%  norm=0.881  lr=2.96e-04  dt=  37.7ms  words=13,582,336
[E02   111/1548 G   1658|CLM] train=2.8542  mask=18.7%  norm=0.775  lr=2.96e-04  dt=  37.6ms  words=13,590,528
[E02   112/1548 G   1659|CLM] train=4.6307  mask=18.7%  norm=0.700  lr=2.96e-04  dt=  37.3ms  words=13,598,720
[E02   113/1548 G   1660|CLM] train=4.7715  mask=18.7%  norm=0.618  lr=2.96e-04  dt=  37.6ms  words=13,606,912
[E02   114/1548 G   1661|CLM] train=4.1504  mask=18.7%  norm=0.667  lr=2.96e-04  dt=  37.5ms  words=13,615,104
[E02   115/1548 G   1662|CLM] train=4.9785  mask=18.7%  norm=0.731  lr=2.96e-04  dt=  37.8ms  words=13,623,296
[E02   116/1548 G   1663|CLM] train=4.9567  mask=18.7%  norm=0.911  lr=2.96e-04  dt=  36.9ms  words=13,631,488
[E02   117/1548 G   1664|CLM] train=5.5696  mask=18.7%  norm=0.789  lr=2.96e-04  dt=  38.7ms  words=13,639,680
[E02   118/1548 G   1665|CLM] train=5.2895  mask=18.7%  norm=0.652  lr=2.96e-04  dt=  37.0ms  words=13,647,872
[E02   119/1548 G   1666|CLM] train=2.9373  mask=18.7%  norm=1.062  lr=2.96e-04  dt=  37.0ms  words=13,656,064
[E02   120/1548 G   1667|CLM] train=6.0456  mask=18.7%  norm=0.705  lr=2.96e-04  dt=  37.8ms  words=13,664,256
[E02   121/1548 G   1668|CLM] train=4.5540  mask=18.7%  norm=0.703  lr=2.96e-04  dt=  37.1ms  words=13,672,448
[E02   122/1548 G   1669|CLM] train=4.3380  mask=18.7%  norm=0.750  lr=2.96e-04  dt=  37.4ms  words=13,680,640
[E02   123/1548 G   1670|CLM] train=4.5722  mask=18.7%  norm=0.681  lr=2.96e-04  dt=  37.1ms  words=13,688,832
[E02   124/1548 G   1671|CLM] train=5.2513  mask=18.7%  norm=0.853  lr=2.96e-04  dt=  37.5ms  words=13,697,024
[E02   125/1548 G   1672|CLM] train=3.1569  mask=18.6%  norm=0.916  lr=2.96e-04  dt=  37.2ms  words=13,705,216
[E02   126/1548 G   1673|CLM] train=2.7417  mask=18.6%  norm=0.876  lr=2.96e-04  dt=  38.0ms  words=13,713,408
[E02   127/1548 G   1674|CLM] train=5.4953  mask=18.6%  norm=0.698  lr=2.96e-04  dt=  37.2ms  words=13,721,600
[E02   128/1548 G   1675|CLM] train=3.2097  mask=18.6%  norm=0.815  lr=2.96e-04  dt=  37.2ms  words=13,729,792
[E02   129/1548 G   1676|CLM] train=5.2765  mask=18.6%  norm=1.213  lr=2.96e-04  dt=  37.0ms  words=13,737,984
[E02   130/1548 G   1677|CLM] train=2.7651  mask=18.6%  norm=0.772  lr=2.96e-04  dt=  36.9ms  words=13,746,176
[E02   131/1548 G   1678|CLM] train=3.1318  mask=18.6%  norm=0.628  lr=2.96e-04  dt=  36.9ms  words=13,754,368
[E02   132/1548 G   1679|CLM] train=2.7773  mask=18.6%  norm=0.865  lr=2.96e-04  dt=  37.1ms  words=13,762,560
[E02   133/1548 G   1680|CLM] train=4.5841  mask=18.6%  norm=1.361  lr=2.96e-04  dt=  37.1ms  words=13,770,752
[E02   134/1548 G   1681|CLM] train=4.7135  mask=18.6%  norm=0.734  lr=2.96e-04  dt=  37.2ms  words=13,778,944
[E02   135/1548 G   1682|CLM] train=3.1712  mask=18.6%  norm=0.732  lr=2.96e-04  dt=  36.9ms  words=13,787,136
[E02   136/1548 G   1683|CLM] train=4.9604  mask=18.6%  norm=0.869  lr=2.96e-04  dt=  37.0ms  words=13,795,328
[E02   137/1548 G   1684|CLM] train=5.3523  mask=18.6%  norm=0.787  lr=2.96e-04  dt=  36.9ms  words=13,803,520
[E02   138/1548 G   1685|CLM] train=4.8239  mask=18.6%  norm=0.660  lr=2.96e-04  dt=  37.0ms  words=13,811,712
[E02   139/1548 G   1686|CLM] train=3.0549  mask=18.6%  norm=0.795  lr=2.96e-04  dt=  37.2ms  words=13,819,904
[E02   140/1548 G   1687|CLM] train=2.8047  mask=18.6%  norm=0.711  lr=2.96e-04  dt=  37.1ms  words=13,828,096
[E02   141/1548 G   1688|CLM] train=5.5721  mask=18.6%  norm=0.888  lr=2.96e-04  dt=  37.1ms  words=13,836,288
[E02   142/1548 G   1689|CLM] train=4.6360  mask=18.6%  norm=0.853  lr=2.96e-04  dt=  37.1ms  words=13,844,480
[E02   143/1548 G   1690|CLM] train=5.4304  mask=18.6%  norm=1.203  lr=2.96e-04  dt=  37.1ms  words=13,852,672
[E02   144/1548 G   1691|CLM] train=5.8180  mask=18.6%  norm=0.667  lr=2.96e-04  dt=  37.0ms  words=13,860,864
[E02   145/1548 G   1692|CLM] train=6.3759  mask=18.6%  norm=1.651  lr=2.96e-04  dt=  36.9ms  words=13,869,056
[E02   146/1548 G   1693|CLM] train=4.3333  mask=18.6%  norm=0.830  lr=2.96e-04  dt=  36.9ms  words=13,877,248
[E02   147/1548 G   1694|CLM] train=2.9898  mask=18.6%  norm=1.038  lr=2.96e-04  dt=  36.8ms  words=13,885,440
[E02   148/1548 G   1695|CLM] train=4.3186  mask=18.6%  norm=0.644  lr=2.96e-04  dt=  36.9ms  words=13,893,632
[E02   149/1548 G   1696|CLM] train=4.4593  mask=18.6%  norm=0.891  lr=2.96e-04  dt=  36.9ms  words=13,901,824
[E02   150/1548 G   1697|CLM] train=5.3991  mask=18.6%  norm=0.945  lr=2.96e-04  dt=  37.1ms  words=13,910,016
[E02   151/1548 G   1698|CLM] train=5.3255  mask=18.6%  norm=0.748  lr=2.96e-04  dt=  36.9ms  words=13,918,208
[E02   152/1548 G   1699|CLM] train=4.7193  mask=18.6%  norm=0.844  lr=2.96e-04  dt=  36.9ms  words=13,926,400
[E02   153/1548 G   1700|CLM] train=5.4419  mask=18.6%  norm=0.790  lr=2.96e-04  dt=  36.8ms  words=13,934,592
[E02   154/1548 G   1701|CLM] train=3.6921  mask=18.6%  norm=1.567  lr=2.96e-04  dt=  36.8ms  words=13,942,784
[E02   155/1548 G   1702|CLM] train=2.8241  mask=18.6%  norm=0.736  lr=2.96e-04  dt=  37.0ms  words=13,950,976
[E02   156/1548 G   1703|CLM] train=3.4519  mask=18.6%  norm=1.281  lr=2.96e-04  dt=  37.1ms  words=13,959,168
[E02   157/1548 G   1704|CLM] train=3.1076  mask=18.6%  norm=1.319  lr=2.96e-04  dt=  36.9ms  words=13,967,360
[E02   158/1548 G   1705|CLM] train=2.8571  mask=18.6%  norm=0.767  lr=2.96e-04  dt=  37.1ms  words=13,975,552
[E02   159/1548 G   1706|CLM] train=4.2836  mask=18.6%  norm=1.235  lr=2.96e-04  dt=  36.8ms  words=13,983,744
[E02   160/1548 G   1707|CLM] train=3.4457  mask=18.6%  norm=0.878  lr=2.96e-04  dt=  46.6ms  words=13,991,936
[E02   161/1548 G   1708|CLM] train=4.7668  mask=18.6%  norm=0.776  lr=2.96e-04  dt=  38.5ms  words=14,000,128
[E02   162/1548 G   1709|CLM] train=3.3634  mask=18.6%  norm=1.222  lr=2.96e-04  dt=  37.4ms  words=14,008,320
[E02   163/1548 G   1710|CLM] train=2.9695  mask=18.6%  norm=0.809  lr=2.96e-04  dt=  37.0ms  words=14,016,512
[E02   164/1548 G   1711|CLM] train=3.0189  mask=18.6%  norm=0.871  lr=2.96e-04  dt=  39.1ms  words=14,024,704
[E02   165/1548 G   1712|CLM] train=3.0340  mask=18.6%  norm=0.917  lr=2.96e-04  dt=  36.8ms  words=14,032,896
[E02   166/1548 G   1713|CLM] train=5.9657  mask=18.6%  norm=1.404  lr=2.96e-04  dt=  36.9ms  words=14,041,088
[E02   167/1548 G   1714|CLM] train=4.7065  mask=18.6%  norm=0.927  lr=2.96e-04  dt=  36.9ms  words=14,049,280
[E02   168/1548 G   1715|CLM] train=3.3175  mask=18.6%  norm=0.734  lr=2.96e-04  dt=  37.8ms  words=14,057,472
[E02   169/1548 G   1716|CLM] train=5.1051  mask=18.6%  norm=0.815  lr=2.96e-04  dt=  38.6ms  words=14,065,664
[E02   170/1548 G   1717|CLM] train=4.8008  mask=18.6%  norm=0.648  lr=2.96e-04  dt=  38.9ms  words=14,073,856
[E02   171/1548 G   1718|CLM] train=3.3539  mask=18.6%  norm=0.693  lr=2.96e-04  dt=  46.6ms  words=14,082,048
[E02   172/1548 G   1719|CLM] train=2.7327  mask=18.6%  norm=0.881  lr=2.96e-04  dt=  48.3ms  words=14,090,240
[E02   173/1548 G   1720|CLM] train=4.3902  mask=18.6%  norm=0.632  lr=2.96e-04  dt=  44.4ms  words=14,098,432
[E02   174/1548 G   1721|CLM] train=5.5719  mask=18.6%  norm=0.861  lr=2.96e-04  dt=  42.9ms  words=14,106,624
[E02   175/1548 G   1722|CLM] train=2.6899  mask=18.6%  norm=0.691  lr=2.96e-04  dt=  37.3ms  words=14,114,816
[E02   176/1548 G   1723|CLM] train=5.0984  mask=18.6%  norm=0.822  lr=2.96e-04  dt=  36.8ms  words=14,123,008
[E02   177/1548 G   1724|CLM] train=3.0475  mask=18.6%  norm=0.738  lr=2.96e-04  dt=  36.8ms  words=14,131,200
[E02   178/1548 G   1725|CLM] train=5.3153  mask=18.6%  norm=0.666  lr=2.96e-04  dt=  37.2ms  words=14,139,392
[E02   179/1548 G   1726|CLM] train=2.7893  mask=18.6%  norm=0.594  lr=2.96e-04  dt=  36.9ms  words=14,147,584
[E02   180/1548 G   1727|CLM] train=4.8342  mask=18.6%  norm=0.643  lr=2.96e-04  dt=  36.7ms  words=14,155,776
[E02   181/1548 G   1728|CLM] train=4.4239  mask=18.6%  norm=0.561  lr=2.96e-04  dt=  36.8ms  words=14,163,968
[E02   182/1548 G   1729|CLM] train=3.0825  mask=18.6%  norm=0.647  lr=2.96e-04  dt=  37.0ms  words=14,172,160
[E02   183/1548 G   1730|CLM] train=4.6323  mask=18.6%  norm=0.880  lr=2.95e-04  dt=  38.3ms  words=14,180,352
[E02   184/1548 G   1731|CLM] train=4.1866  mask=18.6%  norm=0.560  lr=2.95e-04  dt=  37.5ms  words=14,188,544
[E02   185/1548 G   1732|CLM] train=4.3618  mask=18.6%  norm=0.673  lr=2.95e-04  dt=  37.0ms  words=14,196,736
[E02   186/1548 G   1733|CLM] train=3.2910  mask=18.6%  norm=1.123  lr=2.95e-04  dt=  36.9ms  words=14,204,928
[E02   187/1548 G   1734|CLM] train=4.6150  mask=18.6%  norm=0.579  lr=2.95e-04  dt=  36.9ms  words=14,213,120
[E02   188/1548 G   1735|CLM] train=3.2554  mask=18.6%  norm=0.656  lr=2.95e-04  dt=  36.9ms  words=14,221,312
[E02   189/1548 G   1736|CLM] train=5.6869  mask=18.6%  norm=0.956  lr=2.95e-04  dt=  36.9ms  words=14,229,504
[E02   190/1548 G   1737|CLM] train=4.7314  mask=18.6%  norm=1.017  lr=2.95e-04  dt=  36.9ms  words=14,237,696
[E02   191/1548 G   1738|CLM] train=2.9001  mask=18.6%  norm=1.119  lr=2.95e-04  dt=  37.0ms  words=14,245,888
[E02   192/1548 G   1739|CLM] train=5.3135  mask=18.6%  norm=0.760  lr=2.95e-04  dt=  36.9ms  words=14,254,080
[E02   193/1548 G   1740|CLM] train=4.4594  mask=18.6%  norm=0.625  lr=2.95e-04  dt=  37.0ms  words=14,262,272
[E02   194/1548 G   1741|CLM] train=4.8831  mask=18.6%  norm=0.621  lr=2.95e-04  dt=  36.8ms  words=14,270,464
[E02   195/1548 G   1742|CLM] train=5.2964  mask=18.6%  norm=0.995  lr=2.95e-04  dt=  36.9ms  words=14,278,656
[E02   196/1548 G   1743|CLM] train=2.8114  mask=18.6%  norm=0.710  lr=2.95e-04  dt=  37.0ms  words=14,286,848
[E02   197/1548 G   1744|CLM] train=5.2356  mask=18.6%  norm=0.856  lr=2.95e-04  dt=  37.0ms  words=14,295,040
[E02   198/1548 G   1745|CLM] train=4.7517  mask=18.6%  norm=0.951  lr=2.95e-04  dt=  37.5ms  words=14,303,232
[E02   199/1548 G   1746|CLM] train=5.9528  mask=18.6%  norm=1.831  lr=2.95e-04  dt=  37.0ms  words=14,311,424
[E02   200/1548 G   1747|CLM] train=5.1224  mask=18.6%  norm=1.551  lr=2.95e-04  dt=  37.0ms  words=14,319,616
[E02   201/1548 G   1748|CLM] train=3.5239  mask=18.6%  norm=1.171  lr=2.95e-04  dt=  36.9ms  words=14,327,808
[E02   202/1548 G   1749|CLM] train=3.1217  mask=18.6%  norm=1.152  lr=2.95e-04  dt=  36.8ms  words=14,336,000
[E02   203/1548 G   1750|CLM] train=2.8809  mask=18.6%  norm=0.742  lr=2.95e-04  dt=  36.9ms  words=14,344,192
[E02   204/1548 G   1751|CLM] train=2.8042  mask=18.6%  norm=0.736  lr=2.95e-04  dt=  37.0ms  words=14,352,384
[E02   205/1548 G   1752|CLM] train=4.7312  mask=18.6%  norm=0.958  lr=2.95e-04  dt=  36.8ms  words=14,360,576
[E02   206/1548 G   1753|CLM] train=4.6847  mask=18.6%  norm=0.804  lr=2.95e-04  dt=  36.9ms  words=14,368,768
[E02   207/1548 G   1754|CLM] train=4.9215  mask=18.6%  norm=0.872  lr=2.95e-04  dt=  37.0ms  words=14,376,960
[E02   208/1548 G   1755|CLM] train=3.2381  mask=18.6%  norm=0.920  lr=2.95e-04  dt=  37.0ms  words=14,385,152
[E02   209/1548 G   1756|CLM] train=5.0375  mask=18.6%  norm=0.843  lr=2.95e-04  dt=  36.9ms  words=14,393,344
[E02   210/1548 G   1757|CLM] train=2.6642  mask=18.6%  norm=1.270  lr=2.95e-04  dt=  36.9ms  words=14,401,536
[E02   211/1548 G   1758|CLM] train=4.8762  mask=18.6%  norm=0.696  lr=2.95e-04  dt=  37.0ms  words=14,409,728
[E02   212/1548 G   1759|CLM] train=3.0636  mask=18.6%  norm=0.838  lr=2.95e-04  dt=  37.1ms  words=14,417,920
[E02   213/1548 G   1760|CLM] train=4.7901  mask=18.6%  norm=0.803  lr=2.95e-04  dt=  37.0ms  words=14,426,112
[E02   214/1548 G   1761|CLM] train=5.6612  mask=18.6%  norm=11.168  lr=2.95e-04  dt=  37.0ms  words=14,434,304
[E02   215/1548 G   1762|CLM] train=6.5451  mask=18.6%  norm=1.500  lr=2.95e-04  dt=  36.8ms  words=14,442,496
[E02   216/1548 G   1763|CLM] train=2.5764  mask=18.6%  norm=1.060  lr=2.95e-04  dt=  36.9ms  words=14,450,688
[E02   217/1548 G   1764|CLM] train=2.9411  mask=18.6%  norm=0.950  lr=2.95e-04  dt=  36.9ms  words=14,458,880
[E02   218/1548 G   1765|CLM] train=2.9026  mask=18.6%  norm=0.904  lr=2.95e-04  dt=  36.8ms  words=14,467,072
[E02   219/1548 G   1766|CLM] train=3.2009  mask=18.6%  norm=1.121  lr=2.95e-04  dt=  37.0ms  words=14,475,264
[E02   220/1548 G   1767|CLM] train=5.4014  mask=18.6%  norm=0.788  lr=2.95e-04  dt=  37.1ms  words=14,483,456
[E02   221/1548 G   1768|CLM] train=4.9935  mask=18.6%  norm=1.560  lr=2.95e-04  dt=  36.8ms  words=14,491,648
[E02   222/1548 G   1769|CLM] train=5.1463  mask=18.6%  norm=1.222  lr=2.95e-04  dt=  36.9ms  words=14,499,840
[E02   223/1548 G   1770|CLM] train=6.1152  mask=18.6%  norm=3.274  lr=2.95e-04  dt=  36.9ms  words=14,508,032
[E02   224/1548 G   1771|CLM] train=3.0505  mask=18.6%  norm=0.900  lr=2.95e-04  dt=  37.1ms  words=14,516,224
[E02   225/1548 G   1772|CLM] train=5.4158  mask=18.6%  norm=1.025  lr=2.95e-04  dt=  36.8ms  words=14,524,416
[E02   226/1548 G   1773|CLM] train=5.4585  mask=18.6%  norm=0.874  lr=2.95e-04  dt=  36.8ms  words=14,532,608
[E02   227/1548 G   1774|CLM] train=3.1308  mask=18.6%  norm=1.871  lr=2.95e-04  dt=  36.9ms  words=14,540,800
[E02   228/1548 G   1775|CLM] train=5.1479  mask=18.6%  norm=0.763  lr=2.95e-04  dt=  37.0ms  words=14,548,992
[E02   229/1548 G   1776|CLM] train=3.0714  mask=18.6%  norm=0.696  lr=2.95e-04  dt=  36.9ms  words=14,557,184
[E02   230/1548 G   1777|CLM] train=4.4035  mask=18.6%  norm=0.704  lr=2.95e-04  dt=  36.9ms  words=14,565,376
[E02   231/1548 G   1778|CLM] train=4.4669  mask=18.6%  norm=0.594  lr=2.95e-04  dt=  37.0ms  words=14,573,568
[E02   232/1548 G   1779|CLM] train=4.9672  mask=18.6%  norm=0.687  lr=2.95e-04  dt=  37.0ms  words=14,581,760
[E02   233/1548 G   1780|CLM] train=5.1113  mask=18.6%  norm=0.717  lr=2.95e-04  dt=  36.8ms  words=14,589,952
[E02   234/1548 G   1781|CLM] train=3.0316  mask=18.6%  norm=0.685  lr=2.95e-04  dt=  36.8ms  words=14,598,144
[E02   235/1548 G   1782|CLM] train=4.5841  mask=18.6%  norm=0.689  lr=2.95e-04  dt=  37.0ms  words=14,606,336
[E02   236/1548 G   1783|CLM] train=2.6641  mask=18.6%  norm=0.616  lr=2.95e-04  dt=  37.0ms  words=14,614,528
[E02   237/1548 G   1784|CLM] train=2.8438  mask=18.6%  norm=0.651  lr=2.95e-04  dt=  36.8ms  words=14,622,720
[E02   238/1548 G   1785|CLM] train=3.0094  mask=18.6%  norm=0.808  lr=2.95e-04  dt=  36.9ms  words=14,630,912
[E02   239/1548 G   1786|CLM] train=2.8433  mask=18.6%  norm=0.683  lr=2.95e-04  dt=  36.9ms  words=14,639,104
[E02   240/1548 G   1787|CLM] train=5.0447  mask=18.6%  norm=0.855  lr=2.95e-04  dt=  37.0ms  words=14,647,296
[E02   241/1548 G   1788|CLM] train=4.5483  mask=18.6%  norm=0.840  lr=2.95e-04  dt=  36.8ms  words=14,655,488
[E02   242/1548 G   1789|CLM] train=3.1548  mask=18.6%  norm=1.386  lr=2.95e-04  dt=  36.8ms  words=14,663,680
[E02   243/1548 G   1790|CLM] train=3.0717  mask=18.6%  norm=1.119  lr=2.95e-04  dt=  36.9ms  words=14,671,872
[E02   244/1548 G   1791|CLM] train=2.7166  mask=18.6%  norm=0.736  lr=2.95e-04  dt=  37.0ms  words=14,680,064
[E02   245/1548 G   1792|CLM] train=2.8861  mask=18.6%  norm=0.562  lr=2.95e-04  dt=  36.8ms  words=14,688,256
[E02   246/1548 G   1793|CLM] train=2.9702  mask=18.6%  norm=0.550  lr=2.95e-04  dt=  36.9ms  words=14,696,448
[E02   247/1548 G   1794|CLM] train=3.1334  mask=18.6%  norm=1.031  lr=2.95e-04  dt=  36.9ms  words=14,704,640
[E02   248/1548 G   1795|CLM] train=4.4873  mask=18.6%  norm=1.137  lr=2.95e-04  dt=  37.1ms  words=14,712,832
[E02   249/1548 G   1796|CLM] train=3.1222  mask=18.5%  norm=0.770  lr=2.95e-04  dt=  37.0ms  words=14,721,024
[E02   250/1548 G   1797|CLM] train=2.8006  mask=18.5%  norm=0.927  lr=2.95e-04  dt=  36.9ms  words=14,729,216
[E02   251/1548 G   1798|CLM] train=4.3570  mask=18.5%  norm=0.627  lr=2.95e-04  dt=  36.9ms  words=14,737,408
[E02   252/1548 G   1799|CLM] train=2.5718  mask=18.5%  norm=0.718  lr=2.95e-04  dt=  37.4ms  words=14,745,600
[E02   253/1548 G   1800|CLM] train=2.5106  mask=18.5%  norm=0.572  lr=2.95e-04  dt=  36.8ms  words=14,753,792
[E02   254/1548 G   1801|CLM] train=2.7831  mask=18.5%  norm=0.731  lr=2.95e-04  dt=  36.9ms  words=14,761,984
[E02   255/1548 G   1802|CLM] train=2.7119  mask=18.5%  norm=0.740  lr=2.95e-04  dt=  36.9ms  words=14,770,176
[E02   256/1548 G   1803|CLM] train=4.8160  mask=18.5%  norm=0.656  lr=2.95e-04  dt=  37.1ms  words=14,778,368
[E02   257/1548 G   1804|CLM] train=2.6843  mask=18.5%  norm=0.511  lr=2.95e-04  dt=  36.8ms  words=14,786,560
[E02   258/1548 G   1805|CLM] train=4.5383  mask=18.5%  norm=1.149  lr=2.95e-04  dt=  36.8ms  words=14,794,752
[E02   259/1548 G   1806|CLM] train=2.7858  mask=18.5%  norm=0.826  lr=2.95e-04  dt=  37.0ms  words=14,802,944
[E02   260/1548 G   1807|CLM] train=2.6394  mask=18.5%  norm=0.554  lr=2.95e-04  dt=  37.1ms  words=14,811,136
[E02   261/1548 G   1808|CLM] train=5.0446  mask=18.5%  norm=0.699  lr=2.95e-04  dt=  36.9ms  words=14,819,328
[E02   262/1548 G   1809|CLM] train=4.4717  mask=18.5%  norm=0.815  lr=2.95e-04  dt=  36.7ms  words=14,827,520
[E02   263/1548 G   1810|CLM] train=2.9080  mask=18.5%  norm=1.050  lr=2.95e-04  dt=  37.0ms  words=14,835,712
[E02   264/1548 G   1811|CLM] train=4.5564  mask=18.5%  norm=0.658  lr=2.95e-04  dt=  37.0ms  words=14,843,904
[E02   265/1548 G   1812|CLM] train=4.8684  mask=18.5%  norm=1.017  lr=2.95e-04  dt=  36.9ms  words=14,852,096
[E02   266/1548 G   1813|CLM] train=5.4624  mask=18.5%  norm=0.870  lr=2.95e-04  dt=  36.8ms  words=14,860,288
[E02   267/1548 G   1814|CLM] train=4.1314  mask=18.5%  norm=0.673  lr=2.95e-04  dt=  36.9ms  words=14,868,480
[E02   268/1548 G   1815|CLM] train=5.0833  mask=18.5%  norm=1.047  lr=2.95e-04  dt=  36.9ms  words=14,876,672
[E02   269/1548 G   1816|CLM] train=3.4972  mask=18.5%  norm=1.047  lr=2.95e-04  dt=  36.9ms  words=14,884,864
[E02   270/1548 G   1817|CLM] train=4.9971  mask=18.5%  norm=0.678  lr=2.95e-04  dt=  36.8ms  words=14,893,056
[E02   271/1548 G   1818|CLM] train=4.6857  mask=18.5%  norm=0.640  lr=2.95e-04  dt=  36.9ms  words=14,901,248
[E02   272/1548 G   1819|CLM] train=2.7989  mask=18.5%  norm=0.986  lr=2.95e-04  dt=  36.9ms  words=14,909,440
[E02   273/1548 G   1820|CLM] train=4.3876  mask=18.5%  norm=2.572  lr=2.95e-04  dt=  37.0ms  words=14,917,632
[E02   274/1548 G   1821|CLM] train=4.5219  mask=18.5%  norm=1.093  lr=2.95e-04  dt=  36.9ms  words=14,925,824
[E02   275/1548 G   1822|CLM] train=5.0587  mask=18.5%  norm=0.730  lr=2.95e-04  dt=  36.9ms  words=14,934,016
[E02   276/1548 G   1823|CLM] train=2.7088  mask=18.5%  norm=0.807  lr=2.95e-04  dt=  37.4ms  words=14,942,208
[E02   277/1548 G   1824|CLM] train=5.3862  mask=18.5%  norm=0.829  lr=2.95e-04  dt=  36.9ms  words=14,950,400
[E02   278/1548 G   1825|CLM] train=2.5797  mask=18.5%  norm=0.630  lr=2.95e-04  dt=  36.8ms  words=14,958,592
[E02   279/1548 G   1826|CLM] train=2.7728  mask=18.5%  norm=0.523  lr=2.95e-04  dt=  37.1ms  words=14,966,784
[E02   280/1548 G   1827|CLM] train=3.2418  mask=18.5%  norm=0.692  lr=2.95e-04  dt=  36.9ms  words=14,974,976
[E02   281/1548 G   1828|CLM] train=5.4134  mask=18.5%  norm=0.711  lr=2.94e-04  dt=  36.7ms  words=14,983,168
[E02   282/1548 G   1829|CLM] train=4.7215  mask=18.5%  norm=0.688  lr=2.94e-04  dt=  36.8ms  words=14,991,360
[E02   283/1548 G   1830|CLM] train=6.2893  mask=18.5%  norm=1.357  lr=2.94e-04  dt=  36.8ms  words=14,999,552
[E02   284/1548 G   1831|CLM] train=2.8428  mask=18.5%  norm=0.741  lr=2.94e-04  dt=  37.0ms  words=15,007,744
[E02   285/1548 G   1832|CLM] train=4.3301  mask=18.5%  norm=0.650  lr=2.94e-04  dt=  36.9ms  words=15,015,936
[E02   286/1548 G   1833|CLM] train=5.0127  mask=18.5%  norm=2.681  lr=2.94e-04  dt=  36.9ms  words=15,024,128
[E02   287/1548 G   1834|CLM] train=3.8739  mask=18.5%  norm=0.637  lr=2.94e-04  dt=  37.0ms  words=15,032,320
[E02   288/1548 G   1835|CLM] train=5.2930  mask=18.5%  norm=0.722  lr=2.94e-04  dt=  36.9ms  words=15,040,512
[E02   289/1548 G   1836|CLM] train=2.9969  mask=18.5%  norm=0.828  lr=2.94e-04  dt=  36.9ms  words=15,048,704
[E02   290/1548 G   1837|CLM] train=2.8150  mask=18.5%  norm=0.888  lr=2.94e-04  dt=  36.9ms  words=15,056,896
[E02   291/1548 G   1838|CLM] train=5.4863  mask=18.5%  norm=0.731  lr=2.94e-04  dt=  36.8ms  words=15,065,088
[E02   292/1548 G   1839|CLM] train=5.5298  mask=18.5%  norm=1.006  lr=2.94e-04  dt=  37.3ms  words=15,073,280
[E02   293/1548 G   1840|CLM] train=4.8790  mask=18.5%  norm=0.741  lr=2.94e-04  dt=  37.2ms  words=15,081,472
[E02   294/1548 G   1841|CLM] train=4.1848  mask=18.5%  norm=0.799  lr=2.94e-04  dt=  39.3ms  words=15,089,664
[E02   295/1548 G   1842|CLM] train=4.0563  mask=18.5%  norm=0.705  lr=2.94e-04  dt=  45.6ms  words=15,097,856
[E02   296/1548 G   1843|CLM] train=5.1122  mask=18.5%  norm=0.725  lr=2.94e-04  dt=  42.4ms  words=15,106,048
[E02   297/1548 G   1844|CLM] train=4.6259  mask=18.5%  norm=0.535  lr=2.94e-04  dt=  38.7ms  words=15,114,240
[E02   298/1548 G   1845|CLM] train=4.1970  mask=18.5%  norm=0.493  lr=2.94e-04  dt=  38.7ms  words=15,122,432
[E02   299/1548 G   1846|CLM] train=6.4266  mask=18.5%  norm=1.532  lr=2.94e-04  dt=  42.0ms  words=15,130,624
[E02   300/1548 G   1847|CLM] train=4.6749  mask=18.5%  norm=0.816  lr=2.94e-04  dt=  43.0ms  words=15,138,816
[E02   301/1548 G   1848|CLM] train=2.7067  mask=18.5%  norm=0.961  lr=2.94e-04  dt=  42.0ms  words=15,147,008
[E02   302/1548 G   1849|CLM] train=4.5886  mask=18.5%  norm=0.661  lr=2.94e-04  dt=  37.1ms  words=15,155,200
[E02   303/1548 G   1850|CLM] train=2.8176  mask=18.5%  norm=0.698  lr=2.94e-04  dt=  41.3ms  words=15,163,392
[E02   304/1548 G   1851|CLM] train=4.8176  mask=18.5%  norm=0.647  lr=2.94e-04  dt=  37.2ms  words=15,171,584
[E02   305/1548 G   1852|CLM] train=3.1393  mask=18.5%  norm=0.781  lr=2.94e-04  dt=  37.7ms  words=15,179,776
[E02   306/1548 G   1853|CLM] train=4.5991  mask=18.5%  norm=0.557  lr=2.94e-04  dt=  44.7ms  words=15,187,968
[E02   307/1548 G   1854|CLM] train=5.7655  mask=18.5%  norm=1.039  lr=2.94e-04  dt=  37.8ms  words=15,196,160
[E02   308/1548 G   1855|CLM] train=2.8179  mask=18.5%  norm=0.677  lr=2.94e-04  dt=  37.3ms  words=15,204,352
[E02   309/1548 G   1856|CLM] train=5.2044  mask=18.5%  norm=0.731  lr=2.94e-04  dt=  37.1ms  words=15,212,544
[E02   310/1548 G   1857|CLM] train=5.3731  mask=18.5%  norm=0.894  lr=2.94e-04  dt=  37.1ms  words=15,220,736
[E02   311/1548 G   1858|CLM] train=3.3890  mask=18.5%  norm=0.852  lr=2.94e-04  dt=  36.9ms  words=15,228,928
[E02   312/1548 G   1859|CLM] train=4.8300  mask=18.5%  norm=0.695  lr=2.94e-04  dt=  37.0ms  words=15,237,120
[E02   313/1548 G   1860|CLM] train=5.3515  mask=18.5%  norm=0.814  lr=2.94e-04  dt=  36.8ms  words=15,245,312
[E02   314/1548 G   1861|CLM] train=5.2888  mask=18.5%  norm=0.936  lr=2.94e-04  dt=  46.1ms  words=15,253,504
[E02   315/1548 G   1862|CLM] train=3.0243  mask=18.5%  norm=0.855  lr=2.94e-04  dt=  37.1ms  words=15,261,696
[E02   316/1548 G   1863|CLM] train=5.9724  mask=18.5%  norm=0.907  lr=2.94e-04  dt=  45.5ms  words=15,269,888
[E02   317/1548 G   1864|CLM] train=3.1713  mask=18.5%  norm=0.827  lr=2.94e-04  dt=  45.8ms  words=15,278,080
[E02   318/1548 G   1865|CLM] train=2.8643  mask=18.5%  norm=0.956  lr=2.94e-04  dt=  47.1ms  words=15,286,272
[E02   319/1548 G   1866|CLM] train=2.9731  mask=18.5%  norm=1.036  lr=2.94e-04  dt=  39.1ms  words=15,294,464
[E02   320/1548 G   1867|CLM] train=2.5566  mask=18.5%  norm=0.573  lr=2.94e-04  dt=  42.4ms  words=15,302,656
[E02   321/1548 G   1868|CLM] train=6.0292  mask=18.5%  norm=0.973  lr=2.94e-04  dt=  42.4ms  words=15,310,848
[E02   322/1548 G   1869|CLM] train=4.4587  mask=18.5%  norm=0.921  lr=2.94e-04  dt=  37.7ms  words=15,319,040
[E02   323/1548 G   1870|CLM] train=4.8600  mask=18.5%  norm=0.745  lr=2.94e-04  dt=  43.2ms  words=15,327,232
[E02   324/1548 G   1871|CLM] train=2.5999  mask=18.5%  norm=0.814  lr=2.94e-04  dt=  46.7ms  words=15,335,424
[E02   325/1548 G   1872|CLM] train=2.8560  mask=18.5%  norm=0.808  lr=2.94e-04  dt=  40.4ms  words=15,343,616
[E02   326/1548 G   1873|CLM] train=2.8602  mask=18.5%  norm=0.787  lr=2.94e-04  dt=  46.7ms  words=15,351,808
[E02   327/1548 G   1874|CLM] train=6.3229  mask=18.5%  norm=1.234  lr=2.94e-04  dt=  47.7ms  words=15,360,000
[E02   328/1548 G   1875|CLM] train=4.3667  mask=18.5%  norm=0.683  lr=2.94e-04  dt=  45.5ms  words=15,368,192
[E02   329/1548 G   1876|CLM] train=3.1618  mask=18.5%  norm=0.750  lr=2.94e-04  dt=  46.0ms  words=15,376,384
[E02   330/1548 G   1877|CLM] train=4.5091  mask=18.5%  norm=0.705  lr=2.94e-04  dt=  37.3ms  words=15,384,576
[E02   331/1548 G   1878|CLM] train=5.8112  mask=18.5%  norm=0.903  lr=2.94e-04  dt=  37.1ms  words=15,392,768
[E02   332/1548 G   1879|CLM] train=5.4483  mask=18.5%  norm=0.600  lr=2.94e-04  dt=  37.3ms  words=15,400,960
[E02   333/1548 G   1880|CLM] train=2.8523  mask=18.5%  norm=0.933  lr=2.94e-04  dt=  37.4ms  words=15,409,152
[E02   334/1548 G   1881|CLM] train=3.1017  mask=18.5%  norm=0.730  lr=2.94e-04  dt=  37.6ms  words=15,417,344
[E02   335/1548 G   1882|CLM] train=2.3571  mask=18.5%  norm=0.620  lr=2.94e-04  dt=  37.5ms  words=15,425,536
[E02   336/1548 G   1883|CLM] train=5.0170  mask=18.5%  norm=0.797  lr=2.94e-04  dt=  37.5ms  words=15,433,728
[E02   337/1548 G   1884|CLM] train=2.8784  mask=18.5%  norm=0.674  lr=2.94e-04  dt=  36.9ms  words=15,441,920
[E02   338/1548 G   1885|CLM] train=5.0566  mask=18.5%  norm=0.655  lr=2.94e-04  dt=  37.2ms  words=15,450,112
[E02   339/1548 G   1886|CLM] train=2.8837  mask=18.5%  norm=0.716  lr=2.94e-04  dt=  37.3ms  words=15,458,304
[E02   340/1548 G   1887|CLM] train=3.4637  mask=18.5%  norm=0.716  lr=2.94e-04  dt=  37.3ms  words=15,466,496
[E02   341/1548 G   1888|CLM] train=4.5058  mask=18.5%  norm=1.212  lr=2.94e-04  dt=  37.0ms  words=15,474,688
[E02   342/1548 G   1889|CLM] train=2.8766  mask=18.5%  norm=0.514  lr=2.94e-04  dt=  37.0ms  words=15,482,880
[E02   343/1548 G   1890|CLM] train=5.2455  mask=18.5%  norm=0.908  lr=2.94e-04  dt=  37.1ms  words=15,491,072
[E02   344/1548 G   1891|CLM] train=5.3808  mask=18.5%  norm=0.736  lr=2.94e-04  dt=  37.3ms  words=15,499,264
[E02   345/1548 G   1892|CLM] train=5.1217  mask=18.5%  norm=0.659  lr=2.94e-04  dt=  37.1ms  words=15,507,456
[E02   346/1548 G   1893|CLM] train=4.8749  mask=18.5%  norm=0.809  lr=2.94e-04  dt=  37.0ms  words=15,515,648
[E02   347/1548 G   1894|CLM] train=5.2244  mask=18.5%  norm=1.871  lr=2.94e-04  dt=  37.2ms  words=15,523,840
[E02   348/1548 G   1895|CLM] train=2.9584  mask=18.5%  norm=0.704  lr=2.94e-04  dt=  37.1ms  words=15,532,032
[E02   349/1548 G   1896|CLM] train=3.2918  mask=18.5%  norm=0.982  lr=2.94e-04  dt=  37.1ms  words=15,540,224
[E02   350/1548 G   1897|CLM] train=4.8489  mask=18.5%  norm=0.844  lr=2.94e-04  dt=  37.0ms  words=15,548,416
[E02   351/1548 G   1898|CLM] train=4.3580  mask=18.5%  norm=0.828  lr=2.94e-04  dt=  37.0ms  words=15,556,608
[E02   352/1548 G   1899|CLM] train=4.9664  mask=18.5%  norm=1.128  lr=2.94e-04  dt=  37.0ms  words=15,564,800
[E02   353/1548 G   1900|CLM] train=5.1984  mask=18.5%  norm=0.997  lr=2.94e-04  dt=  37.0ms  words=15,572,992
[E02   354/1548 G   1901|CLM] train=3.3702  mask=18.5%  norm=0.840  lr=2.94e-04  dt=  37.1ms  words=15,581,184
[E02   355/1548 G   1902|CLM] train=4.9296  mask=18.5%  norm=1.109  lr=2.94e-04  dt=  37.7ms  words=15,589,376
[E02   356/1548 G   1903|CLM] train=4.8244  mask=18.5%  norm=0.738  lr=2.94e-04  dt=  37.5ms  words=15,597,568
[E02   357/1548 G   1904|CLM] train=2.7267  mask=18.5%  norm=0.915  lr=2.94e-04  dt=  37.3ms  words=15,605,760
[E02   358/1548 G   1905|CLM] train=3.1521  mask=18.5%  norm=0.974  lr=2.94e-04  dt=  37.4ms  words=15,613,952
[E02   359/1548 G   1906|CLM] train=4.6712  mask=18.5%  norm=1.161  lr=2.94e-04  dt=  37.4ms  words=15,622,144
[E02   360/1548 G   1907|CLM] train=4.5366  mask=18.5%  norm=0.717  lr=2.94e-04  dt=  37.1ms  words=15,630,336
[E02   361/1548 G   1908|CLM] train=4.8673  mask=18.5%  norm=0.691  lr=2.94e-04  dt=  36.9ms  words=15,638,528
[E02   362/1548 G   1909|CLM] train=3.2340  mask=18.5%  norm=0.812  lr=2.94e-04  dt=  37.0ms  words=15,646,720
[E02   363/1548 G   1910|CLM] train=6.1443  mask=18.5%  norm=0.968  lr=2.94e-04  dt=  37.0ms  words=15,654,912
[E02   364/1548 G   1911|CLM] train=2.5519  mask=18.5%  norm=0.757  lr=2.94e-04  dt=  36.9ms  words=15,663,104
[E02   365/1548 G   1912|CLM] train=3.1112  mask=18.5%  norm=0.680  lr=2.94e-04  dt=  37.2ms  words=15,671,296
[E02   366/1548 G   1913|CLM] train=4.3168  mask=18.5%  norm=0.831  lr=2.94e-04  dt=  36.9ms  words=15,679,488
[E02   367/1548 G   1914|CLM] train=4.7594  mask=18.5%  norm=0.756  lr=2.94e-04  dt=  37.0ms  words=15,687,680
[E02   368/1548 G   1915|CLM] train=5.3209  mask=18.5%  norm=0.862  lr=2.94e-04  dt=  37.2ms  words=15,695,872
[E02   369/1548 G   1916|CLM] train=4.6232  mask=18.5%  norm=0.837  lr=2.94e-04  dt=  37.2ms  words=15,704,064
[E02   370/1548 G   1917|CLM] train=5.3593  mask=18.5%  norm=0.815  lr=2.94e-04  dt=  36.8ms  words=15,712,256
[E02   371/1548 G   1918|CLM] train=5.7821  mask=18.5%  norm=0.863  lr=2.93e-04  dt=  36.9ms  words=15,720,448
[E02   372/1548 G   1919|CLM] train=4.6352  mask=18.5%  norm=0.714  lr=2.93e-04  dt=  36.9ms  words=15,728,640
[E02   373/1548 G   1920|CLM] train=3.1373  mask=18.4%  norm=0.953  lr=2.93e-04  dt=  37.0ms  words=15,736,832
[E02   374/1548 G   1921|CLM] train=4.9355  mask=18.4%  norm=0.874  lr=2.93e-04  dt=  36.9ms  words=15,745,024
[E02   375/1548 G   1922|CLM] train=6.5907  mask=18.4%  norm=1.272  lr=2.93e-04  dt=  37.0ms  words=15,753,216
[E02   376/1548 G   1923|CLM] train=4.8569  mask=18.4%  norm=1.356  lr=2.93e-04  dt=  37.0ms  words=15,761,408
[E02   377/1548 G   1924|CLM] train=4.3539  mask=18.4%  norm=2.363  lr=2.93e-04  dt=  37.1ms  words=15,769,600
[E02   378/1548 G   1925|CLM] train=5.1274  mask=18.4%  norm=1.047  lr=2.93e-04  dt=  37.0ms  words=15,777,792
[E02   379/1548 G   1926|CLM] train=3.2993  mask=18.4%  norm=1.024  lr=2.93e-04  dt=  37.1ms  words=15,785,984
[E02   380/1548 G   1927|CLM] train=4.5195  mask=18.4%  norm=0.865  lr=2.93e-04  dt=  37.1ms  words=15,794,176
[E02   381/1548 G   1928|CLM] train=3.3475  mask=18.4%  norm=1.369  lr=2.93e-04  dt=  36.9ms  words=15,802,368
[E02   382/1548 G   1929|CLM] train=5.1593  mask=18.4%  norm=0.816  lr=2.93e-04  dt=  37.0ms  words=15,810,560
[E02   383/1548 G   1930|CLM] train=2.8810  mask=18.4%  norm=0.622  lr=2.93e-04  dt=  37.0ms  words=15,818,752
[E02   384/1548 G   1931|CLM] train=3.0474  mask=18.4%  norm=0.625  lr=2.93e-04  dt=  37.0ms  words=15,826,944
[E02   385/1548 G   1932|CLM] train=4.9635  mask=18.4%  norm=1.340  lr=2.93e-04  dt=  36.9ms  words=15,835,136
[E02   386/1548 G   1933|CLM] train=6.2022  mask=18.4%  norm=1.681  lr=2.93e-04  dt=  36.9ms  words=15,843,328
[E02   387/1548 G   1934|CLM] train=5.8723  mask=18.4%  norm=1.482  lr=2.93e-04  dt=  37.2ms  words=15,851,520
[E02   388/1548 G   1935|CLM] train=4.9405  mask=18.4%  norm=1.011  lr=2.93e-04  dt=  37.1ms  words=15,859,712
[E02   389/1548 G   1936|CLM] train=4.4436  mask=18.4%  norm=0.770  lr=2.93e-04  dt=  37.0ms  words=15,867,904
[E02   390/1548 G   1937|CLM] train=5.1174  mask=18.4%  norm=0.605  lr=2.93e-04  dt=  37.1ms  words=15,876,096
[E02   391/1548 G   1938|CLM] train=5.0406  mask=18.4%  norm=0.918  lr=2.93e-04  dt=  37.0ms  words=15,884,288
[E02   392/1548 G   1939|CLM] train=3.1595  mask=18.4%  norm=0.637  lr=2.93e-04  dt=  36.9ms  words=15,892,480
[E02   393/1548 G   1940|CLM] train=5.5349  mask=18.4%  norm=0.996  lr=2.93e-04  dt=  37.0ms  words=15,900,672
[E02   394/1548 G   1941|CLM] train=5.7767  mask=18.4%  norm=0.840  lr=2.93e-04  dt=  36.9ms  words=15,908,864
[E02   395/1548 G   1942|CLM] train=5.2142  mask=18.4%  norm=0.932  lr=2.93e-04  dt=  37.1ms  words=15,917,056
[E02   396/1548 G   1943|CLM] train=5.6793  mask=18.4%  norm=0.736  lr=2.93e-04  dt=  37.1ms  words=15,925,248
[E02   397/1548 G   1944|CLM] train=4.4698  mask=18.4%  norm=0.821  lr=2.93e-04  dt=  37.1ms  words=15,933,440
[E02   398/1548 G   1945|CLM] train=2.4869  mask=18.4%  norm=1.368  lr=2.93e-04  dt=  37.2ms  words=15,941,632
[E02   399/1548 G   1946|CLM] train=4.4855  mask=18.4%  norm=0.751  lr=2.93e-04  dt=  36.9ms  words=15,949,824
[E02   400/1548 G   1947|CLM] train=4.9999  mask=18.4%  norm=0.843  lr=2.93e-04  dt=  37.0ms  words=15,958,016
[E02   401/1548 G   1948|CLM] train=2.9527  mask=18.4%  norm=0.747  lr=2.93e-04  dt=  37.0ms  words=15,966,208
[E02   402/1548 G   1949|CLM] train=5.5670  mask=18.4%  norm=1.116  lr=2.93e-04  dt=  37.0ms  words=15,974,400
[E02   403/1548 G   1950|CLM] train=5.6390  mask=18.4%  norm=1.186  lr=2.93e-04  dt=  37.1ms  words=15,982,592
[E02   404/1548 G   1951|CLM] train=2.8936  mask=18.4%  norm=0.863  lr=2.93e-04  dt=  37.1ms  words=15,990,784
[E02   405/1548 G   1952|CLM] train=2.8016  mask=18.4%  norm=0.752  lr=2.93e-04  dt=  37.1ms  words=15,998,976
[E02   406/1548 G   1953|CLM] train=2.6649  mask=18.4%  norm=0.764  lr=2.93e-04  dt=  37.2ms  words=16,007,168
[E02   407/1548 G   1954|CLM] train=6.1791  mask=18.4%  norm=3.962  lr=2.93e-04  dt=  37.0ms  words=16,015,360
[E02   408/1548 G   1955|CLM] train=4.6371  mask=18.4%  norm=0.897  lr=2.93e-04  dt=  36.8ms  words=16,023,552
[E02   409/1548 G   1956|CLM] train=3.2531  mask=18.4%  norm=0.787  lr=2.93e-04  dt=  37.0ms  words=16,031,744
[E02   410/1548 G   1957|CLM] train=5.9982  mask=18.4%  norm=1.559  lr=2.93e-04  dt=  37.0ms  words=16,039,936
[E02   411/1548 G   1958|CLM] train=5.4178  mask=18.4%  norm=1.033  lr=2.93e-04  dt=  37.2ms  words=16,048,128
[E02   412/1548 G   1959|CLM] train=4.6767  mask=18.4%  norm=1.307  lr=2.93e-04  dt=  37.2ms  words=16,056,320
[E02   413/1548 G   1960|CLM] train=4.9344  mask=18.4%  norm=1.163  lr=2.93e-04  dt=  37.2ms  words=16,064,512
[E02   414/1548 G   1961|CLM] train=3.5992  mask=18.4%  norm=0.875  lr=2.93e-04  dt=  37.0ms  words=16,072,704
[E02   415/1548 G   1962|CLM] train=4.5100  mask=18.4%  norm=0.720  lr=2.93e-04  dt=  36.9ms  words=16,080,896
[E02   416/1548 G   1963|CLM] train=2.7746  mask=18.4%  norm=1.122  lr=2.93e-04  dt=  37.0ms  words=16,089,088
[E02   417/1548 G   1964|CLM] train=5.2283  mask=18.4%  norm=0.974  lr=2.93e-04  dt=  37.1ms  words=16,097,280
[E02   418/1548 G   1965|CLM] train=4.9243  mask=18.4%  norm=0.721  lr=2.93e-04  dt=  37.1ms  words=16,105,472
[E02   419/1548 G   1966|CLM] train=5.6222  mask=18.4%  norm=0.777  lr=2.93e-04  dt=  37.2ms  words=16,113,664
[E02   420/1548 G   1967|CLM] train=2.7390  mask=18.4%  norm=0.948  lr=2.93e-04  dt=  37.0ms  words=16,121,856
[E02   421/1548 G   1968|CLM] train=4.5039  mask=18.4%  norm=0.661  lr=2.93e-04  dt=  36.9ms  words=16,130,048
[E02   422/1548 G   1969|CLM] train=4.3741  mask=18.4%  norm=1.827  lr=2.93e-04  dt=  37.0ms  words=16,138,240
[E02   423/1548 G   1970|CLM] train=4.6992  mask=18.4%  norm=0.657  lr=2.93e-04  dt=  37.2ms  words=16,146,432
[E02   424/1548 G   1971|CLM] train=6.3272  mask=18.4%  norm=4.229  lr=2.93e-04  dt=  46.5ms  words=16,154,624
[E02   425/1548 G   1972|CLM] train=5.2616  mask=18.4%  norm=0.761  lr=2.93e-04  dt=  45.9ms  words=16,162,816
[E02   426/1548 G   1973|CLM] train=3.0671  mask=18.4%  norm=1.006  lr=2.93e-04  dt=  37.5ms  words=16,171,008
[E02   427/1548 G   1974|CLM] train=5.2680  mask=18.4%  norm=0.852  lr=2.93e-04  dt=  37.6ms  words=16,179,200
[E02   428/1548 G   1975|CLM] train=5.1243  mask=18.4%  norm=1.067  lr=2.93e-04  dt=  37.6ms  words=16,187,392
[E02   429/1548 G   1976|CLM] train=4.5029  mask=18.4%  norm=0.803  lr=2.93e-04  dt=  37.6ms  words=16,195,584
[E02   430/1548 G   1977|CLM] train=2.6905  mask=18.4%  norm=0.918  lr=2.93e-04  dt=  42.9ms  words=16,203,776
[E02   431/1548 G   1978|CLM] train=3.1517  mask=18.4%  norm=0.770  lr=2.93e-04  dt=  43.2ms  words=16,211,968
[E02   432/1548 G   1979|CLM] train=2.6173  mask=18.4%  norm=0.997  lr=2.93e-04  dt=  41.5ms  words=16,220,160
[E02   433/1548 G   1980|CLM] train=2.6936  mask=18.4%  norm=0.882  lr=2.93e-04  dt=  37.4ms  words=16,228,352
[E02   434/1548 G   1981|CLM] train=4.8968  mask=18.4%  norm=1.256  lr=2.93e-04  dt=  41.4ms  words=16,236,544
[E02   435/1548 G   1982|CLM] train=5.3505  mask=18.4%  norm=0.847  lr=2.93e-04  dt=  38.7ms  words=16,244,736
[E02   436/1548 G   1983|CLM] train=2.7446  mask=18.4%  norm=0.870  lr=2.93e-04  dt=  38.1ms  words=16,252,928
[E02   437/1548 G   1984|CLM] train=2.6031  mask=18.4%  norm=1.349  lr=2.93e-04  dt=  37.2ms  words=16,261,120
[E02   438/1548 G   1985|CLM] train=5.1167  mask=18.4%  norm=0.926  lr=2.93e-04  dt=  37.0ms  words=16,269,312
[E02   439/1548 G   1986|CLM] train=4.5193  mask=18.4%  norm=0.618  lr=2.93e-04  dt=  37.1ms  words=16,277,504
[E02   440/1548 G   1987|CLM] train=2.8707  mask=18.4%  norm=0.632  lr=2.93e-04  dt=  37.1ms  words=16,285,696
[E02   441/1548 G   1988|CLM] train=5.3706  mask=18.4%  norm=0.841  lr=2.93e-04  dt=  38.5ms  words=16,293,888
[E02   442/1548 G   1989|CLM] train=3.0165  mask=18.4%  norm=1.033  lr=2.93e-04  dt=  39.6ms  words=16,302,080
[E02   443/1548 G   1990|CLM] train=5.1210  mask=18.4%  norm=0.853  lr=2.93e-04  dt=  41.7ms  words=16,310,272
[E02   444/1548 G   1991|CLM] train=3.2138  mask=18.4%  norm=0.747  lr=2.93e-04  dt=  47.0ms  words=16,318,464
[E02   445/1548 G   1992|CLM] train=2.8824  mask=18.4%  norm=0.744  lr=2.93e-04  dt=  42.8ms  words=16,326,656
[E02   446/1548 G   1993|CLM] train=4.0649  mask=18.4%  norm=0.673  lr=2.93e-04  dt=  37.1ms  words=16,334,848
[E02   447/1548 G   1994|CLM] train=5.1277  mask=18.4%  norm=0.630  lr=2.93e-04  dt=  37.2ms  words=16,343,040
[E02   448/1548 G   1995|CLM] train=4.3190  mask=18.4%  norm=0.695  lr=2.93e-04  dt=  37.0ms  words=16,351,232
[E02   449/1548 G   1996|CLM] train=2.6590  mask=18.4%  norm=0.641  lr=2.93e-04  dt=  37.1ms  words=16,359,424
[E02   450/1548 G   1997|CLM] train=4.5469  mask=18.4%  norm=0.533  lr=2.93e-04  dt=  37.1ms  words=16,367,616
[E02   451/1548 G   1998|CLM] train=5.2249  mask=18.4%  norm=1.170  lr=2.93e-04  dt=  37.0ms  words=16,375,808
[E02   452/1548 G   1999|CLM] train=4.5841  mask=18.4%  norm=0.563  lr=2.93e-04  dt=  37.0ms  words=16,384,000
[E02   453/1548 G   2000|CLM] train=5.3440  mask=18.4%  norm=0.935  lr=2.93e-04  dt=  39.6ms  words=16,392,192
[E02   454/1548 G   2001|CLM] train=4.7479  mask=18.4%  norm=0.763  lr=2.93e-04  dt=  37.0ms  words=16,400,384
[E02   455/1548 G   2002|CLM] train=4.8265  mask=18.4%  norm=0.581  lr=2.92e-04  dt=  37.1ms  words=16,408,576
[E02   456/1548 G   2003|CLM] train=5.6314  mask=18.4%  norm=0.718  lr=2.92e-04  dt=  37.1ms  words=16,416,768
[E02   457/1548 G   2004|CLM] train=2.6877  mask=18.4%  norm=1.442  lr=2.92e-04  dt=  37.1ms  words=16,424,960
[E02   458/1548 G   2005|CLM] train=3.3019  mask=18.4%  norm=0.866  lr=2.92e-04  dt=  37.1ms  words=16,433,152
[E02   459/1548 G   2006|CLM] train=4.5012  mask=18.4%  norm=0.716  lr=2.92e-04  dt=  37.0ms  words=16,441,344
[E02   460/1548 G   2007|CLM] train=5.2129  mask=18.4%  norm=0.775  lr=2.92e-04  dt=  36.9ms  words=16,449,536
[E02   461/1548 G   2008|CLM] train=4.4621  mask=18.4%  norm=0.634  lr=2.92e-04  dt=  36.9ms  words=16,457,728
[E02   462/1548 G   2009|CLM] train=2.9491  mask=18.4%  norm=0.882  lr=2.92e-04  dt=  37.1ms  words=16,465,920
[E02   463/1548 G   2010|CLM] train=4.9722  mask=18.4%  norm=0.758  lr=2.92e-04  dt=  37.0ms  words=16,474,112
[E02   464/1548 G   2011|CLM] train=5.3620  mask=18.4%  norm=0.609  lr=2.92e-04  dt=  37.1ms  words=16,482,304
[E02   465/1548 G   2012|CLM] train=4.1926  mask=18.4%  norm=0.669  lr=2.92e-04  dt=  37.2ms  words=16,490,496
[E02   466/1548 G   2013|CLM] train=2.8557  mask=18.4%  norm=0.759  lr=2.92e-04  dt=  37.0ms  words=16,498,688
[E02   467/1548 G   2014|CLM] train=5.5271  mask=18.4%  norm=0.708  lr=2.92e-04  dt=  37.1ms  words=16,506,880
[E02   468/1548 G   2015|CLM] train=4.6913  mask=18.4%  norm=0.895  lr=2.92e-04  dt=  37.0ms  words=16,515,072
[E02   469/1548 G   2016|CLM] train=3.9870  mask=18.4%  norm=0.663  lr=2.92e-04  dt=  37.0ms  words=16,523,264
[E02   470/1548 G   2017|CLM] train=5.2534  mask=18.4%  norm=0.695  lr=2.92e-04  dt=  36.9ms  words=16,531,456
[E02   471/1548 G   2018|CLM] train=4.5343  mask=18.4%  norm=0.556  lr=2.92e-04  dt=  36.9ms  words=16,539,648
[E02   472/1548 G   2019|CLM] train=2.6742  mask=18.4%  norm=0.712  lr=2.92e-04  dt=  36.9ms  words=16,547,840
[E02   473/1548 G   2020|CLM] train=3.3353  mask=18.4%  norm=1.369  lr=2.92e-04  dt=  36.9ms  words=16,556,032
[E02   474/1548 G   2021|CLM] train=5.9440  mask=18.4%  norm=1.427  lr=2.92e-04  dt=  36.9ms  words=16,564,224
[E02   475/1548 G   2022|CLM] train=2.5798  mask=18.4%  norm=0.615  lr=2.92e-04  dt=  37.0ms  words=16,572,416
[E02   476/1548 G   2023|CLM] train=2.7351  mask=18.4%  norm=0.655  lr=2.92e-04  dt=  36.9ms  words=16,580,608
[E02   477/1548 G   2024|CLM] train=5.1545  mask=18.4%  norm=0.862  lr=2.92e-04  dt=  37.1ms  words=16,588,800
[E02   478/1548 G   2025|CLM] train=5.2700  mask=18.4%  norm=0.735  lr=2.92e-04  dt=  37.2ms  words=16,596,992
[E02   479/1548 G   2026|CLM] train=2.6167  mask=18.4%  norm=0.651  lr=2.92e-04  dt=  37.1ms  words=16,605,184
[E02   480/1548 G   2027|CLM] train=4.7253  mask=18.4%  norm=0.862  lr=2.92e-04  dt=  37.2ms  words=16,613,376
[E02   481/1548 G   2028|CLM] train=2.7636  mask=18.4%  norm=0.638  lr=2.92e-04  dt=  37.0ms  words=16,621,568
[E02   482/1548 G   2029|CLM] train=4.5893  mask=18.4%  norm=0.915  lr=2.92e-04  dt=  37.0ms  words=16,629,760
[E02   483/1548 G   2030|CLM] train=2.9353  mask=18.4%  norm=0.892  lr=2.92e-04  dt=  37.0ms  words=16,637,952
[E02   484/1548 G   2031|CLM] train=2.3355  mask=18.4%  norm=0.831  lr=2.92e-04  dt=  37.1ms  words=16,646,144
[E02   485/1548 G   2032|CLM] train=2.9046  mask=18.4%  norm=1.250  lr=2.92e-04  dt=  37.2ms  words=16,654,336
[E02   486/1548 G   2033|CLM] train=4.7930  mask=18.4%  norm=0.668  lr=2.92e-04  dt=  37.0ms  words=16,662,528
[E02   487/1548 G   2034|CLM] train=4.4532  mask=18.4%  norm=1.024  lr=2.92e-04  dt=  37.3ms  words=16,670,720
[E02   488/1548 G   2035|CLM] train=5.3410  mask=18.4%  norm=0.762  lr=2.92e-04  dt=  37.3ms  words=16,678,912
[E02   489/1548 G   2036|CLM] train=5.5552  mask=18.4%  norm=1.475  lr=2.92e-04  dt=  37.4ms  words=16,687,104
[E02   490/1548 G   2037|CLM] train=2.8301  mask=18.4%  norm=0.836  lr=2.92e-04  dt=  37.3ms  words=16,695,296
[E02   491/1548 G   2038|CLM] train=5.8096  mask=18.4%  norm=1.304  lr=2.92e-04  dt=  37.3ms  words=16,703,488
[E02   492/1548 G   2039|CLM] train=4.8467  mask=18.4%  norm=0.773  lr=2.92e-04  dt=  37.2ms  words=16,711,680
[E02   493/1548 G   2040|CLM] train=5.1116  mask=18.4%  norm=0.822  lr=2.92e-04  dt=  37.0ms  words=16,719,872
[E02   494/1548 G   2041|CLM] train=2.7520  mask=18.4%  norm=0.923  lr=2.92e-04  dt=  37.2ms  words=16,728,064
[E02   495/1548 G   2042|CLM] train=4.4621  mask=18.4%  norm=0.847  lr=2.92e-04  dt=  37.1ms  words=16,736,256
[E02   496/1548 G   2043|CLM] train=5.3471  mask=18.4%  norm=0.880  lr=2.92e-04  dt=  37.2ms  words=16,744,448
[E02   497/1548 G   2044|CLM] train=3.1376  mask=18.3%  norm=0.888  lr=2.92e-04  dt=  36.9ms  words=16,752,640
[E02   498/1548 G   2045|CLM] train=5.2619  mask=18.3%  norm=1.919  lr=2.92e-04  dt=  37.0ms  words=16,760,832
[E02   499/1548 G   2046|CLM] train=3.3972  mask=18.3%  norm=0.705  lr=2.92e-04  dt=  36.9ms  words=16,769,024
[E02   500/1548 G   2047|CLM] train=5.1267  mask=18.3%  norm=0.745  lr=2.92e-04  dt=  37.1ms  words=16,777,216
[E02   501/1548 G   2048|CLM] train=4.6489  mask=18.3%  norm=0.902  lr=2.92e-04  dt=  37.4ms  words=16,785,408
[E02   502/1548 G   2049|CLM] train=4.4606  mask=18.3%  norm=0.807  lr=2.92e-04  dt=  37.3ms  words=16,793,600
[E02   503/1548 G   2050|CLM] train=4.5834  mask=18.3%  norm=0.646  lr=2.92e-04  dt=  37.3ms  words=16,801,792
[E02   504/1548 G   2051|CLM] train=2.7590  mask=18.3%  norm=0.962  lr=2.92e-04  dt=  37.3ms  words=16,809,984
[E02   505/1548 G   2052|CLM] train=4.0312  mask=18.3%  norm=0.555  lr=2.92e-04  dt=  37.2ms  words=16,818,176
[E02   506/1548 G   2053|CLM] train=3.2766  mask=18.3%  norm=0.714  lr=2.92e-04  dt=  37.0ms  words=16,826,368
[E02   507/1548 G   2054|CLM] train=4.2879  mask=18.3%  norm=0.838  lr=2.92e-04  dt=  37.1ms  words=16,834,560
[E02   508/1548 G   2055|CLM] train=2.7084  mask=18.3%  norm=0.694  lr=2.92e-04  dt=  37.1ms  words=16,842,752
[E02   509/1548 G   2056|CLM] train=4.3442  mask=18.3%  norm=0.777  lr=2.92e-04  dt=  37.2ms  words=16,850,944
[E02   510/1548 G   2057|CLM] train=5.3446  mask=18.3%  norm=2.105  lr=2.92e-04  dt=  37.0ms  words=16,859,136
[E02   511/1548 G   2058|CLM] train=4.1042  mask=18.3%  norm=0.634  lr=2.92e-04  dt=  37.0ms  words=16,867,328
[E02   512/1548 G   2059|CLM] train=4.3444  mask=18.3%  norm=0.860  lr=2.92e-04  dt=  37.0ms  words=16,875,520
[E02   513/1548 G   2060|CLM] train=4.9931  mask=18.3%  norm=0.550  lr=2.92e-04  dt=  37.2ms  words=16,883,712
[E02   514/1548 G   2061|CLM] train=4.3664  mask=18.3%  norm=0.590  lr=2.92e-04  dt=  37.1ms  words=16,891,904
[E02   515/1548 G   2062|CLM] train=2.7741  mask=18.3%  norm=1.229  lr=2.92e-04  dt=  38.2ms  words=16,900,096
[E02   516/1548 G   2063|CLM] train=2.9699  mask=18.3%  norm=0.872  lr=2.92e-04  dt=  37.2ms  words=16,908,288
[E02   517/1548 G   2064|CLM] train=4.7445  mask=18.3%  norm=0.636  lr=2.92e-04  dt=  37.4ms  words=16,916,480
[E02   518/1548 G   2065|CLM] train=5.1395  mask=18.3%  norm=0.616  lr=2.92e-04  dt=  37.3ms  words=16,924,672
[E02   519/1548 G   2066|CLM] train=3.0667  mask=18.3%  norm=0.736  lr=2.92e-04  dt=  37.2ms  words=16,932,864
[E02   520/1548 G   2067|CLM] train=2.3840  mask=18.3%  norm=0.721  lr=2.92e-04  dt=  37.1ms  words=16,941,056
[E02   521/1548 G   2068|CLM] train=2.6792  mask=18.3%  norm=0.576  lr=2.92e-04  dt=  37.2ms  words=16,949,248
[E02   522/1548 G   2069|CLM] train=4.8183  mask=18.3%  norm=0.737  lr=2.92e-04  dt=  37.1ms  words=16,957,440
[E02   523/1548 G   2070|CLM] train=3.0643  mask=18.3%  norm=0.632  lr=2.92e-04  dt=  36.9ms  words=16,965,632
[E02   524/1548 G   2071|CLM] train=4.5533  mask=18.3%  norm=1.277  lr=2.92e-04  dt=  37.0ms  words=16,973,824
[E02   525/1548 G   2072|CLM] train=4.5353  mask=18.3%  norm=0.513  lr=2.92e-04  dt=  37.1ms  words=16,982,016
[E02   526/1548 G   2073|CLM] train=4.7432  mask=18.3%  norm=0.860  lr=2.92e-04  dt=  36.9ms  words=16,990,208
[E02   527/1548 G   2074|CLM] train=4.3075  mask=18.3%  norm=0.676  lr=2.92e-04  dt=  37.2ms  words=16,998,400
[E02   528/1548 G   2075|CLM] train=2.8603  mask=18.3%  norm=1.370  lr=2.92e-04  dt=  37.5ms  words=17,006,592
[E02   529/1548 G   2076|CLM] train=6.5458  mask=18.3%  norm=1.656  lr=2.92e-04  dt=  37.0ms  words=17,014,784
[E02   530/1548 G   2077|CLM] train=4.9602  mask=18.3%  norm=0.762  lr=2.92e-04  dt=  37.3ms  words=17,022,976
[E02   531/1548 G   2078|CLM] train=2.8347  mask=18.3%  norm=0.626  lr=2.92e-04  dt=  37.5ms  words=17,031,168
[E02   532/1548 G   2079|CLM] train=5.0463  mask=18.3%  norm=0.659  lr=2.92e-04  dt=  36.9ms  words=17,039,360
[E02   533/1548 G   2080|CLM] train=4.2843  mask=18.3%  norm=0.912  lr=2.91e-04  dt=  37.0ms  words=17,047,552
[E02   534/1548 G   2081|CLM] train=5.4381  mask=18.3%  norm=0.941  lr=2.91e-04  dt=  37.0ms  words=17,055,744
[E02   535/1548 G   2082|CLM] train=2.9855  mask=18.3%  norm=0.705  lr=2.91e-04  dt=  37.0ms  words=17,063,936
[E02   536/1548 G   2083|CLM] train=4.4957  mask=18.3%  norm=0.815  lr=2.91e-04  dt=  37.2ms  words=17,072,128
[E02   537/1548 G   2084|CLM] train=4.5582  mask=18.3%  norm=0.718  lr=2.91e-04  dt=  37.2ms  words=17,080,320
[E02   538/1548 G   2085|CLM] train=4.3545  mask=18.3%  norm=0.621  lr=2.91e-04  dt=  37.2ms  words=17,088,512
[E02   539/1548 G   2086|CLM] train=4.8733  mask=18.3%  norm=0.635  lr=2.91e-04  dt=  37.1ms  words=17,096,704
[E02   540/1548 G   2087|CLM] train=2.6767  mask=18.3%  norm=0.630  lr=2.91e-04  dt=  38.4ms  words=17,104,896
[E02   541/1548 G   2088|CLM] train=5.7009  mask=18.3%  norm=0.805  lr=2.91e-04  dt=  37.1ms  words=17,113,088
[E02   542/1548 G   2089|CLM] train=5.4092  mask=18.3%  norm=0.725  lr=2.91e-04  dt=  37.5ms  words=17,121,280
[E02   543/1548 G   2090|CLM] train=2.8141  mask=18.3%  norm=0.813  lr=2.91e-04  dt=  37.4ms  words=17,129,472
[E02   544/1548 G   2091|CLM] train=4.5465  mask=18.3%  norm=0.794  lr=2.91e-04  dt=  37.1ms  words=17,137,664
[E02   545/1548 G   2092|CLM] train=4.4537  mask=18.3%  norm=0.788  lr=2.91e-04  dt=  37.4ms  words=17,145,856
[E02   546/1548 G   2093|CLM] train=2.7813  mask=18.3%  norm=0.621  lr=2.91e-04  dt=  37.2ms  words=17,154,048
[E02   547/1548 G   2094|CLM] train=2.7917  mask=18.3%  norm=0.642  lr=2.91e-04  dt=  37.0ms  words=17,162,240
[E02   548/1548 G   2095|CLM] train=5.1346  mask=18.3%  norm=0.804  lr=2.91e-04  dt=  37.0ms  words=17,170,432
[E02   549/1548 G   2096|CLM] train=4.9286  mask=18.3%  norm=0.683  lr=2.91e-04  dt=  36.9ms  words=17,178,624
[E02   550/1548 G   2097|CLM] train=3.2027  mask=18.3%  norm=0.571  lr=2.91e-04  dt=  37.2ms  words=17,186,816
[E02   551/1548 G   2098|CLM] train=5.3183  mask=18.3%  norm=0.694  lr=2.91e-04  dt=  37.1ms  words=17,195,008
[E02   552/1548 G   2099|CLM] train=4.4265  mask=18.3%  norm=0.852  lr=2.91e-04  dt=  37.1ms  words=17,203,200
[E02   553/1548 G   2100|CLM] train=2.9498  mask=18.3%  norm=0.678  lr=2.91e-04  dt=  37.1ms  words=17,211,392
[E02   554/1548 G   2101|CLM] train=4.7209  mask=18.3%  norm=0.812  lr=2.91e-04  dt=  37.0ms  words=17,219,584
[E02   555/1548 G   2102|CLM] train=3.2202  mask=18.3%  norm=0.637  lr=2.91e-04  dt=  37.2ms  words=17,227,776
[E02   556/1548 G   2103|CLM] train=3.3782  mask=18.3%  norm=1.620  lr=2.91e-04  dt=  38.0ms  words=17,235,968
[E02   557/1548 G   2104|CLM] train=4.6674  mask=18.3%  norm=1.434  lr=2.91e-04  dt=  37.2ms  words=17,244,160
[E02   558/1548 G   2105|CLM] train=4.7579  mask=18.3%  norm=0.814  lr=2.91e-04  dt=  36.9ms  words=17,252,352
[E02   559/1548 G   2106|CLM] train=5.5180  mask=18.3%  norm=0.902  lr=2.91e-04  dt=  37.1ms  words=17,260,544
[E02   560/1548 G   2107|CLM] train=5.3718  mask=18.3%  norm=0.677  lr=2.91e-04  dt=  37.1ms  words=17,268,736
[E02   561/1548 G   2108|CLM] train=5.3391  mask=18.3%  norm=2.737  lr=2.91e-04  dt=  37.0ms  words=17,276,928
[E02   562/1548 G   2109|CLM] train=3.9269  mask=18.3%  norm=0.710  lr=2.91e-04  dt=  36.9ms  words=17,285,120
[E02   563/1548 G   2110|CLM] train=5.7467  mask=18.3%  norm=0.963  lr=2.91e-04  dt=  37.0ms  words=17,293,312
[E02   564/1548 G   2111|CLM] train=5.2488  mask=18.3%  norm=0.870  lr=2.91e-04  dt=  36.9ms  words=17,301,504
[E02   565/1548 G   2112|CLM] train=4.8047  mask=18.3%  norm=0.775  lr=2.91e-04  dt=  37.0ms  words=17,309,696
[E02   566/1548 G   2113|CLM] train=4.7779  mask=18.3%  norm=0.645  lr=2.91e-04  dt=  36.9ms  words=17,317,888
[E02   567/1548 G   2114|CLM] train=4.5749  mask=18.3%  norm=0.672  lr=2.91e-04  dt=  36.9ms  words=17,326,080
[E02   568/1548 G   2115|CLM] train=3.1341  mask=18.3%  norm=0.747  lr=2.91e-04  dt=  37.0ms  words=17,334,272
[E02   569/1548 G   2116|CLM] train=4.8081  mask=18.3%  norm=0.714  lr=2.91e-04  dt=  37.4ms  words=17,342,464
[E02   570/1548 G   2117|CLM] train=4.7177  mask=18.3%  norm=0.820  lr=2.91e-04  dt=  37.1ms  words=17,350,656
[E02   571/1548 G   2118|CLM] train=3.0302  mask=18.3%  norm=1.336  lr=2.91e-04  dt=  36.9ms  words=17,358,848
[E02   572/1548 G   2119|CLM] train=3.2681  mask=18.3%  norm=0.910  lr=2.91e-04  dt=  37.0ms  words=17,367,040
[E02   573/1548 G   2120|CLM] train=2.7812  mask=18.3%  norm=0.646  lr=2.91e-04  dt=  36.9ms  words=17,375,232
[E02   574/1548 G   2121|CLM] train=5.9441  mask=18.3%  norm=1.330  lr=2.91e-04  dt=  36.8ms  words=17,383,424
[E02   575/1548 G   2122|CLM] train=3.2155  mask=18.3%  norm=0.943  lr=2.91e-04  dt=  37.0ms  words=17,391,616
[E02   576/1548 G   2123|CLM] train=2.8756  mask=18.3%  norm=0.896  lr=2.91e-04  dt=  37.0ms  words=17,399,808
[E02   577/1548 G   2124|CLM] train=5.0957  mask=18.3%  norm=1.028  lr=2.91e-04  dt=  36.9ms  words=17,408,000
[E02   578/1548 G   2125|CLM] train=4.8260  mask=18.3%  norm=0.908  lr=2.91e-04  dt=  37.3ms  words=17,416,192
[E02   579/1548 G   2126|CLM] train=5.0629  mask=18.3%  norm=0.683  lr=2.91e-04  dt=  37.0ms  words=17,424,384
[E02   580/1548 G   2127|CLM] train=3.0045  mask=18.3%  norm=0.996  lr=2.91e-04  dt=  37.2ms  words=17,432,576
[E02   581/1548 G   2128|CLM] train=4.7934  mask=18.3%  norm=1.437  lr=2.91e-04  dt=  37.4ms  words=17,440,768
[E02   582/1548 G   2129|CLM] train=2.8005  mask=18.3%  norm=0.599  lr=2.91e-04  dt=  36.8ms  words=17,448,960
[E02   583/1548 G   2130|CLM] train=2.7818  mask=18.3%  norm=0.622  lr=2.91e-04  dt=  36.9ms  words=17,457,152
[E02   584/1548 G   2131|CLM] train=4.6136  mask=18.3%  norm=0.701  lr=2.91e-04  dt=  37.1ms  words=17,465,344
[E02   585/1548 G   2132|CLM] train=3.1669  mask=18.3%  norm=1.219  lr=2.91e-04  dt=  36.9ms  words=17,473,536
[E02   586/1548 G   2133|CLM] train=5.0641  mask=18.3%  norm=0.839  lr=2.91e-04  dt=  37.0ms  words=17,481,728
[E02   587/1548 G   2134|CLM] train=5.0114  mask=18.3%  norm=0.892  lr=2.91e-04  dt=  36.8ms  words=17,489,920
[E02   588/1548 G   2135|CLM] train=2.8874  mask=18.3%  norm=0.950  lr=2.91e-04  dt=  37.0ms  words=17,498,112
[E02   589/1548 G   2136|CLM] train=4.8090  mask=18.3%  norm=1.251  lr=2.91e-04  dt=  37.0ms  words=17,506,304
[E02   590/1548 G   2137|CLM] train=2.7118  mask=18.3%  norm=0.722  lr=2.91e-04  dt=  37.0ms  words=17,514,496
[E02   591/1548 G   2138|CLM] train=2.9110  mask=18.3%  norm=0.628  lr=2.91e-04  dt=  37.0ms  words=17,522,688
[E02   592/1548 G   2139|CLM] train=2.8969  mask=18.3%  norm=0.751  lr=2.91e-04  dt=  37.0ms  words=17,530,880
[E02   593/1548 G   2140|CLM] train=5.0972  mask=18.3%  norm=0.782  lr=2.91e-04  dt=  37.1ms  words=17,539,072
[E02   594/1548 G   2141|CLM] train=4.4663  mask=18.3%  norm=0.602  lr=2.91e-04  dt=  37.1ms  words=17,547,264
[E02   595/1548 G   2142|CLM] train=2.7829  mask=18.3%  norm=0.971  lr=2.91e-04  dt=  44.3ms  words=17,555,456
[E02   596/1548 G   2143|CLM] train=5.7132  mask=18.3%  norm=0.803  lr=2.91e-04  dt=  37.4ms  words=17,563,648
[E02   597/1548 G   2144|CLM] train=4.6106  mask=18.3%  norm=0.672  lr=2.91e-04  dt=  37.1ms  words=17,571,840
[E02   598/1548 G   2145|CLM] train=4.8599  mask=18.3%  norm=1.034  lr=2.91e-04  dt=  39.0ms  words=17,580,032
[E02   599/1548 G   2146|CLM] train=2.6595  mask=18.3%  norm=0.822  lr=2.91e-04  dt=  37.4ms  words=17,588,224
[E02   600/1548 G   2147|CLM] train=5.5308  mask=18.3%  norm=0.556  lr=2.91e-04  dt=  39.2ms  words=17,596,416
[E02   601/1548 G   2148|CLM] train=4.9415  mask=18.3%  norm=0.931  lr=2.91e-04  dt=  41.9ms  words=17,604,608
[E02   602/1548 G   2149|CLM] train=4.0960  mask=18.3%  norm=0.560  lr=2.91e-04  dt=  37.4ms  words=17,612,800
[E02   603/1548 G   2150|CLM] train=4.4350  mask=18.3%  norm=0.655  lr=2.91e-04  dt=  37.4ms  words=17,620,992
[E02   604/1548 G   2151|CLM] train=5.1553  mask=18.3%  norm=0.780  lr=2.91e-04  dt=  47.6ms  words=17,629,184
[E02   605/1548 G   2152|CLM] train=2.6986  mask=18.3%  norm=0.906  lr=2.91e-04  dt=  45.2ms  words=17,637,376
[E02   606/1548 G   2153|CLM] train=6.4773  mask=18.3%  norm=2.803  lr=2.91e-04  dt=  42.0ms  words=17,645,568
[E02   607/1548 G   2154|CLM] train=5.2658  mask=18.3%  norm=0.677  lr=2.91e-04  dt=  39.3ms  words=17,653,760
[E02   608/1548 G   2155|CLM] train=5.5835  mask=18.3%  norm=0.863  lr=2.90e-04  dt=  37.5ms  words=17,661,952
[E02   609/1548 G   2156|CLM] train=2.5926  mask=18.3%  norm=0.866  lr=2.90e-04  dt=  37.4ms  words=17,670,144
[E02   610/1548 G   2157|CLM] train=4.6994  mask=18.3%  norm=0.669  lr=2.90e-04  dt=  37.4ms  words=17,678,336
[E02   611/1548 G   2158|CLM] train=4.9609  mask=18.3%  norm=0.594  lr=2.90e-04  dt=  37.5ms  words=17,686,528
[E02   612/1548 G   2159|CLM] train=5.1018  mask=18.3%  norm=0.742  lr=2.90e-04  dt=  37.4ms  words=17,694,720
[E02   613/1548 G   2160|CLM] train=2.8453  mask=18.3%  norm=0.685  lr=2.90e-04  dt=  37.1ms  words=17,702,912
[E02   614/1548 G   2161|CLM] train=4.5740  mask=18.3%  norm=0.656  lr=2.90e-04  dt=  37.7ms  words=17,711,104
[E02   615/1548 G   2162|CLM] train=6.2737  mask=18.3%  norm=1.435  lr=2.90e-04  dt=  37.2ms  words=17,719,296
[E02   616/1548 G   2163|CLM] train=2.9220  mask=18.3%  norm=0.823  lr=2.90e-04  dt=  37.2ms  words=17,727,488
[E02   617/1548 G   2164|CLM] train=2.7487  mask=18.3%  norm=0.926  lr=2.90e-04  dt=  37.2ms  words=17,735,680
[E02   618/1548 G   2165|CLM] train=2.9738  mask=18.3%  norm=0.816  lr=2.90e-04  dt=  37.4ms  words=17,743,872
[E02   619/1548 G   2166|CLM] train=4.8096  mask=18.3%  norm=0.806  lr=2.90e-04  dt=  37.4ms  words=17,752,064
[E02   620/1548 G   2167|CLM] train=2.7831  mask=18.3%  norm=0.774  lr=2.90e-04  dt=  37.4ms  words=17,760,256
[E02   621/1548 G   2168|CLM] train=5.2049  mask=18.2%  norm=0.953  lr=2.90e-04  dt=  37.8ms  words=17,768,448
[E02   622/1548 G   2169|CLM] train=4.3495  mask=18.2%  norm=0.686  lr=2.90e-04  dt=  37.5ms  words=17,776,640
[E02   623/1548 G   2170|CLM] train=4.9070  mask=18.2%  norm=0.764  lr=2.90e-04  dt=  37.8ms  words=17,784,832
[E02   624/1548 G   2171|CLM] train=2.8120  mask=18.2%  norm=0.839  lr=2.90e-04  dt=  37.4ms  words=17,793,024
[E02   625/1548 G   2172|CLM] train=2.8680  mask=18.2%  norm=0.974  lr=2.90e-04  dt=  37.1ms  words=17,801,216
[E02   626/1548 G   2173|CLM] train=2.8814  mask=18.2%  norm=0.888  lr=2.90e-04  dt=  37.3ms  words=17,809,408
[E02   627/1548 G   2174|CLM] train=5.1503  mask=18.2%  norm=1.121  lr=2.90e-04  dt=  37.1ms  words=17,817,600
[E02   628/1548 G   2175|CLM] train=2.6390  mask=18.2%  norm=1.108  lr=2.90e-04  dt=  37.3ms  words=17,825,792
[E02   629/1548 G   2176|CLM] train=4.4341  mask=18.2%  norm=0.955  lr=2.90e-04  dt=  37.2ms  words=17,833,984
[E02   630/1548 G   2177|CLM] train=5.4375  mask=18.2%  norm=0.916  lr=2.90e-04  dt=  37.2ms  words=17,842,176
[E02   631/1548 G   2178|CLM] train=5.4220  mask=18.2%  norm=0.747  lr=2.90e-04  dt=  37.1ms  words=17,850,368
[E02   632/1548 G   2179|CLM] train=4.6731  mask=18.2%  norm=0.962  lr=2.90e-04  dt=  37.2ms  words=17,858,560
[E02   633/1548 G   2180|CLM] train=5.5181  mask=18.2%  norm=1.094  lr=2.90e-04  dt=  37.4ms  words=17,866,752
[E02   634/1548 G   2181|CLM] train=4.3419  mask=18.2%  norm=0.688  lr=2.90e-04  dt=  37.2ms  words=17,874,944
[E02   635/1548 G   2182|CLM] train=2.6428  mask=18.2%  norm=0.964  lr=2.90e-04  dt=  37.2ms  words=17,883,136
[E02   636/1548 G   2183|CLM] train=4.5636  mask=18.2%  norm=0.969  lr=2.90e-04  dt=  37.2ms  words=17,891,328
[E02   637/1548 G   2184|CLM] train=4.1112  mask=18.2%  norm=0.690  lr=2.90e-04  dt=  37.2ms  words=17,899,520
[E02   638/1548 G   2185|CLM] train=5.2106  mask=18.2%  norm=0.780  lr=2.90e-04  dt=  37.2ms  words=17,907,712
[E02   639/1548 G   2186|CLM] train=4.5600  mask=18.2%  norm=0.619  lr=2.90e-04  dt=  37.0ms  words=17,915,904
[E02   640/1548 G   2187|CLM] train=4.9160  mask=18.2%  norm=0.994  lr=2.90e-04  dt=  37.0ms  words=17,924,096
[E02   641/1548 G   2188|CLM] train=2.7503  mask=18.2%  norm=0.778  lr=2.90e-04  dt=  37.2ms  words=17,932,288
[E02   642/1548 G   2189|CLM] train=2.6827  mask=18.2%  norm=0.547  lr=2.90e-04  dt=  37.1ms  words=17,940,480
[E02   643/1548 G   2190|CLM] train=2.7276  mask=18.2%  norm=0.823  lr=2.90e-04  dt=  37.2ms  words=17,948,672
[E02   644/1548 G   2191|CLM] train=4.0500  mask=18.2%  norm=1.002  lr=2.90e-04  dt=  37.1ms  words=17,956,864
[E02   645/1548 G   2192|CLM] train=4.8953  mask=18.2%  norm=0.828  lr=2.90e-04  dt=  37.1ms  words=17,965,056
[E02   646/1548 G   2193|CLM] train=5.9451  mask=18.2%  norm=5.610  lr=2.90e-04  dt=  37.1ms  words=17,973,248
[E02   647/1548 G   2194|CLM] train=2.7951  mask=18.2%  norm=1.092  lr=2.90e-04  dt=  37.2ms  words=17,981,440
[E02   648/1548 G   2195|CLM] train=3.2110  mask=18.2%  norm=0.933  lr=2.90e-04  dt=  37.4ms  words=17,989,632
[E02   649/1548 G   2196|CLM] train=2.9549  mask=18.2%  norm=0.837  lr=2.90e-04  dt=  37.4ms  words=17,997,824
[E02   650/1548 G   2197|CLM] train=5.0348  mask=18.2%  norm=0.859  lr=2.90e-04  dt=  37.3ms  words=18,006,016
[E02   651/1548 G   2198|CLM] train=3.2478  mask=18.2%  norm=0.979  lr=2.90e-04  dt=  37.2ms  words=18,014,208
[E02   652/1548 G   2199|CLM] train=4.2880  mask=18.2%  norm=0.856  lr=2.90e-04  dt=  37.2ms  words=18,022,400
[E02   653/1548 G   2200|CLM] train=2.5799  mask=18.2%  norm=0.854  lr=2.90e-04  dt=  37.1ms  words=18,030,592
[E02   654/1548 G   2201|CLM] train=5.6207  mask=18.2%  norm=0.751  lr=2.90e-04  dt=  37.3ms  words=18,038,784
[E02   655/1548 G   2202|CLM] train=4.6314  mask=18.2%  norm=0.642  lr=2.90e-04  dt=  37.0ms  words=18,046,976
[E02   656/1548 G   2203|CLM] train=4.8001  mask=18.2%  norm=0.648  lr=2.90e-04  dt=  37.3ms  words=18,055,168
[E02   657/1548 G   2204|CLM] train=2.9310  mask=18.2%  norm=0.799  lr=2.90e-04  dt=  37.3ms  words=18,063,360
[E02   658/1548 G   2205|CLM] train=2.7843  mask=18.2%  norm=0.648  lr=2.90e-04  dt=  37.1ms  words=18,071,552
[E02   659/1548 G   2206|CLM] train=4.5695  mask=18.2%  norm=0.625  lr=2.90e-04  dt=  37.0ms  words=18,079,744
[E02   660/1548 G   2207|CLM] train=4.9788  mask=18.2%  norm=0.817  lr=2.90e-04  dt=  37.3ms  words=18,087,936
[E02   661/1548 G   2208|CLM] train=5.1394  mask=18.2%  norm=0.635  lr=2.90e-04  dt=  37.1ms  words=18,096,128
[E02   662/1548 G   2209|CLM] train=4.2439  mask=18.2%  norm=0.736  lr=2.90e-04  dt=  37.0ms  words=18,104,320
[E02   663/1548 G   2210|CLM] train=4.6557  mask=18.2%  norm=0.983  lr=2.90e-04  dt=  37.1ms  words=18,112,512
[E02   664/1548 G   2211|CLM] train=4.9018  mask=18.2%  norm=0.792  lr=2.90e-04  dt=  37.1ms  words=18,120,704
[E02   665/1548 G   2212|CLM] train=3.0554  mask=18.2%  norm=1.002  lr=2.90e-04  dt=  37.1ms  words=18,128,896
[E02   666/1548 G   2213|CLM] train=3.2076  mask=18.2%  norm=0.893  lr=2.90e-04  dt=  37.2ms  words=18,137,088
[E02   667/1548 G   2214|CLM] train=5.1170  mask=18.2%  norm=0.933  lr=2.90e-04  dt=  37.2ms  words=18,145,280
[E02   668/1548 G   2215|CLM] train=2.9121  mask=18.2%  norm=0.781  lr=2.90e-04  dt=  37.0ms  words=18,153,472
[E02   669/1548 G   2216|CLM] train=4.7029  mask=18.2%  norm=0.683  lr=2.90e-04  dt=  37.2ms  words=18,161,664
[E02   670/1548 G   2217|CLM] train=2.7358  mask=18.2%  norm=0.758  lr=2.90e-04  dt=  37.2ms  words=18,169,856
[E02   671/1548 G   2218|CLM] train=3.1861  mask=18.2%  norm=0.895  lr=2.90e-04  dt=  37.1ms  words=18,178,048
[E02   672/1548 G   2219|CLM] train=2.9352  mask=18.2%  norm=0.782  lr=2.90e-04  dt=  37.0ms  words=18,186,240
[E02   673/1548 G   2220|CLM] train=2.6713  mask=18.2%  norm=0.557  lr=2.90e-04  dt=  37.0ms  words=18,194,432
[E02   674/1548 G   2221|CLM] train=4.8363  mask=18.2%  norm=0.858  lr=2.90e-04  dt=  37.1ms  words=18,202,624
[E02   675/1548 G   2222|CLM] train=5.0113  mask=18.2%  norm=0.853  lr=2.90e-04  dt=  37.4ms  words=18,210,816
[E02   676/1548 G   2223|CLM] train=2.8178  mask=18.2%  norm=0.694  lr=2.90e-04  dt=  37.0ms  words=18,219,008
[E02   677/1548 G   2224|CLM] train=2.9543  mask=18.2%  norm=0.671  lr=2.90e-04  dt=  37.2ms  words=18,227,200
[E02   678/1548 G   2225|CLM] train=4.1474  mask=18.2%  norm=0.675  lr=2.89e-04  dt=  37.1ms  words=18,235,392
[E02   679/1548 G   2226|CLM] train=2.7439  mask=18.2%  norm=0.558  lr=2.89e-04  dt=  37.2ms  words=18,243,584
[E02   680/1548 G   2227|CLM] train=4.3636  mask=18.2%  norm=0.966  lr=2.89e-04  dt=  37.2ms  words=18,251,776
[E02   681/1548 G   2228|CLM] train=5.2746  mask=18.2%  norm=0.868  lr=2.89e-04  dt=  37.3ms  words=18,259,968
[E02   682/1548 G   2229|CLM] train=5.4346  mask=18.2%  norm=1.107  lr=2.89e-04  dt=  37.2ms  words=18,268,160
[E02   683/1548 G   2230|CLM] train=2.6601  mask=18.2%  norm=0.671  lr=2.89e-04  dt=  37.3ms  words=18,276,352
[E02   684/1548 G   2231|CLM] train=2.8698  mask=18.2%  norm=1.122  lr=2.89e-04  dt=  37.0ms  words=18,284,544
[E02   685/1548 G   2232|CLM] train=3.0455  mask=18.2%  norm=0.754  lr=2.89e-04  dt=  37.0ms  words=18,292,736
[E02   686/1548 G   2233|CLM] train=2.7889  mask=18.2%  norm=0.625  lr=2.89e-04  dt=  37.3ms  words=18,300,928
[E02   687/1548 G   2234|CLM] train=3.2911  mask=18.2%  norm=1.099  lr=2.89e-04  dt=  37.2ms  words=18,309,120
[E02   688/1548 G   2235|CLM] train=5.1108  mask=18.2%  norm=0.852  lr=2.89e-04  dt=  37.1ms  words=18,317,312
[E02   689/1548 G   2236|CLM] train=2.6315  mask=18.2%  norm=0.929  lr=2.89e-04  dt=  37.0ms  words=18,325,504
[E02   690/1548 G   2237|CLM] train=4.6570  mask=18.2%  norm=0.940  lr=2.89e-04  dt=  37.3ms  words=18,333,696
[E02   691/1548 G   2238|CLM] train=5.2348  mask=18.2%  norm=1.497  lr=2.89e-04  dt=  42.5ms  words=18,341,888
[E02   692/1548 G   2239|CLM] train=4.3973  mask=18.2%  norm=0.870  lr=2.89e-04  dt=  38.7ms  words=18,350,080
[E02   693/1548 G   2240|CLM] train=3.9824  mask=18.2%  norm=0.574  lr=2.89e-04  dt=  37.3ms  words=18,358,272
[E02   694/1548 G   2241|CLM] train=4.4344  mask=18.2%  norm=0.623  lr=2.89e-04  dt=  38.9ms  words=18,366,464
[E02   695/1548 G   2242|CLM] train=2.5525  mask=18.2%  norm=0.794  lr=2.89e-04  dt=  43.5ms  words=18,374,656
[E02   696/1548 G   2243|CLM] train=2.8940  mask=18.2%  norm=0.776  lr=2.89e-04  dt=  37.4ms  words=18,382,848
[E02   697/1548 G   2244|CLM] train=3.1094  mask=18.2%  norm=0.856  lr=2.89e-04  dt=  37.5ms  words=18,391,040
[E02   698/1548 G   2245|CLM] train=2.6074  mask=18.2%  norm=0.691  lr=2.89e-04  dt=  37.3ms  words=18,399,232
[E02   699/1548 G   2246|CLM] train=4.7455  mask=18.2%  norm=0.832  lr=2.89e-04  dt=  37.2ms  words=18,407,424
[E02   700/1548 G   2247|CLM] train=5.5486  mask=18.2%  norm=0.850  lr=2.89e-04  dt=  36.8ms  words=18,415,616
[E02   701/1548 G   2248|CLM] train=5.2194  mask=18.2%  norm=0.775  lr=2.89e-04  dt=  37.0ms  words=18,423,808
[E02   702/1548 G   2249|CLM] train=2.6917  mask=18.2%  norm=1.033  lr=2.89e-04  dt=  37.0ms  words=18,432,000
[E02   703/1548 G   2250|CLM] train=6.0151  mask=18.2%  norm=0.747  lr=2.89e-04  dt=  36.9ms  words=18,440,192
[E02   704/1548 G   2251|CLM] train=5.2366  mask=18.2%  norm=0.854  lr=2.89e-04  dt=  37.0ms  words=18,448,384
[E02   705/1548 G   2252|CLM] train=2.7759  mask=18.2%  norm=0.800  lr=2.89e-04  dt=  37.1ms  words=18,456,576
[E02   706/1548 G   2253|CLM] train=5.1333  mask=18.2%  norm=0.911  lr=2.89e-04  dt=  37.2ms  words=18,464,768
[E02   707/1548 G   2254|CLM] train=3.0885  mask=18.2%  norm=0.690  lr=2.89e-04  dt=  37.0ms  words=18,472,960
[E02   708/1548 G   2255|CLM] train=3.3825  mask=18.2%  norm=0.997  lr=2.89e-04  dt=  37.0ms  words=18,481,152
[E02   709/1548 G   2256|CLM] train=2.8460  mask=18.2%  norm=0.809  lr=2.89e-04  dt=  36.9ms  words=18,489,344
[E02   710/1548 G   2257|CLM] train=3.1780  mask=18.2%  norm=0.893  lr=2.89e-04  dt=  37.0ms  words=18,497,536
[E02   711/1548 G   2258|CLM] train=2.8315  mask=18.2%  norm=0.657  lr=2.89e-04  dt=  37.0ms  words=18,505,728
[E02   712/1548 G   2259|CLM] train=4.7374  mask=18.2%  norm=0.803  lr=2.89e-04  dt=  36.9ms  words=18,513,920
[E02   713/1548 G   2260|CLM] train=2.4137  mask=18.2%  norm=0.925  lr=2.89e-04  dt=  37.0ms  words=18,522,112
[E02   714/1548 G   2261|CLM] train=5.7374  mask=18.2%  norm=1.621  lr=2.89e-04  dt=  37.3ms  words=18,530,304
[E02   715/1548 G   2262|CLM] train=5.1954  mask=18.2%  norm=0.959  lr=2.89e-04  dt=  37.1ms  words=18,538,496
[E02   716/1548 G   2263|CLM] train=3.9158  mask=18.2%  norm=0.910  lr=2.89e-04  dt=  37.0ms  words=18,546,688
[E02   717/1548 G   2264|CLM] train=4.5614  mask=18.2%  norm=0.642  lr=2.89e-04  dt=  36.9ms  words=18,554,880
[E02   718/1548 G   2265|CLM] train=4.9273  mask=18.2%  norm=0.785  lr=2.89e-04  dt=  37.0ms  words=18,563,072
[E02   719/1548 G   2266|CLM] train=4.7269  mask=18.2%  norm=0.764  lr=2.89e-04  dt=  36.8ms  words=18,571,264
[E02   720/1548 G   2267|CLM] train=3.0228  mask=18.2%  norm=0.828  lr=2.89e-04  dt=  36.9ms  words=18,579,456
[E02   721/1548 G   2268|CLM] train=2.8512  mask=18.2%  norm=1.450  lr=2.89e-04  dt=  37.0ms  words=18,587,648
[E02   722/1548 G   2269|CLM] train=4.7367  mask=18.2%  norm=0.981  lr=2.89e-04  dt=  36.8ms  words=18,595,840
[E02   723/1548 G   2270|CLM] train=4.8010  mask=18.2%  norm=0.738  lr=2.89e-04  dt=  36.8ms  words=18,604,032
[E02   724/1548 G   2271|CLM] train=2.7497  mask=18.2%  norm=0.754  lr=2.89e-04  dt=  37.0ms  words=18,612,224
[E02   725/1548 G   2272|CLM] train=4.8479  mask=18.2%  norm=0.964  lr=2.89e-04  dt=  36.9ms  words=18,620,416
[E02   726/1548 G   2273|CLM] train=2.8668  mask=18.2%  norm=0.873  lr=2.89e-04  dt=  36.8ms  words=18,628,608
[E02   727/1548 G   2274|CLM] train=2.8010  mask=18.2%  norm=1.186  lr=2.89e-04  dt=  36.9ms  words=18,636,800
[E02   728/1548 G   2275|CLM] train=2.9480  mask=18.2%  norm=0.533  lr=2.89e-04  dt=  37.0ms  words=18,644,992
[E02   729/1548 G   2276|CLM] train=3.1334  mask=18.2%  norm=1.432  lr=2.89e-04  dt=  37.0ms  words=18,653,184
[E02   730/1548 G   2277|CLM] train=2.5554  mask=18.2%  norm=0.658  lr=2.89e-04  dt=  36.8ms  words=18,661,376
[E02   731/1548 G   2278|CLM] train=2.7267  mask=18.2%  norm=0.716  lr=2.89e-04  dt=  37.0ms  words=18,669,568
[E02   732/1548 G   2279|CLM] train=5.0937  mask=18.2%  norm=0.763  lr=2.89e-04  dt=  36.9ms  words=18,677,760
[E02   733/1548 G   2280|CLM] train=5.2107  mask=18.2%  norm=1.154  lr=2.89e-04  dt=  36.9ms  words=18,685,952
[E02   734/1548 G   2281|CLM] train=5.4215  mask=18.2%  norm=1.051  lr=2.89e-04  dt=  36.8ms  words=18,694,144
[E02   735/1548 G   2282|CLM] train=2.7206  mask=18.2%  norm=0.734  lr=2.89e-04  dt=  37.0ms  words=18,702,336
[E02   736/1548 G   2283|CLM] train=5.1673  mask=18.2%  norm=0.805  lr=2.89e-04  dt=  36.9ms  words=18,710,528
[E02   737/1548 G   2284|CLM] train=4.2401  mask=18.2%  norm=0.769  lr=2.89e-04  dt=  36.9ms  words=18,718,720
[E02   738/1548 G   2285|CLM] train=5.3076  mask=18.2%  norm=0.921  lr=2.89e-04  dt=  36.9ms  words=18,726,912
[E02   739/1548 G   2286|CLM] train=2.6893  mask=18.2%  norm=0.914  lr=2.89e-04  dt=  36.9ms  words=18,735,104
[E02   740/1548 G   2287|CLM] train=4.7239  mask=18.2%  norm=0.816  lr=2.89e-04  dt=  36.8ms  words=18,743,296
[E02   741/1548 G   2288|CLM] train=5.4865  mask=18.2%  norm=0.827  lr=2.89e-04  dt=  37.2ms  words=18,751,488
[E02   742/1548 G   2289|CLM] train=4.9333  mask=18.2%  norm=0.682  lr=2.89e-04  dt=  36.8ms  words=18,759,680
[E02   743/1548 G   2290|CLM] train=2.8779  mask=18.2%  norm=1.221  lr=2.89e-04  dt=  37.0ms  words=18,767,872
[E02   744/1548 G   2291|CLM] train=2.7364  mask=18.2%  norm=0.629  lr=2.89e-04  dt=  36.9ms  words=18,776,064
[E02   745/1548 G   2292|CLM] train=4.3473  mask=18.1%  norm=0.639  lr=2.88e-04  dt=  36.9ms  words=18,784,256
[E02   746/1548 G   2293|CLM] train=4.9153  mask=18.1%  norm=0.820  lr=2.88e-04  dt=  36.8ms  words=18,792,448
[E02   747/1548 G   2294|CLM] train=5.1691  mask=18.1%  norm=0.923  lr=2.88e-04  dt=  36.8ms  words=18,800,640
[E02   748/1548 G   2295|CLM] train=3.2301  mask=18.1%  norm=0.599  lr=2.88e-04  dt=  36.8ms  words=18,808,832
[E02   749/1548 G   2296|CLM] train=4.9843  mask=18.1%  norm=0.988  lr=2.88e-04  dt=  37.0ms  words=18,817,024
[E02   750/1548 G   2297|CLM] train=5.0986  mask=18.1%  norm=0.897  lr=2.88e-04  dt=  36.8ms  words=18,825,216
[E02   751/1548 G   2298|CLM] train=4.6432  mask=18.1%  norm=0.934  lr=2.88e-04  dt=  36.8ms  words=18,833,408
[E02   752/1548 G   2299|CLM] train=4.9188  mask=18.1%  norm=0.738  lr=2.88e-04  dt=  37.1ms  words=18,841,600
[E02   753/1548 G   2300|CLM] train=5.1287  mask=18.1%  norm=0.769  lr=2.88e-04  dt=  36.9ms  words=18,849,792
[E02   754/1548 G   2301|CLM] train=5.1040  mask=18.1%  norm=0.931  lr=2.88e-04  dt=  37.1ms  words=18,857,984
[E02   755/1548 G   2302|CLM] train=5.1794  mask=18.1%  norm=0.714  lr=2.88e-04  dt=  36.9ms  words=18,866,176
[E02   756/1548 G   2303|CLM] train=2.7569  mask=18.1%  norm=0.741  lr=2.88e-04  dt=  36.8ms  words=18,874,368
[E02   757/1548 G   2304|CLM] train=4.6147  mask=18.1%  norm=0.794  lr=2.88e-04  dt=  36.9ms  words=18,882,560
[E02   758/1548 G   2305|CLM] train=2.9873  mask=18.1%  norm=0.995  lr=2.88e-04  dt=  36.9ms  words=18,890,752
[E02   759/1548 G   2306|CLM] train=4.9732  mask=18.1%  norm=0.761  lr=2.88e-04  dt=  36.8ms  words=18,898,944
[E02   760/1548 G   2307|CLM] train=4.7383  mask=18.1%  norm=0.632  lr=2.88e-04  dt=  37.0ms  words=18,907,136
[E02   761/1548 G   2308|CLM] train=4.9692  mask=18.1%  norm=0.675  lr=2.88e-04  dt=  36.8ms  words=18,915,328
[E02   762/1548 G   2309|CLM] train=2.8185  mask=18.1%  norm=0.722  lr=2.88e-04  dt=  37.0ms  words=18,923,520
[E02   763/1548 G   2310|CLM] train=2.7893  mask=18.1%  norm=0.825  lr=2.88e-04  dt=  36.8ms  words=18,931,712
[E02   764/1548 G   2311|CLM] train=5.5053  mask=18.1%  norm=0.767  lr=2.88e-04  dt=  36.7ms  words=18,939,904
[E02   765/1548 G   2312|CLM] train=4.8009  mask=18.1%  norm=1.032  lr=2.88e-04  dt=  37.0ms  words=18,948,096
[E02   766/1548 G   2313|CLM] train=4.9272  mask=18.1%  norm=0.813  lr=2.88e-04  dt=  36.9ms  words=18,956,288
[E02   767/1548 G   2314|CLM] train=4.6892  mask=18.1%  norm=0.715  lr=2.88e-04  dt=  36.9ms  words=18,964,480
[E02   768/1548 G   2315|CLM] train=4.2947  mask=18.1%  norm=1.101  lr=2.88e-04  dt=  37.4ms  words=18,972,672
[E02   769/1548 G   2316|CLM] train=2.5197  mask=18.1%  norm=1.102  lr=2.88e-04  dt=  36.8ms  words=18,980,864
[E02   770/1548 G   2317|CLM] train=3.0751  mask=18.1%  norm=0.875  lr=2.88e-04  dt=  36.8ms  words=18,989,056
[E02   771/1548 G   2318|CLM] train=3.2141  mask=18.1%  norm=1.645  lr=2.88e-04  dt=  36.9ms  words=18,997,248
[E02   772/1548 G   2319|CLM] train=5.3138  mask=18.1%  norm=0.905  lr=2.88e-04  dt=  36.8ms  words=19,005,440
[E02   773/1548 G   2320|CLM] train=5.8931  mask=18.1%  norm=1.117  lr=2.88e-04  dt=  36.9ms  words=19,013,632
[E02   774/1548 G   2321|CLM] train=2.7547  mask=18.1%  norm=0.592  lr=2.88e-04  dt=  37.1ms  words=19,021,824
[E02   775/1548 G   2322|CLM] train=3.1309  mask=18.1%  norm=0.651  lr=2.88e-04  dt=  36.7ms  words=19,030,016
[E02   776/1548 G   2323|CLM] train=5.1433  mask=18.1%  norm=0.887  lr=2.88e-04  dt=  37.0ms  words=19,038,208
[E02   777/1548 G   2324|CLM] train=5.1638  mask=18.1%  norm=0.898  lr=2.88e-04  dt=  36.8ms  words=19,046,400
[E02   778/1548 G   2325|CLM] train=2.6114  mask=18.1%  norm=0.664  lr=2.88e-04  dt=  37.0ms  words=19,054,592
[E02   779/1548 G   2326|CLM] train=2.7171  mask=18.1%  norm=0.814  lr=2.88e-04  dt=  36.9ms  words=19,062,784
[E02   780/1548 G   2327|CLM] train=4.9462  mask=18.1%  norm=0.852  lr=2.88e-04  dt=  37.0ms  words=19,070,976
[E02   781/1548 G   2328|CLM] train=2.8772  mask=18.1%  norm=0.984  lr=2.88e-04  dt=  36.9ms  words=19,079,168
[E02   782/1548 G   2329|CLM] train=2.9445  mask=18.1%  norm=0.624  lr=2.88e-04  dt=  36.9ms  words=19,087,360
[E02   783/1548 G   2330|CLM] train=4.8744  mask=18.1%  norm=0.754  lr=2.88e-04  dt=  37.1ms  words=19,095,552
[E02   784/1548 G   2331|CLM] train=2.6634  mask=18.1%  norm=0.640  lr=2.88e-04  dt=  36.8ms  words=19,103,744
[E02   785/1548 G   2332|CLM] train=3.0061  mask=18.1%  norm=0.565  lr=2.88e-04  dt=  36.9ms  words=19,111,936
[E02   786/1548 G   2333|CLM] train=6.0262  mask=18.1%  norm=2.220  lr=2.88e-04  dt=  36.9ms  words=19,120,128
[E02   787/1548 G   2334|CLM] train=5.1599  mask=18.1%  norm=0.827  lr=2.88e-04  dt=  37.0ms  words=19,128,320
[E02   788/1548 G   2335|CLM] train=2.5355  mask=18.1%  norm=1.306  lr=2.88e-04  dt=  37.0ms  words=19,136,512
[E02   789/1548 G   2336|CLM] train=2.9344  mask=18.1%  norm=0.681  lr=2.88e-04  dt=  36.9ms  words=19,144,704
[E02   790/1548 G   2337|CLM] train=2.9307  mask=18.1%  norm=0.871  lr=2.88e-04  dt=  36.9ms  words=19,152,896
[E02   791/1548 G   2338|CLM] train=2.8861  mask=18.1%  norm=0.552  lr=2.88e-04  dt=  36.9ms  words=19,161,088
[E02   792/1548 G   2339|CLM] train=2.5972  mask=18.1%  norm=0.746  lr=2.88e-04  dt=  36.8ms  words=19,169,280
[E02   793/1548 G   2340|CLM] train=4.6551  mask=18.1%  norm=0.705  lr=2.88e-04  dt=  37.0ms  words=19,177,472
[E02   794/1548 G   2341|CLM] train=2.8490  mask=18.1%  norm=0.803  lr=2.88e-04  dt=  36.8ms  words=19,185,664
[E02   795/1548 G   2342|CLM] train=2.7302  mask=18.1%  norm=0.710  lr=2.88e-04  dt=  37.1ms  words=19,193,856
[E02   796/1548 G   2343|CLM] train=2.9954  mask=18.1%  norm=0.710  lr=2.88e-04  dt=  36.9ms  words=19,202,048
[E02   797/1548 G   2344|CLM] train=4.9476  mask=18.1%  norm=1.993  lr=2.88e-04  dt=  37.0ms  words=19,210,240
[E02   798/1548 G   2345|CLM] train=4.7029  mask=18.1%  norm=1.004  lr=2.88e-04  dt=  37.0ms  words=19,218,432
[E02   799/1548 G   2346|CLM] train=2.7645  mask=18.1%  norm=0.883  lr=2.88e-04  dt=  37.0ms  words=19,226,624
[E02   800/1548 G   2347|CLM] train=5.5679  mask=18.1%  norm=0.701  lr=2.88e-04  dt=  37.0ms  words=19,234,816
[E02   801/1548 G   2348|CLM] train=4.8616  mask=18.1%  norm=1.287  lr=2.88e-04  dt=  37.1ms  words=19,243,008
[E02   802/1548 G   2349|CLM] train=4.9249  mask=18.1%  norm=0.725  lr=2.88e-04  dt=  37.0ms  words=19,251,200
[E02   803/1548 G   2350|CLM] train=5.2089  mask=18.1%  norm=0.867  lr=2.88e-04  dt=  37.1ms  words=19,259,392
[E02   804/1548 G   2351|CLM] train=2.9482  mask=18.1%  norm=1.182  lr=2.88e-04  dt=  36.8ms  words=19,267,584
[E02   805/1548 G   2352|CLM] train=4.9414  mask=18.1%  norm=0.723  lr=2.88e-04  dt=  37.1ms  words=19,275,776
[E02   806/1548 G   2353|CLM] train=2.6224  mask=18.1%  norm=0.986  lr=2.88e-04  dt=  36.8ms  words=19,283,968
[E02   807/1548 G   2354|CLM] train=4.4895  mask=18.1%  norm=0.858  lr=2.88e-04  dt=  37.1ms  words=19,292,160
[E02   808/1548 G   2355|CLM] train=2.6000  mask=18.1%  norm=0.698  lr=2.88e-04  dt=  36.8ms  words=19,300,352
[E02   809/1548 G   2356|CLM] train=3.9116  mask=18.1%  norm=0.761  lr=2.87e-04  dt=  37.0ms  words=19,308,544
[E02   810/1548 G   2357|CLM] train=4.4612  mask=18.1%  norm=0.832  lr=2.87e-04  dt=  36.9ms  words=19,316,736
[E02   811/1548 G   2358|CLM] train=4.7926  mask=18.1%  norm=0.950  lr=2.87e-04  dt=  37.1ms  words=19,324,928
[E02   812/1548 G   2359|CLM] train=4.7474  mask=18.1%  norm=0.751  lr=2.87e-04  dt=  37.0ms  words=19,333,120
[E02   813/1548 G   2360|CLM] train=2.4745  mask=18.1%  norm=1.186  lr=2.87e-04  dt=  36.9ms  words=19,341,312
[E02   814/1548 G   2361|CLM] train=4.9521  mask=18.1%  norm=0.616  lr=2.87e-04  dt=  36.9ms  words=19,349,504
[E02   815/1548 G   2362|CLM] train=2.8576  mask=18.1%  norm=0.740  lr=2.87e-04  dt=  36.8ms  words=19,357,696
[E02   816/1548 G   2363|CLM] train=4.9523  mask=18.1%  norm=0.713  lr=2.87e-04  dt=  36.9ms  words=19,365,888
[E02   817/1548 G   2364|CLM] train=4.4187  mask=18.1%  norm=0.647  lr=2.87e-04  dt=  36.9ms  words=19,374,080
[E02   818/1548 G   2365|CLM] train=5.6383  mask=18.1%  norm=0.783  lr=2.87e-04  dt=  36.8ms  words=19,382,272
[E02   819/1548 G   2366|CLM] train=3.0701  mask=18.1%  norm=0.651  lr=2.87e-04  dt=  36.9ms  words=19,390,464
[E02   820/1548 G   2367|CLM] train=3.1263  mask=18.1%  norm=0.573  lr=2.87e-04  dt=  36.9ms  words=19,398,656
[E02   821/1548 G   2368|CLM] train=5.4563  mask=18.1%  norm=0.870  lr=2.87e-04  dt=  37.1ms  words=19,406,848
[E02   822/1548 G   2369|CLM] train=2.5952  mask=18.1%  norm=0.599  lr=2.87e-04  dt=  37.0ms  words=19,415,040
[E02   823/1548 G   2370|CLM] train=2.7850  mask=18.1%  norm=0.757  lr=2.87e-04  dt=  37.2ms  words=19,423,232
[E02   824/1548 G   2371|CLM] train=2.6375  mask=18.1%  norm=0.702  lr=2.87e-04  dt=  37.0ms  words=19,431,424
[E02   825/1548 G   2372|CLM] train=2.6953  mask=18.1%  norm=0.580  lr=2.87e-04  dt=  37.0ms  words=19,439,616
[E02   826/1548 G   2373|CLM] train=2.8005  mask=18.1%  norm=0.589  lr=2.87e-04  dt=  37.0ms  words=19,447,808
[E02   827/1548 G   2374|CLM] train=4.4090  mask=18.1%  norm=0.743  lr=2.87e-04  dt=  37.1ms  words=19,456,000
[E02   828/1548 G   2375|CLM] train=2.6826  mask=18.1%  norm=1.060  lr=2.87e-04  dt=  37.1ms  words=19,464,192
[E02   829/1548 G   2376|CLM] train=5.0446  mask=18.1%  norm=0.747  lr=2.87e-04  dt=  36.9ms  words=19,472,384
[E02   830/1548 G   2377|CLM] train=2.7713  mask=18.1%  norm=1.179  lr=2.87e-04  dt=  37.0ms  words=19,480,576
[E02   831/1548 G   2378|CLM] train=2.8598  mask=18.1%  norm=0.694  lr=2.87e-04  dt=  36.9ms  words=19,488,768
[E02   832/1548 G   2379|CLM] train=4.9213  mask=18.1%  norm=1.250  lr=2.87e-04  dt=  37.0ms  words=19,496,960
[E02   833/1548 G   2380|CLM] train=4.5773  mask=18.1%  norm=1.234  lr=2.87e-04  dt=  37.0ms  words=19,505,152
[E02   834/1548 G   2381|CLM] train=4.4451  mask=18.1%  norm=0.567  lr=2.87e-04  dt=  37.2ms  words=19,513,344
[E02   835/1548 G   2382|CLM] train=2.8432  mask=18.1%  norm=0.909  lr=2.87e-04  dt=  37.1ms  words=19,521,536
[E02   836/1548 G   2383|CLM] train=5.9321  mask=18.1%  norm=0.907  lr=2.87e-04  dt=  37.3ms  words=19,529,728
[E02   837/1548 G   2384|CLM] train=2.9506  mask=18.1%  norm=0.596  lr=2.87e-04  dt=  36.8ms  words=19,537,920
[E02   838/1548 G   2385|CLM] train=2.9501  mask=18.1%  norm=0.703  lr=2.87e-04  dt=  37.0ms  words=19,546,112
[E02   839/1548 G   2386|CLM] train=4.8085  mask=18.1%  norm=0.852  lr=2.87e-04  dt=  36.9ms  words=19,554,304
[E02   840/1548 G   2387|CLM] train=2.6504  mask=18.1%  norm=0.602  lr=2.87e-04  dt=  36.8ms  words=19,562,496
[E02   841/1548 G   2388|CLM] train=4.9208  mask=18.1%  norm=1.053  lr=2.87e-04  dt=  36.9ms  words=19,570,688
[E02   842/1548 G   2389|CLM] train=4.9177  mask=18.1%  norm=0.672  lr=2.87e-04  dt=  37.0ms  words=19,578,880
[E02   843/1548 G   2390|CLM] train=4.6322  mask=18.1%  norm=0.612  lr=2.87e-04  dt=  36.9ms  words=19,587,072
[E02   844/1548 G   2391|CLM] train=4.4876  mask=18.1%  norm=0.548  lr=2.87e-04  dt=  36.9ms  words=19,595,264
[E02   845/1548 G   2392|CLM] train=3.1286  mask=18.1%  norm=0.744  lr=2.87e-04  dt=  36.9ms  words=19,603,456
[E02   846/1548 G   2393|CLM] train=5.3551  mask=18.1%  norm=1.155  lr=2.87e-04  dt=  36.8ms  words=19,611,648
[E02   847/1548 G   2394|CLM] train=4.8862  mask=18.1%  norm=0.769  lr=2.87e-04  dt=  36.8ms  words=19,619,840
[E02   848/1548 G   2395|CLM] train=4.0197  mask=18.1%  norm=0.635  lr=2.87e-04  dt=  36.9ms  words=19,628,032
[E02   849/1548 G   2396|CLM] train=2.6182  mask=18.1%  norm=0.848  lr=2.87e-04  dt=  37.5ms  words=19,636,224
[E02   850/1548 G   2397|CLM] train=5.5058  mask=18.1%  norm=0.822  lr=2.87e-04  dt=  37.1ms  words=19,644,416
[E02   851/1548 G   2398|CLM] train=2.6742  mask=18.1%  norm=0.795  lr=2.87e-04  dt=  37.1ms  words=19,652,608
[E02   852/1548 G   2399|CLM] train=5.0909  mask=18.1%  norm=0.652  lr=2.87e-04  dt=  37.1ms  words=19,660,800
[E02   853/1548 G   2400|CLM] train=3.0201  mask=18.1%  norm=0.634  lr=2.87e-04  dt=  40.1ms  words=19,668,992
[E02   854/1548 G   2401|CLM] train=4.5467  mask=18.1%  norm=0.577  lr=2.87e-04  dt=  37.6ms  words=19,677,184
[E02   855/1548 G   2402|CLM] train=2.9774  mask=18.1%  norm=0.600  lr=2.87e-04  dt=  42.7ms  words=19,685,376
[E02   856/1548 G   2403|CLM] train=4.4109  mask=18.1%  norm=0.565  lr=2.87e-04  dt=  42.3ms  words=19,693,568
[E02   857/1548 G   2404|CLM] train=3.0555  mask=18.1%  norm=0.626  lr=2.87e-04  dt=  41.5ms  words=19,701,760
[E02   858/1548 G   2405|CLM] train=4.7174  mask=18.1%  norm=0.962  lr=2.87e-04  dt=  42.6ms  words=19,709,952
[E02   859/1548 G   2406|CLM] train=2.5664  mask=18.1%  norm=0.761  lr=2.87e-04  dt=  43.4ms  words=19,718,144
[E02   860/1548 G   2407|CLM] train=5.3944  mask=18.1%  norm=0.825  lr=2.87e-04  dt=  40.6ms  words=19,726,336
[E02   861/1548 G   2408|CLM] train=4.2395  mask=18.1%  norm=0.642  lr=2.87e-04  dt=  37.6ms  words=19,734,528
[E02   862/1548 G   2409|CLM] train=2.8085  mask=18.1%  norm=0.781  lr=2.87e-04  dt=  37.8ms  words=19,742,720
[E02   863/1548 G   2410|CLM] train=2.7477  mask=18.1%  norm=0.643  lr=2.87e-04  dt=  37.8ms  words=19,750,912
[E02   864/1548 G   2411|CLM] train=4.5298  mask=18.1%  norm=0.915  lr=2.87e-04  dt=  37.6ms  words=19,759,104
[E02   865/1548 G   2412|CLM] train=3.9096  mask=18.1%  norm=0.708  lr=2.87e-04  dt=  37.7ms  words=19,767,296
[E02   866/1548 G   2413|CLM] train=3.0695  mask=18.1%  norm=0.641  lr=2.87e-04  dt=  37.4ms  words=19,775,488
[E02   867/1548 G   2414|CLM] train=4.4333  mask=18.1%  norm=0.834  lr=2.87e-04  dt=  37.9ms  words=19,783,680
[E02   868/1548 G   2415|CLM] train=3.0552  mask=18.0%  norm=0.716  lr=2.87e-04  dt=  37.7ms  words=19,791,872
[E02   869/1548 G   2416|CLM] train=2.8572  mask=18.0%  norm=0.955  lr=2.87e-04  dt=  37.6ms  words=19,800,064
[E02   870/1548 G   2417|CLM] train=2.6556  mask=18.0%  norm=0.628  lr=2.87e-04  dt=  37.4ms  words=19,808,256
[E02   871/1548 G   2418|CLM] train=4.9258  mask=18.0%  norm=0.674  lr=2.86e-04  dt=  37.4ms  words=19,816,448
[E02   872/1548 G   2419|CLM] train=5.4885  mask=18.0%  norm=0.884  lr=2.86e-04  dt=  37.4ms  words=19,824,640
[E02   873/1548 G   2420|CLM] train=4.7067  mask=18.0%  norm=0.750  lr=2.86e-04  dt=  37.8ms  words=19,832,832
[E02   874/1548 G   2421|CLM] train=4.9374  mask=18.0%  norm=0.700  lr=2.86e-04  dt=  37.6ms  words=19,841,024
[E02   875/1548 G   2422|CLM] train=4.6785  mask=18.0%  norm=0.698  lr=2.86e-04  dt=  37.3ms  words=19,849,216
[E02   876/1548 G   2423|CLM] train=2.6142  mask=18.0%  norm=0.737  lr=2.86e-04  dt=  37.2ms  words=19,857,408
[E02   877/1548 G   2424|CLM] train=4.7783  mask=18.0%  norm=0.790  lr=2.86e-04  dt=  37.2ms  words=19,865,600
[E02   878/1548 G   2425|CLM] train=5.0726  mask=18.0%  norm=0.715  lr=2.86e-04  dt=  37.2ms  words=19,873,792
[E02   879/1548 G   2426|CLM] train=4.9326  mask=18.0%  norm=1.180  lr=2.86e-04  dt=  37.3ms  words=19,881,984
[E02   880/1548 G   2427|CLM] train=2.8210  mask=18.0%  norm=0.633  lr=2.86e-04  dt=  37.2ms  words=19,890,176
[E02   881/1548 G   2428|CLM] train=5.0088  mask=18.0%  norm=1.068  lr=2.86e-04  dt=  37.2ms  words=19,898,368
[E02   882/1548 G   2429|CLM] train=5.3141  mask=18.0%  norm=0.860  lr=2.86e-04  dt=  37.2ms  words=19,906,560
[E02   883/1548 G   2430|CLM] train=2.8113  mask=18.0%  norm=0.746  lr=2.86e-04  dt=  37.0ms  words=19,914,752
[E02   884/1548 G   2431|CLM] train=2.6397  mask=18.0%  norm=0.666  lr=2.86e-04  dt=  37.3ms  words=19,922,944
[E02   885/1548 G   2432|CLM] train=4.3329  mask=18.0%  norm=0.833  lr=2.86e-04  dt=  37.6ms  words=19,931,136
[E02   886/1548 G   2433|CLM] train=2.8926  mask=18.0%  norm=0.807  lr=2.86e-04  dt=  37.2ms  words=19,939,328
[E02   887/1548 G   2434|CLM] train=3.1071  mask=18.0%  norm=0.725  lr=2.86e-04  dt=  37.2ms  words=19,947,520
[E02   888/1548 G   2435|CLM] train=2.9885  mask=18.0%  norm=0.567  lr=2.86e-04  dt=  37.3ms  words=19,955,712
[E02   889/1548 G   2436|CLM] train=4.3617  mask=18.0%  norm=0.819  lr=2.86e-04  dt=  37.6ms  words=19,963,904
[E02   890/1548 G   2437|CLM] train=4.3036  mask=18.0%  norm=0.571  lr=2.86e-04  dt=  37.2ms  words=19,972,096
[E02   891/1548 G   2438|CLM] train=5.0478  mask=18.0%  norm=0.669  lr=2.86e-04  dt=  37.3ms  words=19,980,288
[E02   892/1548 G   2439|CLM] train=4.4551  mask=18.0%  norm=0.579  lr=2.86e-04  dt=  37.2ms  words=19,988,480
[E02   893/1548 G   2440|CLM] train=4.9612  mask=18.0%  norm=0.736  lr=2.86e-04  dt=  37.1ms  words=19,996,672
[E02   894/1548 G   2441|CLM] train=2.7057  mask=18.0%  norm=0.888  lr=2.86e-04  dt=  37.2ms  words=20,004,864

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_20M'...
[Checkpoint] Checkpoint 'chck_20M' successfully saved.
[E02   895/1548 G   2442|CLM] train=4.6431  mask=18.0%  norm=0.792  lr=2.86e-04  dt=  38.5ms  words=20,013,056
[E02   896/1548 G   2443|CLM] train=4.1997  mask=18.0%  norm=0.728  lr=2.86e-04  dt=  37.9ms  words=20,021,248
[E02   897/1548 G   2444|CLM] train=2.7953  mask=18.0%  norm=0.872  lr=2.86e-04  dt=  37.5ms  words=20,029,440
[E02   898/1548 G   2445|CLM] train=2.7614  mask=18.0%  norm=0.655  lr=2.86e-04  dt=  37.2ms  words=20,037,632
[E02   899/1548 G   2446|CLM] train=4.6854  mask=18.0%  norm=0.807  lr=2.86e-04  dt=  37.1ms  words=20,045,824
[E02   900/1548 G   2447|CLM] train=2.7157  mask=18.0%  norm=0.585  lr=2.86e-04  dt=  37.3ms  words=20,054,016
[E02   901/1548 G   2448|CLM] train=6.2970  mask=18.0%  norm=1.411  lr=2.86e-04  dt=  37.0ms  words=20,062,208
[E02   902/1548 G   2449|CLM] train=5.5833  mask=18.0%  norm=0.783  lr=2.86e-04  dt=  37.2ms  words=20,070,400
[E02   903/1548 G   2450|CLM] train=6.2622  mask=18.0%  norm=0.755  lr=2.86e-04  dt=  37.1ms  words=20,078,592
[E02   904/1548 G   2451|CLM] train=5.3675  mask=18.0%  norm=1.122  lr=2.86e-04  dt=  37.3ms  words=20,086,784
[E02   905/1548 G   2452|CLM] train=4.8372  mask=18.0%  norm=0.634  lr=2.86e-04  dt=  37.2ms  words=20,094,976
[E02   906/1548 G   2453|CLM] train=4.6788  mask=18.0%  norm=0.640  lr=2.86e-04  dt=  37.2ms  words=20,103,168
[E02   907/1548 G   2454|CLM] train=4.1049  mask=18.0%  norm=0.763  lr=2.86e-04  dt=  37.0ms  words=20,111,360
[E02   908/1548 G   2455|CLM] train=4.7230  mask=18.0%  norm=0.670  lr=2.86e-04  dt=  37.3ms  words=20,119,552
[E02   909/1548 G   2456|CLM] train=3.0448  mask=18.0%  norm=0.952  lr=2.86e-04  dt=  37.3ms  words=20,127,744
[E02   910/1548 G   2457|CLM] train=2.9489  mask=18.0%  norm=0.932  lr=2.86e-04  dt=  37.2ms  words=20,135,936
[E02   911/1548 G   2458|CLM] train=4.3043  mask=18.0%  norm=2.660  lr=2.86e-04  dt=  37.3ms  words=20,144,128
[E02   912/1548 G   2459|CLM] train=4.3177  mask=18.0%  norm=0.868  lr=2.86e-04  dt=  37.1ms  words=20,152,320
[E02   913/1548 G   2460|CLM] train=5.9286  mask=18.0%  norm=1.701  lr=2.86e-04  dt=  37.1ms  words=20,160,512
[E02   914/1548 G   2461|CLM] train=4.7519  mask=18.0%  norm=0.649  lr=2.86e-04  dt=  37.1ms  words=20,168,704
[E02   915/1548 G   2462|CLM] train=3.1007  mask=18.0%  norm=0.927  lr=2.86e-04  dt=  37.3ms  words=20,176,896
[E02   916/1548 G   2463|CLM] train=2.5951  mask=18.0%  norm=1.210  lr=2.86e-04  dt=  37.2ms  words=20,185,088
[E02   917/1548 G   2464|CLM] train=4.3326  mask=18.0%  norm=0.780  lr=2.86e-04  dt=  37.1ms  words=20,193,280
[E02   918/1548 G   2465|CLM] train=5.4870  mask=18.0%  norm=0.862  lr=2.86e-04  dt=  37.1ms  words=20,201,472
[E02   919/1548 G   2466|CLM] train=5.0284  mask=18.0%  norm=0.812  lr=2.86e-04  dt=  37.1ms  words=20,209,664
[E02   920/1548 G   2467|CLM] train=2.8831  mask=18.0%  norm=0.723  lr=2.86e-04  dt=  37.2ms  words=20,217,856
[E02   921/1548 G   2468|CLM] train=4.4602  mask=18.0%  norm=0.680  lr=2.86e-04  dt=  37.2ms  words=20,226,048
[E02   922/1548 G   2469|CLM] train=5.2651  mask=18.0%  norm=0.852  lr=2.86e-04  dt=  37.2ms  words=20,234,240
[E02   923/1548 G   2470|CLM] train=2.6931  mask=18.0%  norm=0.815  lr=2.86e-04  dt=  37.2ms  words=20,242,432
[E02   924/1548 G   2471|CLM] train=4.8010  mask=18.0%  norm=0.932  lr=2.86e-04  dt=  37.5ms  words=20,250,624
[E02   925/1548 G   2472|CLM] train=2.7581  mask=18.0%  norm=0.611  lr=2.86e-04  dt=  39.0ms  words=20,258,816
[E02   926/1548 G   2473|CLM] train=4.5126  mask=18.0%  norm=0.796  lr=2.86e-04  dt=  37.4ms  words=20,267,008
[E02   927/1548 G   2474|CLM] train=3.3097  mask=18.0%  norm=0.684  lr=2.86e-04  dt=  37.1ms  words=20,275,200
[E02   928/1548 G   2475|CLM] train=3.1523  mask=18.0%  norm=0.609  lr=2.86e-04  dt=  37.0ms  words=20,283,392
[E02   929/1548 G   2476|CLM] train=5.2523  mask=18.0%  norm=0.837  lr=2.86e-04  dt=  37.0ms  words=20,291,584
[E02   930/1548 G   2477|CLM] train=2.4989  mask=18.0%  norm=0.911  lr=2.86e-04  dt=  37.0ms  words=20,299,776
[E02   931/1548 G   2478|CLM] train=4.4990  mask=18.0%  norm=0.877  lr=2.85e-04  dt=  37.5ms  words=20,307,968
[E02   932/1548 G   2479|CLM] train=4.6558  mask=18.0%  norm=0.829  lr=2.85e-04  dt=  37.0ms  words=20,316,160
[E02   933/1548 G   2480|CLM] train=4.9921  mask=18.0%  norm=0.827  lr=2.85e-04  dt=  37.2ms  words=20,324,352
[E02   934/1548 G   2481|CLM] train=3.2993  mask=18.0%  norm=0.947  lr=2.85e-04  dt=  37.6ms  words=20,332,544
[E02   935/1548 G   2482|CLM] train=4.7502  mask=18.0%  norm=0.637  lr=2.85e-04  dt=  37.2ms  words=20,340,736
[E02   936/1548 G   2483|CLM] train=3.2209  mask=18.0%  norm=0.853  lr=2.85e-04  dt=  37.1ms  words=20,348,928
[E02   937/1548 G   2484|CLM] train=2.5478  mask=18.0%  norm=0.709  lr=2.85e-04  dt=  37.5ms  words=20,357,120
[E02   938/1548 G   2485|CLM] train=6.2045  mask=18.0%  norm=0.933  lr=2.85e-04  dt=  37.1ms  words=20,365,312
[E02   939/1548 G   2486|CLM] train=4.9197  mask=18.0%  norm=0.765  lr=2.85e-04  dt=  37.1ms  words=20,373,504
[E02   940/1548 G   2487|CLM] train=2.9214  mask=18.0%  norm=0.639  lr=2.85e-04  dt=  37.2ms  words=20,381,696
[E02   941/1548 G   2488|CLM] train=2.7776  mask=18.0%  norm=1.353  lr=2.85e-04  dt=  37.2ms  words=20,389,888
[E02   942/1548 G   2489|CLM] train=2.8854  mask=18.0%  norm=0.715  lr=2.85e-04  dt=  37.2ms  words=20,398,080
[E02   943/1548 G   2490|CLM] train=3.1507  mask=18.0%  norm=1.391  lr=2.85e-04  dt=  36.9ms  words=20,406,272
[E02   944/1548 G   2491|CLM] train=2.3110  mask=18.0%  norm=0.987  lr=2.85e-04  dt=  37.3ms  words=20,414,464
[E02   945/1548 G   2492|CLM] train=2.7228  mask=18.0%  norm=0.691  lr=2.85e-04  dt=  37.3ms  words=20,422,656
[E02   946/1548 G   2493|CLM] train=2.7788  mask=18.0%  norm=0.755  lr=2.85e-04  dt=  37.1ms  words=20,430,848
[E02   947/1548 G   2494|CLM] train=4.5109  mask=18.0%  norm=0.790  lr=2.85e-04  dt=  37.1ms  words=20,439,040
[E02   948/1548 G   2495|CLM] train=4.5733  mask=18.0%  norm=0.728  lr=2.85e-04  dt=  37.2ms  words=20,447,232
[E02   949/1548 G   2496|CLM] train=2.8894  mask=18.0%  norm=0.733  lr=2.85e-04  dt=  37.3ms  words=20,455,424
[E02   950/1548 G   2497|CLM] train=4.2306  mask=18.0%  norm=0.564  lr=2.85e-04  dt=  37.0ms  words=20,463,616
[E02   951/1548 G   2498|CLM] train=4.7836  mask=18.0%  norm=0.656  lr=2.85e-04  dt=  38.3ms  words=20,471,808
[E02   952/1548 G   2499|CLM] train=4.9068  mask=18.0%  norm=0.689  lr=2.85e-04  dt=  38.4ms  words=20,480,000
[E02   953/1548 G   2500|CLM] train=3.2699  mask=18.0%  norm=0.674  lr=2.85e-04  dt=  37.5ms  words=20,488,192
[E02   954/1548 G   2501|CLM] train=4.8153  mask=18.0%  norm=0.707  lr=2.85e-04  dt=  37.4ms  words=20,496,384
[E02   955/1548 G   2502|CLM] train=2.7284  mask=18.0%  norm=0.692  lr=2.85e-04  dt=  37.6ms  words=20,504,576
[E02   956/1548 G   2503|CLM] train=3.1128  mask=18.0%  norm=1.716  lr=2.85e-04  dt=  37.5ms  words=20,512,768
[E02   957/1548 G   2504|CLM] train=2.7746  mask=18.0%  norm=1.181  lr=2.85e-04  dt=  37.4ms  words=20,520,960
[E02   958/1548 G   2505|CLM] train=5.2417  mask=18.0%  norm=0.701  lr=2.85e-04  dt=  37.3ms  words=20,529,152
[E02   959/1548 G   2506|CLM] train=4.2542  mask=18.0%  norm=0.626  lr=2.85e-04  dt=  37.1ms  words=20,537,344
[E02   960/1548 G   2507|CLM] train=4.0456  mask=18.0%  norm=0.900  lr=2.85e-04  dt=  37.4ms  words=20,545,536
[E02   961/1548 G   2508|CLM] train=4.7597  mask=18.0%  norm=1.172  lr=2.85e-04  dt=  37.9ms  words=20,553,728
[E02   962/1548 G   2509|CLM] train=2.6337  mask=18.0%  norm=0.873  lr=2.85e-04  dt=  38.1ms  words=20,561,920
[E02   963/1548 G   2510|CLM] train=2.6290  mask=18.0%  norm=0.838  lr=2.85e-04  dt=  37.3ms  words=20,570,112
[E02   964/1548 G   2511|CLM] train=4.5136  mask=18.0%  norm=0.671  lr=2.85e-04  dt=  37.9ms  words=20,578,304
[E02   965/1548 G   2512|CLM] train=5.1415  mask=18.0%  norm=0.922  lr=2.85e-04  dt=  37.4ms  words=20,586,496
[E02   966/1548 G   2513|CLM] train=3.2728  mask=18.0%  norm=0.825  lr=2.85e-04  dt=  51.2ms  words=20,594,688
[E02   967/1548 G   2514|CLM] train=6.0929  mask=18.0%  norm=1.033  lr=2.85e-04  dt=  37.0ms  words=20,602,880
[E02   968/1548 G   2515|CLM] train=4.6797  mask=18.0%  norm=0.827  lr=2.85e-04  dt=  41.4ms  words=20,611,072
[E02   969/1548 G   2516|CLM] train=4.2151  mask=18.0%  norm=0.830  lr=2.85e-04  dt=  37.0ms  words=20,619,264
[E02   970/1548 G   2517|CLM] train=4.3385  mask=18.0%  norm=0.708  lr=2.85e-04  dt=  37.1ms  words=20,627,456
[E02   971/1548 G   2518|CLM] train=4.4429  mask=18.0%  norm=0.551  lr=2.85e-04  dt=  37.0ms  words=20,635,648
[E02   972/1548 G   2519|CLM] train=2.8885  mask=18.0%  norm=1.185  lr=2.85e-04  dt=  36.9ms  words=20,643,840
[E02   973/1548 G   2520|CLM] train=5.3276  mask=18.0%  norm=1.159  lr=2.85e-04  dt=  36.8ms  words=20,652,032
[E02   974/1548 G   2521|CLM] train=4.9398  mask=18.0%  norm=1.051  lr=2.85e-04  dt=  37.3ms  words=20,660,224
[E02   975/1548 G   2522|CLM] train=5.6466  mask=18.0%  norm=1.252  lr=2.85e-04  dt=  37.7ms  words=20,668,416
[E02   976/1548 G   2523|CLM] train=3.0238  mask=18.0%  norm=0.788  lr=2.85e-04  dt=  37.2ms  words=20,676,608
[E02   977/1548 G   2524|CLM] train=5.3685  mask=18.0%  norm=0.867  lr=2.85e-04  dt=  37.3ms  words=20,684,800
[E02   978/1548 G   2525|CLM] train=4.4400  mask=18.0%  norm=0.797  lr=2.85e-04  dt=  37.1ms  words=20,692,992
[E02   979/1548 G   2526|CLM] train=2.9099  mask=18.0%  norm=0.655  lr=2.85e-04  dt=  37.3ms  words=20,701,184
[E02   980/1548 G   2527|CLM] train=5.1427  mask=18.0%  norm=0.693  lr=2.85e-04  dt=  37.6ms  words=20,709,376
[E02   981/1548 G   2528|CLM] train=2.8986  mask=18.0%  norm=0.648  lr=2.85e-04  dt=  37.1ms  words=20,717,568
[E02   982/1548 G   2529|CLM] train=3.5009  mask=18.0%  norm=0.781  lr=2.85e-04  dt=  37.1ms  words=20,725,760
[E02   983/1548 G   2530|CLM] train=4.9642  mask=18.0%  norm=0.717  lr=2.85e-04  dt=  37.1ms  words=20,733,952
[E02   984/1548 G   2531|CLM] train=4.0353  mask=18.0%  norm=0.770  lr=2.85e-04  dt=  37.0ms  words=20,742,144
[E02   985/1548 G   2532|CLM] train=6.3373  mask=18.0%  norm=1.667  lr=2.85e-04  dt=  37.2ms  words=20,750,336
[E02   986/1548 G   2533|CLM] train=4.8552  mask=18.0%  norm=0.696  lr=2.85e-04  dt=  37.2ms  words=20,758,528
[E02   987/1548 G   2534|CLM] train=5.0700  mask=18.0%  norm=0.673  lr=2.85e-04  dt=  37.1ms  words=20,766,720
[E02   988/1548 G   2535|CLM] train=4.9837  mask=18.0%  norm=0.859  lr=2.85e-04  dt=  37.2ms  words=20,774,912
[E02   989/1548 G   2536|CLM] train=2.7504  mask=18.0%  norm=0.752  lr=2.84e-04  dt=  37.3ms  words=20,783,104
[E02   990/1548 G   2537|CLM] train=2.2299  mask=18.0%  norm=1.191  lr=2.84e-04  dt=  37.2ms  words=20,791,296
[E02   991/1548 G   2538|CLM] train=2.6339  mask=18.0%  norm=0.787  lr=2.84e-04  dt=  37.2ms  words=20,799,488
[E02   992/1548 G   2539|CLM] train=4.6676  mask=17.9%  norm=0.900  lr=2.84e-04  dt=  37.2ms  words=20,807,680
[E02   993/1548 G   2540|CLM] train=2.5579  mask=17.9%  norm=0.526  lr=2.84e-04  dt=  37.1ms  words=20,815,872
[E02   994/1548 G   2541|CLM] train=5.3216  mask=17.9%  norm=1.091  lr=2.84e-04  dt=  37.1ms  words=20,824,064
[E02   995/1548 G   2542|CLM] train=2.6730  mask=17.9%  norm=0.768  lr=2.84e-04  dt=  37.3ms  words=20,832,256
[E02   996/1548 G   2543|CLM] train=5.4058  mask=17.9%  norm=1.696  lr=2.84e-04  dt=  37.1ms  words=20,840,448
[E02   997/1548 G   2544|CLM] train=5.3142  mask=17.9%  norm=0.777  lr=2.84e-04  dt=  37.0ms  words=20,848,640
[E02   998/1548 G   2545|CLM] train=2.8756  mask=17.9%  norm=0.820  lr=2.84e-04  dt=  37.1ms  words=20,856,832
[E02   999/1548 G   2546|CLM] train=2.8415  mask=17.9%  norm=0.789  lr=2.84e-04  dt=  37.1ms  words=20,865,024
[E02  1000/1548 G   2547|CLM] train=5.9446  mask=17.9%  norm=0.857  lr=2.84e-04  dt=  37.0ms  words=20,873,216
[E02  1001/1548 G   2548|CLM] train=4.8334  mask=17.9%  norm=0.673  lr=2.84e-04  dt=  37.2ms  words=20,881,408
[E02  1002/1548 G   2549|CLM] train=2.5515  mask=17.9%  norm=0.716  lr=2.84e-04  dt=  37.5ms  words=20,889,600
[E02  1003/1548 G   2550|CLM] train=4.4174  mask=17.9%  norm=1.126  lr=2.84e-04  dt=  37.3ms  words=20,897,792
[E02  1004/1548 G   2551|CLM] train=2.7801  mask=17.9%  norm=1.086  lr=2.84e-04  dt=  37.2ms  words=20,905,984
[E02  1005/1548 G   2552|CLM] train=4.8170  mask=17.9%  norm=0.680  lr=2.84e-04  dt=  37.1ms  words=20,914,176
[E02  1006/1548 G   2553|CLM] train=4.9670  mask=17.9%  norm=0.793  lr=2.84e-04  dt=  37.2ms  words=20,922,368
[E02  1007/1548 G   2554|CLM] train=4.9024  mask=17.9%  norm=0.599  lr=2.84e-04  dt=  37.2ms  words=20,930,560
[E02  1008/1548 G   2555|CLM] train=6.4762  mask=17.9%  norm=1.505  lr=2.84e-04  dt=  37.1ms  words=20,938,752
[E02  1009/1548 G   2556|CLM] train=3.0595  mask=17.9%  norm=1.142  lr=2.84e-04  dt=  37.2ms  words=20,946,944
[E02  1010/1548 G   2557|CLM] train=4.8292  mask=17.9%  norm=0.693  lr=2.84e-04  dt=  36.9ms  words=20,955,136
[E02  1011/1548 G   2558|CLM] train=2.8151  mask=17.9%  norm=0.881  lr=2.84e-04  dt=  37.0ms  words=20,963,328
[E02  1012/1548 G   2559|CLM] train=4.7210  mask=17.9%  norm=0.683  lr=2.84e-04  dt=  37.1ms  words=20,971,520
[E02  1013/1548 G   2560|CLM] train=4.6256  mask=17.9%  norm=0.740  lr=2.84e-04  dt=  36.9ms  words=20,979,712
[E02  1014/1548 G   2561|CLM] train=4.8163  mask=17.9%  norm=0.602  lr=2.84e-04  dt=  37.2ms  words=20,987,904
[E02  1015/1548 G   2562|CLM] train=2.7919  mask=17.9%  norm=0.682  lr=2.84e-04  dt=  37.2ms  words=20,996,096
[E02  1016/1548 G   2563|CLM] train=2.6398  mask=17.9%  norm=0.710  lr=2.84e-04  dt=  37.0ms  words=21,004,288
[E02  1017/1548 G   2564|CLM] train=5.1090  mask=17.9%  norm=1.794  lr=2.84e-04  dt=  37.7ms  words=21,012,480
[E02  1018/1548 G   2565|CLM] train=2.7310  mask=17.9%  norm=0.710  lr=2.84e-04  dt=  37.2ms  words=21,020,672
[E02  1019/1548 G   2566|CLM] train=5.0833  mask=17.9%  norm=0.844  lr=2.84e-04  dt=  37.0ms  words=21,028,864
[E02  1020/1548 G   2567|CLM] train=4.6654  mask=17.9%  norm=0.871  lr=2.84e-04  dt=  36.9ms  words=21,037,056
[E02  1021/1548 G   2568|CLM] train=2.6370  mask=17.9%  norm=0.666  lr=2.84e-04  dt=  37.0ms  words=21,045,248
[E02  1022/1548 G   2569|CLM] train=2.7786  mask=17.9%  norm=1.026  lr=2.84e-04  dt=  37.1ms  words=21,053,440
[E02  1023/1548 G   2570|CLM] train=5.6268  mask=17.9%  norm=0.879  lr=2.84e-04  dt=  37.2ms  words=21,061,632
[E02  1024/1548 G   2571|CLM] train=3.2508  mask=17.9%  norm=0.657  lr=2.84e-04  dt=  37.2ms  words=21,069,824
[E02  1025/1548 G   2572|CLM] train=4.4492  mask=17.9%  norm=0.687  lr=2.84e-04  dt=  37.2ms  words=21,078,016
[E02  1026/1548 G   2573|CLM] train=4.7381  mask=17.9%  norm=0.637  lr=2.84e-04  dt=  36.9ms  words=21,086,208
[E02  1027/1548 G   2574|CLM] train=5.9948  mask=17.9%  norm=1.459  lr=2.84e-04  dt=  37.5ms  words=21,094,400
[E02  1028/1548 G   2575|CLM] train=2.9088  mask=17.9%  norm=0.522  lr=2.84e-04  dt=  37.1ms  words=21,102,592
[E02  1029/1548 G   2576|CLM] train=2.7469  mask=17.9%  norm=0.658  lr=2.84e-04  dt=  37.3ms  words=21,110,784
[E02  1030/1548 G   2577|CLM] train=2.6249  mask=17.9%  norm=0.740  lr=2.84e-04  dt=  37.0ms  words=21,118,976
[E02  1031/1548 G   2578|CLM] train=4.6590  mask=17.9%  norm=0.769  lr=2.84e-04  dt=  36.9ms  words=21,127,168
[E02  1032/1548 G   2579|CLM] train=2.9260  mask=17.9%  norm=0.718  lr=2.84e-04  dt=  37.1ms  words=21,135,360
[E02  1033/1548 G   2580|CLM] train=2.8042  mask=17.9%  norm=0.705  lr=2.84e-04  dt=  37.3ms  words=21,143,552
[E02  1034/1548 G   2581|CLM] train=4.0206  mask=17.9%  norm=0.675  lr=2.84e-04  dt=  37.0ms  words=21,151,744
[E02  1035/1548 G   2582|CLM] train=4.3939  mask=17.9%  norm=0.996  lr=2.84e-04  dt=  37.3ms  words=21,159,936
[E02  1036/1548 G   2583|CLM] train=4.3567  mask=17.9%  norm=0.576  lr=2.84e-04  dt=  37.1ms  words=21,168,128
[E02  1037/1548 G   2584|CLM] train=2.5527  mask=17.9%  norm=0.920  lr=2.84e-04  dt=  37.1ms  words=21,176,320
[E02  1038/1548 G   2585|CLM] train=3.4564  mask=17.9%  norm=1.367  lr=2.84e-04  dt=  37.2ms  words=21,184,512
[E02  1039/1548 G   2586|CLM] train=5.1447  mask=17.9%  norm=0.810  lr=2.84e-04  dt=  36.9ms  words=21,192,704
[E02  1040/1548 G   2587|CLM] train=4.6052  mask=17.9%  norm=0.739  lr=2.84e-04  dt=  36.9ms  words=21,200,896
[E02  1041/1548 G   2588|CLM] train=5.1254  mask=17.9%  norm=0.719  lr=2.84e-04  dt=  37.0ms  words=21,209,088
[E02  1042/1548 G   2589|CLM] train=4.3480  mask=17.9%  norm=0.713  lr=2.84e-04  dt=  37.1ms  words=21,217,280
[E02  1043/1548 G   2590|CLM] train=5.4250  mask=17.9%  norm=0.879  lr=2.84e-04  dt=  37.0ms  words=21,225,472
[E02  1044/1548 G   2591|CLM] train=4.6715  mask=17.9%  norm=0.668  lr=2.84e-04  dt=  37.4ms  words=21,233,664
[E02  1045/1548 G   2592|CLM] train=2.7572  mask=17.9%  norm=0.805  lr=2.84e-04  dt=  37.1ms  words=21,241,856
[E02  1046/1548 G   2593|CLM] train=2.7816  mask=17.9%  norm=0.802  lr=2.83e-04  dt=  36.9ms  words=21,250,048
[E02  1047/1548 G   2594|CLM] train=4.7884  mask=17.9%  norm=0.777  lr=2.83e-04  dt=  37.0ms  words=21,258,240
[E02  1048/1548 G   2595|CLM] train=4.3491  mask=17.9%  norm=0.661  lr=2.83e-04  dt=  36.9ms  words=21,266,432
[E02  1049/1548 G   2596|CLM] train=4.2980  mask=17.9%  norm=0.768  lr=2.83e-04  dt=  37.1ms  words=21,274,624
[E02  1050/1548 G   2597|CLM] train=3.2570  mask=17.9%  norm=0.625  lr=2.83e-04  dt=  37.1ms  words=21,282,816
[E02  1051/1548 G   2598|CLM] train=5.1485  mask=17.9%  norm=1.004  lr=2.83e-04  dt=  37.0ms  words=21,291,008
[E02  1052/1548 G   2599|CLM] train=4.7258  mask=17.9%  norm=0.645  lr=2.83e-04  dt=  37.1ms  words=21,299,200
[E02  1053/1548 G   2600|CLM] train=3.9256  mask=17.9%  norm=0.619  lr=2.83e-04  dt=  36.9ms  words=21,307,392
[E02  1054/1548 G   2601|CLM] train=5.1445  mask=17.9%  norm=0.724  lr=2.83e-04  dt=  37.3ms  words=21,315,584
[E02  1055/1548 G   2602|CLM] train=2.7275  mask=17.9%  norm=0.867  lr=2.83e-04  dt=  38.0ms  words=21,323,776
[E02  1056/1548 G   2603|CLM] train=2.5664  mask=17.9%  norm=0.791  lr=2.83e-04  dt=  42.1ms  words=21,331,968
[E02  1057/1548 G   2604|CLM] train=4.8408  mask=17.9%  norm=0.842  lr=2.83e-04  dt=  39.4ms  words=21,340,160
[E02  1058/1548 G   2605|CLM] train=4.5929  mask=17.9%  norm=1.036  lr=2.83e-04  dt=  37.0ms  words=21,348,352
[E02  1059/1548 G   2606|CLM] train=2.7935  mask=17.9%  norm=0.542  lr=2.83e-04  dt=  37.1ms  words=21,356,544
[E02  1060/1548 G   2607|CLM] train=2.4140  mask=17.9%  norm=0.900  lr=2.83e-04  dt=  37.0ms  words=21,364,736
[E02  1061/1548 G   2608|CLM] train=2.6203  mask=17.9%  norm=0.632  lr=2.83e-04  dt=  37.2ms  words=21,372,928
[E02  1062/1548 G   2609|CLM] train=3.0914  mask=17.9%  norm=0.605  lr=2.83e-04  dt=  37.2ms  words=21,381,120
[E02  1063/1548 G   2610|CLM] train=4.6629  mask=17.9%  norm=0.773  lr=2.83e-04  dt=  37.0ms  words=21,389,312
[E02  1064/1548 G   2611|CLM] train=2.5316  mask=17.9%  norm=0.909  lr=2.83e-04  dt=  36.9ms  words=21,397,504
[E02  1065/1548 G   2612|CLM] train=2.7354  mask=17.9%  norm=0.716  lr=2.83e-04  dt=  36.9ms  words=21,405,696
[E02  1066/1548 G   2613|CLM] train=5.0181  mask=17.9%  norm=0.795  lr=2.83e-04  dt=  37.1ms  words=21,413,888
[E02  1067/1548 G   2614|CLM] train=3.2188  mask=17.9%  norm=0.781  lr=2.83e-04  dt=  37.0ms  words=21,422,080
[E02  1068/1548 G   2615|CLM] train=2.8591  mask=17.9%  norm=0.736  lr=2.83e-04  dt=  37.0ms  words=21,430,272
[E02  1069/1548 G   2616|CLM] train=5.1730  mask=17.9%  norm=1.099  lr=2.83e-04  dt=  37.0ms  words=21,438,464
[E02  1070/1548 G   2617|CLM] train=2.7333  mask=17.9%  norm=0.592  lr=2.83e-04  dt=  37.2ms  words=21,446,656
[E02  1071/1548 G   2618|CLM] train=6.0259  mask=17.9%  norm=2.785  lr=2.83e-04  dt=  37.0ms  words=21,454,848
[E02  1072/1548 G   2619|CLM] train=5.5758  mask=17.9%  norm=0.752  lr=2.83e-04  dt=  36.9ms  words=21,463,040
[E02  1073/1548 G   2620|CLM] train=4.0389  mask=17.9%  norm=0.886  lr=2.83e-04  dt=  37.2ms  words=21,471,232
[E02  1074/1548 G   2621|CLM] train=4.4163  mask=17.9%  norm=0.633  lr=2.83e-04  dt=  36.9ms  words=21,479,424
[E02  1075/1548 G   2622|CLM] train=4.7285  mask=17.9%  norm=0.631  lr=2.83e-04  dt=  37.1ms  words=21,487,616
[E02  1076/1548 G   2623|CLM] train=4.2173  mask=17.9%  norm=0.813  lr=2.83e-04  dt=  36.9ms  words=21,495,808
[E02  1077/1548 G   2624|CLM] train=2.8073  mask=17.9%  norm=0.828  lr=2.83e-04  dt=  37.1ms  words=21,504,000
[E02  1078/1548 G   2625|CLM] train=2.7838  mask=17.9%  norm=0.668  lr=2.83e-04  dt=  37.2ms  words=21,512,192
[E02  1079/1548 G   2626|CLM] train=3.1537  mask=17.9%  norm=0.740  lr=2.83e-04  dt=  37.0ms  words=21,520,384
[E02  1080/1548 G   2627|CLM] train=4.9423  mask=17.9%  norm=0.631  lr=2.83e-04  dt=  37.4ms  words=21,528,576
[E02  1081/1548 G   2628|CLM] train=4.1090  mask=17.9%  norm=0.636  lr=2.83e-04  dt=  37.1ms  words=21,536,768
[E02  1082/1548 G   2629|CLM] train=4.6129  mask=17.9%  norm=0.750  lr=2.83e-04  dt=  37.2ms  words=21,544,960
[E02  1083/1548 G   2630|CLM] train=6.1370  mask=17.9%  norm=1.232  lr=2.83e-04  dt=  37.5ms  words=21,553,152
[E02  1084/1548 G   2631|CLM] train=5.1709  mask=17.9%  norm=0.755  lr=2.83e-04  dt=  37.4ms  words=21,561,344
[E02  1085/1548 G   2632|CLM] train=4.8788  mask=17.9%  norm=0.905  lr=2.83e-04  dt=  46.4ms  words=21,569,536
[E02  1086/1548 G   2633|CLM] train=4.7084  mask=17.9%  norm=0.984  lr=2.83e-04  dt=  50.0ms  words=21,577,728
[E02  1087/1548 G   2634|CLM] train=4.9109  mask=17.9%  norm=0.824  lr=2.83e-04  dt=  39.5ms  words=21,585,920
[E02  1088/1548 G   2635|CLM] train=2.4809  mask=17.9%  norm=0.762  lr=2.83e-04  dt=  36.8ms  words=21,594,112
[E02  1089/1548 G   2636|CLM] train=4.6484  mask=17.9%  norm=0.620  lr=2.83e-04  dt=  37.1ms  words=21,602,304
[E02  1090/1548 G   2637|CLM] train=4.6378  mask=17.9%  norm=0.762  lr=2.83e-04  dt=  36.9ms  words=21,610,496
[E02  1091/1548 G   2638|CLM] train=4.4755  mask=17.9%  norm=0.571  lr=2.83e-04  dt=  37.0ms  words=21,618,688
[E02  1092/1548 G   2639|CLM] train=2.7053  mask=17.9%  norm=0.824  lr=2.83e-04  dt=  36.9ms  words=21,626,880
[E02  1093/1548 G   2640|CLM] train=4.7706  mask=17.9%  norm=0.583  lr=2.83e-04  dt=  37.0ms  words=21,635,072
[E02  1094/1548 G   2641|CLM] train=5.3143  mask=17.9%  norm=0.932  lr=2.83e-04  dt=  36.9ms  words=21,643,264
[E02  1095/1548 G   2642|CLM] train=4.4204  mask=17.9%  norm=0.950  lr=2.83e-04  dt=  37.0ms  words=21,651,456
[E02  1096/1548 G   2643|CLM] train=5.9117  mask=17.9%  norm=0.710  lr=2.83e-04  dt=  36.9ms  words=21,659,648
[E02  1097/1548 G   2644|CLM] train=4.1455  mask=17.9%  norm=0.622  lr=2.83e-04  dt=  37.1ms  words=21,667,840
[E02  1098/1548 G   2645|CLM] train=3.1698  mask=17.9%  norm=0.703  lr=2.83e-04  dt=  36.8ms  words=21,676,032
[E02  1099/1548 G   2646|CLM] train=5.1107  mask=17.9%  norm=0.860  lr=2.83e-04  dt=  36.8ms  words=21,684,224
[E02  1100/1548 G   2647|CLM] train=4.2573  mask=17.9%  norm=0.679  lr=2.82e-04  dt=  37.1ms  words=21,692,416
[E02  1101/1548 G   2648|CLM] train=5.9294  mask=17.9%  norm=1.176  lr=2.82e-04  dt=  37.0ms  words=21,700,608
[E02  1102/1548 G   2649|CLM] train=5.0628  mask=17.9%  norm=0.800  lr=2.82e-04  dt=  36.8ms  words=21,708,800
[E02  1103/1548 G   2650|CLM] train=4.8443  mask=17.9%  norm=0.724  lr=2.82e-04  dt=  36.7ms  words=21,716,992
[E02  1104/1548 G   2651|CLM] train=4.7826  mask=17.9%  norm=0.642  lr=2.82e-04  dt=  36.9ms  words=21,725,184
[E02  1105/1548 G   2652|CLM] train=2.5685  mask=17.9%  norm=0.738  lr=2.82e-04  dt=  37.0ms  words=21,733,376
[E02  1106/1548 G   2653|CLM] train=6.2884  mask=17.9%  norm=1.927  lr=2.82e-04  dt=  37.0ms  words=21,741,568
[E02  1107/1548 G   2654|CLM] train=2.7630  mask=17.9%  norm=1.103  lr=2.82e-04  dt=  37.1ms  words=21,749,760
[E02  1108/1548 G   2655|CLM] train=5.6955  mask=17.9%  norm=0.899  lr=2.82e-04  dt=  37.0ms  words=21,757,952
[E02  1109/1548 G   2656|CLM] train=2.8555  mask=17.9%  norm=0.638  lr=2.82e-04  dt=  38.7ms  words=21,766,144
[E02  1110/1548 G   2657|CLM] train=4.5875  mask=17.9%  norm=0.696  lr=2.82e-04  dt=  44.3ms  words=21,774,336
[E02  1111/1548 G   2658|CLM] train=5.2066  mask=17.9%  norm=0.824  lr=2.82e-04  dt=  43.7ms  words=21,782,528
[E02  1112/1548 G   2659|CLM] train=4.8303  mask=17.9%  norm=0.823  lr=2.82e-04  dt=  44.2ms  words=21,790,720
[E02  1113/1548 G   2660|CLM] train=2.8246  mask=17.9%  norm=0.717  lr=2.82e-04  dt=  37.3ms  words=21,798,912
[E02  1114/1548 G   2661|CLM] train=4.6006  mask=17.9%  norm=0.743  lr=2.82e-04  dt=  37.7ms  words=21,807,104
[E02  1115/1548 G   2662|CLM] train=4.7417  mask=17.9%  norm=0.634  lr=2.82e-04  dt=  38.0ms  words=21,815,296
[E02  1116/1548 G   2663|CLM] train=5.0363  mask=17.8%  norm=0.687  lr=2.82e-04  dt=  38.0ms  words=21,823,488
[E02  1117/1548 G   2664|CLM] train=5.3905  mask=17.8%  norm=0.773  lr=2.82e-04  dt=  37.7ms  words=21,831,680
[E02  1118/1548 G   2665|CLM] train=3.0489  mask=17.8%  norm=1.466  lr=2.82e-04  dt=  38.5ms  words=21,839,872
[E02  1119/1548 G   2666|CLM] train=4.3182  mask=17.8%  norm=0.738  lr=2.82e-04  dt=  38.3ms  words=21,848,064
[E02  1120/1548 G   2667|CLM] train=3.9987  mask=17.8%  norm=0.603  lr=2.82e-04  dt=  38.0ms  words=21,856,256
[E02  1121/1548 G   2668|CLM] train=4.1892  mask=17.8%  norm=0.567  lr=2.82e-04  dt=  38.4ms  words=21,864,448
[E02  1122/1548 G   2669|CLM] train=2.5854  mask=17.8%  norm=0.829  lr=2.82e-04  dt=  37.1ms  words=21,872,640
[E02  1123/1548 G   2670|CLM] train=4.4985  mask=17.8%  norm=1.020  lr=2.82e-04  dt=  39.6ms  words=21,880,832
[E02  1124/1548 G   2671|CLM] train=4.8984  mask=17.8%  norm=0.894  lr=2.82e-04  dt=  44.6ms  words=21,889,024
[E02  1125/1548 G   2672|CLM] train=4.1443  mask=17.8%  norm=0.662  lr=2.82e-04  dt=  45.3ms  words=21,897,216
[E02  1126/1548 G   2673|CLM] train=3.0272  mask=17.8%  norm=0.767  lr=2.82e-04  dt=  43.5ms  words=21,905,408
[E02  1127/1548 G   2674|CLM] train=5.0872  mask=17.8%  norm=0.727  lr=2.82e-04  dt=  41.3ms  words=21,913,600
[E02  1128/1548 G   2675|CLM] train=5.5612  mask=17.8%  norm=0.777  lr=2.82e-04  dt=  36.8ms  words=21,921,792
[E02  1129/1548 G   2676|CLM] train=4.4769  mask=17.8%  norm=0.686  lr=2.82e-04  dt=  37.0ms  words=21,929,984
[E02  1130/1548 G   2677|CLM] train=4.6199  mask=17.8%  norm=0.677  lr=2.82e-04  dt=  37.0ms  words=21,938,176
[E02  1131/1548 G   2678|CLM] train=2.5536  mask=17.8%  norm=0.815  lr=2.82e-04  dt=  42.2ms  words=21,946,368
[E02  1132/1548 G   2679|CLM] train=5.8157  mask=17.8%  norm=1.786  lr=2.82e-04  dt=  40.8ms  words=21,954,560
[E02  1133/1548 G   2680|CLM] train=4.2161  mask=17.8%  norm=0.853  lr=2.82e-04  dt=  37.0ms  words=21,962,752
[E02  1134/1548 G   2681|CLM] train=4.7084  mask=17.8%  norm=0.715  lr=2.82e-04  dt=  37.0ms  words=21,970,944
[E02  1135/1548 G   2682|CLM] train=4.3799  mask=17.8%  norm=0.775  lr=2.82e-04  dt=  37.1ms  words=21,979,136
[E02  1136/1548 G   2683|CLM] train=4.6686  mask=17.8%  norm=0.882  lr=2.82e-04  dt=  37.1ms  words=21,987,328
[E02  1137/1548 G   2684|CLM] train=5.0388  mask=17.8%  norm=0.856  lr=2.82e-04  dt=  37.0ms  words=21,995,520
[E02  1138/1548 G   2685|CLM] train=4.5485  mask=17.8%  norm=0.728  lr=2.82e-04  dt=  37.0ms  words=22,003,712
[E02  1139/1548 G   2686|CLM] train=4.0899  mask=17.8%  norm=0.672  lr=2.82e-04  dt=  37.0ms  words=22,011,904
[E02  1140/1548 G   2687|CLM] train=4.8733  mask=17.8%  norm=0.608  lr=2.82e-04  dt=  37.0ms  words=22,020,096
[E02  1141/1548 G   2688|CLM] train=2.5182  mask=17.8%  norm=1.043  lr=2.82e-04  dt=  36.8ms  words=22,028,288
[E02  1142/1548 G   2689|CLM] train=3.0327  mask=17.8%  norm=1.305  lr=2.82e-04  dt=  36.9ms  words=22,036,480
[E02  1143/1548 G   2690|CLM] train=4.7235  mask=17.8%  norm=0.825  lr=2.82e-04  dt=  36.9ms  words=22,044,672
[E02  1144/1548 G   2691|CLM] train=5.0230  mask=17.8%  norm=0.651  lr=2.82e-04  dt=  36.9ms  words=22,052,864
[E02  1145/1548 G   2692|CLM] train=4.7455  mask=17.8%  norm=0.815  lr=2.82e-04  dt=  37.0ms  words=22,061,056
[E02  1146/1548 G   2693|CLM] train=2.6877  mask=17.8%  norm=0.689  lr=2.82e-04  dt=  36.8ms  words=22,069,248
[E02  1147/1548 G   2694|CLM] train=4.5420  mask=17.8%  norm=0.701  lr=2.82e-04  dt=  36.9ms  words=22,077,440
[E02  1148/1548 G   2695|CLM] train=2.7898  mask=17.8%  norm=0.627  lr=2.82e-04  dt=  37.1ms  words=22,085,632
[E02  1149/1548 G   2696|CLM] train=4.5324  mask=17.8%  norm=0.804  lr=2.82e-04  dt=  36.9ms  words=22,093,824
[E02  1150/1548 G   2697|CLM] train=2.7259  mask=17.8%  norm=0.705  lr=2.82e-04  dt=  36.9ms  words=22,102,016
[E02  1151/1548 G   2698|CLM] train=4.3120  mask=17.8%  norm=0.617  lr=2.82e-04  dt=  37.0ms  words=22,110,208
[E02  1152/1548 G   2699|CLM] train=2.8026  mask=17.8%  norm=0.678  lr=2.82e-04  dt=  37.0ms  words=22,118,400
[E02  1153/1548 G   2700|CLM] train=2.8573  mask=17.8%  norm=0.805  lr=2.81e-04  dt=  37.0ms  words=22,126,592
[E02  1154/1548 G   2701|CLM] train=4.3904  mask=17.8%  norm=0.596  lr=2.81e-04  dt=  37.1ms  words=22,134,784
[E02  1155/1548 G   2702|CLM] train=4.6621  mask=17.8%  norm=0.536  lr=2.81e-04  dt=  37.2ms  words=22,142,976
[E02  1156/1548 G   2703|CLM] train=4.1204  mask=17.8%  norm=0.693  lr=2.81e-04  dt=  37.0ms  words=22,151,168
[E02  1157/1548 G   2704|CLM] train=4.4068  mask=17.8%  norm=0.629  lr=2.81e-04  dt=  36.9ms  words=22,159,360
[E02  1158/1548 G   2705|CLM] train=5.1645  mask=17.8%  norm=0.761  lr=2.81e-04  dt=  37.0ms  words=22,167,552
[E02  1159/1548 G   2706|CLM] train=6.3265  mask=17.8%  norm=1.041  lr=2.81e-04  dt=  37.0ms  words=22,175,744
[E02  1160/1548 G   2707|CLM] train=4.1376  mask=17.8%  norm=0.641  lr=2.81e-04  dt=  36.9ms  words=22,183,936
[E02  1161/1548 G   2708|CLM] train=4.2735  mask=17.8%  norm=0.696  lr=2.81e-04  dt=  37.1ms  words=22,192,128
[E02  1162/1548 G   2709|CLM] train=4.3019  mask=17.8%  norm=0.861  lr=2.81e-04  dt=  36.9ms  words=22,200,320
[E02  1163/1548 G   2710|CLM] train=4.2513  mask=17.8%  norm=0.606  lr=2.81e-04  dt=  37.1ms  words=22,208,512
[E02  1164/1548 G   2711|CLM] train=4.9683  mask=17.8%  norm=0.713  lr=2.81e-04  dt=  36.8ms  words=22,216,704
[E02  1165/1548 G   2712|CLM] train=4.3735  mask=17.8%  norm=0.699  lr=2.81e-04  dt=  36.9ms  words=22,224,896
[E02  1166/1548 G   2713|CLM] train=6.1122  mask=17.8%  norm=1.677  lr=2.81e-04  dt=  36.9ms  words=22,233,088
[E02  1167/1548 G   2714|CLM] train=2.6597  mask=17.8%  norm=0.812  lr=2.81e-04  dt=  36.9ms  words=22,241,280
[E02  1168/1548 G   2715|CLM] train=2.9621  mask=17.8%  norm=1.123  lr=2.81e-04  dt=  36.9ms  words=22,249,472
[E02  1169/1548 G   2716|CLM] train=2.7110  mask=17.8%  norm=0.677  lr=2.81e-04  dt=  36.9ms  words=22,257,664
[E02  1170/1548 G   2717|CLM] train=3.0299  mask=17.8%  norm=0.663  lr=2.81e-04  dt=  37.2ms  words=22,265,856
[E02  1171/1548 G   2718|CLM] train=5.2605  mask=17.8%  norm=0.982  lr=2.81e-04  dt=  37.2ms  words=22,274,048
[E02  1172/1548 G   2719|CLM] train=2.5257  mask=17.8%  norm=0.635  lr=2.81e-04  dt=  37.0ms  words=22,282,240
[E02  1173/1548 G   2720|CLM] train=4.8483  mask=17.8%  norm=0.785  lr=2.81e-04  dt=  36.9ms  words=22,290,432
[E02  1174/1548 G   2721|CLM] train=3.0349  mask=17.8%  norm=0.882  lr=2.81e-04  dt=  38.1ms  words=22,298,624
[E02  1175/1548 G   2722|CLM] train=2.4961  mask=17.8%  norm=0.742  lr=2.81e-04  dt=  37.0ms  words=22,306,816
[E02  1176/1548 G   2723|CLM] train=2.8130  mask=17.8%  norm=0.798  lr=2.81e-04  dt=  37.4ms  words=22,315,008
[E02  1177/1548 G   2724|CLM] train=5.1364  mask=17.8%  norm=0.837  lr=2.81e-04  dt=  37.0ms  words=22,323,200
[E02  1178/1548 G   2725|CLM] train=2.8181  mask=17.8%  norm=0.674  lr=2.81e-04  dt=  36.9ms  words=22,331,392
[E02  1179/1548 G   2726|CLM] train=4.7748  mask=17.8%  norm=0.704  lr=2.81e-04  dt=  37.0ms  words=22,339,584
[E02  1180/1548 G   2727|CLM] train=2.9362  mask=17.8%  norm=0.611  lr=2.81e-04  dt=  37.1ms  words=22,347,776
[E02  1181/1548 G   2728|CLM] train=4.5308  mask=17.8%  norm=0.873  lr=2.81e-04  dt=  36.8ms  words=22,355,968
[E02  1182/1548 G   2729|CLM] train=4.3020  mask=17.8%  norm=1.108  lr=2.81e-04  dt=  36.9ms  words=22,364,160
[E02  1183/1548 G   2730|CLM] train=4.7724  mask=17.8%  norm=0.745  lr=2.81e-04  dt=  36.9ms  words=22,372,352
[E02  1184/1548 G   2731|CLM] train=2.7321  mask=17.8%  norm=0.761  lr=2.81e-04  dt=  37.1ms  words=22,380,544
[E02  1185/1548 G   2732|CLM] train=2.7948  mask=17.8%  norm=1.094  lr=2.81e-04  dt=  36.9ms  words=22,388,736
[E02  1186/1548 G   2733|CLM] train=3.2441  mask=17.8%  norm=0.769  lr=2.81e-04  dt=  36.8ms  words=22,396,928
[E02  1187/1548 G   2734|CLM] train=4.5245  mask=17.8%  norm=1.345  lr=2.81e-04  dt=  36.9ms  words=22,405,120
[E02  1188/1548 G   2735|CLM] train=4.3684  mask=17.8%  norm=0.671  lr=2.81e-04  dt=  37.0ms  words=22,413,312
[E02  1189/1548 G   2736|CLM] train=2.9742  mask=17.8%  norm=0.626  lr=2.81e-04  dt=  36.8ms  words=22,421,504
[E02  1190/1548 G   2737|CLM] train=2.8868  mask=17.8%  norm=0.830  lr=2.81e-04  dt=  36.9ms  words=22,429,696
[E02  1191/1548 G   2738|CLM] train=4.5041  mask=17.8%  norm=0.698  lr=2.81e-04  dt=  37.0ms  words=22,437,888
[E02  1192/1548 G   2739|CLM] train=5.5776  mask=17.8%  norm=1.157  lr=2.81e-04  dt=  37.0ms  words=22,446,080
[E02  1193/1548 G   2740|CLM] train=5.1365  mask=17.8%  norm=0.934  lr=2.81e-04  dt=  36.9ms  words=22,454,272
[E02  1194/1548 G   2741|CLM] train=5.0642  mask=17.8%  norm=0.744  lr=2.81e-04  dt=  36.8ms  words=22,462,464
[E02  1195/1548 G   2742|CLM] train=2.9204  mask=17.8%  norm=0.751  lr=2.81e-04  dt=  37.0ms  words=22,470,656
[E02  1196/1548 G   2743|CLM] train=4.7922  mask=17.8%  norm=0.783  lr=2.81e-04  dt=  36.9ms  words=22,478,848
[E02  1197/1548 G   2744|CLM] train=2.6422  mask=17.8%  norm=0.914  lr=2.81e-04  dt=  36.9ms  words=22,487,040
[E02  1198/1548 G   2745|CLM] train=5.5105  mask=17.8%  norm=5.690  lr=2.81e-04  dt=  36.9ms  words=22,495,232
[E02  1199/1548 G   2746|CLM] train=4.4948  mask=17.8%  norm=0.711  lr=2.81e-04  dt=  36.9ms  words=22,503,424
[E02  1200/1548 G   2747|CLM] train=2.7458  mask=17.8%  norm=0.633  lr=2.81e-04  dt=  37.0ms  words=22,511,616
[E02  1201/1548 G   2748|CLM] train=3.1381  mask=17.8%  norm=0.651  lr=2.81e-04  dt=  37.0ms  words=22,519,808
[E02  1202/1548 G   2749|CLM] train=6.0394  mask=17.8%  norm=1.505  lr=2.81e-04  dt=  36.9ms  words=22,528,000
[E02  1203/1548 G   2750|CLM] train=4.9520  mask=17.8%  norm=1.132  lr=2.81e-04  dt=  37.0ms  words=22,536,192
[E02  1204/1548 G   2751|CLM] train=2.8092  mask=17.8%  norm=0.601  lr=2.81e-04  dt=  36.9ms  words=22,544,384
[E02  1205/1548 G   2752|CLM] train=4.7406  mask=17.8%  norm=1.186  lr=2.80e-04  dt=  36.7ms  words=22,552,576
[E02  1206/1548 G   2753|CLM] train=4.6723  mask=17.8%  norm=0.681  lr=2.80e-04  dt=  37.0ms  words=22,560,768
[E02  1207/1548 G   2754|CLM] train=4.1113  mask=17.8%  norm=0.568  lr=2.80e-04  dt=  36.9ms  words=22,568,960
[E02  1208/1548 G   2755|CLM] train=4.5186  mask=17.8%  norm=0.820  lr=2.80e-04  dt=  37.0ms  words=22,577,152
[E02  1209/1548 G   2756|CLM] train=2.7482  mask=17.8%  norm=0.819  lr=2.80e-04  dt=  36.9ms  words=22,585,344
[E02  1210/1548 G   2757|CLM] train=5.2391  mask=17.8%  norm=0.848  lr=2.80e-04  dt=  36.8ms  words=22,593,536
[E02  1211/1548 G   2758|CLM] train=4.3927  mask=17.8%  norm=0.776  lr=2.80e-04  dt=  37.0ms  words=22,601,728
[E02  1212/1548 G   2759|CLM] train=2.8422  mask=17.8%  norm=0.694  lr=2.80e-04  dt=  36.9ms  words=22,609,920
[E02  1213/1548 G   2760|CLM] train=4.6365  mask=17.8%  norm=0.754  lr=2.80e-04  dt=  37.4ms  words=22,618,112
[E02  1214/1548 G   2761|CLM] train=2.6188  mask=17.8%  norm=0.674  lr=2.80e-04  dt=  36.9ms  words=22,626,304
[E02  1215/1548 G   2762|CLM] train=4.7036  mask=17.8%  norm=0.683  lr=2.80e-04  dt=  36.9ms  words=22,634,496
[E02  1216/1548 G   2763|CLM] train=3.2248  mask=17.8%  norm=0.564  lr=2.80e-04  dt=  37.0ms  words=22,642,688
[E02  1217/1548 G   2764|CLM] train=2.7403  mask=17.8%  norm=1.260  lr=2.80e-04  dt=  36.9ms  words=22,650,880
[E02  1218/1548 G   2765|CLM] train=4.1701  mask=17.8%  norm=0.990  lr=2.80e-04  dt=  37.2ms  words=22,659,072
[E02  1219/1548 G   2766|CLM] train=2.8537  mask=17.8%  norm=0.984  lr=2.80e-04  dt=  37.3ms  words=22,667,264
[E02  1220/1548 G   2767|CLM] train=2.8063  mask=17.8%  norm=0.742  lr=2.80e-04  dt=  36.9ms  words=22,675,456
[E02  1221/1548 G   2768|CLM] train=4.3468  mask=17.8%  norm=0.749  lr=2.80e-04  dt=  36.9ms  words=22,683,648
[E02  1222/1548 G   2769|CLM] train=5.1432  mask=17.8%  norm=1.010  lr=2.80e-04  dt=  37.0ms  words=22,691,840
[E02  1223/1548 G   2770|CLM] train=3.0396  mask=17.8%  norm=0.769  lr=2.80e-04  dt=  38.8ms  words=22,700,032
[E02  1224/1548 G   2771|CLM] train=5.1812  mask=17.8%  norm=0.910  lr=2.80e-04  dt=  39.8ms  words=22,708,224
[E02  1225/1548 G   2772|CLM] train=5.1325  mask=17.8%  norm=0.687  lr=2.80e-04  dt=  40.8ms  words=22,716,416
[E02  1226/1548 G   2773|CLM] train=2.2807  mask=17.8%  norm=1.194  lr=2.80e-04  dt=  41.0ms  words=22,724,608
[E02  1227/1548 G   2774|CLM] train=2.8416  mask=17.8%  norm=0.777  lr=2.80e-04  dt=  37.3ms  words=22,732,800
[E02  1228/1548 G   2775|CLM] train=4.9169  mask=17.8%  norm=0.724  lr=2.80e-04  dt=  37.5ms  words=22,740,992
[E02  1229/1548 G   2776|CLM] train=3.9731  mask=17.8%  norm=0.760  lr=2.80e-04  dt=  46.7ms  words=22,749,184
[E02  1230/1548 G   2777|CLM] train=3.9613  mask=17.8%  norm=0.831  lr=2.80e-04  dt=  37.6ms  words=22,757,376
[E02  1231/1548 G   2778|CLM] train=4.7737  mask=17.8%  norm=0.904  lr=2.80e-04  dt=  39.0ms  words=22,765,568
[E02  1232/1548 G   2779|CLM] train=5.0093  mask=17.8%  norm=0.768  lr=2.80e-04  dt=  43.1ms  words=22,773,760
[E02  1233/1548 G   2780|CLM] train=3.9685  mask=17.8%  norm=0.750  lr=2.80e-04  dt=  39.2ms  words=22,781,952
[E02  1234/1548 G   2781|CLM] train=4.6879  mask=17.8%  norm=0.765  lr=2.80e-04  dt=  40.6ms  words=22,790,144
[E02  1235/1548 G   2782|CLM] train=5.0760  mask=17.8%  norm=1.091  lr=2.80e-04  dt=  37.5ms  words=22,798,336
[E02  1236/1548 G   2783|CLM] train=4.6591  mask=17.8%  norm=0.719  lr=2.80e-04  dt=  37.3ms  words=22,806,528
[E02  1237/1548 G   2784|CLM] train=5.2359  mask=17.8%  norm=0.881  lr=2.80e-04  dt=  37.4ms  words=22,814,720
[E02  1238/1548 G   2785|CLM] train=2.9715  mask=17.8%  norm=0.641  lr=2.80e-04  dt=  38.6ms  words=22,822,912
[E02  1239/1548 G   2786|CLM] train=2.8461  mask=17.8%  norm=0.746  lr=2.80e-04  dt=  46.6ms  words=22,831,104
[E02  1240/1548 G   2787|CLM] train=5.0141  mask=17.7%  norm=0.891  lr=2.80e-04  dt=  47.2ms  words=22,839,296
[E02  1241/1548 G   2788|CLM] train=2.5895  mask=17.7%  norm=0.746  lr=2.80e-04  dt=  45.1ms  words=22,847,488
[E02  1242/1548 G   2789|CLM] train=5.1278  mask=17.7%  norm=1.192  lr=2.80e-04  dt=  38.8ms  words=22,855,680
[E02  1243/1548 G   2790|CLM] train=3.0550  mask=17.7%  norm=0.673  lr=2.80e-04  dt=  39.0ms  words=22,863,872
[E02  1244/1548 G   2791|CLM] train=5.6273  mask=17.7%  norm=0.952  lr=2.80e-04  dt=  38.3ms  words=22,872,064
[E02  1245/1548 G   2792|CLM] train=4.6130  mask=17.7%  norm=0.882  lr=2.80e-04  dt=  38.6ms  words=22,880,256
[E02  1246/1548 G   2793|CLM] train=2.5997  mask=17.7%  norm=0.621  lr=2.80e-04  dt=  38.6ms  words=22,888,448
[E02  1247/1548 G   2794|CLM] train=4.8577  mask=17.7%  norm=0.994  lr=2.80e-04  dt=  38.8ms  words=22,896,640
[E02  1248/1548 G   2795|CLM] train=3.2143  mask=17.7%  norm=0.617  lr=2.80e-04  dt=  38.8ms  words=22,904,832
[E02  1249/1548 G   2796|CLM] train=5.4070  mask=17.7%  norm=1.371  lr=2.80e-04  dt=  39.2ms  words=22,913,024
[E02  1250/1548 G   2797|CLM] train=5.8867  mask=17.7%  norm=1.149  lr=2.80e-04  dt=  38.9ms  words=22,921,216
[E02  1251/1548 G   2798|CLM] train=2.7251  mask=17.7%  norm=0.772  lr=2.80e-04  dt=  38.7ms  words=22,929,408
[E02  1252/1548 G   2799|CLM] train=3.4666  mask=17.7%  norm=0.665  lr=2.80e-04  dt=  39.3ms  words=22,937,600
[E02  1253/1548 G   2800|CLM] train=4.8663  mask=17.7%  norm=0.710  lr=2.80e-04  dt=  39.6ms  words=22,945,792
[E02  1254/1548 G   2801|CLM] train=4.8128  mask=17.7%  norm=0.763  lr=2.80e-04  dt=  37.8ms  words=22,953,984
[E02  1255/1548 G   2802|CLM] train=4.5595  mask=17.7%  norm=1.224  lr=2.80e-04  dt=  40.6ms  words=22,962,176
[E02  1256/1548 G   2803|CLM] train=4.2002  mask=17.7%  norm=0.716  lr=2.79e-04  dt=  38.5ms  words=22,970,368
[E02  1257/1548 G   2804|CLM] train=2.6801  mask=17.7%  norm=0.923  lr=2.79e-04  dt=  39.1ms  words=22,978,560
[E02  1258/1548 G   2805|CLM] train=3.4332  mask=17.7%  norm=0.922  lr=2.79e-04  dt=  37.6ms  words=22,986,752
[E02  1259/1548 G   2806|CLM] train=5.0584  mask=17.7%  norm=0.703  lr=2.79e-04  dt=  38.7ms  words=22,994,944
[E02  1260/1548 G   2807|CLM] train=4.0911  mask=17.7%  norm=0.824  lr=2.79e-04  dt=  37.9ms  words=23,003,136
[E02  1261/1548 G   2808|CLM] train=4.5277  mask=17.7%  norm=0.800  lr=2.79e-04  dt=  38.2ms  words=23,011,328
[E02  1262/1548 G   2809|CLM] train=4.5139  mask=17.7%  norm=0.634  lr=2.79e-04  dt=  37.8ms  words=23,019,520
[E02  1263/1548 G   2810|CLM] train=4.6684  mask=17.7%  norm=0.750  lr=2.79e-04  dt=  38.8ms  words=23,027,712
[E02  1264/1548 G   2811|CLM] train=5.2166  mask=17.7%  norm=1.010  lr=2.79e-04  dt=  38.3ms  words=23,035,904
[E02  1265/1548 G   2812|CLM] train=2.8698  mask=17.7%  norm=0.900  lr=2.79e-04  dt=  38.1ms  words=23,044,096
[E02  1266/1548 G   2813|CLM] train=4.6939  mask=17.7%  norm=0.884  lr=2.79e-04  dt=  39.0ms  words=23,052,288
[E02  1267/1548 G   2814|CLM] train=4.6547  mask=17.7%  norm=0.727  lr=2.79e-04  dt=  38.5ms  words=23,060,480
[E02  1268/1548 G   2815|CLM] train=5.2444  mask=17.7%  norm=0.765  lr=2.79e-04  dt=  39.2ms  words=23,068,672
[E02  1269/1548 G   2816|CLM] train=2.6897  mask=17.7%  norm=1.177  lr=2.79e-04  dt=  37.5ms  words=23,076,864
[E02  1270/1548 G   2817|CLM] train=5.0988  mask=17.7%  norm=0.801  lr=2.79e-04  dt=  38.8ms  words=23,085,056
[E02  1271/1548 G   2818|CLM] train=5.3530  mask=17.7%  norm=0.872  lr=2.79e-04  dt=  37.4ms  words=23,093,248
[E02  1272/1548 G   2819|CLM] train=4.9513  mask=17.7%  norm=0.660  lr=2.79e-04  dt=  39.5ms  words=23,101,440
[E02  1273/1548 G   2820|CLM] train=4.3335  mask=17.7%  norm=0.754  lr=2.79e-04  dt=  37.3ms  words=23,109,632
[E02  1274/1548 G   2821|CLM] train=4.5261  mask=17.7%  norm=0.577  lr=2.79e-04  dt=  38.6ms  words=23,117,824
[E02  1275/1548 G   2822|CLM] train=4.2997  mask=17.7%  norm=0.803  lr=2.79e-04  dt=  37.8ms  words=23,126,016
[E02  1276/1548 G   2823|CLM] train=2.1631  mask=17.7%  norm=1.168  lr=2.79e-04  dt=  38.8ms  words=23,134,208
[E02  1277/1548 G   2824|CLM] train=2.6478  mask=17.7%  norm=0.968  lr=2.79e-04  dt=  38.2ms  words=23,142,400
[E02  1278/1548 G   2825|CLM] train=3.9098  mask=17.7%  norm=0.669  lr=2.79e-04  dt=  37.6ms  words=23,150,592
[E02  1279/1548 G   2826|CLM] train=2.8903  mask=17.7%  norm=0.978  lr=2.79e-04  dt=  37.7ms  words=23,158,784
[E02  1280/1548 G   2827|CLM] train=2.6534  mask=17.7%  norm=0.683  lr=2.79e-04  dt=  39.0ms  words=23,166,976
[E02  1281/1548 G   2828|CLM] train=4.3487  mask=17.7%  norm=0.842  lr=2.79e-04  dt=  39.7ms  words=23,175,168
[E02  1282/1548 G   2829|CLM] train=5.4013  mask=17.7%  norm=1.909  lr=2.79e-04  dt=  37.4ms  words=23,183,360
[E02  1283/1548 G   2830|CLM] train=5.7142  mask=17.7%  norm=1.729  lr=2.79e-04  dt=  39.3ms  words=23,191,552
[E02  1284/1548 G   2831|CLM] train=3.2817  mask=17.7%  norm=1.348  lr=2.79e-04  dt=  37.5ms  words=23,199,744
[E02  1285/1548 G   2832|CLM] train=2.4825  mask=17.7%  norm=0.712  lr=2.79e-04  dt=  38.6ms  words=23,207,936
[E02  1286/1548 G   2833|CLM] train=5.0859  mask=17.7%  norm=0.760  lr=2.79e-04  dt=  37.4ms  words=23,216,128
[E02  1287/1548 G   2834|CLM] train=5.0459  mask=17.7%  norm=0.845  lr=2.79e-04  dt=  38.6ms  words=23,224,320
[E02  1288/1548 G   2835|CLM] train=4.3529  mask=17.7%  norm=0.742  lr=2.79e-04  dt=  38.6ms  words=23,232,512
[E02  1289/1548 G   2836|CLM] train=2.8643  mask=17.7%  norm=0.948  lr=2.79e-04  dt=  39.2ms  words=23,240,704
[E02  1290/1548 G   2837|CLM] train=5.2741  mask=17.7%  norm=0.779  lr=2.79e-04  dt=  37.2ms  words=23,248,896
[E02  1291/1548 G   2838|CLM] train=4.3851  mask=17.7%  norm=0.975  lr=2.79e-04  dt=  38.1ms  words=23,257,088
[E02  1292/1548 G   2839|CLM] train=4.4389  mask=17.7%  norm=0.794  lr=2.79e-04  dt=  37.3ms  words=23,265,280
[E02  1293/1548 G   2840|CLM] train=6.1997  mask=17.7%  norm=0.994  lr=2.79e-04  dt=  37.3ms  words=23,273,472
[E02  1294/1548 G   2841|CLM] train=2.9856  mask=17.7%  norm=0.785  lr=2.79e-04  dt=  37.5ms  words=23,281,664
[E02  1295/1548 G   2842|CLM] train=4.5808  mask=17.7%  norm=0.656  lr=2.79e-04  dt=  37.5ms  words=23,289,856
[E02  1296/1548 G   2843|CLM] train=2.2598  mask=17.7%  norm=0.931  lr=2.79e-04  dt=  37.7ms  words=23,298,048
[E02  1297/1548 G   2844|CLM] train=4.8852  mask=17.7%  norm=1.084  lr=2.79e-04  dt=  37.3ms  words=23,306,240
[E02  1298/1548 G   2845|CLM] train=2.5633  mask=17.7%  norm=0.792  lr=2.79e-04  dt=  37.3ms  words=23,314,432
[E02  1299/1548 G   2846|CLM] train=2.4894  mask=17.7%  norm=0.631  lr=2.79e-04  dt=  37.2ms  words=23,322,624
[E02  1300/1548 G   2847|CLM] train=4.4226  mask=17.7%  norm=0.848  lr=2.79e-04  dt=  37.3ms  words=23,330,816
[E02  1301/1548 G   2848|CLM] train=4.8775  mask=17.7%  norm=0.742  lr=2.79e-04  dt=  37.2ms  words=23,339,008
[E02  1302/1548 G   2849|CLM] train=2.7413  mask=17.7%  norm=1.249  lr=2.79e-04  dt=  37.2ms  words=23,347,200
[E02  1303/1548 G   2850|CLM] train=4.3585  mask=17.7%  norm=1.011  lr=2.79e-04  dt=  37.2ms  words=23,355,392
[E02  1304/1548 G   2851|CLM] train=4.4531  mask=17.7%  norm=0.715  lr=2.79e-04  dt=  37.2ms  words=23,363,584
[E02  1305/1548 G   2852|CLM] train=4.8312  mask=17.7%  norm=0.838  lr=2.78e-04  dt=  37.3ms  words=23,371,776
[E02  1306/1548 G   2853|CLM] train=2.5507  mask=17.7%  norm=0.913  lr=2.78e-04  dt=  37.3ms  words=23,379,968
[E02  1307/1548 G   2854|CLM] train=4.7024  mask=17.7%  norm=0.588  lr=2.78e-04  dt=  37.4ms  words=23,388,160
[E02  1308/1548 G   2855|CLM] train=4.8921  mask=17.7%  norm=0.741  lr=2.78e-04  dt=  37.5ms  words=23,396,352
[E02  1309/1548 G   2856|CLM] train=2.6517  mask=17.7%  norm=0.890  lr=2.78e-04  dt=  37.3ms  words=23,404,544
[E02  1310/1548 G   2857|CLM] train=2.7708  mask=17.7%  norm=0.827  lr=2.78e-04  dt=  37.4ms  words=23,412,736
[E02  1311/1548 G   2858|CLM] train=4.8755  mask=17.7%  norm=0.763  lr=2.78e-04  dt=  37.4ms  words=23,420,928
[E02  1312/1548 G   2859|CLM] train=5.5060  mask=17.7%  norm=0.932  lr=2.78e-04  dt=  37.3ms  words=23,429,120
[E02  1313/1548 G   2860|CLM] train=5.1387  mask=17.7%  norm=1.038  lr=2.78e-04  dt=  37.3ms  words=23,437,312
[E02  1314/1548 G   2861|CLM] train=2.8569  mask=17.7%  norm=1.184  lr=2.78e-04  dt=  37.1ms  words=23,445,504
[E02  1315/1548 G   2862|CLM] train=4.0902  mask=17.7%  norm=0.608  lr=2.78e-04  dt=  37.3ms  words=23,453,696
[E02  1316/1548 G   2863|CLM] train=4.8107  mask=17.7%  norm=0.715  lr=2.78e-04  dt=  37.3ms  words=23,461,888
[E02  1317/1548 G   2864|CLM] train=2.8126  mask=17.7%  norm=1.069  lr=2.78e-04  dt=  37.1ms  words=23,470,080
[E02  1318/1548 G   2865|CLM] train=5.2630  mask=17.7%  norm=0.879  lr=2.78e-04  dt=  37.1ms  words=23,478,272
[E02  1319/1548 G   2866|CLM] train=5.0855  mask=17.7%  norm=0.759  lr=2.78e-04  dt=  37.5ms  words=23,486,464
[E02  1320/1548 G   2867|CLM] train=4.8242  mask=17.7%  norm=0.658  lr=2.78e-04  dt=  37.2ms  words=23,494,656
[E02  1321/1548 G   2868|CLM] train=2.8592  mask=17.7%  norm=1.225  lr=2.78e-04  dt=  37.5ms  words=23,502,848
[E02  1322/1548 G   2869|CLM] train=2.8971  mask=17.7%  norm=1.113  lr=2.78e-04  dt=  37.4ms  words=23,511,040
[E02  1323/1548 G   2870|CLM] train=6.0165  mask=17.7%  norm=1.251  lr=2.78e-04  dt=  37.3ms  words=23,519,232
[E02  1324/1548 G   2871|CLM] train=3.7412  mask=17.7%  norm=0.698  lr=2.78e-04  dt=  37.4ms  words=23,527,424
[E02  1325/1548 G   2872|CLM] train=3.4403  mask=17.7%  norm=0.748  lr=2.78e-04  dt=  37.3ms  words=23,535,616
[E02  1326/1548 G   2873|CLM] train=2.7812  mask=17.7%  norm=0.744  lr=2.78e-04  dt=  37.3ms  words=23,543,808
[E02  1327/1548 G   2874|CLM] train=4.9009  mask=17.7%  norm=0.885  lr=2.78e-04  dt=  37.1ms  words=23,552,000
[E02  1328/1548 G   2875|CLM] train=2.6601  mask=17.7%  norm=0.762  lr=2.78e-04  dt=  37.2ms  words=23,560,192
[E02  1329/1548 G   2876|CLM] train=4.7785  mask=17.7%  norm=0.871  lr=2.78e-04  dt=  37.3ms  words=23,568,384
[E02  1330/1548 G   2877|CLM] train=4.5925  mask=17.7%  norm=0.903  lr=2.78e-04  dt=  37.2ms  words=23,576,576
[E02  1331/1548 G   2878|CLM] train=5.0106  mask=17.7%  norm=0.782  lr=2.78e-04  dt=  37.3ms  words=23,584,768
[E02  1332/1548 G   2879|CLM] train=3.1349  mask=17.7%  norm=0.637  lr=2.78e-04  dt=  37.3ms  words=23,592,960
[E02  1333/1548 G   2880|CLM] train=4.4130  mask=17.7%  norm=0.717  lr=2.78e-04  dt=  37.2ms  words=23,601,152
[E02  1334/1548 G   2881|CLM] train=5.0868  mask=17.7%  norm=0.811  lr=2.78e-04  dt=  37.6ms  words=23,609,344
[E02  1335/1548 G   2882|CLM] train=5.2526  mask=17.7%  norm=0.870  lr=2.78e-04  dt=  37.3ms  words=23,617,536
[E02  1336/1548 G   2883|CLM] train=2.7072  mask=17.7%  norm=1.292  lr=2.78e-04  dt=  37.5ms  words=23,625,728
[E02  1337/1548 G   2884|CLM] train=5.0624  mask=17.7%  norm=0.786  lr=2.78e-04  dt=  37.6ms  words=23,633,920
[E02  1338/1548 G   2885|CLM] train=3.8383  mask=17.7%  norm=0.733  lr=2.78e-04  dt=  37.3ms  words=23,642,112
[E02  1339/1548 G   2886|CLM] train=3.3148  mask=17.7%  norm=0.740  lr=2.78e-04  dt=  37.4ms  words=23,650,304
[E02  1340/1548 G   2887|CLM] train=4.3878  mask=17.7%  norm=0.797  lr=2.78e-04  dt=  37.3ms  words=23,658,496
[E02  1341/1548 G   2888|CLM] train=4.4439  mask=17.7%  norm=0.844  lr=2.78e-04  dt=  37.2ms  words=23,666,688
[E02  1342/1548 G   2889|CLM] train=4.4232  mask=17.7%  norm=0.948  lr=2.78e-04  dt=  37.2ms  words=23,674,880
[E02  1343/1548 G   2890|CLM] train=3.0538  mask=17.7%  norm=0.609  lr=2.78e-04  dt=  37.3ms  words=23,683,072
[E02  1344/1548 G   2891|CLM] train=3.0406  mask=17.7%  norm=0.587  lr=2.78e-04  dt=  37.3ms  words=23,691,264
[E02  1345/1548 G   2892|CLM] train=4.7569  mask=17.7%  norm=1.062  lr=2.78e-04  dt=  37.1ms  words=23,699,456
[E02  1346/1548 G   2893|CLM] train=4.6597  mask=17.7%  norm=0.725  lr=2.78e-04  dt=  37.5ms  words=23,707,648
[E02  1347/1548 G   2894|CLM] train=2.8015  mask=17.7%  norm=0.782  lr=2.78e-04  dt=  37.7ms  words=23,715,840
[E02  1348/1548 G   2895|CLM] train=4.6432  mask=17.7%  norm=0.729  lr=2.78e-04  dt=  48.2ms  words=23,724,032
[E02  1349/1548 G   2896|CLM] train=4.3512  mask=17.7%  norm=0.667  lr=2.78e-04  dt=  45.4ms  words=23,732,224
[E02  1350/1548 G   2897|CLM] train=2.2419  mask=17.7%  norm=0.842  lr=2.78e-04  dt=  45.2ms  words=23,740,416
[E02  1351/1548 G   2898|CLM] train=4.0742  mask=17.7%  norm=0.723  lr=2.78e-04  dt=  37.3ms  words=23,748,608
[E02  1352/1548 G   2899|CLM] train=2.8812  mask=17.7%  norm=0.720  lr=2.78e-04  dt=  44.9ms  words=23,756,800
[E02  1353/1548 G   2900|CLM] train=2.9592  mask=17.7%  norm=0.722  lr=2.78e-04  dt=  41.9ms  words=23,764,992
[E02  1354/1548 G   2901|CLM] train=4.3907  mask=17.7%  norm=0.763  lr=2.77e-04  dt=  38.6ms  words=23,773,184
[E02  1355/1548 G   2902|CLM] train=2.4957  mask=17.7%  norm=0.928  lr=2.77e-04  dt=  42.1ms  words=23,781,376
[E02  1356/1548 G   2903|CLM] train=4.8791  mask=17.7%  norm=0.721  lr=2.77e-04  dt=  42.2ms  words=23,789,568
[E02  1357/1548 G   2904|CLM] train=4.6216  mask=17.7%  norm=1.108  lr=2.77e-04  dt=  39.3ms  words=23,797,760
[E02  1358/1548 G   2905|CLM] train=4.6941  mask=17.7%  norm=1.020  lr=2.77e-04  dt=  37.3ms  words=23,805,952
[E02  1359/1548 G   2906|CLM] train=2.6406  mask=17.7%  norm=0.701  lr=2.77e-04  dt=  40.7ms  words=23,814,144
[E02  1360/1548 G   2907|CLM] train=4.5570  mask=17.7%  norm=0.675  lr=2.77e-04  dt=  46.4ms  words=23,822,336
[E02  1361/1548 G   2908|CLM] train=4.9822  mask=17.7%  norm=0.637  lr=2.77e-04  dt=  36.9ms  words=23,830,528
[E02  1362/1548 G   2909|CLM] train=2.8160  mask=17.7%  norm=0.561  lr=2.77e-04  dt=  41.8ms  words=23,838,720
[E02  1363/1548 G   2910|CLM] train=2.8138  mask=17.7%  norm=0.785  lr=2.77e-04  dt=  43.4ms  words=23,846,912
[E02  1364/1548 G   2911|CLM] train=2.5966  mask=17.6%  norm=0.690  lr=2.77e-04  dt=  37.0ms  words=23,855,104
[E02  1365/1548 G   2912|CLM] train=4.5880  mask=17.6%  norm=0.910  lr=2.77e-04  dt=  45.1ms  words=23,863,296
[E02  1366/1548 G   2913|CLM] train=2.8702  mask=17.6%  norm=0.668  lr=2.77e-04  dt=  37.1ms  words=23,871,488
[E02  1367/1548 G   2914|CLM] train=5.4725  mask=17.6%  norm=0.814  lr=2.77e-04  dt=  40.8ms  words=23,879,680
[E02  1368/1548 G   2915|CLM] train=2.4119  mask=17.6%  norm=0.922  lr=2.77e-04  dt=  36.8ms  words=23,887,872
[E02  1369/1548 G   2916|CLM] train=2.7896  mask=17.6%  norm=0.693  lr=2.77e-04  dt=  38.5ms  words=23,896,064
[E02  1370/1548 G   2917|CLM] train=4.1287  mask=17.6%  norm=0.824  lr=2.77e-04  dt=  37.2ms  words=23,904,256
[E02  1371/1548 G   2918|CLM] train=4.0534  mask=17.6%  norm=0.666  lr=2.77e-04  dt=  43.8ms  words=23,912,448
[E02  1372/1548 G   2919|CLM] train=5.0567  mask=17.6%  norm=0.937  lr=2.77e-04  dt=  37.0ms  words=23,920,640
[E02  1373/1548 G   2920|CLM] train=4.7518  mask=17.6%  norm=0.599  lr=2.77e-04  dt=  37.3ms  words=23,928,832
[E02  1374/1548 G   2921|CLM] train=2.8568  mask=17.6%  norm=0.650  lr=2.77e-04  dt=  37.1ms  words=23,937,024
[E02  1375/1548 G   2922|CLM] train=4.2344  mask=17.6%  norm=0.743  lr=2.77e-04  dt=  38.0ms  words=23,945,216
[E02  1376/1548 G   2923|CLM] train=5.0152  mask=17.6%  norm=0.822  lr=2.77e-04  dt=  39.6ms  words=23,953,408
[E02  1377/1548 G   2924|CLM] train=5.0618  mask=17.6%  norm=1.494  lr=2.77e-04  dt=  42.1ms  words=23,961,600
[E02  1378/1548 G   2925|CLM] train=5.5899  mask=17.6%  norm=0.862  lr=2.77e-04  dt=  41.3ms  words=23,969,792
[E02  1379/1548 G   2926|CLM] train=4.6694  mask=17.6%  norm=0.629  lr=2.77e-04  dt=  43.6ms  words=23,977,984
[E02  1380/1548 G   2927|CLM] train=2.9275  mask=17.6%  norm=0.728  lr=2.77e-04  dt=  40.2ms  words=23,986,176
[E02  1381/1548 G   2928|CLM] train=2.9438  mask=17.6%  norm=0.717  lr=2.77e-04  dt=  42.1ms  words=23,994,368
[E02  1382/1548 G   2929|CLM] train=4.3648  mask=17.6%  norm=0.779  lr=2.77e-04  dt=  39.6ms  words=24,002,560
[E02  1383/1548 G   2930|CLM] train=4.8599  mask=17.6%  norm=0.685  lr=2.77e-04  dt=  37.3ms  words=24,010,752
[E02  1384/1548 G   2931|CLM] train=4.8532  mask=17.6%  norm=1.133  lr=2.77e-04  dt=  37.1ms  words=24,018,944
[E02  1385/1548 G   2932|CLM] train=4.6307  mask=17.6%  norm=0.778  lr=2.77e-04  dt=  39.0ms  words=24,027,136
[E02  1386/1548 G   2933|CLM] train=4.0229  mask=17.6%  norm=0.611  lr=2.77e-04  dt=  38.6ms  words=24,035,328
[E02  1387/1548 G   2934|CLM] train=5.9952  mask=17.6%  norm=1.176  lr=2.77e-04  dt=  43.1ms  words=24,043,520
[E02  1388/1548 G   2935|CLM] train=5.8407  mask=17.6%  norm=1.288  lr=2.77e-04  dt=  40.3ms  words=24,051,712
[E02  1389/1548 G   2936|CLM] train=4.2905  mask=17.6%  norm=1.396  lr=2.77e-04  dt=  40.6ms  words=24,059,904
[E02  1390/1548 G   2937|CLM] train=5.0456  mask=17.6%  norm=0.925  lr=2.77e-04  dt=  38.6ms  words=24,068,096
[E02  1391/1548 G   2938|CLM] train=2.4991  mask=17.6%  norm=0.841  lr=2.77e-04  dt=  38.4ms  words=24,076,288
[E02  1392/1548 G   2939|CLM] train=4.6778  mask=17.6%  norm=0.890  lr=2.77e-04  dt=  37.0ms  words=24,084,480
[E02  1393/1548 G   2940|CLM] train=2.7559  mask=17.6%  norm=0.952  lr=2.77e-04  dt=  37.0ms  words=24,092,672
[E02  1394/1548 G   2941|CLM] train=4.9617  mask=17.6%  norm=0.751  lr=2.77e-04  dt=  36.8ms  words=24,100,864
[E02  1395/1548 G   2942|CLM] train=2.6436  mask=17.6%  norm=0.589  lr=2.77e-04  dt=  36.8ms  words=24,109,056
[E02  1396/1548 G   2943|CLM] train=5.1938  mask=17.6%  norm=0.945  lr=2.77e-04  dt=  36.9ms  words=24,117,248
[E02  1397/1548 G   2944|CLM] train=4.0138  mask=17.6%  norm=0.949  lr=2.77e-04  dt=  37.0ms  words=24,125,440
[E02  1398/1548 G   2945|CLM] train=4.4606  mask=17.6%  norm=0.758  lr=2.77e-04  dt=  37.0ms  words=24,133,632
[E02  1399/1548 G   2946|CLM] train=2.8777  mask=17.6%  norm=0.767  lr=2.77e-04  dt=  36.7ms  words=24,141,824
[E02  1400/1548 G   2947|CLM] train=4.8879  mask=17.6%  norm=0.670  lr=2.77e-04  dt=  36.9ms  words=24,150,016
[E02  1401/1548 G   2948|CLM] train=2.7118  mask=17.6%  norm=1.115  lr=2.76e-04  dt=  36.9ms  words=24,158,208
[E02  1402/1548 G   2949|CLM] train=3.1759  mask=17.6%  norm=0.866  lr=2.76e-04  dt=  36.9ms  words=24,166,400
[E02  1403/1548 G   2950|CLM] train=4.0927  mask=17.6%  norm=0.916  lr=2.76e-04  dt=  36.9ms  words=24,174,592
[E02  1404/1548 G   2951|CLM] train=2.6703  mask=17.6%  norm=0.631  lr=2.76e-04  dt=  36.9ms  words=24,182,784
[E02  1405/1548 G   2952|CLM] train=2.6201  mask=17.6%  norm=0.974  lr=2.76e-04  dt=  36.9ms  words=24,190,976
[E02  1406/1548 G   2953|CLM] train=4.3749  mask=17.6%  norm=0.701  lr=2.76e-04  dt=  37.2ms  words=24,199,168
[E02  1407/1548 G   2954|CLM] train=4.5237  mask=17.6%  norm=0.727  lr=2.76e-04  dt=  36.6ms  words=24,207,360
[E02  1408/1548 G   2955|CLM] train=4.2697  mask=17.6%  norm=0.643  lr=2.76e-04  dt=  36.9ms  words=24,215,552
[E02  1409/1548 G   2956|CLM] train=2.7797  mask=17.6%  norm=0.792  lr=2.76e-04  dt=  37.3ms  words=24,223,744
[E02  1410/1548 G   2957|CLM] train=5.1237  mask=17.6%  norm=0.881  lr=2.76e-04  dt=  37.6ms  words=24,231,936
[E02  1411/1548 G   2958|CLM] train=4.3224  mask=17.6%  norm=0.866  lr=2.76e-04  dt=  37.0ms  words=24,240,128
[E02  1412/1548 G   2959|CLM] train=2.9472  mask=17.6%  norm=0.856  lr=2.76e-04  dt=  37.1ms  words=24,248,320
[E02  1413/1548 G   2960|CLM] train=5.1980  mask=17.6%  norm=0.789  lr=2.76e-04  dt=  36.8ms  words=24,256,512
[E02  1414/1548 G   2961|CLM] train=4.5501  mask=17.6%  norm=0.626  lr=2.76e-04  dt=  36.9ms  words=24,264,704
[E02  1415/1548 G   2962|CLM] train=5.1065  mask=17.6%  norm=0.969  lr=2.76e-04  dt=  36.8ms  words=24,272,896
[E02  1416/1548 G   2963|CLM] train=2.5535  mask=17.6%  norm=0.730  lr=2.76e-04  dt=  37.0ms  words=24,281,088
[E02  1417/1548 G   2964|CLM] train=4.4465  mask=17.6%  norm=0.689  lr=2.76e-04  dt=  36.9ms  words=24,289,280
[E02  1418/1548 G   2965|CLM] train=4.1727  mask=17.6%  norm=0.631  lr=2.76e-04  dt=  36.8ms  words=24,297,472
[E02  1419/1548 G   2966|CLM] train=4.7385  mask=17.6%  norm=0.728  lr=2.76e-04  dt=  36.9ms  words=24,305,664
[E02  1420/1548 G   2967|CLM] train=2.8177  mask=17.6%  norm=0.548  lr=2.76e-04  dt=  36.9ms  words=24,313,856
[E02  1421/1548 G   2968|CLM] train=5.3570  mask=17.6%  norm=0.757  lr=2.76e-04  dt=  36.8ms  words=24,322,048
[E02  1422/1548 G   2969|CLM] train=4.5339  mask=17.6%  norm=0.669  lr=2.76e-04  dt=  36.9ms  words=24,330,240
[E02  1423/1548 G   2970|CLM] train=5.0726  mask=17.6%  norm=0.670  lr=2.76e-04  dt=  37.0ms  words=24,338,432
[E02  1424/1548 G   2971|CLM] train=2.5379  mask=17.6%  norm=0.919  lr=2.76e-04  dt=  37.1ms  words=24,346,624
[E02  1425/1548 G   2972|CLM] train=4.5755  mask=17.6%  norm=0.825  lr=2.76e-04  dt=  36.9ms  words=24,354,816
[E02  1426/1548 G   2973|CLM] train=2.8256  mask=17.6%  norm=1.301  lr=2.76e-04  dt=  37.0ms  words=24,363,008
[E02  1427/1548 G   2974|CLM] train=2.2735  mask=17.6%  norm=0.770  lr=2.76e-04  dt=  36.8ms  words=24,371,200
[E02  1428/1548 G   2975|CLM] train=4.2686  mask=17.6%  norm=0.824  lr=2.76e-04  dt=  36.8ms  words=24,379,392
[E02  1429/1548 G   2976|CLM] train=2.5341  mask=17.6%  norm=0.846  lr=2.76e-04  dt=  36.8ms  words=24,387,584
[E02  1430/1548 G   2977|CLM] train=4.6396  mask=17.6%  norm=0.621  lr=2.76e-04  dt=  36.8ms  words=24,395,776
[E02  1431/1548 G   2978|CLM] train=2.7336  mask=17.6%  norm=0.673  lr=2.76e-04  dt=  36.8ms  words=24,403,968
[E02  1432/1548 G   2979|CLM] train=2.6064  mask=17.6%  norm=0.643  lr=2.76e-04  dt=  36.8ms  words=24,412,160
[E02  1433/1548 G   2980|CLM] train=4.5180  mask=17.6%  norm=0.525  lr=2.76e-04  dt=  36.9ms  words=24,420,352
[E02  1434/1548 G   2981|CLM] train=4.5410  mask=17.6%  norm=0.660  lr=2.76e-04  dt=  36.8ms  words=24,428,544
[E02  1435/1548 G   2982|CLM] train=4.7415  mask=17.6%  norm=0.904  lr=2.76e-04  dt=  36.9ms  words=24,436,736
[E02  1436/1548 G   2983|CLM] train=4.7138  mask=17.6%  norm=0.957  lr=2.76e-04  dt=  36.8ms  words=24,444,928
[E02  1437/1548 G   2984|CLM] train=4.6797  mask=17.6%  norm=1.469  lr=2.76e-04  dt=  36.9ms  words=24,453,120
[E02  1438/1548 G   2985|CLM] train=5.2942  mask=17.6%  norm=0.727  lr=2.76e-04  dt=  36.9ms  words=24,461,312
[E02  1439/1548 G   2986|CLM] train=4.2565  mask=17.6%  norm=0.814  lr=2.76e-04  dt=  36.8ms  words=24,469,504
[E02  1440/1548 G   2987|CLM] train=4.6790  mask=17.6%  norm=0.901  lr=2.76e-04  dt=  36.9ms  words=24,477,696
[E02  1441/1548 G   2988|CLM] train=3.0317  mask=17.6%  norm=0.721  lr=2.76e-04  dt=  37.1ms  words=24,485,888
[E02  1442/1548 G   2989|CLM] train=3.0580  mask=17.6%  norm=0.653  lr=2.76e-04  dt=  36.7ms  words=24,494,080
[E02  1443/1548 G   2990|CLM] train=4.1881  mask=17.6%  norm=0.707  lr=2.76e-04  dt=  36.9ms  words=24,502,272
[E02  1444/1548 G   2991|CLM] train=2.6301  mask=17.6%  norm=0.704  lr=2.76e-04  dt=  36.8ms  words=24,510,464
[E02  1445/1548 G   2992|CLM] train=4.7417  mask=17.6%  norm=0.701  lr=2.76e-04  dt=  37.0ms  words=24,518,656
[E02  1446/1548 G   2993|CLM] train=5.0363  mask=17.6%  norm=1.116  lr=2.76e-04  dt=  36.9ms  words=24,526,848
[E02  1447/1548 G   2994|CLM] train=4.3836  mask=17.6%  norm=0.744  lr=2.76e-04  dt=  36.9ms  words=24,535,040
[E02  1448/1548 G   2995|CLM] train=4.5292  mask=17.6%  norm=0.722  lr=2.75e-04  dt=  36.8ms  words=24,543,232
[E02  1449/1548 G   2996|CLM] train=4.0243  mask=17.6%  norm=0.721  lr=2.75e-04  dt=  37.1ms  words=24,551,424
[E02  1450/1548 G   2997|CLM] train=5.1174  mask=17.6%  norm=0.758  lr=2.75e-04  dt=  37.0ms  words=24,559,616
[E02  1451/1548 G   2998|CLM] train=5.6507  mask=17.6%  norm=1.907  lr=2.75e-04  dt=  37.0ms  words=24,567,808
[E02  1452/1548 G   2999|CLM] train=2.6873  mask=17.6%  norm=0.727  lr=2.75e-04  dt=  37.0ms  words=24,576,000
[E02  1453/1548 G   3000|CLM] train=4.4272  mask=17.6%  norm=0.800  lr=2.75e-04  dt=  36.9ms  words=24,584,192
[E02  1454/1548 G   3001|CLM] train=3.2016  mask=17.6%  norm=0.842  lr=2.75e-04  dt=  36.9ms  words=24,592,384
[E02  1455/1548 G   3002|CLM] train=2.7898  mask=17.6%  norm=0.896  lr=2.75e-04  dt=  36.9ms  words=24,600,576
[E02  1456/1548 G   3003|CLM] train=4.7355  mask=17.6%  norm=0.905  lr=2.75e-04  dt=  36.9ms  words=24,608,768
[E02  1457/1548 G   3004|CLM] train=4.4645  mask=17.6%  norm=0.757  lr=2.75e-04  dt=  37.0ms  words=24,616,960
[E02  1458/1548 G   3005|CLM] train=2.9330  mask=17.6%  norm=2.559  lr=2.75e-04  dt=  36.8ms  words=24,625,152
[E02  1459/1548 G   3006|CLM] train=4.3609  mask=17.6%  norm=0.651  lr=2.75e-04  dt=  36.8ms  words=24,633,344
[E02  1460/1548 G   3007|CLM] train=4.6946  mask=17.6%  norm=0.815  lr=2.75e-04  dt=  37.0ms  words=24,641,536
[E02  1461/1548 G   3008|CLM] train=5.4822  mask=17.6%  norm=1.283  lr=2.75e-04  dt=  36.9ms  words=24,649,728
[E02  1462/1548 G   3009|CLM] train=4.9046  mask=17.6%  norm=0.711  lr=2.75e-04  dt=  37.0ms  words=24,657,920
[E02  1463/1548 G   3010|CLM] train=2.8676  mask=17.6%  norm=0.879  lr=2.75e-04  dt=  36.8ms  words=24,666,112
[E02  1464/1548 G   3011|CLM] train=6.0440  mask=17.6%  norm=1.147  lr=2.75e-04  dt=  36.9ms  words=24,674,304
[E02  1465/1548 G   3012|CLM] train=2.8728  mask=17.6%  norm=0.825  lr=2.75e-04  dt=  37.1ms  words=24,682,496
[E02  1466/1548 G   3013|CLM] train=5.2188  mask=17.6%  norm=1.011  lr=2.75e-04  dt=  36.8ms  words=24,690,688
[E02  1467/1548 G   3014|CLM] train=4.7906  mask=17.6%  norm=0.646  lr=2.75e-04  dt=  37.0ms  words=24,698,880
[E02  1468/1548 G   3015|CLM] train=4.3606  mask=17.6%  norm=0.571  lr=2.75e-04  dt=  36.9ms  words=24,707,072
[E02  1469/1548 G   3016|CLM] train=4.4132  mask=17.6%  norm=0.670  lr=2.75e-04  dt=  36.9ms  words=24,715,264
[E02  1470/1548 G   3017|CLM] train=4.4532  mask=17.6%  norm=0.648  lr=2.75e-04  dt=  36.9ms  words=24,723,456
[E02  1471/1548 G   3018|CLM] train=4.5764  mask=17.6%  norm=0.754  lr=2.75e-04  dt=  36.8ms  words=24,731,648
[E02  1472/1548 G   3019|CLM] train=5.6051  mask=17.6%  norm=1.026  lr=2.75e-04  dt= 446.8ms  words=24,739,840
[E02  1473/1548 G   3020|CLM] train=4.8186  mask=17.6%  norm=0.796  lr=2.75e-04  dt=  40.0ms  words=24,748,032
[E02  1474/1548 G   3021|CLM] train=2.4719  mask=17.6%  norm=0.854  lr=2.75e-04  dt=  38.1ms  words=24,756,224
[E02  1475/1548 G   3022|CLM] train=2.7089  mask=17.6%  norm=0.675  lr=2.75e-04  dt=  37.9ms  words=24,764,416
[E02  1476/1548 G   3023|CLM] train=2.7585  mask=17.6%  norm=0.615  lr=2.75e-04  dt=  39.7ms  words=24,772,608
[E02  1477/1548 G   3024|CLM] train=2.6492  mask=17.6%  norm=0.463  lr=2.75e-04  dt=  39.9ms  words=24,780,800
[E02  1478/1548 G   3025|CLM] train=4.4502  mask=17.6%  norm=1.117  lr=2.75e-04  dt=  37.4ms  words=24,788,992
[E02  1479/1548 G   3026|CLM] train=4.9441  mask=17.6%  norm=0.781  lr=2.75e-04  dt=  37.9ms  words=24,797,184
[E02  1480/1548 G   3027|CLM] train=2.6957  mask=17.6%  norm=0.855  lr=2.75e-04  dt=  37.4ms  words=24,805,376
[E02  1481/1548 G   3028|CLM] train=2.6409  mask=17.6%  norm=1.170  lr=2.75e-04  dt=  36.8ms  words=24,813,568
[E02  1482/1548 G   3029|CLM] train=4.4523  mask=17.6%  norm=0.707  lr=2.75e-04  dt=  37.0ms  words=24,821,760
[E02  1483/1548 G   3030|CLM] train=4.3362  mask=17.6%  norm=0.845  lr=2.75e-04  dt=  36.8ms  words=24,829,952
[E02  1484/1548 G   3031|CLM] train=2.6440  mask=17.6%  norm=1.126  lr=2.75e-04  dt=  36.9ms  words=24,838,144
[E02  1485/1548 G   3032|CLM] train=2.6221  mask=17.6%  norm=0.925  lr=2.75e-04  dt=  36.9ms  words=24,846,336
[E02  1486/1548 G   3033|CLM] train=4.6902  mask=17.6%  norm=0.807  lr=2.75e-04  dt=  37.0ms  words=24,854,528
[E02  1487/1548 G   3034|CLM] train=5.4985  mask=17.6%  norm=0.948  lr=2.75e-04  dt=  36.9ms  words=24,862,720
[E02  1488/1548 G   3035|CLM] train=2.5335  mask=17.5%  norm=0.908  lr=2.75e-04  dt=  36.9ms  words=24,870,912
[E02  1489/1548 G   3036|CLM] train=2.7627  mask=17.5%  norm=1.069  lr=2.75e-04  dt=  36.9ms  words=24,879,104
[E02  1490/1548 G   3037|CLM] train=3.1309  mask=17.5%  norm=1.548  lr=2.75e-04  dt=  37.2ms  words=24,887,296
[E02  1491/1548 G   3038|CLM] train=2.8314  mask=17.5%  norm=0.975  lr=2.75e-04  dt=  36.8ms  words=24,895,488
[E02  1492/1548 G   3039|CLM] train=2.9084  mask=17.5%  norm=0.686  lr=2.75e-04  dt=  37.1ms  words=24,903,680
[E02  1493/1548 G   3040|CLM] train=2.9318  mask=17.5%  norm=0.679  lr=2.75e-04  dt=  36.9ms  words=24,911,872
[E02  1494/1548 G   3041|CLM] train=4.7899  mask=17.5%  norm=0.875  lr=2.74e-04  dt=  36.9ms  words=24,920,064
[E02  1495/1548 G   3042|CLM] train=2.8565  mask=17.5%  norm=0.729  lr=2.74e-04  dt=  36.9ms  words=24,928,256
[E02  1496/1548 G   3043|CLM] train=3.1884  mask=17.5%  norm=1.016  lr=2.74e-04  dt=  37.0ms  words=24,936,448
[E02  1497/1548 G   3044|CLM] train=4.6876  mask=17.5%  norm=1.570  lr=2.74e-04  dt=  36.8ms  words=24,944,640
[E02  1498/1548 G   3045|CLM] train=2.5511  mask=17.5%  norm=0.835  lr=2.74e-04  dt=  37.1ms  words=24,952,832
[E02  1499/1548 G   3046|CLM] train=4.1672  mask=17.5%  norm=0.653  lr=2.74e-04  dt=  36.8ms  words=24,961,024
[E02  1500/1548 G   3047|CLM] train=4.7929  mask=17.5%  norm=0.717  lr=2.74e-04  dt=  37.0ms  words=24,969,216
[E02  1501/1548 G   3048|CLM] train=5.3371  mask=17.5%  norm=0.827  lr=2.74e-04  dt=  36.8ms  words=24,977,408
[E02  1502/1548 G   3049|CLM] train=5.2229  mask=17.5%  norm=0.933  lr=2.74e-04  dt=  36.9ms  words=24,985,600
[E02  1503/1548 G   3050|CLM] train=4.3749  mask=17.5%  norm=0.753  lr=2.74e-04  dt=  36.9ms  words=24,993,792
[E02  1504/1548 G   3051|CLM] train=5.6258  mask=17.5%  norm=0.939  lr=2.74e-04  dt=  36.8ms  words=25,001,984
[E02  1505/1548 G   3052|CLM] train=4.3083  mask=17.5%  norm=0.649  lr=2.74e-04  dt=  36.9ms  words=25,010,176
[E02  1506/1548 G   3053|CLM] train=4.9585  mask=17.5%  norm=0.862  lr=2.74e-04  dt=  37.0ms  words=25,018,368
[E02  1507/1548 G   3054|CLM] train=3.4451  mask=17.5%  norm=0.941  lr=2.74e-04  dt=  37.2ms  words=25,026,560
[E02  1508/1548 G   3055|CLM] train=4.8002  mask=17.5%  norm=0.625  lr=2.74e-04  dt=  36.8ms  words=25,034,752
[E02  1509/1548 G   3056|CLM] train=2.9027  mask=17.5%  norm=1.764  lr=2.74e-04  dt=  36.8ms  words=25,042,944
[E02  1510/1548 G   3057|CLM] train=4.8951  mask=17.5%  norm=0.804  lr=2.74e-04  dt=  37.0ms  words=25,051,136
[E02  1511/1548 G   3058|CLM] train=4.3514  mask=17.5%  norm=0.640  lr=2.74e-04  dt=  36.8ms  words=25,059,328
[E02  1512/1548 G   3059|CLM] train=4.4407  mask=17.5%  norm=0.576  lr=2.74e-04  dt=  37.1ms  words=25,067,520
[E02  1513/1548 G   3060|CLM] train=3.0984  mask=17.5%  norm=0.647  lr=2.74e-04  dt=  36.8ms  words=25,075,712
[E02  1514/1548 G   3061|CLM] train=4.4525  mask=17.5%  norm=0.746  lr=2.74e-04  dt=  36.9ms  words=25,083,904
[E02  1515/1548 G   3062|CLM] train=4.8556  mask=17.5%  norm=0.713  lr=2.74e-04  dt=  36.8ms  words=25,092,096
[E02  1516/1548 G   3063|CLM] train=3.9282  mask=17.5%  norm=0.770  lr=2.74e-04  dt=  36.8ms  words=25,100,288
[E02  1517/1548 G   3064|CLM] train=2.6243  mask=17.5%  norm=0.832  lr=2.74e-04  dt=  37.1ms  words=25,108,480
[E02  1518/1548 G   3065|CLM] train=2.6804  mask=17.5%  norm=0.662  lr=2.74e-04  dt=  36.9ms  words=25,116,672
[E02  1519/1548 G   3066|CLM] train=3.9494  mask=17.5%  norm=0.698  lr=2.74e-04  dt=  36.9ms  words=25,124,864
[E02  1520/1548 G   3067|CLM] train=2.6225  mask=17.5%  norm=0.726  lr=2.74e-04  dt=  36.9ms  words=25,133,056
[E02  1521/1548 G   3068|CLM] train=2.9242  mask=17.5%  norm=0.628  lr=2.74e-04  dt=  36.9ms  words=25,141,248
[E02  1522/1548 G   3069|CLM] train=3.9834  mask=17.5%  norm=0.696  lr=2.74e-04  dt=  37.0ms  words=25,149,440
[E02  1523/1548 G   3070|CLM] train=3.8818  mask=17.5%  norm=0.611  lr=2.74e-04  dt=  36.8ms  words=25,157,632
[E02  1524/1548 G   3071|CLM] train=3.0010  mask=17.5%  norm=0.841  lr=2.74e-04  dt=  36.8ms  words=25,165,824
[E02  1525/1548 G   3072|CLM] train=4.8145  mask=17.5%  norm=0.722  lr=2.74e-04  dt=  36.9ms  words=25,174,016
[E02  1526/1548 G   3073|CLM] train=5.5031  mask=17.5%  norm=0.971  lr=2.74e-04  dt=  37.1ms  words=25,182,208
[E02  1527/1548 G   3074|CLM] train=5.0907  mask=17.5%  norm=0.697  lr=2.74e-04  dt=  36.8ms  words=25,190,400
[E02  1528/1548 G   3075|CLM] train=5.4421  mask=17.5%  norm=0.693  lr=2.74e-04  dt=  36.7ms  words=25,198,592
[E02  1529/1548 G   3076|CLM] train=4.7813  mask=17.5%  norm=0.711  lr=2.74e-04  dt=  36.8ms  words=25,206,784
[E02  1530/1548 G   3077|CLM] train=4.1274  mask=17.5%  norm=0.845  lr=2.74e-04  dt=  36.9ms  words=25,214,976
[E02  1531/1548 G   3078|CLM] train=2.5990  mask=17.5%  norm=1.480  lr=2.74e-04  dt=  36.9ms  words=25,223,168
[E02  1532/1548 G   3079|CLM] train=3.2004  mask=17.5%  norm=1.084  lr=2.74e-04  dt=  36.7ms  words=25,231,360
[E02  1533/1548 G   3080|CLM] train=4.5067  mask=17.5%  norm=1.514  lr=2.74e-04  dt=  36.7ms  words=25,239,552
[E02  1534/1548 G   3081|CLM] train=4.6074  mask=17.5%  norm=0.733  lr=2.74e-04  dt=  37.1ms  words=25,247,744
[E02  1535/1548 G   3082|CLM] train=4.7028  mask=17.5%  norm=0.851  lr=2.74e-04  dt=  36.9ms  words=25,255,936
[E02  1536/1548 G   3083|CLM] train=4.8451  mask=17.5%  norm=0.876  lr=2.74e-04  dt=  37.4ms  words=25,264,128
[E02  1537/1548 G   3084|CLM] train=4.3455  mask=17.5%  norm=0.704  lr=2.74e-04  dt=  37.0ms  words=25,272,320
[E02  1538/1548 G   3085|CLM] train=5.4735  mask=17.5%  norm=0.818  lr=2.74e-04  dt=  36.7ms  words=25,280,512
[E02  1539/1548 G   3086|CLM] train=5.1040  mask=17.5%  norm=0.721  lr=2.73e-04  dt=  37.1ms  words=25,288,704
[E02  1540/1548 G   3087|CLM] train=5.3180  mask=17.5%  norm=1.008  lr=2.73e-04  dt=  36.8ms  words=25,296,896
[E02  1541/1548 G   3088|CLM] train=4.8363  mask=17.5%  norm=1.475  lr=2.73e-04  dt=  36.8ms  words=25,305,088
[E02  1542/1548 G   3089|CLM] train=4.6075  mask=17.5%  norm=0.991  lr=2.73e-04  dt=  36.9ms  words=25,313,280
[E02  1543/1548 G   3090|CLM] train=4.5136  mask=17.5%  norm=0.825  lr=2.73e-04  dt=  36.9ms  words=25,321,472
[E02  1544/1548 G   3091|CLM] train=5.1489  mask=17.5%  norm=0.714  lr=2.73e-04  dt=  36.7ms  words=25,329,664
[E02  1545/1548 G   3092|CLM] train=4.8510  mask=17.5%  norm=0.648  lr=2.73e-04  dt=  37.1ms  words=25,337,856
[E02  1546/1548 G   3093|CLM] train=5.2761  mask=17.5%  norm=1.171  lr=2.73e-04  dt=  36.9ms  words=25,346,048
[E02  1547/1548 G   3094|CLM] train=4.6468  mask=17.5%  norm=0.826  lr=2.73e-04  dt=  36.8ms  words=25,354,240
[E02  1548/1548 G   3095|CLM] train=2.9719  mask=17.5%  norm=1.335  lr=2.73e-04  dt=  36.7ms  words=25,362,432
[E03     1/1548 G   3096|CLM] train=2.5834  mask=17.5%  norm=1.227  lr=2.73e-04  dt=  36.9ms  words=25,370,624
[E03     2/1548 G   3097|CLM] train=2.7686  mask=17.5%  norm=0.982  lr=2.73e-04  dt=  36.9ms  words=25,378,816
[E03     3/1548 G   3098|CLM] train=4.9304  mask=17.5%  norm=0.735  lr=2.73e-04  dt=  37.1ms  words=25,387,008
[E03     4/1548 G   3099|CLM] train=4.5245  mask=17.5%  norm=0.683  lr=2.73e-04  dt=  37.0ms  words=25,395,200
[E03     5/1548 G   3100|CLM] train=2.8503  mask=17.5%  norm=0.750  lr=2.73e-04  dt=  37.0ms  words=25,403,392
[E03     6/1548 G   3101|CLM] train=4.1271  mask=17.5%  norm=0.708  lr=2.73e-04  dt=  37.3ms  words=25,411,584
[E03     7/1548 G   3102|CLM] train=4.5650  mask=17.5%  norm=0.880  lr=2.73e-04  dt=  36.9ms  words=25,419,776
[E03     8/1548 G   3103|CLM] train=4.6025  mask=17.5%  norm=0.664  lr=2.73e-04  dt=  37.1ms  words=25,427,968
[E03     9/1548 G   3104|CLM] train=4.2113  mask=17.5%  norm=0.787  lr=2.73e-04  dt=  37.0ms  words=25,436,160
[E03    10/1548 G   3105|CLM] train=2.9567  mask=17.5%  norm=0.940  lr=2.73e-04  dt=  37.2ms  words=25,444,352
[E03    11/1548 G   3106|CLM] train=3.9466  mask=17.5%  norm=0.702  lr=2.73e-04  dt=  36.8ms  words=25,452,544
[E03    12/1548 G   3107|CLM] train=4.8481  mask=17.5%  norm=0.713  lr=2.73e-04  dt=  37.0ms  words=25,460,736
[E03    13/1548 G   3108|CLM] train=4.8207  mask=17.5%  norm=0.977  lr=2.73e-04  dt=  37.0ms  words=25,468,928
[E03    14/1548 G   3109|CLM] train=4.7784  mask=17.5%  norm=0.814  lr=2.73e-04  dt=  37.0ms  words=25,477,120
[E03    15/1548 G   3110|CLM] train=5.3673  mask=17.5%  norm=0.766  lr=2.73e-04  dt=  37.0ms  words=25,485,312
[E03    16/1548 G   3111|CLM] train=2.9919  mask=17.5%  norm=0.741  lr=2.73e-04  dt=  37.0ms  words=25,493,504
[E03    17/1548 G   3112|CLM] train=6.0324  mask=17.5%  norm=1.369  lr=2.73e-04  dt=  37.2ms  words=25,501,696
[E03    18/1548 G   3113|CLM] train=5.6973  mask=17.5%  norm=1.115  lr=2.73e-04  dt=  36.9ms  words=25,509,888
[E03    19/1548 G   3114|CLM] train=4.4533  mask=17.5%  norm=0.868  lr=2.73e-04  dt=  36.9ms  words=25,518,080
[E03    20/1548 G   3115|CLM] train=5.4639  mask=17.5%  norm=0.697  lr=2.73e-04  dt=  37.3ms  words=25,526,272
[E03    21/1548 G   3116|CLM] train=4.7129  mask=17.5%  norm=0.739  lr=2.73e-04  dt=  37.0ms  words=25,534,464
[E03    22/1548 G   3117|CLM] train=5.1690  mask=17.5%  norm=0.793  lr=2.73e-04  dt=  36.9ms  words=25,542,656
[E03    23/1548 G   3118|CLM] train=2.4702  mask=17.5%  norm=1.009  lr=2.73e-04  dt=  37.0ms  words=25,550,848
[E03    24/1548 G   3119|CLM] train=2.6160  mask=17.5%  norm=0.799  lr=2.73e-04  dt=  37.0ms  words=25,559,040
[E03    25/1548 G   3120|CLM] train=4.8168  mask=17.5%  norm=0.658  lr=2.73e-04  dt=  37.0ms  words=25,567,232
[E03    26/1548 G   3121|CLM] train=5.0089  mask=17.5%  norm=0.867  lr=2.73e-04  dt=  36.9ms  words=25,575,424
[E03    27/1548 G   3122|CLM] train=5.7678  mask=17.5%  norm=1.559  lr=2.73e-04  dt=  37.1ms  words=25,583,616
[E03    28/1548 G   3123|CLM] train=4.3059  mask=17.5%  norm=0.833  lr=2.73e-04  dt=  36.9ms  words=25,591,808
[E03    29/1548 G   3124|CLM] train=5.0014  mask=17.5%  norm=1.426  lr=2.73e-04  dt=  37.1ms  words=25,600,000
[E03    30/1548 G   3125|CLM] train=4.1067  mask=17.5%  norm=0.804  lr=2.73e-04  dt=  36.9ms  words=25,608,192
[E03    31/1548 G   3126|CLM] train=2.8991  mask=17.5%  norm=0.953  lr=2.73e-04  dt=  36.8ms  words=25,616,384
[E03    32/1548 G   3127|CLM] train=5.1668  mask=17.5%  norm=1.194  lr=2.73e-04  dt=  37.0ms  words=25,624,576
[E03    33/1548 G   3128|CLM] train=4.5544  mask=17.5%  norm=0.666  lr=2.73e-04  dt=  36.9ms  words=25,632,768
[E03    34/1548 G   3129|CLM] train=2.3287  mask=17.5%  norm=1.019  lr=2.73e-04  dt=  36.8ms  words=25,640,960
[E03    35/1548 G   3130|CLM] train=2.8121  mask=17.5%  norm=1.034  lr=2.72e-04  dt=  37.0ms  words=25,649,152
[E03    36/1548 G   3131|CLM] train=3.1722  mask=17.5%  norm=0.721  lr=2.72e-04  dt=  37.1ms  words=25,657,344
[E03    37/1548 G   3132|CLM] train=4.6924  mask=17.5%  norm=0.879  lr=2.72e-04  dt=  36.9ms  words=25,665,536
[E03    38/1548 G   3133|CLM] train=2.5690  mask=17.5%  norm=0.996  lr=2.72e-04  dt=  38.1ms  words=25,673,728
[E03    39/1548 G   3134|CLM] train=2.6150  mask=17.5%  norm=0.785  lr=2.72e-04  dt=  37.1ms  words=25,681,920
[E03    40/1548 G   3135|CLM] train=2.8250  mask=17.5%  norm=0.741  lr=2.72e-04  dt=  37.2ms  words=25,690,112
[E03    41/1548 G   3136|CLM] train=2.4239  mask=17.5%  norm=0.734  lr=2.72e-04  dt=  38.2ms  words=25,698,304
[E03    42/1548 G   3137|CLM] train=2.7905  mask=17.5%  norm=1.010  lr=2.72e-04  dt=  36.9ms  words=25,706,496
[E03    43/1548 G   3138|CLM] train=4.1189  mask=17.5%  norm=0.945  lr=2.72e-04  dt=  37.0ms  words=25,714,688
[E03    44/1548 G   3139|CLM] train=4.3128  mask=17.5%  norm=0.760  lr=2.72e-04  dt=  37.2ms  words=25,722,880
[E03    45/1548 G   3140|CLM] train=4.7157  mask=17.5%  norm=0.760  lr=2.72e-04  dt=  37.3ms  words=25,731,072
[E03    46/1548 G   3141|CLM] train=2.6549  mask=17.5%  norm=0.707  lr=2.72e-04  dt=  37.0ms  words=25,739,264
[E03    47/1548 G   3142|CLM] train=4.7892  mask=17.5%  norm=0.753  lr=2.72e-04  dt=  37.0ms  words=25,747,456
[E03    48/1548 G   3143|CLM] train=5.9808  mask=17.5%  norm=1.246  lr=2.72e-04  dt=  37.0ms  words=25,755,648
[E03    49/1548 G   3144|CLM] train=4.5401  mask=17.5%  norm=0.714  lr=2.72e-04  dt=  36.8ms  words=25,763,840
[E03    50/1548 G   3145|CLM] train=4.3138  mask=17.5%  norm=1.300  lr=2.72e-04  dt=  36.9ms  words=25,772,032
[E03    51/1548 G   3146|CLM] train=4.8957  mask=17.5%  norm=0.952  lr=2.72e-04  dt=  36.9ms  words=25,780,224
[E03    52/1548 G   3147|CLM] train=4.6230  mask=17.5%  norm=0.817  lr=2.72e-04  dt=  37.0ms  words=25,788,416
[E03    53/1548 G   3148|CLM] train=2.7593  mask=17.5%  norm=0.721  lr=2.72e-04  dt=  36.9ms  words=25,796,608
[E03    54/1548 G   3149|CLM] train=4.7766  mask=17.5%  norm=0.870  lr=2.72e-04  dt=  38.2ms  words=25,804,800
[E03    55/1548 G   3150|CLM] train=2.7601  mask=17.5%  norm=1.081  lr=2.72e-04  dt=  42.6ms  words=25,812,992
[E03    56/1548 G   3151|CLM] train=2.6748  mask=17.5%  norm=0.773  lr=2.72e-04  dt=  45.9ms  words=25,821,184
[E03    57/1548 G   3152|CLM] train=2.5953  mask=17.5%  norm=0.549  lr=2.72e-04  dt=  37.0ms  words=25,829,376
[E03    58/1548 G   3153|CLM] train=2.6372  mask=17.5%  norm=0.548  lr=2.72e-04  dt=  40.9ms  words=25,837,568
[E03    59/1548 G   3154|CLM] train=2.5029  mask=17.5%  norm=0.595  lr=2.72e-04  dt=  43.1ms  words=25,845,760
[E03    60/1548 G   3155|CLM] train=4.4440  mask=17.5%  norm=1.041  lr=2.72e-04  dt=  45.3ms  words=25,853,952
[E03    61/1548 G   3156|CLM] train=2.6934  mask=17.5%  norm=0.621  lr=2.72e-04  dt=  45.9ms  words=25,862,144
[E03    62/1548 G   3157|CLM] train=4.7415  mask=17.5%  norm=0.890  lr=2.72e-04  dt=  36.9ms  words=25,870,336
[E03    63/1548 G   3158|CLM] train=2.4612  mask=17.4%  norm=0.821  lr=2.72e-04  dt=  37.0ms  words=25,878,528
[E03    64/1548 G   3159|CLM] train=2.6198  mask=17.4%  norm=0.652  lr=2.72e-04  dt=  37.1ms  words=25,886,720
[E03    65/1548 G   3160|CLM] train=4.4297  mask=17.4%  norm=0.837  lr=2.72e-04  dt=  37.0ms  words=25,894,912
[E03    66/1548 G   3161|CLM] train=3.1189  mask=17.4%  norm=1.038  lr=2.72e-04  dt=  37.2ms  words=25,903,104
[E03    67/1548 G   3162|CLM] train=4.4603  mask=17.4%  norm=0.693  lr=2.72e-04  dt=  41.1ms  words=25,911,296
[E03    68/1548 G   3163|CLM] train=2.6714  mask=17.4%  norm=0.860  lr=2.72e-04  dt=  40.6ms  words=25,919,488
[E03    69/1548 G   3164|CLM] train=4.7674  mask=17.4%  norm=0.615  lr=2.72e-04  dt=  37.0ms  words=25,927,680
[E03    70/1548 G   3165|CLM] train=4.4167  mask=17.4%  norm=0.572  lr=2.72e-04  dt=  36.8ms  words=25,935,872
[E03    71/1548 G   3166|CLM] train=5.4857  mask=17.4%  norm=1.513  lr=2.72e-04  dt=  36.9ms  words=25,944,064
[E03    72/1548 G   3167|CLM] train=2.9259  mask=17.4%  norm=0.759  lr=2.72e-04  dt=  38.4ms  words=25,952,256
[E03    73/1548 G   3168|CLM] train=3.3822  mask=17.4%  norm=0.713  lr=2.72e-04  dt=  41.0ms  words=25,960,448
[E03    74/1548 G   3169|CLM] train=4.7476  mask=17.4%  norm=0.865  lr=2.72e-04  dt=  38.1ms  words=25,968,640
[E03    75/1548 G   3170|CLM] train=4.6161  mask=17.4%  norm=2.076  lr=2.72e-04  dt=  42.2ms  words=25,976,832
[E03    76/1548 G   3171|CLM] train=2.5864  mask=17.4%  norm=0.805  lr=2.72e-04  dt=  39.5ms  words=25,985,024
[E03    77/1548 G   3172|CLM] train=4.4094  mask=17.4%  norm=0.616  lr=2.72e-04  dt=  37.1ms  words=25,993,216
[E03    78/1548 G   3173|CLM] train=5.2687  mask=17.4%  norm=0.885  lr=2.71e-04  dt=  37.1ms  words=26,001,408
[E03    79/1548 G   3174|CLM] train=5.0463  mask=17.4%  norm=0.959  lr=2.71e-04  dt=  37.2ms  words=26,009,600
[E03    80/1548 G   3175|CLM] train=2.3317  mask=17.4%  norm=0.775  lr=2.71e-04  dt=  38.1ms  words=26,017,792
[E03    81/1548 G   3176|CLM] train=5.2923  mask=17.4%  norm=1.418  lr=2.71e-04  dt=  37.0ms  words=26,025,984
[E03    82/1548 G   3177|CLM] train=4.6452  mask=17.4%  norm=0.669  lr=2.71e-04  dt=  38.1ms  words=26,034,176
[E03    83/1548 G   3178|CLM] train=4.7746  mask=17.4%  norm=0.726  lr=2.71e-04  dt=  36.9ms  words=26,042,368
[E03    84/1548 G   3179|CLM] train=4.2672  mask=17.4%  norm=0.645  lr=2.71e-04  dt=  38.1ms  words=26,050,560
[E03    85/1548 G   3180|CLM] train=4.1861  mask=17.4%  norm=0.658  lr=2.71e-04  dt=  38.0ms  words=26,058,752
[E03    86/1548 G   3181|CLM] train=4.5242  mask=17.4%  norm=0.601  lr=2.71e-04  dt=  42.2ms  words=26,066,944
[E03    87/1548 G   3182|CLM] train=4.5028  mask=17.4%  norm=0.618  lr=2.71e-04  dt=  37.8ms  words=26,075,136
[E03    88/1548 G   3183|CLM] train=2.4505  mask=17.4%  norm=0.927  lr=2.71e-04  dt=  37.0ms  words=26,083,328
[E03    89/1548 G   3184|CLM] train=4.8921  mask=17.4%  norm=0.651  lr=2.71e-04  dt=  37.3ms  words=26,091,520
[E03    90/1548 G   3185|CLM] train=2.6642  mask=17.4%  norm=0.646  lr=2.71e-04  dt=  37.1ms  words=26,099,712
[E03    91/1548 G   3186|CLM] train=4.6223  mask=17.4%  norm=0.726  lr=2.71e-04  dt=  37.1ms  words=26,107,904
[E03    92/1548 G   3187|CLM] train=2.6729  mask=17.4%  norm=0.647  lr=2.71e-04  dt=  37.5ms  words=26,116,096
[E03    93/1548 G   3188|CLM] train=4.9282  mask=17.4%  norm=0.752  lr=2.71e-04  dt=  37.5ms  words=26,124,288
[E03    94/1548 G   3189|CLM] train=4.2772  mask=17.4%  norm=0.567  lr=2.71e-04  dt=  37.4ms  words=26,132,480
[E03    95/1548 G   3190|CLM] train=4.2344  mask=17.4%  norm=0.702  lr=2.71e-04  dt=  37.1ms  words=26,140,672
[E03    96/1548 G   3191|CLM] train=3.9462  mask=17.4%  norm=0.748  lr=2.71e-04  dt=  37.4ms  words=26,148,864
[E03    97/1548 G   3192|CLM] train=4.2764  mask=17.4%  norm=0.566  lr=2.71e-04  dt=  37.1ms  words=26,157,056
[E03    98/1548 G   3193|CLM] train=4.3532  mask=17.4%  norm=0.762  lr=2.71e-04  dt=  37.3ms  words=26,165,248
[E03    99/1548 G   3194|CLM] train=3.2752  mask=17.4%  norm=1.779  lr=2.71e-04  dt=  37.0ms  words=26,173,440
[E03   100/1548 G   3195|CLM] train=4.1424  mask=17.4%  norm=0.661  lr=2.71e-04  dt=  37.0ms  words=26,181,632
[E03   101/1548 G   3196|CLM] train=4.5078  mask=17.4%  norm=0.746  lr=2.71e-04  dt=  37.0ms  words=26,189,824
[E03   102/1548 G   3197|CLM] train=4.4219  mask=17.4%  norm=0.800  lr=2.71e-04  dt=  37.1ms  words=26,198,016
[E03   103/1548 G   3198|CLM] train=2.9676  mask=17.4%  norm=0.777  lr=2.71e-04  dt=  37.0ms  words=26,206,208
[E03   104/1548 G   3199|CLM] train=5.1921  mask=17.4%  norm=0.784  lr=2.71e-04  dt=  37.3ms  words=26,214,400
[E03   105/1548 G   3200|CLM] train=4.5722  mask=17.4%  norm=0.604  lr=2.71e-04  dt=  37.8ms  words=26,222,592
[E03   106/1548 G   3201|CLM] train=2.6175  mask=17.4%  norm=0.537  lr=2.71e-04  dt=  36.9ms  words=26,230,784
[E03   107/1548 G   3202|CLM] train=4.8211  mask=17.4%  norm=0.912  lr=2.71e-04  dt=  36.9ms  words=26,238,976
[E03   108/1548 G   3203|CLM] train=2.9290  mask=17.4%  norm=0.732  lr=2.71e-04  dt=  37.0ms  words=26,247,168
[E03   109/1548 G   3204|CLM] train=5.0647  mask=17.4%  norm=0.671  lr=2.71e-04  dt=  36.8ms  words=26,255,360
[E03   110/1548 G   3205|CLM] train=4.8749  mask=17.4%  norm=0.629  lr=2.71e-04  dt=  36.9ms  words=26,263,552
[E03   111/1548 G   3206|CLM] train=4.0485  mask=17.4%  norm=0.854  lr=2.71e-04  dt=  36.9ms  words=26,271,744
[E03   112/1548 G   3207|CLM] train=5.0908  mask=17.4%  norm=0.838  lr=2.71e-04  dt=  36.9ms  words=26,279,936
[E03   113/1548 G   3208|CLM] train=4.5010  mask=17.4%  norm=0.638  lr=2.71e-04  dt=  36.9ms  words=26,288,128
[E03   114/1548 G   3209|CLM] train=4.7183  mask=17.4%  norm=0.753  lr=2.71e-04  dt=  36.9ms  words=26,296,320
[E03   115/1548 G   3210|CLM] train=3.8680  mask=17.4%  norm=0.598  lr=2.71e-04  dt=  37.2ms  words=26,304,512
[E03   116/1548 G   3211|CLM] train=5.7865  mask=17.4%  norm=1.397  lr=2.71e-04  dt=  36.9ms  words=26,312,704
[E03   117/1548 G   3212|CLM] train=2.5530  mask=17.4%  norm=0.762  lr=2.71e-04  dt=  36.9ms  words=26,320,896
[E03   118/1548 G   3213|CLM] train=2.5731  mask=17.4%  norm=0.576  lr=2.71e-04  dt=  36.8ms  words=26,329,088
[E03   119/1548 G   3214|CLM] train=2.7032  mask=17.4%  norm=1.214  lr=2.71e-04  dt=  37.0ms  words=26,337,280
[E03   120/1548 G   3215|CLM] train=2.9581  mask=17.4%  norm=0.656  lr=2.71e-04  dt=  36.9ms  words=26,345,472
[E03   121/1548 G   3216|CLM] train=3.0988  mask=17.4%  norm=0.586  lr=2.70e-04  dt=  36.9ms  words=26,353,664
[E03   122/1548 G   3217|CLM] train=5.0538  mask=17.4%  norm=1.014  lr=2.70e-04  dt=  37.0ms  words=26,361,856
[E03   123/1548 G   3218|CLM] train=5.0422  mask=17.4%  norm=0.767  lr=2.70e-04  dt=  36.9ms  words=26,370,048
[E03   124/1548 G   3219|CLM] train=4.3991  mask=17.4%  norm=1.016  lr=2.70e-04  dt=  37.0ms  words=26,378,240
[E03   125/1548 G   3220|CLM] train=4.9789  mask=17.4%  norm=1.918  lr=2.70e-04  dt=  36.9ms  words=26,386,432
[E03   126/1548 G   3221|CLM] train=2.9637  mask=17.4%  norm=1.486  lr=2.70e-04  dt=  36.8ms  words=26,394,624
[E03   127/1548 G   3222|CLM] train=4.6588  mask=17.4%  norm=0.859  lr=2.70e-04  dt=  36.9ms  words=26,402,816
[E03   128/1548 G   3223|CLM] train=2.5614  mask=17.4%  norm=1.036  lr=2.70e-04  dt=  37.0ms  words=26,411,008
[E03   129/1548 G   3224|CLM] train=5.0217  mask=17.4%  norm=0.973  lr=2.70e-04  dt=  37.0ms  words=26,419,200
[E03   130/1548 G   3225|CLM] train=4.4291  mask=17.4%  norm=0.675  lr=2.70e-04  dt=  36.9ms  words=26,427,392
[E03   131/1548 G   3226|CLM] train=2.8561  mask=17.4%  norm=0.841  lr=2.70e-04  dt=  37.1ms  words=26,435,584
[E03   132/1548 G   3227|CLM] train=4.9008  mask=17.4%  norm=0.916  lr=2.70e-04  dt=  36.9ms  words=26,443,776
[E03   133/1548 G   3228|CLM] train=4.9494  mask=17.4%  norm=0.816  lr=2.70e-04  dt=  36.8ms  words=26,451,968
[E03   134/1548 G   3229|CLM] train=5.3565  mask=17.4%  norm=0.730  lr=2.70e-04  dt=  36.8ms  words=26,460,160
[E03   135/1548 G   3230|CLM] train=4.4361  mask=17.4%  norm=0.855  lr=2.70e-04  dt=  36.9ms  words=26,468,352
[E03   136/1548 G   3231|CLM] train=4.2350  mask=17.4%  norm=0.816  lr=2.70e-04  dt=  36.9ms  words=26,476,544
[E03   137/1548 G   3232|CLM] train=4.3647  mask=17.4%  norm=0.800  lr=2.70e-04  dt=  37.1ms  words=26,484,736
[E03   138/1548 G   3233|CLM] train=4.5134  mask=17.4%  norm=0.700  lr=2.70e-04  dt=  36.7ms  words=26,492,928
[E03   139/1548 G   3234|CLM] train=4.8075  mask=17.4%  norm=0.737  lr=2.70e-04  dt=  37.0ms  words=26,501,120
[E03   140/1548 G   3235|CLM] train=2.3810  mask=17.4%  norm=0.915  lr=2.70e-04  dt=  37.0ms  words=26,509,312
[E03   141/1548 G   3236|CLM] train=2.7873  mask=17.4%  norm=1.073  lr=2.70e-04  dt=  36.8ms  words=26,517,504
[E03   142/1548 G   3237|CLM] train=4.6191  mask=17.4%  norm=0.792  lr=2.70e-04  dt=  36.7ms  words=26,525,696
[E03   143/1548 G   3238|CLM] train=4.5421  mask=17.4%  norm=1.242  lr=2.70e-04  dt=  36.9ms  words=26,533,888
[E03   144/1548 G   3239|CLM] train=4.0116  mask=17.4%  norm=2.375  lr=2.70e-04  dt=  36.7ms  words=26,542,080
[E03   145/1548 G   3240|CLM] train=3.6939  mask=17.4%  norm=2.221  lr=2.70e-04  dt=  37.0ms  words=26,550,272
[E03   146/1548 G   3241|CLM] train=2.5489  mask=17.4%  norm=0.968  lr=2.70e-04  dt=  36.8ms  words=26,558,464
[E03   147/1548 G   3242|CLM] train=2.7500  mask=17.4%  norm=1.309  lr=2.70e-04  dt=  36.7ms  words=26,566,656
[E03   148/1548 G   3243|CLM] train=4.2751  mask=17.4%  norm=1.092  lr=2.70e-04  dt=  36.9ms  words=26,574,848
[E03   149/1548 G   3244|CLM] train=4.3037  mask=17.4%  norm=1.491  lr=2.70e-04  dt=  37.0ms  words=26,583,040
[E03   150/1548 G   3245|CLM] train=3.9205  mask=17.4%  norm=0.731  lr=2.70e-04  dt=  36.8ms  words=26,591,232
[E03   151/1548 G   3246|CLM] train=2.7307  mask=17.4%  norm=1.069  lr=2.70e-04  dt=  37.0ms  words=26,599,424
[E03   152/1548 G   3247|CLM] train=2.6718  mask=17.4%  norm=0.773  lr=2.70e-04  dt=  36.8ms  words=26,607,616
[E03   153/1548 G   3248|CLM] train=4.7628  mask=17.4%  norm=0.943  lr=2.70e-04  dt=  37.2ms  words=26,615,808
[E03   154/1548 G   3249|CLM] train=2.6551  mask=17.4%  norm=0.835  lr=2.70e-04  dt=  36.8ms  words=26,624,000
[E03   155/1548 G   3250|CLM] train=4.7709  mask=17.4%  norm=1.345  lr=2.70e-04  dt=  36.8ms  words=26,632,192
[E03   156/1548 G   3251|CLM] train=3.0596  mask=17.4%  norm=0.971  lr=2.70e-04  dt=  36.9ms  words=26,640,384
[E03   157/1548 G   3252|CLM] train=4.8095  mask=17.4%  norm=0.777  lr=2.70e-04  dt=  37.0ms  words=26,648,576
[E03   158/1548 G   3253|CLM] train=4.6052  mask=17.4%  norm=0.915  lr=2.70e-04  dt=  37.1ms  words=26,656,768
[E03   159/1548 G   3254|CLM] train=4.3183  mask=17.4%  norm=0.696  lr=2.70e-04  dt=  36.9ms  words=26,664,960
[E03   160/1548 G   3255|CLM] train=4.6964  mask=17.4%  norm=0.675  lr=2.70e-04  dt=  36.9ms  words=26,673,152
[E03   161/1548 G   3256|CLM] train=4.4659  mask=17.4%  norm=0.664  lr=2.70e-04  dt=  37.0ms  words=26,681,344
[E03   162/1548 G   3257|CLM] train=2.6145  mask=17.4%  norm=0.915  lr=2.70e-04  dt=  36.9ms  words=26,689,536
[E03   163/1548 G   3258|CLM] train=4.6213  mask=17.4%  norm=0.977  lr=2.69e-04  dt=  36.9ms  words=26,697,728
[E03   164/1548 G   3259|CLM] train=3.9960  mask=17.4%  norm=0.678  lr=2.69e-04  dt=  37.1ms  words=26,705,920
[E03   165/1548 G   3260|CLM] train=4.9614  mask=17.4%  norm=1.054  lr=2.69e-04  dt=  37.0ms  words=26,714,112
[E03   166/1548 G   3261|CLM] train=2.6395  mask=17.4%  norm=1.147  lr=2.69e-04  dt=  36.7ms  words=26,722,304
[E03   167/1548 G   3262|CLM] train=5.0330  mask=17.4%  norm=1.059  lr=2.69e-04  dt=  36.9ms  words=26,730,496
[E03   168/1548 G   3263|CLM] train=2.4713  mask=17.4%  norm=0.723  lr=2.69e-04  dt=  36.9ms  words=26,738,688
[E03   169/1548 G   3264|CLM] train=4.0067  mask=17.4%  norm=0.732  lr=2.69e-04  dt=  36.9ms  words=26,746,880
[E03   170/1548 G   3265|CLM] train=4.5191  mask=17.4%  norm=1.085  lr=2.69e-04  dt=  36.9ms  words=26,755,072
[E03   171/1548 G   3266|CLM] train=3.0698  mask=17.4%  norm=0.793  lr=2.69e-04  dt=  36.9ms  words=26,763,264
[E03   172/1548 G   3267|CLM] train=2.7509  mask=17.4%  norm=1.221  lr=2.69e-04  dt=  36.9ms  words=26,771,456
[E03   173/1548 G   3268|CLM] train=6.2393  mask=17.4%  norm=1.187  lr=2.69e-04  dt=  37.0ms  words=26,779,648
[E03   174/1548 G   3269|CLM] train=4.2943  mask=17.4%  norm=0.705  lr=2.69e-04  dt=  36.9ms  words=26,787,840
[E03   175/1548 G   3270|CLM] train=2.9717  mask=17.4%  norm=0.655  lr=2.69e-04  dt=  36.8ms  words=26,796,032
[E03   176/1548 G   3271|CLM] train=4.5691  mask=17.4%  norm=0.857  lr=2.69e-04  dt=  37.0ms  words=26,804,224
[E03   177/1548 G   3272|CLM] train=3.2130  mask=17.4%  norm=0.650  lr=2.69e-04  dt=  37.1ms  words=26,812,416
[E03   178/1548 G   3273|CLM] train=2.6848  mask=17.4%  norm=0.881  lr=2.69e-04  dt=  36.8ms  words=26,820,608
[E03   179/1548 G   3274|CLM] train=2.8373  mask=17.4%  norm=0.613  lr=2.69e-04  dt=  36.9ms  words=26,828,800
[E03   180/1548 G   3275|CLM] train=2.7221  mask=17.4%  norm=0.536  lr=2.69e-04  dt=  36.9ms  words=26,836,992
[E03   181/1548 G   3276|CLM] train=4.5652  mask=17.4%  norm=0.892  lr=2.69e-04  dt=  37.1ms  words=26,845,184
[E03   182/1548 G   3277|CLM] train=2.6759  mask=17.4%  norm=0.665  lr=2.69e-04  dt=  36.9ms  words=26,853,376
[E03   183/1548 G   3278|CLM] train=5.4639  mask=17.4%  norm=1.100  lr=2.69e-04  dt=  36.8ms  words=26,861,568
[E03   184/1548 G   3279|CLM] train=2.6961  mask=17.4%  norm=0.957  lr=2.69e-04  dt=  36.9ms  words=26,869,760
[E03   185/1548 G   3280|CLM] train=4.0579  mask=17.4%  norm=0.711  lr=2.69e-04  dt=  37.2ms  words=26,877,952
[E03   186/1548 G   3281|CLM] train=4.7600  mask=17.4%  norm=0.789  lr=2.69e-04  dt=  36.8ms  words=26,886,144
[E03   187/1548 G   3282|CLM] train=4.8300  mask=17.3%  norm=1.001  lr=2.69e-04  dt=  37.0ms  words=26,894,336
[E03   188/1548 G   3283|CLM] train=2.0361  mask=17.3%  norm=0.794  lr=2.69e-04  dt=  37.2ms  words=26,902,528
[E03   189/1548 G   3284|CLM] train=5.4474  mask=17.3%  norm=0.983  lr=2.69e-04  dt=  37.2ms  words=26,910,720
[E03   190/1548 G   3285|CLM] train=2.5783  mask=17.3%  norm=0.969  lr=2.69e-04  dt=  37.1ms  words=26,918,912
[E03   191/1548 G   3286|CLM] train=4.2008  mask=17.3%  norm=0.765  lr=2.69e-04  dt=  38.9ms  words=26,927,104
[E03   192/1548 G   3287|CLM] train=2.6834  mask=17.3%  norm=0.909  lr=2.69e-04  dt=  37.4ms  words=26,935,296
[E03   193/1548 G   3288|CLM] train=2.8155  mask=17.3%  norm=0.678  lr=2.69e-04  dt=  38.6ms  words=26,943,488
[E03   194/1548 G   3289|CLM] train=2.7232  mask=17.3%  norm=0.854  lr=2.69e-04  dt=  38.5ms  words=26,951,680
[E03   195/1548 G   3290|CLM] train=2.4181  mask=17.3%  norm=0.543  lr=2.69e-04  dt=  40.5ms  words=26,959,872
[E03   196/1548 G   3291|CLM] train=5.1497  mask=17.3%  norm=0.903  lr=2.69e-04  dt=  38.2ms  words=26,968,064
[E03   197/1548 G   3292|CLM] train=5.0535  mask=17.3%  norm=0.839  lr=2.69e-04  dt=  38.3ms  words=26,976,256
[E03   198/1548 G   3293|CLM] train=3.7401  mask=17.3%  norm=0.729  lr=2.69e-04  dt=  37.0ms  words=26,984,448
[E03   199/1548 G   3294|CLM] train=4.6689  mask=17.3%  norm=0.802  lr=2.69e-04  dt=  36.9ms  words=26,992,640
[E03   200/1548 G   3295|CLM] train=5.3507  mask=17.3%  norm=5.873  lr=2.69e-04  dt=  38.6ms  words=27,000,832
[E03   201/1548 G   3296|CLM] train=4.5303  mask=17.3%  norm=0.726  lr=2.69e-04  dt=  39.8ms  words=27,009,024
[E03   202/1548 G   3297|CLM] train=5.8490  mask=17.3%  norm=1.368  lr=2.69e-04  dt=  36.8ms  words=27,017,216
[E03   203/1548 G   3298|CLM] train=3.8868  mask=17.3%  norm=0.699  lr=2.69e-04  dt=  36.8ms  words=27,025,408
[E03   204/1548 G   3299|CLM] train=4.9495  mask=17.3%  norm=1.065  lr=2.69e-04  dt=  37.1ms  words=27,033,600
[E03   205/1548 G   3300|CLM] train=4.0395  mask=17.3%  norm=0.734  lr=2.68e-04  dt=  36.9ms  words=27,041,792
[E03   206/1548 G   3301|CLM] train=5.0684  mask=17.3%  norm=0.639  lr=2.68e-04  dt=  36.8ms  words=27,049,984
[E03   207/1548 G   3302|CLM] train=4.7227  mask=17.3%  norm=0.874  lr=2.68e-04  dt=  36.9ms  words=27,058,176
[E03   208/1548 G   3303|CLM] train=4.5793  mask=17.3%  norm=0.740  lr=2.68e-04  dt=  36.9ms  words=27,066,368
[E03   209/1548 G   3304|CLM] train=4.5445  mask=17.3%  norm=1.026  lr=2.68e-04  dt=  36.9ms  words=27,074,560
[E03   210/1548 G   3305|CLM] train=2.5393  mask=17.3%  norm=1.448  lr=2.68e-04  dt=  36.7ms  words=27,082,752
[E03   211/1548 G   3306|CLM] train=4.6931  mask=17.3%  norm=0.958  lr=2.68e-04  dt=  36.8ms  words=27,090,944
[E03   212/1548 G   3307|CLM] train=5.0773  mask=17.3%  norm=0.757  lr=2.68e-04  dt=  37.2ms  words=27,099,136
[E03   213/1548 G   3308|CLM] train=2.6003  mask=17.3%  norm=0.717  lr=2.68e-04  dt=  36.9ms  words=27,107,328
[E03   214/1548 G   3309|CLM] train=2.5630  mask=17.3%  norm=0.828  lr=2.68e-04  dt=  36.9ms  words=27,115,520
[E03   215/1548 G   3310|CLM] train=4.7258  mask=17.3%  norm=0.876  lr=2.68e-04  dt=  37.0ms  words=27,123,712
[E03   216/1548 G   3311|CLM] train=4.2314  mask=17.3%  norm=0.811  lr=2.68e-04  dt=  37.1ms  words=27,131,904
[E03   217/1548 G   3312|CLM] train=2.8393  mask=17.3%  norm=1.291  lr=2.68e-04  dt=  36.8ms  words=27,140,096
[E03   218/1548 G   3313|CLM] train=2.8903  mask=17.3%  norm=0.780  lr=2.68e-04  dt=  36.7ms  words=27,148,288
[E03   219/1548 G   3314|CLM] train=5.6133  mask=17.3%  norm=2.078  lr=2.68e-04  dt=  36.9ms  words=27,156,480
[E03   220/1548 G   3315|CLM] train=4.3185  mask=17.3%  norm=1.050  lr=2.68e-04  dt=  37.1ms  words=27,164,672
[E03   221/1548 G   3316|CLM] train=2.8468  mask=17.3%  norm=0.777  lr=2.68e-04  dt=  36.9ms  words=27,172,864
[E03   222/1548 G   3317|CLM] train=5.8390  mask=17.3%  norm=1.590  lr=2.68e-04  dt=  37.2ms  words=27,181,056
[E03   223/1548 G   3318|CLM] train=2.9548  mask=17.3%  norm=0.655  lr=2.68e-04  dt=  37.0ms  words=27,189,248
[E03   224/1548 G   3319|CLM] train=4.6843  mask=17.3%  norm=1.033  lr=2.68e-04  dt=  37.0ms  words=27,197,440
[E03   225/1548 G   3320|CLM] train=4.6690  mask=17.3%  norm=0.717  lr=2.68e-04  dt=  37.1ms  words=27,205,632
[E03   226/1548 G   3321|CLM] train=4.0399  mask=17.3%  norm=0.705  lr=2.68e-04  dt=  37.0ms  words=27,213,824
[E03   227/1548 G   3322|CLM] train=3.9935  mask=17.3%  norm=0.891  lr=2.68e-04  dt=  37.1ms  words=27,222,016
[E03   228/1548 G   3323|CLM] train=4.3902  mask=17.3%  norm=1.160  lr=2.68e-04  dt=  36.8ms  words=27,230,208
[E03   229/1548 G   3324|CLM] train=4.4385  mask=17.3%  norm=0.938  lr=2.68e-04  dt=  36.9ms  words=27,238,400
[E03   230/1548 G   3325|CLM] train=4.8390  mask=17.3%  norm=1.003  lr=2.68e-04  dt=  37.0ms  words=27,246,592
[E03   231/1548 G   3326|CLM] train=4.5791  mask=17.3%  norm=0.752  lr=2.68e-04  dt=  37.0ms  words=27,254,784
[E03   232/1548 G   3327|CLM] train=5.8754  mask=17.3%  norm=0.958  lr=2.68e-04  dt=  36.9ms  words=27,262,976
[E03   233/1548 G   3328|CLM] train=4.4882  mask=17.3%  norm=1.050  lr=2.68e-04  dt=  37.0ms  words=27,271,168
[E03   234/1548 G   3329|CLM] train=2.7421  mask=17.3%  norm=0.631  lr=2.68e-04  dt=  36.9ms  words=27,279,360
[E03   235/1548 G   3330|CLM] train=2.7538  mask=17.3%  norm=0.907  lr=2.68e-04  dt=  37.0ms  words=27,287,552
[E03   236/1548 G   3331|CLM] train=4.4636  mask=17.3%  norm=0.835  lr=2.68e-04  dt=  36.9ms  words=27,295,744
[E03   237/1548 G   3332|CLM] train=5.7604  mask=17.3%  norm=4.214  lr=2.68e-04  dt=  36.9ms  words=27,303,936
[E03   238/1548 G   3333|CLM] train=2.5814  mask=17.3%  norm=0.734  lr=2.68e-04  dt=  37.0ms  words=27,312,128
[E03   239/1548 G   3334|CLM] train=2.8582  mask=17.3%  norm=1.192  lr=2.68e-04  dt=  37.1ms  words=27,320,320
[E03   240/1548 G   3335|CLM] train=5.4065  mask=17.3%  norm=1.051  lr=2.68e-04  dt=  36.9ms  words=27,328,512
[E03   241/1548 G   3336|CLM] train=3.9414  mask=17.3%  norm=1.663  lr=2.68e-04  dt=  36.8ms  words=27,336,704
[E03   242/1548 G   3337|CLM] train=4.6921  mask=17.3%  norm=1.357  lr=2.68e-04  dt=  37.0ms  words=27,344,896
[E03   243/1548 G   3338|CLM] train=3.0800  mask=17.3%  norm=1.005  lr=2.68e-04  dt=  37.0ms  words=27,353,088
[E03   244/1548 G   3339|CLM] train=4.1358  mask=17.3%  norm=0.978  lr=2.68e-04  dt=  36.8ms  words=27,361,280
[E03   245/1548 G   3340|CLM] train=4.7851  mask=17.3%  norm=0.779  lr=2.68e-04  dt=  37.0ms  words=27,369,472
[E03   246/1548 G   3341|CLM] train=4.0307  mask=17.3%  norm=0.862  lr=2.67e-04  dt=  37.0ms  words=27,377,664
[E03   247/1548 G   3342|CLM] train=5.2481  mask=17.3%  norm=0.833  lr=2.67e-04  dt=  36.9ms  words=27,385,856
[E03   248/1548 G   3343|CLM] train=4.2100  mask=17.3%  norm=0.817  lr=2.67e-04  dt=  36.9ms  words=27,394,048
[E03   249/1548 G   3344|CLM] train=5.1247  mask=17.3%  norm=0.775  lr=2.67e-04  dt=  37.2ms  words=27,402,240
[E03   250/1548 G   3345|CLM] train=2.0568  mask=17.3%  norm=1.168  lr=2.67e-04  dt=  37.1ms  words=27,410,432
[E03   251/1548 G   3346|CLM] train=4.2228  mask=17.3%  norm=0.829  lr=2.67e-04  dt=  37.4ms  words=27,418,624
[E03   252/1548 G   3347|CLM] train=4.5177  mask=17.3%  norm=0.692  lr=2.67e-04  dt=  37.3ms  words=27,426,816
[E03   253/1548 G   3348|CLM] train=5.7063  mask=17.3%  norm=2.646  lr=2.67e-04  dt=  37.2ms  words=27,435,008
[E03   254/1548 G   3349|CLM] train=4.2521  mask=17.3%  norm=0.762  lr=2.67e-04  dt=  37.0ms  words=27,443,200
[E03   255/1548 G   3350|CLM] train=4.6173  mask=17.3%  norm=0.803  lr=2.67e-04  dt=  36.9ms  words=27,451,392
[E03   256/1548 G   3351|CLM] train=4.4888  mask=17.3%  norm=0.627  lr=2.67e-04  dt=  37.0ms  words=27,459,584
[E03   257/1548 G   3352|CLM] train=2.8570  mask=17.3%  norm=0.985  lr=2.67e-04  dt=  37.0ms  words=27,467,776
[E03   258/1548 G   3353|CLM] train=5.0589  mask=17.3%  norm=0.850  lr=2.67e-04  dt=  36.9ms  words=27,475,968
[E03   259/1548 G   3354|CLM] train=4.9885  mask=17.3%  norm=0.792  lr=2.67e-04  dt=  36.9ms  words=27,484,160
[E03   260/1548 G   3355|CLM] train=2.5055  mask=17.3%  norm=1.237  lr=2.67e-04  dt=  36.9ms  words=27,492,352
[E03   261/1548 G   3356|CLM] train=2.6437  mask=17.3%  norm=0.934  lr=2.67e-04  dt=  37.1ms  words=27,500,544
[E03   262/1548 G   3357|CLM] train=2.5283  mask=17.3%  norm=0.900  lr=2.67e-04  dt=  36.8ms  words=27,508,736
[E03   263/1548 G   3358|CLM] train=2.5714  mask=17.3%  norm=0.709  lr=2.67e-04  dt=  36.8ms  words=27,516,928
[E03   264/1548 G   3359|CLM] train=5.4109  mask=17.3%  norm=0.788  lr=2.67e-04  dt=  37.0ms  words=27,525,120
[E03   265/1548 G   3360|CLM] train=4.8655  mask=17.3%  norm=0.816  lr=2.67e-04  dt=  37.0ms  words=27,533,312
[E03   266/1548 G   3361|CLM] train=4.2322  mask=17.3%  norm=0.948  lr=2.67e-04  dt=  36.9ms  words=27,541,504
[E03   267/1548 G   3362|CLM] train=4.6633  mask=17.3%  norm=0.833  lr=2.67e-04  dt=  36.8ms  words=27,549,696
[E03   268/1548 G   3363|CLM] train=2.7826  mask=17.3%  norm=0.771  lr=2.67e-04  dt=  36.9ms  words=27,557,888
[E03   269/1548 G   3364|CLM] train=3.9782  mask=17.3%  norm=0.674  lr=2.67e-04  dt=  37.0ms  words=27,566,080
[E03   270/1548 G   3365|CLM] train=3.9386  mask=17.3%  norm=0.668  lr=2.67e-04  dt=  36.8ms  words=27,574,272
[E03   271/1548 G   3366|CLM] train=4.9797  mask=17.3%  norm=0.888  lr=2.67e-04  dt=  36.9ms  words=27,582,464
[E03   272/1548 G   3367|CLM] train=5.0512  mask=17.3%  norm=0.879  lr=2.67e-04  dt=  37.0ms  words=27,590,656
[E03   273/1548 G   3368|CLM] train=4.7120  mask=17.3%  norm=0.668  lr=2.67e-04  dt=  36.9ms  words=27,598,848
[E03   274/1548 G   3369|CLM] train=4.8638  mask=17.3%  norm=0.644  lr=2.67e-04  dt=  36.9ms  words=27,607,040
[E03   275/1548 G   3370|CLM] train=2.5778  mask=17.3%  norm=1.042  lr=2.67e-04  dt=  36.9ms  words=27,615,232
[E03   276/1548 G   3371|CLM] train=2.6857  mask=17.3%  norm=0.992  lr=2.67e-04  dt=  36.9ms  words=27,623,424
[E03   277/1548 G   3372|CLM] train=4.3307  mask=17.3%  norm=0.885  lr=2.67e-04  dt=  37.0ms  words=27,631,616
[E03   278/1548 G   3373|CLM] train=4.0409  mask=17.3%  norm=1.111  lr=2.67e-04  dt=  36.8ms  words=27,639,808
[E03   279/1548 G   3374|CLM] train=5.0913  mask=17.3%  norm=2.432  lr=2.67e-04  dt=  37.2ms  words=27,648,000
[E03   280/1548 G   3375|CLM] train=4.4928  mask=17.3%  norm=0.785  lr=2.67e-04  dt=  36.9ms  words=27,656,192
[E03   281/1548 G   3376|CLM] train=3.8751  mask=17.3%  norm=0.613  lr=2.67e-04  dt=  36.9ms  words=27,664,384
[E03   282/1548 G   3377|CLM] train=4.8466  mask=17.3%  norm=0.907  lr=2.67e-04  dt=  36.7ms  words=27,672,576
[E03   283/1548 G   3378|CLM] train=5.0935  mask=17.3%  norm=0.761  lr=2.67e-04  dt=  36.7ms  words=27,680,768
[E03   284/1548 G   3379|CLM] train=4.7407  mask=17.3%  norm=0.750  lr=2.67e-04  dt=  36.9ms  words=27,688,960
[E03   285/1548 G   3380|CLM] train=2.6189  mask=17.3%  norm=1.283  lr=2.67e-04  dt=  37.0ms  words=27,697,152
[E03   286/1548 G   3381|CLM] train=4.2561  mask=17.3%  norm=0.805  lr=2.66e-04  dt=  36.9ms  words=27,705,344
[E03   287/1548 G   3382|CLM] train=4.6515  mask=17.3%  norm=0.695  lr=2.66e-04  dt=  36.9ms  words=27,713,536
[E03   288/1548 G   3383|CLM] train=4.1825  mask=17.3%  norm=1.192  lr=2.66e-04  dt=  36.9ms  words=27,721,728
[E03   289/1548 G   3384|CLM] train=4.0450  mask=17.3%  norm=0.704  lr=2.66e-04  dt=  37.1ms  words=27,729,920
[E03   290/1548 G   3385|CLM] train=4.4987  mask=17.3%  norm=0.695  lr=2.66e-04  dt=  36.9ms  words=27,738,112
[E03   291/1548 G   3386|CLM] train=4.2602  mask=17.3%  norm=0.685  lr=2.66e-04  dt=  36.9ms  words=27,746,304
[E03   292/1548 G   3387|CLM] train=2.6047  mask=17.3%  norm=0.951  lr=2.66e-04  dt=  36.9ms  words=27,754,496
[E03   293/1548 G   3388|CLM] train=5.3555  mask=17.3%  norm=0.823  lr=2.66e-04  dt=  37.1ms  words=27,762,688
[E03   294/1548 G   3389|CLM] train=2.5118  mask=17.3%  norm=0.941  lr=2.66e-04  dt=  36.7ms  words=27,770,880
[E03   295/1548 G   3390|CLM] train=2.7260  mask=17.3%  norm=1.615  lr=2.66e-04  dt=  36.8ms  words=27,779,072
[E03   296/1548 G   3391|CLM] train=3.1100  mask=17.3%  norm=0.571  lr=2.66e-04  dt=  36.9ms  words=27,787,264
[E03   297/1548 G   3392|CLM] train=2.6452  mask=17.3%  norm=0.973  lr=2.66e-04  dt=  37.0ms  words=27,795,456
[E03   298/1548 G   3393|CLM] train=2.6114  mask=17.3%  norm=0.944  lr=2.66e-04  dt=  37.0ms  words=27,803,648
[E03   299/1548 G   3394|CLM] train=2.8041  mask=17.3%  norm=0.665  lr=2.66e-04  dt=  36.9ms  words=27,811,840
[E03   300/1548 G   3395|CLM] train=4.3101  mask=17.3%  norm=0.826  lr=2.66e-04  dt=  36.9ms  words=27,820,032
[E03   301/1548 G   3396|CLM] train=4.5603  mask=17.3%  norm=0.805  lr=2.66e-04  dt=  37.1ms  words=27,828,224
[E03   302/1548 G   3397|CLM] train=5.1439  mask=17.3%  norm=0.971  lr=2.66e-04  dt=  36.9ms  words=27,836,416
[E03   303/1548 G   3398|CLM] train=4.8331  mask=17.3%  norm=1.186  lr=2.66e-04  dt=  36.8ms  words=27,844,608
[E03   304/1548 G   3399|CLM] train=2.8003  mask=17.3%  norm=0.750  lr=2.66e-04  dt=  36.9ms  words=27,852,800
[E03   305/1548 G   3400|CLM] train=2.9965  mask=17.3%  norm=0.778  lr=2.66e-04  dt=  37.0ms  words=27,860,992
[E03   306/1548 G   3401|CLM] train=4.9053  mask=17.3%  norm=0.929  lr=2.66e-04  dt=  36.9ms  words=27,869,184
[E03   307/1548 G   3402|CLM] train=4.6930  mask=17.3%  norm=0.843  lr=2.66e-04  dt=  36.9ms  words=27,877,376
[E03   308/1548 G   3403|CLM] train=2.6795  mask=17.3%  norm=1.006  lr=2.66e-04  dt=  36.9ms  words=27,885,568
[E03   309/1548 G   3404|CLM] train=2.9425  mask=17.3%  norm=0.578  lr=2.66e-04  dt=  37.0ms  words=27,893,760
[E03   310/1548 G   3405|CLM] train=2.6514  mask=17.3%  norm=0.598  lr=2.66e-04  dt=  36.9ms  words=27,901,952
[E03   311/1548 G   3406|CLM] train=4.6365  mask=17.2%  norm=0.743  lr=2.66e-04  dt=  36.9ms  words=27,910,144
[E03   312/1548 G   3407|CLM] train=5.2764  mask=17.2%  norm=1.081  lr=2.66e-04  dt=  36.9ms  words=27,918,336
[E03   313/1548 G   3408|CLM] train=3.3390  mask=17.2%  norm=1.286  lr=2.66e-04  dt=  37.0ms  words=27,926,528
[E03   314/1548 G   3409|CLM] train=4.2376  mask=17.2%  norm=0.859  lr=2.66e-04  dt=  36.9ms  words=27,934,720
[E03   315/1548 G   3410|CLM] train=3.8192  mask=17.2%  norm=0.777  lr=2.66e-04  dt=  36.8ms  words=27,942,912
[E03   316/1548 G   3411|CLM] train=4.2524  mask=17.2%  norm=0.977  lr=2.66e-04  dt=  37.0ms  words=27,951,104
[E03   317/1548 G   3412|CLM] train=4.4991  mask=17.2%  norm=0.853  lr=2.66e-04  dt=  37.1ms  words=27,959,296
[E03   318/1548 G   3413|CLM] train=4.0592  mask=17.2%  norm=0.585  lr=2.66e-04  dt=  36.9ms  words=27,967,488
[E03   319/1548 G   3414|CLM] train=4.6427  mask=17.2%  norm=0.741  lr=2.66e-04  dt=  36.9ms  words=27,975,680
[E03   320/1548 G   3415|CLM] train=4.3939  mask=17.2%  norm=0.836  lr=2.66e-04  dt=  37.0ms  words=27,983,872
[E03   321/1548 G   3416|CLM] train=4.5804  mask=17.2%  norm=0.751  lr=2.66e-04  dt=  37.3ms  words=27,992,064
[E03   322/1548 G   3417|CLM] train=2.6644  mask=17.2%  norm=0.848  lr=2.66e-04  dt=  50.8ms  words=28,000,256
[E03   323/1548 G   3418|CLM] train=4.5854  mask=17.2%  norm=0.890  lr=2.66e-04  dt=  43.3ms  words=28,008,448
[E03   324/1548 G   3419|CLM] train=2.8244  mask=17.2%  norm=0.962  lr=2.66e-04  dt=  42.0ms  words=28,016,640
[E03   325/1548 G   3420|CLM] train=5.2705  mask=17.2%  norm=0.791  lr=2.66e-04  dt=  49.6ms  words=28,024,832
[E03   326/1548 G   3421|CLM] train=2.8167  mask=17.2%  norm=0.722  lr=2.65e-04  dt=  42.4ms  words=28,033,024
[E03   327/1548 G   3422|CLM] train=4.7222  mask=17.2%  norm=0.767  lr=2.65e-04  dt=  41.4ms  words=28,041,216
[E03   328/1548 G   3423|CLM] train=2.6910  mask=17.2%  norm=0.757  lr=2.65e-04  dt=  41.3ms  words=28,049,408
[E03   329/1548 G   3424|CLM] train=4.5348  mask=17.2%  norm=1.377  lr=2.65e-04  dt=  37.8ms  words=28,057,600
[E03   330/1548 G   3425|CLM] train=4.3578  mask=17.2%  norm=0.701  lr=2.65e-04  dt=  37.5ms  words=28,065,792
[E03   331/1548 G   3426|CLM] train=4.7673  mask=17.2%  norm=0.978  lr=2.65e-04  dt=  37.3ms  words=28,073,984
[E03   332/1548 G   3427|CLM] train=4.8997  mask=17.2%  norm=0.859  lr=2.65e-04  dt=  37.3ms  words=28,082,176
[E03   333/1548 G   3428|CLM] train=4.8830  mask=17.2%  norm=0.685  lr=2.65e-04  dt=  39.1ms  words=28,090,368
[E03   334/1548 G   3429|CLM] train=2.1827  mask=17.2%  norm=1.039  lr=2.65e-04  dt=  41.4ms  words=28,098,560
[E03   335/1548 G   3430|CLM] train=4.2552  mask=17.2%  norm=0.744  lr=2.65e-04  dt=  37.3ms  words=28,106,752
[E03   336/1548 G   3431|CLM] train=3.0005  mask=17.2%  norm=1.076  lr=2.65e-04  dt=  37.2ms  words=28,114,944
[E03   337/1548 G   3432|CLM] train=2.7451  mask=17.2%  norm=0.929  lr=2.65e-04  dt=  37.4ms  words=28,123,136
[E03   338/1548 G   3433|CLM] train=2.6681  mask=17.2%  norm=0.930  lr=2.65e-04  dt=  37.2ms  words=28,131,328
[E03   339/1548 G   3434|CLM] train=4.4295  mask=17.2%  norm=0.713  lr=2.65e-04  dt=  37.6ms  words=28,139,520
[E03   340/1548 G   3435|CLM] train=2.6360  mask=17.2%  norm=1.023  lr=2.65e-04  dt=  37.6ms  words=28,147,712
[E03   341/1548 G   3436|CLM] train=2.7922  mask=17.2%  norm=0.627  lr=2.65e-04  dt=  37.7ms  words=28,155,904
[E03   342/1548 G   3437|CLM] train=2.4781  mask=17.2%  norm=0.667  lr=2.65e-04  dt=  40.3ms  words=28,164,096
[E03   343/1548 G   3438|CLM] train=2.6891  mask=17.2%  norm=0.690  lr=2.65e-04  dt=  38.8ms  words=28,172,288
[E03   344/1548 G   3439|CLM] train=5.3207  mask=17.2%  norm=0.971  lr=2.65e-04  dt=  37.4ms  words=28,180,480
[E03   345/1548 G   3440|CLM] train=4.2279  mask=17.2%  norm=0.698  lr=2.65e-04  dt=  37.4ms  words=28,188,672
[E03   346/1548 G   3441|CLM] train=4.3326  mask=17.2%  norm=0.615  lr=2.65e-04  dt=  37.7ms  words=28,196,864
[E03   347/1548 G   3442|CLM] train=2.8056  mask=17.2%  norm=1.203  lr=2.65e-04  dt=  38.4ms  words=28,205,056
[E03   348/1548 G   3443|CLM] train=5.0022  mask=17.2%  norm=0.751  lr=2.65e-04  dt=  37.5ms  words=28,213,248
[E03   349/1548 G   3444|CLM] train=4.5044  mask=17.2%  norm=0.615  lr=2.65e-04  dt=  47.7ms  words=28,221,440
[E03   350/1548 G   3445|CLM] train=4.2569  mask=17.2%  norm=0.775  lr=2.65e-04  dt=  42.5ms  words=28,229,632
[E03   351/1548 G   3446|CLM] train=4.9733  mask=17.2%  norm=0.926  lr=2.65e-04  dt=  37.3ms  words=28,237,824
[E03   352/1548 G   3447|CLM] train=3.8890  mask=17.2%  norm=0.686  lr=2.65e-04  dt=  37.1ms  words=28,246,016
[E03   353/1548 G   3448|CLM] train=4.2697  mask=17.2%  norm=0.624  lr=2.65e-04  dt=  37.4ms  words=28,254,208
[E03   354/1548 G   3449|CLM] train=4.1490  mask=17.2%  norm=0.750  lr=2.65e-04  dt=  37.2ms  words=28,262,400
[E03   355/1548 G   3450|CLM] train=2.4747  mask=17.2%  norm=0.800  lr=2.65e-04  dt=  38.4ms  words=28,270,592
[E03   356/1548 G   3451|CLM] train=4.2320  mask=17.2%  norm=0.714  lr=2.65e-04  dt=  37.8ms  words=28,278,784
[E03   357/1548 G   3452|CLM] train=5.7849  mask=17.2%  norm=1.281  lr=2.65e-04  dt=  37.5ms  words=28,286,976
[E03   358/1548 G   3453|CLM] train=4.4780  mask=17.2%  norm=1.332  lr=2.65e-04  dt=  37.1ms  words=28,295,168
[E03   359/1548 G   3454|CLM] train=2.4470  mask=17.2%  norm=0.722  lr=2.65e-04  dt=  39.2ms  words=28,303,360
[E03   360/1548 G   3455|CLM] train=4.8913  mask=17.2%  norm=0.906  lr=2.65e-04  dt=  43.9ms  words=28,311,552
[E03   361/1548 G   3456|CLM] train=2.8805  mask=17.2%  norm=1.754  lr=2.65e-04  dt=  42.8ms  words=28,319,744
[E03   362/1548 G   3457|CLM] train=4.1733  mask=17.2%  norm=0.683  lr=2.65e-04  dt=  41.6ms  words=28,327,936
[E03   363/1548 G   3458|CLM] train=2.8254  mask=17.2%  norm=0.974  lr=2.65e-04  dt=  40.7ms  words=28,336,128
[E03   364/1548 G   3459|CLM] train=5.0591  mask=17.2%  norm=1.084  lr=2.65e-04  dt=  37.6ms  words=28,344,320
[E03   365/1548 G   3460|CLM] train=2.4206  mask=17.2%  norm=0.648  lr=2.65e-04  dt=  41.6ms  words=28,352,512
[E03   366/1548 G   3461|CLM] train=5.7069  mask=17.2%  norm=1.043  lr=2.64e-04  dt=  47.4ms  words=28,360,704
[E03   367/1548 G   3462|CLM] train=5.0487  mask=17.2%  norm=1.055  lr=2.64e-04  dt=  39.5ms  words=28,368,896
[E03   368/1548 G   3463|CLM] train=5.0637  mask=17.2%  norm=1.199  lr=2.64e-04  dt=  36.8ms  words=28,377,088
[E03   369/1548 G   3464|CLM] train=2.5923  mask=17.2%  norm=0.759  lr=2.64e-04  dt=  37.2ms  words=28,385,280
[E03   370/1548 G   3465|CLM] train=4.1266  mask=17.2%  norm=0.797  lr=2.64e-04  dt=  37.0ms  words=28,393,472
[E03   371/1548 G   3466|CLM] train=3.9653  mask=17.2%  norm=0.756  lr=2.64e-04  dt=  37.2ms  words=28,401,664
[E03   372/1548 G   3467|CLM] train=2.8044  mask=17.2%  norm=0.813  lr=2.64e-04  dt=  37.0ms  words=28,409,856
[E03   373/1548 G   3468|CLM] train=4.7866  mask=17.2%  norm=0.668  lr=2.64e-04  dt=  37.1ms  words=28,418,048
[E03   374/1548 G   3469|CLM] train=4.0474  mask=17.2%  norm=0.655  lr=2.64e-04  dt=  36.9ms  words=28,426,240
[E03   375/1548 G   3470|CLM] train=2.6839  mask=17.2%  norm=0.634  lr=2.64e-04  dt=  37.0ms  words=28,434,432
[E03   376/1548 G   3471|CLM] train=2.8852  mask=17.2%  norm=1.095  lr=2.64e-04  dt=  36.8ms  words=28,442,624
[E03   377/1548 G   3472|CLM] train=2.8158  mask=17.2%  norm=0.622  lr=2.64e-04  dt=  37.1ms  words=28,450,816
[E03   378/1548 G   3473|CLM] train=2.6291  mask=17.2%  norm=0.637  lr=2.64e-04  dt=  36.8ms  words=28,459,008
[E03   379/1548 G   3474|CLM] train=4.7913  mask=17.2%  norm=0.839  lr=2.64e-04  dt=  36.9ms  words=28,467,200
[E03   380/1548 G   3475|CLM] train=4.3237  mask=17.2%  norm=0.857  lr=2.64e-04  dt=  36.8ms  words=28,475,392
[E03   381/1548 G   3476|CLM] train=4.7664  mask=17.2%  norm=0.826  lr=2.64e-04  dt=  37.1ms  words=28,483,584
[E03   382/1548 G   3477|CLM] train=2.6173  mask=17.2%  norm=0.607  lr=2.64e-04  dt=  36.8ms  words=28,491,776
[E03   383/1548 G   3478|CLM] train=2.6077  mask=17.2%  norm=1.213  lr=2.64e-04  dt=  36.9ms  words=28,499,968
[E03   384/1548 G   3479|CLM] train=4.6412  mask=17.2%  norm=1.106  lr=2.64e-04  dt=  37.0ms  words=28,508,160
[E03   385/1548 G   3480|CLM] train=2.4536  mask=17.2%  norm=0.628  lr=2.64e-04  dt=  37.2ms  words=28,516,352
[E03   386/1548 G   3481|CLM] train=4.6549  mask=17.2%  norm=0.989  lr=2.64e-04  dt=  36.8ms  words=28,524,544
[E03   387/1548 G   3482|CLM] train=2.8137  mask=17.2%  norm=0.649  lr=2.64e-04  dt=  36.9ms  words=28,532,736
[E03   388/1548 G   3483|CLM] train=2.5699  mask=17.2%  norm=0.700  lr=2.64e-04  dt=  36.8ms  words=28,540,928
[E03   389/1548 G   3484|CLM] train=4.9270  mask=17.2%  norm=0.635  lr=2.64e-04  dt=  36.8ms  words=28,549,120
[E03   390/1548 G   3485|CLM] train=2.8899  mask=17.2%  norm=0.835  lr=2.64e-04  dt=  36.8ms  words=28,557,312
[E03   391/1548 G   3486|CLM] train=2.7351  mask=17.2%  norm=0.632  lr=2.64e-04  dt=  36.9ms  words=28,565,504
[E03   392/1548 G   3487|CLM] train=4.7676  mask=17.2%  norm=0.770  lr=2.64e-04  dt=  36.8ms  words=28,573,696
[E03   393/1548 G   3488|CLM] train=2.4848  mask=17.2%  norm=0.645  lr=2.64e-04  dt=  37.0ms  words=28,581,888
[E03   394/1548 G   3489|CLM] train=5.0551  mask=17.2%  norm=0.782  lr=2.64e-04  dt=  37.0ms  words=28,590,080
[E03   395/1548 G   3490|CLM] train=2.6259  mask=17.2%  norm=1.166  lr=2.64e-04  dt=  36.9ms  words=28,598,272
[E03   396/1548 G   3491|CLM] train=4.6219  mask=17.2%  norm=0.979  lr=2.64e-04  dt=  36.8ms  words=28,606,464
[E03   397/1548 G   3492|CLM] train=4.3232  mask=17.2%  norm=0.857  lr=2.64e-04  dt=  37.0ms  words=28,614,656
[E03   398/1548 G   3493|CLM] train=4.5450  mask=17.2%  norm=0.865  lr=2.64e-04  dt=  36.8ms  words=28,622,848
[E03   399/1548 G   3494|CLM] train=2.8498  mask=17.2%  norm=0.776  lr=2.64e-04  dt=  36.9ms  words=28,631,040
[E03   400/1548 G   3495|CLM] train=4.5211  mask=17.2%  norm=0.761  lr=2.64e-04  dt=  37.0ms  words=28,639,232
[E03   401/1548 G   3496|CLM] train=5.8598  mask=17.2%  norm=0.922  lr=2.64e-04  dt=  36.7ms  words=28,647,424
[E03   402/1548 G   3497|CLM] train=4.2890  mask=17.2%  norm=0.699  lr=2.64e-04  dt=  37.1ms  words=28,655,616
[E03   403/1548 G   3498|CLM] train=2.7105  mask=17.2%  norm=0.928  lr=2.64e-04  dt=  36.8ms  words=28,663,808
[E03   404/1548 G   3499|CLM] train=4.3781  mask=17.2%  norm=0.668  lr=2.63e-04  dt=  36.9ms  words=28,672,000
[E03   405/1548 G   3500|CLM] train=4.5232  mask=17.2%  norm=0.662  lr=2.63e-04  dt=  37.1ms  words=28,680,192
[E03   406/1548 G   3501|CLM] train=3.0632  mask=17.2%  norm=1.217  lr=2.63e-04  dt=  36.8ms  words=28,688,384
[E03   407/1548 G   3502|CLM] train=2.7121  mask=17.2%  norm=0.899  lr=2.63e-04  dt=  37.0ms  words=28,696,576
[E03   408/1548 G   3503|CLM] train=2.7466  mask=17.2%  norm=0.898  lr=2.63e-04  dt=  36.7ms  words=28,704,768
[E03   409/1548 G   3504|CLM] train=4.3644  mask=17.2%  norm=0.756  lr=2.63e-04  dt=  36.9ms  words=28,712,960
[E03   410/1548 G   3505|CLM] train=2.6450  mask=17.2%  norm=0.681  lr=2.63e-04  dt=  37.0ms  words=28,721,152
[E03   411/1548 G   3506|CLM] train=2.7543  mask=17.2%  norm=0.672  lr=2.63e-04  dt=  36.9ms  words=28,729,344
[E03   412/1548 G   3507|CLM] train=2.6305  mask=17.2%  norm=0.872  lr=2.63e-04  dt=  37.2ms  words=28,737,536
[E03   413/1548 G   3508|CLM] train=4.6705  mask=17.2%  norm=0.716  lr=2.63e-04  dt=  37.1ms  words=28,745,728
[E03   414/1548 G   3509|CLM] train=4.6667  mask=17.2%  norm=0.959  lr=2.63e-04  dt=  36.9ms  words=28,753,920
[E03   415/1548 G   3510|CLM] train=4.4154  mask=17.2%  norm=0.661  lr=2.63e-04  dt=  36.9ms  words=28,762,112
[E03   416/1548 G   3511|CLM] train=5.2146  mask=17.2%  norm=0.651  lr=2.63e-04  dt=  36.8ms  words=28,770,304
[E03   417/1548 G   3512|CLM] train=2.4024  mask=17.2%  norm=0.738  lr=2.63e-04  dt=  36.9ms  words=28,778,496
[E03   418/1548 G   3513|CLM] train=2.4201  mask=17.2%  norm=0.641  lr=2.63e-04  dt=  36.8ms  words=28,786,688
[E03   419/1548 G   3514|CLM] train=4.4113  mask=17.2%  norm=0.764  lr=2.63e-04  dt=  36.9ms  words=28,794,880
[E03   420/1548 G   3515|CLM] train=3.0302  mask=17.2%  norm=0.853  lr=2.63e-04  dt=  36.8ms  words=28,803,072
[E03   421/1548 G   3516|CLM] train=3.0111  mask=17.2%  norm=0.816  lr=2.63e-04  dt=  37.0ms  words=28,811,264
[E03   422/1548 G   3517|CLM] train=2.6175  mask=17.2%  norm=0.655  lr=2.63e-04  dt=  37.0ms  words=28,819,456
[E03   423/1548 G   3518|CLM] train=2.6242  mask=17.2%  norm=0.717  lr=2.63e-04  dt=  36.9ms  words=28,827,648
[E03   424/1548 G   3519|CLM] train=5.1188  mask=17.2%  norm=0.784  lr=2.63e-04  dt=  37.0ms  words=28,835,840
[E03   425/1548 G   3520|CLM] train=2.6105  mask=17.2%  norm=0.647  lr=2.63e-04  dt=  37.1ms  words=28,844,032
[E03   426/1548 G   3521|CLM] train=4.4149  mask=17.2%  norm=0.672  lr=2.63e-04  dt=  36.7ms  words=28,852,224
[E03   427/1548 G   3522|CLM] train=3.2956  mask=17.2%  norm=0.613  lr=2.63e-04  dt=  37.0ms  words=28,860,416
[E03   428/1548 G   3523|CLM] train=5.0563  mask=17.2%  norm=1.075  lr=2.63e-04  dt=  36.9ms  words=28,868,608
[E03   429/1548 G   3524|CLM] train=4.2215  mask=17.2%  norm=0.689  lr=2.63e-04  dt=  36.8ms  words=28,876,800
[E03   430/1548 G   3525|CLM] train=4.9798  mask=17.2%  norm=0.759  lr=2.63e-04  dt=  37.0ms  words=28,884,992
[E03   431/1548 G   3526|CLM] train=2.6805  mask=17.2%  norm=0.945  lr=2.63e-04  dt=  36.9ms  words=28,893,184
[E03   432/1548 G   3527|CLM] train=5.4645  mask=17.2%  norm=1.103  lr=2.63e-04  dt=  36.8ms  words=28,901,376
[E03   433/1548 G   3528|CLM] train=2.9324  mask=17.2%  norm=0.648  lr=2.63e-04  dt=  36.9ms  words=28,909,568
[E03   434/1548 G   3529|CLM] train=4.7663  mask=17.2%  norm=0.655  lr=2.63e-04  dt=  37.0ms  words=28,917,760
[E03   435/1548 G   3530|CLM] train=2.5434  mask=17.1%  norm=0.751  lr=2.63e-04  dt=  36.9ms  words=28,925,952
[E03   436/1548 G   3531|CLM] train=4.4939  mask=17.1%  norm=0.674  lr=2.63e-04  dt=  37.0ms  words=28,934,144
[E03   437/1548 G   3532|CLM] train=4.6299  mask=17.1%  norm=0.657  lr=2.63e-04  dt=  37.0ms  words=28,942,336
[E03   438/1548 G   3533|CLM] train=3.7180  mask=17.1%  norm=0.714  lr=2.63e-04  dt=  37.1ms  words=28,950,528
[E03   439/1548 G   3534|CLM] train=2.7713  mask=17.1%  norm=0.746  lr=2.63e-04  dt=  36.9ms  words=28,958,720
[E03   440/1548 G   3535|CLM] train=4.4446  mask=17.1%  norm=0.579  lr=2.63e-04  dt=  36.9ms  words=28,966,912
[E03   441/1548 G   3536|CLM] train=2.6351  mask=17.1%  norm=0.770  lr=2.63e-04  dt=  36.9ms  words=28,975,104
[E03   442/1548 G   3537|CLM] train=4.6274  mask=17.1%  norm=0.621  lr=2.63e-04  dt=  36.8ms  words=28,983,296
[E03   443/1548 G   3538|CLM] train=2.3291  mask=17.1%  norm=0.816  lr=2.62e-04  dt=  36.9ms  words=28,991,488
[E03   444/1548 G   3539|CLM] train=4.7714  mask=17.1%  norm=0.822  lr=2.62e-04  dt=  36.7ms  words=28,999,680
[E03   445/1548 G   3540|CLM] train=5.3427  mask=17.1%  norm=1.160  lr=2.62e-04  dt=  36.9ms  words=29,007,872
[E03   446/1548 G   3541|CLM] train=2.4824  mask=17.1%  norm=0.603  lr=2.62e-04  dt=  37.0ms  words=29,016,064
[E03   447/1548 G   3542|CLM] train=2.6121  mask=17.1%  norm=0.784  lr=2.62e-04  dt=  36.9ms  words=29,024,256
[E03   448/1548 G   3543|CLM] train=2.3721  mask=17.1%  norm=0.487  lr=2.62e-04  dt=  36.9ms  words=29,032,448
[E03   449/1548 G   3544|CLM] train=4.8383  mask=17.1%  norm=0.703  lr=2.62e-04  dt=  37.0ms  words=29,040,640
[E03   450/1548 G   3545|CLM] train=2.3473  mask=17.1%  norm=0.830  lr=2.62e-04  dt=  37.0ms  words=29,048,832
[E03   451/1548 G   3546|CLM] train=4.2259  mask=17.1%  norm=0.701  lr=2.62e-04  dt=  36.9ms  words=29,057,024
[E03   452/1548 G   3547|CLM] train=2.7518  mask=17.1%  norm=0.919  lr=2.62e-04  dt=  37.0ms  words=29,065,216
[E03   453/1548 G   3548|CLM] train=4.1446  mask=17.1%  norm=0.815  lr=2.62e-04  dt=  38.2ms  words=29,073,408
[E03   454/1548 G   3549|CLM] train=2.5332  mask=17.1%  norm=0.975  lr=2.62e-04  dt=  37.1ms  words=29,081,600
[E03   455/1548 G   3550|CLM] train=2.6397  mask=17.1%  norm=0.669  lr=2.62e-04  dt=  36.9ms  words=29,089,792
[E03   456/1548 G   3551|CLM] train=4.2359  mask=17.1%  norm=0.593  lr=2.62e-04  dt=  36.9ms  words=29,097,984
[E03   457/1548 G   3552|CLM] train=3.1756  mask=17.1%  norm=1.033  lr=2.62e-04  dt=  37.5ms  words=29,106,176
[E03   458/1548 G   3553|CLM] train=5.0135  mask=17.1%  norm=0.982  lr=2.62e-04  dt=  37.6ms  words=29,114,368
[E03   459/1548 G   3554|CLM] train=2.6525  mask=17.1%  norm=0.889  lr=2.62e-04  dt=  37.2ms  words=29,122,560
[E03   460/1548 G   3555|CLM] train=3.7532  mask=17.1%  norm=0.633  lr=2.62e-04  dt=  37.2ms  words=29,130,752
[E03   461/1548 G   3556|CLM] train=2.7141  mask=17.1%  norm=0.664  lr=2.62e-04  dt=  37.0ms  words=29,138,944
[E03   462/1548 G   3557|CLM] train=4.3009  mask=17.1%  norm=0.917  lr=2.62e-04  dt=  37.0ms  words=29,147,136
[E03   463/1548 G   3558|CLM] train=3.1062  mask=17.1%  norm=0.667  lr=2.62e-04  dt=  37.0ms  words=29,155,328
[E03   464/1548 G   3559|CLM] train=2.7697  mask=17.1%  norm=0.638  lr=2.62e-04  dt=  37.4ms  words=29,163,520
[E03   465/1548 G   3560|CLM] train=2.5663  mask=17.1%  norm=0.820  lr=2.62e-04  dt=  37.2ms  words=29,171,712
[E03   466/1548 G   3561|CLM] train=2.5259  mask=17.1%  norm=0.807  lr=2.62e-04  dt=  37.4ms  words=29,179,904
[E03   467/1548 G   3562|CLM] train=2.6007  mask=17.1%  norm=0.751  lr=2.62e-04  dt=  37.2ms  words=29,188,096
[E03   468/1548 G   3563|CLM] train=4.1607  mask=17.1%  norm=0.688  lr=2.62e-04  dt=  37.0ms  words=29,196,288
[E03   469/1548 G   3564|CLM] train=4.5104  mask=17.1%  norm=0.897  lr=2.62e-04  dt=  37.0ms  words=29,204,480
[E03   470/1548 G   3565|CLM] train=4.2314  mask=17.1%  norm=0.840  lr=2.62e-04  dt=  36.8ms  words=29,212,672
[E03   471/1548 G   3566|CLM] train=5.3840  mask=17.1%  norm=1.054  lr=2.62e-04  dt=  37.2ms  words=29,220,864
[E03   472/1548 G   3567|CLM] train=2.4547  mask=17.1%  norm=1.091  lr=2.62e-04  dt=  36.9ms  words=29,229,056
[E03   473/1548 G   3568|CLM] train=2.6313  mask=17.1%  norm=1.099  lr=2.62e-04  dt=  36.9ms  words=29,237,248
[E03   474/1548 G   3569|CLM] train=2.6593  mask=17.1%  norm=0.792  lr=2.62e-04  dt=  36.9ms  words=29,245,440
[E03   475/1548 G   3570|CLM] train=4.6316  mask=17.1%  norm=0.676  lr=2.62e-04  dt=  36.8ms  words=29,253,632
[E03   476/1548 G   3571|CLM] train=4.1239  mask=17.1%  norm=0.616  lr=2.62e-04  dt=  36.9ms  words=29,261,824
[E03   477/1548 G   3572|CLM] train=4.0413  mask=17.1%  norm=0.808  lr=2.62e-04  dt=  36.9ms  words=29,270,016
[E03   478/1548 G   3573|CLM] train=4.4671  mask=17.1%  norm=0.648  lr=2.62e-04  dt=  37.1ms  words=29,278,208
[E03   479/1548 G   3574|CLM] train=2.5672  mask=17.1%  norm=1.569  lr=2.62e-04  dt=  36.9ms  words=29,286,400
[E03   480/1548 G   3575|CLM] train=4.9219  mask=17.1%  norm=0.801  lr=2.62e-04  dt=  36.8ms  words=29,294,592
[E03   481/1548 G   3576|CLM] train=4.1267  mask=17.1%  norm=0.739  lr=2.61e-04  dt=  36.9ms  words=29,302,784
[E03   482/1548 G   3577|CLM] train=5.2821  mask=17.1%  norm=0.787  lr=2.61e-04  dt=  36.9ms  words=29,310,976
[E03   483/1548 G   3578|CLM] train=2.9706  mask=17.1%  norm=0.825  lr=2.61e-04  dt=  36.7ms  words=29,319,168
[E03   484/1548 G   3579|CLM] train=4.2005  mask=17.1%  norm=0.756  lr=2.61e-04  dt=  36.9ms  words=29,327,360
[E03   485/1548 G   3580|CLM] train=2.7017  mask=17.1%  norm=0.853  lr=2.61e-04  dt=  36.9ms  words=29,335,552
[E03   486/1548 G   3581|CLM] train=2.8499  mask=17.1%  norm=0.731  lr=2.61e-04  dt=  37.0ms  words=29,343,744
[E03   487/1548 G   3582|CLM] train=2.8458  mask=17.1%  norm=0.673  lr=2.61e-04  dt=  36.9ms  words=29,351,936
[E03   488/1548 G   3583|CLM] train=5.8362  mask=17.1%  norm=1.274  lr=2.61e-04  dt=  36.9ms  words=29,360,128
[E03   489/1548 G   3584|CLM] train=2.4611  mask=17.1%  norm=0.672  lr=2.61e-04  dt=  36.9ms  words=29,368,320
[E03   490/1548 G   3585|CLM] train=4.2704  mask=17.1%  norm=0.748  lr=2.61e-04  dt=  36.8ms  words=29,376,512
[E03   491/1548 G   3586|CLM] train=4.5891  mask=17.1%  norm=0.696  lr=2.61e-04  dt=  36.9ms  words=29,384,704
[E03   492/1548 G   3587|CLM] train=2.4147  mask=17.1%  norm=0.889  lr=2.61e-04  dt=  37.1ms  words=29,392,896
[E03   493/1548 G   3588|CLM] train=4.5631  mask=17.1%  norm=0.763  lr=2.61e-04  dt=  37.1ms  words=29,401,088
[E03   494/1548 G   3589|CLM] train=4.7565  mask=17.1%  norm=0.716  lr=2.61e-04  dt=  37.1ms  words=29,409,280
[E03   495/1548 G   3590|CLM] train=4.5397  mask=17.1%  norm=0.669  lr=2.61e-04  dt=  37.0ms  words=29,417,472
[E03   496/1548 G   3591|CLM] train=3.0256  mask=17.1%  norm=0.769  lr=2.61e-04  dt=  37.0ms  words=29,425,664
[E03   497/1548 G   3592|CLM] train=5.1060  mask=17.1%  norm=0.975  lr=2.61e-04  dt=  37.0ms  words=29,433,856
[E03   498/1548 G   3593|CLM] train=4.2274  mask=17.1%  norm=0.733  lr=2.61e-04  dt=  36.9ms  words=29,442,048
[E03   499/1548 G   3594|CLM] train=2.9501  mask=17.1%  norm=0.648  lr=2.61e-04  dt=  37.0ms  words=29,450,240
[E03   500/1548 G   3595|CLM] train=4.2137  mask=17.1%  norm=0.744  lr=2.61e-04  dt=  36.9ms  words=29,458,432
[E03   501/1548 G   3596|CLM] train=4.4996  mask=17.1%  norm=0.678  lr=2.61e-04  dt=  37.1ms  words=29,466,624
[E03   502/1548 G   3597|CLM] train=2.4760  mask=17.1%  norm=1.019  lr=2.61e-04  dt=  36.9ms  words=29,474,816
[E03   503/1548 G   3598|CLM] train=5.4417  mask=17.1%  norm=1.401  lr=2.61e-04  dt=  37.0ms  words=29,483,008
[E03   504/1548 G   3599|CLM] train=2.6582  mask=17.1%  norm=1.130  lr=2.61e-04  dt=  36.9ms  words=29,491,200
[E03   505/1548 G   3600|CLM] train=2.5682  mask=17.1%  norm=0.827  lr=2.61e-04  dt=  37.0ms  words=29,499,392
[E03   506/1548 G   3601|CLM] train=2.8147  mask=17.1%  norm=0.915  lr=2.61e-04  dt=  37.1ms  words=29,507,584
[E03   507/1548 G   3602|CLM] train=4.4492  mask=17.1%  norm=0.819  lr=2.61e-04  dt=  37.1ms  words=29,515,776
[E03   508/1548 G   3603|CLM] train=2.4670  mask=17.1%  norm=0.643  lr=2.61e-04  dt=  37.1ms  words=29,523,968
[E03   509/1548 G   3604|CLM] train=2.3852  mask=17.1%  norm=0.573  lr=2.61e-04  dt=  37.1ms  words=29,532,160
[E03   510/1548 G   3605|CLM] train=4.1917  mask=17.1%  norm=0.706  lr=2.61e-04  dt=  36.9ms  words=29,540,352
[E03   511/1548 G   3606|CLM] train=4.9147  mask=17.1%  norm=0.886  lr=2.61e-04  dt=  37.0ms  words=29,548,544
[E03   512/1548 G   3607|CLM] train=2.4556  mask=17.1%  norm=0.804  lr=2.61e-04  dt=  37.1ms  words=29,556,736
[E03   513/1548 G   3608|CLM] train=2.8161  mask=17.1%  norm=0.670  lr=2.61e-04  dt=  36.8ms  words=29,564,928
[E03   514/1548 G   3609|CLM] train=3.0850  mask=17.1%  norm=0.737  lr=2.61e-04  dt=  36.9ms  words=29,573,120
[E03   515/1548 G   3610|CLM] train=4.0107  mask=17.1%  norm=0.695  lr=2.61e-04  dt=  36.9ms  words=29,581,312
[E03   516/1548 G   3611|CLM] train=2.4815  mask=17.1%  norm=0.896  lr=2.61e-04  dt=  37.1ms  words=29,589,504
[E03   517/1548 G   3612|CLM] train=2.4269  mask=17.1%  norm=0.935  lr=2.61e-04  dt=  37.0ms  words=29,597,696
[E03   518/1548 G   3613|CLM] train=2.5025  mask=17.1%  norm=0.696  lr=2.61e-04  dt=  37.1ms  words=29,605,888
[E03   519/1548 G   3614|CLM] train=2.4883  mask=17.1%  norm=0.730  lr=2.60e-04  dt=  37.3ms  words=29,614,080
[E03   520/1548 G   3615|CLM] train=4.7010  mask=17.1%  norm=1.060  lr=2.60e-04  dt=  37.1ms  words=29,622,272
[E03   521/1548 G   3616|CLM] train=4.9600  mask=17.1%  norm=1.105  lr=2.60e-04  dt=  36.9ms  words=29,630,464
[E03   522/1548 G   3617|CLM] train=2.4738  mask=17.1%  norm=0.730  lr=2.60e-04  dt=  36.9ms  words=29,638,656
[E03   523/1548 G   3618|CLM] train=2.4355  mask=17.1%  norm=1.047  lr=2.60e-04  dt=  37.1ms  words=29,646,848
[E03   524/1548 G   3619|CLM] train=4.5499  mask=17.1%  norm=0.810  lr=2.60e-04  dt=  36.8ms  words=29,655,040
[E03   525/1548 G   3620|CLM] train=2.4011  mask=17.1%  norm=0.778  lr=2.60e-04  dt=  36.9ms  words=29,663,232
[E03   526/1548 G   3621|CLM] train=4.8156  mask=17.1%  norm=0.843  lr=2.60e-04  dt=  36.9ms  words=29,671,424
[E03   527/1548 G   3622|CLM] train=2.4805  mask=17.1%  norm=0.637  lr=2.60e-04  dt=  37.1ms  words=29,679,616
[E03   528/1548 G   3623|CLM] train=2.4479  mask=17.1%  norm=0.611  lr=2.60e-04  dt=  37.1ms  words=29,687,808
[E03   529/1548 G   3624|CLM] train=4.4973  mask=17.1%  norm=0.682  lr=2.60e-04  dt=  37.1ms  words=29,696,000
[E03   530/1548 G   3625|CLM] train=4.3320  mask=17.1%  norm=0.791  lr=2.60e-04  dt=  37.1ms  words=29,704,192
[E03   531/1548 G   3626|CLM] train=4.2267  mask=17.1%  norm=0.672  lr=2.60e-04  dt=  37.0ms  words=29,712,384
[E03   532/1548 G   3627|CLM] train=4.3269  mask=17.1%  norm=0.758  lr=2.60e-04  dt=  37.2ms  words=29,720,576
[E03   533/1548 G   3628|CLM] train=2.9038  mask=17.1%  norm=0.894  lr=2.60e-04  dt=  36.9ms  words=29,728,768
[E03   534/1548 G   3629|CLM] train=2.8720  mask=17.1%  norm=0.931  lr=2.60e-04  dt=  37.1ms  words=29,736,960
[E03   535/1548 G   3630|CLM] train=4.6661  mask=17.1%  norm=0.853  lr=2.60e-04  dt=  37.1ms  words=29,745,152
[E03   536/1548 G   3631|CLM] train=4.4662  mask=17.1%  norm=0.697  lr=2.60e-04  dt=  37.1ms  words=29,753,344
[E03   537/1548 G   3632|CLM] train=2.5001  mask=17.1%  norm=0.740  lr=2.60e-04  dt=  37.1ms  words=29,761,536
[E03   538/1548 G   3633|CLM] train=4.4433  mask=17.1%  norm=0.978  lr=2.60e-04  dt=  37.0ms  words=29,769,728
[E03   539/1548 G   3634|CLM] train=5.1303  mask=17.1%  norm=0.868  lr=2.60e-04  dt=  37.0ms  words=29,777,920
[E03   540/1548 G   3635|CLM] train=4.9180  mask=17.1%  norm=0.894  lr=2.60e-04  dt=  37.1ms  words=29,786,112
[E03   541/1548 G   3636|CLM] train=2.6052  mask=17.1%  norm=0.939  lr=2.60e-04  dt=  37.1ms  words=29,794,304
[E03   542/1548 G   3637|CLM] train=3.0458  mask=17.1%  norm=0.839  lr=2.60e-04  dt=  36.9ms  words=29,802,496
[E03   543/1548 G   3638|CLM] train=4.6900  mask=17.1%  norm=0.862  lr=2.60e-04  dt=  37.0ms  words=29,810,688
[E03   544/1548 G   3639|CLM] train=2.9792  mask=17.1%  norm=0.666  lr=2.60e-04  dt=  37.2ms  words=29,818,880
[E03   545/1548 G   3640|CLM] train=4.8248  mask=17.1%  norm=1.019  lr=2.60e-04  dt=  37.0ms  words=29,827,072
[E03   546/1548 G   3641|CLM] train=4.3786  mask=17.1%  norm=0.785  lr=2.60e-04  dt=  37.1ms  words=29,835,264
[E03   547/1548 G   3642|CLM] train=3.7710  mask=17.1%  norm=0.536  lr=2.60e-04  dt=  37.2ms  words=29,843,456
[E03   548/1548 G   3643|CLM] train=2.7268  mask=17.1%  norm=0.981  lr=2.60e-04  dt=  37.0ms  words=29,851,648
[E03   549/1548 G   3644|CLM] train=2.5819  mask=17.1%  norm=0.721  lr=2.60e-04  dt=  37.1ms  words=29,859,840
[E03   550/1548 G   3645|CLM] train=4.2739  mask=17.1%  norm=0.600  lr=2.60e-04  dt=  37.1ms  words=29,868,032
[E03   551/1548 G   3646|CLM] train=2.2294  mask=17.1%  norm=0.862  lr=2.60e-04  dt=  37.1ms  words=29,876,224
[E03   552/1548 G   3647|CLM] train=4.2936  mask=17.1%  norm=0.647  lr=2.60e-04  dt=  37.0ms  words=29,884,416
[E03   553/1548 G   3648|CLM] train=4.0625  mask=17.1%  norm=0.976  lr=2.60e-04  dt=  37.0ms  words=29,892,608
[E03   554/1548 G   3649|CLM] train=4.9869  mask=17.1%  norm=1.253  lr=2.60e-04  dt=  36.9ms  words=29,900,800
[E03   555/1548 G   3650|CLM] train=4.9018  mask=17.1%  norm=1.288  lr=2.60e-04  dt=  37.1ms  words=29,908,992
[E03   556/1548 G   3651|CLM] train=4.6004  mask=17.1%  norm=0.785  lr=2.59e-04  dt=  36.8ms  words=29,917,184
[E03   557/1548 G   3652|CLM] train=5.0855  mask=17.1%  norm=0.706  lr=2.59e-04  dt=  36.9ms  words=29,925,376
[E03   558/1548 G   3653|CLM] train=4.5348  mask=17.1%  norm=0.914  lr=2.59e-04  dt=  36.9ms  words=29,933,568
[E03   559/1548 G   3654|CLM] train=2.6118  mask=17.0%  norm=0.807  lr=2.59e-04  dt=  37.6ms  words=29,941,760
[E03   560/1548 G   3655|CLM] train=4.5738  mask=17.0%  norm=0.768  lr=2.59e-04  dt=  36.9ms  words=29,949,952
[E03   561/1548 G   3656|CLM] train=4.9404  mask=17.0%  norm=0.991  lr=2.59e-04  dt=  37.1ms  words=29,958,144
[E03   562/1548 G   3657|CLM] train=2.3425  mask=17.0%  norm=0.920  lr=2.59e-04  dt=  37.0ms  words=29,966,336
[E03   563/1548 G   3658|CLM] train=4.6825  mask=17.0%  norm=0.817  lr=2.59e-04  dt=  36.9ms  words=29,974,528
[E03   564/1548 G   3659|CLM] train=2.4306  mask=17.0%  norm=0.847  lr=2.59e-04  dt=  36.9ms  words=29,982,720
[E03   565/1548 G   3660|CLM] train=4.2571  mask=17.0%  norm=0.780  lr=2.59e-04  dt=  37.0ms  words=29,990,912
[E03   566/1548 G   3661|CLM] train=4.1206  mask=17.0%  norm=0.777  lr=2.59e-04  dt=  37.0ms  words=29,999,104
[E03   567/1548 G   3662|CLM] train=4.4201  mask=17.0%  norm=1.515  lr=2.59e-04  dt=  37.1ms  words=30,007,296

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_30M'...
[Checkpoint] Checkpoint 'chck_30M' successfully saved.
[E03   568/1548 G   3663|CLM] train=4.9915  mask=17.0%  norm=1.120  lr=2.59e-04  dt=  38.2ms  words=30,015,488
[E03   569/1548 G   3664|CLM] train=4.5539  mask=17.0%  norm=0.988  lr=2.59e-04  dt=  37.0ms  words=30,023,680
[E03   570/1548 G   3665|CLM] train=4.8985  mask=17.0%  norm=0.648  lr=2.59e-04  dt=  37.3ms  words=30,031,872
[E03   571/1548 G   3666|CLM] train=4.3589  mask=17.0%  norm=0.683  lr=2.59e-04  dt=  37.3ms  words=30,040,064
[E03   572/1548 G   3667|CLM] train=2.4920  mask=17.0%  norm=0.745  lr=2.59e-04  dt=  37.0ms  words=30,048,256
[E03   573/1548 G   3668|CLM] train=4.9830  mask=17.0%  norm=0.780  lr=2.59e-04  dt=  37.0ms  words=30,056,448
[E03   574/1548 G   3669|CLM] train=2.5720  mask=17.0%  norm=0.885  lr=2.59e-04  dt=  36.9ms  words=30,064,640
[E03   575/1548 G   3670|CLM] train=2.7200  mask=17.0%  norm=1.859  lr=2.59e-04  dt=  37.1ms  words=30,072,832
[E03   576/1548 G   3671|CLM] train=5.0039  mask=17.0%  norm=0.784  lr=2.59e-04  dt=  37.1ms  words=30,081,024
[E03   577/1548 G   3672|CLM] train=4.9271  mask=17.0%  norm=0.980  lr=2.59e-04  dt=  37.1ms  words=30,089,216
[E03   578/1548 G   3673|CLM] train=4.4446  mask=17.0%  norm=0.927  lr=2.59e-04  dt=  37.1ms  words=30,097,408
[E03   579/1548 G   3674|CLM] train=4.9049  mask=17.0%  norm=1.119  lr=2.59e-04  dt=  37.0ms  words=30,105,600
[E03   580/1548 G   3675|CLM] train=2.8362  mask=17.0%  norm=0.765  lr=2.59e-04  dt=  37.4ms  words=30,113,792
[E03   581/1548 G   3676|CLM] train=4.6740  mask=17.0%  norm=0.735  lr=2.59e-04  dt=  37.1ms  words=30,121,984
[E03   582/1548 G   3677|CLM] train=4.9217  mask=17.0%  norm=0.828  lr=2.59e-04  dt=  39.0ms  words=30,130,176
[E03   583/1548 G   3678|CLM] train=3.9412  mask=17.0%  norm=0.692  lr=2.59e-04  dt=  41.6ms  words=30,138,368
[E03   584/1548 G   3679|CLM] train=4.6547  mask=17.0%  norm=0.774  lr=2.59e-04  dt=  38.4ms  words=30,146,560
[E03   585/1548 G   3680|CLM] train=5.0265  mask=17.0%  norm=0.871  lr=2.59e-04  dt=  38.5ms  words=30,154,752
[E03   586/1548 G   3681|CLM] train=4.7918  mask=17.0%  norm=0.753  lr=2.59e-04  dt=  37.1ms  words=30,162,944
[E03   587/1548 G   3682|CLM] train=3.8966  mask=17.0%  norm=0.671  lr=2.59e-04  dt=  37.1ms  words=30,171,136
[E03   588/1548 G   3683|CLM] train=2.5737  mask=17.0%  norm=1.049  lr=2.59e-04  dt=  38.4ms  words=30,179,328
[E03   589/1548 G   3684|CLM] train=4.8432  mask=17.0%  norm=0.728  lr=2.59e-04  dt=  42.5ms  words=30,187,520
[E03   590/1548 G   3685|CLM] train=4.4928  mask=17.0%  norm=0.757  lr=2.59e-04  dt=  39.0ms  words=30,195,712
[E03   591/1548 G   3686|CLM] train=4.8207  mask=17.0%  norm=0.884  lr=2.59e-04  dt=  37.4ms  words=30,203,904
[E03   592/1548 G   3687|CLM] train=4.3991  mask=17.0%  norm=0.817  lr=2.59e-04  dt=  37.3ms  words=30,212,096
[E03   593/1548 G   3688|CLM] train=4.4527  mask=17.0%  norm=0.819  lr=2.58e-04  dt=  37.4ms  words=30,220,288
[E03   594/1548 G   3689|CLM] train=4.4715  mask=17.0%  norm=1.551  lr=2.58e-04  dt=  37.5ms  words=30,228,480
[E03   595/1548 G   3690|CLM] train=4.8004  mask=17.0%  norm=0.677  lr=2.58e-04  dt=  42.2ms  words=30,236,672
[E03   596/1548 G   3691|CLM] train=5.0947  mask=17.0%  norm=0.677  lr=2.58e-04  dt=  46.2ms  words=30,244,864
[E03   597/1548 G   3692|CLM] train=4.1164  mask=17.0%  norm=0.697  lr=2.58e-04  dt=  37.3ms  words=30,253,056
[E03   598/1548 G   3693|CLM] train=3.5872  mask=17.0%  norm=0.675  lr=2.58e-04  dt=  37.1ms  words=30,261,248
[E03   599/1548 G   3694|CLM] train=2.5270  mask=17.0%  norm=1.079  lr=2.58e-04  dt=  45.7ms  words=30,269,440
[E03   600/1548 G   3695|CLM] train=2.2700  mask=17.0%  norm=0.849  lr=2.58e-04  dt=  37.1ms  words=30,277,632
[E03   601/1548 G   3696|CLM] train=3.1196  mask=17.0%  norm=0.733  lr=2.58e-04  dt=  36.8ms  words=30,285,824
[E03   602/1548 G   3697|CLM] train=3.7238  mask=17.0%  norm=0.684  lr=2.58e-04  dt=  36.8ms  words=30,294,016
[E03   603/1548 G   3698|CLM] train=2.6499  mask=17.0%  norm=0.895  lr=2.58e-04  dt=  38.4ms  words=30,302,208
[E03   604/1548 G   3699|CLM] train=2.5521  mask=17.0%  norm=0.726  lr=2.58e-04  dt=  37.1ms  words=30,310,400
[E03   605/1548 G   3700|CLM] train=4.3858  mask=17.0%  norm=0.740  lr=2.58e-04  dt=  37.0ms  words=30,318,592
[E03   606/1548 G   3701|CLM] train=4.4313  mask=17.0%  norm=0.959  lr=2.58e-04  dt=  37.3ms  words=30,326,784
[E03   607/1548 G   3702|CLM] train=5.8237  mask=17.0%  norm=1.176  lr=2.58e-04  dt=  40.7ms  words=30,334,976
[E03   608/1548 G   3703|CLM] train=4.8983  mask=17.0%  norm=0.940  lr=2.58e-04  dt=  43.2ms  words=30,343,168
[E03   609/1548 G   3704|CLM] train=5.1541  mask=17.0%  norm=0.872  lr=2.58e-04  dt=  37.6ms  words=30,351,360
[E03   610/1548 G   3705|CLM] train=4.6820  mask=17.0%  norm=0.695  lr=2.58e-04  dt=  37.4ms  words=30,359,552
[E03   611/1548 G   3706|CLM] train=2.7791  mask=17.0%  norm=0.825  lr=2.58e-04  dt=  37.5ms  words=30,367,744
[E03   612/1548 G   3707|CLM] train=3.1340  mask=17.0%  norm=0.977  lr=2.58e-04  dt=  37.3ms  words=30,375,936
[E03   613/1548 G   3708|CLM] train=4.6592  mask=17.0%  norm=0.817  lr=2.58e-04  dt=  37.4ms  words=30,384,128
[E03   614/1548 G   3709|CLM] train=5.1601  mask=17.0%  norm=1.453  lr=2.58e-04  dt=  37.8ms  words=30,392,320
[E03   615/1548 G   3710|CLM] train=2.5164  mask=17.0%  norm=0.705  lr=2.58e-04  dt=  42.6ms  words=30,400,512
[E03   616/1548 G   3711|CLM] train=2.5055  mask=17.0%  norm=0.682  lr=2.58e-04  dt=  38.2ms  words=30,408,704
[E03   617/1548 G   3712|CLM] train=4.5325  mask=17.0%  norm=0.673  lr=2.58e-04  dt=  37.8ms  words=30,416,896
[E03   618/1548 G   3713|CLM] train=4.4313  mask=17.0%  norm=0.909  lr=2.58e-04  dt=  39.5ms  words=30,425,088
[E03   619/1548 G   3714|CLM] train=5.9154  mask=17.0%  norm=1.820  lr=2.58e-04  dt=  47.7ms  words=30,433,280
[E03   620/1548 G   3715|CLM] train=4.9455  mask=17.0%  norm=1.003  lr=2.58e-04  dt=  38.8ms  words=30,441,472
[E03   621/1548 G   3716|CLM] train=2.6894  mask=17.0%  norm=0.888  lr=2.58e-04  dt=  43.1ms  words=30,449,664
[E03   622/1548 G   3717|CLM] train=4.2217  mask=17.0%  norm=0.846  lr=2.58e-04  dt=  43.4ms  words=30,457,856
[E03   623/1548 G   3718|CLM] train=2.3310  mask=17.0%  norm=0.689  lr=2.58e-04  dt=  37.8ms  words=30,466,048
[E03   624/1548 G   3719|CLM] train=2.2209  mask=17.0%  norm=0.767  lr=2.58e-04  dt=  39.9ms  words=30,474,240
[E03   625/1548 G   3720|CLM] train=3.0764  mask=17.0%  norm=0.783  lr=2.58e-04  dt=  47.9ms  words=30,482,432
[E03   626/1548 G   3721|CLM] train=4.0368  mask=17.0%  norm=0.760  lr=2.58e-04  dt=  44.4ms  words=30,490,624
[E03   627/1548 G   3722|CLM] train=2.8157  mask=17.0%  norm=0.985  lr=2.58e-04  dt=  39.4ms  words=30,498,816
[E03   628/1548 G   3723|CLM] train=4.9340  mask=17.0%  norm=0.876  lr=2.58e-04  dt=  37.1ms  words=30,507,008
[E03   629/1548 G   3724|CLM] train=3.0868  mask=17.0%  norm=0.951  lr=2.57e-04  dt=  37.3ms  words=30,515,200
[E03   630/1548 G   3725|CLM] train=2.3424  mask=17.0%  norm=0.673  lr=2.57e-04  dt=  37.1ms  words=30,523,392
[E03   631/1548 G   3726|CLM] train=4.1546  mask=17.0%  norm=0.744  lr=2.57e-04  dt=  37.2ms  words=30,531,584
[E03   632/1548 G   3727|CLM] train=4.8592  mask=17.0%  norm=0.849  lr=2.57e-04  dt=  37.1ms  words=30,539,776
[E03   633/1548 G   3728|CLM] train=4.9353  mask=17.0%  norm=0.833  lr=2.57e-04  dt=  37.2ms  words=30,547,968
[E03   634/1548 G   3729|CLM] train=2.6049  mask=17.0%  norm=0.816  lr=2.57e-04  dt=  37.0ms  words=30,556,160
[E03   635/1548 G   3730|CLM] train=4.5840  mask=17.0%  norm=0.695  lr=2.57e-04  dt=  37.1ms  words=30,564,352
[E03   636/1548 G   3731|CLM] train=2.2430  mask=17.0%  norm=0.536  lr=2.57e-04  dt=  36.9ms  words=30,572,544
[E03   637/1548 G   3732|CLM] train=2.4863  mask=17.0%  norm=0.919  lr=2.57e-04  dt=  36.9ms  words=30,580,736
[E03   638/1548 G   3733|CLM] train=4.4608  mask=17.0%  norm=0.817  lr=2.57e-04  dt=  37.3ms  words=30,588,928
[E03   639/1548 G   3734|CLM] train=5.5042  mask=17.0%  norm=1.995  lr=2.57e-04  dt=  36.9ms  words=30,597,120
[E03   640/1548 G   3735|CLM] train=2.8407  mask=17.0%  norm=0.627  lr=2.57e-04  dt=  37.2ms  words=30,605,312
[E03   641/1548 G   3736|CLM] train=2.3805  mask=17.0%  norm=0.812  lr=2.57e-04  dt=  37.2ms  words=30,613,504
[E03   642/1548 G   3737|CLM] train=2.5389  mask=17.0%  norm=0.827  lr=2.57e-04  dt=  37.1ms  words=30,621,696
[E03   643/1548 G   3738|CLM] train=2.7201  mask=17.0%  norm=0.741  lr=2.57e-04  dt=  36.9ms  words=30,629,888
[E03   644/1548 G   3739|CLM] train=4.8802  mask=17.0%  norm=0.869  lr=2.57e-04  dt=  37.1ms  words=30,638,080
[E03   645/1548 G   3740|CLM] train=2.7484  mask=17.0%  norm=0.588  lr=2.57e-04  dt=  37.7ms  words=30,646,272
[E03   646/1548 G   3741|CLM] train=5.2327  mask=17.0%  norm=0.903  lr=2.57e-04  dt=  37.1ms  words=30,654,464
[E03   647/1548 G   3742|CLM] train=4.0921  mask=17.0%  norm=0.795  lr=2.57e-04  dt=  37.5ms  words=30,662,656
[E03   648/1548 G   3743|CLM] train=4.6083  mask=17.0%  norm=0.693  lr=2.57e-04  dt=  37.1ms  words=30,670,848
[E03   649/1548 G   3744|CLM] train=4.0924  mask=17.0%  norm=0.723  lr=2.57e-04  dt=  37.2ms  words=30,679,040
[E03   650/1548 G   3745|CLM] train=2.6410  mask=17.0%  norm=0.634  lr=2.57e-04  dt=  36.9ms  words=30,687,232
[E03   651/1548 G   3746|CLM] train=2.6652  mask=17.0%  norm=0.557  lr=2.57e-04  dt=  37.1ms  words=30,695,424
[E03   652/1548 G   3747|CLM] train=2.6353  mask=17.0%  norm=0.866  lr=2.57e-04  dt=  37.5ms  words=30,703,616
[E03   653/1548 G   3748|CLM] train=4.2859  mask=17.0%  norm=0.755  lr=2.57e-04  dt=  37.0ms  words=30,711,808
[E03   654/1548 G   3749|CLM] train=3.8757  mask=17.0%  norm=0.714  lr=2.57e-04  dt=  37.1ms  words=30,720,000
[E03   655/1548 G   3750|CLM] train=2.7076  mask=17.0%  norm=0.993  lr=2.57e-04  dt=  37.1ms  words=30,728,192
[E03   656/1548 G   3751|CLM] train=2.1693  mask=17.0%  norm=0.877  lr=2.57e-04  dt=  37.1ms  words=30,736,384
[E03   657/1548 G   3752|CLM] train=4.4601  mask=17.0%  norm=0.714  lr=2.57e-04  dt=  37.2ms  words=30,744,576
[E03   658/1548 G   3753|CLM] train=2.8714  mask=17.0%  norm=0.679  lr=2.57e-04  dt=  37.5ms  words=30,752,768
[E03   659/1548 G   3754|CLM] train=3.7777  mask=17.0%  norm=0.922  lr=2.57e-04  dt=  37.3ms  words=30,760,960
[E03   660/1548 G   3755|CLM] train=2.9144  mask=17.0%  norm=0.874  lr=2.57e-04  dt=  37.1ms  words=30,769,152
[E03   661/1548 G   3756|CLM] train=2.6208  mask=17.0%  norm=1.198  lr=2.57e-04  dt=  37.0ms  words=30,777,344
[E03   662/1548 G   3757|CLM] train=2.7415  mask=17.0%  norm=0.830  lr=2.57e-04  dt=  37.1ms  words=30,785,536
[E03   663/1548 G   3758|CLM] train=2.5269  mask=17.0%  norm=0.904  lr=2.57e-04  dt=  37.1ms  words=30,793,728
[E03   664/1548 G   3759|CLM] train=3.8278  mask=17.0%  norm=0.747  lr=2.57e-04  dt=  37.1ms  words=30,801,920
[E03   665/1548 G   3760|CLM] train=2.4442  mask=17.0%  norm=0.700  lr=2.56e-04  dt=  37.1ms  words=30,810,112
[E03   666/1548 G   3761|CLM] train=2.4705  mask=17.0%  norm=0.640  lr=2.56e-04  dt=  37.2ms  words=30,818,304
[E03   667/1548 G   3762|CLM] train=4.2770  mask=17.0%  norm=0.917  lr=2.56e-04  dt=  37.1ms  words=30,826,496
[E03   668/1548 G   3763|CLM] train=3.9250  mask=17.0%  norm=0.636  lr=2.56e-04  dt=  37.1ms  words=30,834,688
[E03   669/1548 G   3764|CLM] train=2.4294  mask=17.0%  norm=0.628  lr=2.56e-04  dt=  37.0ms  words=30,842,880
[E03   670/1548 G   3765|CLM] train=3.5766  mask=17.0%  norm=0.631  lr=2.56e-04  dt=  37.6ms  words=30,851,072
[E03   671/1548 G   3766|CLM] train=4.2718  mask=17.0%  norm=0.733  lr=2.56e-04  dt=  37.5ms  words=30,859,264
[E03   672/1548 G   3767|CLM] train=2.3229  mask=17.0%  norm=0.559  lr=2.56e-04  dt=  37.2ms  words=30,867,456
[E03   673/1548 G   3768|CLM] train=2.7517  mask=17.0%  norm=0.862  lr=2.56e-04  dt=  37.2ms  words=30,875,648
[E03   674/1548 G   3769|CLM] train=4.8682  mask=17.0%  norm=0.861  lr=2.56e-04  dt=  36.9ms  words=30,883,840
[E03   675/1548 G   3770|CLM] train=5.4632  mask=17.0%  norm=0.859  lr=2.56e-04  dt=  37.0ms  words=30,892,032
[E03   676/1548 G   3771|CLM] train=4.4342  mask=17.0%  norm=1.114  lr=2.56e-04  dt=  37.1ms  words=30,900,224
[E03   677/1548 G   3772|CLM] train=2.3951  mask=17.0%  norm=0.679  lr=2.56e-04  dt=  36.9ms  words=30,908,416
[E03   678/1548 G   3773|CLM] train=2.5651  mask=17.0%  norm=0.836  lr=2.56e-04  dt=  37.0ms  words=30,916,608
[E03   679/1548 G   3774|CLM] train=4.5061  mask=17.0%  norm=0.879  lr=2.56e-04  dt=  36.9ms  words=30,924,800
[E03   680/1548 G   3775|CLM] train=2.9793  mask=17.0%  norm=0.759  lr=2.56e-04  dt=  37.1ms  words=30,932,992
[E03   681/1548 G   3776|CLM] train=2.5743  mask=17.0%  norm=0.704  lr=2.56e-04  dt=  36.9ms  words=30,941,184
[E03   682/1548 G   3777|CLM] train=5.5200  mask=17.0%  norm=2.175  lr=2.56e-04  dt=  36.7ms  words=30,949,376
[E03   683/1548 G   3778|CLM] train=4.0735  mask=16.9%  norm=0.922  lr=2.56e-04  dt=  37.0ms  words=30,957,568
[E03   684/1548 G   3779|CLM] train=2.6839  mask=16.9%  norm=0.768  lr=2.56e-04  dt=  37.0ms  words=30,965,760
[E03   685/1548 G   3780|CLM] train=4.4374  mask=16.9%  norm=0.976  lr=2.56e-04  dt=  36.9ms  words=30,973,952
[E03   686/1548 G   3781|CLM] train=2.7503  mask=16.9%  norm=0.603  lr=2.56e-04  dt=  36.8ms  words=30,982,144
[E03   687/1548 G   3782|CLM] train=4.2343  mask=16.9%  norm=0.684  lr=2.56e-04  dt=  36.9ms  words=30,990,336
[E03   688/1548 G   3783|CLM] train=4.9912  mask=16.9%  norm=0.747  lr=2.56e-04  dt=  37.1ms  words=30,998,528
[E03   689/1548 G   3784|CLM] train=3.0755  mask=16.9%  norm=0.945  lr=2.56e-04  dt=  37.0ms  words=31,006,720
[E03   690/1548 G   3785|CLM] train=2.5900  mask=16.9%  norm=0.631  lr=2.56e-04  dt=  37.1ms  words=31,014,912
[E03   691/1548 G   3786|CLM] train=5.0396  mask=16.9%  norm=0.934  lr=2.56e-04  dt=  37.2ms  words=31,023,104
[E03   692/1548 G   3787|CLM] train=4.8528  mask=16.9%  norm=0.807  lr=2.56e-04  dt=  36.9ms  words=31,031,296
[E03   693/1548 G   3788|CLM] train=4.5118  mask=16.9%  norm=0.844  lr=2.56e-04  dt=  36.9ms  words=31,039,488
[E03   694/1548 G   3789|CLM] train=4.6355  mask=16.9%  norm=0.770  lr=2.56e-04  dt=  36.9ms  words=31,047,680
[E03   695/1548 G   3790|CLM] train=3.1945  mask=16.9%  norm=0.808  lr=2.56e-04  dt=  37.1ms  words=31,055,872
[E03   696/1548 G   3791|CLM] train=2.6832  mask=16.9%  norm=0.847  lr=2.56e-04  dt=  36.9ms  words=31,064,064
[E03   697/1548 G   3792|CLM] train=4.7600  mask=16.9%  norm=1.060  lr=2.56e-04  dt=  37.1ms  words=31,072,256
[E03   698/1548 G   3793|CLM] train=2.6869  mask=16.9%  norm=0.692  lr=2.56e-04  dt=  36.9ms  words=31,080,448
[E03   699/1548 G   3794|CLM] train=2.8054  mask=16.9%  norm=0.734  lr=2.56e-04  dt=  37.1ms  words=31,088,640
[E03   700/1548 G   3795|CLM] train=4.8426  mask=16.9%  norm=0.929  lr=2.56e-04  dt=  36.8ms  words=31,096,832
[E03   701/1548 G   3796|CLM] train=4.3465  mask=16.9%  norm=0.675  lr=2.55e-04  dt=  37.0ms  words=31,105,024
[E03   702/1548 G   3797|CLM] train=4.5470  mask=16.9%  norm=0.692  lr=2.55e-04  dt=  37.0ms  words=31,113,216
[E03   703/1548 G   3798|CLM] train=4.3610  mask=16.9%  norm=0.607  lr=2.55e-04  dt=  37.1ms  words=31,121,408
[E03   704/1548 G   3799|CLM] train=2.8502  mask=16.9%  norm=0.660  lr=2.55e-04  dt=  37.0ms  words=31,129,600
[E03   705/1548 G   3800|CLM] train=5.1205  mask=16.9%  norm=0.770  lr=2.55e-04  dt=  37.1ms  words=31,137,792
[E03   706/1548 G   3801|CLM] train=2.4403  mask=16.9%  norm=0.672  lr=2.55e-04  dt=  37.2ms  words=31,145,984
[E03   707/1548 G   3802|CLM] train=2.4683  mask=16.9%  norm=0.651  lr=2.55e-04  dt=  37.0ms  words=31,154,176
[E03   708/1548 G   3803|CLM] train=4.7804  mask=16.9%  norm=0.649  lr=2.55e-04  dt=  37.0ms  words=31,162,368
[E03   709/1548 G   3804|CLM] train=2.5820  mask=16.9%  norm=0.648  lr=2.55e-04  dt=  36.9ms  words=31,170,560
[E03   710/1548 G   3805|CLM] train=5.1148  mask=16.9%  norm=1.053  lr=2.55e-04  dt=  37.0ms  words=31,178,752
[E03   711/1548 G   3806|CLM] train=2.5477  mask=16.9%  norm=0.566  lr=2.55e-04  dt=  36.9ms  words=31,186,944
[E03   712/1548 G   3807|CLM] train=4.9314  mask=16.9%  norm=0.802  lr=2.55e-04  dt=  36.9ms  words=31,195,136
[E03   713/1548 G   3808|CLM] train=5.6898  mask=16.9%  norm=0.756  lr=2.55e-04  dt=  37.4ms  words=31,203,328
[E03   714/1548 G   3809|CLM] train=3.8263  mask=16.9%  norm=0.735  lr=2.55e-04  dt=  37.2ms  words=31,211,520
[E03   715/1548 G   3810|CLM] train=4.4581  mask=16.9%  norm=0.696  lr=2.55e-04  dt=  37.4ms  words=31,219,712
[E03   716/1548 G   3811|CLM] train=4.4869  mask=16.9%  norm=0.785  lr=2.55e-04  dt=  37.1ms  words=31,227,904
[E03   717/1548 G   3812|CLM] train=2.5847  mask=16.9%  norm=0.857  lr=2.55e-04  dt=  37.2ms  words=31,236,096
[E03   718/1548 G   3813|CLM] train=4.6739  mask=16.9%  norm=0.788  lr=2.55e-04  dt=  38.3ms  words=31,244,288
[E03   719/1548 G   3814|CLM] train=5.4402  mask=16.9%  norm=0.871  lr=2.55e-04  dt=  45.2ms  words=31,252,480
[E03   720/1548 G   3815|CLM] train=5.3990  mask=16.9%  norm=0.901  lr=2.55e-04  dt=  46.9ms  words=31,260,672
[E03   721/1548 G   3816|CLM] train=4.2648  mask=16.9%  norm=0.733  lr=2.55e-04  dt=  47.0ms  words=31,268,864
[E03   722/1548 G   3817|CLM] train=4.7639  mask=16.9%  norm=0.777  lr=2.55e-04  dt=  37.2ms  words=31,277,056
[E03   723/1548 G   3818|CLM] train=3.7955  mask=16.9%  norm=0.639  lr=2.55e-04  dt=  37.0ms  words=31,285,248
[E03   724/1548 G   3819|CLM] train=2.6205  mask=16.9%  norm=0.693  lr=2.55e-04  dt=  37.1ms  words=31,293,440
[E03   725/1548 G   3820|CLM] train=4.2713  mask=16.9%  norm=0.693  lr=2.55e-04  dt=  47.6ms  words=31,301,632
[E03   726/1548 G   3821|CLM] train=4.8967  mask=16.9%  norm=0.951  lr=2.55e-04  dt=  37.1ms  words=31,309,824
[E03   727/1548 G   3822|CLM] train=4.0091  mask=16.9%  norm=0.603  lr=2.55e-04  dt=  42.0ms  words=31,318,016
[E03   728/1548 G   3823|CLM] train=2.5073  mask=16.9%  norm=1.012  lr=2.55e-04  dt=  46.5ms  words=31,326,208
[E03   729/1548 G   3824|CLM] train=2.5444  mask=16.9%  norm=0.643  lr=2.55e-04  dt=  41.1ms  words=31,334,400
[E03   730/1548 G   3825|CLM] train=2.4720  mask=16.9%  norm=0.837  lr=2.55e-04  dt=  36.8ms  words=31,342,592
[E03   731/1548 G   3826|CLM] train=4.1230  mask=16.9%  norm=0.769  lr=2.55e-04  dt=  37.0ms  words=31,350,784
[E03   732/1548 G   3827|CLM] train=4.6761  mask=16.9%  norm=1.047  lr=2.55e-04  dt=  37.0ms  words=31,358,976
[E03   733/1548 G   3828|CLM] train=2.6232  mask=16.9%  norm=0.686  lr=2.55e-04  dt=  36.8ms  words=31,367,168
[E03   734/1548 G   3829|CLM] train=4.4167  mask=16.9%  norm=0.858  lr=2.55e-04  dt=  42.6ms  words=31,375,360
[E03   735/1548 G   3830|CLM] train=2.5352  mask=16.9%  norm=0.762  lr=2.55e-04  dt=  36.9ms  words=31,383,552
[E03   736/1548 G   3831|CLM] train=2.1601  mask=16.9%  norm=0.831  lr=2.55e-04  dt=  36.9ms  words=31,391,744
[E03   737/1548 G   3832|CLM] train=1.8975  mask=16.9%  norm=0.679  lr=2.54e-04  dt=  37.3ms  words=31,399,936
[E03   738/1548 G   3833|CLM] train=4.0799  mask=16.9%  norm=0.706  lr=2.54e-04  dt=  37.3ms  words=31,408,128
[E03   739/1548 G   3834|CLM] train=4.4655  mask=16.9%  norm=0.868  lr=2.54e-04  dt=  37.2ms  words=31,416,320
[E03   740/1548 G   3835|CLM] train=2.4756  mask=16.9%  norm=0.584  lr=2.54e-04  dt=  37.3ms  words=31,424,512
[E03   741/1548 G   3836|CLM] train=2.9389  mask=16.9%  norm=0.669  lr=2.54e-04  dt=  37.1ms  words=31,432,704
[E03   742/1548 G   3837|CLM] train=4.6335  mask=16.9%  norm=0.717  lr=2.54e-04  dt=  36.9ms  words=31,440,896
[E03   743/1548 G   3838|CLM] train=5.7762  mask=16.9%  norm=2.893  lr=2.54e-04  dt=  37.0ms  words=31,449,088
[E03   744/1548 G   3839|CLM] train=2.7704  mask=16.9%  norm=1.283  lr=2.54e-04  dt=  36.9ms  words=31,457,280
[E03   745/1548 G   3840|CLM] train=4.0991  mask=16.9%  norm=0.753  lr=2.54e-04  dt=  37.0ms  words=31,465,472
[E03   746/1548 G   3841|CLM] train=2.3811  mask=16.9%  norm=0.860  lr=2.54e-04  dt=  36.9ms  words=31,473,664
[E03   747/1548 G   3842|CLM] train=2.5457  mask=16.9%  norm=0.713  lr=2.54e-04  dt=  36.8ms  words=31,481,856
[E03   748/1548 G   3843|CLM] train=4.3771  mask=16.9%  norm=0.827  lr=2.54e-04  dt=  36.9ms  words=31,490,048
[E03   749/1548 G   3844|CLM] train=2.0105  mask=16.9%  norm=1.195  lr=2.54e-04  dt=  37.0ms  words=31,498,240
[E03   750/1548 G   3845|CLM] train=5.2402  mask=16.9%  norm=0.915  lr=2.54e-04  dt=  36.9ms  words=31,506,432
[E03   751/1548 G   3846|CLM] train=4.9617  mask=16.9%  norm=0.914  lr=2.54e-04  dt=  36.8ms  words=31,514,624
[E03   752/1548 G   3847|CLM] train=2.5058  mask=16.9%  norm=0.933  lr=2.54e-04  dt=  36.9ms  words=31,522,816
[E03   753/1548 G   3848|CLM] train=5.3150  mask=16.9%  norm=0.872  lr=2.54e-04  dt=  37.2ms  words=31,531,008
[E03   754/1548 G   3849|CLM] train=3.8530  mask=16.9%  norm=0.678  lr=2.54e-04  dt=  37.4ms  words=31,539,200
[E03   755/1548 G   3850|CLM] train=4.1367  mask=16.9%  norm=0.951  lr=2.54e-04  dt=  37.1ms  words=31,547,392
[E03   756/1548 G   3851|CLM] train=4.6060  mask=16.9%  norm=0.896  lr=2.54e-04  dt=  37.1ms  words=31,555,584
[E03   757/1548 G   3852|CLM] train=2.5222  mask=16.9%  norm=0.992  lr=2.54e-04  dt=  37.0ms  words=31,563,776
[E03   758/1548 G   3853|CLM] train=4.5636  mask=16.9%  norm=0.765  lr=2.54e-04  dt=  36.8ms  words=31,571,968
[E03   759/1548 G   3854|CLM] train=5.1099  mask=16.9%  norm=1.132  lr=2.54e-04  dt=  36.9ms  words=31,580,160
[E03   760/1548 G   3855|CLM] train=4.4774  mask=16.9%  norm=0.751  lr=2.54e-04  dt=  37.1ms  words=31,588,352
[E03   761/1548 G   3856|CLM] train=2.7472  mask=16.9%  norm=0.669  lr=2.54e-04  dt=  36.9ms  words=31,596,544
[E03   762/1548 G   3857|CLM] train=5.3618  mask=16.9%  norm=1.258  lr=2.54e-04  dt=  36.9ms  words=31,604,736
[E03   763/1548 G   3858|CLM] train=4.5421  mask=16.9%  norm=1.063  lr=2.54e-04  dt=  37.0ms  words=31,612,928
[E03   764/1548 G   3859|CLM] train=4.1113  mask=16.9%  norm=0.763  lr=2.54e-04  dt=  37.0ms  words=31,621,120
[E03   765/1548 G   3860|CLM] train=2.5595  mask=16.9%  norm=0.958  lr=2.54e-04  dt=  36.9ms  words=31,629,312
[E03   766/1548 G   3861|CLM] train=2.5891  mask=16.9%  norm=0.897  lr=2.54e-04  dt=  37.2ms  words=31,637,504
[E03   767/1548 G   3862|CLM] train=4.4392  mask=16.9%  norm=0.709  lr=2.54e-04  dt=  37.2ms  words=31,645,696
[E03   768/1548 G   3863|CLM] train=4.5933  mask=16.9%  norm=0.912  lr=2.54e-04  dt=  37.0ms  words=31,653,888
[E03   769/1548 G   3864|CLM] train=4.0310  mask=16.9%  norm=0.889  lr=2.54e-04  dt=  37.1ms  words=31,662,080
[E03   770/1548 G   3865|CLM] train=4.2504  mask=16.9%  norm=0.737  lr=2.54e-04  dt=  36.9ms  words=31,670,272
[E03   771/1548 G   3866|CLM] train=4.5543  mask=16.9%  norm=1.285  lr=2.54e-04  dt=  37.0ms  words=31,678,464
[E03   772/1548 G   3867|CLM] train=5.3156  mask=16.9%  norm=0.943  lr=2.53e-04  dt=  36.8ms  words=31,686,656
[E03   773/1548 G   3868|CLM] train=4.4898  mask=16.9%  norm=0.691  lr=2.53e-04  dt=  37.0ms  words=31,694,848
[E03   774/1548 G   3869|CLM] train=4.5686  mask=16.9%  norm=0.904  lr=2.53e-04  dt=  36.9ms  words=31,703,040
[E03   775/1548 G   3870|CLM] train=4.5907  mask=16.9%  norm=0.657  lr=2.53e-04  dt=  37.1ms  words=31,711,232
[E03   776/1548 G   3871|CLM] train=4.0472  mask=16.9%  norm=0.654  lr=2.53e-04  dt=  36.9ms  words=31,719,424
[E03   777/1548 G   3872|CLM] train=2.7420  mask=16.9%  norm=0.943  lr=2.53e-04  dt=  37.2ms  words=31,727,616
[E03   778/1548 G   3873|CLM] train=2.6213  mask=16.9%  norm=1.087  lr=2.53e-04  dt=  37.0ms  words=31,735,808
[E03   779/1548 G   3874|CLM] train=4.1673  mask=16.9%  norm=0.871  lr=2.53e-04  dt=  37.1ms  words=31,744,000
[E03   780/1548 G   3875|CLM] train=2.6968  mask=16.9%  norm=1.286  lr=2.53e-04  dt=  36.9ms  words=31,752,192
[E03   781/1548 G   3876|CLM] train=2.9352  mask=16.9%  norm=0.588  lr=2.53e-04  dt=  37.0ms  words=31,760,384
[E03   782/1548 G   3877|CLM] train=3.9277  mask=16.9%  norm=0.771  lr=2.53e-04  dt=  37.1ms  words=31,768,576
[E03   783/1548 G   3878|CLM] train=4.7953  mask=16.9%  norm=0.738  lr=2.53e-04  dt=  36.9ms  words=31,776,768
[E03   784/1548 G   3879|CLM] train=4.4917  mask=16.9%  norm=0.676  lr=2.53e-04  dt=  36.9ms  words=31,784,960
[E03   785/1548 G   3880|CLM] train=2.2880  mask=16.9%  norm=0.789  lr=2.53e-04  dt=  37.0ms  words=31,793,152
[E03   786/1548 G   3881|CLM] train=4.9123  mask=16.9%  norm=0.785  lr=2.53e-04  dt=  37.1ms  words=31,801,344
[E03   787/1548 G   3882|CLM] train=4.3714  mask=16.9%  norm=0.781  lr=2.53e-04  dt=  37.2ms  words=31,809,536
[E03   788/1548 G   3883|CLM] train=2.9266  mask=16.9%  norm=0.943  lr=2.53e-04  dt=  37.0ms  words=31,817,728
[E03   789/1548 G   3884|CLM] train=2.6071  mask=16.9%  norm=0.770  lr=2.53e-04  dt=  37.2ms  words=31,825,920
[E03   790/1548 G   3885|CLM] train=4.4481  mask=16.9%  norm=0.855  lr=2.53e-04  dt=  36.9ms  words=31,834,112
[E03   791/1548 G   3886|CLM] train=2.8530  mask=16.9%  norm=0.843  lr=2.53e-04  dt=  37.0ms  words=31,842,304
[E03   792/1548 G   3887|CLM] train=4.4978  mask=16.9%  norm=0.603  lr=2.53e-04  dt=  36.8ms  words=31,850,496
[E03   793/1548 G   3888|CLM] train=4.8546  mask=16.9%  norm=0.853  lr=2.53e-04  dt=  37.1ms  words=31,858,688
[E03   794/1548 G   3889|CLM] train=4.3660  mask=16.9%  norm=0.911  lr=2.53e-04  dt=  36.9ms  words=31,866,880
[E03   795/1548 G   3890|CLM] train=4.4573  mask=16.9%  norm=0.873  lr=2.53e-04  dt=  37.0ms  words=31,875,072
[E03   796/1548 G   3891|CLM] train=2.3496  mask=16.9%  norm=0.720  lr=2.53e-04  dt=  36.9ms  words=31,883,264
[E03   797/1548 G   3892|CLM] train=4.7860  mask=16.9%  norm=0.772  lr=2.53e-04  dt=  37.1ms  words=31,891,456
[E03   798/1548 G   3893|CLM] train=2.4304  mask=16.9%  norm=0.653  lr=2.53e-04  dt=  37.0ms  words=31,899,648
[E03   799/1548 G   3894|CLM] train=3.8602  mask=16.9%  norm=0.952  lr=2.53e-04  dt=  37.1ms  words=31,907,840
[E03   800/1548 G   3895|CLM] train=4.2344  mask=16.9%  norm=0.740  lr=2.53e-04  dt=  37.1ms  words=31,916,032
[E03   801/1548 G   3896|CLM] train=2.9377  mask=16.9%  norm=0.600  lr=2.53e-04  dt=  37.2ms  words=31,924,224
[E03   802/1548 G   3897|CLM] train=4.2544  mask=16.9%  norm=0.719  lr=2.53e-04  dt=  36.9ms  words=31,932,416
[E03   803/1548 G   3898|CLM] train=2.4265  mask=16.9%  norm=0.830  lr=2.53e-04  dt=  37.0ms  words=31,940,608
[E03   804/1548 G   3899|CLM] train=2.8178  mask=16.9%  norm=0.611  lr=2.53e-04  dt=  36.9ms  words=31,948,800
[E03   805/1548 G   3900|CLM] train=4.7611  mask=16.9%  norm=0.798  lr=2.53e-04  dt=  37.0ms  words=31,956,992
[E03   806/1548 G   3901|CLM] train=5.7986  mask=16.8%  norm=1.165  lr=2.53e-04  dt=  36.9ms  words=31,965,184
[E03   807/1548 G   3902|CLM] train=4.8382  mask=16.8%  norm=0.890  lr=2.52e-04  dt=  36.9ms  words=31,973,376
[E03   808/1548 G   3903|CLM] train=5.0654  mask=16.8%  norm=0.845  lr=2.52e-04  dt=  37.0ms  words=31,981,568
[E03   809/1548 G   3904|CLM] train=4.2651  mask=16.8%  norm=0.893  lr=2.52e-04  dt=  37.2ms  words=31,989,760
[E03   810/1548 G   3905|CLM] train=2.9047  mask=16.8%  norm=0.654  lr=2.52e-04  dt=  37.0ms  words=31,997,952
[E03   811/1548 G   3906|CLM] train=4.9400  mask=16.8%  norm=1.108  lr=2.52e-04  dt=  37.2ms  words=32,006,144
[E03   812/1548 G   3907|CLM] train=4.2886  mask=16.8%  norm=0.895  lr=2.52e-04  dt=  36.9ms  words=32,014,336
[E03   813/1548 G   3908|CLM] train=3.9346  mask=16.8%  norm=0.664  lr=2.52e-04  dt=  37.0ms  words=32,022,528
[E03   814/1548 G   3909|CLM] train=4.3680  mask=16.8%  norm=0.923  lr=2.52e-04  dt=  37.0ms  words=32,030,720
[E03   815/1548 G   3910|CLM] train=2.5533  mask=16.8%  norm=0.733  lr=2.52e-04  dt=  37.0ms  words=32,038,912
[E03   816/1548 G   3911|CLM] train=4.5494  mask=16.8%  norm=0.849  lr=2.52e-04  dt=  36.8ms  words=32,047,104
[E03   817/1548 G   3912|CLM] train=2.6022  mask=16.8%  norm=0.982  lr=2.52e-04  dt=  36.9ms  words=32,055,296
[E03   818/1548 G   3913|CLM] train=4.2251  mask=16.8%  norm=0.793  lr=2.52e-04  dt=  37.1ms  words=32,063,488
[E03   819/1548 G   3914|CLM] train=5.6931  mask=16.8%  norm=1.812  lr=2.52e-04  dt=  37.1ms  words=32,071,680
[E03   820/1548 G   3915|CLM] train=2.5273  mask=16.8%  norm=0.880  lr=2.52e-04  dt=  37.0ms  words=32,079,872
[E03   821/1548 G   3916|CLM] train=4.3242  mask=16.8%  norm=0.652  lr=2.52e-04  dt=  37.2ms  words=32,088,064
[E03   822/1548 G   3917|CLM] train=4.6670  mask=16.8%  norm=0.723  lr=2.52e-04  dt=  37.1ms  words=32,096,256
[E03   823/1548 G   3918|CLM] train=2.4814  mask=16.8%  norm=0.919  lr=2.52e-04  dt=  37.0ms  words=32,104,448
[E03   824/1548 G   3919|CLM] train=4.1975  mask=16.8%  norm=0.603  lr=2.52e-04  dt=  37.1ms  words=32,112,640
[E03   825/1548 G   3920|CLM] train=4.3201  mask=16.8%  norm=1.146  lr=2.52e-04  dt=  37.1ms  words=32,120,832
[E03   826/1548 G   3921|CLM] train=4.2154  mask=16.8%  norm=0.902  lr=2.52e-04  dt=  37.0ms  words=32,129,024
[E03   827/1548 G   3922|CLM] train=2.4775  mask=16.8%  norm=0.640  lr=2.52e-04  dt=  37.2ms  words=32,137,216
[E03   828/1548 G   3923|CLM] train=6.0369  mask=16.8%  norm=1.643  lr=2.52e-04  dt=  36.9ms  words=32,145,408
[E03   829/1548 G   3924|CLM] train=4.4411  mask=16.8%  norm=0.801  lr=2.52e-04  dt=  37.1ms  words=32,153,600
[E03   830/1548 G   3925|CLM] train=4.0407  mask=16.8%  norm=0.693  lr=2.52e-04  dt=  37.1ms  words=32,161,792
[E03   831/1548 G   3926|CLM] train=5.6347  mask=16.8%  norm=1.354  lr=2.52e-04  dt=  37.0ms  words=32,169,984
[E03   832/1548 G   3927|CLM] train=4.5452  mask=16.8%  norm=1.411  lr=2.52e-04  dt=  37.0ms  words=32,178,176
[E03   833/1548 G   3928|CLM] train=4.2853  mask=16.8%  norm=0.742  lr=2.52e-04  dt=  37.1ms  words=32,186,368
[E03   834/1548 G   3929|CLM] train=2.3959  mask=16.8%  norm=0.629  lr=2.52e-04  dt=  37.0ms  words=32,194,560
[E03   835/1548 G   3930|CLM] train=4.5044  mask=16.8%  norm=0.920  lr=2.52e-04  dt=  37.2ms  words=32,202,752
[E03   836/1548 G   3931|CLM] train=2.6390  mask=16.8%  norm=0.944  lr=2.52e-04  dt=  37.2ms  words=32,210,944
[E03   837/1548 G   3932|CLM] train=4.9452  mask=16.8%  norm=0.844  lr=2.52e-04  dt=  36.9ms  words=32,219,136
[E03   838/1548 G   3933|CLM] train=4.6361  mask=16.8%  norm=0.779  lr=2.52e-04  dt=  36.9ms  words=32,227,328
[E03   839/1548 G   3934|CLM] train=5.4536  mask=16.8%  norm=1.371  lr=2.52e-04  dt=  37.1ms  words=32,235,520
[E03   840/1548 G   3935|CLM] train=3.7847  mask=16.8%  norm=0.759  lr=2.52e-04  dt=  37.0ms  words=32,243,712
[E03   841/1548 G   3936|CLM] train=2.2597  mask=16.8%  norm=0.726  lr=2.51e-04  dt=  36.9ms  words=32,251,904
[E03   842/1548 G   3937|CLM] train=4.9476  mask=16.8%  norm=0.919  lr=2.51e-04  dt=  37.0ms  words=32,260,096
[E03   843/1548 G   3938|CLM] train=2.3166  mask=16.8%  norm=0.738  lr=2.51e-04  dt=  36.9ms  words=32,268,288
[E03   844/1548 G   3939|CLM] train=2.4608  mask=16.8%  norm=0.665  lr=2.51e-04  dt=  37.0ms  words=32,276,480
[E03   845/1548 G   3940|CLM] train=4.9614  mask=16.8%  norm=1.157  lr=2.51e-04  dt=  37.1ms  words=32,284,672
[E03   846/1548 G   3941|CLM] train=4.3162  mask=16.8%  norm=1.535  lr=2.51e-04  dt=  37.5ms  words=32,292,864
[E03   847/1548 G   3942|CLM] train=4.3621  mask=16.8%  norm=0.752  lr=2.51e-04  dt=  37.7ms  words=32,301,056
[E03   848/1548 G   3943|CLM] train=5.5179  mask=16.8%  norm=1.055  lr=2.51e-04  dt=  37.5ms  words=32,309,248
[E03   849/1548 G   3944|CLM] train=4.5082  mask=16.8%  norm=0.709  lr=2.51e-04  dt=  39.1ms  words=32,317,440
[E03   850/1548 G   3945|CLM] train=4.5015  mask=16.8%  norm=0.732  lr=2.51e-04  dt=  36.9ms  words=32,325,632
[E03   851/1548 G   3946|CLM] train=4.3661  mask=16.8%  norm=0.795  lr=2.51e-04  dt=  37.3ms  words=32,333,824
[E03   852/1548 G   3947|CLM] train=4.4049  mask=16.8%  norm=0.642  lr=2.51e-04  dt=  38.2ms  words=32,342,016
[E03   853/1548 G   3948|CLM] train=4.4677  mask=16.8%  norm=0.742  lr=2.51e-04  dt=  37.2ms  words=32,350,208
[E03   854/1548 G   3949|CLM] train=5.4930  mask=16.8%  norm=1.163  lr=2.51e-04  dt=  37.2ms  words=32,358,400
[E03   855/1548 G   3950|CLM] train=4.8404  mask=16.8%  norm=0.868  lr=2.51e-04  dt=  36.8ms  words=32,366,592
[E03   856/1548 G   3951|CLM] train=4.4037  mask=16.8%  norm=1.010  lr=2.51e-04  dt=  37.3ms  words=32,374,784
[E03   857/1548 G   3952|CLM] train=4.8185  mask=16.8%  norm=0.873  lr=2.51e-04  dt=  37.3ms  words=32,382,976
[E03   858/1548 G   3953|CLM] train=4.7894  mask=16.8%  norm=1.923  lr=2.51e-04  dt=  37.0ms  words=32,391,168
[E03   859/1548 G   3954|CLM] train=4.9052  mask=16.8%  norm=0.780  lr=2.51e-04  dt=  37.3ms  words=32,399,360
[E03   860/1548 G   3955|CLM] train=4.8173  mask=16.8%  norm=0.972  lr=2.51e-04  dt=  37.0ms  words=32,407,552
[E03   861/1548 G   3956|CLM] train=4.7668  mask=16.8%  norm=0.883  lr=2.51e-04  dt=  37.2ms  words=32,415,744
[E03   862/1548 G   3957|CLM] train=2.9359  mask=16.8%  norm=0.990  lr=2.51e-04  dt=  37.1ms  words=32,423,936
[E03   863/1548 G   3958|CLM] train=4.9384  mask=16.8%  norm=0.801  lr=2.51e-04  dt=  37.3ms  words=32,432,128
[E03   864/1548 G   3959|CLM] train=5.6976  mask=16.8%  norm=1.558  lr=2.51e-04  dt=  36.9ms  words=32,440,320
[E03   865/1548 G   3960|CLM] train=2.5950  mask=16.8%  norm=1.182  lr=2.51e-04  dt=  37.1ms  words=32,448,512
[E03   866/1548 G   3961|CLM] train=5.5080  mask=16.8%  norm=0.820  lr=2.51e-04  dt=  37.2ms  words=32,456,704
[E03   867/1548 G   3962|CLM] train=2.6213  mask=16.8%  norm=0.885  lr=2.51e-04  dt=  43.9ms  words=32,464,896
[E03   868/1548 G   3963|CLM] train=4.1736  mask=16.8%  norm=0.698  lr=2.51e-04  dt=  43.4ms  words=32,473,088
[E03   869/1548 G   3964|CLM] train=2.5271  mask=16.8%  norm=0.585  lr=2.51e-04  dt=  37.2ms  words=32,481,280
[E03   870/1548 G   3965|CLM] train=3.1495  mask=16.8%  norm=1.504  lr=2.51e-04  dt=  45.5ms  words=32,489,472
[E03   871/1548 G   3966|CLM] train=2.5112  mask=16.8%  norm=0.647  lr=2.51e-04  dt=  37.3ms  words=32,497,664
[E03   872/1548 G   3967|CLM] train=3.1549  mask=16.8%  norm=0.684  lr=2.51e-04  dt=  37.3ms  words=32,505,856
[E03   873/1548 G   3968|CLM] train=2.1269  mask=16.8%  norm=0.661  lr=2.51e-04  dt=  37.1ms  words=32,514,048
[E03   874/1548 G   3969|CLM] train=5.1438  mask=16.8%  norm=1.186  lr=2.51e-04  dt=  37.0ms  words=32,522,240
[E03   875/1548 G   3970|CLM] train=4.3389  mask=16.8%  norm=0.731  lr=2.51e-04  dt=  37.8ms  words=32,530,432
[E03   876/1548 G   3971|CLM] train=4.7386  mask=16.8%  norm=0.768  lr=2.50e-04  dt=  37.0ms  words=32,538,624
[E03   877/1548 G   3972|CLM] train=3.1414  mask=16.8%  norm=1.268  lr=2.50e-04  dt=  37.1ms  words=32,546,816
[E03   878/1548 G   3973|CLM] train=2.7751  mask=16.8%  norm=0.722  lr=2.50e-04  dt=  37.3ms  words=32,555,008
[E03   879/1548 G   3974|CLM] train=4.8615  mask=16.8%  norm=0.812  lr=2.50e-04  dt=  38.7ms  words=32,563,200
[E03   880/1548 G   3975|CLM] train=4.1800  mask=16.8%  norm=0.870  lr=2.50e-04  dt=  38.5ms  words=32,571,392
[E03   881/1548 G   3976|CLM] train=4.9935  mask=16.8%  norm=0.781  lr=2.50e-04  dt=  37.9ms  words=32,579,584
[E03   882/1548 G   3977|CLM] train=3.9811  mask=16.8%  norm=0.713  lr=2.50e-04  dt=  38.4ms  words=32,587,776
[E03   883/1548 G   3978|CLM] train=2.7348  mask=16.8%  norm=1.159  lr=2.50e-04  dt=  38.9ms  words=32,595,968
[E03   884/1548 G   3979|CLM] train=2.4725  mask=16.8%  norm=0.878  lr=2.50e-04  dt=  38.0ms  words=32,604,160
[E03   885/1548 G   3980|CLM] train=2.8214  mask=16.8%  norm=0.880  lr=2.50e-04  dt=  37.6ms  words=32,612,352
[E03   886/1548 G   3981|CLM] train=4.8506  mask=16.8%  norm=0.709  lr=2.50e-04  dt=  37.4ms  words=32,620,544
[E03   887/1548 G   3982|CLM] train=5.0635  mask=16.8%  norm=1.024  lr=2.50e-04  dt=  37.1ms  words=32,628,736
[E03   888/1548 G   3983|CLM] train=4.3919  mask=16.8%  norm=0.840  lr=2.50e-04  dt=  37.0ms  words=32,636,928
[E03   889/1548 G   3984|CLM] train=2.3635  mask=16.8%  norm=0.864  lr=2.50e-04  dt=  46.0ms  words=32,645,120
[E03   890/1548 G   3985|CLM] train=4.8286  mask=16.8%  norm=0.778  lr=2.50e-04  dt=  48.9ms  words=32,653,312
[E03   891/1548 G   3986|CLM] train=4.8126  mask=16.8%  norm=0.804  lr=2.50e-04  dt=  37.5ms  words=32,661,504
[E03   892/1548 G   3987|CLM] train=2.9637  mask=16.8%  norm=0.596  lr=2.50e-04  dt=  37.5ms  words=32,669,696
[E03   893/1548 G   3988|CLM] train=4.1328  mask=16.8%  norm=0.774  lr=2.50e-04  dt=  37.3ms  words=32,677,888
[E03   894/1548 G   3989|CLM] train=2.8272  mask=16.8%  norm=0.609  lr=2.50e-04  dt=  37.1ms  words=32,686,080
[E03   895/1548 G   3990|CLM] train=3.8194  mask=16.8%  norm=0.712  lr=2.50e-04  dt=  37.3ms  words=32,694,272
[E03   896/1548 G   3991|CLM] train=2.7404  mask=16.8%  norm=0.690  lr=2.50e-04  dt=  37.1ms  words=32,702,464
[E03   897/1548 G   3992|CLM] train=2.7255  mask=16.8%  norm=0.867  lr=2.50e-04  dt=  37.4ms  words=32,710,656
[E03   898/1548 G   3993|CLM] train=2.6620  mask=16.8%  norm=2.453  lr=2.50e-04  dt=  37.3ms  words=32,718,848
[E03   899/1548 G   3994|CLM] train=4.5678  mask=16.8%  norm=0.722  lr=2.50e-04  dt=  37.2ms  words=32,727,040
[E03   900/1548 G   3995|CLM] train=5.8941  mask=16.8%  norm=1.317  lr=2.50e-04  dt=  37.1ms  words=32,735,232
[E03   901/1548 G   3996|CLM] train=4.1451  mask=16.8%  norm=0.700  lr=2.50e-04  dt=  37.0ms  words=32,743,424
[E03   902/1548 G   3997|CLM] train=2.9960  mask=16.8%  norm=0.763  lr=2.50e-04  dt=  37.2ms  words=32,751,616
[E03   903/1548 G   3998|CLM] train=6.0601  mask=16.8%  norm=1.026  lr=2.50e-04  dt=  37.0ms  words=32,759,808
[E03   904/1548 G   3999|CLM] train=4.1753  mask=16.8%  norm=0.590  lr=2.50e-04  dt=  37.0ms  words=32,768,000
[E03   905/1548 G   4000|CLM] train=4.4845  mask=16.8%  norm=1.541  lr=2.50e-04  dt=  37.0ms  words=32,776,192
[E03   906/1548 G   4001|CLM] train=2.5619  mask=16.8%  norm=0.861  lr=2.50e-04  dt=  37.2ms  words=32,784,384
[E03   907/1548 G   4002|CLM] train=4.4036  mask=16.8%  norm=0.636  lr=2.50e-04  dt=  37.1ms  words=32,792,576
[E03   908/1548 G   4003|CLM] train=5.5442  mask=16.8%  norm=0.998  lr=2.50e-04  dt=  37.4ms  words=32,800,768
[E03   909/1548 G   4004|CLM] train=2.4672  mask=16.8%  norm=0.638  lr=2.50e-04  dt=  37.2ms  words=32,808,960
[E03   910/1548 G   4005|CLM] train=2.9629  mask=16.8%  norm=0.762  lr=2.49e-04  dt=  37.7ms  words=32,817,152
[E03   911/1548 G   4006|CLM] train=2.4463  mask=16.8%  norm=0.716  lr=2.49e-04  dt=  37.3ms  words=32,825,344
[E03   912/1548 G   4007|CLM] train=4.7007  mask=16.8%  norm=0.739  lr=2.49e-04  dt=  37.2ms  words=32,833,536
[E03   913/1548 G   4008|CLM] train=2.6690  mask=16.8%  norm=0.711  lr=2.49e-04  dt=  37.6ms  words=32,841,728
[E03   914/1548 G   4009|CLM] train=4.8605  mask=16.8%  norm=0.897  lr=2.49e-04  dt=  37.4ms  words=32,849,920
[E03   915/1548 G   4010|CLM] train=2.5596  mask=16.8%  norm=0.656  lr=2.49e-04  dt=  37.3ms  words=32,858,112
[E03   916/1548 G   4011|CLM] train=5.1497  mask=16.8%  norm=0.759  lr=2.49e-04  dt=  37.3ms  words=32,866,304
[E03   917/1548 G   4012|CLM] train=4.4073  mask=16.8%  norm=0.928  lr=2.49e-04  dt=  37.1ms  words=32,874,496
[E03   918/1548 G   4013|CLM] train=4.2747  mask=16.8%  norm=0.661  lr=2.49e-04  dt=  37.0ms  words=32,882,688
[E03   919/1548 G   4014|CLM] train=4.4280  mask=16.8%  norm=0.779  lr=2.49e-04  dt=  36.9ms  words=32,890,880
[E03   920/1548 G   4015|CLM] train=4.5250  mask=16.8%  norm=0.602  lr=2.49e-04  dt=  36.9ms  words=32,899,072
[E03   921/1548 G   4016|CLM] train=2.8136  mask=16.8%  norm=0.765  lr=2.49e-04  dt=  37.0ms  words=32,907,264
[E03   922/1548 G   4017|CLM] train=4.5069  mask=16.8%  norm=0.764  lr=2.49e-04  dt=  37.2ms  words=32,915,456
[E03   923/1548 G   4018|CLM] train=4.1121  mask=16.8%  norm=0.624  lr=2.49e-04  dt=  37.1ms  words=32,923,648
[E03   924/1548 G   4019|CLM] train=4.5920  mask=16.8%  norm=0.699  lr=2.49e-04  dt=  37.2ms  words=32,931,840
[E03   925/1548 G   4020|CLM] train=4.1133  mask=16.8%  norm=0.785  lr=2.49e-04  dt=  37.1ms  words=32,940,032
[E03   926/1548 G   4021|CLM] train=5.1106  mask=16.8%  norm=0.779  lr=2.49e-04  dt=  37.0ms  words=32,948,224
[E03   927/1548 G   4022|CLM] train=4.5313  mask=16.8%  norm=0.865  lr=2.49e-04  dt=  37.5ms  words=32,956,416
[E03   928/1548 G   4023|CLM] train=3.9031  mask=16.8%  norm=0.682  lr=2.49e-04  dt=  37.1ms  words=32,964,608
[E03   929/1548 G   4024|CLM] train=4.9917  mask=16.8%  norm=0.991  lr=2.49e-04  dt=  37.0ms  words=32,972,800
[E03   930/1548 G   4025|CLM] train=2.8958  mask=16.7%  norm=0.781  lr=2.49e-04  dt=  37.0ms  words=32,980,992
[E03   931/1548 G   4026|CLM] train=2.4983  mask=16.7%  norm=0.737  lr=2.49e-04  dt=  37.3ms  words=32,989,184
[E03   932/1548 G   4027|CLM] train=2.3630  mask=16.7%  norm=1.023  lr=2.49e-04  dt=  37.3ms  words=32,997,376
[E03   933/1548 G   4028|CLM] train=2.8653  mask=16.7%  norm=0.834  lr=2.49e-04  dt=  37.0ms  words=33,005,568
[E03   934/1548 G   4029|CLM] train=4.5765  mask=16.7%  norm=0.984  lr=2.49e-04  dt=  37.4ms  words=33,013,760
[E03   935/1548 G   4030|CLM] train=5.1193  mask=16.7%  norm=1.056  lr=2.49e-04  dt=  37.1ms  words=33,021,952
[E03   936/1548 G   4031|CLM] train=2.5466  mask=16.7%  norm=0.715  lr=2.49e-04  dt=  37.3ms  words=33,030,144
[E03   937/1548 G   4032|CLM] train=4.0095  mask=16.7%  norm=0.847  lr=2.49e-04  dt=  37.4ms  words=33,038,336
[E03   938/1548 G   4033|CLM] train=4.6211  mask=16.7%  norm=1.056  lr=2.49e-04  dt=  37.6ms  words=33,046,528
[E03   939/1548 G   4034|CLM] train=4.9002  mask=16.7%  norm=1.036  lr=2.49e-04  dt=  37.3ms  words=33,054,720
[E03   940/1548 G   4035|CLM] train=3.6632  mask=16.7%  norm=0.745  lr=2.49e-04  dt=  37.1ms  words=33,062,912
[E03   941/1548 G   4036|CLM] train=2.5107  mask=16.7%  norm=0.926  lr=2.49e-04  dt=  37.1ms  words=33,071,104
[E03   942/1548 G   4037|CLM] train=2.7651  mask=16.7%  norm=0.717  lr=2.49e-04  dt=  37.5ms  words=33,079,296
[E03   943/1548 G   4038|CLM] train=4.2787  mask=16.7%  norm=0.631  lr=2.48e-04  dt=  37.1ms  words=33,087,488
[E03   944/1548 G   4039|CLM] train=4.5449  mask=16.7%  norm=0.686  lr=2.48e-04  dt=  37.1ms  words=33,095,680
[E03   945/1548 G   4040|CLM] train=4.1756  mask=16.7%  norm=0.861  lr=2.48e-04  dt=  37.1ms  words=33,103,872
[E03   946/1548 G   4041|CLM] train=4.3953  mask=16.7%  norm=0.688  lr=2.48e-04  dt=  37.4ms  words=33,112,064
[E03   947/1548 G   4042|CLM] train=3.7246  mask=16.7%  norm=0.631  lr=2.48e-04  dt=  37.1ms  words=33,120,256
[E03   948/1548 G   4043|CLM] train=2.5880  mask=16.7%  norm=0.794  lr=2.48e-04  dt=  37.1ms  words=33,128,448
[E03   949/1548 G   4044|CLM] train=5.2199  mask=16.7%  norm=1.684  lr=2.48e-04  dt=  37.2ms  words=33,136,640
[E03   950/1548 G   4045|CLM] train=2.7224  mask=16.7%  norm=0.821  lr=2.48e-04  dt=  37.0ms  words=33,144,832
[E03   951/1548 G   4046|CLM] train=2.7341  mask=16.7%  norm=0.700  lr=2.48e-04  dt=  37.2ms  words=33,153,024
[E03   952/1548 G   4047|CLM] train=4.7869  mask=16.7%  norm=0.884  lr=2.48e-04  dt=  37.4ms  words=33,161,216
[E03   953/1548 G   4048|CLM] train=2.4831  mask=16.7%  norm=0.593  lr=2.48e-04  dt=  36.9ms  words=33,169,408
[E03   954/1548 G   4049|CLM] train=2.0831  mask=16.7%  norm=0.594  lr=2.48e-04  dt=  37.1ms  words=33,177,600
[E03   955/1548 G   4050|CLM] train=2.3965  mask=16.7%  norm=0.528  lr=2.48e-04  dt=  37.4ms  words=33,185,792
[E03   956/1548 G   4051|CLM] train=4.0309  mask=16.7%  norm=0.983  lr=2.48e-04  dt=  37.1ms  words=33,193,984
[E03   957/1548 G   4052|CLM] train=2.6655  mask=16.7%  norm=0.779  lr=2.48e-04  dt=  36.9ms  words=33,202,176
[E03   958/1548 G   4053|CLM] train=4.6195  mask=16.7%  norm=1.144  lr=2.48e-04  dt=  37.1ms  words=33,210,368
[E03   959/1548 G   4054|CLM] train=4.7503  mask=16.7%  norm=0.891  lr=2.48e-04  dt=  37.2ms  words=33,218,560
[E03   960/1548 G   4055|CLM] train=4.1481  mask=16.7%  norm=0.905  lr=2.48e-04  dt=  37.1ms  words=33,226,752
[E03   961/1548 G   4056|CLM] train=4.9818  mask=16.7%  norm=0.859  lr=2.48e-04  dt=  37.2ms  words=33,234,944
[E03   962/1548 G   4057|CLM] train=5.0523  mask=16.7%  norm=0.798  lr=2.48e-04  dt=  37.3ms  words=33,243,136
[E03   963/1548 G   4058|CLM] train=4.0227  mask=16.7%  norm=0.805  lr=2.48e-04  dt=  37.1ms  words=33,251,328
[E03   964/1548 G   4059|CLM] train=2.7525  mask=16.7%  norm=0.948  lr=2.48e-04  dt=  37.3ms  words=33,259,520
[E03   965/1548 G   4060|CLM] train=2.6096  mask=16.7%  norm=0.887  lr=2.48e-04  dt=  37.8ms  words=33,267,712
[E03   966/1548 G   4061|CLM] train=2.4315  mask=16.7%  norm=0.726  lr=2.48e-04  dt=  37.0ms  words=33,275,904
[E03   967/1548 G   4062|CLM] train=4.2304  mask=16.7%  norm=0.769  lr=2.48e-04  dt=  37.0ms  words=33,284,096
[E03   968/1548 G   4063|CLM] train=4.2042  mask=16.7%  norm=1.049  lr=2.48e-04  dt=  37.1ms  words=33,292,288
[E03   969/1548 G   4064|CLM] train=5.2971  mask=16.7%  norm=2.727  lr=2.48e-04  dt=  37.5ms  words=33,300,480
[E03   970/1548 G   4065|CLM] train=4.5578  mask=16.7%  norm=0.882  lr=2.48e-04  dt=  37.1ms  words=33,308,672
[E03   971/1548 G   4066|CLM] train=5.7285  mask=16.7%  norm=1.743  lr=2.48e-04  dt=  37.4ms  words=33,316,864
[E03   972/1548 G   4067|CLM] train=4.1223  mask=16.7%  norm=0.670  lr=2.48e-04  dt=  37.0ms  words=33,325,056
[E03   973/1548 G   4068|CLM] train=4.8168  mask=16.7%  norm=0.783  lr=2.48e-04  dt=  37.3ms  words=33,333,248
[E03   974/1548 G   4069|CLM] train=2.5396  mask=16.7%  norm=0.842  lr=2.48e-04  dt=  37.2ms  words=33,341,440
[E03   975/1548 G   4070|CLM] train=4.5202  mask=16.7%  norm=0.705  lr=2.48e-04  dt=  36.9ms  words=33,349,632
[E03   976/1548 G   4071|CLM] train=2.9152  mask=16.7%  norm=0.656  lr=2.48e-04  dt=  37.0ms  words=33,357,824
[E03   977/1548 G   4072|CLM] train=4.4431  mask=16.7%  norm=0.837  lr=2.47e-04  dt=  37.0ms  words=33,366,016
[E03   978/1548 G   4073|CLM] train=4.0507  mask=16.7%  norm=0.797  lr=2.47e-04  dt=  37.2ms  words=33,374,208
[E03   979/1548 G   4074|CLM] train=4.4591  mask=16.7%  norm=0.709  lr=2.47e-04  dt=  37.5ms  words=33,382,400
[E03   980/1548 G   4075|CLM] train=2.5359  mask=16.7%  norm=0.672  lr=2.47e-04  dt=  37.3ms  words=33,390,592
[E03   981/1548 G   4076|CLM] train=3.7270  mask=16.7%  norm=0.714  lr=2.47e-04  dt=  37.2ms  words=33,398,784
[E03   982/1548 G   4077|CLM] train=4.4148  mask=16.7%  norm=0.760  lr=2.47e-04  dt=  37.0ms  words=33,406,976
[E03   983/1548 G   4078|CLM] train=2.6722  mask=16.7%  norm=0.818  lr=2.47e-04  dt=  37.8ms  words=33,415,168
[E03   984/1548 G   4079|CLM] train=2.3317  mask=16.7%  norm=0.756  lr=2.47e-04  dt=  37.1ms  words=33,423,360
[E03   985/1548 G   4080|CLM] train=4.6238  mask=16.7%  norm=0.853  lr=2.47e-04  dt=  38.1ms  words=33,431,552
[E03   986/1548 G   4081|CLM] train=2.4266  mask=16.7%  norm=0.740  lr=2.47e-04  dt=  38.3ms  words=33,439,744
[E03   987/1548 G   4082|CLM] train=4.5137  mask=16.7%  norm=0.801  lr=2.47e-04  dt=  37.3ms  words=33,447,936
[E03   988/1548 G   4083|CLM] train=5.1149  mask=16.7%  norm=0.813  lr=2.47e-04  dt=  37.5ms  words=33,456,128
[E03   989/1548 G   4084|CLM] train=2.1885  mask=16.7%  norm=0.864  lr=2.47e-04  dt=  37.5ms  words=33,464,320
[E03   990/1548 G   4085|CLM] train=3.9998  mask=16.7%  norm=0.779  lr=2.47e-04  dt=  37.1ms  words=33,472,512
[E03   991/1548 G   4086|CLM] train=2.4323  mask=16.7%  norm=0.980  lr=2.47e-04  dt=  36.9ms  words=33,480,704
[E03   992/1548 G   4087|CLM] train=4.0443  mask=16.7%  norm=0.873  lr=2.47e-04  dt=  47.2ms  words=33,488,896
[E03   993/1548 G   4088|CLM] train=2.3169  mask=16.7%  norm=0.764  lr=2.47e-04  dt=  38.5ms  words=33,497,088
[E03   994/1548 G   4089|CLM] train=5.2038  mask=16.7%  norm=0.772  lr=2.47e-04  dt=  39.6ms  words=33,505,280
[E03   995/1548 G   4090|CLM] train=3.9104  mask=16.7%  norm=0.530  lr=2.47e-04  dt=  47.0ms  words=33,513,472
[E03   996/1548 G   4091|CLM] train=5.7426  mask=16.7%  norm=2.836  lr=2.47e-04  dt=  42.6ms  words=33,521,664
[E03   997/1548 G   4092|CLM] train=4.6515  mask=16.7%  norm=0.877  lr=2.47e-04  dt=  41.2ms  words=33,529,856
[E03   998/1548 G   4093|CLM] train=4.6441  mask=16.7%  norm=0.739  lr=2.47e-04  dt=  36.9ms  words=33,538,048
[E03   999/1548 G   4094|CLM] train=2.5164  mask=16.7%  norm=0.985  lr=2.47e-04  dt=  37.0ms  words=33,546,240
[E03  1000/1548 G   4095|CLM] train=4.0631  mask=16.7%  norm=0.665  lr=2.47e-04  dt=  37.0ms  words=33,554,432
[E03  1001/1548 G   4096|CLM] train=2.9972  mask=16.7%  norm=0.663  lr=2.47e-04  dt=  36.9ms  words=33,562,624
[E03  1002/1548 G   4097|CLM] train=4.6940  mask=16.7%  norm=0.751  lr=2.47e-04  dt=  36.8ms  words=33,570,816
[E03  1003/1548 G   4098|CLM] train=3.7698  mask=16.7%  norm=0.640  lr=2.47e-04  dt=  37.2ms  words=33,579,008
[E03  1004/1548 G   4099|CLM] train=3.7315  mask=16.7%  norm=0.661  lr=2.47e-04  dt=  37.0ms  words=33,587,200
[E03  1005/1548 G   4100|CLM] train=2.5019  mask=16.7%  norm=0.831  lr=2.47e-04  dt=  36.8ms  words=33,595,392
[E03  1006/1548 G   4101|CLM] train=2.3857  mask=16.7%  norm=0.649  lr=2.47e-04  dt=  36.9ms  words=33,603,584
[E03  1007/1548 G   4102|CLM] train=4.3111  mask=16.7%  norm=0.648  lr=2.47e-04  dt=  36.8ms  words=33,611,776
[E03  1008/1548 G   4103|CLM] train=3.7076  mask=16.7%  norm=0.563  lr=2.47e-04  dt=  36.9ms  words=33,619,968
[E03  1009/1548 G   4104|CLM] train=4.4302  mask=16.7%  norm=0.654  lr=2.47e-04  dt=  37.0ms  words=33,628,160
[E03  1010/1548 G   4105|CLM] train=4.7621  mask=16.7%  norm=0.652  lr=2.46e-04  dt=  36.7ms  words=33,636,352
[E03  1011/1548 G   4106|CLM] train=4.1245  mask=16.7%  norm=0.571  lr=2.46e-04  dt=  37.0ms  words=33,644,544
[E03  1012/1548 G   4107|CLM] train=2.8801  mask=16.7%  norm=0.633  lr=2.46e-04  dt=  37.1ms  words=33,652,736
[E03  1013/1548 G   4108|CLM] train=3.0059  mask=16.7%  norm=0.658  lr=2.46e-04  dt=  36.9ms  words=33,660,928
[E03  1014/1548 G   4109|CLM] train=4.5517  mask=16.7%  norm=0.650  lr=2.46e-04  dt=  36.8ms  words=33,669,120
[E03  1015/1548 G   4110|CLM] train=4.0069  mask=16.7%  norm=0.585  lr=2.46e-04  dt=  37.0ms  words=33,677,312
[E03  1016/1548 G   4111|CLM] train=4.6827  mask=16.7%  norm=0.710  lr=2.46e-04  dt=  37.0ms  words=33,685,504
[E03  1017/1548 G   4112|CLM] train=2.9496  mask=16.7%  norm=0.949  lr=2.46e-04  dt=  37.0ms  words=33,693,696
[E03  1018/1548 G   4113|CLM] train=3.9761  mask=16.7%  norm=0.706  lr=2.46e-04  dt=  37.1ms  words=33,701,888
[E03  1019/1548 G   4114|CLM] train=4.4063  mask=16.7%  norm=0.739  lr=2.46e-04  dt=  36.9ms  words=33,710,080
[E03  1020/1548 G   4115|CLM] train=2.9460  mask=16.7%  norm=1.007  lr=2.46e-04  dt=  36.9ms  words=33,718,272
[E03  1021/1548 G   4116|CLM] train=3.8728  mask=16.7%  norm=3.646  lr=2.46e-04  dt=  36.7ms  words=33,726,464
[E03  1022/1548 G   4117|CLM] train=4.1241  mask=16.7%  norm=0.651  lr=2.46e-04  dt=  36.7ms  words=33,734,656
[E03  1023/1548 G   4118|CLM] train=3.9006  mask=16.7%  norm=0.705  lr=2.46e-04  dt=  36.9ms  words=33,742,848
[E03  1024/1548 G   4119|CLM] train=2.1776  mask=16.7%  norm=0.933  lr=2.46e-04  dt=  37.1ms  words=33,751,040
[E03  1025/1548 G   4120|CLM] train=2.4747  mask=16.7%  norm=0.887  lr=2.46e-04  dt=  36.8ms  words=33,759,232
[E03  1026/1548 G   4121|CLM] train=2.2898  mask=16.7%  norm=0.777  lr=2.46e-04  dt=  36.9ms  words=33,767,424
[E03  1027/1548 G   4122|CLM] train=5.5338  mask=16.7%  norm=2.050  lr=2.46e-04  dt=  36.9ms  words=33,775,616
[E03  1028/1548 G   4123|CLM] train=5.0652  mask=16.7%  norm=0.760  lr=2.46e-04  dt=  37.0ms  words=33,783,808
[E03  1029/1548 G   4124|CLM] train=5.6114  mask=16.7%  norm=0.698  lr=2.46e-04  dt=  36.8ms  words=33,792,000
[E03  1030/1548 G   4125|CLM] train=3.0237  mask=16.7%  norm=0.931  lr=2.46e-04  dt=  36.9ms  words=33,800,192
[E03  1031/1548 G   4126|CLM] train=5.1955  mask=16.7%  norm=0.822  lr=2.46e-04  dt=  36.9ms  words=33,808,384
[E03  1032/1548 G   4127|CLM] train=2.7019  mask=16.7%  norm=0.736  lr=2.46e-04  dt=  37.0ms  words=33,816,576
[E03  1033/1548 G   4128|CLM] train=4.5292  mask=16.7%  norm=0.716  lr=2.46e-04  dt=  37.0ms  words=33,824,768
[E03  1034/1548 G   4129|CLM] train=4.0793  mask=16.7%  norm=0.766  lr=2.46e-04  dt=  36.9ms  words=33,832,960
[E03  1035/1548 G   4130|CLM] train=4.2133  mask=16.7%  norm=0.903  lr=2.46e-04  dt=  36.8ms  words=33,841,152
[E03  1036/1548 G   4131|CLM] train=2.7157  mask=16.7%  norm=0.904  lr=2.46e-04  dt=  37.0ms  words=33,849,344
[E03  1037/1548 G   4132|CLM] train=4.7803  mask=16.7%  norm=0.870  lr=2.46e-04  dt=  36.7ms  words=33,857,536
[E03  1038/1548 G   4133|CLM] train=4.4621  mask=16.7%  norm=0.773  lr=2.46e-04  dt=  36.9ms  words=33,865,728
[E03  1039/1548 G   4134|CLM] train=2.5984  mask=16.7%  norm=0.996  lr=2.46e-04  dt=  36.8ms  words=33,873,920
[E03  1040/1548 G   4135|CLM] train=2.6072  mask=16.7%  norm=1.221  lr=2.46e-04  dt=  37.0ms  words=33,882,112
[E03  1041/1548 G   4136|CLM] train=2.5903  mask=16.7%  norm=0.689  lr=2.46e-04  dt=  37.0ms  words=33,890,304
[E03  1042/1548 G   4137|CLM] train=4.8256  mask=16.7%  norm=0.975  lr=2.46e-04  dt=  36.8ms  words=33,898,496
[E03  1043/1548 G   4138|CLM] train=4.6393  mask=16.7%  norm=0.820  lr=2.45e-04  dt=  36.9ms  words=33,906,688
[E03  1044/1548 G   4139|CLM] train=2.4195  mask=16.7%  norm=0.878  lr=2.45e-04  dt=  37.0ms  words=33,914,880
[E03  1045/1548 G   4140|CLM] train=2.5563  mask=16.7%  norm=0.760  lr=2.45e-04  dt=  37.4ms  words=33,923,072
[E03  1046/1548 G   4141|CLM] train=2.6245  mask=16.7%  norm=0.712  lr=2.45e-04  dt=  36.9ms  words=33,931,264
[E03  1047/1548 G   4142|CLM] train=2.4011  mask=16.7%  norm=0.746  lr=2.45e-04  dt=  36.9ms  words=33,939,456
[E03  1048/1548 G   4143|CLM] train=4.4010  mask=16.7%  norm=0.814  lr=2.45e-04  dt=  37.0ms  words=33,947,648
[E03  1049/1548 G   4144|CLM] train=4.3577  mask=16.7%  norm=0.890  lr=2.45e-04  dt=  36.9ms  words=33,955,840
[E03  1050/1548 G   4145|CLM] train=4.3813  mask=16.7%  norm=0.764  lr=2.45e-04  dt=  36.9ms  words=33,964,032
[E03  1051/1548 G   4146|CLM] train=4.8260  mask=16.7%  norm=0.748  lr=2.45e-04  dt=  36.8ms  words=33,972,224
[E03  1052/1548 G   4147|CLM] train=5.1448  mask=16.7%  norm=1.060  lr=2.45e-04  dt=  36.9ms  words=33,980,416
[E03  1053/1548 G   4148|CLM] train=4.5531  mask=16.7%  norm=0.798  lr=2.45e-04  dt=  36.8ms  words=33,988,608
[E03  1054/1548 G   4149|CLM] train=4.6413  mask=16.6%  norm=0.635  lr=2.45e-04  dt=  36.7ms  words=33,996,800
[E03  1055/1548 G   4150|CLM] train=2.8478  mask=16.6%  norm=0.993  lr=2.45e-04  dt=  37.0ms  words=34,004,992
[E03  1056/1548 G   4151|CLM] train=4.1002  mask=16.6%  norm=0.721  lr=2.45e-04  dt=  36.8ms  words=34,013,184
[E03  1057/1548 G   4152|CLM] train=4.5697  mask=16.6%  norm=0.645  lr=2.45e-04  dt=  37.1ms  words=34,021,376
[E03  1058/1548 G   4153|CLM] train=4.9849  mask=16.6%  norm=1.040  lr=2.45e-04  dt=  36.7ms  words=34,029,568
[E03  1059/1548 G   4154|CLM] train=2.8051  mask=16.6%  norm=0.811  lr=2.45e-04  dt=  36.9ms  words=34,037,760
[E03  1060/1548 G   4155|CLM] train=4.4763  mask=16.6%  norm=0.691  lr=2.45e-04  dt=  37.0ms  words=34,045,952
[E03  1061/1548 G   4156|CLM] train=2.3385  mask=16.6%  norm=0.779  lr=2.45e-04  dt=  37.0ms  words=34,054,144
[E03  1062/1548 G   4157|CLM] train=4.8755  mask=16.6%  norm=1.127  lr=2.45e-04  dt=  36.8ms  words=34,062,336
[E03  1063/1548 G   4158|CLM] train=4.8199  mask=16.6%  norm=0.736  lr=2.45e-04  dt=  36.9ms  words=34,070,528
[E03  1064/1548 G   4159|CLM] train=4.9700  mask=16.6%  norm=1.008  lr=2.45e-04  dt=  36.9ms  words=34,078,720
[E03  1065/1548 G   4160|CLM] train=4.1514  mask=16.6%  norm=0.838  lr=2.45e-04  dt=  36.9ms  words=34,086,912
[E03  1066/1548 G   4161|CLM] train=5.2398  mask=16.6%  norm=0.931  lr=2.45e-04  dt=  36.9ms  words=34,095,104
[E03  1067/1548 G   4162|CLM] train=4.8987  mask=16.6%  norm=0.696  lr=2.45e-04  dt=  36.9ms  words=34,103,296
[E03  1068/1548 G   4163|CLM] train=2.3700  mask=16.6%  norm=0.694  lr=2.45e-04  dt=  37.0ms  words=34,111,488
[E03  1069/1548 G   4164|CLM] train=2.7384  mask=16.6%  norm=0.774  lr=2.45e-04  dt=  36.8ms  words=34,119,680
[E03  1070/1548 G   4165|CLM] train=3.8126  mask=16.6%  norm=0.678  lr=2.45e-04  dt=  36.8ms  words=34,127,872
[E03  1071/1548 G   4166|CLM] train=4.6010  mask=16.6%  norm=0.761  lr=2.45e-04  dt=  37.1ms  words=34,136,064
[E03  1072/1548 G   4167|CLM] train=4.5230  mask=16.6%  norm=0.956  lr=2.45e-04  dt=  37.5ms  words=34,144,256
[E03  1073/1548 G   4168|CLM] train=4.6899  mask=16.6%  norm=0.837  lr=2.45e-04  dt=  36.8ms  words=34,152,448
[E03  1074/1548 G   4169|CLM] train=4.1647  mask=16.6%  norm=0.729  lr=2.45e-04  dt=  36.6ms  words=34,160,640
[E03  1075/1548 G   4170|CLM] train=4.1044  mask=16.6%  norm=0.758  lr=2.45e-04  dt=  37.0ms  words=34,168,832
[E03  1076/1548 G   4171|CLM] train=2.5795  mask=16.6%  norm=0.774  lr=2.44e-04  dt=  36.9ms  words=34,177,024
[E03  1077/1548 G   4172|CLM] train=4.0108  mask=16.6%  norm=0.742  lr=2.44e-04  dt=  36.8ms  words=34,185,216
[E03  1078/1548 G   4173|CLM] train=4.0297  mask=16.6%  norm=0.643  lr=2.44e-04  dt=  36.7ms  words=34,193,408
[E03  1079/1548 G   4174|CLM] train=2.5033  mask=16.6%  norm=0.755  lr=2.44e-04  dt=  36.8ms  words=34,201,600
[E03  1080/1548 G   4175|CLM] train=2.5183  mask=16.6%  norm=0.766  lr=2.44e-04  dt=  36.8ms  words=34,209,792
[E03  1081/1548 G   4176|CLM] train=4.4946  mask=16.6%  norm=0.702  lr=2.44e-04  dt=  37.0ms  words=34,217,984
[E03  1082/1548 G   4177|CLM] train=2.4873  mask=16.6%  norm=0.788  lr=2.44e-04  dt=  36.7ms  words=34,226,176
[E03  1083/1548 G   4178|CLM] train=4.7224  mask=16.6%  norm=0.841  lr=2.44e-04  dt=  36.7ms  words=34,234,368
[E03  1084/1548 G   4179|CLM] train=5.3849  mask=16.6%  norm=0.965  lr=2.44e-04  dt=  37.0ms  words=34,242,560
[E03  1085/1548 G   4180|CLM] train=4.4391  mask=16.6%  norm=0.781  lr=2.44e-04  dt=  36.9ms  words=34,250,752
[E03  1086/1548 G   4181|CLM] train=2.0234  mask=16.6%  norm=0.826  lr=2.44e-04  dt=  36.8ms  words=34,258,944
[E03  1087/1548 G   4182|CLM] train=6.0606  mask=16.6%  norm=2.155  lr=2.44e-04  dt=  36.8ms  words=34,267,136
[E03  1088/1548 G   4183|CLM] train=4.7046  mask=16.6%  norm=0.707  lr=2.44e-04  dt=  36.9ms  words=34,275,328
[E03  1089/1548 G   4184|CLM] train=2.3950  mask=16.6%  norm=0.664  lr=2.44e-04  dt=  37.0ms  words=34,283,520
[E03  1090/1548 G   4185|CLM] train=4.7813  mask=16.6%  norm=0.848  lr=2.44e-04  dt=  36.8ms  words=34,291,712
[E03  1091/1548 G   4186|CLM] train=4.3217  mask=16.6%  norm=1.110  lr=2.44e-04  dt=  36.9ms  words=34,299,904
[E03  1092/1548 G   4187|CLM] train=3.8737  mask=16.6%  norm=0.685  lr=2.44e-04  dt=  37.0ms  words=34,308,096
[E03  1093/1548 G   4188|CLM] train=3.0800  mask=16.6%  norm=1.007  lr=2.44e-04  dt=  36.9ms  words=34,316,288
[E03  1094/1548 G   4189|CLM] train=4.7397  mask=16.6%  norm=0.769  lr=2.44e-04  dt=  36.8ms  words=34,324,480
[E03  1095/1548 G   4190|CLM] train=2.6402  mask=16.6%  norm=0.739  lr=2.44e-04  dt=  36.8ms  words=34,332,672
[E03  1096/1548 G   4191|CLM] train=3.0664  mask=16.6%  norm=0.595  lr=2.44e-04  dt=  36.9ms  words=34,340,864
[E03  1097/1548 G   4192|CLM] train=4.7196  mask=16.6%  norm=0.876  lr=2.44e-04  dt=  38.1ms  words=34,349,056
[E03  1098/1548 G   4193|CLM] train=3.2624  mask=16.6%  norm=0.776  lr=2.44e-04  dt=  36.7ms  words=34,357,248
[E03  1099/1548 G   4194|CLM] train=2.4314  mask=16.6%  norm=0.621  lr=2.44e-04  dt=  37.6ms  words=34,365,440
[E03  1100/1548 G   4195|CLM] train=2.1661  mask=16.6%  norm=0.647  lr=2.44e-04  dt=  36.9ms  words=34,373,632
[E03  1101/1548 G   4196|CLM] train=5.2029  mask=16.6%  norm=0.777  lr=2.44e-04  dt=  36.6ms  words=34,381,824
[E03  1102/1548 G   4197|CLM] train=4.0634  mask=16.6%  norm=0.703  lr=2.44e-04  dt=  36.8ms  words=34,390,016
[E03  1103/1548 G   4198|CLM] train=2.6238  mask=16.6%  norm=0.743  lr=2.44e-04  dt=  36.9ms  words=34,398,208
[E03  1104/1548 G   4199|CLM] train=4.2787  mask=16.6%  norm=0.655  lr=2.44e-04  dt=  37.0ms  words=34,406,400
[E03  1105/1548 G   4200|CLM] train=4.7597  mask=16.6%  norm=0.729  lr=2.44e-04  dt=  36.9ms  words=34,414,592
[E03  1106/1548 G   4201|CLM] train=4.8469  mask=16.6%  norm=0.813  lr=2.44e-04  dt=  36.7ms  words=34,422,784
[E03  1107/1548 G   4202|CLM] train=4.1849  mask=16.6%  norm=0.595  lr=2.44e-04  dt=  36.9ms  words=34,430,976
[E03  1108/1548 G   4203|CLM] train=4.5348  mask=16.6%  norm=0.885  lr=2.44e-04  dt=  36.9ms  words=34,439,168
[E03  1109/1548 G   4204|CLM] train=4.2980  mask=16.6%  norm=0.583  lr=2.43e-04  dt=  37.0ms  words=34,447,360
[E03  1110/1548 G   4205|CLM] train=5.2036  mask=16.6%  norm=0.817  lr=2.43e-04  dt=  36.7ms  words=34,455,552
[E03  1111/1548 G   4206|CLM] train=4.0833  mask=16.6%  norm=0.603  lr=2.43e-04  dt=  37.5ms  words=34,463,744
[E03  1112/1548 G   4207|CLM] train=2.9166  mask=16.6%  norm=0.945  lr=2.43e-04  dt=  36.9ms  words=34,471,936
[E03  1113/1548 G   4208|CLM] train=2.2342  mask=16.6%  norm=0.944  lr=2.43e-04  dt=  38.0ms  words=34,480,128
[E03  1114/1548 G   4209|CLM] train=2.9897  mask=16.6%  norm=0.816  lr=2.43e-04  dt=  37.4ms  words=34,488,320
[E03  1115/1548 G   4210|CLM] train=4.3487  mask=16.6%  norm=0.896  lr=2.43e-04  dt=  37.8ms  words=34,496,512
[E03  1116/1548 G   4211|CLM] train=5.8893  mask=16.6%  norm=1.052  lr=2.43e-04  dt=  39.0ms  words=34,504,704
[E03  1117/1548 G   4212|CLM] train=2.8475  mask=16.6%  norm=1.223  lr=2.43e-04  dt=  41.0ms  words=34,512,896
[E03  1118/1548 G   4213|CLM] train=4.3066  mask=16.6%  norm=0.733  lr=2.43e-04  dt=  42.3ms  words=34,521,088
[E03  1119/1548 G   4214|CLM] train=4.1486  mask=16.6%  norm=0.761  lr=2.43e-04  dt=  39.8ms  words=34,529,280
[E03  1120/1548 G   4215|CLM] train=2.9938  mask=16.6%  norm=0.857  lr=2.43e-04  dt=  42.1ms  words=34,537,472
[E03  1121/1548 G   4216|CLM] train=4.1507  mask=16.6%  norm=0.850  lr=2.43e-04  dt=  40.1ms  words=34,545,664
[E03  1122/1548 G   4217|CLM] train=4.7247  mask=16.6%  norm=0.982  lr=2.43e-04  dt=  39.2ms  words=34,553,856
[E03  1123/1548 G   4218|CLM] train=2.6495  mask=16.6%  norm=1.082  lr=2.43e-04  dt=  42.7ms  words=34,562,048
[E03  1124/1548 G   4219|CLM] train=4.9356  mask=16.6%  norm=1.063  lr=2.43e-04  dt=  42.6ms  words=34,570,240
[E03  1125/1548 G   4220|CLM] train=4.2231  mask=16.6%  norm=1.048  lr=2.43e-04  dt=  41.3ms  words=34,578,432
[E03  1126/1548 G   4221|CLM] train=2.6900  mask=16.6%  norm=0.908  lr=2.43e-04  dt=  37.0ms  words=34,586,624
[E03  1127/1548 G   4222|CLM] train=3.9805  mask=16.6%  norm=0.685  lr=2.43e-04  dt=  37.1ms  words=34,594,816
[E03  1128/1548 G   4223|CLM] train=2.4544  mask=16.6%  norm=0.845  lr=2.43e-04  dt=  37.2ms  words=34,603,008
[E03  1129/1548 G   4224|CLM] train=4.9137  mask=16.6%  norm=1.165  lr=2.43e-04  dt=  36.8ms  words=34,611,200
[E03  1130/1548 G   4225|CLM] train=4.8564  mask=16.6%  norm=0.734  lr=2.43e-04  dt=  36.7ms  words=34,619,392
[E03  1131/1548 G   4226|CLM] train=4.0408  mask=16.6%  norm=0.713  lr=2.43e-04  dt=  37.0ms  words=34,627,584
[E03  1132/1548 G   4227|CLM] train=2.8793  mask=16.6%  norm=0.738  lr=2.43e-04  dt=  37.0ms  words=34,635,776
[E03  1133/1548 G   4228|CLM] train=2.7755  mask=16.6%  norm=0.821  lr=2.43e-04  dt=  36.7ms  words=34,643,968
[E03  1134/1548 G   4229|CLM] train=4.5677  mask=16.6%  norm=0.757  lr=2.43e-04  dt=  36.8ms  words=34,652,160
[E03  1135/1548 G   4230|CLM] train=5.2302  mask=16.6%  norm=1.033  lr=2.43e-04  dt=  36.8ms  words=34,660,352
[E03  1136/1548 G   4231|CLM] train=4.3471  mask=16.6%  norm=0.843  lr=2.43e-04  dt=  36.9ms  words=34,668,544
[E03  1137/1548 G   4232|CLM] train=2.8419  mask=16.6%  norm=1.070  lr=2.43e-04  dt=  36.9ms  words=34,676,736
[E03  1138/1548 G   4233|CLM] train=4.2002  mask=16.6%  norm=0.862  lr=2.43e-04  dt=  36.7ms  words=34,684,928
[E03  1139/1548 G   4234|CLM] train=4.7913  mask=16.6%  norm=0.719  lr=2.43e-04  dt=  37.3ms  words=34,693,120
[E03  1140/1548 G   4235|CLM] train=4.7215  mask=16.6%  norm=0.756  lr=2.43e-04  dt=  37.1ms  words=34,701,312
[E03  1141/1548 G   4236|CLM] train=4.3116  mask=16.6%  norm=0.607  lr=2.42e-04  dt=  37.0ms  words=34,709,504
[E03  1142/1548 G   4237|CLM] train=4.0533  mask=16.6%  norm=0.782  lr=2.42e-04  dt=  36.9ms  words=34,717,696
[E03  1143/1548 G   4238|CLM] train=2.7150  mask=16.6%  norm=0.622  lr=2.42e-04  dt=  38.3ms  words=34,725,888
[E03  1144/1548 G   4239|CLM] train=2.4870  mask=16.6%  norm=0.646  lr=2.42e-04  dt=  42.8ms  words=34,734,080
[E03  1145/1548 G   4240|CLM] train=1.9569  mask=16.6%  norm=0.807  lr=2.42e-04  dt=  38.5ms  words=34,742,272
[E03  1146/1548 G   4241|CLM] train=5.7471  mask=16.6%  norm=1.039  lr=2.42e-04  dt=  38.0ms  words=34,750,464
[E03  1147/1548 G   4242|CLM] train=2.7642  mask=16.6%  norm=0.651  lr=2.42e-04  dt=  41.4ms  words=34,758,656
[E03  1148/1548 G   4243|CLM] train=4.4494  mask=16.6%  norm=0.847  lr=2.42e-04  dt=  42.9ms  words=34,766,848
[E03  1149/1548 G   4244|CLM] train=2.5984  mask=16.6%  norm=0.674  lr=2.42e-04  dt=  43.6ms  words=34,775,040
[E03  1150/1548 G   4245|CLM] train=2.6927  mask=16.6%  norm=0.621  lr=2.42e-04  dt=  42.1ms  words=34,783,232
[E03  1151/1548 G   4246|CLM] train=4.4357  mask=16.6%  norm=0.850  lr=2.42e-04  dt=  41.6ms  words=34,791,424
[E03  1152/1548 G   4247|CLM] train=4.7266  mask=16.6%  norm=0.864  lr=2.42e-04  dt=  36.9ms  words=34,799,616
[E03  1153/1548 G   4248|CLM] train=4.3270  mask=16.6%  norm=0.643  lr=2.42e-04  dt=  36.9ms  words=34,807,808
[E03  1154/1548 G   4249|CLM] train=4.6601  mask=16.6%  norm=0.668  lr=2.42e-04  dt=  37.1ms  words=34,816,000
[E03  1155/1548 G   4250|CLM] train=4.9304  mask=16.6%  norm=0.862  lr=2.42e-04  dt=  38.2ms  words=34,824,192
[E03  1156/1548 G   4251|CLM] train=2.4090  mask=16.6%  norm=0.569  lr=2.42e-04  dt=  36.9ms  words=34,832,384
[E03  1157/1548 G   4252|CLM] train=4.7657  mask=16.6%  norm=0.768  lr=2.42e-04  dt=  37.2ms  words=34,840,576
[E03  1158/1548 G   4253|CLM] train=4.9226  mask=16.6%  norm=0.777  lr=2.42e-04  dt=  46.2ms  words=34,848,768
[E03  1159/1548 G   4254|CLM] train=3.7489  mask=16.6%  norm=0.746  lr=2.42e-04  dt=  46.2ms  words=34,856,960
[E03  1160/1548 G   4255|CLM] train=4.5378  mask=16.6%  norm=0.782  lr=2.42e-04  dt=  37.0ms  words=34,865,152
[E03  1161/1548 G   4256|CLM] train=5.5394  mask=16.6%  norm=0.931  lr=2.42e-04  dt=  37.3ms  words=34,873,344
[E03  1162/1548 G   4257|CLM] train=2.9132  mask=16.6%  norm=0.810  lr=2.42e-04  dt=  37.0ms  words=34,881,536
[E03  1163/1548 G   4258|CLM] train=4.5302  mask=16.6%  norm=0.883  lr=2.42e-04  dt=  37.1ms  words=34,889,728
[E03  1164/1548 G   4259|CLM] train=2.5212  mask=16.6%  norm=0.520  lr=2.42e-04  dt=  37.0ms  words=34,897,920
[E03  1165/1548 G   4260|CLM] train=5.1795  mask=16.6%  norm=0.724  lr=2.42e-04  dt=  36.8ms  words=34,906,112
[E03  1166/1548 G   4261|CLM] train=2.5083  mask=16.6%  norm=0.719  lr=2.42e-04  dt=  37.0ms  words=34,914,304
[E03  1167/1548 G   4262|CLM] train=5.0105  mask=16.6%  norm=0.937  lr=2.42e-04  dt=  36.8ms  words=34,922,496
[E03  1168/1548 G   4263|CLM] train=2.2978  mask=16.6%  norm=0.562  lr=2.42e-04  dt=  36.9ms  words=34,930,688
[E03  1169/1548 G   4264|CLM] train=2.3628  mask=16.6%  norm=0.553  lr=2.42e-04  dt=  37.0ms  words=34,938,880
[E03  1170/1548 G   4265|CLM] train=4.2837  mask=16.6%  norm=0.723  lr=2.42e-04  dt=  37.0ms  words=34,947,072
[E03  1171/1548 G   4266|CLM] train=2.3579  mask=16.6%  norm=0.527  lr=2.42e-04  dt=  36.8ms  words=34,955,264
[E03  1172/1548 G   4267|CLM] train=2.6799  mask=16.6%  norm=0.893  lr=2.42e-04  dt=  36.9ms  words=34,963,456
[E03  1173/1548 G   4268|CLM] train=3.9579  mask=16.6%  norm=3.042  lr=2.41e-04  dt=  36.9ms  words=34,971,648
[E03  1174/1548 G   4269|CLM] train=4.2974  mask=16.6%  norm=0.898  lr=2.41e-04  dt=  37.0ms  words=34,979,840
[E03  1175/1548 G   4270|CLM] train=3.9152  mask=16.6%  norm=0.849  lr=2.41e-04  dt=  36.7ms  words=34,988,032
[E03  1176/1548 G   4271|CLM] train=4.5740  mask=16.6%  norm=1.214  lr=2.41e-04  dt=  36.9ms  words=34,996,224
[E03  1177/1548 G   4272|CLM] train=2.5413  mask=16.6%  norm=0.978  lr=2.41e-04  dt=  37.4ms  words=35,004,416
[E03  1178/1548 G   4273|CLM] train=4.7298  mask=16.5%  norm=0.927  lr=2.41e-04  dt=  37.2ms  words=35,012,608
[E03  1179/1548 G   4274|CLM] train=5.0616  mask=16.5%  norm=1.140  lr=2.41e-04  dt=  37.0ms  words=35,020,800
[E03  1180/1548 G   4275|CLM] train=4.4318  mask=16.5%  norm=0.912  lr=2.41e-04  dt=  36.9ms  words=35,028,992
[E03  1181/1548 G   4276|CLM] train=4.5372  mask=16.5%  norm=0.819  lr=2.41e-04  dt=  37.0ms  words=35,037,184
[E03  1182/1548 G   4277|CLM] train=5.4942  mask=16.5%  norm=1.644  lr=2.41e-04  dt=  36.9ms  words=35,045,376
[E03  1183/1548 G   4278|CLM] train=5.0218  mask=16.5%  norm=0.741  lr=2.41e-04  dt=  37.0ms  words=35,053,568
[E03  1184/1548 G   4279|CLM] train=4.5779  mask=16.5%  norm=1.168  lr=2.41e-04  dt=  36.9ms  words=35,061,760
[E03  1185/1548 G   4280|CLM] train=4.8168  mask=16.5%  norm=0.793  lr=2.41e-04  dt=  37.0ms  words=35,069,952
[E03  1186/1548 G   4281|CLM] train=4.3950  mask=16.5%  norm=1.315  lr=2.41e-04  dt=  36.9ms  words=35,078,144
[E03  1187/1548 G   4282|CLM] train=2.7943  mask=16.5%  norm=0.843  lr=2.41e-04  dt=  36.9ms  words=35,086,336
[E03  1188/1548 G   4283|CLM] train=2.3851  mask=16.5%  norm=0.761  lr=2.41e-04  dt=  36.9ms  words=35,094,528
[E03  1189/1548 G   4284|CLM] train=3.8537  mask=16.5%  norm=0.853  lr=2.41e-04  dt=  36.9ms  words=35,102,720
[E03  1190/1548 G   4285|CLM] train=2.2314  mask=16.5%  norm=0.700  lr=2.41e-04  dt=  37.3ms  words=35,110,912
[E03  1191/1548 G   4286|CLM] train=4.4638  mask=16.5%  norm=1.078  lr=2.41e-04  dt=  37.0ms  words=35,119,104
[E03  1192/1548 G   4287|CLM] train=4.6395  mask=16.5%  norm=0.837  lr=2.41e-04  dt=  37.2ms  words=35,127,296
[E03  1193/1548 G   4288|CLM] train=2.1971  mask=16.5%  norm=0.649  lr=2.41e-04  dt=  37.0ms  words=35,135,488
[E03  1194/1548 G   4289|CLM] train=2.5532  mask=16.5%  norm=0.755  lr=2.41e-04  dt=  36.9ms  words=35,143,680
[E03  1195/1548 G   4290|CLM] train=4.0292  mask=16.5%  norm=0.684  lr=2.41e-04  dt=  37.0ms  words=35,151,872
[E03  1196/1548 G   4291|CLM] train=4.3956  mask=16.5%  norm=1.192  lr=2.41e-04  dt=  37.0ms  words=35,160,064
[E03  1197/1548 G   4292|CLM] train=4.1701  mask=16.5%  norm=0.943  lr=2.41e-04  dt=  36.9ms  words=35,168,256
[E03  1198/1548 G   4293|CLM] train=5.2743  mask=16.5%  norm=1.080  lr=2.41e-04  dt=  36.9ms  words=35,176,448
[E03  1199/1548 G   4294|CLM] train=4.6902  mask=16.5%  norm=1.020  lr=2.41e-04  dt=  37.0ms  words=35,184,640
[E03  1200/1548 G   4295|CLM] train=4.1559  mask=16.5%  norm=0.689  lr=2.41e-04  dt=  37.0ms  words=35,192,832
[E03  1201/1548 G   4296|CLM] train=4.1702  mask=16.5%  norm=0.702  lr=2.41e-04  dt=  36.9ms  words=35,201,024
[E03  1202/1548 G   4297|CLM] train=3.0149  mask=16.5%  norm=1.580  lr=2.41e-04  dt=  36.9ms  words=35,209,216
[E03  1203/1548 G   4298|CLM] train=4.4643  mask=16.5%  norm=0.833  lr=2.41e-04  dt=  37.3ms  words=35,217,408
[E03  1204/1548 G   4299|CLM] train=4.8941  mask=16.5%  norm=0.958  lr=2.41e-04  dt=  37.0ms  words=35,225,600
[E03  1205/1548 G   4300|CLM] train=5.2418  mask=16.5%  norm=0.977  lr=2.40e-04  dt=  36.9ms  words=35,233,792
[E03  1206/1548 G   4301|CLM] train=4.4134  mask=16.5%  norm=0.926  lr=2.40e-04  dt=  37.2ms  words=35,241,984
[E03  1207/1548 G   4302|CLM] train=4.3494  mask=16.5%  norm=0.670  lr=2.40e-04  dt=  37.1ms  words=35,250,176
[E03  1208/1548 G   4303|CLM] train=5.9284  mask=16.5%  norm=1.482  lr=2.40e-04  dt=  37.0ms  words=35,258,368
[E03  1209/1548 G   4304|CLM] train=4.5688  mask=16.5%  norm=0.706  lr=2.40e-04  dt=  36.9ms  words=35,266,560
[E03  1210/1548 G   4305|CLM] train=2.4597  mask=16.5%  norm=0.922  lr=2.40e-04  dt=  36.9ms  words=35,274,752
[E03  1211/1548 G   4306|CLM] train=4.6404  mask=16.5%  norm=0.814  lr=2.40e-04  dt=  37.0ms  words=35,282,944
[E03  1212/1548 G   4307|CLM] train=4.2589  mask=16.5%  norm=1.077  lr=2.40e-04  dt=  37.0ms  words=35,291,136
[E03  1213/1548 G   4308|CLM] train=5.2879  mask=16.5%  norm=0.924  lr=2.40e-04  dt=  36.8ms  words=35,299,328
[E03  1214/1548 G   4309|CLM] train=2.5721  mask=16.5%  norm=0.950  lr=2.40e-04  dt=  36.9ms  words=35,307,520
[E03  1215/1548 G   4310|CLM] train=4.4819  mask=16.5%  norm=0.691  lr=2.40e-04  dt=  37.0ms  words=35,315,712
[E03  1216/1548 G   4311|CLM] train=4.6138  mask=16.5%  norm=0.809  lr=2.40e-04  dt=  36.9ms  words=35,323,904
[E03  1217/1548 G   4312|CLM] train=4.4738  mask=16.5%  norm=0.895  lr=2.40e-04  dt=  37.0ms  words=35,332,096
[E03  1218/1548 G   4313|CLM] train=2.0662  mask=16.5%  norm=0.839  lr=2.40e-04  dt=  36.9ms  words=35,340,288
[E03  1219/1548 G   4314|CLM] train=2.4419  mask=16.5%  norm=1.060  lr=2.40e-04  dt=  37.1ms  words=35,348,480
[E03  1220/1548 G   4315|CLM] train=4.0737  mask=16.5%  norm=0.623  lr=2.40e-04  dt=  37.2ms  words=35,356,672
[E03  1221/1548 G   4316|CLM] train=2.6320  mask=16.5%  norm=0.823  lr=2.40e-04  dt=  37.1ms  words=35,364,864
[E03  1222/1548 G   4317|CLM] train=4.4485  mask=16.5%  norm=0.825  lr=2.40e-04  dt=  37.0ms  words=35,373,056
[E03  1223/1548 G   4318|CLM] train=4.7528  mask=16.5%  norm=0.882  lr=2.40e-04  dt=  36.9ms  words=35,381,248
[E03  1224/1548 G   4319|CLM] train=5.7126  mask=16.5%  norm=1.331  lr=2.40e-04  dt=  36.9ms  words=35,389,440
[E03  1225/1548 G   4320|CLM] train=2.8526  mask=16.5%  norm=1.305  lr=2.40e-04  dt=  37.0ms  words=35,397,632
[E03  1226/1548 G   4321|CLM] train=2.5742  mask=16.5%  norm=0.668  lr=2.40e-04  dt=  37.1ms  words=35,405,824
[E03  1227/1548 G   4322|CLM] train=4.2277  mask=16.5%  norm=0.695  lr=2.40e-04  dt=  36.9ms  words=35,414,016
[E03  1228/1548 G   4323|CLM] train=2.5056  mask=16.5%  norm=0.738  lr=2.40e-04  dt=  36.9ms  words=35,422,208
[E03  1229/1548 G   4324|CLM] train=5.0818  mask=16.5%  norm=0.852  lr=2.40e-04  dt=  36.9ms  words=35,430,400
[E03  1230/1548 G   4325|CLM] train=2.9783  mask=16.5%  norm=0.678  lr=2.40e-04  dt=  37.0ms  words=35,438,592
[E03  1231/1548 G   4326|CLM] train=3.8584  mask=16.5%  norm=0.590  lr=2.40e-04  dt=  37.0ms  words=35,446,784
[E03  1232/1548 G   4327|CLM] train=4.4198  mask=16.5%  norm=0.687  lr=2.40e-04  dt=  36.9ms  words=35,454,976
[E03  1233/1548 G   4328|CLM] train=2.4321  mask=16.5%  norm=0.633  lr=2.40e-04  dt=  36.9ms  words=35,463,168
[E03  1234/1548 G   4329|CLM] train=5.2577  mask=16.5%  norm=0.929  lr=2.40e-04  dt=  36.9ms  words=35,471,360
[E03  1235/1548 G   4330|CLM] train=2.7999  mask=16.5%  norm=0.640  lr=2.40e-04  dt=  36.9ms  words=35,479,552
[E03  1236/1548 G   4331|CLM] train=2.5457  mask=16.5%  norm=0.577  lr=2.40e-04  dt=  36.9ms  words=35,487,744
[E03  1237/1548 G   4332|CLM] train=3.0895  mask=16.5%  norm=0.597  lr=2.39e-04  dt=  36.9ms  words=35,495,936
[E03  1238/1548 G   4333|CLM] train=4.2672  mask=16.5%  norm=0.963  lr=2.39e-04  dt=  37.0ms  words=35,504,128
[E03  1239/1548 G   4334|CLM] train=4.9367  mask=16.5%  norm=0.984  lr=2.39e-04  dt=  37.2ms  words=35,512,320
[E03  1240/1548 G   4335|CLM] train=4.9745  mask=16.5%  norm=0.747  lr=2.39e-04  dt=  37.1ms  words=35,520,512
[E03  1241/1548 G   4336|CLM] train=4.8221  mask=16.5%  norm=0.832  lr=2.39e-04  dt=  36.9ms  words=35,528,704
[E03  1242/1548 G   4337|CLM] train=5.2209  mask=16.5%  norm=0.868  lr=2.39e-04  dt=  37.0ms  words=35,536,896
[E03  1243/1548 G   4338|CLM] train=2.6940  mask=16.5%  norm=0.795  lr=2.39e-04  dt=  36.8ms  words=35,545,088
[E03  1244/1548 G   4339|CLM] train=2.2921  mask=16.5%  norm=0.907  lr=2.39e-04  dt=  37.1ms  words=35,553,280
[E03  1245/1548 G   4340|CLM] train=2.3016  mask=16.5%  norm=0.975  lr=2.39e-04  dt=  37.5ms  words=35,561,472
[E03  1246/1548 G   4341|CLM] train=2.8343  mask=16.5%  norm=1.529  lr=2.39e-04  dt=  46.6ms  words=35,569,664
[E03  1247/1548 G   4342|CLM] train=4.4149  mask=16.5%  norm=0.949  lr=2.39e-04  dt=  47.6ms  words=35,577,856
[E03  1248/1548 G   4343|CLM] train=4.1867  mask=16.5%  norm=1.054  lr=2.39e-04  dt=  47.4ms  words=35,586,048
[E03  1249/1548 G   4344|CLM] train=4.0651  mask=16.5%  norm=4.454  lr=2.39e-04  dt=  45.7ms  words=35,594,240
[E03  1250/1548 G   4345|CLM] train=5.2444  mask=16.5%  norm=1.547  lr=2.39e-04  dt=  50.1ms  words=35,602,432
[E03  1251/1548 G   4346|CLM] train=3.0885  mask=16.5%  norm=0.785  lr=2.39e-04  dt=  42.7ms  words=35,610,624
[E03  1252/1548 G   4347|CLM] train=4.4652  mask=16.5%  norm=0.978  lr=2.39e-04  dt=  37.1ms  words=35,618,816
[E03  1253/1548 G   4348|CLM] train=4.6408  mask=16.5%  norm=1.064  lr=2.39e-04  dt=  46.9ms  words=35,627,008
[E03  1254/1548 G   4349|CLM] train=4.4742  mask=16.5%  norm=0.816  lr=2.39e-04  dt=  46.6ms  words=35,635,200
[E03  1255/1548 G   4350|CLM] train=2.8396  mask=16.5%  norm=1.691  lr=2.39e-04  dt=  46.9ms  words=35,643,392
[E03  1256/1548 G   4351|CLM] train=4.6669  mask=16.5%  norm=0.738  lr=2.39e-04  dt=  37.9ms  words=35,651,584
[E03  1257/1548 G   4352|CLM] train=2.4450  mask=16.5%  norm=0.821  lr=2.39e-04  dt=  44.7ms  words=35,659,776
[E03  1258/1548 G   4353|CLM] train=4.6366  mask=16.5%  norm=0.912  lr=2.39e-04  dt=  47.7ms  words=35,667,968
[E03  1259/1548 G   4354|CLM] train=5.0172  mask=16.5%  norm=2.671  lr=2.39e-04  dt=  41.8ms  words=35,676,160
[E03  1260/1548 G   4355|CLM] train=5.0824  mask=16.5%  norm=1.009  lr=2.39e-04  dt=  47.0ms  words=35,684,352
[E03  1261/1548 G   4356|CLM] train=2.3987  mask=16.5%  norm=1.227  lr=2.39e-04  dt=  42.7ms  words=35,692,544
[E03  1262/1548 G   4357|CLM] train=4.7249  mask=16.5%  norm=0.686  lr=2.39e-04  dt=  37.2ms  words=35,700,736
[E03  1263/1548 G   4358|CLM] train=4.4445  mask=16.5%  norm=0.762  lr=2.39e-04  dt=  46.9ms  words=35,708,928
[E03  1264/1548 G   4359|CLM] train=4.4729  mask=16.5%  norm=0.832  lr=2.39e-04  dt=  37.0ms  words=35,717,120
[E03  1265/1548 G   4360|CLM] train=4.7268  mask=16.5%  norm=0.876  lr=2.39e-04  dt=  37.0ms  words=35,725,312
[E03  1266/1548 G   4361|CLM] train=2.2503  mask=16.5%  norm=0.766  lr=2.39e-04  dt=  37.3ms  words=35,733,504
[E03  1267/1548 G   4362|CLM] train=4.2524  mask=16.5%  norm=0.688  lr=2.39e-04  dt=  39.1ms  words=35,741,696
[E03  1268/1548 G   4363|CLM] train=4.3136  mask=16.5%  norm=0.707  lr=2.38e-04  dt=  37.6ms  words=35,749,888
[E03  1269/1548 G   4364|CLM] train=2.8706  mask=16.5%  norm=1.216  lr=2.38e-04  dt=  37.1ms  words=35,758,080
[E03  1270/1548 G   4365|CLM] train=2.7838  mask=16.5%  norm=0.803  lr=2.38e-04  dt=  37.3ms  words=35,766,272
[E03  1271/1548 G   4366|CLM] train=4.1208  mask=16.5%  norm=0.935  lr=2.38e-04  dt=  37.2ms  words=35,774,464
[E03  1272/1548 G   4367|CLM] train=2.7690  mask=16.5%  norm=0.929  lr=2.38e-04  dt=  37.2ms  words=35,782,656
[E03  1273/1548 G   4368|CLM] train=2.3325  mask=16.5%  norm=0.718  lr=2.38e-04  dt=  37.4ms  words=35,790,848
[E03  1274/1548 G   4369|CLM] train=5.1247  mask=16.5%  norm=2.790  lr=2.38e-04  dt=  37.4ms  words=35,799,040
[E03  1275/1548 G   4370|CLM] train=4.4359  mask=16.5%  norm=0.969  lr=2.38e-04  dt=  37.3ms  words=35,807,232
[E03  1276/1548 G   4371|CLM] train=4.1667  mask=16.5%  norm=0.738  lr=2.38e-04  dt=  37.1ms  words=35,815,424
[E03  1277/1548 G   4372|CLM] train=3.2763  mask=16.5%  norm=0.778  lr=2.38e-04  dt=  37.4ms  words=35,823,616
[E03  1278/1548 G   4373|CLM] train=4.2164  mask=16.5%  norm=0.655  lr=2.38e-04  dt=  37.2ms  words=35,831,808
[E03  1279/1548 G   4374|CLM] train=4.3521  mask=16.5%  norm=0.824  lr=2.38e-04  dt=  37.3ms  words=35,840,000
[E03  1280/1548 G   4375|CLM] train=2.6402  mask=16.5%  norm=1.000  lr=2.38e-04  dt=  37.6ms  words=35,848,192
[E03  1281/1548 G   4376|CLM] train=4.9344  mask=16.5%  norm=0.936  lr=2.38e-04  dt=  37.5ms  words=35,856,384
[E03  1282/1548 G   4377|CLM] train=2.6034  mask=16.5%  norm=0.859  lr=2.38e-04  dt=  37.4ms  words=35,864,576
[E03  1283/1548 G   4378|CLM] train=3.8530  mask=16.5%  norm=0.894  lr=2.38e-04  dt=  37.4ms  words=35,872,768
[E03  1284/1548 G   4379|CLM] train=2.8189  mask=16.5%  norm=0.674  lr=2.38e-04  dt=  37.3ms  words=35,880,960
[E03  1285/1548 G   4380|CLM] train=4.1515  mask=16.5%  norm=1.016  lr=2.38e-04  dt=  37.3ms  words=35,889,152
[E03  1286/1548 G   4381|CLM] train=4.5085  mask=16.5%  norm=0.703  lr=2.38e-04  dt=  37.4ms  words=35,897,344
[E03  1287/1548 G   4382|CLM] train=3.2942  mask=16.5%  norm=0.735  lr=2.38e-04  dt=  37.2ms  words=35,905,536
[E03  1288/1548 G   4383|CLM] train=4.4927  mask=16.5%  norm=0.560  lr=2.38e-04  dt=  37.2ms  words=35,913,728
[E03  1289/1548 G   4384|CLM] train=4.2750  mask=16.5%  norm=0.581  lr=2.38e-04  dt=  37.3ms  words=35,921,920
[E03  1290/1548 G   4385|CLM] train=4.9019  mask=16.5%  norm=0.886  lr=2.38e-04  dt=  37.2ms  words=35,930,112
[E03  1291/1548 G   4386|CLM] train=4.9004  mask=16.5%  norm=0.801  lr=2.38e-04  dt=  37.2ms  words=35,938,304
[E03  1292/1548 G   4387|CLM] train=4.6908  mask=16.5%  norm=0.760  lr=2.38e-04  dt=  37.3ms  words=35,946,496
[E03  1293/1548 G   4388|CLM] train=2.5202  mask=16.5%  norm=0.742  lr=2.38e-04  dt=  37.2ms  words=35,954,688
[E03  1294/1548 G   4389|CLM] train=4.4486  mask=16.5%  norm=0.894  lr=2.38e-04  dt=  37.3ms  words=35,962,880
[E03  1295/1548 G   4390|CLM] train=4.7679  mask=16.5%  norm=1.714  lr=2.38e-04  dt=  37.3ms  words=35,971,072
[E03  1296/1548 G   4391|CLM] train=4.2573  mask=16.5%  norm=0.729  lr=2.38e-04  dt=  37.2ms  words=35,979,264
[E03  1297/1548 G   4392|CLM] train=4.3890  mask=16.5%  norm=0.797  lr=2.38e-04  dt=  37.3ms  words=35,987,456
[E03  1298/1548 G   4393|CLM] train=2.9949  mask=16.5%  norm=0.845  lr=2.38e-04  dt=  37.2ms  words=35,995,648
[E03  1299/1548 G   4394|CLM] train=4.8434  mask=16.5%  norm=0.916  lr=2.38e-04  dt=  37.3ms  words=36,003,840
[E03  1300/1548 G   4395|CLM] train=2.0326  mask=16.5%  norm=0.916  lr=2.37e-04  dt=  37.2ms  words=36,012,032
[E03  1301/1548 G   4396|CLM] train=2.3197  mask=16.5%  norm=0.729  lr=2.37e-04  dt=  37.2ms  words=36,020,224
[E03  1302/1548 G   4397|CLM] train=2.5620  mask=16.4%  norm=0.639  lr=2.37e-04  dt=  37.2ms  words=36,028,416
[E03  1303/1548 G   4398|CLM] train=3.9655  mask=16.4%  norm=0.710  lr=2.37e-04  dt=  37.0ms  words=36,036,608
[E03  1304/1548 G   4399|CLM] train=4.8612  mask=16.4%  norm=0.681  lr=2.37e-04  dt=  37.3ms  words=36,044,800
[E03  1305/1548 G   4400|CLM] train=4.3023  mask=16.4%  norm=1.645  lr=2.37e-04  dt=  37.4ms  words=36,052,992
[E03  1306/1548 G   4401|CLM] train=4.2766  mask=16.4%  norm=0.588  lr=2.37e-04  dt=  38.2ms  words=36,061,184
[E03  1307/1548 G   4402|CLM] train=4.6513  mask=16.4%  norm=0.839  lr=2.37e-04  dt=  37.3ms  words=36,069,376
[E03  1308/1548 G   4403|CLM] train=4.6261  mask=16.4%  norm=0.788  lr=2.37e-04  dt=  37.7ms  words=36,077,568
[E03  1309/1548 G   4404|CLM] train=5.2886  mask=16.4%  norm=0.849  lr=2.37e-04  dt=  37.2ms  words=36,085,760
[E03  1310/1548 G   4405|CLM] train=4.4805  mask=16.4%  norm=0.903  lr=2.37e-04  dt=  37.4ms  words=36,093,952
[E03  1311/1548 G   4406|CLM] train=2.5720  mask=16.4%  norm=1.151  lr=2.37e-04  dt=  37.2ms  words=36,102,144
[E03  1312/1548 G   4407|CLM] train=2.6411  mask=16.4%  norm=0.944  lr=2.37e-04  dt=  37.1ms  words=36,110,336
[E03  1313/1548 G   4408|CLM] train=4.3090  mask=16.4%  norm=0.635  lr=2.37e-04  dt=  37.6ms  words=36,118,528
[E03  1314/1548 G   4409|CLM] train=2.5531  mask=16.4%  norm=1.152  lr=2.37e-04  dt=  37.2ms  words=36,126,720
[E03  1315/1548 G   4410|CLM] train=4.5618  mask=16.4%  norm=0.990  lr=2.37e-04  dt=  37.2ms  words=36,134,912
[E03  1316/1548 G   4411|CLM] train=2.3256  mask=16.4%  norm=0.713  lr=2.37e-04  dt=  37.2ms  words=36,143,104
[E03  1317/1548 G   4412|CLM] train=4.6363  mask=16.4%  norm=0.702  lr=2.37e-04  dt=  37.2ms  words=36,151,296
[E03  1318/1548 G   4413|CLM] train=4.0699  mask=16.4%  norm=0.873  lr=2.37e-04  dt=  37.2ms  words=36,159,488
[E03  1319/1548 G   4414|CLM] train=4.2686  mask=16.4%  norm=1.094  lr=2.37e-04  dt=  37.2ms  words=36,167,680
[E03  1320/1548 G   4415|CLM] train=5.0311  mask=16.4%  norm=0.942  lr=2.37e-04  dt=  37.6ms  words=36,175,872
[E03  1321/1548 G   4416|CLM] train=3.0545  mask=16.4%  norm=0.853  lr=2.37e-04  dt=  37.2ms  words=36,184,064
[E03  1322/1548 G   4417|CLM] train=5.0267  mask=16.4%  norm=0.825  lr=2.37e-04  dt=  37.3ms  words=36,192,256
[E03  1323/1548 G   4418|CLM] train=2.2871  mask=16.4%  norm=0.634  lr=2.37e-04  dt=  37.3ms  words=36,200,448
[E03  1324/1548 G   4419|CLM] train=4.0747  mask=16.4%  norm=0.780  lr=2.37e-04  dt=  37.7ms  words=36,208,640
[E03  1325/1548 G   4420|CLM] train=2.4548  mask=16.4%  norm=0.785  lr=2.37e-04  dt=  37.1ms  words=36,216,832
[E03  1326/1548 G   4421|CLM] train=4.5584  mask=16.4%  norm=2.058  lr=2.37e-04  dt=  37.0ms  words=36,225,024
[E03  1327/1548 G   4422|CLM] train=2.3591  mask=16.4%  norm=0.615  lr=2.37e-04  dt=  37.1ms  words=36,233,216
[E03  1328/1548 G   4423|CLM] train=5.1317  mask=16.4%  norm=2.725  lr=2.37e-04  dt=  37.2ms  words=36,241,408
[E03  1329/1548 G   4424|CLM] train=4.4983  mask=16.4%  norm=0.787  lr=2.37e-04  dt=  37.2ms  words=36,249,600
[E03  1330/1548 G   4425|CLM] train=4.8831  mask=16.4%  norm=1.034  lr=2.37e-04  dt=  37.1ms  words=36,257,792
[E03  1331/1548 G   4426|CLM] train=4.1884  mask=16.4%  norm=0.613  lr=2.36e-04  dt=  37.3ms  words=36,265,984
[E03  1332/1548 G   4427|CLM] train=2.5961  mask=16.4%  norm=0.924  lr=2.36e-04  dt=  37.2ms  words=36,274,176
[E03  1333/1548 G   4428|CLM] train=3.5661  mask=16.4%  norm=0.600  lr=2.36e-04  dt=  37.2ms  words=36,282,368
[E03  1334/1548 G   4429|CLM] train=4.0729  mask=16.4%  norm=0.713  lr=2.36e-04  dt=  37.2ms  words=36,290,560
[E03  1335/1548 G   4430|CLM] train=2.5666  mask=16.4%  norm=0.743  lr=2.36e-04  dt=  37.7ms  words=36,298,752
[E03  1336/1548 G   4431|CLM] train=2.0933  mask=16.4%  norm=0.756  lr=2.36e-04  dt=  37.0ms  words=36,306,944
[E03  1337/1548 G   4432|CLM] train=5.0857  mask=16.4%  norm=0.793  lr=2.36e-04  dt=  37.2ms  words=36,315,136
[E03  1338/1548 G   4433|CLM] train=4.9862  mask=16.4%  norm=0.951  lr=2.36e-04  dt=  37.1ms  words=36,323,328
[E03  1339/1548 G   4434|CLM] train=2.3712  mask=16.4%  norm=0.750  lr=2.36e-04  dt=  37.3ms  words=36,331,520
[E03  1340/1548 G   4435|CLM] train=4.2400  mask=16.4%  norm=0.657  lr=2.36e-04  dt=  37.2ms  words=36,339,712
[E03  1341/1548 G   4436|CLM] train=2.6334  mask=16.4%  norm=0.894  lr=2.36e-04  dt=  37.3ms  words=36,347,904
[E03  1342/1548 G   4437|CLM] train=4.9295  mask=16.4%  norm=1.146  lr=2.36e-04  dt=  37.2ms  words=36,356,096
[E03  1343/1548 G   4438|CLM] train=2.5131  mask=16.4%  norm=0.740  lr=2.36e-04  dt=  37.2ms  words=36,364,288
[E03  1344/1548 G   4439|CLM] train=2.8972  mask=16.4%  norm=0.749  lr=2.36e-04  dt=  37.0ms  words=36,372,480
[E03  1345/1548 G   4440|CLM] train=4.7822  mask=16.4%  norm=0.872  lr=2.36e-04  dt=  37.3ms  words=36,380,672
[E03  1346/1548 G   4441|CLM] train=4.4506  mask=16.4%  norm=0.932  lr=2.36e-04  dt=  37.3ms  words=36,388,864
[E03  1347/1548 G   4442|CLM] train=4.4833  mask=16.4%  norm=0.853  lr=2.36e-04  dt=  37.5ms  words=36,397,056
[E03  1348/1548 G   4443|CLM] train=2.8460  mask=16.4%  norm=0.722  lr=2.36e-04  dt=  37.2ms  words=36,405,248
[E03  1349/1548 G   4444|CLM] train=2.2931  mask=16.4%  norm=0.815  lr=2.36e-04  dt=  37.3ms  words=36,413,440
[E03  1350/1548 G   4445|CLM] train=3.8647  mask=16.4%  norm=0.729  lr=2.36e-04  dt=  37.2ms  words=36,421,632
[E03  1351/1548 G   4446|CLM] train=4.2181  mask=16.4%  norm=0.645  lr=2.36e-04  dt=  37.3ms  words=36,429,824
[E03  1352/1548 G   4447|CLM] train=2.6698  mask=16.4%  norm=0.910  lr=2.36e-04  dt=  37.2ms  words=36,438,016
[E03  1353/1548 G   4448|CLM] train=2.6452  mask=16.4%  norm=0.969  lr=2.36e-04  dt=  37.1ms  words=36,446,208
[E03  1354/1548 G   4449|CLM] train=2.8216  mask=16.4%  norm=0.734  lr=2.36e-04  dt=  37.2ms  words=36,454,400
[E03  1355/1548 G   4450|CLM] train=4.2394  mask=16.4%  norm=1.178  lr=2.36e-04  dt=  37.3ms  words=36,462,592
[E03  1356/1548 G   4451|CLM] train=4.7588  mask=16.4%  norm=1.563  lr=2.36e-04  dt=  37.0ms  words=36,470,784
[E03  1357/1548 G   4452|CLM] train=2.5801  mask=16.4%  norm=0.949  lr=2.36e-04  dt=  37.1ms  words=36,478,976
[E03  1358/1548 G   4453|CLM] train=2.6141  mask=16.4%  norm=0.565  lr=2.36e-04  dt=  37.4ms  words=36,487,168
[E03  1359/1548 G   4454|CLM] train=4.4087  mask=16.4%  norm=0.827  lr=2.36e-04  dt=  37.4ms  words=36,495,360
[E03  1360/1548 G   4455|CLM] train=3.8056  mask=16.4%  norm=0.784  lr=2.36e-04  dt=  37.1ms  words=36,503,552
[E03  1361/1548 G   4456|CLM] train=5.0665  mask=16.4%  norm=0.998  lr=2.36e-04  dt=  37.5ms  words=36,511,744
[E03  1362/1548 G   4457|CLM] train=4.8421  mask=16.4%  norm=0.808  lr=2.35e-04  dt=  37.1ms  words=36,519,936
[E03  1363/1548 G   4458|CLM] train=2.4629  mask=16.4%  norm=0.748  lr=2.35e-04  dt=  37.1ms  words=36,528,128
[E03  1364/1548 G   4459|CLM] train=4.7240  mask=16.4%  norm=0.707  lr=2.35e-04  dt=  37.3ms  words=36,536,320
[E03  1365/1548 G   4460|CLM] train=3.9376  mask=16.4%  norm=0.744  lr=2.35e-04  dt=  37.2ms  words=36,544,512
[E03  1366/1548 G   4461|CLM] train=4.1163  mask=16.4%  norm=0.999  lr=2.35e-04  dt=  37.1ms  words=36,552,704
[E03  1367/1548 G   4462|CLM] train=2.8637  mask=16.4%  norm=0.769  lr=2.35e-04  dt=  37.0ms  words=36,560,896
[E03  1368/1548 G   4463|CLM] train=4.6666  mask=16.4%  norm=0.765  lr=2.35e-04  dt=  37.2ms  words=36,569,088
[E03  1369/1548 G   4464|CLM] train=1.9879  mask=16.4%  norm=0.679  lr=2.35e-04  dt=  37.3ms  words=36,577,280
[E03  1370/1548 G   4465|CLM] train=4.4052  mask=16.4%  norm=0.741  lr=2.35e-04  dt=  37.2ms  words=36,585,472
[E03  1371/1548 G   4466|CLM] train=4.5973  mask=16.4%  norm=0.770  lr=2.35e-04  dt=  37.2ms  words=36,593,664
[E03  1372/1548 G   4467|CLM] train=2.5419  mask=16.4%  norm=1.080  lr=2.35e-04  dt=  37.2ms  words=36,601,856
[E03  1373/1548 G   4468|CLM] train=5.3772  mask=16.4%  norm=0.815  lr=2.35e-04  dt=  37.2ms  words=36,610,048
[E03  1374/1548 G   4469|CLM] train=2.3268  mask=16.4%  norm=0.765  lr=2.35e-04  dt=  37.3ms  words=36,618,240
[E03  1375/1548 G   4470|CLM] train=2.4757  mask=16.4%  norm=0.767  lr=2.35e-04  dt=  37.3ms  words=36,626,432
[E03  1376/1548 G   4471|CLM] train=4.8114  mask=16.4%  norm=0.704  lr=2.35e-04  dt=  44.7ms  words=36,634,624
[E03  1377/1548 G   4472|CLM] train=4.4962  mask=16.4%  norm=0.641  lr=2.35e-04  dt=  37.3ms  words=36,642,816
[E03  1378/1548 G   4473|CLM] train=2.3872  mask=16.4%  norm=0.676  lr=2.35e-04  dt=  37.7ms  words=36,651,008
[E03  1379/1548 G   4474|CLM] train=2.5849  mask=16.4%  norm=0.955  lr=2.35e-04  dt=  37.9ms  words=36,659,200
[E03  1380/1548 G   4475|CLM] train=4.7644  mask=16.4%  norm=0.815  lr=2.35e-04  dt=  37.2ms  words=36,667,392
[E03  1381/1548 G   4476|CLM] train=4.4502  mask=16.4%  norm=1.009  lr=2.35e-04  dt=  40.1ms  words=36,675,584
[E03  1382/1548 G   4477|CLM] train=2.5336  mask=16.4%  norm=0.694  lr=2.35e-04  dt=  38.6ms  words=36,683,776
[E03  1383/1548 G   4478|CLM] train=3.0046  mask=16.4%  norm=0.790  lr=2.35e-04  dt=  42.2ms  words=36,691,968
[E03  1384/1548 G   4479|CLM] train=2.5145  mask=16.4%  norm=0.653  lr=2.35e-04  dt=  38.1ms  words=36,700,160
[E03  1385/1548 G   4480|CLM] train=5.1994  mask=16.4%  norm=0.889  lr=2.35e-04  dt=  37.6ms  words=36,708,352
[E03  1386/1548 G   4481|CLM] train=2.6414  mask=16.4%  norm=0.666  lr=2.35e-04  dt=  38.6ms  words=36,716,544
[E03  1387/1548 G   4482|CLM] train=4.4990  mask=16.4%  norm=0.690  lr=2.35e-04  dt=  44.0ms  words=36,724,736
[E03  1388/1548 G   4483|CLM] train=4.2201  mask=16.4%  norm=0.905  lr=2.35e-04  dt=  39.9ms  words=36,732,928
[E03  1389/1548 G   4484|CLM] train=5.1610  mask=16.4%  norm=1.205  lr=2.35e-04  dt=  36.9ms  words=36,741,120
[E03  1390/1548 G   4485|CLM] train=3.6409  mask=16.4%  norm=0.665  lr=2.35e-04  dt=  37.2ms  words=36,749,312
[E03  1391/1548 G   4486|CLM] train=2.8378  mask=16.4%  norm=0.963  lr=2.35e-04  dt=  37.6ms  words=36,757,504
[E03  1392/1548 G   4487|CLM] train=4.2556  mask=16.4%  norm=0.759  lr=2.35e-04  dt=  37.6ms  words=36,765,696
[E03  1393/1548 G   4488|CLM] train=2.6699  mask=16.4%  norm=1.146  lr=2.34e-04  dt=  37.3ms  words=36,773,888
[E03  1394/1548 G   4489|CLM] train=4.5801  mask=16.4%  norm=0.875  lr=2.34e-04  dt=  37.1ms  words=36,782,080
[E03  1395/1548 G   4490|CLM] train=4.0044  mask=16.4%  norm=0.650  lr=2.34e-04  dt=  37.7ms  words=36,790,272
[E03  1396/1548 G   4491|CLM] train=4.9246  mask=16.4%  norm=1.001  lr=2.34e-04  dt=  37.3ms  words=36,798,464
[E03  1397/1548 G   4492|CLM] train=5.7819  mask=16.4%  norm=1.470  lr=2.34e-04  dt=  37.1ms  words=36,806,656
[E03  1398/1548 G   4493|CLM] train=4.8616  mask=16.4%  norm=0.903  lr=2.34e-04  dt=  37.2ms  words=36,814,848
[E03  1399/1548 G   4494|CLM] train=4.5733  mask=16.4%  norm=0.874  lr=2.34e-04  dt=  37.4ms  words=36,823,040
[E03  1400/1548 G   4495|CLM] train=2.7911  mask=16.4%  norm=1.059  lr=2.34e-04  dt=  37.2ms  words=36,831,232
[E03  1401/1548 G   4496|CLM] train=2.5914  mask=16.4%  norm=0.947  lr=2.34e-04  dt=  37.2ms  words=36,839,424
[E03  1402/1548 G   4497|CLM] train=4.5219  mask=16.4%  norm=0.670  lr=2.34e-04  dt=  38.4ms  words=36,847,616
[E03  1403/1548 G   4498|CLM] train=2.4328  mask=16.4%  norm=0.748  lr=2.34e-04  dt=  47.3ms  words=36,855,808
[E03  1404/1548 G   4499|CLM] train=4.9396  mask=16.4%  norm=1.042  lr=2.34e-04  dt=  46.3ms  words=36,864,000
[E03  1405/1548 G   4500|CLM] train=3.2030  mask=16.4%  norm=1.010  lr=2.34e-04  dt=  38.6ms  words=36,872,192
[E03  1406/1548 G   4501|CLM] train=3.9706  mask=16.4%  norm=0.670  lr=2.34e-04  dt=  41.6ms  words=36,880,384
[E03  1407/1548 G   4502|CLM] train=2.4256  mask=16.4%  norm=0.727  lr=2.34e-04  dt=  37.2ms  words=36,888,576
[E03  1408/1548 G   4503|CLM] train=5.3479  mask=16.4%  norm=0.885  lr=2.34e-04  dt=  37.4ms  words=36,896,768
[E03  1409/1548 G   4504|CLM] train=3.7033  mask=16.4%  norm=0.614  lr=2.34e-04  dt=  37.5ms  words=36,904,960
[E03  1410/1548 G   4505|CLM] train=5.3414  mask=16.4%  norm=1.515  lr=2.34e-04  dt=  38.0ms  words=36,913,152
[E03  1411/1548 G   4506|CLM] train=4.2400  mask=16.4%  norm=0.768  lr=2.34e-04  dt=  37.4ms  words=36,921,344
[E03  1412/1548 G   4507|CLM] train=2.6973  mask=16.4%  norm=0.718  lr=2.34e-04  dt=  39.2ms  words=36,929,536
[E03  1413/1548 G   4508|CLM] train=3.8454  mask=16.4%  norm=0.689  lr=2.34e-04  dt=  37.1ms  words=36,937,728
[E03  1414/1548 G   4509|CLM] train=4.6144  mask=16.4%  norm=0.796  lr=2.34e-04  dt=  37.0ms  words=36,945,920
[E03  1415/1548 G   4510|CLM] train=5.5604  mask=16.4%  norm=1.494  lr=2.34e-04  dt=  39.9ms  words=36,954,112
[E03  1416/1548 G   4511|CLM] train=4.7330  mask=16.4%  norm=0.989  lr=2.34e-04  dt=  37.3ms  words=36,962,304
[E03  1417/1548 G   4512|CLM] train=6.1358  mask=16.4%  norm=1.345  lr=2.34e-04  dt=  37.1ms  words=36,970,496
[E03  1418/1548 G   4513|CLM] train=4.8016  mask=16.4%  norm=0.928  lr=2.34e-04  dt=  37.0ms  words=36,978,688
[E03  1419/1548 G   4514|CLM] train=5.7487  mask=16.4%  norm=1.803  lr=2.34e-04  dt=  37.6ms  words=36,986,880
[E03  1420/1548 G   4515|CLM] train=2.7557  mask=16.4%  norm=0.927  lr=2.34e-04  dt=  36.8ms  words=36,995,072
[E03  1421/1548 G   4516|CLM] train=2.5251  mask=16.4%  norm=0.772  lr=2.34e-04  dt=  37.8ms  words=37,003,264
[E03  1422/1548 G   4517|CLM] train=5.9232  mask=16.4%  norm=0.997  lr=2.34e-04  dt=  37.4ms  words=37,011,456
[E03  1423/1548 G   4518|CLM] train=4.7500  mask=16.4%  norm=0.905  lr=2.33e-04  dt=  37.8ms  words=37,019,648
[E03  1424/1548 G   4519|CLM] train=5.0348  mask=16.4%  norm=0.933  lr=2.33e-04  dt=  36.8ms  words=37,027,840
[E03  1425/1548 G   4520|CLM] train=2.7880  mask=16.4%  norm=0.657  lr=2.33e-04  dt=  36.8ms  words=37,036,032
[E03  1426/1548 G   4521|CLM] train=2.4105  mask=16.3%  norm=0.829  lr=2.33e-04  dt=  36.9ms  words=37,044,224
[E03  1427/1548 G   4522|CLM] train=2.8462  mask=16.3%  norm=0.730  lr=2.33e-04  dt=  37.0ms  words=37,052,416
[E03  1428/1548 G   4523|CLM] train=2.8122  mask=16.3%  norm=0.624  lr=2.33e-04  dt=  36.8ms  words=37,060,608
[E03  1429/1548 G   4524|CLM] train=4.3768  mask=16.3%  norm=0.941  lr=2.33e-04  dt=  36.9ms  words=37,068,800
[E03  1430/1548 G   4525|CLM] train=4.9797  mask=16.3%  norm=0.813  lr=2.33e-04  dt=  36.9ms  words=37,076,992
[E03  1431/1548 G   4526|CLM] train=2.4870  mask=16.3%  norm=0.799  lr=2.33e-04  dt=  37.1ms  words=37,085,184
[E03  1432/1548 G   4527|CLM] train=4.2317  mask=16.3%  norm=0.933  lr=2.33e-04  dt=  36.9ms  words=37,093,376
[E03  1433/1548 G   4528|CLM] train=2.2431  mask=16.3%  norm=0.912  lr=2.33e-04  dt=  36.9ms  words=37,101,568
[E03  1434/1548 G   4529|CLM] train=4.0147  mask=16.3%  norm=0.676  lr=2.33e-04  dt=  37.0ms  words=37,109,760
[E03  1435/1548 G   4530|CLM] train=4.3313  mask=16.3%  norm=0.662  lr=2.33e-04  dt=  37.1ms  words=37,117,952
[E03  1436/1548 G   4531|CLM] train=4.2112  mask=16.3%  norm=0.799  lr=2.33e-04  dt=  36.7ms  words=37,126,144
[E03  1437/1548 G   4532|CLM] train=4.9703  mask=16.3%  norm=0.861  lr=2.33e-04  dt=  37.1ms  words=37,134,336
[E03  1438/1548 G   4533|CLM] train=2.4816  mask=16.3%  norm=0.927  lr=2.33e-04  dt=  37.0ms  words=37,142,528
[E03  1439/1548 G   4534|CLM] train=3.0365  mask=16.3%  norm=1.154  lr=2.33e-04  dt=  37.0ms  words=37,150,720
[E03  1440/1548 G   4535|CLM] train=2.7835  mask=16.3%  norm=0.734  lr=2.33e-04  dt=  37.3ms  words=37,158,912
[E03  1441/1548 G   4536|CLM] train=2.4664  mask=16.3%  norm=1.098  lr=2.33e-04  dt=  37.0ms  words=37,167,104
[E03  1442/1548 G   4537|CLM] train=4.7156  mask=16.3%  norm=0.836  lr=2.33e-04  dt=  37.0ms  words=37,175,296
[E03  1443/1548 G   4538|CLM] train=2.8063  mask=16.3%  norm=0.855  lr=2.33e-04  dt=  36.9ms  words=37,183,488
[E03  1444/1548 G   4539|CLM] train=4.6011  mask=16.3%  norm=0.702  lr=2.33e-04  dt=  36.8ms  words=37,191,680
[E03  1445/1548 G   4540|CLM] train=4.3884  mask=16.3%  norm=0.843  lr=2.33e-04  dt=  36.9ms  words=37,199,872
[E03  1446/1548 G   4541|CLM] train=4.7107  mask=16.3%  norm=0.772  lr=2.33e-04  dt=  37.0ms  words=37,208,064
[E03  1447/1548 G   4542|CLM] train=2.8307  mask=16.3%  norm=0.924  lr=2.33e-04  dt=  36.9ms  words=37,216,256
[E03  1448/1548 G   4543|CLM] train=3.9488  mask=16.3%  norm=0.663  lr=2.33e-04  dt=  36.7ms  words=37,224,448
[E03  1449/1548 G   4544|CLM] train=4.5697  mask=16.3%  norm=0.958  lr=2.33e-04  dt=  37.1ms  words=37,232,640
[E03  1450/1548 G   4545|CLM] train=5.2137  mask=16.3%  norm=0.967  lr=2.33e-04  dt=  37.0ms  words=37,240,832
[E03  1451/1548 G   4546|CLM] train=2.8456  mask=16.3%  norm=0.887  lr=2.33e-04  dt=  36.9ms  words=37,249,024
[E03  1452/1548 G   4547|CLM] train=3.7989  mask=16.3%  norm=0.613  lr=2.33e-04  dt=  36.9ms  words=37,257,216
[E03  1453/1548 G   4548|CLM] train=2.6889  mask=16.3%  norm=1.017  lr=2.33e-04  dt=  37.0ms  words=37,265,408
[E03  1454/1548 G   4549|CLM] train=2.6998  mask=16.3%  norm=0.729  lr=2.32e-04  dt=  36.9ms  words=37,273,600
[E03  1455/1548 G   4550|CLM] train=2.6316  mask=16.3%  norm=0.616  lr=2.32e-04  dt=  36.8ms  words=37,281,792
[E03  1456/1548 G   4551|CLM] train=5.2918  mask=16.3%  norm=2.114  lr=2.32e-04  dt=  37.0ms  words=37,289,984
[E03  1457/1548 G   4552|CLM] train=2.4950  mask=16.3%  norm=1.139  lr=2.32e-04  dt=  36.9ms  words=37,298,176
[E03  1458/1548 G   4553|CLM] train=4.5431  mask=16.3%  norm=0.770  lr=2.32e-04  dt=  37.0ms  words=37,306,368
[E03  1459/1548 G   4554|CLM] train=4.7051  mask=16.3%  norm=0.832  lr=2.32e-04  dt=  36.9ms  words=37,314,560
[E03  1460/1548 G   4555|CLM] train=2.5948  mask=16.3%  norm=0.795  lr=2.32e-04  dt=  36.9ms  words=37,322,752
[E03  1461/1548 G   4556|CLM] train=4.3666  mask=16.3%  norm=0.994  lr=2.32e-04  dt=  36.9ms  words=37,330,944
[E03  1462/1548 G   4557|CLM] train=2.5359  mask=16.3%  norm=0.674  lr=2.32e-04  dt=  36.9ms  words=37,339,136
[E03  1463/1548 G   4558|CLM] train=5.0423  mask=16.3%  norm=0.854  lr=2.32e-04  dt=  36.9ms  words=37,347,328
[E03  1464/1548 G   4559|CLM] train=5.0811  mask=16.3%  norm=1.018  lr=2.32e-04  dt=  36.8ms  words=37,355,520
[E03  1465/1548 G   4560|CLM] train=2.4031  mask=16.3%  norm=1.050  lr=2.32e-04  dt=  37.0ms  words=37,363,712
[E03  1466/1548 G   4561|CLM] train=4.8229  mask=16.3%  norm=0.849  lr=2.32e-04  dt=  37.0ms  words=37,371,904
[E03  1467/1548 G   4562|CLM] train=5.3341  mask=16.3%  norm=1.239  lr=2.32e-04  dt=  37.0ms  words=37,380,096
[E03  1468/1548 G   4563|CLM] train=5.1928  mask=16.3%  norm=0.713  lr=2.32e-04  dt=  36.9ms  words=37,388,288
[E03  1469/1548 G   4564|CLM] train=2.5596  mask=16.3%  norm=0.750  lr=2.32e-04  dt=  36.9ms  words=37,396,480
[E03  1470/1548 G   4565|CLM] train=4.4008  mask=16.3%  norm=1.198  lr=2.32e-04  dt=  36.9ms  words=37,404,672
[E03  1471/1548 G   4566|CLM] train=4.2597  mask=16.3%  norm=0.913  lr=2.32e-04  dt=  36.8ms  words=37,412,864
[E03  1472/1548 G   4567|CLM] train=2.7196  mask=16.3%  norm=0.657  lr=2.32e-04  dt=  36.8ms  words=37,421,056
[E03  1473/1548 G   4568|CLM] train=4.4180  mask=16.3%  norm=0.716  lr=2.32e-04  dt=  37.1ms  words=37,429,248
[E03  1474/1548 G   4569|CLM] train=2.5504  mask=16.3%  norm=0.731  lr=2.32e-04  dt=  36.9ms  words=37,437,440
[E03  1475/1548 G   4570|CLM] train=4.4113  mask=16.3%  norm=0.724  lr=2.32e-04  dt=  36.9ms  words=37,445,632
[E03  1476/1548 G   4571|CLM] train=3.9426  mask=16.3%  norm=0.787  lr=2.32e-04  dt=  37.0ms  words=37,453,824
[E03  1477/1548 G   4572|CLM] train=3.0682  mask=16.3%  norm=0.912  lr=2.32e-04  dt=  37.0ms  words=37,462,016
[E03  1478/1548 G   4573|CLM] train=4.3408  mask=16.3%  norm=0.661  lr=2.32e-04  dt=  36.9ms  words=37,470,208
[E03  1479/1548 G   4574|CLM] train=2.7730  mask=16.3%  norm=0.699  lr=2.32e-04  dt=  36.9ms  words=37,478,400
[E03  1480/1548 G   4575|CLM] train=2.3928  mask=16.3%  norm=0.636  lr=2.32e-04  dt=  36.9ms  words=37,486,592
[E03  1481/1548 G   4576|CLM] train=4.1684  mask=16.3%  norm=0.687  lr=2.32e-04  dt=  36.9ms  words=37,494,784
[E03  1482/1548 G   4577|CLM] train=5.3142  mask=16.3%  norm=0.827  lr=2.32e-04  dt=  36.9ms  words=37,502,976
[E03  1483/1548 G   4578|CLM] train=4.5325  mask=16.3%  norm=0.734  lr=2.32e-04  dt=  37.0ms  words=37,511,168
[E03  1484/1548 G   4579|CLM] train=2.3231  mask=16.3%  norm=0.895  lr=2.31e-04  dt=  36.9ms  words=37,519,360
[E03  1485/1548 G   4580|CLM] train=2.4322  mask=16.3%  norm=0.686  lr=2.31e-04  dt=  36.9ms  words=37,527,552
[E03  1486/1548 G   4581|CLM] train=4.2090  mask=16.3%  norm=0.761  lr=2.31e-04  dt=  36.9ms  words=37,535,744
[E03  1487/1548 G   4582|CLM] train=4.3493  mask=16.3%  norm=0.662  lr=2.31e-04  dt=  36.9ms  words=37,543,936
[E03  1488/1548 G   4583|CLM] train=5.5259  mask=16.3%  norm=1.017  lr=2.31e-04  dt=  36.8ms  words=37,552,128
[E03  1489/1548 G   4584|CLM] train=4.0097  mask=16.3%  norm=0.860  lr=2.31e-04  dt=  37.0ms  words=37,560,320
[E03  1490/1548 G   4585|CLM] train=2.4116  mask=16.3%  norm=0.713  lr=2.31e-04  dt=  37.0ms  words=37,568,512
[E03  1491/1548 G   4586|CLM] train=4.4888  mask=16.3%  norm=0.791  lr=2.31e-04  dt=  36.9ms  words=37,576,704
[E03  1492/1548 G   4587|CLM] train=4.4269  mask=16.3%  norm=0.673  lr=2.31e-04  dt=  37.2ms  words=37,584,896
[E03  1493/1548 G   4588|CLM] train=4.7321  mask=16.3%  norm=0.744  lr=2.31e-04  dt=  36.9ms  words=37,593,088
[E03  1494/1548 G   4589|CLM] train=5.0757  mask=16.3%  norm=0.970  lr=2.31e-04  dt=  37.0ms  words=37,601,280
[E03  1495/1548 G   4590|CLM] train=4.6586  mask=16.3%  norm=0.734  lr=2.31e-04  dt=  36.8ms  words=37,609,472
[E03  1496/1548 G   4591|CLM] train=2.5634  mask=16.3%  norm=1.275  lr=2.31e-04  dt=  36.7ms  words=37,617,664
[E03  1497/1548 G   4592|CLM] train=4.5706  mask=16.3%  norm=0.776  lr=2.31e-04  dt=  36.9ms  words=37,625,856
[E03  1498/1548 G   4593|CLM] train=2.4298  mask=16.3%  norm=0.793  lr=2.31e-04  dt=  37.0ms  words=37,634,048
[E03  1499/1548 G   4594|CLM] train=4.2698  mask=16.3%  norm=1.011  lr=2.31e-04  dt=  36.9ms  words=37,642,240
[E03  1500/1548 G   4595|CLM] train=2.7325  mask=16.3%  norm=0.661  lr=2.31e-04  dt=  36.8ms  words=37,650,432
[E03  1501/1548 G   4596|CLM] train=2.6380  mask=16.3%  norm=1.023  lr=2.31e-04  dt=  36.9ms  words=37,658,624
[E03  1502/1548 G   4597|CLM] train=2.5209  mask=16.3%  norm=0.884  lr=2.31e-04  dt=  37.0ms  words=37,666,816
[E03  1503/1548 G   4598|CLM] train=4.4442  mask=16.3%  norm=0.827  lr=2.31e-04  dt=  36.8ms  words=37,675,008
[E03  1504/1548 G   4599|CLM] train=3.0198  mask=16.3%  norm=0.662  lr=2.31e-04  dt=  36.8ms  words=37,683,200
[E03  1505/1548 G   4600|CLM] train=4.9175  mask=16.3%  norm=0.780  lr=2.31e-04  dt=  37.0ms  words=37,691,392
[E03  1506/1548 G   4601|CLM] train=2.4399  mask=16.3%  norm=1.237  lr=2.31e-04  dt=  37.0ms  words=37,699,584
[E03  1507/1548 G   4602|CLM] train=2.4515  mask=16.3%  norm=0.646  lr=2.31e-04  dt=  37.1ms  words=37,707,776
[E03  1508/1548 G   4603|CLM] train=4.0159  mask=16.3%  norm=0.710  lr=2.31e-04  dt=  36.9ms  words=37,715,968
[E03  1509/1548 G   4604|CLM] train=4.3888  mask=16.3%  norm=0.936  lr=2.31e-04  dt=  40.0ms  words=37,724,160
[E03  1510/1548 G   4605|CLM] train=2.3428  mask=16.3%  norm=0.863  lr=2.31e-04  dt=  41.6ms  words=37,732,352
[E03  1511/1548 G   4606|CLM] train=4.4364  mask=16.3%  norm=0.748  lr=2.31e-04  dt=  37.3ms  words=37,740,544
[E03  1512/1548 G   4607|CLM] train=4.4439  mask=16.3%  norm=0.878  lr=2.31e-04  dt=  37.2ms  words=37,748,736
[E03  1513/1548 G   4608|CLM] train=4.6907  mask=16.3%  norm=0.784  lr=2.31e-04  dt=  38.1ms  words=37,756,928
[E03  1514/1548 G   4609|CLM] train=2.7103  mask=16.3%  norm=0.678  lr=2.30e-04  dt=  37.0ms  words=37,765,120
[E03  1515/1548 G   4610|CLM] train=4.4958  mask=16.3%  norm=1.267  lr=2.30e-04  dt=  38.6ms  words=37,773,312
[E03  1516/1548 G   4611|CLM] train=2.4582  mask=16.3%  norm=0.828  lr=2.30e-04  dt=  37.7ms  words=37,781,504
[E03  1517/1548 G   4612|CLM] train=4.7815  mask=16.3%  norm=0.838  lr=2.30e-04  dt=  36.8ms  words=37,789,696
[E03  1518/1548 G   4613|CLM] train=4.5339  mask=16.3%  norm=1.112  lr=2.30e-04  dt=  36.9ms  words=37,797,888
[E03  1519/1548 G   4614|CLM] train=2.6061  mask=16.3%  norm=0.692  lr=2.30e-04  dt=  37.8ms  words=37,806,080
[E03  1520/1548 G   4615|CLM] train=2.6398  mask=16.3%  norm=0.741  lr=2.30e-04  dt=  36.8ms  words=37,814,272
[E03  1521/1548 G   4616|CLM] train=2.3611  mask=16.3%  norm=0.934  lr=2.30e-04  dt=  37.9ms  words=37,822,464
[E03  1522/1548 G   4617|CLM] train=4.7844  mask=16.3%  norm=0.718  lr=2.30e-04  dt=  39.0ms  words=37,830,656
[E03  1523/1548 G   4618|CLM] train=4.6297  mask=16.3%  norm=0.950  lr=2.30e-04  dt=  38.3ms  words=37,838,848
[E03  1524/1548 G   4619|CLM] train=3.8983  mask=16.3%  norm=0.711  lr=2.30e-04  dt=  42.7ms  words=37,847,040
[E03  1525/1548 G   4620|CLM] train=4.0627  mask=16.3%  norm=0.643  lr=2.30e-04  dt=  40.0ms  words=37,855,232
[E03  1526/1548 G   4621|CLM] train=2.4424  mask=16.3%  norm=0.739  lr=2.30e-04  dt=  42.2ms  words=37,863,424
[E03  1527/1548 G   4622|CLM] train=2.2552  mask=16.3%  norm=0.769  lr=2.30e-04  dt=  36.9ms  words=37,871,616
[E03  1528/1548 G   4623|CLM] train=4.7207  mask=16.3%  norm=0.897  lr=2.30e-04  dt=  36.8ms  words=37,879,808
[E03  1529/1548 G   4624|CLM] train=4.6203  mask=16.3%  norm=0.757  lr=2.30e-04  dt=  36.9ms  words=37,888,000
[E03  1530/1548 G   4625|CLM] train=2.3710  mask=16.3%  norm=0.788  lr=2.30e-04  dt=  36.6ms  words=37,896,192
[E03  1531/1548 G   4626|CLM] train=2.3563  mask=16.3%  norm=0.752  lr=2.30e-04  dt=  37.0ms  words=37,904,384
[E03  1532/1548 G   4627|CLM] train=4.1721  mask=16.3%  norm=0.595  lr=2.30e-04  dt=  36.7ms  words=37,912,576
[E03  1533/1548 G   4628|CLM] train=4.5478  mask=16.3%  norm=0.790  lr=2.30e-04  dt=  38.7ms  words=37,920,768
[E03  1534/1548 G   4629|CLM] train=4.5490  mask=16.3%  norm=0.722  lr=2.30e-04  dt=  44.6ms  words=37,928,960
[E03  1535/1548 G   4630|CLM] train=2.7224  mask=16.3%  norm=0.762  lr=2.30e-04  dt= 436.4ms  words=37,937,152
[E03  1536/1548 G   4631|CLM] train=2.7859  mask=16.3%  norm=0.649  lr=2.30e-04  dt=  37.8ms  words=37,945,344
[E03  1537/1548 G   4632|CLM] train=4.0812  mask=16.3%  norm=0.713  lr=2.30e-04  dt=  37.3ms  words=37,953,536
[E03  1538/1548 G   4633|CLM] train=4.5359  mask=16.3%  norm=0.805  lr=2.30e-04  dt=  36.9ms  words=37,961,728
[E03  1539/1548 G   4634|CLM] train=4.9137  mask=16.3%  norm=0.834  lr=2.30e-04  dt=  36.8ms  words=37,969,920
[E03  1540/1548 G   4635|CLM] train=4.3789  mask=16.3%  norm=0.724  lr=2.30e-04  dt=  36.9ms  words=37,978,112
[E03  1541/1548 G   4636|CLM] train=2.6231  mask=16.3%  norm=0.761  lr=2.30e-04  dt=  37.0ms  words=37,986,304
[E03  1542/1548 G   4637|CLM] train=4.8839  mask=16.3%  norm=0.728  lr=2.30e-04  dt=  36.9ms  words=37,994,496
[E03  1543/1548 G   4638|CLM] train=4.5601  mask=16.3%  norm=0.785  lr=2.30e-04  dt=  36.9ms  words=38,002,688
[E03  1544/1548 G   4639|CLM] train=4.1164  mask=16.3%  norm=0.712  lr=2.29e-04  dt=  37.0ms  words=38,010,880
[E03  1545/1548 G   4640|CLM] train=2.8347  mask=16.3%  norm=0.732  lr=2.29e-04  dt=  37.0ms  words=38,019,072
[E03  1546/1548 G   4641|CLM] train=5.3245  mask=16.3%  norm=0.876  lr=2.29e-04  dt=  36.8ms  words=38,027,264
[E03  1547/1548 G   4642|CLM] train=2.5588  mask=16.3%  norm=0.884  lr=2.29e-04  dt=  36.8ms  words=38,035,456
[E03  1548/1548 G   4643|CLM] train=2.2646  mask=16.3%  norm=0.925  lr=2.29e-04  dt=  36.9ms  words=38,043,648
[E04     1/1548 G   4644|CLM] train=4.4858  mask=16.2%  norm=0.784  lr=2.29e-04  dt=  37.0ms  words=38,051,840
[E04     2/1548 G   4645|CLM] train=4.2628  mask=16.2%  norm=0.731  lr=2.29e-04  dt=  37.0ms  words=38,060,032
[E04     3/1548 G   4646|CLM] train=2.4657  mask=16.2%  norm=0.581  lr=2.29e-04  dt=  37.1ms  words=38,068,224
[E04     4/1548 G   4647|CLM] train=4.5900  mask=16.2%  norm=0.949  lr=2.29e-04  dt=  37.1ms  words=38,076,416
[E04     5/1548 G   4648|CLM] train=2.7498  mask=16.2%  norm=0.628  lr=2.29e-04  dt=  37.0ms  words=38,084,608
[E04     6/1548 G   4649|CLM] train=4.4238  mask=16.2%  norm=0.647  lr=2.29e-04  dt=  37.0ms  words=38,092,800
[E04     7/1548 G   4650|CLM] train=4.2531  mask=16.2%  norm=0.832  lr=2.29e-04  dt=  37.0ms  words=38,100,992
[E04     8/1548 G   4651|CLM] train=4.1833  mask=16.2%  norm=0.666  lr=2.29e-04  dt=  37.0ms  words=38,109,184
[E04     9/1548 G   4652|CLM] train=2.2688  mask=16.2%  norm=0.646  lr=2.29e-04  dt=  36.9ms  words=38,117,376
[E04    10/1548 G   4653|CLM] train=2.9506  mask=16.2%  norm=0.696  lr=2.29e-04  dt=  36.8ms  words=38,125,568
[E04    11/1548 G   4654|CLM] train=4.4442  mask=16.2%  norm=0.800  lr=2.29e-04  dt=  36.9ms  words=38,133,760
[E04    12/1548 G   4655|CLM] train=2.3521  mask=16.2%  norm=0.771  lr=2.29e-04  dt=  37.1ms  words=38,141,952
[E04    13/1548 G   4656|CLM] train=3.9578  mask=16.2%  norm=0.874  lr=2.29e-04  dt=  36.8ms  words=38,150,144
[E04    14/1548 G   4657|CLM] train=4.3451  mask=16.2%  norm=0.742  lr=2.29e-04  dt=  36.7ms  words=38,158,336
[E04    15/1548 G   4658|CLM] train=4.0875  mask=16.2%  norm=0.678  lr=2.29e-04  dt=  37.1ms  words=38,166,528
[E04    16/1548 G   4659|CLM] train=4.0703  mask=16.2%  norm=0.724  lr=2.29e-04  dt=  37.0ms  words=38,174,720
[E04    17/1548 G   4660|CLM] train=2.3186  mask=16.2%  norm=0.622  lr=2.29e-04  dt=  36.9ms  words=38,182,912
[E04    18/1548 G   4661|CLM] train=4.0428  mask=16.2%  norm=0.697  lr=2.29e-04  dt=  36.9ms  words=38,191,104
[E04    19/1548 G   4662|CLM] train=2.4946  mask=16.2%  norm=0.677  lr=2.29e-04  dt=  37.0ms  words=38,199,296
[E04    20/1548 G   4663|CLM] train=5.7450  mask=16.2%  norm=1.572  lr=2.29e-04  dt=  37.0ms  words=38,207,488
[E04    21/1548 G   4664|CLM] train=5.1465  mask=16.2%  norm=0.982  lr=2.29e-04  dt=  36.9ms  words=38,215,680
[E04    22/1548 G   4665|CLM] train=4.8400  mask=16.2%  norm=0.893  lr=2.29e-04  dt=  36.8ms  words=38,223,872
[E04    23/1548 G   4666|CLM] train=4.6656  mask=16.2%  norm=0.877  lr=2.29e-04  dt=  36.9ms  words=38,232,064
[E04    24/1548 G   4667|CLM] train=4.5811  mask=16.2%  norm=0.921  lr=2.29e-04  dt=  37.1ms  words=38,240,256
[E04    25/1548 G   4668|CLM] train=2.8783  mask=16.2%  norm=0.718  lr=2.29e-04  dt=  36.9ms  words=38,248,448
[E04    26/1548 G   4669|CLM] train=4.9643  mask=16.2%  norm=0.940  lr=2.28e-04  dt=  36.9ms  words=38,256,640
[E04    27/1548 G   4670|CLM] train=4.4894  mask=16.2%  norm=0.766  lr=2.28e-04  dt=  37.0ms  words=38,264,832
[E04    28/1548 G   4671|CLM] train=4.0549  mask=16.2%  norm=0.841  lr=2.28e-04  dt=  37.1ms  words=38,273,024
[E04    29/1548 G   4672|CLM] train=3.5925  mask=16.2%  norm=0.773  lr=2.28e-04  dt=  36.9ms  words=38,281,216
[E04    30/1548 G   4673|CLM] train=4.0315  mask=16.2%  norm=0.898  lr=2.28e-04  dt=  36.9ms  words=38,289,408
[E04    31/1548 G   4674|CLM] train=5.4658  mask=16.2%  norm=1.938  lr=2.28e-04  dt=  36.9ms  words=38,297,600
[E04    32/1548 G   4675|CLM] train=4.2856  mask=16.2%  norm=0.758  lr=2.28e-04  dt=  36.9ms  words=38,305,792
[E04    33/1548 G   4676|CLM] train=3.1975  mask=16.2%  norm=0.898  lr=2.28e-04  dt=  36.8ms  words=38,313,984
[E04    34/1548 G   4677|CLM] train=4.1031  mask=16.2%  norm=0.821  lr=2.28e-04  dt=  36.8ms  words=38,322,176
[E04    35/1548 G   4678|CLM] train=4.4178  mask=16.2%  norm=0.741  lr=2.28e-04  dt=  37.0ms  words=38,330,368
[E04    36/1548 G   4679|CLM] train=5.2222  mask=16.2%  norm=1.737  lr=2.28e-04  dt=  37.1ms  words=38,338,560
[E04    37/1548 G   4680|CLM] train=4.3736  mask=16.2%  norm=0.780  lr=2.28e-04  dt=  36.8ms  words=38,346,752
[E04    38/1548 G   4681|CLM] train=2.2889  mask=16.2%  norm=0.979  lr=2.28e-04  dt=  36.9ms  words=38,354,944
[E04    39/1548 G   4682|CLM] train=2.5676  mask=16.2%  norm=0.762  lr=2.28e-04  dt=  37.0ms  words=38,363,136
[E04    40/1548 G   4683|CLM] train=4.8270  mask=16.2%  norm=0.825  lr=2.28e-04  dt=  36.9ms  words=38,371,328
[E04    41/1548 G   4684|CLM] train=4.3893  mask=16.2%  norm=1.027  lr=2.28e-04  dt=  36.8ms  words=38,379,520
[E04    42/1548 G   4685|CLM] train=4.2263  mask=16.2%  norm=0.988  lr=2.28e-04  dt=  36.7ms  words=38,387,712
[E04    43/1548 G   4686|CLM] train=5.0184  mask=16.2%  norm=0.942  lr=2.28e-04  dt=  36.9ms  words=38,395,904
[E04    44/1548 G   4687|CLM] train=2.3537  mask=16.2%  norm=0.701  lr=2.28e-04  dt=  37.0ms  words=38,404,096
[E04    45/1548 G   4688|CLM] train=2.6917  mask=16.2%  norm=0.624  lr=2.28e-04  dt=  36.9ms  words=38,412,288
[E04    46/1548 G   4689|CLM] train=2.2794  mask=16.2%  norm=0.675  lr=2.28e-04  dt=  37.0ms  words=38,420,480
[E04    47/1548 G   4690|CLM] train=2.2627  mask=16.2%  norm=0.851  lr=2.28e-04  dt=  36.9ms  words=38,428,672
[E04    48/1548 G   4691|CLM] train=2.2447  mask=16.2%  norm=0.772  lr=2.28e-04  dt=  37.0ms  words=38,436,864
[E04    49/1548 G   4692|CLM] train=4.3030  mask=16.2%  norm=0.796  lr=2.28e-04  dt=  36.9ms  words=38,445,056
[E04    50/1548 G   4693|CLM] train=2.3578  mask=16.2%  norm=0.654  lr=2.28e-04  dt=  36.8ms  words=38,453,248
[E04    51/1548 G   4694|CLM] train=4.1449  mask=16.2%  norm=0.981  lr=2.28e-04  dt=  36.8ms  words=38,461,440
[E04    52/1548 G   4695|CLM] train=2.5807  mask=16.2%  norm=0.564  lr=2.28e-04  dt=  36.9ms  words=38,469,632
[E04    53/1548 G   4696|CLM] train=4.6154  mask=16.2%  norm=1.022  lr=2.28e-04  dt=  37.0ms  words=38,477,824
[E04    54/1548 G   4697|CLM] train=4.3286  mask=16.2%  norm=0.848  lr=2.28e-04  dt=  36.9ms  words=38,486,016
[E04    55/1548 G   4698|CLM] train=2.7414  mask=16.2%  norm=0.774  lr=2.28e-04  dt=  37.4ms  words=38,494,208
[E04    56/1548 G   4699|CLM] train=2.4120  mask=16.2%  norm=0.859  lr=2.27e-04  dt=  37.0ms  words=38,502,400
[E04    57/1548 G   4700|CLM] train=4.2074  mask=16.2%  norm=0.815  lr=2.27e-04  dt=  36.9ms  words=38,510,592
[E04    58/1548 G   4701|CLM] train=4.7954  mask=16.2%  norm=0.939  lr=2.27e-04  dt=  36.9ms  words=38,518,784
[E04    59/1548 G   4702|CLM] train=5.0569  mask=16.2%  norm=0.919  lr=2.27e-04  dt=  36.8ms  words=38,526,976
[E04    60/1548 G   4703|CLM] train=4.4334  mask=16.2%  norm=1.009  lr=2.27e-04  dt=  36.9ms  words=38,535,168
[E04    61/1548 G   4704|CLM] train=3.6620  mask=16.2%  norm=0.866  lr=2.27e-04  dt=  36.9ms  words=38,543,360
[E04    62/1548 G   4705|CLM] train=2.4943  mask=16.2%  norm=0.748  lr=2.27e-04  dt=  36.7ms  words=38,551,552
[E04    63/1548 G   4706|CLM] train=2.4067  mask=16.2%  norm=0.721  lr=2.27e-04  dt=  36.8ms  words=38,559,744
[E04    64/1548 G   4707|CLM] train=2.4907  mask=16.2%  norm=0.710  lr=2.27e-04  dt=  37.0ms  words=38,567,936
[E04    65/1548 G   4708|CLM] train=3.9934  mask=16.2%  norm=0.745  lr=2.27e-04  dt=  37.0ms  words=38,576,128
[E04    66/1548 G   4709|CLM] train=4.3600  mask=16.2%  norm=0.735  lr=2.27e-04  dt=  36.9ms  words=38,584,320
[E04    67/1548 G   4710|CLM] train=2.5151  mask=16.2%  norm=0.797  lr=2.27e-04  dt=  36.9ms  words=38,592,512
[E04    68/1548 G   4711|CLM] train=4.8679  mask=16.2%  norm=1.092  lr=2.27e-04  dt=  37.1ms  words=38,600,704
[E04    69/1548 G   4712|CLM] train=2.7076  mask=16.2%  norm=0.729  lr=2.27e-04  dt=  36.7ms  words=38,608,896
[E04    70/1548 G   4713|CLM] train=2.6643  mask=16.2%  norm=0.612  lr=2.27e-04  dt=  36.8ms  words=38,617,088
[E04    71/1548 G   4714|CLM] train=3.5924  mask=16.2%  norm=0.780  lr=2.27e-04  dt=  37.4ms  words=38,625,280
[E04    72/1548 G   4715|CLM] train=2.5019  mask=16.2%  norm=0.661  lr=2.27e-04  dt=  36.9ms  words=38,633,472
[E04    73/1548 G   4716|CLM] train=4.3258  mask=16.2%  norm=0.850  lr=2.27e-04  dt=  36.8ms  words=38,641,664
[E04    74/1548 G   4717|CLM] train=2.8192  mask=16.2%  norm=0.606  lr=2.27e-04  dt=  36.8ms  words=38,649,856
[E04    75/1548 G   4718|CLM] train=2.3668  mask=16.2%  norm=0.674  lr=2.27e-04  dt=  36.9ms  words=38,658,048
[E04    76/1548 G   4719|CLM] train=4.7695  mask=16.2%  norm=1.297  lr=2.27e-04  dt=  37.0ms  words=38,666,240
[E04    77/1548 G   4720|CLM] train=2.4623  mask=16.2%  norm=0.797  lr=2.27e-04  dt=  36.8ms  words=38,674,432
[E04    78/1548 G   4721|CLM] train=5.2546  mask=16.2%  norm=1.299  lr=2.27e-04  dt=  36.8ms  words=38,682,624
[E04    79/1548 G   4722|CLM] train=4.4783  mask=16.2%  norm=1.099  lr=2.27e-04  dt=  36.8ms  words=38,690,816
[E04    80/1548 G   4723|CLM] train=4.4347  mask=16.2%  norm=0.774  lr=2.27e-04  dt=  37.1ms  words=38,699,008
[E04    81/1548 G   4724|CLM] train=4.3150  mask=16.2%  norm=0.788  lr=2.27e-04  dt=  36.8ms  words=38,707,200
[E04    82/1548 G   4725|CLM] train=3.0719  mask=16.2%  norm=0.625  lr=2.27e-04  dt=  37.2ms  words=38,715,392
[E04    83/1548 G   4726|CLM] train=2.4995  mask=16.2%  norm=0.715  lr=2.27e-04  dt=  36.8ms  words=38,723,584
[E04    84/1548 G   4727|CLM] train=2.6328  mask=16.2%  norm=0.555  lr=2.27e-04  dt=  38.3ms  words=38,731,776
[E04    85/1548 G   4728|CLM] train=4.8704  mask=16.2%  norm=1.004  lr=2.27e-04  dt=  44.1ms  words=38,739,968
[E04    86/1548 G   4729|CLM] train=5.7736  mask=16.2%  norm=1.125  lr=2.26e-04  dt=  37.1ms  words=38,748,160
[E04    87/1548 G   4730|CLM] train=2.9149  mask=16.2%  norm=0.609  lr=2.26e-04  dt=  37.3ms  words=38,756,352
[E04    88/1548 G   4731|CLM] train=5.3129  mask=16.2%  norm=0.849  lr=2.26e-04  dt=  37.2ms  words=38,764,544
[E04    89/1548 G   4732|CLM] train=4.2786  mask=16.2%  norm=1.265  lr=2.26e-04  dt=  37.6ms  words=38,772,736
[E04    90/1548 G   4733|CLM] train=4.3108  mask=16.2%  norm=0.756  lr=2.26e-04  dt=  36.9ms  words=38,780,928
[E04    91/1548 G   4734|CLM] train=4.3426  mask=16.2%  norm=0.848  lr=2.26e-04  dt=  37.4ms  words=38,789,120
[E04    92/1548 G   4735|CLM] train=5.0157  mask=16.2%  norm=0.972  lr=2.26e-04  dt=  37.0ms  words=38,797,312
[E04    93/1548 G   4736|CLM] train=4.9543  mask=16.2%  norm=0.883  lr=2.26e-04  dt=  37.4ms  words=38,805,504
[E04    94/1548 G   4737|CLM] train=4.0870  mask=16.2%  norm=0.927  lr=2.26e-04  dt=  36.8ms  words=38,813,696
[E04    95/1548 G   4738|CLM] train=4.5783  mask=16.2%  norm=0.841  lr=2.26e-04  dt=  37.6ms  words=38,821,888
[E04    96/1548 G   4739|CLM] train=4.6001  mask=16.2%  norm=0.892  lr=2.26e-04  dt=  37.4ms  words=38,830,080
[E04    97/1548 G   4740|CLM] train=2.7537  mask=16.2%  norm=0.741  lr=2.26e-04  dt=  37.5ms  words=38,838,272
[E04    98/1548 G   4741|CLM] train=2.7863  mask=16.2%  norm=0.633  lr=2.26e-04  dt=  37.5ms  words=38,846,464
[E04    99/1548 G   4742|CLM] train=4.8244  mask=16.2%  norm=0.765  lr=2.26e-04  dt=  37.2ms  words=38,854,656
[E04   100/1548 G   4743|CLM] train=4.1575  mask=16.2%  norm=0.676  lr=2.26e-04  dt=  37.0ms  words=38,862,848
[E04   101/1548 G   4744|CLM] train=5.4359  mask=16.2%  norm=1.153  lr=2.26e-04  dt=  39.6ms  words=38,871,040
[E04   102/1548 G   4745|CLM] train=2.9539  mask=16.2%  norm=1.279  lr=2.26e-04  dt=  42.0ms  words=38,879,232
[E04   103/1548 G   4746|CLM] train=4.5071  mask=16.2%  norm=0.886  lr=2.26e-04  dt=  41.5ms  words=38,887,424
[E04   104/1548 G   4747|CLM] train=2.3212  mask=16.2%  norm=0.807  lr=2.26e-04  dt=  45.6ms  words=38,895,616
[E04   105/1548 G   4748|CLM] train=4.6719  mask=16.2%  norm=0.868  lr=2.26e-04  dt=  42.4ms  words=38,903,808
[E04   106/1548 G   4749|CLM] train=2.6200  mask=16.2%  norm=0.720  lr=2.26e-04  dt=  37.2ms  words=38,912,000
[E04   107/1548 G   4750|CLM] train=2.4717  mask=16.2%  norm=0.615  lr=2.26e-04  dt=  37.2ms  words=38,920,192
[E04   108/1548 G   4751|CLM] train=4.2461  mask=16.2%  norm=0.881  lr=2.26e-04  dt=  37.0ms  words=38,928,384
[E04   109/1548 G   4752|CLM] train=4.6831  mask=16.2%  norm=0.715  lr=2.26e-04  dt=  36.9ms  words=38,936,576
[E04   110/1548 G   4753|CLM] train=5.6827  mask=16.2%  norm=0.986  lr=2.26e-04  dt=  37.2ms  words=38,944,768
[E04   111/1548 G   4754|CLM] train=2.6218  mask=16.2%  norm=0.851  lr=2.26e-04  dt=  37.4ms  words=38,952,960
[E04   112/1548 G   4755|CLM] train=2.7194  mask=16.2%  norm=0.830  lr=2.26e-04  dt=  37.7ms  words=38,961,152
[E04   113/1548 G   4756|CLM] train=3.6876  mask=16.2%  norm=0.676  lr=2.26e-04  dt=  37.5ms  words=38,969,344
[E04   114/1548 G   4757|CLM] train=2.6570  mask=16.2%  norm=0.664  lr=2.26e-04  dt=  36.9ms  words=38,977,536
[E04   115/1548 G   4758|CLM] train=4.7221  mask=16.2%  norm=0.898  lr=2.25e-04  dt=  38.2ms  words=38,985,728
[E04   116/1548 G   4759|CLM] train=2.5001  mask=16.2%  norm=0.797  lr=2.25e-04  dt=  37.6ms  words=38,993,920
[E04   117/1548 G   4760|CLM] train=4.0335  mask=16.2%  norm=0.638  lr=2.25e-04  dt=  38.1ms  words=39,002,112
[E04   118/1548 G   4761|CLM] train=2.5433  mask=16.2%  norm=0.835  lr=2.25e-04  dt=  38.7ms  words=39,010,304
[E04   119/1548 G   4762|CLM] train=4.3410  mask=16.2%  norm=1.598  lr=2.25e-04  dt=  40.8ms  words=39,018,496
[E04   120/1548 G   4763|CLM] train=2.8199  mask=16.2%  norm=0.640  lr=2.25e-04  dt=  38.0ms  words=39,026,688
[E04   121/1548 G   4764|CLM] train=3.9633  mask=16.2%  norm=0.973  lr=2.25e-04  dt=  38.0ms  words=39,034,880
[E04   122/1548 G   4765|CLM] train=2.4681  mask=16.2%  norm=0.769  lr=2.25e-04  dt=  37.6ms  words=39,043,072
[E04   123/1548 G   4766|CLM] train=2.6572  mask=16.2%  norm=0.691  lr=2.25e-04  dt=  39.7ms  words=39,051,264
[E04   124/1548 G   4767|CLM] train=4.6166  mask=16.2%  norm=0.878  lr=2.25e-04  dt=  47.3ms  words=39,059,456
[E04   125/1548 G   4768|CLM] train=3.7622  mask=16.1%  norm=0.691  lr=2.25e-04  dt=  41.5ms  words=39,067,648
[E04   126/1548 G   4769|CLM] train=4.1745  mask=16.1%  norm=0.656  lr=2.25e-04  dt=  41.4ms  words=39,075,840
[E04   127/1548 G   4770|CLM] train=4.3819  mask=16.1%  norm=0.800  lr=2.25e-04  dt=  48.4ms  words=39,084,032
[E04   128/1548 G   4771|CLM] train=2.7168  mask=16.1%  norm=0.902  lr=2.25e-04  dt=  43.4ms  words=39,092,224
[E04   129/1548 G   4772|CLM] train=4.4643  mask=16.1%  norm=0.917  lr=2.25e-04  dt=  40.0ms  words=39,100,416
[E04   130/1548 G   4773|CLM] train=4.4175  mask=16.1%  norm=0.695  lr=2.25e-04  dt=  37.9ms  words=39,108,608
[E04   131/1548 G   4774|CLM] train=2.4745  mask=16.1%  norm=0.849  lr=2.25e-04  dt=  37.6ms  words=39,116,800
[E04   132/1548 G   4775|CLM] train=2.5050  mask=16.1%  norm=0.778  lr=2.25e-04  dt=  37.5ms  words=39,124,992
[E04   133/1548 G   4776|CLM] train=4.2822  mask=16.1%  norm=0.826  lr=2.25e-04  dt=  37.7ms  words=39,133,184
[E04   134/1548 G   4777|CLM] train=4.3257  mask=16.1%  norm=0.899  lr=2.25e-04  dt=  37.5ms  words=39,141,376
[E04   135/1548 G   4778|CLM] train=4.3014  mask=16.1%  norm=0.899  lr=2.25e-04  dt=  37.5ms  words=39,149,568
[E04   136/1548 G   4779|CLM] train=2.3401  mask=16.1%  norm=0.752  lr=2.25e-04  dt=  37.8ms  words=39,157,760
[E04   137/1548 G   4780|CLM] train=4.2143  mask=16.1%  norm=0.831  lr=2.25e-04  dt=  37.5ms  words=39,165,952
[E04   138/1548 G   4781|CLM] train=4.2197  mask=16.1%  norm=0.846  lr=2.25e-04  dt=  37.3ms  words=39,174,144
[E04   139/1548 G   4782|CLM] train=2.2295  mask=16.1%  norm=0.745  lr=2.25e-04  dt=  37.1ms  words=39,182,336
[E04   140/1548 G   4783|CLM] train=2.4054  mask=16.1%  norm=1.079  lr=2.25e-04  dt=  37.3ms  words=39,190,528
[E04   141/1548 G   4784|CLM] train=4.1135  mask=16.1%  norm=0.807  lr=2.25e-04  dt=  37.3ms  words=39,198,720
[E04   142/1548 G   4785|CLM] train=2.5020  mask=16.1%  norm=0.657  lr=2.25e-04  dt=  37.3ms  words=39,206,912
[E04   143/1548 G   4786|CLM] train=2.7019  mask=16.1%  norm=1.160  lr=2.25e-04  dt=  37.4ms  words=39,215,104
[E04   144/1548 G   4787|CLM] train=2.3112  mask=16.1%  norm=0.724  lr=2.25e-04  dt=  37.7ms  words=39,223,296
[E04   145/1548 G   4788|CLM] train=3.8210  mask=16.1%  norm=0.676  lr=2.24e-04  dt=  37.5ms  words=39,231,488
[E04   146/1548 G   4789|CLM] train=2.4154  mask=16.1%  norm=0.714  lr=2.24e-04  dt=  37.1ms  words=39,239,680
[E04   147/1548 G   4790|CLM] train=4.1037  mask=16.1%  norm=1.065  lr=2.24e-04  dt=  37.6ms  words=39,247,872
[E04   148/1548 G   4791|CLM] train=4.4253  mask=16.1%  norm=0.760  lr=2.24e-04  dt=  37.5ms  words=39,256,064
[E04   149/1548 G   4792|CLM] train=3.9853  mask=16.1%  norm=0.842  lr=2.24e-04  dt=  37.5ms  words=39,264,256
[E04   150/1548 G   4793|CLM] train=4.5031  mask=16.1%  norm=0.785  lr=2.24e-04  dt=  37.5ms  words=39,272,448
[E04   151/1548 G   4794|CLM] train=5.0546  mask=16.1%  norm=0.938  lr=2.24e-04  dt=  37.7ms  words=39,280,640
[E04   152/1548 G   4795|CLM] train=4.2957  mask=16.1%  norm=0.667  lr=2.24e-04  dt=  37.4ms  words=39,288,832
[E04   153/1548 G   4796|CLM] train=2.1081  mask=16.1%  norm=0.805  lr=2.24e-04  dt=  37.3ms  words=39,297,024
[E04   154/1548 G   4797|CLM] train=4.4264  mask=16.1%  norm=0.770  lr=2.24e-04  dt=  37.2ms  words=39,305,216
[E04   155/1548 G   4798|CLM] train=4.1355  mask=16.1%  norm=1.799  lr=2.24e-04  dt=  37.3ms  words=39,313,408
[E04   156/1548 G   4799|CLM] train=4.6681  mask=16.1%  norm=1.116  lr=2.24e-04  dt=  37.3ms  words=39,321,600
[E04   157/1548 G   4800|CLM] train=5.4992  mask=16.1%  norm=1.159  lr=2.24e-04  dt=  37.3ms  words=39,329,792
[E04   158/1548 G   4801|CLM] train=4.6329  mask=16.1%  norm=1.481  lr=2.24e-04  dt=  37.2ms  words=39,337,984
[E04   159/1548 G   4802|CLM] train=4.6770  mask=16.1%  norm=0.940  lr=2.24e-04  dt=  37.3ms  words=39,346,176
[E04   160/1548 G   4803|CLM] train=4.6585  mask=16.1%  norm=0.770  lr=2.24e-04  dt=  37.6ms  words=39,354,368
[E04   161/1548 G   4804|CLM] train=2.3195  mask=16.1%  norm=0.989  lr=2.24e-04  dt=  37.3ms  words=39,362,560
[E04   162/1548 G   4805|CLM] train=5.0156  mask=16.1%  norm=0.841  lr=2.24e-04  dt=  37.3ms  words=39,370,752
[E04   163/1548 G   4806|CLM] train=2.5143  mask=16.1%  norm=0.944  lr=2.24e-04  dt=  37.7ms  words=39,378,944
[E04   164/1548 G   4807|CLM] train=2.6979  mask=16.1%  norm=0.669  lr=2.24e-04  dt=  37.3ms  words=39,387,136
[E04   165/1548 G   4808|CLM] train=4.3360  mask=16.1%  norm=1.232  lr=2.24e-04  dt=  37.3ms  words=39,395,328
[E04   166/1548 G   4809|CLM] train=4.2279  mask=16.1%  norm=0.938  lr=2.24e-04  dt=  37.5ms  words=39,403,520
[E04   167/1548 G   4810|CLM] train=4.0131  mask=16.1%  norm=0.691  lr=2.24e-04  dt=  37.3ms  words=39,411,712
[E04   168/1548 G   4811|CLM] train=3.8146  mask=16.1%  norm=0.737  lr=2.24e-04  dt=  37.0ms  words=39,419,904
[E04   169/1548 G   4812|CLM] train=2.8642  mask=16.1%  norm=0.714  lr=2.24e-04  dt=  37.3ms  words=39,428,096
[E04   170/1548 G   4813|CLM] train=4.1189  mask=16.1%  norm=0.783  lr=2.24e-04  dt=  37.4ms  words=39,436,288
[E04   171/1548 G   4814|CLM] train=4.2750  mask=16.1%  norm=0.702  lr=2.24e-04  dt=  37.1ms  words=39,444,480
[E04   172/1548 G   4815|CLM] train=5.5911  mask=16.1%  norm=1.383  lr=2.24e-04  dt=  37.3ms  words=39,452,672
[E04   173/1548 G   4816|CLM] train=2.7379  mask=16.1%  norm=0.941  lr=2.24e-04  dt=  37.8ms  words=39,460,864
[E04   174/1548 G   4817|CLM] train=2.8872  mask=16.1%  norm=0.630  lr=2.23e-04  dt=  37.5ms  words=39,469,056
[E04   175/1548 G   4818|CLM] train=4.4916  mask=16.1%  norm=1.224  lr=2.23e-04  dt=  37.7ms  words=39,477,248
[E04   176/1548 G   4819|CLM] train=3.0224  mask=16.1%  norm=1.567  lr=2.23e-04  dt=  37.3ms  words=39,485,440
[E04   177/1548 G   4820|CLM] train=2.4003  mask=16.1%  norm=0.730  lr=2.23e-04  dt=  37.3ms  words=39,493,632
[E04   178/1548 G   4821|CLM] train=2.3510  mask=16.1%  norm=1.096  lr=2.23e-04  dt=  37.4ms  words=39,501,824
[E04   179/1548 G   4822|CLM] train=2.3662  mask=16.1%  norm=0.824  lr=2.23e-04  dt=  37.3ms  words=39,510,016
[E04   180/1548 G   4823|CLM] train=4.3073  mask=16.1%  norm=0.979  lr=2.23e-04  dt=  37.4ms  words=39,518,208
[E04   181/1548 G   4824|CLM] train=5.4888  mask=16.1%  norm=1.604  lr=2.23e-04  dt=  37.3ms  words=39,526,400
[E04   182/1548 G   4825|CLM] train=1.9881  mask=16.1%  norm=0.740  lr=2.23e-04  dt=  37.3ms  words=39,534,592
[E04   183/1548 G   4826|CLM] train=4.1903  mask=16.1%  norm=0.867  lr=2.23e-04  dt=  37.3ms  words=39,542,784
[E04   184/1548 G   4827|CLM] train=4.9688  mask=16.1%  norm=0.876  lr=2.23e-04  dt=  37.3ms  words=39,550,976
[E04   185/1548 G   4828|CLM] train=4.5787  mask=16.1%  norm=0.755  lr=2.23e-04  dt=  37.2ms  words=39,559,168
[E04   186/1548 G   4829|CLM] train=4.7344  mask=16.1%  norm=0.891  lr=2.23e-04  dt=  37.2ms  words=39,567,360
[E04   187/1548 G   4830|CLM] train=4.8723  mask=16.1%  norm=1.890  lr=2.23e-04  dt=  37.6ms  words=39,575,552
[E04   188/1548 G   4831|CLM] train=2.2505  mask=16.1%  norm=1.443  lr=2.23e-04  dt=  37.3ms  words=39,583,744
[E04   189/1548 G   4832|CLM] train=4.0162  mask=16.1%  norm=0.729  lr=2.23e-04  dt=  37.6ms  words=39,591,936
[E04   190/1548 G   4833|CLM] train=4.1664  mask=16.1%  norm=0.845  lr=2.23e-04  dt=  37.3ms  words=39,600,128
[E04   191/1548 G   4834|CLM] train=4.6385  mask=16.1%  norm=1.225  lr=2.23e-04  dt=  37.6ms  words=39,608,320
[E04   192/1548 G   4835|CLM] train=5.2526  mask=16.1%  norm=1.232  lr=2.23e-04  dt=  37.3ms  words=39,616,512
[E04   193/1548 G   4836|CLM] train=4.6701  mask=16.1%  norm=1.031  lr=2.23e-04  dt=  37.3ms  words=39,624,704
[E04   194/1548 G   4837|CLM] train=4.5171  mask=16.1%  norm=0.681  lr=2.23e-04  dt=  37.3ms  words=39,632,896
[E04   195/1548 G   4838|CLM] train=4.2148  mask=16.1%  norm=0.663  lr=2.23e-04  dt=  37.4ms  words=39,641,088
[E04   196/1548 G   4839|CLM] train=2.3627  mask=16.1%  norm=0.960  lr=2.23e-04  dt=  37.2ms  words=39,649,280
[E04   197/1548 G   4840|CLM] train=3.8126  mask=16.1%  norm=0.806  lr=2.23e-04  dt=  37.5ms  words=39,657,472
[E04   198/1548 G   4841|CLM] train=5.0303  mask=16.1%  norm=0.931  lr=2.23e-04  dt=  37.3ms  words=39,665,664
[E04   199/1548 G   4842|CLM] train=4.2145  mask=16.1%  norm=0.736  lr=2.23e-04  dt=  37.3ms  words=39,673,856
[E04   200/1548 G   4843|CLM] train=4.1132  mask=16.1%  norm=0.762  lr=2.23e-04  dt=  37.1ms  words=39,682,048
[E04   201/1548 G   4844|CLM] train=4.7120  mask=16.1%  norm=1.002  lr=2.23e-04  dt=  37.5ms  words=39,690,240
[E04   202/1548 G   4845|CLM] train=2.2470  mask=16.1%  norm=1.204  lr=2.23e-04  dt=  37.5ms  words=39,698,432
[E04   203/1548 G   4846|CLM] train=2.4185  mask=16.1%  norm=0.707  lr=2.22e-04  dt=  37.7ms  words=39,706,624
[E04   204/1548 G   4847|CLM] train=2.6727  mask=16.1%  norm=0.821  lr=2.22e-04  dt=  37.4ms  words=39,714,816
[E04   205/1548 G   4848|CLM] train=1.8851  mask=16.1%  norm=0.622  lr=2.22e-04  dt=  37.5ms  words=39,723,008
[E04   206/1548 G   4849|CLM] train=4.3650  mask=16.1%  norm=1.012  lr=2.22e-04  dt=  37.3ms  words=39,731,200
[E04   207/1548 G   4850|CLM] train=3.9969  mask=16.1%  norm=0.751  lr=2.22e-04  dt=  37.2ms  words=39,739,392
[E04   208/1548 G   4851|CLM] train=2.4130  mask=16.1%  norm=0.748  lr=2.22e-04  dt=  37.1ms  words=39,747,584
[E04   209/1548 G   4852|CLM] train=4.7577  mask=16.1%  norm=1.080  lr=2.22e-04  dt=  37.3ms  words=39,755,776
[E04   210/1548 G   4853|CLM] train=4.4120  mask=16.1%  norm=0.739  lr=2.22e-04  dt=  37.4ms  words=39,763,968
[E04   211/1548 G   4854|CLM] train=2.3975  mask=16.1%  norm=0.743  lr=2.22e-04  dt=  37.2ms  words=39,772,160
[E04   212/1548 G   4855|CLM] train=4.7758  mask=16.1%  norm=1.191  lr=2.22e-04  dt=  37.3ms  words=39,780,352
[E04   213/1548 G   4856|CLM] train=4.4112  mask=16.1%  norm=0.790  lr=2.22e-04  dt=  37.2ms  words=39,788,544
[E04   214/1548 G   4857|CLM] train=4.9115  mask=16.1%  norm=0.910  lr=2.22e-04  dt=  37.5ms  words=39,796,736
[E04   215/1548 G   4858|CLM] train=3.0362  mask=16.1%  norm=0.686  lr=2.22e-04  dt=  38.6ms  words=39,804,928
[E04   216/1548 G   4859|CLM] train=3.9826  mask=16.1%  norm=0.821  lr=2.22e-04  dt=  39.7ms  words=39,813,120
[E04   217/1548 G   4860|CLM] train=3.8294  mask=16.1%  norm=0.646  lr=2.22e-04  dt=  42.7ms  words=39,821,312
[E04   218/1548 G   4861|CLM] train=4.4918  mask=16.1%  norm=1.281  lr=2.22e-04  dt=  42.0ms  words=39,829,504
[E04   219/1548 G   4862|CLM] train=2.2490  mask=16.1%  norm=0.851  lr=2.22e-04  dt=  44.2ms  words=39,837,696
[E04   220/1548 G   4863|CLM] train=3.9588  mask=16.1%  norm=1.067  lr=2.22e-04  dt=  41.4ms  words=39,845,888
[E04   221/1548 G   4864|CLM] train=2.6475  mask=16.1%  norm=0.773  lr=2.22e-04  dt=  42.6ms  words=39,854,080
[E04   222/1548 G   4865|CLM] train=4.1650  mask=16.1%  norm=0.622  lr=2.22e-04  dt=  38.1ms  words=39,862,272
[E04   223/1548 G   4866|CLM] train=2.2096  mask=16.1%  norm=0.758  lr=2.22e-04  dt=  38.6ms  words=39,870,464
[E04   224/1548 G   4867|CLM] train=3.8571  mask=16.1%  norm=0.691  lr=2.22e-04  dt=  37.9ms  words=39,878,656
[E04   225/1548 G   4868|CLM] train=4.7486  mask=16.1%  norm=0.862  lr=2.22e-04  dt=  37.6ms  words=39,886,848
[E04   226/1548 G   4869|CLM] train=4.7071  mask=16.1%  norm=1.413  lr=2.22e-04  dt=  37.9ms  words=39,895,040
[E04   227/1548 G   4870|CLM] train=2.2637  mask=16.1%  norm=0.720  lr=2.22e-04  dt=  37.9ms  words=39,903,232
[E04   228/1548 G   4871|CLM] train=4.5118  mask=16.1%  norm=0.672  lr=2.22e-04  dt=  37.6ms  words=39,911,424
[E04   229/1548 G   4872|CLM] train=2.9260  mask=16.1%  norm=1.120  lr=2.22e-04  dt=  37.5ms  words=39,919,616
[E04   230/1548 G   4873|CLM] train=4.4342  mask=16.1%  norm=0.997  lr=2.22e-04  dt=  37.6ms  words=39,927,808
[E04   231/1548 G   4874|CLM] train=2.4479  mask=16.1%  norm=0.997  lr=2.22e-04  dt=  37.4ms  words=39,936,000
[E04   232/1548 G   4875|CLM] train=5.1838  mask=16.1%  norm=1.064  lr=2.21e-04  dt=  37.5ms  words=39,944,192
[E04   233/1548 G   4876|CLM] train=3.5620  mask=16.1%  norm=0.946  lr=2.21e-04  dt=  37.5ms  words=39,952,384
[E04   234/1548 G   4877|CLM] train=2.1604  mask=16.1%  norm=0.666  lr=2.21e-04  dt=  37.5ms  words=39,960,576
[E04   235/1548 G   4878|CLM] train=4.7076  mask=16.1%  norm=0.951  lr=2.21e-04  dt=  37.4ms  words=39,968,768
[E04   236/1548 G   4879|CLM] train=2.7208  mask=16.1%  norm=0.590  lr=2.21e-04  dt=  37.3ms  words=39,976,960
[E04   237/1548 G   4880|CLM] train=4.2617  mask=16.1%  norm=1.083  lr=2.21e-04  dt=  37.2ms  words=39,985,152
[E04   238/1548 G   4881|CLM] train=1.9758  mask=16.1%  norm=0.730  lr=2.21e-04  dt=  37.5ms  words=39,993,344
[E04   239/1548 G   4882|CLM] train=2.2852  mask=16.1%  norm=0.636  lr=2.21e-04  dt=  37.4ms  words=40,001,536

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_40M'...
[Checkpoint] Checkpoint 'chck_40M' successfully saved.
[E04   240/1548 G   4883|CLM] train=4.2062  mask=16.1%  norm=0.676  lr=2.21e-04  dt=  37.9ms  words=40,009,728
[E04   241/1548 G   4884|CLM] train=4.4675  mask=16.1%  norm=1.061  lr=2.21e-04  dt=  37.4ms  words=40,017,920
[E04   242/1548 G   4885|CLM] train=2.4578  mask=16.1%  norm=0.857  lr=2.21e-04  dt=  37.3ms  words=40,026,112
[E04   243/1548 G   4886|CLM] train=4.8941  mask=16.1%  norm=0.869  lr=2.21e-04  dt=  37.3ms  words=40,034,304
[E04   244/1548 G   4887|CLM] train=4.0012  mask=16.1%  norm=0.954  lr=2.21e-04  dt=  37.3ms  words=40,042,496
[E04   245/1548 G   4888|CLM] train=3.5814  mask=16.1%  norm=0.860  lr=2.21e-04  dt=  37.1ms  words=40,050,688
[E04   246/1548 G   4889|CLM] train=2.4430  mask=16.1%  norm=0.684  lr=2.21e-04  dt=  37.3ms  words=40,058,880
[E04   247/1548 G   4890|CLM] train=2.7980  mask=16.1%  norm=0.687  lr=2.21e-04  dt=  37.3ms  words=40,067,072
[E04   248/1548 G   4891|CLM] train=2.5243  mask=16.1%  norm=0.614  lr=2.21e-04  dt=  37.6ms  words=40,075,264
[E04   249/1548 G   4892|CLM] train=4.4365  mask=16.0%  norm=0.859  lr=2.21e-04  dt=  37.4ms  words=40,083,456
[E04   250/1548 G   4893|CLM] train=3.9562  mask=16.0%  norm=0.847  lr=2.21e-04  dt=  37.4ms  words=40,091,648
[E04   251/1548 G   4894|CLM] train=4.3466  mask=16.0%  norm=0.701  lr=2.21e-04  dt=  37.3ms  words=40,099,840
[E04   252/1548 G   4895|CLM] train=2.4836  mask=16.0%  norm=0.712  lr=2.21e-04  dt=  37.4ms  words=40,108,032
[E04   253/1548 G   4896|CLM] train=2.4372  mask=16.0%  norm=1.189  lr=2.21e-04  dt=  37.4ms  words=40,116,224
[E04   254/1548 G   4897|CLM] train=4.7852  mask=16.0%  norm=0.771  lr=2.21e-04  dt=  37.1ms  words=40,124,416
[E04   255/1548 G   4898|CLM] train=4.6365  mask=16.0%  norm=0.697  lr=2.21e-04  dt=  37.3ms  words=40,132,608
[E04   256/1548 G   4899|CLM] train=2.7787  mask=16.0%  norm=0.770  lr=2.21e-04  dt=  37.3ms  words=40,140,800
[E04   257/1548 G   4900|CLM] train=2.4250  mask=16.0%  norm=0.942  lr=2.21e-04  dt=  37.3ms  words=40,148,992
[E04   258/1548 G   4901|CLM] train=4.1318  mask=16.0%  norm=0.708  lr=2.21e-04  dt=  37.4ms  words=40,157,184
[E04   259/1548 G   4902|CLM] train=4.3977  mask=16.0%  norm=0.786  lr=2.21e-04  dt=  37.3ms  words=40,165,376
[E04   260/1548 G   4903|CLM] train=4.4084  mask=16.0%  norm=0.990  lr=2.21e-04  dt=  37.2ms  words=40,173,568
[E04   261/1548 G   4904|CLM] train=4.9017  mask=16.0%  norm=1.027  lr=2.20e-04  dt=  37.4ms  words=40,181,760
[E04   262/1548 G   4905|CLM] train=2.6695  mask=16.0%  norm=0.736  lr=2.20e-04  dt=  37.3ms  words=40,189,952
[E04   263/1548 G   4906|CLM] train=4.2876  mask=16.0%  norm=0.754  lr=2.20e-04  dt=  37.6ms  words=40,198,144
[E04   264/1548 G   4907|CLM] train=2.3207  mask=16.0%  norm=0.929  lr=2.20e-04  dt=  37.4ms  words=40,206,336
[E04   265/1548 G   4908|CLM] train=2.2170  mask=16.0%  norm=0.634  lr=2.20e-04  dt=  37.3ms  words=40,214,528
[E04   266/1548 G   4909|CLM] train=2.4825  mask=16.0%  norm=0.763  lr=2.20e-04  dt=  37.4ms  words=40,222,720
[E04   267/1548 G   4910|CLM] train=2.4777  mask=16.0%  norm=0.714  lr=2.20e-04  dt=  37.3ms  words=40,230,912
[E04   268/1548 G   4911|CLM] train=2.8447  mask=16.0%  norm=0.716  lr=2.20e-04  dt=  37.4ms  words=40,239,104
[E04   269/1548 G   4912|CLM] train=3.6996  mask=16.0%  norm=0.985  lr=2.20e-04  dt=  37.1ms  words=40,247,296
[E04   270/1548 G   4913|CLM] train=4.6574  mask=16.0%  norm=0.923  lr=2.20e-04  dt=  37.2ms  words=40,255,488
[E04   271/1548 G   4914|CLM] train=4.5273  mask=16.0%  norm=0.959  lr=2.20e-04  dt=  37.3ms  words=40,263,680
[E04   272/1548 G   4915|CLM] train=4.6049  mask=16.0%  norm=0.712  lr=2.20e-04  dt=  37.2ms  words=40,271,872
[E04   273/1548 G   4916|CLM] train=4.2782  mask=16.0%  norm=0.718  lr=2.20e-04  dt=  37.2ms  words=40,280,064
[E04   274/1548 G   4917|CLM] train=2.4741  mask=16.0%  norm=1.065  lr=2.20e-04  dt=  37.3ms  words=40,288,256
[E04   275/1548 G   4918|CLM] train=2.5770  mask=16.0%  norm=1.028  lr=2.20e-04  dt=  37.6ms  words=40,296,448
[E04   276/1548 G   4919|CLM] train=4.2436  mask=16.0%  norm=0.702  lr=2.20e-04  dt=  37.3ms  words=40,304,640
[E04   277/1548 G   4920|CLM] train=4.5314  mask=16.0%  norm=0.987  lr=2.20e-04  dt=  37.2ms  words=40,312,832
[E04   278/1548 G   4921|CLM] train=2.5898  mask=16.0%  norm=0.630  lr=2.20e-04  dt=  37.5ms  words=40,321,024
[E04   279/1548 G   4922|CLM] train=5.1132  mask=16.0%  norm=1.623  lr=2.20e-04  dt=  37.2ms  words=40,329,216
[E04   280/1548 G   4923|CLM] train=4.0304  mask=16.0%  norm=1.092  lr=2.20e-04  dt=  37.3ms  words=40,337,408
[E04   281/1548 G   4924|CLM] train=4.4650  mask=16.0%  norm=0.739  lr=2.20e-04  dt=  37.3ms  words=40,345,600
[E04   282/1548 G   4925|CLM] train=4.5307  mask=16.0%  norm=0.870  lr=2.20e-04  dt=  37.2ms  words=40,353,792
[E04   283/1548 G   4926|CLM] train=2.7246  mask=16.0%  norm=0.746  lr=2.20e-04  dt=  37.3ms  words=40,361,984
[E04   284/1548 G   4927|CLM] train=4.6557  mask=16.0%  norm=0.823  lr=2.20e-04  dt=  37.3ms  words=40,370,176
[E04   285/1548 G   4928|CLM] train=4.6364  mask=16.0%  norm=0.817  lr=2.20e-04  dt=  37.2ms  words=40,378,368
[E04   286/1548 G   4929|CLM] train=2.8925  mask=16.0%  norm=0.770  lr=2.20e-04  dt=  37.3ms  words=40,386,560
[E04   287/1548 G   4930|CLM] train=4.4467  mask=16.0%  norm=0.833  lr=2.20e-04  dt=  37.5ms  words=40,394,752
[E04   288/1548 G   4931|CLM] train=4.4466  mask=16.0%  norm=1.229  lr=2.20e-04  dt=  37.4ms  words=40,402,944
[E04   289/1548 G   4932|CLM] train=2.3879  mask=16.0%  norm=0.635  lr=2.20e-04  dt=  37.4ms  words=40,411,136
[E04   290/1548 G   4933|CLM] train=4.3298  mask=16.0%  norm=0.803  lr=2.19e-04  dt=  37.5ms  words=40,419,328
[E04   291/1548 G   4934|CLM] train=3.7779  mask=16.0%  norm=0.745  lr=2.19e-04  dt=  37.3ms  words=40,427,520
[E04   292/1548 G   4935|CLM] train=4.1088  mask=16.0%  norm=1.126  lr=2.19e-04  dt=  37.4ms  words=40,435,712
[E04   293/1548 G   4936|CLM] train=4.3880  mask=16.0%  norm=0.851  lr=2.19e-04  dt=  37.2ms  words=40,443,904
[E04   294/1548 G   4937|CLM] train=4.3183  mask=16.0%  norm=0.849  lr=2.19e-04  dt=  37.1ms  words=40,452,096
[E04   295/1548 G   4938|CLM] train=2.2535  mask=16.0%  norm=0.735  lr=2.19e-04  dt=  37.2ms  words=40,460,288
[E04   296/1548 G   4939|CLM] train=2.5462  mask=16.0%  norm=0.996  lr=2.19e-04  dt=  37.3ms  words=40,468,480
[E04   297/1548 G   4940|CLM] train=2.5113  mask=16.0%  norm=0.735  lr=2.19e-04  dt=  37.2ms  words=40,476,672
[E04   298/1548 G   4941|CLM] train=3.6316  mask=16.0%  norm=0.812  lr=2.19e-04  dt=  37.2ms  words=40,484,864
[E04   299/1548 G   4942|CLM] train=2.3901  mask=16.0%  norm=0.686  lr=2.19e-04  dt=  37.2ms  words=40,493,056
[E04   300/1548 G   4943|CLM] train=4.3618  mask=16.0%  norm=0.786  lr=2.19e-04  dt=  37.3ms  words=40,501,248
[E04   301/1548 G   4944|CLM] train=5.2703  mask=16.0%  norm=3.012  lr=2.19e-04  dt=  37.1ms  words=40,509,440
[E04   302/1548 G   4945|CLM] train=2.0514  mask=16.0%  norm=0.897  lr=2.19e-04  dt=  37.4ms  words=40,517,632
[E04   303/1548 G   4946|CLM] train=4.2532  mask=16.0%  norm=1.293  lr=2.19e-04  dt=  37.4ms  words=40,525,824
[E04   304/1548 G   4947|CLM] train=4.1243  mask=16.0%  norm=0.791  lr=2.19e-04  dt=  37.4ms  words=40,534,016
[E04   305/1548 G   4948|CLM] train=2.4299  mask=16.0%  norm=0.666  lr=2.19e-04  dt=  37.4ms  words=40,542,208
[E04   306/1548 G   4949|CLM] train=2.3453  mask=16.0%  norm=0.660  lr=2.19e-04  dt=  37.4ms  words=40,550,400
[E04   307/1548 G   4950|CLM] train=2.4334  mask=16.0%  norm=0.956  lr=2.19e-04  dt=  37.2ms  words=40,558,592
[E04   308/1548 G   4951|CLM] train=3.8461  mask=16.0%  norm=0.743  lr=2.19e-04  dt=  37.4ms  words=40,566,784
[E04   309/1548 G   4952|CLM] train=4.8467  mask=16.0%  norm=1.000  lr=2.19e-04  dt=  37.4ms  words=40,574,976
[E04   310/1548 G   4953|CLM] train=4.1834  mask=16.0%  norm=0.617  lr=2.19e-04  dt=  37.2ms  words=40,583,168
[E04   311/1548 G   4954|CLM] train=4.3080  mask=16.0%  norm=0.935  lr=2.19e-04  dt=  37.2ms  words=40,591,360
[E04   312/1548 G   4955|CLM] train=3.9112  mask=16.0%  norm=0.742  lr=2.19e-04  dt=  37.2ms  words=40,599,552
[E04   313/1548 G   4956|CLM] train=4.0727  mask=16.0%  norm=0.725  lr=2.19e-04  dt=  37.2ms  words=40,607,744
[E04   314/1548 G   4957|CLM] train=4.3636  mask=16.0%  norm=0.758  lr=2.19e-04  dt=  37.4ms  words=40,615,936
[E04   315/1548 G   4958|CLM] train=2.3287  mask=16.0%  norm=1.066  lr=2.19e-04  dt=  37.5ms  words=40,624,128
[E04   316/1548 G   4959|CLM] train=2.3673  mask=16.0%  norm=1.053  lr=2.19e-04  dt=  37.4ms  words=40,632,320
[E04   317/1548 G   4960|CLM] train=5.1498  mask=16.0%  norm=0.809  lr=2.19e-04  dt=  37.3ms  words=40,640,512
[E04   318/1548 G   4961|CLM] train=4.5319  mask=16.0%  norm=0.765  lr=2.18e-04  dt=  37.5ms  words=40,648,704
[E04   319/1548 G   4962|CLM] train=4.1269  mask=16.0%  norm=0.793  lr=2.18e-04  dt=  37.2ms  words=40,656,896
[E04   320/1548 G   4963|CLM] train=4.2678  mask=16.0%  norm=0.865  lr=2.18e-04  dt=  37.2ms  words=40,665,088
[E04   321/1548 G   4964|CLM] train=4.2203  mask=16.0%  norm=1.343  lr=2.18e-04  dt=  37.2ms  words=40,673,280
[E04   322/1548 G   4965|CLM] train=4.7498  mask=16.0%  norm=0.979  lr=2.18e-04  dt=  37.2ms  words=40,681,472
[E04   323/1548 G   4966|CLM] train=3.9524  mask=16.0%  norm=0.705  lr=2.18e-04  dt=  37.2ms  words=40,689,664
[E04   324/1548 G   4967|CLM] train=2.0884  mask=16.0%  norm=0.820  lr=2.18e-04  dt=  37.3ms  words=40,697,856
[E04   325/1548 G   4968|CLM] train=3.9531  mask=16.0%  norm=0.863  lr=2.18e-04  dt=  37.3ms  words=40,706,048
[E04   326/1548 G   4969|CLM] train=2.2405  mask=16.0%  norm=0.647  lr=2.18e-04  dt=  37.5ms  words=40,714,240
[E04   327/1548 G   4970|CLM] train=4.1131  mask=16.0%  norm=0.709  lr=2.18e-04  dt=  37.3ms  words=40,722,432
[E04   328/1548 G   4971|CLM] train=4.0725  mask=16.0%  norm=1.021  lr=2.18e-04  dt=  37.4ms  words=40,730,624
[E04   329/1548 G   4972|CLM] train=4.8301  mask=16.0%  norm=0.851  lr=2.18e-04  dt=  37.5ms  words=40,738,816
[E04   330/1548 G   4973|CLM] train=2.1716  mask=16.0%  norm=0.668  lr=2.18e-04  dt=  37.4ms  words=40,747,008
[E04   331/1548 G   4974|CLM] train=2.5718  mask=16.0%  norm=1.260  lr=2.18e-04  dt=  37.5ms  words=40,755,200
[E04   332/1548 G   4975|CLM] train=2.6122  mask=16.0%  norm=0.819  lr=2.18e-04  dt=  37.3ms  words=40,763,392
[E04   333/1548 G   4976|CLM] train=2.3613  mask=16.0%  norm=0.710  lr=2.18e-04  dt=  37.4ms  words=40,771,584
[E04   334/1548 G   4977|CLM] train=4.7052  mask=16.0%  norm=0.977  lr=2.18e-04  dt=  37.2ms  words=40,779,776
[E04   335/1548 G   4978|CLM] train=5.3172  mask=16.0%  norm=0.934  lr=2.18e-04  dt=  37.2ms  words=40,787,968
[E04   336/1548 G   4979|CLM] train=2.4685  mask=16.0%  norm=0.607  lr=2.18e-04  dt=  37.2ms  words=40,796,160
[E04   337/1548 G   4980|CLM] train=4.6200  mask=16.0%  norm=0.949  lr=2.18e-04  dt=  37.3ms  words=40,804,352
[E04   338/1548 G   4981|CLM] train=5.2444  mask=16.0%  norm=1.507  lr=2.18e-04  dt=  37.3ms  words=40,812,544
[E04   339/1548 G   4982|CLM] train=2.6193  mask=16.0%  norm=0.809  lr=2.18e-04  dt=  37.2ms  words=40,820,736
[E04   340/1548 G   4983|CLM] train=4.6514  mask=16.0%  norm=0.806  lr=2.18e-04  dt=  37.3ms  words=40,828,928
[E04   341/1548 G   4984|CLM] train=2.2974  mask=16.0%  norm=0.751  lr=2.18e-04  dt=  37.3ms  words=40,837,120
[E04   342/1548 G   4985|CLM] train=3.2007  mask=16.0%  norm=0.831  lr=2.18e-04  dt=  38.1ms  words=40,845,312
[E04   343/1548 G   4986|CLM] train=4.7624  mask=16.0%  norm=0.962  lr=2.18e-04  dt=  38.0ms  words=40,853,504
[E04   344/1548 G   4987|CLM] train=1.7927  mask=16.0%  norm=0.804  lr=2.18e-04  dt=  37.8ms  words=40,861,696
[E04   345/1548 G   4988|CLM] train=4.1233  mask=16.0%  norm=0.813  lr=2.18e-04  dt=  37.6ms  words=40,869,888
[E04   346/1548 G   4989|CLM] train=4.6014  mask=16.0%  norm=0.885  lr=2.18e-04  dt=  37.8ms  words=40,878,080
[E04   347/1548 G   4990|CLM] train=2.3343  mask=16.0%  norm=0.686  lr=2.17e-04  dt=  38.7ms  words=40,886,272
[E04   348/1548 G   4991|CLM] train=4.2828  mask=16.0%  norm=0.946  lr=2.17e-04  dt=  37.6ms  words=40,894,464
[E04   349/1548 G   4992|CLM] train=2.7196  mask=16.0%  norm=0.699  lr=2.17e-04  dt=  39.0ms  words=40,902,656
[E04   350/1548 G   4993|CLM] train=5.2298  mask=16.0%  norm=0.940  lr=2.17e-04  dt=  38.5ms  words=40,910,848
[E04   351/1548 G   4994|CLM] train=2.4591  mask=16.0%  norm=1.092  lr=2.17e-04  dt=  37.4ms  words=40,919,040
[E04   352/1548 G   4995|CLM] train=4.1278  mask=16.0%  norm=0.737  lr=2.17e-04  dt=  37.4ms  words=40,927,232
[E04   353/1548 G   4996|CLM] train=3.7456  mask=16.0%  norm=0.728  lr=2.17e-04  dt=  37.4ms  words=40,935,424
[E04   354/1548 G   4997|CLM] train=4.6745  mask=16.0%  norm=0.929  lr=2.17e-04  dt=  37.5ms  words=40,943,616
[E04   355/1548 G   4998|CLM] train=2.3967  mask=16.0%  norm=0.751  lr=2.17e-04  dt=  37.7ms  words=40,951,808
[E04   356/1548 G   4999|CLM] train=2.5408  mask=16.0%  norm=0.737  lr=2.17e-04  dt=  37.3ms  words=40,960,000
[E04   357/1548 G   5000|CLM] train=5.1181  mask=16.0%  norm=1.085  lr=2.17e-04  dt=  37.5ms  words=40,968,192
[E04   358/1548 G   5001|CLM] train=4.3244  mask=16.0%  norm=0.777  lr=2.17e-04  dt=  37.6ms  words=40,976,384
[E04   359/1548 G   5002|CLM] train=4.4400  mask=16.0%  norm=0.865  lr=2.17e-04  dt=  37.4ms  words=40,984,576
[E04   360/1548 G   5003|CLM] train=2.4433  mask=16.0%  norm=0.650  lr=2.17e-04  dt=  37.3ms  words=40,992,768
[E04   361/1548 G   5004|CLM] train=4.2692  mask=16.0%  norm=1.011  lr=2.17e-04  dt=  37.5ms  words=41,000,960
[E04   362/1548 G   5005|CLM] train=2.8464  mask=16.0%  norm=0.772  lr=2.17e-04  dt=  37.3ms  words=41,009,152
[E04   363/1548 G   5006|CLM] train=2.6626  mask=16.0%  norm=0.734  lr=2.17e-04  dt=  37.3ms  words=41,017,344
[E04   364/1548 G   5007|CLM] train=3.7465  mask=16.0%  norm=0.704  lr=2.17e-04  dt=  37.4ms  words=41,025,536
[E04   365/1548 G   5008|CLM] train=2.1765  mask=16.0%  norm=0.732  lr=2.17e-04  dt=  37.1ms  words=41,033,728
[E04   366/1548 G   5009|CLM] train=3.7907  mask=16.0%  norm=0.645  lr=2.17e-04  dt=  37.4ms  words=41,041,920
[E04   367/1548 G   5010|CLM] train=4.4921  mask=16.0%  norm=0.846  lr=2.17e-04  dt=  37.7ms  words=41,050,112
[E04   368/1548 G   5011|CLM] train=2.4174  mask=16.0%  norm=0.606  lr=2.17e-04  dt=  37.4ms  words=41,058,304
[E04   369/1548 G   5012|CLM] train=4.8268  mask=16.0%  norm=1.109  lr=2.17e-04  dt=  38.0ms  words=41,066,496
[E04   370/1548 G   5013|CLM] train=4.4547  mask=16.0%  norm=0.742  lr=2.17e-04  dt=  37.8ms  words=41,074,688
[E04   371/1548 G   5014|CLM] train=4.1946  mask=16.0%  norm=0.648  lr=2.17e-04  dt=  37.8ms  words=41,082,880
[E04   372/1548 G   5015|CLM] train=2.1988  mask=16.0%  norm=0.824  lr=2.17e-04  dt=  37.1ms  words=41,091,072
[E04   373/1548 G   5016|CLM] train=3.9463  mask=15.9%  norm=0.973  lr=2.17e-04  dt=  37.4ms  words=41,099,264
[E04   374/1548 G   5017|CLM] train=4.2057  mask=15.9%  norm=0.762  lr=2.17e-04  dt=  37.4ms  words=41,107,456
[E04   375/1548 G   5018|CLM] train=4.5465  mask=15.9%  norm=0.801  lr=2.16e-04  dt=  37.1ms  words=41,115,648
[E04   376/1548 G   5019|CLM] train=4.2156  mask=15.9%  norm=0.629  lr=2.16e-04  dt=  37.3ms  words=41,123,840
[E04   377/1548 G   5020|CLM] train=4.3467  mask=15.9%  norm=0.628  lr=2.16e-04  dt=  37.1ms  words=41,132,032
[E04   378/1548 G   5021|CLM] train=2.6171  mask=15.9%  norm=0.703  lr=2.16e-04  dt=  38.0ms  words=41,140,224
[E04   379/1548 G   5022|CLM] train=2.6108  mask=15.9%  norm=0.635  lr=2.16e-04  dt=  37.3ms  words=41,148,416
[E04   380/1548 G   5023|CLM] train=3.1690  mask=15.9%  norm=0.803  lr=2.16e-04  dt=  37.4ms  words=41,156,608
[E04   381/1548 G   5024|CLM] train=4.5574  mask=15.9%  norm=0.796  lr=2.16e-04  dt=  37.8ms  words=41,164,800
[E04   382/1548 G   5025|CLM] train=4.8998  mask=15.9%  norm=0.932  lr=2.16e-04  dt=  38.2ms  words=41,172,992
[E04   383/1548 G   5026|CLM] train=4.6529  mask=15.9%  norm=0.750  lr=2.16e-04  dt=  42.8ms  words=41,181,184
[E04   384/1548 G   5027|CLM] train=2.5316  mask=15.9%  norm=0.650  lr=2.16e-04  dt=  41.5ms  words=41,189,376
[E04   385/1548 G   5028|CLM] train=2.2245  mask=15.9%  norm=0.554  lr=2.16e-04  dt=  37.4ms  words=41,197,568
[E04   386/1548 G   5029|CLM] train=2.4389  mask=15.9%  norm=0.759  lr=2.16e-04  dt=  38.6ms  words=41,205,760
[E04   387/1548 G   5030|CLM] train=4.0355  mask=15.9%  norm=0.641  lr=2.16e-04  dt=  43.4ms  words=41,213,952
[E04   388/1548 G   5031|CLM] train=2.1760  mask=15.9%  norm=0.846  lr=2.16e-04  dt=  39.7ms  words=41,222,144
[E04   389/1548 G   5032|CLM] train=3.6680  mask=15.9%  norm=0.745  lr=2.16e-04  dt=  38.5ms  words=41,230,336
[E04   390/1548 G   5033|CLM] train=2.6196  mask=15.9%  norm=0.627  lr=2.16e-04  dt=  38.3ms  words=41,238,528
[E04   391/1548 G   5034|CLM] train=4.3999  mask=15.9%  norm=0.656  lr=2.16e-04  dt=  37.3ms  words=41,246,720
[E04   392/1548 G   5035|CLM] train=3.8052  mask=15.9%  norm=0.689  lr=2.16e-04  dt=  37.4ms  words=41,254,912
[E04   393/1548 G   5036|CLM] train=2.3578  mask=15.9%  norm=0.723  lr=2.16e-04  dt=  37.2ms  words=41,263,104
[E04   394/1548 G   5037|CLM] train=5.7689  mask=15.9%  norm=2.283  lr=2.16e-04  dt=  37.0ms  words=41,271,296
[E04   395/1548 G   5038|CLM] train=5.9351  mask=15.9%  norm=1.444  lr=2.16e-04  dt=  37.0ms  words=41,279,488
[E04   396/1548 G   5039|CLM] train=4.1754  mask=15.9%  norm=0.817  lr=2.16e-04  dt=  36.8ms  words=41,287,680
[E04   397/1548 G   5040|CLM] train=4.4993  mask=15.9%  norm=0.865  lr=2.16e-04  dt=  37.4ms  words=41,295,872
[E04   398/1548 G   5041|CLM] train=3.7124  mask=15.9%  norm=0.715  lr=2.16e-04  dt=  37.0ms  words=41,304,064
[E04   399/1548 G   5042|CLM] train=4.3935  mask=15.9%  norm=0.798  lr=2.16e-04  dt=  37.0ms  words=41,312,256
[E04   400/1548 G   5043|CLM] train=4.2013  mask=15.9%  norm=0.744  lr=2.16e-04  dt=  37.2ms  words=41,320,448
[E04   401/1548 G   5044|CLM] train=4.2798  mask=15.9%  norm=0.821  lr=2.16e-04  dt=  37.2ms  words=41,328,640
[E04   402/1548 G   5045|CLM] train=4.4222  mask=15.9%  norm=0.672  lr=2.16e-04  dt=  36.8ms  words=41,336,832
[E04   403/1548 G   5046|CLM] train=4.2868  mask=15.9%  norm=0.659  lr=2.16e-04  dt=  37.3ms  words=41,345,024
[E04   404/1548 G   5047|CLM] train=4.2539  mask=15.9%  norm=1.155  lr=2.15e-04  dt=  37.6ms  words=41,353,216
[E04   405/1548 G   5048|CLM] train=2.6667  mask=15.9%  norm=0.711  lr=2.15e-04  dt=  36.9ms  words=41,361,408
[E04   406/1548 G   5049|CLM] train=4.0335  mask=15.9%  norm=0.870  lr=2.15e-04  dt=  37.0ms  words=41,369,600
[E04   407/1548 G   5050|CLM] train=3.7348  mask=15.9%  norm=0.693  lr=2.15e-04  dt=  37.3ms  words=41,377,792
[E04   408/1548 G   5051|CLM] train=4.2518  mask=15.9%  norm=0.970  lr=2.15e-04  dt=  37.2ms  words=41,385,984
[E04   409/1548 G   5052|CLM] train=2.4214  mask=15.9%  norm=0.648  lr=2.15e-04  dt=  36.8ms  words=41,394,176
[E04   410/1548 G   5053|CLM] train=4.4301  mask=15.9%  norm=0.790  lr=2.15e-04  dt=  37.1ms  words=41,402,368
[E04   411/1548 G   5054|CLM] train=4.3553  mask=15.9%  norm=0.943  lr=2.15e-04  dt=  37.0ms  words=41,410,560
[E04   412/1548 G   5055|CLM] train=4.2305  mask=15.9%  norm=0.810  lr=2.15e-04  dt=  36.9ms  words=41,418,752
[E04   413/1548 G   5056|CLM] train=4.8954  mask=15.9%  norm=0.884  lr=2.15e-04  dt=  37.1ms  words=41,426,944
[E04   414/1548 G   5057|CLM] train=4.1192  mask=15.9%  norm=0.679  lr=2.15e-04  dt=  37.0ms  words=41,435,136
[E04   415/1548 G   5058|CLM] train=4.2530  mask=15.9%  norm=0.761  lr=2.15e-04  dt=  37.1ms  words=41,443,328
[E04   416/1548 G   5059|CLM] train=1.6712  mask=15.9%  norm=0.841  lr=2.15e-04  dt=  37.0ms  words=41,451,520
[E04   417/1548 G   5060|CLM] train=5.5339  mask=15.9%  norm=1.223  lr=2.15e-04  dt=  37.1ms  words=41,459,712
[E04   418/1548 G   5061|CLM] train=2.7761  mask=15.9%  norm=0.667  lr=2.15e-04  dt=  37.1ms  words=41,467,904
[E04   419/1548 G   5062|CLM] train=2.2244  mask=15.9%  norm=0.738  lr=2.15e-04  dt=  37.0ms  words=41,476,096
[E04   420/1548 G   5063|CLM] train=4.0990  mask=15.9%  norm=0.613  lr=2.15e-04  dt=  37.1ms  words=41,484,288
[E04   421/1548 G   5064|CLM] train=4.5311  mask=15.9%  norm=0.681  lr=2.15e-04  dt=  37.0ms  words=41,492,480
[E04   422/1548 G   5065|CLM] train=2.3280  mask=15.9%  norm=0.857  lr=2.15e-04  dt=  37.1ms  words=41,500,672
[E04   423/1548 G   5066|CLM] train=2.8309  mask=15.9%  norm=0.646  lr=2.15e-04  dt=  37.1ms  words=41,508,864
[E04   424/1548 G   5067|CLM] train=4.2738  mask=15.9%  norm=0.765  lr=2.15e-04  dt=  37.3ms  words=41,517,056
[E04   425/1548 G   5068|CLM] train=2.5137  mask=15.9%  norm=0.744  lr=2.15e-04  dt=  37.2ms  words=41,525,248
[E04   426/1548 G   5069|CLM] train=2.4230  mask=15.9%  norm=0.830  lr=2.15e-04  dt=  36.9ms  words=41,533,440
[E04   427/1548 G   5070|CLM] train=4.0950  mask=15.9%  norm=0.795  lr=2.15e-04  dt=  37.3ms  words=41,541,632
[E04   428/1548 G   5071|CLM] train=4.0263  mask=15.9%  norm=1.026  lr=2.15e-04  dt=  37.1ms  words=41,549,824
[E04   429/1548 G   5072|CLM] train=2.3717  mask=15.9%  norm=0.739  lr=2.15e-04  dt=  37.1ms  words=41,558,016
[E04   430/1548 G   5073|CLM] train=3.6136  mask=15.9%  norm=0.642  lr=2.15e-04  dt=  36.9ms  words=41,566,208
[E04   431/1548 G   5074|CLM] train=4.2143  mask=15.9%  norm=0.718  lr=2.15e-04  dt=  37.3ms  words=41,574,400
[E04   432/1548 G   5075|CLM] train=2.6712  mask=15.9%  norm=1.066  lr=2.14e-04  dt=  37.0ms  words=41,582,592
[E04   433/1548 G   5076|CLM] train=2.6751  mask=15.9%  norm=0.649  lr=2.14e-04  dt=  37.2ms  words=41,590,784
[E04   434/1548 G   5077|CLM] train=2.7154  mask=15.9%  norm=0.767  lr=2.14e-04  dt=  37.2ms  words=41,598,976
[E04   435/1548 G   5078|CLM] train=2.4652  mask=15.9%  norm=0.841  lr=2.14e-04  dt=  36.9ms  words=41,607,168
[E04   436/1548 G   5079|CLM] train=4.9494  mask=15.9%  norm=1.007  lr=2.14e-04  dt=  36.9ms  words=41,615,360
[E04   437/1548 G   5080|CLM] train=2.5485  mask=15.9%  norm=0.680  lr=2.14e-04  dt=  37.0ms  words=41,623,552
[E04   438/1548 G   5081|CLM] train=4.9008  mask=15.9%  norm=1.216  lr=2.14e-04  dt=  37.2ms  words=41,631,744
[E04   439/1548 G   5082|CLM] train=2.2629  mask=15.9%  norm=0.647  lr=2.14e-04  dt=  37.2ms  words=41,639,936
[E04   440/1548 G   5083|CLM] train=4.6199  mask=15.9%  norm=0.867  lr=2.14e-04  dt=  37.0ms  words=41,648,128
[E04   441/1548 G   5084|CLM] train=2.9131  mask=15.9%  norm=0.649  lr=2.14e-04  dt=  37.2ms  words=41,656,320
[E04   442/1548 G   5085|CLM] train=5.0140  mask=15.9%  norm=0.945  lr=2.14e-04  dt=  37.1ms  words=41,664,512
[E04   443/1548 G   5086|CLM] train=4.8615  mask=15.9%  norm=0.870  lr=2.14e-04  dt=  36.9ms  words=41,672,704
[E04   444/1548 G   5087|CLM] train=4.5676  mask=15.9%  norm=1.407  lr=2.14e-04  dt=  37.4ms  words=41,680,896
[E04   445/1548 G   5088|CLM] train=3.9746  mask=15.9%  norm=0.739  lr=2.14e-04  dt=  37.2ms  words=41,689,088
[E04   446/1548 G   5089|CLM] train=4.6031  mask=15.9%  norm=1.051  lr=2.14e-04  dt=  37.1ms  words=41,697,280
[E04   447/1548 G   5090|CLM] train=4.0497  mask=15.9%  norm=0.899  lr=2.14e-04  dt=  37.1ms  words=41,705,472
[E04   448/1548 G   5091|CLM] train=4.8333  mask=15.9%  norm=1.197  lr=2.14e-04  dt=  36.9ms  words=41,713,664
[E04   449/1548 G   5092|CLM] train=5.7396  mask=15.9%  norm=1.161  lr=2.14e-04  dt=  37.0ms  words=41,721,856
[E04   450/1548 G   5093|CLM] train=4.2080  mask=15.9%  norm=0.728  lr=2.14e-04  dt=  37.0ms  words=41,730,048
[E04   451/1548 G   5094|CLM] train=4.1784  mask=15.9%  norm=0.775  lr=2.14e-04  dt=  37.3ms  words=41,738,240
[E04   452/1548 G   5095|CLM] train=4.7815  mask=15.9%  norm=0.886  lr=2.14e-04  dt=  37.0ms  words=41,746,432
[E04   453/1548 G   5096|CLM] train=2.8889  mask=15.9%  norm=0.995  lr=2.14e-04  dt=  37.2ms  words=41,754,624
[E04   454/1548 G   5097|CLM] train=3.9054  mask=15.9%  norm=0.805  lr=2.14e-04  dt=  36.9ms  words=41,762,816
[E04   455/1548 G   5098|CLM] train=4.6398  mask=15.9%  norm=0.850  lr=2.14e-04  dt=  37.1ms  words=41,771,008
[E04   456/1548 G   5099|CLM] train=2.6452  mask=15.9%  norm=0.695  lr=2.14e-04  dt=  37.0ms  words=41,779,200
[E04   457/1548 G   5100|CLM] train=2.3630  mask=15.9%  norm=0.722  lr=2.14e-04  dt=  37.2ms  words=41,787,392
[E04   458/1548 G   5101|CLM] train=4.2462  mask=15.9%  norm=0.888  lr=2.14e-04  dt=  37.0ms  words=41,795,584
[E04   459/1548 G   5102|CLM] train=2.8409  mask=15.9%  norm=0.739  lr=2.14e-04  dt=  37.4ms  words=41,803,776
[E04   460/1548 G   5103|CLM] train=2.6618  mask=15.9%  norm=0.618  lr=2.13e-04  dt=  36.9ms  words=41,811,968
[E04   461/1548 G   5104|CLM] train=2.4269  mask=15.9%  norm=0.641  lr=2.13e-04  dt=  37.0ms  words=41,820,160
[E04   462/1548 G   5105|CLM] train=5.3560  mask=15.9%  norm=3.446  lr=2.13e-04  dt=  37.0ms  words=41,828,352
[E04   463/1548 G   5106|CLM] train=4.9699  mask=15.9%  norm=1.401  lr=2.13e-04  dt=  37.0ms  words=41,836,544
[E04   464/1548 G   5107|CLM] train=2.4897  mask=15.9%  norm=0.698  lr=2.13e-04  dt=  36.9ms  words=41,844,736
[E04   465/1548 G   5108|CLM] train=4.0386  mask=15.9%  norm=1.042  lr=2.13e-04  dt=  37.0ms  words=41,852,928
[E04   466/1548 G   5109|CLM] train=4.7529  mask=15.9%  norm=0.833  lr=2.13e-04  dt=  37.2ms  words=41,861,120
[E04   467/1548 G   5110|CLM] train=4.8532  mask=15.9%  norm=0.999  lr=2.13e-04  dt=  37.1ms  words=41,869,312
[E04   468/1548 G   5111|CLM] train=2.4558  mask=15.9%  norm=0.662  lr=2.13e-04  dt=  37.0ms  words=41,877,504
[E04   469/1548 G   5112|CLM] train=5.0351  mask=15.9%  norm=0.755  lr=2.13e-04  dt=  37.2ms  words=41,885,696
[E04   470/1548 G   5113|CLM] train=4.0455  mask=15.9%  norm=0.792  lr=2.13e-04  dt=  37.0ms  words=41,893,888
[E04   471/1548 G   5114|CLM] train=4.3043  mask=15.9%  norm=0.778  lr=2.13e-04  dt=  37.3ms  words=41,902,080
[E04   472/1548 G   5115|CLM] train=2.4660  mask=15.9%  norm=0.621  lr=2.13e-04  dt=  37.3ms  words=41,910,272
[E04   473/1548 G   5116|CLM] train=2.3728  mask=15.9%  norm=0.633  lr=2.13e-04  dt=  37.1ms  words=41,918,464
[E04   474/1548 G   5117|CLM] train=2.7446  mask=15.9%  norm=0.648  lr=2.13e-04  dt=  37.3ms  words=41,926,656
[E04   475/1548 G   5118|CLM] train=4.4138  mask=15.9%  norm=0.811  lr=2.13e-04  dt=  37.1ms  words=41,934,848
[E04   476/1548 G   5119|CLM] train=5.0451  mask=15.9%  norm=0.777  lr=2.13e-04  dt=  46.5ms  words=41,943,040
[E04   477/1548 G   5120|CLM] train=3.9685  mask=15.9%  norm=0.887  lr=2.13e-04  dt=  37.0ms  words=41,951,232
[E04   478/1548 G   5121|CLM] train=4.2852  mask=15.9%  norm=0.845  lr=2.13e-04  dt=  38.1ms  words=41,959,424
[E04   479/1548 G   5122|CLM] train=2.9595  mask=15.9%  norm=0.649  lr=2.13e-04  dt=  37.7ms  words=41,967,616
[E04   480/1548 G   5123|CLM] train=2.4747  mask=15.9%  norm=0.678  lr=2.13e-04  dt=  37.9ms  words=41,975,808
[E04   481/1548 G   5124|CLM] train=2.5333  mask=15.9%  norm=0.657  lr=2.13e-04  dt=  38.8ms  words=41,984,000
[E04   482/1548 G   5125|CLM] train=4.0693  mask=15.9%  norm=0.706  lr=2.13e-04  dt=  38.7ms  words=41,992,192
[E04   483/1548 G   5126|CLM] train=2.3771  mask=15.9%  norm=0.934  lr=2.13e-04  dt=  37.6ms  words=42,000,384
[E04   484/1548 G   5127|CLM] train=2.5058  mask=15.9%  norm=0.795  lr=2.13e-04  dt=  37.0ms  words=42,008,576
[E04   485/1548 G   5128|CLM] train=2.8532  mask=15.9%  norm=0.625  lr=2.13e-04  dt=  37.4ms  words=42,016,768
[E04   486/1548 G   5129|CLM] train=4.2456  mask=15.9%  norm=0.872  lr=2.13e-04  dt=  36.9ms  words=42,024,960
[E04   487/1548 G   5130|CLM] train=2.8295  mask=15.9%  norm=0.603  lr=2.13e-04  dt=  38.6ms  words=42,033,152
[E04   488/1548 G   5131|CLM] train=4.4434  mask=15.9%  norm=0.833  lr=2.12e-04  dt=  47.3ms  words=42,041,344
[E04   489/1548 G   5132|CLM] train=3.8980  mask=15.9%  norm=0.819  lr=2.12e-04  dt=  37.1ms  words=42,049,536
[E04   490/1548 G   5133|CLM] train=5.2648  mask=15.9%  norm=1.232  lr=2.12e-04  dt=  37.4ms  words=42,057,728
[E04   491/1548 G   5134|CLM] train=4.4418  mask=15.9%  norm=0.739  lr=2.12e-04  dt=  41.3ms  words=42,065,920
[E04   492/1548 G   5135|CLM] train=2.3908  mask=15.9%  norm=0.849  lr=2.12e-04  dt=  46.8ms  words=42,074,112
[E04   493/1548 G   5136|CLM] train=5.0046  mask=15.9%  norm=1.040  lr=2.12e-04  dt=  36.9ms  words=42,082,304
[E04   494/1548 G   5137|CLM] train=4.4347  mask=15.9%  norm=0.806  lr=2.12e-04  dt=  37.1ms  words=42,090,496
[E04   495/1548 G   5138|CLM] train=4.4497  mask=15.9%  norm=0.794  lr=2.12e-04  dt=  37.0ms  words=42,098,688
[E04   496/1548 G   5139|CLM] train=2.5198  mask=15.9%  norm=1.187  lr=2.12e-04  dt=  36.9ms  words=42,106,880
[E04   497/1548 G   5140|CLM] train=2.6453  mask=15.8%  norm=0.717  lr=2.12e-04  dt=  36.7ms  words=42,115,072
[E04   498/1548 G   5141|CLM] train=2.2917  mask=15.8%  norm=1.022  lr=2.12e-04  dt=  37.2ms  words=42,123,264
[E04   499/1548 G   5142|CLM] train=4.3194  mask=15.8%  norm=0.907  lr=2.12e-04  dt=  37.0ms  words=42,131,456
[E04   500/1548 G   5143|CLM] train=3.9703  mask=15.8%  norm=0.964  lr=2.12e-04  dt=  36.9ms  words=42,139,648
[E04   501/1548 G   5144|CLM] train=2.3781  mask=15.8%  norm=1.144  lr=2.12e-04  dt=  36.8ms  words=42,147,840
[E04   502/1548 G   5145|CLM] train=2.6154  mask=15.8%  norm=0.731  lr=2.12e-04  dt=  37.1ms  words=42,156,032
[E04   503/1548 G   5146|CLM] train=4.7054  mask=15.8%  norm=1.262  lr=2.12e-04  dt=  37.1ms  words=42,164,224
[E04   504/1548 G   5147|CLM] train=2.6311  mask=15.8%  norm=0.700  lr=2.12e-04  dt=  37.0ms  words=42,172,416
[E04   505/1548 G   5148|CLM] train=2.5755  mask=15.8%  norm=0.866  lr=2.12e-04  dt=  36.8ms  words=42,180,608
[E04   506/1548 G   5149|CLM] train=2.3280  mask=15.8%  norm=1.039  lr=2.12e-04  dt=  36.9ms  words=42,188,800
[E04   507/1548 G   5150|CLM] train=2.6149  mask=15.8%  norm=0.754  lr=2.12e-04  dt=  37.1ms  words=42,196,992
[E04   508/1548 G   5151|CLM] train=2.2757  mask=15.8%  norm=0.650  lr=2.12e-04  dt=  36.8ms  words=42,205,184
[E04   509/1548 G   5152|CLM] train=2.4563  mask=15.8%  norm=0.858  lr=2.12e-04  dt=  37.0ms  words=42,213,376
[E04   510/1548 G   5153|CLM] train=5.0911  mask=15.8%  norm=1.013  lr=2.12e-04  dt=  36.9ms  words=42,221,568
[E04   511/1548 G   5154|CLM] train=2.3379  mask=15.8%  norm=0.712  lr=2.12e-04  dt=  37.2ms  words=42,229,760
[E04   512/1548 G   5155|CLM] train=2.2988  mask=15.8%  norm=0.967  lr=2.12e-04  dt=  36.8ms  words=42,237,952
[E04   513/1548 G   5156|CLM] train=4.4008  mask=15.8%  norm=0.839  lr=2.12e-04  dt=  37.1ms  words=42,246,144
[E04   514/1548 G   5157|CLM] train=4.2310  mask=15.8%  norm=1.662  lr=2.12e-04  dt=  37.6ms  words=42,254,336
[E04   515/1548 G   5158|CLM] train=2.3546  mask=15.8%  norm=1.116  lr=2.12e-04  dt=  36.8ms  words=42,262,528
[E04   516/1548 G   5159|CLM] train=4.2072  mask=15.8%  norm=0.830  lr=2.11e-04  dt=  36.7ms  words=42,270,720
[E04   517/1548 G   5160|CLM] train=3.8496  mask=15.8%  norm=0.734  lr=2.11e-04  dt=  37.1ms  words=42,278,912
[E04   518/1548 G   5161|CLM] train=2.3301  mask=15.8%  norm=0.652  lr=2.11e-04  dt=  37.1ms  words=42,287,104
[E04   519/1548 G   5162|CLM] train=4.6783  mask=15.8%  norm=0.911  lr=2.11e-04  dt=  36.8ms  words=42,295,296
[E04   520/1548 G   5163|CLM] train=4.0433  mask=15.8%  norm=0.957  lr=2.11e-04  dt=  36.9ms  words=42,303,488
[E04   521/1548 G   5164|CLM] train=4.1088  mask=15.8%  norm=0.695  lr=2.11e-04  dt=  36.8ms  words=42,311,680
[E04   522/1548 G   5165|CLM] train=4.7052  mask=15.8%  norm=0.781  lr=2.11e-04  dt=  37.1ms  words=42,319,872
[E04   523/1548 G   5166|CLM] train=4.0791  mask=15.8%  norm=0.688  lr=2.11e-04  dt=  36.7ms  words=42,328,064
[E04   524/1548 G   5167|CLM] train=4.5810  mask=15.8%  norm=0.773  lr=2.11e-04  dt=  36.9ms  words=42,336,256
[E04   525/1548 G   5168|CLM] train=4.1058  mask=15.8%  norm=0.804  lr=2.11e-04  dt=  36.9ms  words=42,344,448
[E04   526/1548 G   5169|CLM] train=4.8436  mask=15.8%  norm=0.833  lr=2.11e-04  dt=  37.0ms  words=42,352,640
[E04   527/1548 G   5170|CLM] train=1.6809  mask=15.8%  norm=0.612  lr=2.11e-04  dt=  36.8ms  words=42,360,832
[E04   528/1548 G   5171|CLM] train=2.8744  mask=15.8%  norm=0.696  lr=2.11e-04  dt=  37.1ms  words=42,369,024
[E04   529/1548 G   5172|CLM] train=4.3025  mask=15.8%  norm=0.884  lr=2.11e-04  dt=  37.0ms  words=42,377,216
[E04   530/1548 G   5173|CLM] train=4.7217  mask=15.8%  norm=0.854  lr=2.11e-04  dt=  36.9ms  words=42,385,408
[E04   531/1548 G   5174|CLM] train=3.9800  mask=15.8%  norm=0.745  lr=2.11e-04  dt=  37.0ms  words=42,393,600
[E04   532/1548 G   5175|CLM] train=4.6777  mask=15.8%  norm=0.727  lr=2.11e-04  dt=  37.1ms  words=42,401,792
[E04   533/1548 G   5176|CLM] train=4.6288  mask=15.8%  norm=0.788  lr=2.11e-04  dt=  37.5ms  words=42,409,984
[E04   534/1548 G   5177|CLM] train=4.7578  mask=15.8%  norm=0.734  lr=2.11e-04  dt=  36.9ms  words=42,418,176
[E04   535/1548 G   5178|CLM] train=1.9966  mask=15.8%  norm=0.776  lr=2.11e-04  dt=  36.8ms  words=42,426,368
[E04   536/1548 G   5179|CLM] train=4.8164  mask=15.8%  norm=0.757  lr=2.11e-04  dt=  37.0ms  words=42,434,560
[E04   537/1548 G   5180|CLM] train=3.8668  mask=15.8%  norm=0.955  lr=2.11e-04  dt=  37.0ms  words=42,442,752
[E04   538/1548 G   5181|CLM] train=4.5175  mask=15.8%  norm=0.883  lr=2.11e-04  dt=  37.0ms  words=42,450,944
[E04   539/1548 G   5182|CLM] train=5.5060  mask=15.8%  norm=1.171  lr=2.11e-04  dt=  36.7ms  words=42,459,136
[E04   540/1548 G   5183|CLM] train=4.5574  mask=15.8%  norm=0.772  lr=2.11e-04  dt=  37.1ms  words=42,467,328
[E04   541/1548 G   5184|CLM] train=2.7672  mask=15.8%  norm=0.810  lr=2.11e-04  dt=  37.4ms  words=42,475,520
[E04   542/1548 G   5185|CLM] train=3.8784  mask=15.8%  norm=0.659  lr=2.11e-04  dt=  37.1ms  words=42,483,712
[E04   543/1548 G   5186|CLM] train=4.2747  mask=15.8%  norm=0.738  lr=2.11e-04  dt=  36.9ms  words=42,491,904
[E04   544/1548 G   5187|CLM] train=4.2862  mask=15.8%  norm=0.810  lr=2.10e-04  dt=  37.2ms  words=42,500,096
[E04   545/1548 G   5188|CLM] train=2.7752  mask=15.8%  norm=0.750  lr=2.10e-04  dt=  37.0ms  words=42,508,288
[E04   546/1548 G   5189|CLM] train=2.8526  mask=15.8%  norm=0.661  lr=2.10e-04  dt=  36.9ms  words=42,516,480
[E04   547/1548 G   5190|CLM] train=2.8305  mask=15.8%  norm=0.889  lr=2.10e-04  dt=  36.8ms  words=42,524,672
[E04   548/1548 G   5191|CLM] train=2.2593  mask=15.8%  norm=0.777  lr=2.10e-04  dt=  36.9ms  words=42,532,864
[E04   549/1548 G   5192|CLM] train=4.4738  mask=15.8%  norm=0.956  lr=2.10e-04  dt=  36.9ms  words=42,541,056
[E04   550/1548 G   5193|CLM] train=2.6348  mask=15.8%  norm=0.745  lr=2.10e-04  dt=  36.9ms  words=42,549,248
[E04   551/1548 G   5194|CLM] train=4.5602  mask=15.8%  norm=0.843  lr=2.10e-04  dt=  37.1ms  words=42,557,440
[E04   552/1548 G   5195|CLM] train=4.4575  mask=15.8%  norm=0.743  lr=2.10e-04  dt=  37.2ms  words=42,565,632
[E04   553/1548 G   5196|CLM] train=4.6294  mask=15.8%  norm=0.682  lr=2.10e-04  dt=  36.9ms  words=42,573,824
[E04   554/1548 G   5197|CLM] train=2.2811  mask=15.8%  norm=0.662  lr=2.10e-04  dt=  37.2ms  words=42,582,016
[E04   555/1548 G   5198|CLM] train=4.7450  mask=15.8%  norm=0.965  lr=2.10e-04  dt=  37.3ms  words=42,590,208
[E04   556/1548 G   5199|CLM] train=5.4632  mask=15.8%  norm=1.224  lr=2.10e-04  dt=  36.8ms  words=42,598,400
[E04   557/1548 G   5200|CLM] train=2.0877  mask=15.8%  norm=0.544  lr=2.10e-04  dt=  37.1ms  words=42,606,592
[E04   558/1548 G   5201|CLM] train=4.3675  mask=15.8%  norm=0.927  lr=2.10e-04  dt=  36.9ms  words=42,614,784
[E04   559/1548 G   5202|CLM] train=4.7560  mask=15.8%  norm=1.020  lr=2.10e-04  dt=  36.9ms  words=42,622,976
[E04   560/1548 G   5203|CLM] train=2.2141  mask=15.8%  norm=0.665  lr=2.10e-04  dt=  36.8ms  words=42,631,168
[E04   561/1548 G   5204|CLM] train=4.9685  mask=15.8%  norm=0.873  lr=2.10e-04  dt=  37.0ms  words=42,639,360
[E04   562/1548 G   5205|CLM] train=4.3174  mask=15.8%  norm=0.924  lr=2.10e-04  dt=  36.8ms  words=42,647,552
[E04   563/1548 G   5206|CLM] train=2.4124  mask=15.8%  norm=0.743  lr=2.10e-04  dt=  37.2ms  words=42,655,744
[E04   564/1548 G   5207|CLM] train=2.3408  mask=15.8%  norm=0.613  lr=2.10e-04  dt=  36.8ms  words=42,663,936
[E04   565/1548 G   5208|CLM] train=3.8052  mask=15.8%  norm=0.807  lr=2.10e-04  dt=  36.8ms  words=42,672,128
[E04   566/1548 G   5209|CLM] train=4.0803  mask=15.8%  norm=0.762  lr=2.10e-04  dt=  36.9ms  words=42,680,320
[E04   567/1548 G   5210|CLM] train=4.0632  mask=15.8%  norm=0.807  lr=2.10e-04  dt=  37.0ms  words=42,688,512
[E04   568/1548 G   5211|CLM] train=2.4375  mask=15.8%  norm=0.791  lr=2.10e-04  dt=  37.1ms  words=42,696,704
[E04   569/1548 G   5212|CLM] train=3.9036  mask=15.8%  norm=0.638  lr=2.10e-04  dt=  36.9ms  words=42,704,896
[E04   570/1548 G   5213|CLM] train=3.4945  mask=15.8%  norm=0.623  lr=2.10e-04  dt=  36.9ms  words=42,713,088
[E04   571/1548 G   5214|CLM] train=4.2120  mask=15.8%  norm=0.846  lr=2.10e-04  dt=  36.9ms  words=42,721,280
[E04   572/1548 G   5215|CLM] train=4.5797  mask=15.8%  norm=0.719  lr=2.09e-04  dt=  36.9ms  words=42,729,472
[E04   573/1548 G   5216|CLM] train=4.7322  mask=15.8%  norm=0.779  lr=2.09e-04  dt=  36.8ms  words=42,737,664
[E04   574/1548 G   5217|CLM] train=2.3212  mask=15.8%  norm=0.723  lr=2.09e-04  dt=  36.8ms  words=42,745,856
[E04   575/1548 G   5218|CLM] train=2.3106  mask=15.8%  norm=0.776  lr=2.09e-04  dt=  37.1ms  words=42,754,048
[E04   576/1548 G   5219|CLM] train=4.1861  mask=15.8%  norm=0.782  lr=2.09e-04  dt=  36.9ms  words=42,762,240
[E04   577/1548 G   5220|CLM] train=4.3630  mask=15.8%  norm=0.796  lr=2.09e-04  dt=  36.8ms  words=42,770,432
[E04   578/1548 G   5221|CLM] train=5.3693  mask=15.8%  norm=1.281  lr=2.09e-04  dt=  36.9ms  words=42,778,624
[E04   579/1548 G   5222|CLM] train=4.8607  mask=15.8%  norm=0.816  lr=2.09e-04  dt=  37.0ms  words=42,786,816
[E04   580/1548 G   5223|CLM] train=4.3895  mask=15.8%  norm=0.794  lr=2.09e-04  dt=  36.8ms  words=42,795,008
[E04   581/1548 G   5224|CLM] train=4.0516  mask=15.8%  norm=0.653  lr=2.09e-04  dt=  36.8ms  words=42,803,200
[E04   582/1548 G   5225|CLM] train=2.4660  mask=15.8%  norm=0.723  lr=2.09e-04  dt=  36.9ms  words=42,811,392
[E04   583/1548 G   5226|CLM] train=4.3632  mask=15.8%  norm=0.735  lr=2.09e-04  dt=  37.1ms  words=42,819,584
[E04   584/1548 G   5227|CLM] train=4.4627  mask=15.8%  norm=0.772  lr=2.09e-04  dt=  36.8ms  words=42,827,776
[E04   585/1548 G   5228|CLM] train=3.7158  mask=15.8%  norm=0.741  lr=2.09e-04  dt=  36.8ms  words=42,835,968
[E04   586/1548 G   5229|CLM] train=3.9930  mask=15.8%  norm=0.794  lr=2.09e-04  dt=  37.1ms  words=42,844,160
[E04   587/1548 G   5230|CLM] train=4.8746  mask=15.8%  norm=0.928  lr=2.09e-04  dt=  37.0ms  words=42,852,352
[E04   588/1548 G   5231|CLM] train=2.4916  mask=15.8%  norm=0.797  lr=2.09e-04  dt=  36.8ms  words=42,860,544
[E04   589/1548 G   5232|CLM] train=4.5042  mask=15.8%  norm=1.046  lr=2.09e-04  dt=  36.8ms  words=42,868,736
[E04   590/1548 G   5233|CLM] train=4.8422  mask=15.8%  norm=0.904  lr=2.09e-04  dt=  36.9ms  words=42,876,928
[E04   591/1548 G   5234|CLM] train=3.9106  mask=15.8%  norm=0.771  lr=2.09e-04  dt=  37.0ms  words=42,885,120
[E04   592/1548 G   5235|CLM] train=2.2848  mask=15.8%  norm=0.724  lr=2.09e-04  dt=  37.0ms  words=42,893,312
[E04   593/1548 G   5236|CLM] train=2.8612  mask=15.8%  norm=0.998  lr=2.09e-04  dt=  38.0ms  words=42,901,504
[E04   594/1548 G   5237|CLM] train=2.2916  mask=15.8%  norm=0.695  lr=2.09e-04  dt=  37.4ms  words=42,909,696
[E04   595/1548 G   5238|CLM] train=4.7509  mask=15.8%  norm=0.830  lr=2.09e-04  dt=  37.4ms  words=42,917,888
[E04   596/1548 G   5239|CLM] train=4.7128  mask=15.8%  norm=1.128  lr=2.09e-04  dt=  36.9ms  words=42,926,080
[E04   597/1548 G   5240|CLM] train=2.7429  mask=15.8%  norm=0.868  lr=2.09e-04  dt=  37.1ms  words=42,934,272
[E04   598/1548 G   5241|CLM] train=4.3743  mask=15.8%  norm=1.068  lr=2.09e-04  dt=  37.0ms  words=42,942,464
[E04   599/1548 G   5242|CLM] train=4.0433  mask=15.8%  norm=1.107  lr=2.09e-04  dt=  37.1ms  words=42,950,656
[E04   600/1548 G   5243|CLM] train=2.1914  mask=15.8%  norm=0.774  lr=2.08e-04  dt=  37.1ms  words=42,958,848
[E04   601/1548 G   5244|CLM] train=2.4355  mask=15.8%  norm=1.037  lr=2.08e-04  dt=  37.0ms  words=42,967,040
[E04   602/1548 G   5245|CLM] train=2.3427  mask=15.8%  norm=0.865  lr=2.08e-04  dt=  37.0ms  words=42,975,232
[E04   603/1548 G   5246|CLM] train=4.5418  mask=15.8%  norm=0.854  lr=2.08e-04  dt=  37.1ms  words=42,983,424
[E04   604/1548 G   5247|CLM] train=4.5089  mask=15.8%  norm=1.100  lr=2.08e-04  dt=  37.0ms  words=42,991,616
[E04   605/1548 G   5248|CLM] train=3.8016  mask=15.8%  norm=0.776  lr=2.08e-04  dt=  36.9ms  words=42,999,808
[E04   606/1548 G   5249|CLM] train=3.0214  mask=15.8%  norm=0.726  lr=2.08e-04  dt=  36.9ms  words=43,008,000
[E04   607/1548 G   5250|CLM] train=4.2280  mask=15.8%  norm=0.860  lr=2.08e-04  dt=  36.8ms  words=43,016,192
[E04   608/1548 G   5251|CLM] train=4.8374  mask=15.8%  norm=0.827  lr=2.08e-04  dt=  37.0ms  words=43,024,384
[E04   609/1548 G   5252|CLM] train=4.5370  mask=15.8%  norm=0.887  lr=2.08e-04  dt=  39.0ms  words=43,032,576
[E04   610/1548 G   5253|CLM] train=4.5996  mask=15.8%  norm=0.830  lr=2.08e-04  dt=  37.9ms  words=43,040,768
[E04   611/1548 G   5254|CLM] train=2.1202  mask=15.8%  norm=1.071  lr=2.08e-04  dt=  38.7ms  words=43,048,960
[E04   612/1548 G   5255|CLM] train=4.3584  mask=15.8%  norm=0.715  lr=2.08e-04  dt=  46.3ms  words=43,057,152
[E04   613/1548 G   5256|CLM] train=4.6201  mask=15.8%  norm=0.840  lr=2.08e-04  dt=  40.9ms  words=43,065,344
[E04   614/1548 G   5257|CLM] train=4.4109  mask=15.8%  norm=0.804  lr=2.08e-04  dt=  37.2ms  words=43,073,536
[E04   615/1548 G   5258|CLM] train=4.2191  mask=15.8%  norm=0.731  lr=2.08e-04  dt=  39.2ms  words=43,081,728
[E04   616/1548 G   5259|CLM] train=2.6674  mask=15.8%  norm=0.711  lr=2.08e-04  dt=  37.1ms  words=43,089,920
[E04   617/1548 G   5260|CLM] train=2.4853  mask=15.8%  norm=0.821  lr=2.08e-04  dt=  37.0ms  words=43,098,112
[E04   618/1548 G   5261|CLM] train=2.2598  mask=15.8%  norm=1.192  lr=2.08e-04  dt=  38.1ms  words=43,106,304
[E04   619/1548 G   5262|CLM] train=2.5143  mask=15.8%  norm=0.741  lr=2.08e-04  dt=  37.2ms  words=43,114,496
[E04   620/1548 G   5263|CLM] train=4.6715  mask=15.8%  norm=0.849  lr=2.08e-04  dt=  37.3ms  words=43,122,688
[E04   621/1548 G   5264|CLM] train=2.7667  mask=15.7%  norm=0.777  lr=2.08e-04  dt=  37.3ms  words=43,130,880
[E04   622/1548 G   5265|CLM] train=4.4344  mask=15.7%  norm=0.863  lr=2.08e-04  dt=  37.0ms  words=43,139,072
[E04   623/1548 G   5266|CLM] train=2.3132  mask=15.7%  norm=0.755  lr=2.08e-04  dt=  45.1ms  words=43,147,264
[E04   624/1548 G   5267|CLM] train=4.5908  mask=15.7%  norm=0.691  lr=2.08e-04  dt=  37.4ms  words=43,155,456
[E04   625/1548 G   5268|CLM] train=4.2321  mask=15.7%  norm=0.991  lr=2.08e-04  dt=  43.3ms  words=43,163,648
[E04   626/1548 G   5269|CLM] train=4.3672  mask=15.7%  norm=0.755  lr=2.08e-04  dt=  39.1ms  words=43,171,840
[E04   627/1548 G   5270|CLM] train=2.5018  mask=15.7%  norm=1.090  lr=2.08e-04  dt=  37.0ms  words=43,180,032
[E04   628/1548 G   5271|CLM] train=4.4508  mask=15.7%  norm=0.665  lr=2.07e-04  dt=  37.2ms  words=43,188,224
[E04   629/1548 G   5272|CLM] train=2.6849  mask=15.7%  norm=0.779  lr=2.07e-04  dt=  37.0ms  words=43,196,416
[E04   630/1548 G   5273|CLM] train=3.7801  mask=15.7%  norm=0.794  lr=2.07e-04  dt=  36.9ms  words=43,204,608
[E04   631/1548 G   5274|CLM] train=4.1574  mask=15.7%  norm=0.770  lr=2.07e-04  dt=  37.3ms  words=43,212,800
[E04   632/1548 G   5275|CLM] train=2.5164  mask=15.7%  norm=0.688  lr=2.07e-04  dt=  36.9ms  words=43,220,992
[E04   633/1548 G   5276|CLM] train=4.7675  mask=15.7%  norm=0.796  lr=2.07e-04  dt=  36.9ms  words=43,229,184
[E04   634/1548 G   5277|CLM] train=3.8480  mask=15.7%  norm=0.726  lr=2.07e-04  dt=  43.5ms  words=43,237,376
[E04   635/1548 G   5278|CLM] train=2.6397  mask=15.7%  norm=0.662  lr=2.07e-04  dt=  48.3ms  words=43,245,568
[E04   636/1548 G   5279|CLM] train=2.4164  mask=15.7%  norm=1.198  lr=2.07e-04  dt=  48.1ms  words=43,253,760
[E04   637/1548 G   5280|CLM] train=5.0721  mask=15.7%  norm=1.041  lr=2.07e-04  dt=  39.2ms  words=43,261,952
[E04   638/1548 G   5281|CLM] train=5.0857  mask=15.7%  norm=1.002  lr=2.07e-04  dt=  40.4ms  words=43,270,144
[E04   639/1548 G   5282|CLM] train=4.4187  mask=15.7%  norm=0.665  lr=2.07e-04  dt=  42.2ms  words=43,278,336
[E04   640/1548 G   5283|CLM] train=2.4841  mask=15.7%  norm=0.724  lr=2.07e-04  dt=  41.3ms  words=43,286,528
[E04   641/1548 G   5284|CLM] train=4.6830  mask=15.7%  norm=0.820  lr=2.07e-04  dt=  37.1ms  words=43,294,720
[E04   642/1548 G   5285|CLM] train=4.7230  mask=15.7%  norm=0.813  lr=2.07e-04  dt=  36.9ms  words=43,302,912
[E04   643/1548 G   5286|CLM] train=5.1769  mask=15.7%  norm=1.180  lr=2.07e-04  dt=  37.0ms  words=43,311,104
[E04   644/1548 G   5287|CLM] train=4.7720  mask=15.7%  norm=1.607  lr=2.07e-04  dt=  36.7ms  words=43,319,296
[E04   645/1548 G   5288|CLM] train=4.6023  mask=15.7%  norm=0.736  lr=2.07e-04  dt=  36.9ms  words=43,327,488
[E04   646/1548 G   5289|CLM] train=3.7698  mask=15.7%  norm=0.813  lr=2.07e-04  dt=  43.8ms  words=43,335,680
[E04   647/1548 G   5290|CLM] train=2.9114  mask=15.7%  norm=1.023  lr=2.07e-04  dt=  44.7ms  words=43,343,872
[E04   648/1548 G   5291|CLM] train=4.9477  mask=15.7%  norm=1.040  lr=2.07e-04  dt=  36.9ms  words=43,352,064
[E04   649/1548 G   5292|CLM] train=2.4930  mask=15.7%  norm=0.716  lr=2.07e-04  dt=  37.4ms  words=43,360,256
[E04   650/1548 G   5293|CLM] train=4.6480  mask=15.7%  norm=0.881  lr=2.07e-04  dt=  36.9ms  words=43,368,448
[E04   651/1548 G   5294|CLM] train=2.5710  mask=15.7%  norm=0.776  lr=2.07e-04  dt=  36.9ms  words=43,376,640
[E04   652/1548 G   5295|CLM] train=4.1957  mask=15.7%  norm=0.786  lr=2.07e-04  dt=  37.0ms  words=43,384,832
[E04   653/1548 G   5296|CLM] train=4.6139  mask=15.7%  norm=0.810  lr=2.07e-04  dt=  45.8ms  words=43,393,024
[E04   654/1548 G   5297|CLM] train=4.3350  mask=15.7%  norm=0.726  lr=2.07e-04  dt=  46.9ms  words=43,401,216
[E04   655/1548 G   5298|CLM] train=4.3610  mask=15.7%  norm=0.926  lr=2.06e-04  dt=  41.0ms  words=43,409,408
[E04   656/1548 G   5299|CLM] train=2.5234  mask=15.7%  norm=0.784  lr=2.06e-04  dt=  37.5ms  words=43,417,600
[E04   657/1548 G   5300|CLM] train=2.7223  mask=15.7%  norm=0.778  lr=2.06e-04  dt=  46.7ms  words=43,425,792
[E04   658/1548 G   5301|CLM] train=4.3514  mask=15.7%  norm=0.755  lr=2.06e-04  dt=  42.8ms  words=43,433,984
[E04   659/1548 G   5302|CLM] train=2.4708  mask=15.7%  norm=0.968  lr=2.06e-04  dt=  37.7ms  words=43,442,176
[E04   660/1548 G   5303|CLM] train=2.6004  mask=15.7%  norm=0.684  lr=2.06e-04  dt=  38.1ms  words=43,450,368
[E04   661/1548 G   5304|CLM] train=3.9815  mask=15.7%  norm=0.746  lr=2.06e-04  dt=  37.1ms  words=43,458,560
[E04   662/1548 G   5305|CLM] train=2.4549  mask=15.7%  norm=0.804  lr=2.06e-04  dt=  37.6ms  words=43,466,752
[E04   663/1548 G   5306|CLM] train=4.0299  mask=15.7%  norm=0.743  lr=2.06e-04  dt=  37.2ms  words=43,474,944
[E04   664/1548 G   5307|CLM] train=5.6431  mask=15.7%  norm=1.484  lr=2.06e-04  dt=  43.0ms  words=43,483,136
[E04   665/1548 G   5308|CLM] train=2.7047  mask=15.7%  norm=0.788  lr=2.06e-04  dt=  39.3ms  words=43,491,328
[E04   666/1548 G   5309|CLM] train=4.3511  mask=15.7%  norm=0.899  lr=2.06e-04  dt=  40.4ms  words=43,499,520
[E04   667/1548 G   5310|CLM] train=2.5407  mask=15.7%  norm=0.610  lr=2.06e-04  dt=  40.1ms  words=43,507,712
[E04   668/1548 G   5311|CLM] train=4.5621  mask=15.7%  norm=0.917  lr=2.06e-04  dt=  40.8ms  words=43,515,904
[E04   669/1548 G   5312|CLM] train=5.4808  mask=15.7%  norm=1.150  lr=2.06e-04  dt=  41.2ms  words=43,524,096
[E04   670/1548 G   5313|CLM] train=3.4353  mask=15.7%  norm=0.786  lr=2.06e-04  dt=  40.9ms  words=43,532,288
[E04   671/1548 G   5314|CLM] train=2.0607  mask=15.7%  norm=0.957  lr=2.06e-04  dt=  41.3ms  words=43,540,480
[E04   672/1548 G   5315|CLM] train=5.5302  mask=15.7%  norm=0.983  lr=2.06e-04  dt=  41.4ms  words=43,548,672
[E04   673/1548 G   5316|CLM] train=2.3723  mask=15.7%  norm=0.730  lr=2.06e-04  dt=  41.1ms  words=43,556,864
[E04   674/1548 G   5317|CLM] train=4.3104  mask=15.7%  norm=0.889  lr=2.06e-04  dt=  40.4ms  words=43,565,056
[E04   675/1548 G   5318|CLM] train=2.2398  mask=15.7%  norm=0.813  lr=2.06e-04  dt=  40.9ms  words=43,573,248
[E04   676/1548 G   5319|CLM] train=4.5472  mask=15.7%  norm=0.742  lr=2.06e-04  dt=  40.9ms  words=43,581,440
[E04   677/1548 G   5320|CLM] train=2.2601  mask=15.7%  norm=0.630  lr=2.06e-04  dt=  40.8ms  words=43,589,632
[E04   678/1548 G   5321|CLM] train=2.4362  mask=15.7%  norm=0.698  lr=2.06e-04  dt=  41.2ms  words=43,597,824
[E04   679/1548 G   5322|CLM] train=3.9975  mask=15.7%  norm=0.715  lr=2.06e-04  dt=  41.5ms  words=43,606,016
[E04   680/1548 G   5323|CLM] train=2.3113  mask=15.7%  norm=0.826  lr=2.06e-04  dt=  40.6ms  words=43,614,208
[E04   681/1548 G   5324|CLM] train=2.9089  mask=15.7%  norm=0.898  lr=2.06e-04  dt=  41.3ms  words=43,622,400
[E04   682/1548 G   5325|CLM] train=2.6831  mask=15.7%  norm=0.705  lr=2.06e-04  dt=  41.3ms  words=43,630,592
[E04   683/1548 G   5326|CLM] train=2.6410  mask=15.7%  norm=0.872  lr=2.05e-04  dt=  42.1ms  words=43,638,784
[E04   684/1548 G   5327|CLM] train=4.2236  mask=15.7%  norm=0.656  lr=2.05e-04  dt=  41.8ms  words=43,646,976
[E04   685/1548 G   5328|CLM] train=2.6168  mask=15.7%  norm=0.788  lr=2.05e-04  dt=  41.9ms  words=43,655,168
[E04   686/1548 G   5329|CLM] train=4.6948  mask=15.7%  norm=1.017  lr=2.05e-04  dt=  41.4ms  words=43,663,360
[E04   687/1548 G   5330|CLM] train=4.4876  mask=15.7%  norm=0.886  lr=2.05e-04  dt=  41.5ms  words=43,671,552
[E04   688/1548 G   5331|CLM] train=4.2662  mask=15.7%  norm=0.724  lr=2.05e-04  dt=  41.5ms  words=43,679,744
[E04   689/1548 G   5332|CLM] train=4.0166  mask=15.7%  norm=0.753  lr=2.05e-04  dt=  41.9ms  words=43,687,936
[E04   690/1548 G   5333|CLM] train=2.4940  mask=15.7%  norm=1.061  lr=2.05e-04  dt=  40.9ms  words=43,696,128
[E04   691/1548 G   5334|CLM] train=2.4304  mask=15.7%  norm=0.967  lr=2.05e-04  dt=  41.8ms  words=43,704,320
[E04   692/1548 G   5335|CLM] train=2.2408  mask=15.7%  norm=0.747  lr=2.05e-04  dt=  41.7ms  words=43,712,512
[E04   693/1548 G   5336|CLM] train=4.2682  mask=15.7%  norm=0.955  lr=2.05e-04  dt=  38.0ms  words=43,720,704
[E04   694/1548 G   5337|CLM] train=2.3309  mask=15.7%  norm=0.726  lr=2.05e-04  dt=  40.6ms  words=43,728,896
[E04   695/1548 G   5338|CLM] train=2.5377  mask=15.7%  norm=0.663  lr=2.05e-04  dt=  40.9ms  words=43,737,088
[E04   696/1548 G   5339|CLM] train=2.5603  mask=15.7%  norm=1.050  lr=2.05e-04  dt=  40.8ms  words=43,745,280
[E04   697/1548 G   5340|CLM] train=1.9350  mask=15.7%  norm=0.708  lr=2.05e-04  dt=  41.2ms  words=43,753,472
[E04   698/1548 G   5341|CLM] train=2.7333  mask=15.7%  norm=0.875  lr=2.05e-04  dt=  41.2ms  words=43,761,664
[E04   699/1548 G   5342|CLM] train=2.6272  mask=15.7%  norm=0.894  lr=2.05e-04  dt=  41.0ms  words=43,769,856
[E04   700/1548 G   5343|CLM] train=2.7021  mask=15.7%  norm=0.852  lr=2.05e-04  dt=  40.7ms  words=43,778,048
[E04   701/1548 G   5344|CLM] train=4.7392  mask=15.7%  norm=0.894  lr=2.05e-04  dt=  40.8ms  words=43,786,240
[E04   702/1548 G   5345|CLM] train=4.0335  mask=15.7%  norm=0.786  lr=2.05e-04  dt=  40.7ms  words=43,794,432
[E04   703/1548 G   5346|CLM] train=2.2734  mask=15.7%  norm=0.738  lr=2.05e-04  dt=  40.6ms  words=43,802,624
[E04   704/1548 G   5347|CLM] train=2.3220  mask=15.7%  norm=0.673  lr=2.05e-04  dt=  40.5ms  words=43,810,816
[E04   705/1548 G   5348|CLM] train=2.5161  mask=15.7%  norm=0.777  lr=2.05e-04  dt=  40.6ms  words=43,819,008
[E04   706/1548 G   5349|CLM] train=2.3722  mask=15.7%  norm=0.750  lr=2.05e-04  dt=  36.9ms  words=43,827,200
[E04   707/1548 G   5350|CLM] train=2.4917  mask=15.7%  norm=0.719  lr=2.05e-04  dt=  37.2ms  words=43,835,392
[E04   708/1548 G   5351|CLM] train=4.5220  mask=15.7%  norm=0.814  lr=2.05e-04  dt=  37.0ms  words=43,843,584
[E04   709/1548 G   5352|CLM] train=3.9898  mask=15.7%  norm=0.815  lr=2.05e-04  dt=  36.8ms  words=43,851,776
[E04   710/1548 G   5353|CLM] train=2.3154  mask=15.7%  norm=0.617  lr=2.04e-04  dt=  36.9ms  words=43,859,968
[E04   711/1548 G   5354|CLM] train=2.5094  mask=15.7%  norm=0.685  lr=2.04e-04  dt=  37.0ms  words=43,868,160
[E04   712/1548 G   5355|CLM] train=4.5786  mask=15.7%  norm=0.870  lr=2.04e-04  dt=  37.0ms  words=43,876,352
[E04   713/1548 G   5356|CLM] train=4.4319  mask=15.7%  norm=0.801  lr=2.04e-04  dt=  37.0ms  words=43,884,544
[E04   714/1548 G   5357|CLM] train=4.5433  mask=15.7%  norm=0.716  lr=2.04e-04  dt=  37.3ms  words=43,892,736
[E04   715/1548 G   5358|CLM] train=4.0587  mask=15.7%  norm=0.744  lr=2.04e-04  dt=  37.0ms  words=43,900,928
[E04   716/1548 G   5359|CLM] train=2.3204  mask=15.7%  norm=0.811  lr=2.04e-04  dt=  36.9ms  words=43,909,120
[E04   717/1548 G   5360|CLM] train=2.6807  mask=15.7%  norm=0.664  lr=2.04e-04  dt=  36.8ms  words=43,917,312
[E04   718/1548 G   5361|CLM] train=2.6055  mask=15.7%  norm=0.638  lr=2.04e-04  dt=  36.9ms  words=43,925,504
[E04   719/1548 G   5362|CLM] train=4.3927  mask=15.7%  norm=0.799  lr=2.04e-04  dt=  37.1ms  words=43,933,696
[E04   720/1548 G   5363|CLM] train=3.9748  mask=15.7%  norm=0.765  lr=2.04e-04  dt=  36.9ms  words=43,941,888
[E04   721/1548 G   5364|CLM] train=2.5503  mask=15.7%  norm=0.625  lr=2.04e-04  dt=  36.9ms  words=43,950,080
[E04   722/1548 G   5365|CLM] train=3.5559  mask=15.7%  norm=0.734  lr=2.04e-04  dt=  36.9ms  words=43,958,272
[E04   723/1548 G   5366|CLM] train=2.4447  mask=15.7%  norm=0.721  lr=2.04e-04  dt=  36.9ms  words=43,966,464
[E04   724/1548 G   5367|CLM] train=4.7888  mask=15.7%  norm=0.821  lr=2.04e-04  dt=  36.8ms  words=43,974,656
[E04   725/1548 G   5368|CLM] train=2.7770  mask=15.7%  norm=0.895  lr=2.04e-04  dt=  36.8ms  words=43,982,848
[E04   726/1548 G   5369|CLM] train=2.4206  mask=15.7%  norm=0.757  lr=2.04e-04  dt=  36.9ms  words=43,991,040
[E04   727/1548 G   5370|CLM] train=5.5110  mask=15.7%  norm=1.630  lr=2.04e-04  dt=  37.1ms  words=43,999,232
[E04   728/1548 G   5371|CLM] train=4.4790  mask=15.7%  norm=0.865  lr=2.04e-04  dt=  36.9ms  words=44,007,424
[E04   729/1548 G   5372|CLM] train=4.0063  mask=15.7%  norm=0.818  lr=2.04e-04  dt=  36.8ms  words=44,015,616
[E04   730/1548 G   5373|CLM] train=3.8146  mask=15.7%  norm=0.741  lr=2.04e-04  dt=  36.9ms  words=44,023,808
[E04   731/1548 G   5374|CLM] train=4.6022  mask=15.7%  norm=0.837  lr=2.04e-04  dt=  37.0ms  words=44,032,000
[E04   732/1548 G   5375|CLM] train=5.0695  mask=15.7%  norm=1.060  lr=2.04e-04  dt=  37.0ms  words=44,040,192
[E04   733/1548 G   5376|CLM] train=4.8366  mask=15.7%  norm=0.944  lr=2.04e-04  dt=  36.9ms  words=44,048,384
[E04   734/1548 G   5377|CLM] train=2.1871  mask=15.7%  norm=0.843  lr=2.04e-04  dt=  37.4ms  words=44,056,576
[E04   735/1548 G   5378|CLM] train=3.6529  mask=15.7%  norm=0.811  lr=2.04e-04  dt=  37.0ms  words=44,064,768
[E04   736/1548 G   5379|CLM] train=2.6830  mask=15.7%  norm=0.855  lr=2.04e-04  dt=  47.3ms  words=44,072,960
[E04   737/1548 G   5380|CLM] train=5.2146  mask=15.7%  norm=0.858  lr=2.04e-04  dt=  37.9ms  words=44,081,152
[E04   738/1548 G   5381|CLM] train=4.8181  mask=15.7%  norm=1.068  lr=2.03e-04  dt=  45.5ms  words=44,089,344
[E04   739/1548 G   5382|CLM] train=4.8701  mask=15.7%  norm=0.877  lr=2.03e-04  dt=  38.0ms  words=44,097,536
[E04   740/1548 G   5383|CLM] train=2.3378  mask=15.7%  norm=0.754  lr=2.03e-04  dt=  46.4ms  words=44,105,728
[E04   741/1548 G   5384|CLM] train=2.4279  mask=15.7%  norm=0.738  lr=2.03e-04  dt=  43.1ms  words=44,113,920
[E04   742/1548 G   5385|CLM] train=4.4744  mask=15.7%  norm=0.873  lr=2.03e-04  dt=  37.0ms  words=44,122,112
[E04   743/1548 G   5386|CLM] train=4.3500  mask=15.7%  norm=0.749  lr=2.03e-04  dt=  37.0ms  words=44,130,304
[E04   744/1548 G   5387|CLM] train=4.3407  mask=15.7%  norm=0.794  lr=2.03e-04  dt=  36.9ms  words=44,138,496
[E04   745/1548 G   5388|CLM] train=4.2314  mask=15.6%  norm=0.770  lr=2.03e-04  dt=  37.6ms  words=44,146,688
[E04   746/1548 G   5389|CLM] train=4.3778  mask=15.6%  norm=0.782  lr=2.03e-04  dt=  36.9ms  words=44,154,880
[E04   747/1548 G   5390|CLM] train=4.3933  mask=15.6%  norm=0.915  lr=2.03e-04  dt=  40.6ms  words=44,163,072
[E04   748/1548 G   5391|CLM] train=2.4454  mask=15.6%  norm=1.084  lr=2.03e-04  dt=  43.0ms  words=44,171,264
[E04   749/1548 G   5392|CLM] train=5.0214  mask=15.6%  norm=0.866  lr=2.03e-04  dt=  37.0ms  words=44,179,456
[E04   750/1548 G   5393|CLM] train=2.4020  mask=15.6%  norm=0.832  lr=2.03e-04  dt=  37.0ms  words=44,187,648
[E04   751/1548 G   5394|CLM] train=2.1252  mask=15.6%  norm=0.767  lr=2.03e-04  dt=  37.1ms  words=44,195,840
[E04   752/1548 G   5395|CLM] train=2.2888  mask=15.6%  norm=0.733  lr=2.03e-04  dt=  37.0ms  words=44,204,032
[E04   753/1548 G   5396|CLM] train=4.5898  mask=15.6%  norm=0.872  lr=2.03e-04  dt=  42.4ms  words=44,212,224
[E04   754/1548 G   5397|CLM] train=2.2259  mask=15.6%  norm=0.871  lr=2.03e-04  dt=  38.5ms  words=44,220,416
[E04   755/1548 G   5398|CLM] train=2.4045  mask=15.6%  norm=0.749  lr=2.03e-04  dt=  36.9ms  words=44,228,608
[E04   756/1548 G   5399|CLM] train=4.6610  mask=15.6%  norm=0.993  lr=2.03e-04  dt=  37.0ms  words=44,236,800
[E04   757/1548 G   5400|CLM] train=4.8019  mask=15.6%  norm=1.037  lr=2.03e-04  dt=  37.0ms  words=44,244,992
[E04   758/1548 G   5401|CLM] train=2.9511  mask=15.6%  norm=0.890  lr=2.03e-04  dt=  42.2ms  words=44,253,184
[E04   759/1548 G   5402|CLM] train=4.2859  mask=15.6%  norm=0.888  lr=2.03e-04  dt=  36.9ms  words=44,261,376
[E04   760/1548 G   5403|CLM] train=2.2388  mask=15.6%  norm=0.716  lr=2.03e-04  dt=  37.0ms  words=44,269,568
[E04   761/1548 G   5404|CLM] train=2.3137  mask=15.6%  norm=0.814  lr=2.03e-04  dt=  37.1ms  words=44,277,760
[E04   762/1548 G   5405|CLM] train=2.3768  mask=15.6%  norm=1.068  lr=2.03e-04  dt=  37.0ms  words=44,285,952
[E04   763/1548 G   5406|CLM] train=2.3732  mask=15.6%  norm=0.730  lr=2.03e-04  dt=  37.1ms  words=44,294,144
[E04   764/1548 G   5407|CLM] train=4.3211  mask=15.6%  norm=0.854  lr=2.03e-04  dt=  37.2ms  words=44,302,336
[E04   765/1548 G   5408|CLM] train=2.2652  mask=15.6%  norm=0.613  lr=2.02e-04  dt=  37.1ms  words=44,310,528
[E04   766/1548 G   5409|CLM] train=2.7032  mask=15.6%  norm=0.864  lr=2.02e-04  dt=  37.0ms  words=44,318,720
[E04   767/1548 G   5410|CLM] train=4.6918  mask=15.6%  norm=0.856  lr=2.02e-04  dt=  37.0ms  words=44,326,912
[E04   768/1548 G   5411|CLM] train=2.4306  mask=15.6%  norm=0.821  lr=2.02e-04  dt=  36.9ms  words=44,335,104
[E04   769/1548 G   5412|CLM] train=2.3972  mask=15.6%  norm=0.710  lr=2.02e-04  dt=  37.1ms  words=44,343,296
[E04   770/1548 G   5413|CLM] train=3.5906  mask=15.6%  norm=0.714  lr=2.02e-04  dt=  36.8ms  words=44,351,488
[E04   771/1548 G   5414|CLM] train=4.1143  mask=15.6%  norm=0.726  lr=2.02e-04  dt=  37.1ms  words=44,359,680
[E04   772/1548 G   5415|CLM] train=3.9659  mask=15.6%  norm=0.782  lr=2.02e-04  dt=  36.9ms  words=44,367,872
[E04   773/1548 G   5416|CLM] train=2.4252  mask=15.6%  norm=0.793  lr=2.02e-04  dt=  37.1ms  words=44,376,064
[E04   774/1548 G   5417|CLM] train=2.5028  mask=15.6%  norm=1.082  lr=2.02e-04  dt=  37.1ms  words=44,384,256
[E04   775/1548 G   5418|CLM] train=4.1509  mask=15.6%  norm=0.792  lr=2.02e-04  dt=  37.2ms  words=44,392,448
[E04   776/1548 G   5419|CLM] train=2.4335  mask=15.6%  norm=0.670  lr=2.02e-04  dt=  37.1ms  words=44,400,640
[E04   777/1548 G   5420|CLM] train=4.6714  mask=15.6%  norm=0.882  lr=2.02e-04  dt=  37.1ms  words=44,408,832
[E04   778/1548 G   5421|CLM] train=4.6400  mask=15.6%  norm=0.760  lr=2.02e-04  dt=  37.2ms  words=44,417,024
[E04   779/1548 G   5422|CLM] train=5.0203  mask=15.6%  norm=2.057  lr=2.02e-04  dt=  37.1ms  words=44,425,216
[E04   780/1548 G   5423|CLM] train=2.5378  mask=15.6%  norm=0.804  lr=2.02e-04  dt=  37.1ms  words=44,433,408
[E04   781/1548 G   5424|CLM] train=3.9244  mask=15.6%  norm=0.812  lr=2.02e-04  dt=  37.1ms  words=44,441,600
[E04   782/1548 G   5425|CLM] train=4.2455  mask=15.6%  norm=0.724  lr=2.02e-04  dt=  37.0ms  words=44,449,792
[E04   783/1548 G   5426|CLM] train=3.6605  mask=15.6%  norm=0.626  lr=2.02e-04  dt=  37.1ms  words=44,457,984
[E04   784/1548 G   5427|CLM] train=4.4839  mask=15.6%  norm=1.020  lr=2.02e-04  dt=  37.1ms  words=44,466,176
[E04   785/1548 G   5428|CLM] train=3.7443  mask=15.6%  norm=0.734  lr=2.02e-04  dt=  37.0ms  words=44,474,368
[E04   786/1548 G   5429|CLM] train=5.3292  mask=15.6%  norm=0.847  lr=2.02e-04  dt=  37.2ms  words=44,482,560
[E04   787/1548 G   5430|CLM] train=5.4525  mask=15.6%  norm=2.791  lr=2.02e-04  dt=  37.0ms  words=44,490,752
[E04   788/1548 G   5431|CLM] train=2.7738  mask=15.6%  norm=0.706  lr=2.02e-04  dt=  36.8ms  words=44,498,944
[E04   789/1548 G   5432|CLM] train=2.7632  mask=15.6%  norm=1.788  lr=2.02e-04  dt=  37.1ms  words=44,507,136
[E04   790/1548 G   5433|CLM] train=2.4428  mask=15.6%  norm=0.727  lr=2.02e-04  dt=  37.0ms  words=44,515,328
[E04   791/1548 G   5434|CLM] train=4.7458  mask=15.6%  norm=1.140  lr=2.02e-04  dt=  36.9ms  words=44,523,520
[E04   792/1548 G   5435|CLM] train=4.2385  mask=15.6%  norm=0.980  lr=2.01e-04  dt=  37.2ms  words=44,531,712
[E04   793/1548 G   5436|CLM] train=4.2863  mask=15.6%  norm=1.091  lr=2.01e-04  dt=  37.2ms  words=44,539,904
[E04   794/1548 G   5437|CLM] train=2.9472  mask=15.6%  norm=0.751  lr=2.01e-04  dt=  37.0ms  words=44,548,096
[E04   795/1548 G   5438|CLM] train=4.3032  mask=15.6%  norm=0.830  lr=2.01e-04  dt=  37.0ms  words=44,556,288
[E04   796/1548 G   5439|CLM] train=3.5066  mask=15.6%  norm=0.694  lr=2.01e-04  dt=  37.0ms  words=44,564,480
[E04   797/1548 G   5440|CLM] train=2.2932  mask=15.6%  norm=0.592  lr=2.01e-04  dt=  37.1ms  words=44,572,672
[E04   798/1548 G   5441|CLM] train=4.0718  mask=15.6%  norm=0.779  lr=2.01e-04  dt=  36.9ms  words=44,580,864
[E04   799/1548 G   5442|CLM] train=4.7379  mask=15.6%  norm=1.091  lr=2.01e-04  dt=  38.0ms  words=44,589,056
[E04   800/1548 G   5443|CLM] train=3.8638  mask=15.6%  norm=0.926  lr=2.01e-04  dt=  37.1ms  words=44,597,248
[E04   801/1548 G   5444|CLM] train=4.1397  mask=15.6%  norm=0.915  lr=2.01e-04  dt=  37.2ms  words=44,605,440
[E04   802/1548 G   5445|CLM] train=4.3575  mask=15.6%  norm=0.759  lr=2.01e-04  dt=  37.1ms  words=44,613,632
[E04   803/1548 G   5446|CLM] train=5.3719  mask=15.6%  norm=0.898  lr=2.01e-04  dt=  37.2ms  words=44,621,824
[E04   804/1548 G   5447|CLM] train=2.2861  mask=15.6%  norm=0.856  lr=2.01e-04  dt=  37.0ms  words=44,630,016
[E04   805/1548 G   5448|CLM] train=4.3807  mask=15.6%  norm=0.864  lr=2.01e-04  dt=  37.2ms  words=44,638,208
[E04   806/1548 G   5449|CLM] train=3.9877  mask=15.6%  norm=0.874  lr=2.01e-04  dt=  37.0ms  words=44,646,400
[E04   807/1548 G   5450|CLM] train=2.4052  mask=15.6%  norm=0.917  lr=2.01e-04  dt=  37.0ms  words=44,654,592
[E04   808/1548 G   5451|CLM] train=4.8926  mask=15.6%  norm=1.066  lr=2.01e-04  dt=  36.9ms  words=44,662,784
[E04   809/1548 G   5452|CLM] train=2.3578  mask=15.6%  norm=0.820  lr=2.01e-04  dt=  37.0ms  words=44,670,976
[E04   810/1548 G   5453|CLM] train=2.7916  mask=15.6%  norm=0.814  lr=2.01e-04  dt=  37.1ms  words=44,679,168
[E04   811/1548 G   5454|CLM] train=4.7477  mask=15.6%  norm=0.878  lr=2.01e-04  dt=  36.9ms  words=44,687,360
[E04   812/1548 G   5455|CLM] train=2.2839  mask=15.6%  norm=0.666  lr=2.01e-04  dt=  37.0ms  words=44,695,552
[E04   813/1548 G   5456|CLM] train=4.3116  mask=15.6%  norm=1.356  lr=2.01e-04  dt=  37.1ms  words=44,703,744
[E04   814/1548 G   5457|CLM] train=4.5133  mask=15.6%  norm=0.791  lr=2.01e-04  dt=  36.8ms  words=44,711,936
[E04   815/1548 G   5458|CLM] train=4.8169  mask=15.6%  norm=0.930  lr=2.01e-04  dt=  38.3ms  words=44,720,128
[E04   816/1548 G   5459|CLM] train=2.8340  mask=15.6%  norm=0.695  lr=2.01e-04  dt=  37.0ms  words=44,728,320
[E04   817/1548 G   5460|CLM] train=2.4091  mask=15.6%  norm=0.674  lr=2.01e-04  dt=  36.9ms  words=44,736,512
[E04   818/1548 G   5461|CLM] train=5.4700  mask=15.6%  norm=1.528  lr=2.01e-04  dt=  36.7ms  words=44,744,704
[E04   819/1548 G   5462|CLM] train=2.5866  mask=15.6%  norm=0.578  lr=2.00e-04  dt=  37.1ms  words=44,752,896
[E04   820/1548 G   5463|CLM] train=1.8394  mask=15.6%  norm=0.845  lr=2.00e-04  dt=  37.2ms  words=44,761,088
[E04   821/1548 G   5464|CLM] train=4.5147  mask=15.6%  norm=0.826  lr=2.00e-04  dt=  36.9ms  words=44,769,280
[E04   822/1548 G   5465|CLM] train=3.9393  mask=15.6%  norm=1.250  lr=2.00e-04  dt=  36.8ms  words=44,777,472
[E04   823/1548 G   5466|CLM] train=4.3612  mask=15.6%  norm=0.969  lr=2.00e-04  dt=  37.0ms  words=44,785,664
[E04   824/1548 G   5467|CLM] train=5.0980  mask=15.6%  norm=0.870  lr=2.00e-04  dt=  37.0ms  words=44,793,856
[E04   825/1548 G   5468|CLM] train=2.2608  mask=15.6%  norm=0.763  lr=2.00e-04  dt=  36.8ms  words=44,802,048
[E04   826/1548 G   5469|CLM] train=3.9824  mask=15.6%  norm=0.724  lr=2.00e-04  dt=  36.9ms  words=44,810,240
[E04   827/1548 G   5470|CLM] train=4.6259  mask=15.6%  norm=0.818  lr=2.00e-04  dt=  36.9ms  words=44,818,432
[E04   828/1548 G   5471|CLM] train=4.4487  mask=15.6%  norm=1.072  lr=2.00e-04  dt=  37.4ms  words=44,826,624
[E04   829/1548 G   5472|CLM] train=2.6335  mask=15.6%  norm=0.782  lr=2.00e-04  dt=  36.9ms  words=44,834,816
[E04   830/1548 G   5473|CLM] train=3.9196  mask=15.6%  norm=0.719  lr=2.00e-04  dt=  36.8ms  words=44,843,008
[E04   831/1548 G   5474|CLM] train=3.6213  mask=15.6%  norm=0.640  lr=2.00e-04  dt=  37.0ms  words=44,851,200
[E04   832/1548 G   5475|CLM] train=2.7388  mask=15.6%  norm=0.792  lr=2.00e-04  dt=  37.2ms  words=44,859,392
[E04   833/1548 G   5476|CLM] train=2.4948  mask=15.6%  norm=0.893  lr=2.00e-04  dt=  37.1ms  words=44,867,584
[E04   834/1548 G   5477|CLM] train=4.6990  mask=15.6%  norm=0.927  lr=2.00e-04  dt=  36.8ms  words=44,875,776
[E04   835/1548 G   5478|CLM] train=2.3988  mask=15.6%  norm=1.062  lr=2.00e-04  dt=  37.2ms  words=44,883,968
[E04   836/1548 G   5479|CLM] train=4.3725  mask=15.6%  norm=0.809  lr=2.00e-04  dt=  36.9ms  words=44,892,160
[E04   837/1548 G   5480|CLM] train=2.3750  mask=15.6%  norm=1.192  lr=2.00e-04  dt=  36.8ms  words=44,900,352
[E04   838/1548 G   5481|CLM] train=4.3800  mask=15.6%  norm=0.724  lr=2.00e-04  dt=  36.8ms  words=44,908,544
[E04   839/1548 G   5482|CLM] train=4.9292  mask=15.6%  norm=0.880  lr=2.00e-04  dt=  36.9ms  words=44,916,736
[E04   840/1548 G   5483|CLM] train=3.9958  mask=15.6%  norm=0.812  lr=2.00e-04  dt=  37.1ms  words=44,924,928
[E04   841/1548 G   5484|CLM] train=2.4345  mask=15.6%  norm=0.735  lr=2.00e-04  dt=  37.0ms  words=44,933,120
[E04   842/1548 G   5485|CLM] train=4.0349  mask=15.6%  norm=0.818  lr=2.00e-04  dt=  37.0ms  words=44,941,312
[E04   843/1548 G   5486|CLM] train=2.6236  mask=15.6%  norm=0.810  lr=2.00e-04  dt=  37.0ms  words=44,949,504
[E04   844/1548 G   5487|CLM] train=2.6339  mask=15.6%  norm=0.811  lr=2.00e-04  dt=  36.9ms  words=44,957,696
[E04   845/1548 G   5488|CLM] train=4.1675  mask=15.6%  norm=0.673  lr=2.00e-04  dt=  36.9ms  words=44,965,888
[E04   846/1548 G   5489|CLM] train=2.4164  mask=15.6%  norm=0.567  lr=1.99e-04  dt=  36.9ms  words=44,974,080
[E04   847/1548 G   5490|CLM] train=2.2358  mask=15.6%  norm=0.705  lr=1.99e-04  dt=  37.2ms  words=44,982,272
[E04   848/1548 G   5491|CLM] train=2.6116  mask=15.6%  norm=0.586  lr=1.99e-04  dt=  36.9ms  words=44,990,464
[E04   849/1548 G   5492|CLM] train=4.4882  mask=15.6%  norm=1.001  lr=1.99e-04  dt=  36.8ms  words=44,998,656
[E04   850/1548 G   5493|CLM] train=2.2940  mask=15.6%  norm=0.765  lr=1.99e-04  dt=  36.9ms  words=45,006,848
[E04   851/1548 G   5494|CLM] train=3.6663  mask=15.6%  norm=0.662  lr=1.99e-04  dt=  36.9ms  words=45,015,040
[E04   852/1548 G   5495|CLM] train=4.3135  mask=15.6%  norm=0.769  lr=1.99e-04  dt=  36.9ms  words=45,023,232
[E04   853/1548 G   5496|CLM] train=2.5489  mask=15.6%  norm=0.841  lr=1.99e-04  dt=  37.1ms  words=45,031,424
[E04   854/1548 G   5497|CLM] train=5.3302  mask=15.6%  norm=0.959  lr=1.99e-04  dt=  36.7ms  words=45,039,616
[E04   855/1548 G   5498|CLM] train=4.0411  mask=15.6%  norm=0.692  lr=1.99e-04  dt=  36.9ms  words=45,047,808
[E04   856/1548 G   5499|CLM] train=4.4813  mask=15.6%  norm=0.765  lr=1.99e-04  dt=  36.9ms  words=45,056,000
[E04   857/1548 G   5500|CLM] train=4.3671  mask=15.6%  norm=0.677  lr=1.99e-04  dt=  36.8ms  words=45,064,192
[E04   858/1548 G   5501|CLM] train=2.1195  mask=15.6%  norm=0.928  lr=1.99e-04  dt=  36.9ms  words=45,072,384
[E04   859/1548 G   5502|CLM] train=4.5947  mask=15.6%  norm=0.802  lr=1.99e-04  dt=  37.0ms  words=45,080,576
[E04   860/1548 G   5503|CLM] train=2.7878  mask=15.6%  norm=0.754  lr=1.99e-04  dt=  36.9ms  words=45,088,768
[E04   861/1548 G   5504|CLM] train=1.9681  mask=15.6%  norm=0.640  lr=1.99e-04  dt=  36.9ms  words=45,096,960
[E04   862/1548 G   5505|CLM] train=4.9325  mask=15.6%  norm=0.946  lr=1.99e-04  dt=  36.9ms  words=45,105,152
[E04   863/1548 G   5506|CLM] train=4.6275  mask=15.6%  norm=0.858  lr=1.99e-04  dt=  37.1ms  words=45,113,344
[E04   864/1548 G   5507|CLM] train=2.7530  mask=15.6%  norm=0.724  lr=1.99e-04  dt=  36.8ms  words=45,121,536
[E04   865/1548 G   5508|CLM] train=3.5589  mask=15.6%  norm=0.726  lr=1.99e-04  dt=  36.9ms  words=45,129,728
[E04   866/1548 G   5509|CLM] train=2.6872  mask=15.6%  norm=0.742  lr=1.99e-04  dt=  36.9ms  words=45,137,920
[E04   867/1548 G   5510|CLM] train=2.2239  mask=15.6%  norm=0.825  lr=1.99e-04  dt=  37.0ms  words=45,146,112
[E04   868/1548 G   5511|CLM] train=4.7760  mask=15.5%  norm=1.253  lr=1.99e-04  dt=  36.9ms  words=45,154,304
[E04   869/1548 G   5512|CLM] train=2.2840  mask=15.5%  norm=0.858  lr=1.99e-04  dt=  42.5ms  words=45,162,496
[E04   870/1548 G   5513|CLM] train=2.7897  mask=15.5%  norm=0.672  lr=1.99e-04  dt=  44.3ms  words=45,170,688
[E04   871/1548 G   5514|CLM] train=4.2391  mask=15.5%  norm=1.059  lr=1.99e-04  dt=  43.3ms  words=45,178,880
[E04   872/1548 G   5515|CLM] train=4.1626  mask=15.5%  norm=0.969  lr=1.99e-04  dt=  41.1ms  words=45,187,072
[E04   873/1548 G   5516|CLM] train=3.9130  mask=15.5%  norm=0.817  lr=1.98e-04  dt=  38.1ms  words=45,195,264
[E04   874/1548 G   5517|CLM] train=2.4926  mask=15.5%  norm=1.116  lr=1.98e-04  dt=  39.2ms  words=45,203,456
[E04   875/1548 G   5518|CLM] train=3.9952  mask=15.5%  norm=0.843  lr=1.98e-04  dt=  38.2ms  words=45,211,648
[E04   876/1548 G   5519|CLM] train=4.2116  mask=15.5%  norm=1.066  lr=1.98e-04  dt=  41.8ms  words=45,219,840
[E04   877/1548 G   5520|CLM] train=4.7227  mask=15.5%  norm=1.197  lr=1.98e-04  dt=  40.7ms  words=45,228,032
[E04   878/1548 G   5521|CLM] train=2.6307  mask=15.5%  norm=0.965  lr=1.98e-04  dt=  36.9ms  words=45,236,224
[E04   879/1548 G   5522|CLM] train=2.5192  mask=15.5%  norm=0.785  lr=1.98e-04  dt=  37.0ms  words=45,244,416
[E04   880/1548 G   5523|CLM] train=4.0876  mask=15.5%  norm=0.689  lr=1.98e-04  dt=  38.2ms  words=45,252,608
[E04   881/1548 G   5524|CLM] train=3.7999  mask=15.5%  norm=0.738  lr=1.98e-04  dt=  42.3ms  words=45,260,800
[E04   882/1548 G   5525|CLM] train=4.5698  mask=15.5%  norm=0.922  lr=1.98e-04  dt=  39.8ms  words=45,268,992
[E04   883/1548 G   5526|CLM] train=2.5774  mask=15.5%  norm=1.209  lr=1.98e-04  dt=  36.8ms  words=45,277,184
[E04   884/1548 G   5527|CLM] train=4.4388  mask=15.5%  norm=0.661  lr=1.98e-04  dt=  36.8ms  words=45,285,376
[E04   885/1548 G   5528|CLM] train=3.7314  mask=15.5%  norm=0.637  lr=1.98e-04  dt=  37.1ms  words=45,293,568
[E04   886/1548 G   5529|CLM] train=4.6802  mask=15.5%  norm=0.875  lr=1.98e-04  dt=  36.8ms  words=45,301,760
[E04   887/1548 G   5530|CLM] train=3.7039  mask=15.5%  norm=0.631  lr=1.98e-04  dt=  36.9ms  words=45,309,952
[E04   888/1548 G   5531|CLM] train=2.5503  mask=15.5%  norm=0.612  lr=1.98e-04  dt=  36.8ms  words=45,318,144
[E04   889/1548 G   5532|CLM] train=2.5717  mask=15.5%  norm=0.683  lr=1.98e-04  dt=  36.8ms  words=45,326,336
[E04   890/1548 G   5533|CLM] train=3.0779  mask=15.5%  norm=1.065  lr=1.98e-04  dt=  36.8ms  words=45,334,528
[E04   891/1548 G   5534|CLM] train=4.2114  mask=15.5%  norm=1.031  lr=1.98e-04  dt=  36.8ms  words=45,342,720
[E04   892/1548 G   5535|CLM] train=2.4019  mask=15.5%  norm=1.125  lr=1.98e-04  dt=  36.8ms  words=45,350,912
[E04   893/1548 G   5536|CLM] train=4.4728  mask=15.5%  norm=0.775  lr=1.98e-04  dt=  41.4ms  words=45,359,104
[E04   894/1548 G   5537|CLM] train=2.5090  mask=15.5%  norm=0.650  lr=1.98e-04  dt=  37.0ms  words=45,367,296
[E04   895/1548 G   5538|CLM] train=2.6208  mask=15.5%  norm=0.733  lr=1.98e-04  dt=  37.2ms  words=45,375,488
[E04   896/1548 G   5539|CLM] train=4.2600  mask=15.5%  norm=1.030  lr=1.98e-04  dt=  37.6ms  words=45,383,680
[E04   897/1548 G   5540|CLM] train=4.5873  mask=15.5%  norm=0.805  lr=1.98e-04  dt=  37.6ms  words=45,391,872
[E04   898/1548 G   5541|CLM] train=4.2434  mask=15.5%  norm=0.813  lr=1.98e-04  dt=  37.4ms  words=45,400,064
[E04   899/1548 G   5542|CLM] train=2.2604  mask=15.5%  norm=0.699  lr=1.98e-04  dt=  38.0ms  words=45,408,256
[E04   900/1548 G   5543|CLM] train=2.0510  mask=15.5%  norm=0.726  lr=1.97e-04  dt=  37.4ms  words=45,416,448
[E04   901/1548 G   5544|CLM] train=3.8180  mask=15.5%  norm=0.791  lr=1.97e-04  dt=  37.1ms  words=45,424,640
[E04   902/1548 G   5545|CLM] train=4.8299  mask=15.5%  norm=0.924  lr=1.97e-04  dt=  36.9ms  words=45,432,832
[E04   903/1548 G   5546|CLM] train=4.5033  mask=15.5%  norm=0.805  lr=1.97e-04  dt=  36.9ms  words=45,441,024
[E04   904/1548 G   5547|CLM] train=2.4637  mask=15.5%  norm=0.620  lr=1.97e-04  dt=  36.9ms  words=45,449,216
[E04   905/1548 G   5548|CLM] train=3.9000  mask=15.5%  norm=0.749  lr=1.97e-04  dt=  37.0ms  words=45,457,408
[E04   906/1548 G   5549|CLM] train=2.3600  mask=15.5%  norm=0.878  lr=1.97e-04  dt=  38.0ms  words=45,465,600
[E04   907/1548 G   5550|CLM] train=2.4131  mask=15.5%  norm=1.289  lr=1.97e-04  dt=  37.0ms  words=45,473,792
[E04   908/1548 G   5551|CLM] train=2.6601  mask=15.5%  norm=1.099  lr=1.97e-04  dt=  38.9ms  words=45,481,984
[E04   909/1548 G   5552|CLM] train=4.2172  mask=15.5%  norm=0.868  lr=1.97e-04  dt=  43.5ms  words=45,490,176
[E04   910/1548 G   5553|CLM] train=4.3690  mask=15.5%  norm=0.960  lr=1.97e-04  dt=  45.8ms  words=45,498,368
[E04   911/1548 G   5554|CLM] train=2.2107  mask=15.5%  norm=0.950  lr=1.97e-04  dt=  47.2ms  words=45,506,560
[E04   912/1548 G   5555|CLM] train=2.9349  mask=15.5%  norm=0.773  lr=1.97e-04  dt=  44.3ms  words=45,514,752
[E04   913/1548 G   5556|CLM] train=4.8004  mask=15.5%  norm=0.879  lr=1.97e-04  dt=  37.1ms  words=45,522,944
[E04   914/1548 G   5557|CLM] train=4.4516  mask=15.5%  norm=0.820  lr=1.97e-04  dt=  37.2ms  words=45,531,136
[E04   915/1548 G   5558|CLM] train=3.6518  mask=15.5%  norm=0.728  lr=1.97e-04  dt=  46.7ms  words=45,539,328
[E04   916/1548 G   5559|CLM] train=2.6344  mask=15.5%  norm=0.738  lr=1.97e-04  dt=  36.9ms  words=45,547,520
[E04   917/1548 G   5560|CLM] train=4.1579  mask=15.5%  norm=0.800  lr=1.97e-04  dt=  37.1ms  words=45,555,712
[E04   918/1548 G   5561|CLM] train=4.0773  mask=15.5%  norm=0.785  lr=1.97e-04  dt=  37.2ms  words=45,563,904
[E04   919/1548 G   5562|CLM] train=4.0084  mask=15.5%  norm=0.753  lr=1.97e-04  dt=  37.2ms  words=45,572,096
[E04   920/1548 G   5563|CLM] train=3.7383  mask=15.5%  norm=0.672  lr=1.97e-04  dt=  37.3ms  words=45,580,288
[E04   921/1548 G   5564|CLM] train=4.6311  mask=15.5%  norm=0.837  lr=1.97e-04  dt=  37.2ms  words=45,588,480
[E04   922/1548 G   5565|CLM] train=4.3087  mask=15.5%  norm=0.826  lr=1.97e-04  dt=  36.9ms  words=45,596,672
[E04   923/1548 G   5566|CLM] train=2.4286  mask=15.5%  norm=0.575  lr=1.97e-04  dt=  37.0ms  words=45,604,864
[E04   924/1548 G   5567|CLM] train=4.4915  mask=15.5%  norm=0.729  lr=1.97e-04  dt=  37.1ms  words=45,613,056
[E04   925/1548 G   5568|CLM] train=3.5833  mask=15.5%  norm=0.688  lr=1.97e-04  dt=  37.3ms  words=45,621,248
[E04   926/1548 G   5569|CLM] train=4.8462  mask=15.5%  norm=0.684  lr=1.97e-04  dt=  37.0ms  words=45,629,440
[E04   927/1548 G   5570|CLM] train=2.5151  mask=15.5%  norm=0.705  lr=1.96e-04  dt=  37.1ms  words=45,637,632
[E04   928/1548 G   5571|CLM] train=2.5221  mask=15.5%  norm=0.780  lr=1.96e-04  dt=  37.2ms  words=45,645,824
[E04   929/1548 G   5572|CLM] train=3.9355  mask=15.5%  norm=0.814  lr=1.96e-04  dt=  37.0ms  words=45,654,016
[E04   930/1548 G   5573|CLM] train=4.1283  mask=15.5%  norm=0.793  lr=1.96e-04  dt=  37.2ms  words=45,662,208
[E04   931/1548 G   5574|CLM] train=3.9111  mask=15.5%  norm=0.740  lr=1.96e-04  dt=  37.2ms  words=45,670,400
[E04   932/1548 G   5575|CLM] train=4.5304  mask=15.5%  norm=0.825  lr=1.96e-04  dt=  37.0ms  words=45,678,592
[E04   933/1548 G   5576|CLM] train=4.0239  mask=15.5%  norm=0.678  lr=1.96e-04  dt=  37.4ms  words=45,686,784
[E04   934/1548 G   5577|CLM] train=4.1628  mask=15.5%  norm=0.644  lr=1.96e-04  dt=  37.3ms  words=45,694,976
[E04   935/1548 G   5578|CLM] train=3.9308  mask=15.5%  norm=0.793  lr=1.96e-04  dt=  37.0ms  words=45,703,168
[E04   936/1548 G   5579|CLM] train=4.3579  mask=15.5%  norm=0.831  lr=1.96e-04  dt=  37.1ms  words=45,711,360
[E04   937/1548 G   5580|CLM] train=4.1370  mask=15.5%  norm=1.430  lr=1.96e-04  dt=  37.0ms  words=45,719,552
[E04   938/1548 G   5581|CLM] train=4.2298  mask=15.5%  norm=0.667  lr=1.96e-04  dt=  37.2ms  words=45,727,744
[E04   939/1548 G   5582|CLM] train=4.5984  mask=15.5%  norm=0.763  lr=1.96e-04  dt=  37.0ms  words=45,735,936
[E04   940/1548 G   5583|CLM] train=4.3787  mask=15.5%  norm=0.935  lr=1.96e-04  dt=  37.1ms  words=45,744,128
[E04   941/1548 G   5584|CLM] train=3.0483  mask=15.5%  norm=1.046  lr=1.96e-04  dt=  37.2ms  words=45,752,320
[E04   942/1548 G   5585|CLM] train=4.6396  mask=15.5%  norm=0.838  lr=1.96e-04  dt=  37.0ms  words=45,760,512
[E04   943/1548 G   5586|CLM] train=2.9048  mask=15.5%  norm=0.951  lr=1.96e-04  dt=  37.1ms  words=45,768,704
[E04   944/1548 G   5587|CLM] train=4.1044  mask=15.5%  norm=0.701  lr=1.96e-04  dt=  37.2ms  words=45,776,896
[E04   945/1548 G   5588|CLM] train=4.9633  mask=15.5%  norm=1.156  lr=1.96e-04  dt=  37.1ms  words=45,785,088
[E04   946/1548 G   5589|CLM] train=4.5901  mask=15.5%  norm=0.785  lr=1.96e-04  dt=  37.1ms  words=45,793,280
[E04   947/1548 G   5590|CLM] train=2.6270  mask=15.5%  norm=0.786  lr=1.96e-04  dt=  37.3ms  words=45,801,472
[E04   948/1548 G   5591|CLM] train=4.0432  mask=15.5%  norm=0.693  lr=1.96e-04  dt=  37.1ms  words=45,809,664
[E04   949/1548 G   5592|CLM] train=4.4425  mask=15.5%  norm=0.877  lr=1.96e-04  dt=  37.3ms  words=45,817,856
[E04   950/1548 G   5593|CLM] train=4.2385  mask=15.5%  norm=0.739  lr=1.96e-04  dt=  37.0ms  words=45,826,048
[E04   951/1548 G   5594|CLM] train=2.0147  mask=15.5%  norm=0.594  lr=1.96e-04  dt=  37.0ms  words=45,834,240
[E04   952/1548 G   5595|CLM] train=4.1468  mask=15.5%  norm=1.106  lr=1.96e-04  dt=  37.2ms  words=45,842,432
[E04   953/1548 G   5596|CLM] train=3.9723  mask=15.5%  norm=0.841  lr=1.96e-04  dt=  37.3ms  words=45,850,624
[E04   954/1548 G   5597|CLM] train=4.2434  mask=15.5%  norm=0.721  lr=1.95e-04  dt=  37.1ms  words=45,858,816
[E04   955/1548 G   5598|CLM] train=4.2292  mask=15.5%  norm=0.721  lr=1.95e-04  dt=  36.9ms  words=45,867,008
[E04   956/1548 G   5599|CLM] train=2.7075  mask=15.5%  norm=1.142  lr=1.95e-04  dt=  36.9ms  words=45,875,200
[E04   957/1548 G   5600|CLM] train=4.0632  mask=15.5%  norm=1.323  lr=1.95e-04  dt=  37.1ms  words=45,883,392
[E04   958/1548 G   5601|CLM] train=5.3856  mask=15.5%  norm=1.166  lr=1.95e-04  dt=  37.2ms  words=45,891,584
[E04   959/1548 G   5602|CLM] train=4.2613  mask=15.5%  norm=0.802  lr=1.95e-04  dt=  37.3ms  words=45,899,776
[E04   960/1548 G   5603|CLM] train=4.2226  mask=15.5%  norm=0.806  lr=1.95e-04  dt=  39.2ms  words=45,907,968
[E04   961/1548 G   5604|CLM] train=1.8909  mask=15.5%  norm=1.043  lr=1.95e-04  dt=  37.2ms  words=45,916,160
[E04   962/1548 G   5605|CLM] train=2.9273  mask=15.5%  norm=1.348  lr=1.95e-04  dt=  37.3ms  words=45,924,352
[E04   963/1548 G   5606|CLM] train=2.4589  mask=15.5%  norm=0.767  lr=1.95e-04  dt=  37.2ms  words=45,932,544
[E04   964/1548 G   5607|CLM] train=5.7687  mask=15.5%  norm=1.283  lr=1.95e-04  dt=  37.0ms  words=45,940,736
[E04   965/1548 G   5608|CLM] train=4.0711  mask=15.5%  norm=0.687  lr=1.95e-04  dt=  37.0ms  words=45,948,928
[E04   966/1548 G   5609|CLM] train=5.1048  mask=15.5%  norm=1.281  lr=1.95e-04  dt=  37.2ms  words=45,957,120
[E04   967/1548 G   5610|CLM] train=4.0752  mask=15.5%  norm=0.782  lr=1.95e-04  dt=  37.0ms  words=45,965,312
[E04   968/1548 G   5611|CLM] train=4.6515  mask=15.5%  norm=0.771  lr=1.95e-04  dt=  37.1ms  words=45,973,504
[E04   969/1548 G   5612|CLM] train=4.0564  mask=15.5%  norm=0.675  lr=1.95e-04  dt=  37.2ms  words=45,981,696
[E04   970/1548 G   5613|CLM] train=4.4615  mask=15.5%  norm=0.926  lr=1.95e-04  dt=  37.0ms  words=45,989,888
[E04   971/1548 G   5614|CLM] train=2.6983  mask=15.5%  norm=1.455  lr=1.95e-04  dt=  36.9ms  words=45,998,080
[E04   972/1548 G   5615|CLM] train=5.1178  mask=15.5%  norm=0.956  lr=1.95e-04  dt=  37.2ms  words=46,006,272
[E04   973/1548 G   5616|CLM] train=2.3110  mask=15.5%  norm=0.786  lr=1.95e-04  dt=  37.1ms  words=46,014,464
[E04   974/1548 G   5617|CLM] train=4.3438  mask=15.5%  norm=0.827  lr=1.95e-04  dt=  37.1ms  words=46,022,656
[E04   975/1548 G   5618|CLM] train=4.2830  mask=15.5%  norm=0.817  lr=1.95e-04  dt=  37.1ms  words=46,030,848
[E04   976/1548 G   5619|CLM] train=4.1746  mask=15.5%  norm=0.863  lr=1.95e-04  dt=  37.3ms  words=46,039,040
[E04   977/1548 G   5620|CLM] train=4.6691  mask=15.5%  norm=0.944  lr=1.95e-04  dt=  37.1ms  words=46,047,232
[E04   978/1548 G   5621|CLM] train=4.4424  mask=15.5%  norm=0.763  lr=1.95e-04  dt=  37.1ms  words=46,055,424
[E04   979/1548 G   5622|CLM] train=4.2174  mask=15.5%  norm=0.716  lr=1.95e-04  dt=  37.2ms  words=46,063,616
[E04   980/1548 G   5623|CLM] train=4.4010  mask=15.5%  norm=0.830  lr=1.95e-04  dt=  37.0ms  words=46,071,808
[E04   981/1548 G   5624|CLM] train=3.9444  mask=15.5%  norm=0.784  lr=1.94e-04  dt=  36.9ms  words=46,080,000
[E04   982/1548 G   5625|CLM] train=5.4093  mask=15.5%  norm=1.351  lr=1.94e-04  dt=  37.0ms  words=46,088,192
[E04   983/1548 G   5626|CLM] train=5.4041  mask=15.5%  norm=1.641  lr=1.94e-04  dt=  37.2ms  words=46,096,384
[E04   984/1548 G   5627|CLM] train=4.6879  mask=15.5%  norm=1.039  lr=1.94e-04  dt=  37.1ms  words=46,104,576
[E04   985/1548 G   5628|CLM] train=4.3699  mask=15.5%  norm=0.799  lr=1.94e-04  dt=  37.4ms  words=46,112,768
[E04   986/1548 G   5629|CLM] train=3.9875  mask=15.5%  norm=0.729  lr=1.94e-04  dt=  37.2ms  words=46,120,960
[E04   987/1548 G   5630|CLM] train=2.4653  mask=15.5%  norm=0.830  lr=1.94e-04  dt=  37.2ms  words=46,129,152
[E04   988/1548 G   5631|CLM] train=4.9537  mask=15.5%  norm=1.629  lr=1.94e-04  dt=  37.1ms  words=46,137,344
[E04   989/1548 G   5632|CLM] train=3.9083  mask=15.5%  norm=0.638  lr=1.94e-04  dt=  37.2ms  words=46,145,536
[E04   990/1548 G   5633|CLM] train=3.5350  mask=15.5%  norm=3.474  lr=1.94e-04  dt=  36.9ms  words=46,153,728
[E04   991/1548 G   5634|CLM] train=4.1490  mask=15.5%  norm=0.829  lr=1.94e-04  dt=  36.9ms  words=46,161,920
[E04   992/1548 G   5635|CLM] train=2.5450  mask=15.4%  norm=0.853  lr=1.94e-04  dt=  36.9ms  words=46,170,112
[E04   993/1548 G   5636|CLM] train=2.4130  mask=15.4%  norm=0.849  lr=1.94e-04  dt=  37.2ms  words=46,178,304
[E04   994/1548 G   5637|CLM] train=2.2484  mask=15.4%  norm=0.570  lr=1.94e-04  dt=  37.1ms  words=46,186,496
[E04   995/1548 G   5638|CLM] train=4.4723  mask=15.4%  norm=0.879  lr=1.94e-04  dt=  37.1ms  words=46,194,688
[E04   996/1548 G   5639|CLM] train=4.3819  mask=15.4%  norm=0.634  lr=1.94e-04  dt=  37.3ms  words=46,202,880
[E04   997/1548 G   5640|CLM] train=5.1285  mask=15.4%  norm=1.865  lr=1.94e-04  dt=  36.9ms  words=46,211,072
[E04   998/1548 G   5641|CLM] train=2.8211  mask=15.4%  norm=0.625  lr=1.94e-04  dt=  37.0ms  words=46,219,264
[E04   999/1548 G   5642|CLM] train=4.2426  mask=15.4%  norm=0.783  lr=1.94e-04  dt=  37.4ms  words=46,227,456
[E04  1000/1548 G   5643|CLM] train=2.2580  mask=15.4%  norm=0.848  lr=1.94e-04  dt=  37.1ms  words=46,235,648
[E04  1001/1548 G   5644|CLM] train=3.9578  mask=15.4%  norm=0.726  lr=1.94e-04  dt=  37.2ms  words=46,243,840
[E04  1002/1548 G   5645|CLM] train=5.1503  mask=15.4%  norm=1.696  lr=1.94e-04  dt=  39.0ms  words=46,252,032
[E04  1003/1548 G   5646|CLM] train=2.3375  mask=15.4%  norm=0.638  lr=1.94e-04  dt=  37.7ms  words=46,260,224
[E04  1004/1548 G   5647|CLM] train=2.6167  mask=15.4%  norm=0.935  lr=1.94e-04  dt=  37.5ms  words=46,268,416
[E04  1005/1548 G   5648|CLM] train=3.8043  mask=15.4%  norm=3.954  lr=1.94e-04  dt=  38.2ms  words=46,276,608
[E04  1006/1548 G   5649|CLM] train=2.3895  mask=15.4%  norm=0.882  lr=1.94e-04  dt=  37.3ms  words=46,284,800
[E04  1007/1548 G   5650|CLM] train=4.6616  mask=15.4%  norm=1.050  lr=1.94e-04  dt=  37.6ms  words=46,292,992
[E04  1008/1548 G   5651|CLM] train=2.0809  mask=15.4%  norm=0.600  lr=1.93e-04  dt=  37.8ms  words=46,301,184
[E04  1009/1548 G   5652|CLM] train=2.4051  mask=15.4%  norm=0.661  lr=1.93e-04  dt=  37.1ms  words=46,309,376
[E04  1010/1548 G   5653|CLM] train=1.9921  mask=15.4%  norm=0.651  lr=1.93e-04  dt=  36.9ms  words=46,317,568
[E04  1011/1548 G   5654|CLM] train=4.8370  mask=15.4%  norm=1.086  lr=1.93e-04  dt=  37.1ms  words=46,325,760
[E04  1012/1548 G   5655|CLM] train=2.5088  mask=15.4%  norm=0.655  lr=1.93e-04  dt=  37.5ms  words=46,333,952
[E04  1013/1548 G   5656|CLM] train=4.2140  mask=15.4%  norm=1.340  lr=1.93e-04  dt=  37.5ms  words=46,342,144
[E04  1014/1548 G   5657|CLM] train=4.1050  mask=15.4%  norm=0.676  lr=1.93e-04  dt=  41.5ms  words=46,350,336
[E04  1015/1548 G   5658|CLM] train=4.5708  mask=15.4%  norm=0.889  lr=1.93e-04  dt=  36.9ms  words=46,358,528
[E04  1016/1548 G   5659|CLM] train=4.3869  mask=15.4%  norm=1.398  lr=1.93e-04  dt=  38.3ms  words=46,366,720
[E04  1017/1548 G   5660|CLM] train=2.6335  mask=15.4%  norm=0.985  lr=1.93e-04  dt=  41.2ms  words=46,374,912
[E04  1018/1548 G   5661|CLM] train=3.8469  mask=15.4%  norm=0.734  lr=1.93e-04  dt=  36.9ms  words=46,383,104
[E04  1019/1548 G   5662|CLM] train=4.4118  mask=15.4%  norm=0.854  lr=1.93e-04  dt=  38.3ms  words=46,391,296
[E04  1020/1548 G   5663|CLM] train=4.3485  mask=15.4%  norm=1.218  lr=1.93e-04  dt=  42.7ms  words=46,399,488
[E04  1021/1548 G   5664|CLM] train=2.5422  mask=15.4%  norm=0.716  lr=1.93e-04  dt=  43.0ms  words=46,407,680
[E04  1022/1548 G   5665|CLM] train=5.0195  mask=15.4%  norm=0.940  lr=1.93e-04  dt=  41.3ms  words=46,415,872
[E04  1023/1548 G   5666|CLM] train=3.9230  mask=15.4%  norm=0.658  lr=1.93e-04  dt=  36.9ms  words=46,424,064
[E04  1024/1548 G   5667|CLM] train=2.6170  mask=15.4%  norm=0.626  lr=1.93e-04  dt=  36.7ms  words=46,432,256
[E04  1025/1548 G   5668|CLM] train=5.0556  mask=15.4%  norm=0.979  lr=1.93e-04  dt=  40.5ms  words=46,440,448
[E04  1026/1548 G   5669|CLM] train=4.5567  mask=15.4%  norm=0.751  lr=1.93e-04  dt=  36.9ms  words=46,448,640
[E04  1027/1548 G   5670|CLM] train=2.7058  mask=15.4%  norm=0.913  lr=1.93e-04  dt=  37.1ms  words=46,456,832
[E04  1028/1548 G   5671|CLM] train=3.9680  mask=15.4%  norm=0.762  lr=1.93e-04  dt=  37.0ms  words=46,465,024
[E04  1029/1548 G   5672|CLM] train=4.8037  mask=15.4%  norm=0.781  lr=1.93e-04  dt=  37.0ms  words=46,473,216
[E04  1030/1548 G   5673|CLM] train=2.7518  mask=15.4%  norm=0.561  lr=1.93e-04  dt=  36.8ms  words=46,481,408
[E04  1031/1548 G   5674|CLM] train=2.8658  mask=15.4%  norm=0.698  lr=1.93e-04  dt=  37.1ms  words=46,489,600
[E04  1032/1548 G   5675|CLM] train=4.2795  mask=15.4%  norm=0.708  lr=1.93e-04  dt=  36.8ms  words=46,497,792
[E04  1033/1548 G   5676|CLM] train=3.9787  mask=15.4%  norm=0.744  lr=1.93e-04  dt=  36.9ms  words=46,505,984
[E04  1034/1548 G   5677|CLM] train=2.5657  mask=15.4%  norm=0.960  lr=1.92e-04  dt=  36.9ms  words=46,514,176
[E04  1035/1548 G   5678|CLM] train=4.3249  mask=15.4%  norm=0.847  lr=1.92e-04  dt=  37.0ms  words=46,522,368
[E04  1036/1548 G   5679|CLM] train=4.0707  mask=15.4%  norm=0.809  lr=1.92e-04  dt=  36.8ms  words=46,530,560
[E04  1037/1548 G   5680|CLM] train=3.8343  mask=15.4%  norm=0.628  lr=1.92e-04  dt=  36.7ms  words=46,538,752
[E04  1038/1548 G   5681|CLM] train=4.0368  mask=15.4%  norm=0.613  lr=1.92e-04  dt=  36.9ms  words=46,546,944
[E04  1039/1548 G   5682|CLM] train=2.4136  mask=15.4%  norm=0.862  lr=1.92e-04  dt=  37.2ms  words=46,555,136
[E04  1040/1548 G   5683|CLM] train=2.4466  mask=15.4%  norm=0.955  lr=1.92e-04  dt=  37.1ms  words=46,563,328
[E04  1041/1548 G   5684|CLM] train=2.0990  mask=15.4%  norm=0.881  lr=1.92e-04  dt=  36.7ms  words=46,571,520
[E04  1042/1548 G   5685|CLM] train=4.0975  mask=15.4%  norm=0.875  lr=1.92e-04  dt=  36.9ms  words=46,579,712
[E04  1043/1548 G   5686|CLM] train=2.3654  mask=15.4%  norm=0.824  lr=1.92e-04  dt=  37.0ms  words=46,587,904
[E04  1044/1548 G   5687|CLM] train=3.8197  mask=15.4%  norm=1.712  lr=1.92e-04  dt=  36.8ms  words=46,596,096
[E04  1045/1548 G   5688|CLM] train=2.6091  mask=15.4%  norm=0.897  lr=1.92e-04  dt=  36.8ms  words=46,604,288
[E04  1046/1548 G   5689|CLM] train=4.1222  mask=15.4%  norm=0.853  lr=1.92e-04  dt=  36.8ms  words=46,612,480
[E04  1047/1548 G   5690|CLM] train=4.4943  mask=15.4%  norm=0.921  lr=1.92e-04  dt=  37.0ms  words=46,620,672
[E04  1048/1548 G   5691|CLM] train=3.7160  mask=15.4%  norm=0.836  lr=1.92e-04  dt=  36.9ms  words=46,628,864
[E04  1049/1548 G   5692|CLM] train=2.1863  mask=15.4%  norm=0.710  lr=1.92e-04  dt=  36.9ms  words=46,637,056
[E04  1050/1548 G   5693|CLM] train=3.9401  mask=15.4%  norm=0.744  lr=1.92e-04  dt=  36.9ms  words=46,645,248
[E04  1051/1548 G   5694|CLM] train=4.9589  mask=15.4%  norm=0.869  lr=1.92e-04  dt=  37.0ms  words=46,653,440
[E04  1052/1548 G   5695|CLM] train=3.1693  mask=15.4%  norm=0.837  lr=1.92e-04  dt=  37.0ms  words=46,661,632
[E04  1053/1548 G   5696|CLM] train=2.9300  mask=15.4%  norm=0.913  lr=1.92e-04  dt=  37.0ms  words=46,669,824
[E04  1054/1548 G   5697|CLM] train=2.3107  mask=15.4%  norm=0.755  lr=1.92e-04  dt=  37.0ms  words=46,678,016
[E04  1055/1548 G   5698|CLM] train=4.8158  mask=15.4%  norm=1.139  lr=1.92e-04  dt=  37.0ms  words=46,686,208
[E04  1056/1548 G   5699|CLM] train=2.6054  mask=15.4%  norm=0.728  lr=1.92e-04  dt=  36.9ms  words=46,694,400
[E04  1057/1548 G   5700|CLM] train=4.4136  mask=15.4%  norm=0.777  lr=1.92e-04  dt=  36.9ms  words=46,702,592
[E04  1058/1548 G   5701|CLM] train=4.4462  mask=15.4%  norm=0.848  lr=1.92e-04  dt=  36.8ms  words=46,710,784
[E04  1059/1548 G   5702|CLM] train=2.2912  mask=15.4%  norm=0.808  lr=1.92e-04  dt=  37.0ms  words=46,718,976
[E04  1060/1548 G   5703|CLM] train=3.8192  mask=15.4%  norm=0.847  lr=1.92e-04  dt=  36.9ms  words=46,727,168
[E04  1061/1548 G   5704|CLM] train=2.4593  mask=15.4%  norm=0.755  lr=1.91e-04  dt=  37.0ms  words=46,735,360
[E04  1062/1548 G   5705|CLM] train=4.6331  mask=15.4%  norm=0.835  lr=1.91e-04  dt=  36.8ms  words=46,743,552
[E04  1063/1548 G   5706|CLM] train=4.4077  mask=15.4%  norm=0.924  lr=1.91e-04  dt=  37.1ms  words=46,751,744
[E04  1064/1548 G   5707|CLM] train=2.2188  mask=15.4%  norm=0.865  lr=1.91e-04  dt=  36.7ms  words=46,759,936
[E04  1065/1548 G   5708|CLM] train=4.2940  mask=15.4%  norm=0.980  lr=1.91e-04  dt=  36.9ms  words=46,768,128
[E04  1066/1548 G   5709|CLM] train=5.5220  mask=15.4%  norm=0.950  lr=1.91e-04  dt=  37.1ms  words=46,776,320
[E04  1067/1548 G   5710|CLM] train=2.4220  mask=15.4%  norm=1.196  lr=1.91e-04  dt=  37.3ms  words=46,784,512
[E04  1068/1548 G   5711|CLM] train=4.1970  mask=15.4%  norm=0.822  lr=1.91e-04  dt=  36.8ms  words=46,792,704
[E04  1069/1548 G   5712|CLM] train=4.1428  mask=15.4%  norm=1.031  lr=1.91e-04  dt=  36.9ms  words=46,800,896
[E04  1070/1548 G   5713|CLM] train=3.8888  mask=15.4%  norm=0.727  lr=1.91e-04  dt=  36.9ms  words=46,809,088
[E04  1071/1548 G   5714|CLM] train=2.4152  mask=15.4%  norm=0.863  lr=1.91e-04  dt=  36.9ms  words=46,817,280
[E04  1072/1548 G   5715|CLM] train=4.4024  mask=15.4%  norm=0.789  lr=1.91e-04  dt=  36.7ms  words=46,825,472
[E04  1073/1548 G   5716|CLM] train=2.4774  mask=15.4%  norm=0.724  lr=1.91e-04  dt=  36.9ms  words=46,833,664
[E04  1074/1548 G   5717|CLM] train=4.3761  mask=15.4%  norm=0.925  lr=1.91e-04  dt=  36.8ms  words=46,841,856
[E04  1075/1548 G   5718|CLM] train=4.6372  mask=15.4%  norm=1.379  lr=1.91e-04  dt=  37.0ms  words=46,850,048
[E04  1076/1548 G   5719|CLM] train=2.3550  mask=15.4%  norm=1.199  lr=1.91e-04  dt=  36.8ms  words=46,858,240
[E04  1077/1548 G   5720|CLM] train=2.4273  mask=15.4%  norm=0.833  lr=1.91e-04  dt=  36.9ms  words=46,866,432
[E04  1078/1548 G   5721|CLM] train=2.2209  mask=15.4%  norm=0.783  lr=1.91e-04  dt=  36.9ms  words=46,874,624
[E04  1079/1548 G   5722|CLM] train=4.6920  mask=15.4%  norm=0.751  lr=1.91e-04  dt=  37.2ms  words=46,882,816
[E04  1080/1548 G   5723|CLM] train=4.5223  mask=15.4%  norm=0.745  lr=1.91e-04  dt=  36.8ms  words=46,891,008
[E04  1081/1548 G   5724|CLM] train=4.1355  mask=15.4%  norm=0.815  lr=1.91e-04  dt=  36.9ms  words=46,899,200
[E04  1082/1548 G   5725|CLM] train=4.1915  mask=15.4%  norm=0.842  lr=1.91e-04  dt=  36.8ms  words=46,907,392
[E04  1083/1548 G   5726|CLM] train=4.2486  mask=15.4%  norm=0.751  lr=1.91e-04  dt=  37.0ms  words=46,915,584
[E04  1084/1548 G   5727|CLM] train=4.6389  mask=15.4%  norm=0.718  lr=1.91e-04  dt=  36.8ms  words=46,923,776
[E04  1085/1548 G   5728|CLM] train=4.3034  mask=15.4%  norm=0.686  lr=1.91e-04  dt=  36.8ms  words=46,931,968
[E04  1086/1548 G   5729|CLM] train=2.3978  mask=15.4%  norm=0.955  lr=1.91e-04  dt=  36.7ms  words=46,940,160
[E04  1087/1548 G   5730|CLM] train=2.3908  mask=15.4%  norm=0.822  lr=1.91e-04  dt=  36.9ms  words=46,948,352
[E04  1088/1548 G   5731|CLM] train=5.1090  mask=15.4%  norm=1.069  lr=1.90e-04  dt=  37.0ms  words=46,956,544
[E04  1089/1548 G   5732|CLM] train=2.6845  mask=15.4%  norm=0.761  lr=1.90e-04  dt=  36.8ms  words=46,964,736
[E04  1090/1548 G   5733|CLM] train=4.6948  mask=15.4%  norm=0.840  lr=1.90e-04  dt=  36.8ms  words=46,972,928
[E04  1091/1548 G   5734|CLM] train=3.7168  mask=15.4%  norm=0.895  lr=1.90e-04  dt=  36.7ms  words=46,981,120
[E04  1092/1548 G   5735|CLM] train=4.4043  mask=15.4%  norm=0.847  lr=1.90e-04  dt=  36.9ms  words=46,989,312
[E04  1093/1548 G   5736|CLM] train=4.1837  mask=15.4%  norm=0.985  lr=1.90e-04  dt=  36.9ms  words=46,997,504
[E04  1094/1548 G   5737|CLM] train=2.6771  mask=15.4%  norm=0.602  lr=1.90e-04  dt=  37.5ms  words=47,005,696
[E04  1095/1548 G   5738|CLM] train=2.4982  mask=15.4%  norm=0.967  lr=1.90e-04  dt=  36.9ms  words=47,013,888
[E04  1096/1548 G   5739|CLM] train=4.6149  mask=15.4%  norm=0.976  lr=1.90e-04  dt=  36.9ms  words=47,022,080
[E04  1097/1548 G   5740|CLM] train=4.2786  mask=15.4%  norm=0.765  lr=1.90e-04  dt=  36.9ms  words=47,030,272
[E04  1098/1548 G   5741|CLM] train=4.5403  mask=15.4%  norm=0.961  lr=1.90e-04  dt=  36.9ms  words=47,038,464
[E04  1099/1548 G   5742|CLM] train=2.4248  mask=15.4%  norm=0.705  lr=1.90e-04  dt=  37.0ms  words=47,046,656
[E04  1100/1548 G   5743|CLM] train=4.8539  mask=15.4%  norm=0.806  lr=1.90e-04  dt=  36.9ms  words=47,054,848
[E04  1101/1548 G   5744|CLM] train=4.5391  mask=15.4%  norm=0.768  lr=1.90e-04  dt=  37.0ms  words=47,063,040
[E04  1102/1548 G   5745|CLM] train=4.5163  mask=15.4%  norm=0.776  lr=1.90e-04  dt=  36.9ms  words=47,071,232
[E04  1103/1548 G   5746|CLM] train=4.3298  mask=15.4%  norm=0.928  lr=1.90e-04  dt=  37.0ms  words=47,079,424
[E04  1104/1548 G   5747|CLM] train=2.4146  mask=15.4%  norm=0.930  lr=1.90e-04  dt=  36.9ms  words=47,087,616
[E04  1105/1548 G   5748|CLM] train=4.2449  mask=15.4%  norm=0.689  lr=1.90e-04  dt=  36.9ms  words=47,095,808
[E04  1106/1548 G   5749|CLM] train=2.4221  mask=15.4%  norm=0.637  lr=1.90e-04  dt=  36.9ms  words=47,104,000
[E04  1107/1548 G   5750|CLM] train=2.1394  mask=15.4%  norm=0.824  lr=1.90e-04  dt=  37.0ms  words=47,112,192
[E04  1108/1548 G   5751|CLM] train=4.2640  mask=15.4%  norm=0.874  lr=1.90e-04  dt=  36.8ms  words=47,120,384
[E04  1109/1548 G   5752|CLM] train=4.3290  mask=15.4%  norm=1.161  lr=1.90e-04  dt=  36.8ms  words=47,128,576
[E04  1110/1548 G   5753|CLM] train=3.8176  mask=15.4%  norm=0.772  lr=1.90e-04  dt=  36.9ms  words=47,136,768
[E04  1111/1548 G   5754|CLM] train=4.0450  mask=15.4%  norm=0.937  lr=1.90e-04  dt=  37.0ms  words=47,144,960
[E04  1112/1548 G   5755|CLM] train=4.1643  mask=15.4%  norm=0.739  lr=1.90e-04  dt=  36.7ms  words=47,153,152
[E04  1113/1548 G   5756|CLM] train=4.3044  mask=15.4%  norm=0.960  lr=1.90e-04  dt=  36.7ms  words=47,161,344
[E04  1114/1548 G   5757|CLM] train=4.3156  mask=15.4%  norm=0.886  lr=1.89e-04  dt=  36.7ms  words=47,169,536
[E04  1115/1548 G   5758|CLM] train=3.8420  mask=15.4%  norm=0.726  lr=1.89e-04  dt=  36.8ms  words=47,177,728
[E04  1116/1548 G   5759|CLM] train=4.2531  mask=15.3%  norm=0.833  lr=1.89e-04  dt=  36.9ms  words=47,185,920
[E04  1117/1548 G   5760|CLM] train=4.7195  mask=15.3%  norm=0.872  lr=1.89e-04  dt=  36.8ms  words=47,194,112
[E04  1118/1548 G   5761|CLM] train=3.9340  mask=15.3%  norm=0.731  lr=1.89e-04  dt=  36.7ms  words=47,202,304
[E04  1119/1548 G   5762|CLM] train=4.0545  mask=15.3%  norm=0.802  lr=1.89e-04  dt=  37.2ms  words=47,210,496
[E04  1120/1548 G   5763|CLM] train=2.2952  mask=15.3%  norm=0.794  lr=1.89e-04  dt=  36.9ms  words=47,218,688
[E04  1121/1548 G   5764|CLM] train=5.1504  mask=15.3%  norm=0.847  lr=1.89e-04  dt=  37.0ms  words=47,226,880
[E04  1122/1548 G   5765|CLM] train=4.0694  mask=15.3%  norm=1.824  lr=1.89e-04  dt=  36.7ms  words=47,235,072
[E04  1123/1548 G   5766|CLM] train=4.0833  mask=15.3%  norm=0.762  lr=1.89e-04  dt=  36.9ms  words=47,243,264
[E04  1124/1548 G   5767|CLM] train=4.3114  mask=15.3%  norm=0.828  lr=1.89e-04  dt=  36.9ms  words=47,251,456
[E04  1125/1548 G   5768|CLM] train=2.5057  mask=15.3%  norm=0.664  lr=1.89e-04  dt=  36.9ms  words=47,259,648
[E04  1126/1548 G   5769|CLM] train=3.8727  mask=15.3%  norm=0.788  lr=1.89e-04  dt=  36.8ms  words=47,267,840
[E04  1127/1548 G   5770|CLM] train=4.5482  mask=15.3%  norm=1.006  lr=1.89e-04  dt=  36.9ms  words=47,276,032
[E04  1128/1548 G   5771|CLM] train=4.5805  mask=15.3%  norm=0.796  lr=1.89e-04  dt=  37.0ms  words=47,284,224
[E04  1129/1548 G   5772|CLM] train=4.8482  mask=15.3%  norm=0.856  lr=1.89e-04  dt=  37.0ms  words=47,292,416
[E04  1130/1548 G   5773|CLM] train=4.8330  mask=15.3%  norm=0.916  lr=1.89e-04  dt=  36.8ms  words=47,300,608
[E04  1131/1548 G   5774|CLM] train=2.4504  mask=15.3%  norm=0.707  lr=1.89e-04  dt=  37.0ms  words=47,308,800
[E04  1132/1548 G   5775|CLM] train=4.3595  mask=15.3%  norm=0.843  lr=1.89e-04  dt=  37.0ms  words=47,316,992
[E04  1133/1548 G   5776|CLM] train=5.0581  mask=15.3%  norm=0.985  lr=1.89e-04  dt=  37.1ms  words=47,325,184
[E04  1134/1548 G   5777|CLM] train=4.1905  mask=15.3%  norm=0.678  lr=1.89e-04  dt=  37.0ms  words=47,333,376
[E04  1135/1548 G   5778|CLM] train=4.4503  mask=15.3%  norm=0.845  lr=1.89e-04  dt=  38.0ms  words=47,341,568
[E04  1136/1548 G   5779|CLM] train=4.9914  mask=15.3%  norm=1.090  lr=1.89e-04  dt=  39.1ms  words=47,349,760
[E04  1137/1548 G   5780|CLM] train=5.1769  mask=15.3%  norm=0.954  lr=1.89e-04  dt=  46.3ms  words=47,357,952
[E04  1138/1548 G   5781|CLM] train=2.4186  mask=15.3%  norm=0.754  lr=1.89e-04  dt=  37.1ms  words=47,366,144
[E04  1139/1548 G   5782|CLM] train=2.5762  mask=15.3%  norm=0.767  lr=1.89e-04  dt=  45.4ms  words=47,374,336
[E04  1140/1548 G   5783|CLM] train=4.2759  mask=15.3%  norm=0.826  lr=1.89e-04  dt=  40.1ms  words=47,382,528
[E04  1141/1548 G   5784|CLM] train=4.1221  mask=15.3%  norm=1.286  lr=1.88e-04  dt=  37.0ms  words=47,390,720
[E04  1142/1548 G   5785|CLM] train=4.2256  mask=15.3%  norm=0.887  lr=1.88e-04  dt=  37.7ms  words=47,398,912
[E04  1143/1548 G   5786|CLM] train=3.7917  mask=15.3%  norm=0.865  lr=1.88e-04  dt=  38.0ms  words=47,407,104
[E04  1144/1548 G   5787|CLM] train=2.2924  mask=15.3%  norm=0.754  lr=1.88e-04  dt=  46.2ms  words=47,415,296
[E04  1145/1548 G   5788|CLM] train=2.6710  mask=15.3%  norm=0.952  lr=1.88e-04  dt=  44.1ms  words=47,423,488
[E04  1146/1548 G   5789|CLM] train=2.2290  mask=15.3%  norm=0.693  lr=1.88e-04  dt=  44.2ms  words=47,431,680
[E04  1147/1548 G   5790|CLM] train=2.4664  mask=15.3%  norm=0.824  lr=1.88e-04  dt=  43.3ms  words=47,439,872
[E04  1148/1548 G   5791|CLM] train=4.0502  mask=15.3%  norm=0.724  lr=1.88e-04  dt=  46.7ms  words=47,448,064
[E04  1149/1548 G   5792|CLM] train=2.9619  mask=15.3%  norm=0.928  lr=1.88e-04  dt=  37.1ms  words=47,456,256
[E04  1150/1548 G   5793|CLM] train=4.2163  mask=15.3%  norm=0.793  lr=1.88e-04  dt=  37.0ms  words=47,464,448
[E04  1151/1548 G   5794|CLM] train=4.3315  mask=15.3%  norm=0.850  lr=1.88e-04  dt=  37.1ms  words=47,472,640
[E04  1152/1548 G   5795|CLM] train=4.6721  mask=15.3%  norm=0.845  lr=1.88e-04  dt=  37.0ms  words=47,480,832
[E04  1153/1548 G   5796|CLM] train=4.2680  mask=15.3%  norm=1.024  lr=1.88e-04  dt=  37.1ms  words=47,489,024
[E04  1154/1548 G   5797|CLM] train=4.2391  mask=15.3%  norm=0.712  lr=1.88e-04  dt=  36.8ms  words=47,497,216
[E04  1155/1548 G   5798|CLM] train=5.2122  mask=15.3%  norm=1.005  lr=1.88e-04  dt=  36.9ms  words=47,505,408
[E04  1156/1548 G   5799|CLM] train=4.8627  mask=15.3%  norm=0.945  lr=1.88e-04  dt=  36.9ms  words=47,513,600
[E04  1157/1548 G   5800|CLM] train=3.5634  mask=15.3%  norm=0.686  lr=1.88e-04  dt=  37.0ms  words=47,521,792
[E04  1158/1548 G   5801|CLM] train=4.6121  mask=15.3%  norm=0.839  lr=1.88e-04  dt=  36.9ms  words=47,529,984
[E04  1159/1548 G   5802|CLM] train=2.3951  mask=15.3%  norm=0.787  lr=1.88e-04  dt=  37.3ms  words=47,538,176
[E04  1160/1548 G   5803|CLM] train=4.4471  mask=15.3%  norm=1.009  lr=1.88e-04  dt=  37.1ms  words=47,546,368
[E04  1161/1548 G   5804|CLM] train=2.3035  mask=15.3%  norm=0.737  lr=1.88e-04  dt=  42.1ms  words=47,554,560
[E04  1162/1548 G   5805|CLM] train=4.0349  mask=15.3%  norm=0.973  lr=1.88e-04  dt=  37.6ms  words=47,562,752
[E04  1163/1548 G   5806|CLM] train=3.8843  mask=15.3%  norm=0.809  lr=1.88e-04  dt=  44.8ms  words=47,570,944
[E04  1164/1548 G   5807|CLM] train=4.0487  mask=15.3%  norm=0.649  lr=1.88e-04  dt=  36.9ms  words=47,579,136
[E04  1165/1548 G   5808|CLM] train=4.1238  mask=15.3%  norm=0.681  lr=1.88e-04  dt=  37.3ms  words=47,587,328
[E04  1166/1548 G   5809|CLM] train=4.2180  mask=15.3%  norm=0.996  lr=1.88e-04  dt=  39.8ms  words=47,595,520
[E04  1167/1548 G   5810|CLM] train=4.4506  mask=15.3%  norm=0.802  lr=1.87e-04  dt=  38.5ms  words=47,603,712
[E04  1168/1548 G   5811|CLM] train=5.1568  mask=15.3%  norm=0.880  lr=1.87e-04  dt=  42.4ms  words=47,611,904
[E04  1169/1548 G   5812|CLM] train=2.9361  mask=15.3%  norm=0.914  lr=1.87e-04  dt=  37.5ms  words=47,620,096
[E04  1170/1548 G   5813|CLM] train=4.0290  mask=15.3%  norm=0.767  lr=1.87e-04  dt=  38.3ms  words=47,628,288
[E04  1171/1548 G   5814|CLM] train=4.4055  mask=15.3%  norm=0.712  lr=1.87e-04  dt=  40.4ms  words=47,636,480
[E04  1172/1548 G   5815|CLM] train=2.5324  mask=15.3%  norm=0.976  lr=1.87e-04  dt=  38.3ms  words=47,644,672
[E04  1173/1548 G   5816|CLM] train=2.5833  mask=15.3%  norm=1.400  lr=1.87e-04  dt=  37.7ms  words=47,652,864
[E04  1174/1548 G   5817|CLM] train=2.3420  mask=15.3%  norm=0.788  lr=1.87e-04  dt=  42.5ms  words=47,661,056
[E04  1175/1548 G   5818|CLM] train=5.1322  mask=15.3%  norm=1.012  lr=1.87e-04  dt=  43.7ms  words=47,669,248
[E04  1176/1548 G   5819|CLM] train=4.0793  mask=15.3%  norm=0.845  lr=1.87e-04  dt=  38.9ms  words=47,677,440
[E04  1177/1548 G   5820|CLM] train=2.2414  mask=15.3%  norm=0.932  lr=1.87e-04  dt=  39.5ms  words=47,685,632
[E04  1178/1548 G   5821|CLM] train=4.3559  mask=15.3%  norm=1.147  lr=1.87e-04  dt=  39.6ms  words=47,693,824
[E04  1179/1548 G   5822|CLM] train=3.8595  mask=15.3%  norm=0.732  lr=1.87e-04  dt=  39.6ms  words=47,702,016
[E04  1180/1548 G   5823|CLM] train=2.2576  mask=15.3%  norm=0.741  lr=1.87e-04  dt=  36.8ms  words=47,710,208
[E04  1181/1548 G   5824|CLM] train=2.9432  mask=15.3%  norm=0.711  lr=1.87e-04  dt=  47.0ms  words=47,718,400
[E04  1182/1548 G   5825|CLM] train=4.7227  mask=15.3%  norm=0.917  lr=1.87e-04  dt=  36.8ms  words=47,726,592
[E04  1183/1548 G   5826|CLM] train=4.0256  mask=15.3%  norm=0.893  lr=1.87e-04  dt=  37.0ms  words=47,734,784
[E04  1184/1548 G   5827|CLM] train=4.1676  mask=15.3%  norm=1.217  lr=1.87e-04  dt=  47.3ms  words=47,742,976
[E04  1185/1548 G   5828|CLM] train=4.5187  mask=15.3%  norm=1.004  lr=1.87e-04  dt=  37.4ms  words=47,751,168
[E04  1186/1548 G   5829|CLM] train=2.5552  mask=15.3%  norm=0.640  lr=1.87e-04  dt=  37.0ms  words=47,759,360
[E04  1187/1548 G   5830|CLM] train=4.5385  mask=15.3%  norm=1.053  lr=1.87e-04  dt=  37.0ms  words=47,767,552
[E04  1188/1548 G   5831|CLM] train=4.8549  mask=15.3%  norm=0.858  lr=1.87e-04  dt=  37.0ms  words=47,775,744
[E04  1189/1548 G   5832|CLM] train=3.5972  mask=15.3%  norm=0.845  lr=1.87e-04  dt=  37.1ms  words=47,783,936
[E04  1190/1548 G   5833|CLM] train=4.4103  mask=15.3%  norm=1.095  lr=1.87e-04  dt=  36.8ms  words=47,792,128
[E04  1191/1548 G   5834|CLM] train=4.6408  mask=15.3%  norm=0.773  lr=1.87e-04  dt=  36.9ms  words=47,800,320
[E04  1192/1548 G   5835|CLM] train=4.1632  mask=15.3%  norm=0.853  lr=1.87e-04  dt=  36.9ms  words=47,808,512
[E04  1193/1548 G   5836|CLM] train=4.6983  mask=15.3%  norm=0.795  lr=1.87e-04  dt=  37.0ms  words=47,816,704
[E04  1194/1548 G   5837|CLM] train=4.3408  mask=15.3%  norm=0.867  lr=1.86e-04  dt=  37.2ms  words=47,824,896
[E04  1195/1548 G   5838|CLM] train=2.4245  mask=15.3%  norm=0.613  lr=1.86e-04  dt=  37.0ms  words=47,833,088
[E04  1196/1548 G   5839|CLM] train=4.1285  mask=15.3%  norm=0.727  lr=1.86e-04  dt=  37.1ms  words=47,841,280
[E04  1197/1548 G   5840|CLM] train=3.1901  mask=15.3%  norm=3.267  lr=1.86e-04  dt=  37.5ms  words=47,849,472
[E04  1198/1548 G   5841|CLM] train=2.2781  mask=15.3%  norm=0.851  lr=1.86e-04  dt=  39.3ms  words=47,857,664
[E04  1199/1548 G   5842|CLM] train=3.0983  mask=15.3%  norm=0.871  lr=1.86e-04  dt=  37.1ms  words=47,865,856
[E04  1200/1548 G   5843|CLM] train=2.3254  mask=15.3%  norm=0.802  lr=1.86e-04  dt=  37.1ms  words=47,874,048
[E04  1201/1548 G   5844|CLM] train=2.9860  mask=15.3%  norm=0.767  lr=1.86e-04  dt=  37.0ms  words=47,882,240
[E04  1202/1548 G   5845|CLM] train=4.6496  mask=15.3%  norm=0.863  lr=1.86e-04  dt=  36.9ms  words=47,890,432
[E04  1203/1548 G   5846|CLM] train=2.8300  mask=15.3%  norm=0.606  lr=1.86e-04  dt=  36.8ms  words=47,898,624
[E04  1204/1548 G   5847|CLM] train=4.8782  mask=15.3%  norm=1.123  lr=1.86e-04  dt=  37.0ms  words=47,906,816
[E04  1205/1548 G   5848|CLM] train=4.7921  mask=15.3%  norm=1.065  lr=1.86e-04  dt=  37.1ms  words=47,915,008
[E04  1206/1548 G   5849|CLM] train=4.0349  mask=15.3%  norm=0.738  lr=1.86e-04  dt=  36.8ms  words=47,923,200
[E04  1207/1548 G   5850|CLM] train=2.4393  mask=15.3%  norm=0.956  lr=1.86e-04  dt=  36.9ms  words=47,931,392
[E04  1208/1548 G   5851|CLM] train=2.6870  mask=15.3%  norm=1.065  lr=1.86e-04  dt=  36.9ms  words=47,939,584
[E04  1209/1548 G   5852|CLM] train=2.2195  mask=15.3%  norm=0.979  lr=1.86e-04  dt=  37.0ms  words=47,947,776
[E04  1210/1548 G   5853|CLM] train=3.8092  mask=15.3%  norm=0.760  lr=1.86e-04  dt=  36.9ms  words=47,955,968
[E04  1211/1548 G   5854|CLM] train=4.5022  mask=15.3%  norm=0.865  lr=1.86e-04  dt=  37.0ms  words=47,964,160
[E04  1212/1548 G   5855|CLM] train=2.3873  mask=15.3%  norm=0.758  lr=1.86e-04  dt=  36.9ms  words=47,972,352
[E04  1213/1548 G   5856|CLM] train=4.9183  mask=15.3%  norm=1.126  lr=1.86e-04  dt=  37.0ms  words=47,980,544
[E04  1214/1548 G   5857|CLM] train=4.3213  mask=15.3%  norm=0.875  lr=1.86e-04  dt=  37.1ms  words=47,988,736
[E04  1215/1548 G   5858|CLM] train=2.0263  mask=15.3%  norm=0.639  lr=1.86e-04  dt=  37.2ms  words=47,996,928
[E04  1216/1548 G   5859|CLM] train=4.1255  mask=15.3%  norm=1.089  lr=1.86e-04  dt=  37.2ms  words=48,005,120
[E04  1217/1548 G   5860|CLM] train=2.2172  mask=15.3%  norm=0.689  lr=1.86e-04  dt=  37.1ms  words=48,013,312
[E04  1218/1548 G   5861|CLM] train=3.9144  mask=15.3%  norm=0.765  lr=1.86e-04  dt=  36.9ms  words=48,021,504
[E04  1219/1548 G   5862|CLM] train=2.3357  mask=15.3%  norm=0.615  lr=1.86e-04  dt=  37.0ms  words=48,029,696
[E04  1220/1548 G   5863|CLM] train=2.4536  mask=15.3%  norm=0.766  lr=1.85e-04  dt=  37.2ms  words=48,037,888
[E04  1221/1548 G   5864|CLM] train=4.9391  mask=15.3%  norm=1.123  lr=1.85e-04  dt=  37.2ms  words=48,046,080
[E04  1222/1548 G   5865|CLM] train=4.0746  mask=15.3%  norm=0.803  lr=1.85e-04  dt=  37.1ms  words=48,054,272
[E04  1223/1548 G   5866|CLM] train=2.5660  mask=15.3%  norm=0.642  lr=1.85e-04  dt=  38.2ms  words=48,062,464
[E04  1224/1548 G   5867|CLM] train=2.2829  mask=15.3%  norm=0.866  lr=1.85e-04  dt=  37.4ms  words=48,070,656
[E04  1225/1548 G   5868|CLM] train=2.6568  mask=15.3%  norm=0.808  lr=1.85e-04  dt=  37.5ms  words=48,078,848
[E04  1226/1548 G   5869|CLM] train=2.5214  mask=15.3%  norm=0.600  lr=1.85e-04  dt=  36.9ms  words=48,087,040
[E04  1227/1548 G   5870|CLM] train=3.7068  mask=15.3%  norm=0.742  lr=1.85e-04  dt=  36.9ms  words=48,095,232
[E04  1228/1548 G   5871|CLM] train=4.0599  mask=15.3%  norm=0.801  lr=1.85e-04  dt=  37.1ms  words=48,103,424
[E04  1229/1548 G   5872|CLM] train=2.4850  mask=15.3%  norm=0.581  lr=1.85e-04  dt=  37.1ms  words=48,111,616
[E04  1230/1548 G   5873|CLM] train=2.2749  mask=15.3%  norm=0.721  lr=1.85e-04  dt=  37.1ms  words=48,119,808
[E04  1231/1548 G   5874|CLM] train=4.5459  mask=15.3%  norm=0.826  lr=1.85e-04  dt=  37.1ms  words=48,128,000
[E04  1232/1548 G   5875|CLM] train=4.4388  mask=15.3%  norm=0.841  lr=1.85e-04  dt=  37.1ms  words=48,136,192
[E04  1233/1548 G   5876|CLM] train=2.2268  mask=15.3%  norm=1.232  lr=1.85e-04  dt=  37.0ms  words=48,144,384
[E04  1234/1548 G   5877|CLM] train=2.1507  mask=15.3%  norm=0.761  lr=1.85e-04  dt=  37.0ms  words=48,152,576
[E04  1235/1548 G   5878|CLM] train=2.6429  mask=15.3%  norm=0.787  lr=1.85e-04  dt=  37.0ms  words=48,160,768
[E04  1236/1548 G   5879|CLM] train=4.4235  mask=15.3%  norm=0.766  lr=1.85e-04  dt=  37.2ms  words=48,168,960
[E04  1237/1548 G   5880|CLM] train=4.2005  mask=15.3%  norm=0.905  lr=1.85e-04  dt=  37.6ms  words=48,177,152
[E04  1238/1548 G   5881|CLM] train=4.5391  mask=15.3%  norm=0.782  lr=1.85e-04  dt=  37.0ms  words=48,185,344
[E04  1239/1548 G   5882|CLM] train=2.7880  mask=15.3%  norm=0.680  lr=1.85e-04  dt=  37.2ms  words=48,193,536
[E04  1240/1548 G   5883|CLM] train=4.7454  mask=15.2%  norm=0.901  lr=1.85e-04  dt=  37.1ms  words=48,201,728
[E04  1241/1548 G   5884|CLM] train=3.9477  mask=15.2%  norm=0.740  lr=1.85e-04  dt=  37.1ms  words=48,209,920
[E04  1242/1548 G   5885|CLM] train=2.3295  mask=15.2%  norm=0.663  lr=1.85e-04  dt=  37.2ms  words=48,218,112
[E04  1243/1548 G   5886|CLM] train=2.2438  mask=15.2%  norm=0.739  lr=1.85e-04  dt=  36.9ms  words=48,226,304
[E04  1244/1548 G   5887|CLM] train=2.2886  mask=15.2%  norm=0.815  lr=1.85e-04  dt=  36.9ms  words=48,234,496
[E04  1245/1548 G   5888|CLM] train=2.4292  mask=15.2%  norm=0.767  lr=1.85e-04  dt=  37.0ms  words=48,242,688
[E04  1246/1548 G   5889|CLM] train=3.6851  mask=15.2%  norm=0.742  lr=1.85e-04  dt=  37.0ms  words=48,250,880
[E04  1247/1548 G   5890|CLM] train=4.2763  mask=15.2%  norm=1.116  lr=1.84e-04  dt=  37.2ms  words=48,259,072
[E04  1248/1548 G   5891|CLM] train=3.9228  mask=15.2%  norm=0.921  lr=1.84e-04  dt=  37.0ms  words=48,267,264
[E04  1249/1548 G   5892|CLM] train=4.7093  mask=15.2%  norm=0.954  lr=1.84e-04  dt=  37.2ms  words=48,275,456
[E04  1250/1548 G   5893|CLM] train=4.5686  mask=15.2%  norm=0.870  lr=1.84e-04  dt=  37.1ms  words=48,283,648
[E04  1251/1548 G   5894|CLM] train=4.2772  mask=15.2%  norm=0.694  lr=1.84e-04  dt=  37.3ms  words=48,291,840
[E04  1252/1548 G   5895|CLM] train=4.1126  mask=15.2%  norm=0.778  lr=1.84e-04  dt=  37.7ms  words=48,300,032
[E04  1253/1548 G   5896|CLM] train=2.7285  mask=15.2%  norm=0.699  lr=1.84e-04  dt=  37.0ms  words=48,308,224
[E04  1254/1548 G   5897|CLM] train=4.4725  mask=15.2%  norm=0.743  lr=1.84e-04  dt=  37.2ms  words=48,316,416
[E04  1255/1548 G   5898|CLM] train=4.4627  mask=15.2%  norm=0.754  lr=1.84e-04  dt=  37.2ms  words=48,324,608
[E04  1256/1548 G   5899|CLM] train=2.0886  mask=15.2%  norm=0.842  lr=1.84e-04  dt=  37.3ms  words=48,332,800
[E04  1257/1548 G   5900|CLM] train=4.6080  mask=15.2%  norm=1.163  lr=1.84e-04  dt=  37.3ms  words=48,340,992
[E04  1258/1548 G   5901|CLM] train=2.4456  mask=15.2%  norm=0.692  lr=1.84e-04  dt=  37.1ms  words=48,349,184
[E04  1259/1548 G   5902|CLM] train=4.5783  mask=15.2%  norm=1.033  lr=1.84e-04  dt=  37.2ms  words=48,357,376
[E04  1260/1548 G   5903|CLM] train=5.0762  mask=15.2%  norm=0.995  lr=1.84e-04  dt=  36.9ms  words=48,365,568
[E04  1261/1548 G   5904|CLM] train=5.0121  mask=15.2%  norm=1.432  lr=1.84e-04  dt=  37.0ms  words=48,373,760
[E04  1262/1548 G   5905|CLM] train=4.3208  mask=15.2%  norm=0.815  lr=1.84e-04  dt=  37.0ms  words=48,381,952
[E04  1263/1548 G   5906|CLM] train=4.6342  mask=15.2%  norm=0.777  lr=1.84e-04  dt=  36.9ms  words=48,390,144
[E04  1264/1548 G   5907|CLM] train=4.9004  mask=15.2%  norm=0.900  lr=1.84e-04  dt=  37.6ms  words=48,398,336
[E04  1265/1548 G   5908|CLM] train=2.6835  mask=15.2%  norm=0.998  lr=1.84e-04  dt=  37.2ms  words=48,406,528
[E04  1266/1548 G   5909|CLM] train=3.6897  mask=15.2%  norm=0.678  lr=1.84e-04  dt=  44.9ms  words=48,414,720
[E04  1267/1548 G   5910|CLM] train=2.3808  mask=15.2%  norm=0.805  lr=1.84e-04  dt=  37.2ms  words=48,422,912
[E04  1268/1548 G   5911|CLM] train=4.1072  mask=15.2%  norm=0.775  lr=1.84e-04  dt=  37.1ms  words=48,431,104
[E04  1269/1548 G   5912|CLM] train=4.5283  mask=15.2%  norm=1.441  lr=1.84e-04  dt=  37.3ms  words=48,439,296
[E04  1270/1548 G   5913|CLM] train=4.8654  mask=15.2%  norm=1.154  lr=1.84e-04  dt=  38.0ms  words=48,447,488
[E04  1271/1548 G   5914|CLM] train=2.4211  mask=15.2%  norm=0.686  lr=1.84e-04  dt=  37.8ms  words=48,455,680
[E04  1272/1548 G   5915|CLM] train=4.3783  mask=15.2%  norm=0.782  lr=1.84e-04  dt=  37.6ms  words=48,463,872
[E04  1273/1548 G   5916|CLM] train=4.1506  mask=15.2%  norm=0.772  lr=1.83e-04  dt=  37.5ms  words=48,472,064
[E04  1274/1548 G   5917|CLM] train=5.0855  mask=15.2%  norm=1.098  lr=1.83e-04  dt=  36.9ms  words=48,480,256
[E04  1275/1548 G   5918|CLM] train=4.5949  mask=15.2%  norm=0.753  lr=1.83e-04  dt=  37.3ms  words=48,488,448
[E04  1276/1548 G   5919|CLM] train=4.3714  mask=15.2%  norm=0.762  lr=1.83e-04  dt=  37.0ms  words=48,496,640
[E04  1277/1548 G   5920|CLM] train=2.1792  mask=15.2%  norm=0.788  lr=1.83e-04  dt=  37.0ms  words=48,504,832
[E04  1278/1548 G   5921|CLM] train=1.8686  mask=15.2%  norm=0.746  lr=1.83e-04  dt=  39.4ms  words=48,513,024
[E04  1279/1548 G   5922|CLM] train=2.2749  mask=15.2%  norm=0.603  lr=1.83e-04  dt=  37.0ms  words=48,521,216
[E04  1280/1548 G   5923|CLM] train=4.6223  mask=15.2%  norm=0.752  lr=1.83e-04  dt=  37.0ms  words=48,529,408
[E04  1281/1548 G   5924|CLM] train=4.4186  mask=15.2%  norm=0.857  lr=1.83e-04  dt=  37.1ms  words=48,537,600
[E04  1282/1548 G   5925|CLM] train=2.2115  mask=15.2%  norm=0.786  lr=1.83e-04  dt=  36.9ms  words=48,545,792
[E04  1283/1548 G   5926|CLM] train=5.3588  mask=15.2%  norm=1.381  lr=1.83e-04  dt=  47.0ms  words=48,553,984
[E04  1284/1548 G   5927|CLM] train=4.5579  mask=15.2%  norm=0.849  lr=1.83e-04  dt=  47.5ms  words=48,562,176
[E04  1285/1548 G   5928|CLM] train=4.9187  mask=15.2%  norm=0.962  lr=1.83e-04  dt=  43.3ms  words=48,570,368
[E04  1286/1548 G   5929|CLM] train=2.7055  mask=15.2%  norm=0.789  lr=1.83e-04  dt=  42.7ms  words=48,578,560
[E04  1287/1548 G   5930|CLM] train=2.1212  mask=15.2%  norm=1.055  lr=1.83e-04  dt=  39.3ms  words=48,586,752
[E04  1288/1548 G   5931|CLM] train=4.4428  mask=15.2%  norm=1.069  lr=1.83e-04  dt=  38.3ms  words=48,594,944
[E04  1289/1548 G   5932|CLM] train=2.6371  mask=15.2%  norm=0.641  lr=1.83e-04  dt=  42.5ms  words=48,603,136
[E04  1290/1548 G   5933|CLM] train=2.2356  mask=15.2%  norm=0.586  lr=1.83e-04  dt=  38.8ms  words=48,611,328
[E04  1291/1548 G   5934|CLM] train=2.8921  mask=15.2%  norm=0.892  lr=1.83e-04  dt=  36.6ms  words=48,619,520
[E04  1292/1548 G   5935|CLM] train=2.4439  mask=15.2%  norm=0.555  lr=1.83e-04  dt=  36.3ms  words=48,627,712
[E04  1293/1548 G   5936|CLM] train=3.8377  mask=15.2%  norm=0.815  lr=1.83e-04  dt=  36.6ms  words=48,635,904
[E04  1294/1548 G   5937|CLM] train=4.1824  mask=15.2%  norm=0.984  lr=1.83e-04  dt=  36.5ms  words=48,644,096
[E04  1295/1548 G   5938|CLM] train=3.8201  mask=15.2%  norm=0.853  lr=1.83e-04  dt=  36.6ms  words=48,652,288
[E04  1296/1548 G   5939|CLM] train=4.3088  mask=15.2%  norm=0.829  lr=1.83e-04  dt=  36.5ms  words=48,660,480
[E04  1297/1548 G   5940|CLM] train=2.5242  mask=15.2%  norm=0.957  lr=1.83e-04  dt=  36.4ms  words=48,668,672
[E04  1298/1548 G   5941|CLM] train=3.8390  mask=15.2%  norm=0.711  lr=1.83e-04  dt=  36.5ms  words=48,676,864
[E04  1299/1548 G   5942|CLM] train=2.5253  mask=15.2%  norm=0.662  lr=1.82e-04  dt=  36.4ms  words=48,685,056
[E04  1300/1548 G   5943|CLM] train=3.6574  mask=15.2%  norm=1.491  lr=1.82e-04  dt=  36.6ms  words=48,693,248
[E04  1301/1548 G   5944|CLM] train=3.6665  mask=15.2%  norm=0.703  lr=1.82e-04  dt=  36.5ms  words=48,701,440
[E04  1302/1548 G   5945|CLM] train=2.7223  mask=15.2%  norm=1.537  lr=1.82e-04  dt=  36.5ms  words=48,709,632
[E04  1303/1548 G   5946|CLM] train=5.5609  mask=15.2%  norm=1.358  lr=1.82e-04  dt=  36.5ms  words=48,717,824
[E04  1304/1548 G   5947|CLM] train=4.3665  mask=15.2%  norm=0.854  lr=1.82e-04  dt=  36.4ms  words=48,726,016
[E04  1305/1548 G   5948|CLM] train=2.2653  mask=15.2%  norm=0.964  lr=1.82e-04  dt=  36.5ms  words=48,734,208
[E04  1306/1548 G   5949|CLM] train=4.4781  mask=15.2%  norm=0.810  lr=1.82e-04  dt=  36.3ms  words=48,742,400
[E04  1307/1548 G   5950|CLM] train=1.7809  mask=15.2%  norm=0.799  lr=1.82e-04  dt=  36.5ms  words=48,750,592
[E04  1308/1548 G   5951|CLM] train=4.2553  mask=15.2%  norm=0.767  lr=1.82e-04  dt=  36.5ms  words=48,758,784
[E04  1309/1548 G   5952|CLM] train=2.5504  mask=15.2%  norm=0.813  lr=1.82e-04  dt=  36.7ms  words=48,766,976
[E04  1310/1548 G   5953|CLM] train=3.7392  mask=15.2%  norm=0.720  lr=1.82e-04  dt=  36.5ms  words=48,775,168
[E04  1311/1548 G   5954|CLM] train=2.4128  mask=15.2%  norm=0.645  lr=1.82e-04  dt=  36.5ms  words=48,783,360
[E04  1312/1548 G   5955|CLM] train=4.9863  mask=15.2%  norm=0.850  lr=1.82e-04  dt=  36.6ms  words=48,791,552
[E04  1313/1548 G   5956|CLM] train=4.4629  mask=15.2%  norm=0.765  lr=1.82e-04  dt=  36.4ms  words=48,799,744
[E04  1314/1548 G   5957|CLM] train=4.1436  mask=15.2%  norm=0.809  lr=1.82e-04  dt=  36.6ms  words=48,807,936
[E04  1315/1548 G   5958|CLM] train=2.2349  mask=15.2%  norm=0.703  lr=1.82e-04  dt=  36.4ms  words=48,816,128
[E04  1316/1548 G   5959|CLM] train=4.5334  mask=15.2%  norm=0.834  lr=1.82e-04  dt=  36.5ms  words=48,824,320
[E04  1317/1548 G   5960|CLM] train=2.5156  mask=15.2%  norm=0.665  lr=1.82e-04  dt=  36.5ms  words=48,832,512
[E04  1318/1548 G   5961|CLM] train=2.5062  mask=15.2%  norm=0.773  lr=1.82e-04  dt=  36.4ms  words=48,840,704
[E04  1319/1548 G   5962|CLM] train=3.8571  mask=15.2%  norm=0.760  lr=1.82e-04  dt=  36.5ms  words=48,848,896
[E04  1320/1548 G   5963|CLM] train=3.8720  mask=15.2%  norm=0.748  lr=1.82e-04  dt=  36.5ms  words=48,857,088
[E04  1321/1548 G   5964|CLM] train=2.4641  mask=15.2%  norm=1.014  lr=1.82e-04  dt=  36.6ms  words=48,865,280
[E04  1322/1548 G   5965|CLM] train=4.6967  mask=15.2%  norm=1.140  lr=1.82e-04  dt=  36.6ms  words=48,873,472
[E04  1323/1548 G   5966|CLM] train=2.8248  mask=15.2%  norm=0.628  lr=1.82e-04  dt=  36.4ms  words=48,881,664
[E04  1324/1548 G   5967|CLM] train=3.7670  mask=15.2%  norm=0.685  lr=1.82e-04  dt=  36.6ms  words=48,889,856
[E04  1325/1548 G   5968|CLM] train=2.3329  mask=15.2%  norm=0.686  lr=1.82e-04  dt=  36.4ms  words=48,898,048
[E04  1326/1548 G   5969|CLM] train=3.8522  mask=15.2%  norm=0.815  lr=1.81e-04  dt=  36.6ms  words=48,906,240
[E04  1327/1548 G   5970|CLM] train=4.2218  mask=15.2%  norm=0.639  lr=1.81e-04  dt=  36.5ms  words=48,914,432
[E04  1328/1548 G   5971|CLM] train=2.3054  mask=15.2%  norm=0.851  lr=1.81e-04  dt=  36.4ms  words=48,922,624
[E04  1329/1548 G   5972|CLM] train=5.7123  mask=15.2%  norm=1.249  lr=1.81e-04  dt=  36.6ms  words=48,930,816
[E04  1330/1548 G   5973|CLM] train=4.0050  mask=15.2%  norm=0.832  lr=1.81e-04  dt=  36.4ms  words=48,939,008
[E04  1331/1548 G   5974|CLM] train=2.7788  mask=15.2%  norm=0.690  lr=1.81e-04  dt=  36.7ms  words=48,947,200
[E04  1332/1548 G   5975|CLM] train=2.2123  mask=15.2%  norm=0.837  lr=1.81e-04  dt=  36.4ms  words=48,955,392
[E04  1333/1548 G   5976|CLM] train=4.4570  mask=15.2%  norm=0.803  lr=1.81e-04  dt=  36.5ms  words=48,963,584
[E04  1334/1548 G   5977|CLM] train=4.4145  mask=15.2%  norm=0.796  lr=1.81e-04  dt=  36.8ms  words=48,971,776
[E04  1335/1548 G   5978|CLM] train=2.3924  mask=15.2%  norm=0.704  lr=1.81e-04  dt=  36.5ms  words=48,979,968
[E04  1336/1548 G   5979|CLM] train=3.9222  mask=15.2%  norm=0.775  lr=1.81e-04  dt=  36.5ms  words=48,988,160
[E04  1337/1548 G   5980|CLM] train=3.6591  mask=15.2%  norm=1.024  lr=1.81e-04  dt=  36.7ms  words=48,996,352
[E04  1338/1548 G   5981|CLM] train=5.5201  mask=15.2%  norm=1.202  lr=1.81e-04  dt=  36.6ms  words=49,004,544
[E04  1339/1548 G   5982|CLM] train=4.8300  mask=15.2%  norm=1.202  lr=1.81e-04  dt=  36.4ms  words=49,012,736
[E04  1340/1548 G   5983|CLM] train=5.3977  mask=15.2%  norm=1.214  lr=1.81e-04  dt=  36.7ms  words=49,020,928
[E04  1341/1548 G   5984|CLM] train=2.4188  mask=15.2%  norm=0.842  lr=1.81e-04  dt=  36.6ms  words=49,029,120
[E04  1342/1548 G   5985|CLM] train=4.6747  mask=15.2%  norm=0.867  lr=1.81e-04  dt=  36.4ms  words=49,037,312
[E04  1343/1548 G   5986|CLM] train=5.3421  mask=15.2%  norm=1.036  lr=1.81e-04  dt=  36.6ms  words=49,045,504
[E04  1344/1548 G   5987|CLM] train=4.5111  mask=15.2%  norm=1.001  lr=1.81e-04  dt=  36.3ms  words=49,053,696
[E04  1345/1548 G   5988|CLM] train=4.1619  mask=15.2%  norm=0.955  lr=1.81e-04  dt=  36.6ms  words=49,061,888
[E04  1346/1548 G   5989|CLM] train=4.3691  mask=15.2%  norm=0.878  lr=1.81e-04  dt=  36.4ms  words=49,070,080
[E04  1347/1548 G   5990|CLM] train=4.5875  mask=15.2%  norm=0.874  lr=1.81e-04  dt=  36.6ms  words=49,078,272
[E04  1348/1548 G   5991|CLM] train=4.2172  mask=15.2%  norm=0.853  lr=1.81e-04  dt=  36.6ms  words=49,086,464
[E04  1349/1548 G   5992|CLM] train=4.8197  mask=15.2%  norm=1.027  lr=1.81e-04  dt=  36.5ms  words=49,094,656
[E04  1350/1548 G   5993|CLM] train=4.4075  mask=15.2%  norm=0.815  lr=1.81e-04  dt=  36.6ms  words=49,102,848
[E04  1351/1548 G   5994|CLM] train=2.7398  mask=15.2%  norm=0.716  lr=1.81e-04  dt=  36.5ms  words=49,111,040
[E04  1352/1548 G   5995|CLM] train=3.9054  mask=15.2%  norm=0.772  lr=1.80e-04  dt=  36.5ms  words=49,119,232
[E04  1353/1548 G   5996|CLM] train=5.3860  mask=15.2%  norm=1.167  lr=1.80e-04  dt=  36.7ms  words=49,127,424
[E04  1354/1548 G   5997|CLM] train=2.3079  mask=15.2%  norm=0.873  lr=1.80e-04  dt=  36.4ms  words=49,135,616
[E04  1355/1548 G   5998|CLM] train=4.6561  mask=15.2%  norm=0.866  lr=1.80e-04  dt=  36.7ms  words=49,143,808
[E04  1356/1548 G   5999|CLM] train=4.5322  mask=15.2%  norm=0.854  lr=1.80e-04  dt=  36.5ms  words=49,152,000
[E04  1357/1548 G   6000|CLM] train=2.5916  mask=15.2%  norm=0.896  lr=1.80e-04  dt=  36.4ms  words=49,160,192
[E04  1358/1548 G   6001|CLM] train=2.0052  mask=15.2%  norm=0.721  lr=1.80e-04  dt=  36.5ms  words=49,168,384
[E04  1359/1548 G   6002|CLM] train=4.0813  mask=15.2%  norm=1.014  lr=1.80e-04  dt=  36.7ms  words=49,176,576
[E04  1360/1548 G   6003|CLM] train=4.5972  mask=15.2%  norm=1.117  lr=1.80e-04  dt=  36.6ms  words=49,184,768
[E04  1361/1548 G   6004|CLM] train=4.7667  mask=15.2%  norm=0.751  lr=1.80e-04  dt=  36.6ms  words=49,192,960
[E04  1362/1548 G   6005|CLM] train=2.7736  mask=15.2%  norm=0.743  lr=1.80e-04  dt=  36.5ms  words=49,201,152
[E04  1363/1548 G   6006|CLM] train=2.4758  mask=15.2%  norm=0.821  lr=1.80e-04  dt=  36.6ms  words=49,209,344
[E04  1364/1548 G   6007|CLM] train=4.4027  mask=15.1%  norm=0.972  lr=1.80e-04  dt=  36.6ms  words=49,217,536
[E04  1365/1548 G   6008|CLM] train=2.1409  mask=15.1%  norm=0.643  lr=1.80e-04  dt=  36.5ms  words=49,225,728
[E04  1366/1548 G   6009|CLM] train=3.8154  mask=15.1%  norm=0.782  lr=1.80e-04  dt=  36.7ms  words=49,233,920
[E04  1367/1548 G   6010|CLM] train=3.7309  mask=15.1%  norm=0.822  lr=1.80e-04  dt=  36.7ms  words=49,242,112
[E04  1368/1548 G   6011|CLM] train=2.3085  mask=15.1%  norm=0.965  lr=1.80e-04  dt=  36.5ms  words=49,250,304
[E04  1369/1548 G   6012|CLM] train=3.7973  mask=15.1%  norm=0.677  lr=1.80e-04  dt=  36.5ms  words=49,258,496
[E04  1370/1548 G   6013|CLM] train=4.7600  mask=15.1%  norm=3.438  lr=1.80e-04  dt=  36.5ms  words=49,266,688
[E04  1371/1548 G   6014|CLM] train=4.6738  mask=15.1%  norm=1.035  lr=1.80e-04  dt=  36.5ms  words=49,274,880
[E04  1372/1548 G   6015|CLM] train=4.9963  mask=15.1%  norm=1.185  lr=1.80e-04  dt=  36.6ms  words=49,283,072
[E04  1373/1548 G   6016|CLM] train=4.5273  mask=15.1%  norm=0.906  lr=1.80e-04  dt=  36.5ms  words=49,291,264
[E04  1374/1548 G   6017|CLM] train=4.3353  mask=15.1%  norm=1.167  lr=1.80e-04  dt=  36.4ms  words=49,299,456
[E04  1375/1548 G   6018|CLM] train=2.6133  mask=15.1%  norm=0.795  lr=1.80e-04  dt=  36.6ms  words=49,307,648
[E04  1376/1548 G   6019|CLM] train=2.2684  mask=15.1%  norm=0.774  lr=1.80e-04  dt=  36.5ms  words=49,315,840
[E04  1377/1548 G   6020|CLM] train=3.9913  mask=15.1%  norm=0.733  lr=1.80e-04  dt=  36.4ms  words=49,324,032
[E04  1378/1548 G   6021|CLM] train=2.7398  mask=15.1%  norm=0.702  lr=1.79e-04  dt=  36.5ms  words=49,332,224
[E04  1379/1548 G   6022|CLM] train=4.1065  mask=15.1%  norm=0.840  lr=1.79e-04  dt=  36.6ms  words=49,340,416
[E04  1380/1548 G   6023|CLM] train=4.4192  mask=15.1%  norm=0.874  lr=1.79e-04  dt=  36.5ms  words=49,348,608
[E04  1381/1548 G   6024|CLM] train=4.3501  mask=15.1%  norm=0.942  lr=1.79e-04  dt=  36.5ms  words=49,356,800
[E04  1382/1548 G   6025|CLM] train=5.2614  mask=15.1%  norm=1.008  lr=1.79e-04  dt=  36.5ms  words=49,364,992
[E04  1383/1548 G   6026|CLM] train=4.6305  mask=15.1%  norm=0.938  lr=1.79e-04  dt=  36.4ms  words=49,373,184
[E04  1384/1548 G   6027|CLM] train=2.6475  mask=15.1%  norm=0.691  lr=1.79e-04  dt=  36.6ms  words=49,381,376
[E04  1385/1548 G   6028|CLM] train=2.4781  mask=15.1%  norm=0.811  lr=1.79e-04  dt=  36.3ms  words=49,389,568
[E04  1386/1548 G   6029|CLM] train=4.3866  mask=15.1%  norm=0.792  lr=1.79e-04  dt=  36.6ms  words=49,397,760
[E04  1387/1548 G   6030|CLM] train=4.4494  mask=15.1%  norm=0.765  lr=1.79e-04  dt=  36.5ms  words=49,405,952
[E04  1388/1548 G   6031|CLM] train=4.1011  mask=15.1%  norm=0.848  lr=1.79e-04  dt=  36.5ms  words=49,414,144
[E04  1389/1548 G   6032|CLM] train=4.4113  mask=15.1%  norm=0.947  lr=1.79e-04  dt=  36.7ms  words=49,422,336
[E04  1390/1548 G   6033|CLM] train=2.2270  mask=15.1%  norm=0.737  lr=1.79e-04  dt=  36.5ms  words=49,430,528
[E04  1391/1548 G   6034|CLM] train=2.3093  mask=15.1%  norm=0.693  lr=1.79e-04  dt=  36.6ms  words=49,438,720
[E04  1392/1548 G   6035|CLM] train=4.7772  mask=15.1%  norm=0.825  lr=1.79e-04  dt=  36.7ms  words=49,446,912
[E04  1393/1548 G   6036|CLM] train=2.7646  mask=15.1%  norm=0.708  lr=1.79e-04  dt=  36.5ms  words=49,455,104
[E04  1394/1548 G   6037|CLM] train=2.5244  mask=15.1%  norm=0.599  lr=1.79e-04  dt=  36.5ms  words=49,463,296
[E04  1395/1548 G   6038|CLM] train=4.9696  mask=15.1%  norm=1.274  lr=1.79e-04  dt=  36.5ms  words=49,471,488
[E04  1396/1548 G   6039|CLM] train=2.9462  mask=15.1%  norm=1.140  lr=1.79e-04  dt=  36.4ms  words=49,479,680
[E04  1397/1548 G   6040|CLM] train=3.8528  mask=15.1%  norm=0.895  lr=1.79e-04  dt=  36.7ms  words=49,487,872
[E04  1398/1548 G   6041|CLM] train=2.9447  mask=15.1%  norm=0.686  lr=1.79e-04  dt=  36.5ms  words=49,496,064
[E04  1399/1548 G   6042|CLM] train=5.1117  mask=15.1%  norm=1.120  lr=1.79e-04  dt=  36.6ms  words=49,504,256
[E04  1400/1548 G   6043|CLM] train=3.9379  mask=15.1%  norm=0.730  lr=1.79e-04  dt=  36.6ms  words=49,512,448
[E04  1401/1548 G   6044|CLM] train=4.3381  mask=15.1%  norm=0.723  lr=1.79e-04  dt=  37.4ms  words=49,520,640
[E04  1402/1548 G   6045|CLM] train=4.4646  mask=15.1%  norm=0.735  lr=1.79e-04  dt=  36.5ms  words=49,528,832
[E04  1403/1548 G   6046|CLM] train=2.3372  mask=15.1%  norm=0.663  lr=1.79e-04  dt=  36.5ms  words=49,537,024
[E04  1404/1548 G   6047|CLM] train=2.3728  mask=15.1%  norm=0.689  lr=1.78e-04  dt=  36.4ms  words=49,545,216
[E04  1405/1548 G   6048|CLM] train=4.3593  mask=15.1%  norm=0.975  lr=1.78e-04  dt=  36.5ms  words=49,553,408
[E04  1406/1548 G   6049|CLM] train=4.5860  mask=15.1%  norm=1.058  lr=1.78e-04  dt=  36.6ms  words=49,561,600
[E04  1407/1548 G   6050|CLM] train=4.0534  mask=15.1%  norm=0.844  lr=1.78e-04  dt=  36.7ms  words=49,569,792
[E04  1408/1548 G   6051|CLM] train=5.3836  mask=15.1%  norm=0.919  lr=1.78e-04  dt=  36.4ms  words=49,577,984
[E04  1409/1548 G   6052|CLM] train=4.6499  mask=15.1%  norm=0.923  lr=1.78e-04  dt=  36.3ms  words=49,586,176
[E04  1410/1548 G   6053|CLM] train=1.9189  mask=15.1%  norm=0.650  lr=1.78e-04  dt=  36.4ms  words=49,594,368
[E04  1411/1548 G   6054|CLM] train=4.0718  mask=15.1%  norm=0.710  lr=1.78e-04  dt=  36.6ms  words=49,602,560
[E04  1412/1548 G   6055|CLM] train=5.0707  mask=15.1%  norm=1.000  lr=1.78e-04  dt=  36.6ms  words=49,610,752
[E04  1413/1548 G   6056|CLM] train=2.3326  mask=15.1%  norm=0.667  lr=1.78e-04  dt=  36.4ms  words=49,618,944
[E04  1414/1548 G   6057|CLM] train=2.6266  mask=15.1%  norm=0.609  lr=1.78e-04  dt=  36.7ms  words=49,627,136
[E04  1415/1548 G   6058|CLM] train=4.3969  mask=15.1%  norm=0.849  lr=1.78e-04  dt=  36.6ms  words=49,635,328
[E04  1416/1548 G   6059|CLM] train=4.2984  mask=15.1%  norm=0.924  lr=1.78e-04  dt=  36.5ms  words=49,643,520
[E04  1417/1548 G   6060|CLM] train=4.8592  mask=15.1%  norm=0.942  lr=1.78e-04  dt=  36.7ms  words=49,651,712
[E04  1418/1548 G   6061|CLM] train=4.3122  mask=15.1%  norm=0.850  lr=1.78e-04  dt=  36.7ms  words=49,659,904
[E04  1419/1548 G   6062|CLM] train=2.4827  mask=15.1%  norm=0.884  lr=1.78e-04  dt=  36.6ms  words=49,668,096
[E04  1420/1548 G   6063|CLM] train=1.8814  mask=15.1%  norm=0.755  lr=1.78e-04  dt=  36.4ms  words=49,676,288
[E04  1421/1548 G   6064|CLM] train=4.5703  mask=15.1%  norm=0.783  lr=1.78e-04  dt=  36.4ms  words=49,684,480
[E04  1422/1548 G   6065|CLM] train=4.6651  mask=15.1%  norm=1.156  lr=1.78e-04  dt=  36.4ms  words=49,692,672
[E04  1423/1548 G   6066|CLM] train=2.3307  mask=15.1%  norm=0.623  lr=1.78e-04  dt=  36.6ms  words=49,700,864
[E04  1424/1548 G   6067|CLM] train=4.3405  mask=15.1%  norm=0.935  lr=1.78e-04  dt=  36.4ms  words=49,709,056
[E04  1425/1548 G   6068|CLM] train=4.3751  mask=15.1%  norm=0.871  lr=1.78e-04  dt=  36.6ms  words=49,717,248
[E04  1426/1548 G   6069|CLM] train=2.4842  mask=15.1%  norm=0.806  lr=1.78e-04  dt=  36.5ms  words=49,725,440
[E04  1427/1548 G   6070|CLM] train=4.2812  mask=15.1%  norm=0.736  lr=1.78e-04  dt=  36.6ms  words=49,733,632
[E04  1428/1548 G   6071|CLM] train=2.7451  mask=15.1%  norm=0.675  lr=1.78e-04  dt=  36.6ms  words=49,741,824
[E04  1429/1548 G   6072|CLM] train=5.1583  mask=15.1%  norm=1.729  lr=1.78e-04  dt=  36.5ms  words=49,750,016
[E04  1430/1548 G   6073|CLM] train=2.4208  mask=15.1%  norm=0.633  lr=1.77e-04  dt=  36.7ms  words=49,758,208
[E04  1431/1548 G   6074|CLM] train=2.3145  mask=15.1%  norm=1.036  lr=1.77e-04  dt=  36.6ms  words=49,766,400
[E04  1432/1548 G   6075|CLM] train=2.3117  mask=15.1%  norm=0.585  lr=1.77e-04  dt=  36.5ms  words=49,774,592
[E04  1433/1548 G   6076|CLM] train=3.6521  mask=15.1%  norm=0.799  lr=1.77e-04  dt=  36.7ms  words=49,782,784
[E04  1434/1548 G   6077|CLM] train=4.0112  mask=15.1%  norm=0.865  lr=1.77e-04  dt=  36.5ms  words=49,790,976
[E04  1435/1548 G   6078|CLM] train=4.6408  mask=15.1%  norm=0.914  lr=1.77e-04  dt=  36.5ms  words=49,799,168
[E04  1436/1548 G   6079|CLM] train=4.0223  mask=15.1%  norm=0.827  lr=1.77e-04  dt=  36.4ms  words=49,807,360
[E04  1437/1548 G   6080|CLM] train=4.1627  mask=15.1%  norm=0.830  lr=1.77e-04  dt=  36.5ms  words=49,815,552
[E04  1438/1548 G   6081|CLM] train=2.4633  mask=15.1%  norm=0.988  lr=1.77e-04  dt=  36.4ms  words=49,823,744
[E04  1439/1548 G   6082|CLM] train=4.0398  mask=15.1%  norm=0.732  lr=1.77e-04  dt=  37.7ms  words=49,831,936
[E04  1440/1548 G   6083|CLM] train=4.1200  mask=15.1%  norm=0.718  lr=1.77e-04  dt=  36.4ms  words=49,840,128
[E04  1441/1548 G   6084|CLM] train=4.6348  mask=15.1%  norm=0.753  lr=1.77e-04  dt=  38.3ms  words=49,848,320
[E04  1442/1548 G   6085|CLM] train=4.5232  mask=15.1%  norm=1.057  lr=1.77e-04  dt=  37.8ms  words=49,856,512
[E04  1443/1548 G   6086|CLM] train=4.4027  mask=15.1%  norm=0.725  lr=1.77e-04  dt=  37.4ms  words=49,864,704
[E04  1444/1548 G   6087|CLM] train=4.3337  mask=15.1%  norm=0.836  lr=1.77e-04  dt=  37.1ms  words=49,872,896
[E04  1445/1548 G   6088|CLM] train=2.2631  mask=15.1%  norm=0.890  lr=1.77e-04  dt=  36.9ms  words=49,881,088
[E04  1446/1548 G   6089|CLM] train=4.2862  mask=15.1%  norm=0.711  lr=1.77e-04  dt=  37.1ms  words=49,889,280
[E04  1447/1548 G   6090|CLM] train=5.1459  mask=15.1%  norm=1.643  lr=1.77e-04  dt=  37.1ms  words=49,897,472
[E04  1448/1548 G   6091|CLM] train=3.9456  mask=15.1%  norm=0.887  lr=1.77e-04  dt=  37.2ms  words=49,905,664
[E04  1449/1548 G   6092|CLM] train=2.3026  mask=15.1%  norm=0.826  lr=1.77e-04  dt=  37.5ms  words=49,913,856
[E04  1450/1548 G   6093|CLM] train=2.4077  mask=15.1%  norm=0.815  lr=1.77e-04  dt=  37.3ms  words=49,922,048
[E04  1451/1548 G   6094|CLM] train=3.6826  mask=15.1%  norm=0.649  lr=1.77e-04  dt=  37.8ms  words=49,930,240
[E04  1452/1548 G   6095|CLM] train=4.0858  mask=15.1%  norm=0.906  lr=1.77e-04  dt=  37.8ms  words=49,938,432
[E04  1453/1548 G   6096|CLM] train=2.3255  mask=15.1%  norm=0.580  lr=1.77e-04  dt=  37.2ms  words=49,946,624
[E04  1454/1548 G   6097|CLM] train=4.3054  mask=15.1%  norm=1.030  lr=1.77e-04  dt=  37.0ms  words=49,954,816
[E04  1455/1548 G   6098|CLM] train=5.0407  mask=15.1%  norm=0.857  lr=1.77e-04  dt=  37.0ms  words=49,963,008
[E04  1456/1548 G   6099|CLM] train=4.5699  mask=15.1%  norm=0.758  lr=1.76e-04  dt=  36.9ms  words=49,971,200
[E04  1457/1548 G   6100|CLM] train=5.0998  mask=15.1%  norm=0.859  lr=1.76e-04  dt=  37.0ms  words=49,979,392
[E04  1458/1548 G   6101|CLM] train=4.0757  mask=15.1%  norm=0.866  lr=1.76e-04  dt=  37.0ms  words=49,987,584
[E04  1459/1548 G   6102|CLM] train=2.5627  mask=15.1%  norm=0.678  lr=1.76e-04  dt=  37.0ms  words=49,995,776
[E04  1460/1548 G   6103|CLM] train=4.8104  mask=15.1%  norm=0.788  lr=1.76e-04  dt=  36.8ms  words=50,003,968

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_50M'...
[Checkpoint] Checkpoint 'chck_50M' successfully saved.
[E04  1461/1548 G   6104|CLM] train=4.2953  mask=15.1%  norm=0.752  lr=1.76e-04  dt=  38.4ms  words=50,012,160
[E04  1462/1548 G   6105|CLM] train=3.8550  mask=15.1%  norm=0.775  lr=1.76e-04  dt=  37.2ms  words=50,020,352
[E04  1463/1548 G   6106|CLM] train=4.7907  mask=15.1%  norm=1.176  lr=1.76e-04  dt=  36.9ms  words=50,028,544
[E04  1464/1548 G   6107|CLM] train=4.2717  mask=15.1%  norm=0.690  lr=1.76e-04  dt=  37.1ms  words=50,036,736
[E04  1465/1548 G   6108|CLM] train=3.6457  mask=15.1%  norm=0.753  lr=1.76e-04  dt=  37.0ms  words=50,044,928
[E04  1466/1548 G   6109|CLM] train=4.2548  mask=15.1%  norm=0.879  lr=1.76e-04  dt=  36.9ms  words=50,053,120
[E04  1467/1548 G   6110|CLM] train=2.2034  mask=15.1%  norm=0.757  lr=1.76e-04  dt=  37.1ms  words=50,061,312
[E04  1468/1548 G   6111|CLM] train=4.0860  mask=15.1%  norm=0.692  lr=1.76e-04  dt=  37.0ms  words=50,069,504
[E04  1469/1548 G   6112|CLM] train=3.7070  mask=15.1%  norm=0.657  lr=1.76e-04  dt=  37.0ms  words=50,077,696
[E04  1470/1548 G   6113|CLM] train=4.1786  mask=15.1%  norm=1.322  lr=1.76e-04  dt=  36.9ms  words=50,085,888
[E04  1471/1548 G   6114|CLM] train=4.2613  mask=15.1%  norm=0.718  lr=1.76e-04  dt=  37.0ms  words=50,094,080
[E04  1472/1548 G   6115|CLM] train=4.1772  mask=15.1%  norm=0.636  lr=1.76e-04  dt=  36.9ms  words=50,102,272
[E04  1473/1548 G   6116|CLM] train=4.1285  mask=15.1%  norm=0.919  lr=1.76e-04  dt=  36.9ms  words=50,110,464
[E04  1474/1548 G   6117|CLM] train=4.5876  mask=15.1%  norm=0.981  lr=1.76e-04  dt=  36.9ms  words=50,118,656
[E04  1475/1548 G   6118|CLM] train=3.6737  mask=15.1%  norm=0.683  lr=1.76e-04  dt=  37.0ms  words=50,126,848
[E04  1476/1548 G   6119|CLM] train=4.2810  mask=15.1%  norm=0.715  lr=1.76e-04  dt=  37.0ms  words=50,135,040
[E04  1477/1548 G   6120|CLM] train=2.3588  mask=15.1%  norm=1.136  lr=1.76e-04  dt=  36.9ms  words=50,143,232
[E04  1478/1548 G   6121|CLM] train=5.1836  mask=15.1%  norm=5.109  lr=1.76e-04  dt=  36.8ms  words=50,151,424
[E04  1479/1548 G   6122|CLM] train=5.9078  mask=15.1%  norm=1.515  lr=1.76e-04  dt=  36.9ms  words=50,159,616
[E04  1480/1548 G   6123|CLM] train=4.4999  mask=15.1%  norm=0.969  lr=1.76e-04  dt=  37.1ms  words=50,167,808
[E04  1481/1548 G   6124|CLM] train=3.5556  mask=15.1%  norm=0.662  lr=1.76e-04  dt=  36.9ms  words=50,176,000
[E04  1482/1548 G   6125|CLM] train=2.8519  mask=15.1%  norm=0.901  lr=1.75e-04  dt=  36.9ms  words=50,184,192
[E04  1483/1548 G   6126|CLM] train=2.4996  mask=15.1%  norm=0.599  lr=1.75e-04  dt=  36.9ms  words=50,192,384
[E04  1484/1548 G   6127|CLM] train=4.4568  mask=15.1%  norm=1.783  lr=1.75e-04  dt=  37.0ms  words=50,200,576
[E04  1485/1548 G   6128|CLM] train=2.3173  mask=15.1%  norm=0.674  lr=1.75e-04  dt=  36.8ms  words=50,208,768
[E04  1486/1548 G   6129|CLM] train=5.4028  mask=15.1%  norm=4.685  lr=1.75e-04  dt=  36.9ms  words=50,216,960
[E04  1487/1548 G   6130|CLM] train=2.1366  mask=15.1%  norm=0.821  lr=1.75e-04  dt=  36.8ms  words=50,225,152
[E04  1488/1548 G   6131|CLM] train=2.6640  mask=15.0%  norm=0.670  lr=1.75e-04  dt=  37.3ms  words=50,233,344
[E04  1489/1548 G   6132|CLM] train=4.5513  mask=15.0%  norm=0.968  lr=1.75e-04  dt=  36.8ms  words=50,241,536
[E04  1490/1548 G   6133|CLM] train=2.2502  mask=15.0%  norm=0.588  lr=1.75e-04  dt=  36.9ms  words=50,249,728
[E04  1491/1548 G   6134|CLM] train=4.3148  mask=15.0%  norm=0.826  lr=1.75e-04  dt=  36.8ms  words=50,257,920
[E04  1492/1548 G   6135|CLM] train=2.5781  mask=15.0%  norm=0.894  lr=1.75e-04  dt=  36.9ms  words=50,266,112
[E04  1493/1548 G   6136|CLM] train=2.5332  mask=15.0%  norm=1.967  lr=1.75e-04  dt=  36.7ms  words=50,274,304
[E04  1494/1548 G   6137|CLM] train=4.6551  mask=15.0%  norm=0.827  lr=1.75e-04  dt=  36.9ms  words=50,282,496
[E04  1495/1548 G   6138|CLM] train=2.2752  mask=15.0%  norm=0.654  lr=1.75e-04  dt=  36.9ms  words=50,290,688
[E04  1496/1548 G   6139|CLM] train=4.2415  mask=15.0%  norm=1.308  lr=1.75e-04  dt=  37.2ms  words=50,298,880
[E04  1497/1548 G   6140|CLM] train=3.9687  mask=15.0%  norm=1.120  lr=1.75e-04  dt=  36.8ms  words=50,307,072
[E04  1498/1548 G   6141|CLM] train=4.5838  mask=15.0%  norm=1.036  lr=1.75e-04  dt=  36.9ms  words=50,315,264
[E04  1499/1548 G   6142|CLM] train=4.6193  mask=15.0%  norm=0.846  lr=1.75e-04  dt=  36.9ms  words=50,323,456
[E04  1500/1548 G   6143|CLM] train=2.5808  mask=15.0%  norm=1.083  lr=1.75e-04  dt=  37.0ms  words=50,331,648
[E04  1501/1548 G   6144|CLM] train=2.4484  mask=15.0%  norm=0.796  lr=1.75e-04  dt=  36.8ms  words=50,339,840
[E04  1502/1548 G   6145|CLM] train=3.8933  mask=15.0%  norm=0.690  lr=1.75e-04  dt=  37.1ms  words=50,348,032
[E04  1503/1548 G   6146|CLM] train=2.5082  mask=15.0%  norm=0.901  lr=1.75e-04  dt=  36.8ms  words=50,356,224
[E04  1504/1548 G   6147|CLM] train=4.0602  mask=15.0%  norm=0.872  lr=1.75e-04  dt=  37.0ms  words=50,364,416
[E04  1505/1548 G   6148|CLM] train=4.5158  mask=15.0%  norm=0.822  lr=1.75e-04  dt=  36.9ms  words=50,372,608
[E04  1506/1548 G   6149|CLM] train=2.7575  mask=15.0%  norm=0.718  lr=1.75e-04  dt=  36.9ms  words=50,380,800
[E04  1507/1548 G   6150|CLM] train=4.4713  mask=15.0%  norm=0.794  lr=1.75e-04  dt=  36.9ms  words=50,388,992
[E04  1508/1548 G   6151|CLM] train=4.3461  mask=15.0%  norm=0.835  lr=1.75e-04  dt=  37.0ms  words=50,397,184
[E04  1509/1548 G   6152|CLM] train=2.4941  mask=15.0%  norm=0.651  lr=1.74e-04  dt=  36.8ms  words=50,405,376
[E04  1510/1548 G   6153|CLM] train=4.8475  mask=15.0%  norm=0.788  lr=1.74e-04  dt=  36.9ms  words=50,413,568
[E04  1511/1548 G   6154|CLM] train=5.2714  mask=15.0%  norm=2.443  lr=1.74e-04  dt=  36.9ms  words=50,421,760
[E04  1512/1548 G   6155|CLM] train=4.6497  mask=15.0%  norm=0.809  lr=1.74e-04  dt=  37.0ms  words=50,429,952
[E04  1513/1548 G   6156|CLM] train=4.0063  mask=15.0%  norm=0.732  lr=1.74e-04  dt=  36.8ms  words=50,438,144
[E04  1514/1548 G   6157|CLM] train=2.4738  mask=15.0%  norm=0.854  lr=1.74e-04  dt=  37.0ms  words=50,446,336
[E04  1515/1548 G   6158|CLM] train=4.5930  mask=15.0%  norm=0.878  lr=1.74e-04  dt=  37.1ms  words=50,454,528
[E04  1516/1548 G   6159|CLM] train=2.4361  mask=15.0%  norm=1.235  lr=1.74e-04  dt=  37.3ms  words=50,462,720
[E04  1517/1548 G   6160|CLM] train=4.2444  mask=15.0%  norm=0.825  lr=1.74e-04  dt=  36.7ms  words=50,470,912
[E04  1518/1548 G   6161|CLM] train=2.6130  mask=15.0%  norm=0.684  lr=1.74e-04  dt=  36.8ms  words=50,479,104
[E04  1519/1548 G   6162|CLM] train=2.7665  mask=15.0%  norm=0.909  lr=1.74e-04  dt=  36.8ms  words=50,487,296
[E04  1520/1548 G   6163|CLM] train=2.2462  mask=15.0%  norm=0.742  lr=1.74e-04  dt=  37.0ms  words=50,495,488
[E04  1521/1548 G   6164|CLM] train=2.7800  mask=15.0%  norm=0.621  lr=1.74e-04  dt=  36.8ms  words=50,503,680
[E04  1522/1548 G   6165|CLM] train=3.8505  mask=15.0%  norm=0.998  lr=1.74e-04  dt=  37.0ms  words=50,511,872
[E04  1523/1548 G   6166|CLM] train=4.9763  mask=15.0%  norm=0.932  lr=1.74e-04  dt=  36.9ms  words=50,520,064
[E04  1524/1548 G   6167|CLM] train=2.5038  mask=15.0%  norm=0.671  lr=1.74e-04  dt=  37.0ms  words=50,528,256
[E04  1525/1548 G   6168|CLM] train=4.9422  mask=15.0%  norm=1.035  lr=1.74e-04  dt=  36.8ms  words=50,536,448
[E04  1526/1548 G   6169|CLM] train=2.1933  mask=15.0%  norm=0.902  lr=1.74e-04  dt=  36.8ms  words=50,544,640
[E04  1527/1548 G   6170|CLM] train=4.5149  mask=15.0%  norm=0.770  lr=1.74e-04  dt=  37.0ms  words=50,552,832
[E04  1528/1548 G   6171|CLM] train=4.2006  mask=15.0%  norm=0.832  lr=1.74e-04  dt=  37.0ms  words=50,561,024
[E04  1529/1548 G   6172|CLM] train=2.0698  mask=15.0%  norm=0.630  lr=1.74e-04  dt=  37.1ms  words=50,569,216
[E04  1530/1548 G   6173|CLM] train=3.5570  mask=15.0%  norm=0.860  lr=1.74e-04  dt=  38.0ms  words=50,577,408
[E04  1531/1548 G   6174|CLM] train=2.4672  mask=15.0%  norm=0.857  lr=1.74e-04  dt=  39.0ms  words=50,585,600
[E04  1532/1548 G   6175|CLM] train=2.9072  mask=15.0%  norm=0.868  lr=1.74e-04  dt=  38.6ms  words=50,593,792
[E04  1533/1548 G   6176|CLM] train=4.8466  mask=15.0%  norm=0.791  lr=1.74e-04  dt=  38.2ms  words=50,601,984
[E04  1534/1548 G   6177|CLM] train=2.0909  mask=15.0%  norm=0.837  lr=1.74e-04  dt=  37.9ms  words=50,610,176
[E04  1535/1548 G   6178|CLM] train=2.1458  mask=15.0%  norm=0.711  lr=1.73e-04  dt=  38.7ms  words=50,618,368
[E04  1536/1548 G   6179|CLM] train=2.7766  mask=15.0%  norm=0.679  lr=1.73e-04  dt=  37.8ms  words=50,626,560
[E04  1537/1548 G   6180|CLM] train=2.9645  mask=15.0%  norm=0.788  lr=1.73e-04  dt= 450.8ms  words=50,634,752
[E04  1538/1548 G   6181|CLM] train=3.6354  mask=15.0%  norm=0.748  lr=1.73e-04  dt=  37.9ms  words=50,642,944
[E04  1539/1548 G   6182|CLM] train=4.7908  mask=15.0%  norm=1.146  lr=1.73e-04  dt=  37.7ms  words=50,651,136
[E04  1540/1548 G   6183|CLM] train=2.6633  mask=15.0%  norm=1.295  lr=1.73e-04  dt=  37.2ms  words=50,659,328
[E04  1541/1548 G   6184|CLM] train=2.5991  mask=15.0%  norm=0.582  lr=1.73e-04  dt=  36.9ms  words=50,667,520
[E04  1542/1548 G   6185|CLM] train=2.2862  mask=15.0%  norm=0.847  lr=1.73e-04  dt=  37.1ms  words=50,675,712
[E04  1543/1548 G   6186|CLM] train=2.1351  mask=15.0%  norm=0.865  lr=1.73e-04  dt=  36.7ms  words=50,683,904
[E04  1544/1548 G   6187|CLM] train=2.5854  mask=15.0%  norm=0.816  lr=1.73e-04  dt=  37.1ms  words=50,692,096
[E04  1545/1548 G   6188|CLM] train=2.3721  mask=15.0%  norm=0.753  lr=1.73e-04  dt=  36.8ms  words=50,700,288
[E04  1546/1548 G   6189|CLM] train=2.8019  mask=15.0%  norm=0.695  lr=1.73e-04  dt=  36.9ms  words=50,708,480
[E04  1547/1548 G   6190|CLM] train=4.8402  mask=15.0%  norm=0.910  lr=1.73e-04  dt=  37.0ms  words=50,716,672
[E04  1548/1548 G   6191|CLM] train=4.0334  mask=15.0%  norm=0.845  lr=1.73e-04  dt=  36.7ms  words=50,724,864
[E05     1/1548 G   6192|CLM] train=5.5879  mask=15.0%  norm=1.735  lr=1.73e-04  dt=  36.8ms  words=50,733,056
[E05     2/1548 G   6193|CLM] train=2.2217  mask=15.0%  norm=0.738  lr=1.73e-04  dt=  37.1ms  words=50,741,248
[E05     3/1548 G   6194|CLM] train=4.3379  mask=15.0%  norm=0.798  lr=1.73e-04  dt=  36.6ms  words=50,749,440
[E05     4/1548 G   6195|CLM] train=4.1730  mask=15.0%  norm=0.780  lr=1.73e-04  dt=  36.9ms  words=50,757,632
[E05     5/1548 G   6196|CLM] train=2.2623  mask=15.0%  norm=0.662  lr=1.73e-04  dt=  37.0ms  words=50,765,824
[E05     6/1548 G   6197|CLM] train=2.4789  mask=15.0%  norm=0.747  lr=1.73e-04  dt=  36.9ms  words=50,774,016
[E05     7/1548 G   6198|CLM] train=2.6739  mask=15.0%  norm=0.652  lr=1.73e-04  dt=  36.9ms  words=50,782,208
[E05     8/1548 G   6199|CLM] train=2.1826  mask=15.0%  norm=0.603  lr=1.73e-04  dt=  36.9ms  words=50,790,400
[E05     9/1548 G   6200|CLM] train=4.5786  mask=15.0%  norm=1.166  lr=1.73e-04  dt=  36.9ms  words=50,798,592
[E05    10/1548 G   6201|CLM] train=2.4346  mask=15.0%  norm=0.781  lr=1.73e-04  dt=  37.1ms  words=50,806,784
[E05    11/1548 G   6202|CLM] train=2.2073  mask=15.0%  norm=0.794  lr=1.73e-04  dt=  36.8ms  words=50,814,976
[E05    12/1548 G   6203|CLM] train=4.3076  mask=15.0%  norm=1.136  lr=1.73e-04  dt=  36.8ms  words=50,823,168
[E05    13/1548 G   6204|CLM] train=2.6726  mask=15.0%  norm=0.658  lr=1.72e-04  dt=  37.2ms  words=50,831,360
[E05    14/1548 G   6205|CLM] train=3.5308  mask=15.0%  norm=0.868  lr=1.72e-04  dt=  37.0ms  words=50,839,552
[E05    15/1548 G   6206|CLM] train=2.4128  mask=15.0%  norm=1.003  lr=1.72e-04  dt=  36.8ms  words=50,847,744
[E05    16/1548 G   6207|CLM] train=4.4240  mask=15.0%  norm=1.625  lr=1.72e-04  dt=  36.7ms  words=50,855,936
[E05    17/1548 G   6208|CLM] train=2.4786  mask=15.0%  norm=1.021  lr=1.72e-04  dt=  37.0ms  words=50,864,128
[E05    18/1548 G   6209|CLM] train=2.4256  mask=15.0%  norm=0.712  lr=1.72e-04  dt=  36.9ms  words=50,872,320
[E05    19/1548 G   6210|CLM] train=5.0869  mask=15.0%  norm=1.534  lr=1.72e-04  dt=  36.9ms  words=50,880,512
[E05    20/1548 G   6211|CLM] train=3.9085  mask=15.0%  norm=0.884  lr=1.72e-04  dt=  36.8ms  words=50,888,704
[E05    21/1548 G   6212|CLM] train=4.8892  mask=15.0%  norm=0.846  lr=1.72e-04  dt=  37.0ms  words=50,896,896
[E05    22/1548 G   6213|CLM] train=4.1395  mask=15.0%  norm=0.833  lr=1.72e-04  dt=  36.9ms  words=50,905,088
[E05    23/1548 G   6214|CLM] train=4.6983  mask=15.0%  norm=0.964  lr=1.72e-04  dt=  36.9ms  words=50,913,280
[E05    24/1548 G   6215|CLM] train=4.2698  mask=15.0%  norm=0.775  lr=1.72e-04  dt=  36.8ms  words=50,921,472
[E05    25/1548 G   6216|CLM] train=2.7871  mask=15.0%  norm=0.888  lr=1.72e-04  dt=  37.0ms  words=50,929,664
[E05    26/1548 G   6217|CLM] train=4.6398  mask=15.0%  norm=1.000  lr=1.72e-04  dt=  37.0ms  words=50,937,856
[E05    27/1548 G   6218|CLM] train=2.2120  mask=15.0%  norm=0.864  lr=1.72e-04  dt=  36.9ms  words=50,946,048
[E05    28/1548 G   6219|CLM] train=4.7712  mask=15.0%  norm=0.963  lr=1.72e-04  dt=  36.8ms  words=50,954,240
[E05    29/1548 G   6220|CLM] train=3.9923  mask=15.0%  norm=1.049  lr=1.72e-04  dt=  36.9ms  words=50,962,432
[E05    30/1548 G   6221|CLM] train=3.5373  mask=15.0%  norm=0.687  lr=1.72e-04  dt=  37.0ms  words=50,970,624
[E05    31/1548 G   6222|CLM] train=4.1793  mask=15.0%  norm=1.017  lr=1.72e-04  dt=  37.0ms  words=50,978,816
[E05    32/1548 G   6223|CLM] train=4.6063  mask=15.0%  norm=1.125  lr=1.72e-04  dt=  36.9ms  words=50,987,008
[E05    33/1548 G   6224|CLM] train=4.2009  mask=15.0%  norm=1.377  lr=1.72e-04  dt=  36.9ms  words=50,995,200
[E05    34/1548 G   6225|CLM] train=4.2618  mask=15.0%  norm=1.062  lr=1.72e-04  dt=  37.0ms  words=51,003,392
[E05    35/1548 G   6226|CLM] train=4.0853  mask=15.0%  norm=0.803  lr=1.72e-04  dt=  36.9ms  words=51,011,584
[E05    36/1548 G   6227|CLM] train=4.1061  mask=15.0%  norm=0.701  lr=1.72e-04  dt=  36.9ms  words=51,019,776
[E05    37/1548 G   6228|CLM] train=4.4299  mask=15.0%  norm=0.723  lr=1.72e-04  dt=  37.0ms  words=51,027,968
[E05    38/1548 G   6229|CLM] train=4.6576  mask=15.0%  norm=0.785  lr=1.72e-04  dt=  37.0ms  words=51,036,160
[E05    39/1548 G   6230|CLM] train=3.6592  mask=15.0%  norm=1.574  lr=1.71e-04  dt=  36.9ms  words=51,044,352
[E05    40/1548 G   6231|CLM] train=5.1459  mask=15.0%  norm=0.967  lr=1.71e-04  dt=  36.8ms  words=51,052,544
[E05    41/1548 G   6232|CLM] train=3.6861  mask=15.0%  norm=0.730  lr=1.71e-04  dt=  36.9ms  words=51,060,736
[E05    42/1548 G   6233|CLM] train=2.4284  mask=15.0%  norm=0.706  lr=1.71e-04  dt=  37.0ms  words=51,068,928
[E05    43/1548 G   6234|CLM] train=3.8214  mask=15.0%  norm=0.801  lr=1.71e-04  dt=  36.9ms  words=51,077,120
[E05    44/1548 G   6235|CLM] train=4.1808  mask=15.0%  norm=0.717  lr=1.71e-04  dt=  36.9ms  words=51,085,312
[E05    45/1548 G   6236|CLM] train=4.0354  mask=15.0%  norm=0.743  lr=1.71e-04  dt=  36.9ms  words=51,093,504
[E05    46/1548 G   6237|CLM] train=3.8862  mask=15.0%  norm=0.692  lr=1.71e-04  dt=  36.9ms  words=51,101,696
[E05    47/1548 G   6238|CLM] train=2.7347  mask=15.0%  norm=0.656  lr=1.71e-04  dt=  36.9ms  words=51,109,888
[E05    48/1548 G   6239|CLM] train=2.3437  mask=15.0%  norm=0.776  lr=1.71e-04  dt=  37.0ms  words=51,118,080
[E05    49/1548 G   6240|CLM] train=3.9772  mask=15.0%  norm=1.018  lr=1.71e-04  dt=  36.9ms  words=51,126,272
[E05    50/1548 G   6241|CLM] train=4.3138  mask=15.0%  norm=1.075  lr=1.71e-04  dt=  37.0ms  words=51,134,464
[E05    51/1548 G   6242|CLM] train=3.7035  mask=15.0%  norm=0.766  lr=1.71e-04  dt=  36.9ms  words=51,142,656
[E05    52/1548 G   6243|CLM] train=4.6605  mask=15.0%  norm=0.972  lr=1.71e-04  dt=  36.7ms  words=51,150,848
[E05    53/1548 G   6244|CLM] train=4.5820  mask=15.0%  norm=0.916  lr=1.71e-04  dt=  36.9ms  words=51,159,040
[E05    54/1548 G   6245|CLM] train=2.2464  mask=15.0%  norm=0.695  lr=1.71e-04  dt=  37.0ms  words=51,167,232
[E05    55/1548 G   6246|CLM] train=5.7254  mask=15.0%  norm=1.552  lr=1.71e-04  dt=  36.8ms  words=51,175,424
[E05    56/1548 G   6247|CLM] train=4.3095  mask=15.0%  norm=0.830  lr=1.71e-04  dt=  36.8ms  words=51,183,616
[E05    57/1548 G   6248|CLM] train=3.8474  mask=15.0%  norm=0.753  lr=1.71e-04  dt=  36.9ms  words=51,191,808
[E05    58/1548 G   6249|CLM] train=2.4467  mask=15.0%  norm=0.586  lr=1.71e-04  dt=  36.9ms  words=51,200,000
[E05    59/1548 G   6250|CLM] train=4.1359  mask=15.0%  norm=0.780  lr=1.71e-04  dt=  36.9ms  words=51,208,192
[E05    60/1548 G   6251|CLM] train=2.1439  mask=15.0%  norm=0.819  lr=1.71e-04  dt=  36.8ms  words=51,216,384
[E05    61/1548 G   6252|CLM] train=4.4878  mask=15.0%  norm=0.878  lr=1.71e-04  dt=  37.0ms  words=51,224,576
[E05    62/1548 G   6253|CLM] train=4.2867  mask=15.0%  norm=0.823  lr=1.71e-04  dt=  37.1ms  words=51,232,768
[E05    63/1548 G   6254|CLM] train=4.0569  mask=14.9%  norm=0.756  lr=1.71e-04  dt=  36.9ms  words=51,240,960
[E05    64/1548 G   6255|CLM] train=4.0191  mask=14.9%  norm=1.339  lr=1.71e-04  dt=  37.3ms  words=51,249,152
[E05    65/1548 G   6256|CLM] train=5.1906  mask=14.9%  norm=1.145  lr=1.70e-04  dt=  36.9ms  words=51,257,344
[E05    66/1548 G   6257|CLM] train=4.4833  mask=14.9%  norm=0.786  lr=1.70e-04  dt=  36.9ms  words=51,265,536
[E05    67/1548 G   6258|CLM] train=3.9730  mask=14.9%  norm=0.863  lr=1.70e-04  dt=  36.8ms  words=51,273,728
[E05    68/1548 G   6259|CLM] train=2.2736  mask=14.9%  norm=0.660  lr=1.70e-04  dt=  36.9ms  words=51,281,920
[E05    69/1548 G   6260|CLM] train=3.9112  mask=14.9%  norm=0.997  lr=1.70e-04  dt=  36.9ms  words=51,290,112
[E05    70/1548 G   6261|CLM] train=4.8525  mask=14.9%  norm=1.140  lr=1.70e-04  dt=  37.0ms  words=51,298,304
[E05    71/1548 G   6262|CLM] train=4.5772  mask=14.9%  norm=0.903  lr=1.70e-04  dt=  37.1ms  words=51,306,496
[E05    72/1548 G   6263|CLM] train=2.7779  mask=14.9%  norm=1.055  lr=1.70e-04  dt=  36.7ms  words=51,314,688
[E05    73/1548 G   6264|CLM] train=5.0091  mask=14.9%  norm=0.904  lr=1.70e-04  dt=  36.9ms  words=51,322,880
[E05    74/1548 G   6265|CLM] train=4.2106  mask=14.9%  norm=0.934  lr=1.70e-04  dt=  37.0ms  words=51,331,072
[E05    75/1548 G   6266|CLM] train=5.0289  mask=14.9%  norm=1.140  lr=1.70e-04  dt=  36.8ms  words=51,339,264
[E05    76/1548 G   6267|CLM] train=2.2651  mask=14.9%  norm=0.739  lr=1.70e-04  dt=  36.9ms  words=51,347,456
[E05    77/1548 G   6268|CLM] train=4.7228  mask=14.9%  norm=0.973  lr=1.70e-04  dt=  36.9ms  words=51,355,648
[E05    78/1548 G   6269|CLM] train=2.3769  mask=14.9%  norm=1.001  lr=1.70e-04  dt=  36.9ms  words=51,363,840
[E05    79/1548 G   6270|CLM] train=2.3099  mask=14.9%  norm=0.704  lr=1.70e-04  dt=  36.9ms  words=51,372,032
[E05    80/1548 G   6271|CLM] train=2.5306  mask=14.9%  norm=0.717  lr=1.70e-04  dt=  36.8ms  words=51,380,224
[E05    81/1548 G   6272|CLM] train=4.3180  mask=14.9%  norm=0.849  lr=1.70e-04  dt=  36.9ms  words=51,388,416
[E05    82/1548 G   6273|CLM] train=3.9026  mask=14.9%  norm=1.454  lr=1.70e-04  dt=  36.9ms  words=51,396,608
[E05    83/1548 G   6274|CLM] train=3.8907  mask=14.9%  norm=0.820  lr=1.70e-04  dt=  37.0ms  words=51,404,800
[E05    84/1548 G   6275|CLM] train=2.4603  mask=14.9%  norm=0.704  lr=1.70e-04  dt=  36.8ms  words=51,412,992
[E05    85/1548 G   6276|CLM] train=5.1556  mask=14.9%  norm=1.153  lr=1.70e-04  dt=  37.0ms  words=51,421,184
[E05    86/1548 G   6277|CLM] train=2.8444  mask=14.9%  norm=0.782  lr=1.70e-04  dt=  37.0ms  words=51,429,376
[E05    87/1548 G   6278|CLM] train=3.8964  mask=14.9%  norm=0.701  lr=1.70e-04  dt=  36.9ms  words=51,437,568
[E05    88/1548 G   6279|CLM] train=2.0143  mask=14.9%  norm=0.667  lr=1.70e-04  dt=  36.9ms  words=51,445,760
[E05    89/1548 G   6280|CLM] train=4.0502  mask=14.9%  norm=0.697  lr=1.70e-04  dt=  37.0ms  words=51,453,952
[E05    90/1548 G   6281|CLM] train=4.4079  mask=14.9%  norm=1.021  lr=1.70e-04  dt=  37.5ms  words=51,462,144
[E05    91/1548 G   6282|CLM] train=2.5393  mask=14.9%  norm=0.862  lr=1.69e-04  dt=  37.1ms  words=51,470,336
[E05    92/1548 G   6283|CLM] train=4.7860  mask=14.9%  norm=0.948  lr=1.69e-04  dt=  37.0ms  words=51,478,528
[E05    93/1548 G   6284|CLM] train=4.2275  mask=14.9%  norm=0.832  lr=1.69e-04  dt=  37.7ms  words=51,486,720
[E05    94/1548 G   6285|CLM] train=2.2526  mask=14.9%  norm=0.649  lr=1.69e-04  dt=  36.9ms  words=51,494,912
[E05    95/1548 G   6286|CLM] train=1.9870  mask=14.9%  norm=0.936  lr=1.69e-04  dt=  37.1ms  words=51,503,104
[E05    96/1548 G   6287|CLM] train=4.5729  mask=14.9%  norm=1.100  lr=1.69e-04  dt=  36.9ms  words=51,511,296
[E05    97/1548 G   6288|CLM] train=4.8035  mask=14.9%  norm=0.932  lr=1.69e-04  dt=  36.9ms  words=51,519,488
[E05    98/1548 G   6289|CLM] train=4.4595  mask=14.9%  norm=0.786  lr=1.69e-04  dt=  36.8ms  words=51,527,680
[E05    99/1548 G   6290|CLM] train=4.2670  mask=14.9%  norm=0.764  lr=1.69e-04  dt=  37.1ms  words=51,535,872
[E05   100/1548 G   6291|CLM] train=3.9599  mask=14.9%  norm=0.809  lr=1.69e-04  dt=  37.0ms  words=51,544,064
[E05   101/1548 G   6292|CLM] train=4.7238  mask=14.9%  norm=0.860  lr=1.69e-04  dt=  37.0ms  words=51,552,256
[E05   102/1548 G   6293|CLM] train=2.3385  mask=14.9%  norm=0.745  lr=1.69e-04  dt=  36.9ms  words=51,560,448
[E05   103/1548 G   6294|CLM] train=4.7233  mask=14.9%  norm=1.095  lr=1.69e-04  dt=  37.0ms  words=51,568,640
[E05   104/1548 G   6295|CLM] train=4.8199  mask=14.9%  norm=0.994  lr=1.69e-04  dt=  36.9ms  words=51,576,832
[E05   105/1548 G   6296|CLM] train=2.6942  mask=14.9%  norm=0.777  lr=1.69e-04  dt=  39.1ms  words=51,585,024
[E05   106/1548 G   6297|CLM] train=2.3163  mask=14.9%  norm=0.854  lr=1.69e-04  dt=  38.0ms  words=51,593,216
[E05   107/1548 G   6298|CLM] train=2.7095  mask=14.9%  norm=0.999  lr=1.69e-04  dt=  38.4ms  words=51,601,408
[E05   108/1548 G   6299|CLM] train=4.3895  mask=14.9%  norm=0.823  lr=1.69e-04  dt=  38.6ms  words=51,609,600
[E05   109/1548 G   6300|CLM] train=3.9321  mask=14.9%  norm=0.882  lr=1.69e-04  dt=  37.6ms  words=51,617,792
[E05   110/1548 G   6301|CLM] train=2.3559  mask=14.9%  norm=0.708  lr=1.69e-04  dt=  42.3ms  words=51,625,984
[E05   111/1548 G   6302|CLM] train=2.7551  mask=14.9%  norm=0.652  lr=1.69e-04  dt=  37.6ms  words=51,634,176
[E05   112/1548 G   6303|CLM] train=3.9441  mask=14.9%  norm=0.726  lr=1.69e-04  dt=  37.1ms  words=51,642,368
[E05   113/1548 G   6304|CLM] train=2.5364  mask=14.9%  norm=0.622  lr=1.69e-04  dt=  37.4ms  words=51,650,560
[E05   114/1548 G   6305|CLM] train=3.9691  mask=14.9%  norm=0.711  lr=1.69e-04  dt=  37.3ms  words=51,658,752
[E05   115/1548 G   6306|CLM] train=2.4996  mask=14.9%  norm=0.886  lr=1.69e-04  dt=  37.2ms  words=51,666,944
[E05   116/1548 G   6307|CLM] train=4.0004  mask=14.9%  norm=0.760  lr=1.69e-04  dt=  37.3ms  words=51,675,136
[E05   117/1548 G   6308|CLM] train=2.7036  mask=14.9%  norm=0.641  lr=1.68e-04  dt=  37.9ms  words=51,683,328
[E05   118/1548 G   6309|CLM] train=2.3174  mask=14.9%  norm=0.875  lr=1.68e-04  dt=  38.5ms  words=51,691,520
[E05   119/1548 G   6310|CLM] train=3.4600  mask=14.9%  norm=0.660  lr=1.68e-04  dt=  38.1ms  words=51,699,712
[E05   120/1548 G   6311|CLM] train=4.2177  mask=14.9%  norm=0.935  lr=1.68e-04  dt=  36.9ms  words=51,707,904
[E05   121/1548 G   6312|CLM] train=2.5263  mask=14.9%  norm=1.015  lr=1.68e-04  dt=  37.0ms  words=51,716,096
[E05   122/1548 G   6313|CLM] train=3.6067  mask=14.9%  norm=0.703  lr=1.68e-04  dt=  36.8ms  words=51,724,288
[E05   123/1548 G   6314|CLM] train=2.2707  mask=14.9%  norm=0.798  lr=1.68e-04  dt=  37.2ms  words=51,732,480
[E05   124/1548 G   6315|CLM] train=2.3927  mask=14.9%  norm=0.607  lr=1.68e-04  dt=  37.0ms  words=51,740,672
[E05   125/1548 G   6316|CLM] train=4.2572  mask=14.9%  norm=0.744  lr=1.68e-04  dt=  36.9ms  words=51,748,864
[E05   126/1548 G   6317|CLM] train=3.7964  mask=14.9%  norm=0.652  lr=1.68e-04  dt=  37.0ms  words=51,757,056
[E05   127/1548 G   6318|CLM] train=5.0847  mask=14.9%  norm=1.008  lr=1.68e-04  dt=  36.7ms  words=51,765,248
[E05   128/1548 G   6319|CLM] train=5.5436  mask=14.9%  norm=1.030  lr=1.68e-04  dt=  36.9ms  words=51,773,440
[E05   129/1548 G   6320|CLM] train=4.1622  mask=14.9%  norm=0.684  lr=1.68e-04  dt=  37.0ms  words=51,781,632
[E05   130/1548 G   6321|CLM] train=2.8390  mask=14.9%  norm=0.824  lr=1.68e-04  dt=  37.0ms  words=51,789,824
[E05   131/1548 G   6322|CLM] train=2.4422  mask=14.9%  norm=0.678  lr=1.68e-04  dt=  37.0ms  words=51,798,016
[E05   132/1548 G   6323|CLM] train=3.7558  mask=14.9%  norm=0.850  lr=1.68e-04  dt=  36.7ms  words=51,806,208
[E05   133/1548 G   6324|CLM] train=4.7255  mask=14.9%  norm=1.012  lr=1.68e-04  dt=  37.6ms  words=51,814,400
[E05   134/1548 G   6325|CLM] train=2.2837  mask=14.9%  norm=0.747  lr=1.68e-04  dt=  37.2ms  words=51,822,592
[E05   135/1548 G   6326|CLM] train=4.0444  mask=14.9%  norm=0.693  lr=1.68e-04  dt=  37.5ms  words=51,830,784
[E05   136/1548 G   6327|CLM] train=4.8192  mask=14.9%  norm=0.847  lr=1.68e-04  dt=  37.3ms  words=51,838,976
[E05   137/1548 G   6328|CLM] train=3.5703  mask=14.9%  norm=0.690  lr=1.68e-04  dt=  47.1ms  words=51,847,168
[E05   138/1548 G   6329|CLM] train=4.1035  mask=14.9%  norm=0.891  lr=1.68e-04  dt=  42.2ms  words=51,855,360
[E05   139/1548 G   6330|CLM] train=4.2520  mask=14.9%  norm=0.843  lr=1.68e-04  dt=  37.0ms  words=51,863,552
[E05   140/1548 G   6331|CLM] train=4.1956  mask=14.9%  norm=0.867  lr=1.68e-04  dt=  37.3ms  words=51,871,744
[E05   141/1548 G   6332|CLM] train=2.3368  mask=14.9%  norm=1.218  lr=1.68e-04  dt=  37.2ms  words=51,879,936
[E05   142/1548 G   6333|CLM] train=2.2005  mask=14.9%  norm=0.683  lr=1.68e-04  dt=  43.1ms  words=51,888,128
[E05   143/1548 G   6334|CLM] train=4.6978  mask=14.9%  norm=0.979  lr=1.67e-04  dt=  41.4ms  words=51,896,320
[E05   144/1548 G   6335|CLM] train=4.9474  mask=14.9%  norm=1.180  lr=1.67e-04  dt=  38.0ms  words=51,904,512
[E05   145/1548 G   6336|CLM] train=4.3822  mask=14.9%  norm=0.992  lr=1.67e-04  dt=  38.1ms  words=51,912,704
[E05   146/1548 G   6337|CLM] train=3.8612  mask=14.9%  norm=0.991  lr=1.67e-04  dt=  37.2ms  words=51,920,896
[E05   147/1548 G   6338|CLM] train=4.6812  mask=14.9%  norm=0.991  lr=1.67e-04  dt=  36.9ms  words=51,929,088
[E05   148/1548 G   6339|CLM] train=1.9590  mask=14.9%  norm=0.675  lr=1.67e-04  dt=  36.7ms  words=51,937,280
[E05   149/1548 G   6340|CLM] train=2.5000  mask=14.9%  norm=0.794  lr=1.67e-04  dt=  37.0ms  words=51,945,472
[E05   150/1548 G   6341|CLM] train=3.5971  mask=14.9%  norm=0.676  lr=1.67e-04  dt=  37.7ms  words=51,953,664
[E05   151/1548 G   6342|CLM] train=2.2232  mask=14.9%  norm=0.721  lr=1.67e-04  dt=  37.6ms  words=51,961,856
[E05   152/1548 G   6343|CLM] train=4.0772  mask=14.9%  norm=0.730  lr=1.67e-04  dt=  37.4ms  words=51,970,048
[E05   153/1548 G   6344|CLM] train=4.7599  mask=14.9%  norm=1.078  lr=1.67e-04  dt=  37.7ms  words=51,978,240
[E05   154/1548 G   6345|CLM] train=4.1723  mask=14.9%  norm=0.782  lr=1.67e-04  dt=  37.2ms  words=51,986,432
[E05   155/1548 G   6346|CLM] train=3.4689  mask=14.9%  norm=0.683  lr=1.67e-04  dt=  38.0ms  words=51,994,624
[E05   156/1548 G   6347|CLM] train=4.5175  mask=14.9%  norm=1.003  lr=1.67e-04  dt=  37.0ms  words=52,002,816
[E05   157/1548 G   6348|CLM] train=3.9188  mask=14.9%  norm=0.851  lr=1.67e-04  dt=  37.4ms  words=52,011,008
[E05   158/1548 G   6349|CLM] train=2.6768  mask=14.9%  norm=0.890  lr=1.67e-04  dt=  37.2ms  words=52,019,200
[E05   159/1548 G   6350|CLM] train=2.3693  mask=14.9%  norm=0.692  lr=1.67e-04  dt=  37.1ms  words=52,027,392
[E05   160/1548 G   6351|CLM] train=4.7178  mask=14.9%  norm=0.875  lr=1.67e-04  dt=  36.9ms  words=52,035,584
[E05   161/1548 G   6352|CLM] train=4.7845  mask=14.9%  norm=1.229  lr=1.67e-04  dt=  37.2ms  words=52,043,776
[E05   162/1548 G   6353|CLM] train=4.0582  mask=14.9%  norm=0.833  lr=1.67e-04  dt=  36.8ms  words=52,051,968
[E05   163/1548 G   6354|CLM] train=4.1702  mask=14.9%  norm=0.802  lr=1.67e-04  dt=  37.4ms  words=52,060,160
[E05   164/1548 G   6355|CLM] train=3.8189  mask=14.9%  norm=0.856  lr=1.67e-04  dt=  37.3ms  words=52,068,352
[E05   165/1548 G   6356|CLM] train=3.7424  mask=14.9%  norm=0.743  lr=1.67e-04  dt=  37.1ms  words=52,076,544
[E05   166/1548 G   6357|CLM] train=4.1311  mask=14.9%  norm=0.848  lr=1.67e-04  dt=  36.8ms  words=52,084,736
[E05   167/1548 G   6358|CLM] train=4.6119  mask=14.9%  norm=0.907  lr=1.67e-04  dt=  37.4ms  words=52,092,928
[E05   168/1548 G   6359|CLM] train=4.1912  mask=14.9%  norm=1.260  lr=1.66e-04  dt=  37.1ms  words=52,101,120
[E05   169/1548 G   6360|CLM] train=2.7513  mask=14.9%  norm=0.666  lr=1.66e-04  dt=  37.1ms  words=52,109,312
[E05   170/1548 G   6361|CLM] train=2.3510  mask=14.9%  norm=0.780  lr=1.66e-04  dt=  37.3ms  words=52,117,504
[E05   171/1548 G   6362|CLM] train=3.9207  mask=14.9%  norm=0.917  lr=1.66e-04  dt=  38.0ms  words=52,125,696
[E05   172/1548 G   6363|CLM] train=4.2099  mask=14.9%  norm=0.842  lr=1.66e-04  dt=  37.4ms  words=52,133,888
[E05   173/1548 G   6364|CLM] train=2.3938  mask=14.9%  norm=0.768  lr=1.66e-04  dt=  37.4ms  words=52,142,080
[E05   174/1548 G   6365|CLM] train=4.3475  mask=14.9%  norm=0.834  lr=1.66e-04  dt=  37.2ms  words=52,150,272
[E05   175/1548 G   6366|CLM] train=2.1651  mask=14.9%  norm=0.674  lr=1.66e-04  dt=  37.3ms  words=52,158,464
[E05   176/1548 G   6367|CLM] train=4.5832  mask=14.9%  norm=0.875  lr=1.66e-04  dt=  37.1ms  words=52,166,656
[E05   177/1548 G   6368|CLM] train=2.1923  mask=14.9%  norm=0.991  lr=1.66e-04  dt=  37.5ms  words=52,174,848
[E05   178/1548 G   6369|CLM] train=4.8967  mask=14.9%  norm=0.889  lr=1.66e-04  dt=  37.1ms  words=52,183,040
[E05   179/1548 G   6370|CLM] train=4.1797  mask=14.9%  norm=0.852  lr=1.66e-04  dt=  37.3ms  words=52,191,232
[E05   180/1548 G   6371|CLM] train=4.6635  mask=14.9%  norm=0.921  lr=1.66e-04  dt=  37.0ms  words=52,199,424
[E05   181/1548 G   6372|CLM] train=3.7976  mask=14.9%  norm=0.882  lr=1.66e-04  dt=  37.5ms  words=52,207,616
[E05   182/1548 G   6373|CLM] train=2.5475  mask=14.9%  norm=0.838  lr=1.66e-04  dt=  37.4ms  words=52,215,808
[E05   183/1548 G   6374|CLM] train=4.5096  mask=14.9%  norm=0.869  lr=1.66e-04  dt=  37.8ms  words=52,224,000
[E05   184/1548 G   6375|CLM] train=2.3784  mask=14.9%  norm=0.726  lr=1.66e-04  dt=  37.1ms  words=52,232,192
[E05   185/1548 G   6376|CLM] train=2.8549  mask=14.9%  norm=0.877  lr=1.66e-04  dt=  37.2ms  words=52,240,384
[E05   186/1548 G   6377|CLM] train=1.9086  mask=14.9%  norm=0.619  lr=1.66e-04  dt=  37.0ms  words=52,248,576
[E05   187/1548 G   6378|CLM] train=4.3854  mask=14.8%  norm=0.857  lr=1.66e-04  dt=  37.1ms  words=52,256,768
[E05   188/1548 G   6379|CLM] train=5.1228  mask=14.8%  norm=1.114  lr=1.66e-04  dt=  37.2ms  words=52,264,960
[E05   189/1548 G   6380|CLM] train=4.4076  mask=14.8%  norm=1.036  lr=1.66e-04  dt=  36.9ms  words=52,273,152
[E05   190/1548 G   6381|CLM] train=2.2419  mask=14.8%  norm=0.870  lr=1.66e-04  dt=  36.9ms  words=52,281,344
[E05   191/1548 G   6382|CLM] train=3.8329  mask=14.8%  norm=0.695  lr=1.66e-04  dt=  37.0ms  words=52,289,536
[E05   192/1548 G   6383|CLM] train=1.9648  mask=14.8%  norm=0.711  lr=1.66e-04  dt=  37.1ms  words=52,297,728
[E05   193/1548 G   6384|CLM] train=3.9358  mask=14.8%  norm=0.873  lr=1.66e-04  dt=  37.0ms  words=52,305,920
[E05   194/1548 G   6385|CLM] train=4.1054  mask=14.8%  norm=0.798  lr=1.65e-04  dt=  37.1ms  words=52,314,112
[E05   195/1548 G   6386|CLM] train=2.3564  mask=14.8%  norm=1.111  lr=1.65e-04  dt=  37.3ms  words=52,322,304
[E05   196/1548 G   6387|CLM] train=2.2143  mask=14.8%  norm=1.022  lr=1.65e-04  dt=  36.9ms  words=52,330,496
[E05   197/1548 G   6388|CLM] train=3.9818  mask=14.8%  norm=0.943  lr=1.65e-04  dt=  37.0ms  words=52,338,688
[E05   198/1548 G   6389|CLM] train=4.6931  mask=14.8%  norm=0.954  lr=1.65e-04  dt=  37.0ms  words=52,346,880
[E05   199/1548 G   6390|CLM] train=4.2626  mask=14.8%  norm=0.810  lr=1.65e-04  dt=  37.2ms  words=52,355,072
[E05   200/1548 G   6391|CLM] train=3.1020  mask=14.8%  norm=0.813  lr=1.65e-04  dt=  37.0ms  words=52,363,264
[E05   201/1548 G   6392|CLM] train=2.3770  mask=14.8%  norm=0.823  lr=1.65e-04  dt=  37.2ms  words=52,371,456
[E05   202/1548 G   6393|CLM] train=4.3117  mask=14.8%  norm=0.874  lr=1.65e-04  dt=  37.0ms  words=52,379,648
[E05   203/1548 G   6394|CLM] train=4.1414  mask=14.8%  norm=1.117  lr=1.65e-04  dt=  36.9ms  words=52,387,840
[E05   204/1548 G   6395|CLM] train=4.4485  mask=14.8%  norm=0.829  lr=1.65e-04  dt=  36.9ms  words=52,396,032
[E05   205/1548 G   6396|CLM] train=1.7939  mask=14.8%  norm=1.072  lr=1.65e-04  dt=  36.9ms  words=52,404,224
[E05   206/1548 G   6397|CLM] train=4.4282  mask=14.8%  norm=0.886  lr=1.65e-04  dt=  37.0ms  words=52,412,416
[E05   207/1548 G   6398|CLM] train=4.2926  mask=14.8%  norm=0.774  lr=1.65e-04  dt=  37.2ms  words=52,420,608
[E05   208/1548 G   6399|CLM] train=4.4050  mask=14.8%  norm=0.732  lr=1.65e-04  dt=  37.0ms  words=52,428,800
[E05   209/1548 G   6400|CLM] train=4.5269  mask=14.8%  norm=0.774  lr=1.65e-04  dt=  37.3ms  words=52,436,992
[E05   210/1548 G   6401|CLM] train=3.7874  mask=14.8%  norm=0.775  lr=1.65e-04  dt=  36.9ms  words=52,445,184
[E05   211/1548 G   6402|CLM] train=4.6326  mask=14.8%  norm=0.842  lr=1.65e-04  dt=  37.1ms  words=52,453,376
[E05   212/1548 G   6403|CLM] train=3.7789  mask=14.8%  norm=0.789  lr=1.65e-04  dt=  36.9ms  words=52,461,568
[E05   213/1548 G   6404|CLM] train=2.3424  mask=14.8%  norm=0.768  lr=1.65e-04  dt=  37.1ms  words=52,469,760
[E05   214/1548 G   6405|CLM] train=4.4046  mask=14.8%  norm=0.837  lr=1.65e-04  dt=  37.0ms  words=52,477,952
[E05   215/1548 G   6406|CLM] train=2.4466  mask=14.8%  norm=0.683  lr=1.65e-04  dt=  37.1ms  words=52,486,144
[E05   216/1548 G   6407|CLM] train=4.0501  mask=14.8%  norm=0.874  lr=1.65e-04  dt=  37.1ms  words=52,494,336
[E05   217/1548 G   6408|CLM] train=2.4036  mask=14.8%  norm=0.894  lr=1.65e-04  dt=  37.1ms  words=52,502,528
[E05   218/1548 G   6409|CLM] train=4.9377  mask=14.8%  norm=0.935  lr=1.65e-04  dt=  37.0ms  words=52,510,720
[E05   219/1548 G   6410|CLM] train=2.4170  mask=14.8%  norm=0.875  lr=1.65e-04  dt=  37.1ms  words=52,518,912
[E05   220/1548 G   6411|CLM] train=2.3053  mask=14.8%  norm=0.754  lr=1.64e-04  dt=  36.9ms  words=52,527,104
[E05   221/1548 G   6412|CLM] train=4.6090  mask=14.8%  norm=1.207  lr=1.64e-04  dt=  37.1ms  words=52,535,296
[E05   222/1548 G   6413|CLM] train=4.4825  mask=14.8%  norm=1.034  lr=1.64e-04  dt=  37.0ms  words=52,543,488
[E05   223/1548 G   6414|CLM] train=4.2645  mask=14.8%  norm=0.705  lr=1.64e-04  dt=  37.2ms  words=52,551,680
[E05   224/1548 G   6415|CLM] train=4.2587  mask=14.8%  norm=1.105  lr=1.64e-04  dt=  37.0ms  words=52,559,872
[E05   225/1548 G   6416|CLM] train=3.5594  mask=14.8%  norm=0.892  lr=1.64e-04  dt=  37.1ms  words=52,568,064
[E05   226/1548 G   6417|CLM] train=4.2635  mask=14.8%  norm=0.769  lr=1.64e-04  dt=  37.1ms  words=52,576,256
[E05   227/1548 G   6418|CLM] train=2.4131  mask=14.8%  norm=0.822  lr=1.64e-04  dt=  37.2ms  words=52,584,448
[E05   228/1548 G   6419|CLM] train=2.2436  mask=14.8%  norm=0.670  lr=1.64e-04  dt=  36.9ms  words=52,592,640
[E05   229/1548 G   6420|CLM] train=4.5797  mask=14.8%  norm=1.261  lr=1.64e-04  dt=  37.0ms  words=52,600,832
[E05   230/1548 G   6421|CLM] train=3.8458  mask=14.8%  norm=1.080  lr=1.64e-04  dt=  37.1ms  words=52,609,024
[E05   231/1548 G   6422|CLM] train=3.6009  mask=14.8%  norm=0.720  lr=1.64e-04  dt=  37.0ms  words=52,617,216
[E05   232/1548 G   6423|CLM] train=2.3011  mask=14.8%  norm=0.853  lr=1.64e-04  dt=  36.8ms  words=52,625,408
[E05   233/1548 G   6424|CLM] train=3.8844  mask=14.8%  norm=0.727  lr=1.64e-04  dt=  37.1ms  words=52,633,600
[E05   234/1548 G   6425|CLM] train=3.9569  mask=14.8%  norm=0.712  lr=1.64e-04  dt=  37.0ms  words=52,641,792
[E05   235/1548 G   6426|CLM] train=2.3489  mask=14.8%  norm=0.627  lr=1.64e-04  dt=  36.9ms  words=52,649,984
[E05   236/1548 G   6427|CLM] train=2.4106  mask=14.8%  norm=0.673  lr=1.64e-04  dt=  36.8ms  words=52,658,176
[E05   237/1548 G   6428|CLM] train=3.7323  mask=14.8%  norm=0.860  lr=1.64e-04  dt=  37.1ms  words=52,666,368
[E05   238/1548 G   6429|CLM] train=2.5545  mask=14.8%  norm=0.704  lr=1.64e-04  dt=  37.1ms  words=52,674,560
[E05   239/1548 G   6430|CLM] train=3.9763  mask=14.8%  norm=0.689  lr=1.64e-04  dt=  46.1ms  words=52,682,752
[E05   240/1548 G   6431|CLM] train=4.6763  mask=14.8%  norm=1.032  lr=1.64e-04  dt=  37.1ms  words=52,690,944
[E05   241/1548 G   6432|CLM] train=3.8070  mask=14.8%  norm=0.601  lr=1.64e-04  dt=  44.1ms  words=52,699,136
[E05   242/1548 G   6433|CLM] train=2.5085  mask=14.8%  norm=0.627  lr=1.64e-04  dt=  45.1ms  words=52,707,328
[E05   243/1548 G   6434|CLM] train=4.2608  mask=14.8%  norm=0.745  lr=1.64e-04  dt=  37.5ms  words=52,715,520
[E05   244/1548 G   6435|CLM] train=4.1536  mask=14.8%  norm=0.960  lr=1.64e-04  dt=  37.0ms  words=52,723,712
[E05   245/1548 G   6436|CLM] train=3.8991  mask=14.8%  norm=0.822  lr=1.64e-04  dt=  37.1ms  words=52,731,904
[E05   246/1548 G   6437|CLM] train=4.1760  mask=14.8%  norm=0.880  lr=1.63e-04  dt=  37.5ms  words=52,740,096
[E05   247/1548 G   6438|CLM] train=4.2676  mask=14.8%  norm=1.074  lr=1.63e-04  dt=  37.9ms  words=52,748,288
[E05   248/1548 G   6439|CLM] train=4.2754  mask=14.8%  norm=0.971  lr=1.63e-04  dt=  37.1ms  words=52,756,480
[E05   249/1548 G   6440|CLM] train=4.0017  mask=14.8%  norm=0.826  lr=1.63e-04  dt=  37.2ms  words=52,764,672
[E05   250/1548 G   6441|CLM] train=3.8197  mask=14.8%  norm=0.901  lr=1.63e-04  dt=  37.7ms  words=52,772,864
[E05   251/1548 G   6442|CLM] train=3.9777  mask=14.8%  norm=0.819  lr=1.63e-04  dt=  38.2ms  words=52,781,056
[E05   252/1548 G   6443|CLM] train=3.9614  mask=14.8%  norm=0.838  lr=1.63e-04  dt=  37.0ms  words=52,789,248
[E05   253/1548 G   6444|CLM] train=4.1657  mask=14.8%  norm=1.008  lr=1.63e-04  dt=  37.3ms  words=52,797,440
[E05   254/1548 G   6445|CLM] train=4.1267  mask=14.8%  norm=0.861  lr=1.63e-04  dt=  37.1ms  words=52,805,632
[E05   255/1548 G   6446|CLM] train=4.5565  mask=14.8%  norm=0.919  lr=1.63e-04  dt=  37.2ms  words=52,813,824
[E05   256/1548 G   6447|CLM] train=3.7800  mask=14.8%  norm=0.786  lr=1.63e-04  dt=  37.1ms  words=52,822,016
[E05   257/1548 G   6448|CLM] train=4.0406  mask=14.8%  norm=0.743  lr=1.63e-04  dt=  37.0ms  words=52,830,208
[E05   258/1548 G   6449|CLM] train=3.9469  mask=14.8%  norm=0.957  lr=1.63e-04  dt=  37.2ms  words=52,838,400
[E05   259/1548 G   6450|CLM] train=2.6113  mask=14.8%  norm=0.901  lr=1.63e-04  dt=  37.1ms  words=52,846,592
[E05   260/1548 G   6451|CLM] train=4.1637  mask=14.8%  norm=0.838  lr=1.63e-04  dt=  47.1ms  words=52,854,784
[E05   261/1548 G   6452|CLM] train=2.1521  mask=14.8%  norm=0.808  lr=1.63e-04  dt=  36.9ms  words=52,862,976
[E05   262/1548 G   6453|CLM] train=4.3908  mask=14.8%  norm=0.845  lr=1.63e-04  dt=  41.0ms  words=52,871,168
[E05   263/1548 G   6454|CLM] train=5.3175  mask=14.8%  norm=1.321  lr=1.63e-04  dt=  46.7ms  words=52,879,360
[E05   264/1548 G   6455|CLM] train=4.1605  mask=14.8%  norm=0.899  lr=1.63e-04  dt=  43.9ms  words=52,887,552
[E05   265/1548 G   6456|CLM] train=4.0846  mask=14.8%  norm=0.796  lr=1.63e-04  dt=  36.9ms  words=52,895,744
[E05   266/1548 G   6457|CLM] train=4.1749  mask=14.8%  norm=0.923  lr=1.63e-04  dt=  37.1ms  words=52,903,936
[E05   267/1548 G   6458|CLM] train=3.9933  mask=14.8%  norm=0.877  lr=1.63e-04  dt=  38.3ms  words=52,912,128
[E05   268/1548 G   6459|CLM] train=3.7931  mask=14.8%  norm=0.790  lr=1.63e-04  dt=  37.2ms  words=52,920,320
[E05   269/1548 G   6460|CLM] train=4.1118  mask=14.8%  norm=0.894  lr=1.63e-04  dt=  37.2ms  words=52,928,512
[E05   270/1548 G   6461|CLM] train=3.8808  mask=14.8%  norm=0.678  lr=1.63e-04  dt=  37.0ms  words=52,936,704
[E05   271/1548 G   6462|CLM] train=2.3640  mask=14.8%  norm=0.699  lr=1.63e-04  dt=  37.3ms  words=52,944,896
[E05   272/1548 G   6463|CLM] train=4.5143  mask=14.8%  norm=0.936  lr=1.62e-04  dt=  37.2ms  words=52,953,088
[E05   273/1548 G   6464|CLM] train=4.3720  mask=14.8%  norm=0.751  lr=1.62e-04  dt=  37.1ms  words=52,961,280
[E05   274/1548 G   6465|CLM] train=4.8803  mask=14.8%  norm=1.020  lr=1.62e-04  dt=  36.9ms  words=52,969,472
[E05   275/1548 G   6466|CLM] train=4.3761  mask=14.8%  norm=0.793  lr=1.62e-04  dt=  37.1ms  words=52,977,664
[E05   276/1548 G   6467|CLM] train=2.3874  mask=14.8%  norm=0.743  lr=1.62e-04  dt=  37.3ms  words=52,985,856
[E05   277/1548 G   6468|CLM] train=4.1577  mask=14.8%  norm=0.939  lr=1.62e-04  dt=  37.4ms  words=52,994,048
[E05   278/1548 G   6469|CLM] train=3.4346  mask=14.8%  norm=0.697  lr=1.62e-04  dt=  37.2ms  words=53,002,240
[E05   279/1548 G   6470|CLM] train=3.5186  mask=14.8%  norm=0.811  lr=1.62e-04  dt=  37.1ms  words=53,010,432
[E05   280/1548 G   6471|CLM] train=1.9639  mask=14.8%  norm=0.806  lr=1.62e-04  dt=  36.9ms  words=53,018,624
[E05   281/1548 G   6472|CLM] train=4.4192  mask=14.8%  norm=0.938  lr=1.62e-04  dt=  37.2ms  words=53,026,816
[E05   282/1548 G   6473|CLM] train=2.4536  mask=14.8%  norm=0.740  lr=1.62e-04  dt=  37.2ms  words=53,035,008
[E05   283/1548 G   6474|CLM] train=2.0833  mask=14.8%  norm=0.726  lr=1.62e-04  dt=  37.0ms  words=53,043,200
[E05   284/1548 G   6475|CLM] train=4.3430  mask=14.8%  norm=1.048  lr=1.62e-04  dt=  37.1ms  words=53,051,392
[E05   285/1548 G   6476|CLM] train=4.6819  mask=14.8%  norm=0.936  lr=1.62e-04  dt=  37.3ms  words=53,059,584
[E05   286/1548 G   6477|CLM] train=4.4977  mask=14.8%  norm=0.868  lr=1.62e-04  dt=  37.3ms  words=53,067,776
[E05   287/1548 G   6478|CLM] train=4.3404  mask=14.8%  norm=0.828  lr=1.62e-04  dt=  37.0ms  words=53,075,968
[E05   288/1548 G   6479|CLM] train=4.6327  mask=14.8%  norm=0.838  lr=1.62e-04  dt=  37.1ms  words=53,084,160
[E05   289/1548 G   6480|CLM] train=2.3644  mask=14.8%  norm=0.869  lr=1.62e-04  dt=  37.2ms  words=53,092,352
[E05   290/1548 G   6481|CLM] train=4.3729  mask=14.8%  norm=0.792  lr=1.62e-04  dt=  37.2ms  words=53,100,544
[E05   291/1548 G   6482|CLM] train=2.3448  mask=14.8%  norm=1.049  lr=1.62e-04  dt=  37.1ms  words=53,108,736
[E05   292/1548 G   6483|CLM] train=2.4196  mask=14.8%  norm=0.668  lr=1.62e-04  dt=  37.0ms  words=53,116,928
[E05   293/1548 G   6484|CLM] train=2.2198  mask=14.8%  norm=0.716  lr=1.62e-04  dt=  37.3ms  words=53,125,120
[E05   294/1548 G   6485|CLM] train=4.3707  mask=14.8%  norm=0.902  lr=1.62e-04  dt=  37.1ms  words=53,133,312
[E05   295/1548 G   6486|CLM] train=4.6706  mask=14.8%  norm=0.889  lr=1.62e-04  dt=  37.9ms  words=53,141,504
[E05   296/1548 G   6487|CLM] train=5.0439  mask=14.8%  norm=1.343  lr=1.62e-04  dt=  37.0ms  words=53,149,696
[E05   297/1548 G   6488|CLM] train=4.4141  mask=14.8%  norm=0.831  lr=1.62e-04  dt=  37.2ms  words=53,157,888
[E05   298/1548 G   6489|CLM] train=4.1969  mask=14.8%  norm=0.771  lr=1.61e-04  dt=  37.1ms  words=53,166,080
[E05   299/1548 G   6490|CLM] train=4.6132  mask=14.8%  norm=0.865  lr=1.61e-04  dt=  36.9ms  words=53,174,272
[E05   300/1548 G   6491|CLM] train=4.8148  mask=14.8%  norm=0.978  lr=1.61e-04  dt=  37.1ms  words=53,182,464
[E05   301/1548 G   6492|CLM] train=4.3016  mask=14.8%  norm=1.324  lr=1.61e-04  dt=  37.2ms  words=53,190,656
[E05   302/1548 G   6493|CLM] train=3.8984  mask=14.8%  norm=0.768  lr=1.61e-04  dt=  37.9ms  words=53,198,848
[E05   303/1548 G   6494|CLM] train=2.5720  mask=14.8%  norm=0.907  lr=1.61e-04  dt=  37.4ms  words=53,207,040
[E05   304/1548 G   6495|CLM] train=4.5303  mask=14.8%  norm=0.842  lr=1.61e-04  dt=  37.7ms  words=53,215,232
[E05   305/1548 G   6496|CLM] train=2.3490  mask=14.8%  norm=0.820  lr=1.61e-04  dt=  37.1ms  words=53,223,424
[E05   306/1548 G   6497|CLM] train=4.8838  mask=14.8%  norm=1.012  lr=1.61e-04  dt=  37.1ms  words=53,231,616
[E05   307/1548 G   6498|CLM] train=2.9017  mask=14.8%  norm=0.715  lr=1.61e-04  dt=  37.2ms  words=53,239,808
[E05   308/1548 G   6499|CLM] train=4.4152  mask=14.8%  norm=0.762  lr=1.61e-04  dt=  37.1ms  words=53,248,000
[E05   309/1548 G   6500|CLM] train=2.2144  mask=14.8%  norm=0.705  lr=1.61e-04  dt=  37.2ms  words=53,256,192
[E05   310/1548 G   6501|CLM] train=2.4508  mask=14.8%  norm=1.009  lr=1.61e-04  dt=  37.1ms  words=53,264,384
[E05   311/1548 G   6502|CLM] train=2.2814  mask=14.7%  norm=0.663  lr=1.61e-04  dt=  37.2ms  words=53,272,576
[E05   312/1548 G   6503|CLM] train=2.0155  mask=14.7%  norm=0.691  lr=1.61e-04  dt=  37.2ms  words=53,280,768
[E05   313/1548 G   6504|CLM] train=2.7059  mask=14.7%  norm=0.774  lr=1.61e-04  dt=  37.2ms  words=53,288,960
[E05   314/1548 G   6505|CLM] train=2.2051  mask=14.7%  norm=0.754  lr=1.61e-04  dt=  37.0ms  words=53,297,152
[E05   315/1548 G   6506|CLM] train=2.3672  mask=14.7%  norm=0.736  lr=1.61e-04  dt=  36.9ms  words=53,305,344
[E05   316/1548 G   6507|CLM] train=2.1461  mask=14.7%  norm=0.728  lr=1.61e-04  dt=  37.0ms  words=53,313,536
[E05   317/1548 G   6508|CLM] train=2.3314  mask=14.7%  norm=0.671  lr=1.61e-04  dt=  37.2ms  words=53,321,728
[E05   318/1548 G   6509|CLM] train=2.0519  mask=14.7%  norm=0.824  lr=1.61e-04  dt=  37.1ms  words=53,329,920
[E05   319/1548 G   6510|CLM] train=2.4131  mask=14.7%  norm=0.663  lr=1.61e-04  dt=  37.1ms  words=53,338,112
[E05   320/1548 G   6511|CLM] train=2.6462  mask=14.7%  norm=0.670  lr=1.61e-04  dt=  37.1ms  words=53,346,304
[E05   321/1548 G   6512|CLM] train=4.6380  mask=14.7%  norm=1.759  lr=1.61e-04  dt=  37.0ms  words=53,354,496
[E05   322/1548 G   6513|CLM] train=4.2013  mask=14.7%  norm=1.070  lr=1.61e-04  dt=  37.0ms  words=53,362,688
[E05   323/1548 G   6514|CLM] train=4.1023  mask=14.7%  norm=0.870  lr=1.61e-04  dt=  37.3ms  words=53,370,880
[E05   324/1548 G   6515|CLM] train=3.6631  mask=14.7%  norm=0.712  lr=1.60e-04  dt=  37.1ms  words=53,379,072
[E05   325/1548 G   6516|CLM] train=4.6932  mask=14.7%  norm=1.070  lr=1.60e-04  dt=  37.0ms  words=53,387,264
[E05   326/1548 G   6517|CLM] train=4.4009  mask=14.7%  norm=0.864  lr=1.60e-04  dt=  37.1ms  words=53,395,456
[E05   327/1548 G   6518|CLM] train=2.2375  mask=14.7%  norm=0.831  lr=1.60e-04  dt=  37.1ms  words=53,403,648
[E05   328/1548 G   6519|CLM] train=2.3994  mask=14.7%  norm=0.801  lr=1.60e-04  dt=  37.1ms  words=53,411,840
[E05   329/1548 G   6520|CLM] train=4.0175  mask=14.7%  norm=0.700  lr=1.60e-04  dt=  37.2ms  words=53,420,032
[E05   330/1548 G   6521|CLM] train=4.4044  mask=14.7%  norm=1.040  lr=1.60e-04  dt=  37.2ms  words=53,428,224
[E05   331/1548 G   6522|CLM] train=3.4246  mask=14.7%  norm=0.806  lr=1.60e-04  dt=  37.7ms  words=53,436,416
[E05   332/1548 G   6523|CLM] train=4.3404  mask=14.7%  norm=0.939  lr=1.60e-04  dt=  37.1ms  words=53,444,608
[E05   333/1548 G   6524|CLM] train=2.5727  mask=14.7%  norm=0.687  lr=1.60e-04  dt=  37.3ms  words=53,452,800
[E05   334/1548 G   6525|CLM] train=4.2609  mask=14.7%  norm=0.836  lr=1.60e-04  dt=  38.7ms  words=53,460,992
[E05   335/1548 G   6526|CLM] train=4.4519  mask=14.7%  norm=0.962  lr=1.60e-04  dt=  37.1ms  words=53,469,184
[E05   336/1548 G   6527|CLM] train=1.6733  mask=14.7%  norm=0.678  lr=1.60e-04  dt=  37.2ms  words=53,477,376
[E05   337/1548 G   6528|CLM] train=4.7328  mask=14.7%  norm=1.112  lr=1.60e-04  dt=  39.1ms  words=53,485,568
[E05   338/1548 G   6529|CLM] train=2.6297  mask=14.7%  norm=1.441  lr=1.60e-04  dt=  37.4ms  words=53,493,760
[E05   339/1548 G   6530|CLM] train=4.0336  mask=14.7%  norm=0.896  lr=1.60e-04  dt=  37.3ms  words=53,501,952
[E05   340/1548 G   6531|CLM] train=4.8754  mask=14.7%  norm=1.061  lr=1.60e-04  dt=  37.0ms  words=53,510,144
[E05   341/1548 G   6532|CLM] train=4.0107  mask=14.7%  norm=0.891  lr=1.60e-04  dt=  37.0ms  words=53,518,336
[E05   342/1548 G   6533|CLM] train=4.5775  mask=14.7%  norm=1.126  lr=1.60e-04  dt=  36.9ms  words=53,526,528
[E05   343/1548 G   6534|CLM] train=2.9222  mask=14.7%  norm=0.702  lr=1.60e-04  dt=  37.0ms  words=53,534,720
[E05   344/1548 G   6535|CLM] train=3.8872  mask=14.7%  norm=0.807  lr=1.60e-04  dt=  36.9ms  words=53,542,912
[E05   345/1548 G   6536|CLM] train=2.6818  mask=14.7%  norm=0.712  lr=1.60e-04  dt=  36.9ms  words=53,551,104
[E05   346/1548 G   6537|CLM] train=4.6548  mask=14.7%  norm=2.907  lr=1.60e-04  dt=  36.9ms  words=53,559,296
[E05   347/1548 G   6538|CLM] train=4.5102  mask=14.7%  norm=0.962  lr=1.60e-04  dt=  37.2ms  words=53,567,488
[E05   348/1548 G   6539|CLM] train=1.8523  mask=14.7%  norm=0.679  lr=1.60e-04  dt=  36.9ms  words=53,575,680
[E05   349/1548 G   6540|CLM] train=2.2659  mask=14.7%  norm=1.163  lr=1.60e-04  dt=  37.2ms  words=53,583,872
[E05   350/1548 G   6541|CLM] train=3.7659  mask=14.7%  norm=0.872  lr=1.59e-04  dt=  37.2ms  words=53,592,064
[E05   351/1548 G   6542|CLM] train=4.1596  mask=14.7%  norm=0.892  lr=1.59e-04  dt=  36.9ms  words=53,600,256
[E05   352/1548 G   6543|CLM] train=3.4498  mask=14.7%  norm=0.761  lr=1.59e-04  dt=  36.9ms  words=53,608,448
[E05   353/1548 G   6544|CLM] train=2.2327  mask=14.7%  norm=0.925  lr=1.59e-04  dt=  37.0ms  words=53,616,640
[E05   354/1548 G   6545|CLM] train=4.3520  mask=14.7%  norm=0.791  lr=1.59e-04  dt=  37.1ms  words=53,624,832
[E05   355/1548 G   6546|CLM] train=2.6116  mask=14.7%  norm=0.825  lr=1.59e-04  dt=  36.9ms  words=53,633,024
[E05   356/1548 G   6547|CLM] train=2.1343  mask=14.7%  norm=0.661  lr=1.59e-04  dt=  37.1ms  words=53,641,216
[E05   357/1548 G   6548|CLM] train=4.4485  mask=14.7%  norm=0.829  lr=1.59e-04  dt=  37.1ms  words=53,649,408
[E05   358/1548 G   6549|CLM] train=4.2871  mask=14.7%  norm=0.821  lr=1.59e-04  dt=  37.1ms  words=53,657,600
[E05   359/1548 G   6550|CLM] train=2.3061  mask=14.7%  norm=0.773  lr=1.59e-04  dt=  36.9ms  words=53,665,792
[E05   360/1548 G   6551|CLM] train=3.8240  mask=14.7%  norm=0.970  lr=1.59e-04  dt=  37.1ms  words=53,673,984
[E05   361/1548 G   6552|CLM] train=4.5063  mask=14.7%  norm=1.073  lr=1.59e-04  dt=  37.2ms  words=53,682,176
[E05   362/1548 G   6553|CLM] train=2.1739  mask=14.7%  norm=0.679  lr=1.59e-04  dt=  37.0ms  words=53,690,368
[E05   363/1548 G   6554|CLM] train=3.6963  mask=14.7%  norm=0.772  lr=1.59e-04  dt=  36.9ms  words=53,698,560
[E05   364/1548 G   6555|CLM] train=2.3245  mask=14.7%  norm=0.663  lr=1.59e-04  dt=  36.9ms  words=53,706,752
[E05   365/1548 G   6556|CLM] train=2.5103  mask=14.7%  norm=0.928  lr=1.59e-04  dt=  37.0ms  words=53,714,944
[E05   366/1548 G   6557|CLM] train=2.5684  mask=14.7%  norm=0.818  lr=1.59e-04  dt=  36.9ms  words=53,723,136
[E05   367/1548 G   6558|CLM] train=3.7081  mask=14.7%  norm=0.734  lr=1.59e-04  dt=  37.0ms  words=53,731,328
[E05   368/1548 G   6559|CLM] train=4.2964  mask=14.7%  norm=0.862  lr=1.59e-04  dt=  37.2ms  words=53,739,520
[E05   369/1548 G   6560|CLM] train=2.5168  mask=14.7%  norm=0.801  lr=1.59e-04  dt=  37.1ms  words=53,747,712
[E05   370/1548 G   6561|CLM] train=2.0877  mask=14.7%  norm=0.660  lr=1.59e-04  dt=  37.0ms  words=53,755,904
[E05   371/1548 G   6562|CLM] train=2.1484  mask=14.7%  norm=0.675  lr=1.59e-04  dt=  37.0ms  words=53,764,096
[E05   372/1548 G   6563|CLM] train=4.0566  mask=14.7%  norm=0.899  lr=1.59e-04  dt=  39.1ms  words=53,772,288
[E05   373/1548 G   6564|CLM] train=2.7774  mask=14.7%  norm=0.737  lr=1.59e-04  dt=  40.7ms  words=53,780,480
[E05   374/1548 G   6565|CLM] train=4.4895  mask=14.7%  norm=1.014  lr=1.59e-04  dt=  42.4ms  words=53,788,672
[E05   375/1548 G   6566|CLM] train=4.4560  mask=14.7%  norm=0.822  lr=1.59e-04  dt=  37.9ms  words=53,796,864
[E05   376/1548 G   6567|CLM] train=4.8734  mask=14.7%  norm=1.118  lr=1.58e-04  dt=  37.9ms  words=53,805,056
[E05   377/1548 G   6568|CLM] train=2.7312  mask=14.7%  norm=0.754  lr=1.58e-04  dt=  38.7ms  words=53,813,248
[E05   378/1548 G   6569|CLM] train=3.9167  mask=14.7%  norm=0.695  lr=1.58e-04  dt=  38.2ms  words=53,821,440
[E05   379/1548 G   6570|CLM] train=5.3270  mask=14.7%  norm=1.275  lr=1.58e-04  dt=  45.4ms  words=53,829,632
[E05   380/1548 G   6571|CLM] train=2.3044  mask=14.7%  norm=0.808  lr=1.58e-04  dt=  46.0ms  words=53,837,824
[E05   381/1548 G   6572|CLM] train=4.6613  mask=14.7%  norm=0.858  lr=1.58e-04  dt=  46.3ms  words=53,846,016
[E05   382/1548 G   6573|CLM] train=4.2982  mask=14.7%  norm=0.887  lr=1.58e-04  dt=  46.3ms  words=53,854,208
[E05   383/1548 G   6574|CLM] train=4.0796  mask=14.7%  norm=0.885  lr=1.58e-04  dt=  37.8ms  words=53,862,400
[E05   384/1548 G   6575|CLM] train=2.3775  mask=14.7%  norm=0.721  lr=1.58e-04  dt=  37.2ms  words=53,870,592
[E05   385/1548 G   6576|CLM] train=2.3726  mask=14.7%  norm=0.749  lr=1.58e-04  dt=  37.2ms  words=53,878,784
[E05   386/1548 G   6577|CLM] train=4.0563  mask=14.7%  norm=0.639  lr=1.58e-04  dt=  37.2ms  words=53,886,976
[E05   387/1548 G   6578|CLM] train=2.4928  mask=14.7%  norm=0.807  lr=1.58e-04  dt=  38.0ms  words=53,895,168
[E05   388/1548 G   6579|CLM] train=4.0951  mask=14.7%  norm=0.953  lr=1.58e-04  dt=  41.9ms  words=53,903,360
[E05   389/1548 G   6580|CLM] train=2.2597  mask=14.7%  norm=1.019  lr=1.58e-04  dt=  42.7ms  words=53,911,552
[E05   390/1548 G   6581|CLM] train=1.7849  mask=14.7%  norm=0.651  lr=1.58e-04  dt=  37.3ms  words=53,919,744
[E05   391/1548 G   6582|CLM] train=5.2945  mask=14.7%  norm=1.099  lr=1.58e-04  dt=  41.4ms  words=53,927,936
[E05   392/1548 G   6583|CLM] train=4.4131  mask=14.7%  norm=0.830  lr=1.58e-04  dt=  40.4ms  words=53,936,128
[E05   393/1548 G   6584|CLM] train=2.2094  mask=14.7%  norm=0.675  lr=1.58e-04  dt=  43.0ms  words=53,944,320
[E05   394/1548 G   6585|CLM] train=2.6487  mask=14.7%  norm=0.702  lr=1.58e-04  dt=  38.8ms  words=53,952,512
[E05   395/1548 G   6586|CLM] train=3.9247  mask=14.7%  norm=0.709  lr=1.58e-04  dt=  37.2ms  words=53,960,704
[E05   396/1548 G   6587|CLM] train=4.0865  mask=14.7%  norm=0.735  lr=1.58e-04  dt=  37.2ms  words=53,968,896
[E05   397/1548 G   6588|CLM] train=4.3197  mask=14.7%  norm=0.802  lr=1.58e-04  dt=  37.8ms  words=53,977,088
[E05   398/1548 G   6589|CLM] train=4.4653  mask=14.7%  norm=0.930  lr=1.58e-04  dt=  37.7ms  words=53,985,280
[E05   399/1548 G   6590|CLM] train=4.3817  mask=14.7%  norm=1.040  lr=1.58e-04  dt=  37.5ms  words=53,993,472
[E05   400/1548 G   6591|CLM] train=4.4843  mask=14.7%  norm=0.769  lr=1.58e-04  dt=  37.6ms  words=54,001,664
[E05   401/1548 G   6592|CLM] train=2.4118  mask=14.7%  norm=1.050  lr=1.57e-04  dt=  37.8ms  words=54,009,856
[E05   402/1548 G   6593|CLM] train=4.1022  mask=14.7%  norm=0.854  lr=1.57e-04  dt=  39.4ms  words=54,018,048
[E05   403/1548 G   6594|CLM] train=4.8755  mask=14.7%  norm=0.811  lr=1.57e-04  dt=  37.5ms  words=54,026,240
[E05   404/1548 G   6595|CLM] train=4.8879  mask=14.7%  norm=0.879  lr=1.57e-04  dt=  38.7ms  words=54,034,432
[E05   405/1548 G   6596|CLM] train=2.7826  mask=14.7%  norm=0.865  lr=1.57e-04  dt=  38.0ms  words=54,042,624
[E05   406/1548 G   6597|CLM] train=2.1629  mask=14.7%  norm=0.864  lr=1.57e-04  dt=  37.0ms  words=54,050,816
[E05   407/1548 G   6598|CLM] train=4.2073  mask=14.7%  norm=1.069  lr=1.57e-04  dt=  37.7ms  words=54,059,008
[E05   408/1548 G   6599|CLM] train=4.8524  mask=14.7%  norm=1.058  lr=1.57e-04  dt=  38.0ms  words=54,067,200
[E05   409/1548 G   6600|CLM] train=4.1720  mask=14.7%  norm=0.771  lr=1.57e-04  dt=  37.3ms  words=54,075,392
[E05   410/1548 G   6601|CLM] train=2.1987  mask=14.7%  norm=0.777  lr=1.57e-04  dt=  37.0ms  words=54,083,584
[E05   411/1548 G   6602|CLM] train=2.4765  mask=14.7%  norm=0.659  lr=1.57e-04  dt=  37.2ms  words=54,091,776
[E05   412/1548 G   6603|CLM] train=2.4003  mask=14.7%  norm=0.839  lr=1.57e-04  dt=  37.5ms  words=54,099,968
[E05   413/1548 G   6604|CLM] train=2.8697  mask=14.7%  norm=0.762  lr=1.57e-04  dt=  37.0ms  words=54,108,160
[E05   414/1548 G   6605|CLM] train=4.0164  mask=14.7%  norm=0.724  lr=1.57e-04  dt=  36.8ms  words=54,116,352
[E05   415/1548 G   6606|CLM] train=4.5399  mask=14.7%  norm=1.023  lr=1.57e-04  dt=  37.5ms  words=54,124,544
[E05   416/1548 G   6607|CLM] train=5.2501  mask=14.7%  norm=1.137  lr=1.57e-04  dt=  37.5ms  words=54,132,736
[E05   417/1548 G   6608|CLM] train=4.4874  mask=14.7%  norm=0.917  lr=1.57e-04  dt=  36.9ms  words=54,140,928
[E05   418/1548 G   6609|CLM] train=4.6548  mask=14.7%  norm=0.823  lr=1.57e-04  dt=  37.0ms  words=54,149,120
[E05   419/1548 G   6610|CLM] train=4.1178  mask=14.7%  norm=0.888  lr=1.57e-04  dt=  37.2ms  words=54,157,312
[E05   420/1548 G   6611|CLM] train=4.2917  mask=14.7%  norm=0.764  lr=1.57e-04  dt=  37.1ms  words=54,165,504
[E05   421/1548 G   6612|CLM] train=3.8401  mask=14.7%  norm=1.004  lr=1.57e-04  dt=  37.2ms  words=54,173,696
[E05   422/1548 G   6613|CLM] train=3.7363  mask=14.7%  norm=0.908  lr=1.57e-04  dt=  37.2ms  words=54,181,888
[E05   423/1548 G   6614|CLM] train=4.8248  mask=14.7%  norm=1.121  lr=1.57e-04  dt=  37.2ms  words=54,190,080
[E05   424/1548 G   6615|CLM] train=4.1311  mask=14.7%  norm=1.019  lr=1.57e-04  dt=  37.2ms  words=54,198,272
[E05   425/1548 G   6616|CLM] train=3.7538  mask=14.7%  norm=0.724  lr=1.57e-04  dt=  37.2ms  words=54,206,464
[E05   426/1548 G   6617|CLM] train=2.3021  mask=14.7%  norm=1.063  lr=1.57e-04  dt=  37.0ms  words=54,214,656
[E05   427/1548 G   6618|CLM] train=4.2476  mask=14.7%  norm=0.719  lr=1.56e-04  dt=  37.0ms  words=54,222,848
[E05   428/1548 G   6619|CLM] train=2.2087  mask=14.7%  norm=0.965  lr=1.56e-04  dt=  36.9ms  words=54,231,040
[E05   429/1548 G   6620|CLM] train=2.4304  mask=14.7%  norm=0.761  lr=1.56e-04  dt=  37.2ms  words=54,239,232
[E05   430/1548 G   6621|CLM] train=2.2000  mask=14.7%  norm=0.872  lr=1.56e-04  dt=  37.1ms  words=54,247,424
[E05   431/1548 G   6622|CLM] train=3.6527  mask=14.7%  norm=0.832  lr=1.56e-04  dt=  37.1ms  words=54,255,616
[E05   432/1548 G   6623|CLM] train=3.7215  mask=14.7%  norm=0.824  lr=1.56e-04  dt=  37.7ms  words=54,263,808
[E05   433/1548 G   6624|CLM] train=5.1639  mask=14.7%  norm=1.387  lr=1.56e-04  dt=  37.3ms  words=54,272,000
[E05   434/1548 G   6625|CLM] train=2.5696  mask=14.7%  norm=0.997  lr=1.56e-04  dt=  37.1ms  words=54,280,192
[E05   435/1548 G   6626|CLM] train=3.6122  mask=14.6%  norm=0.731  lr=1.56e-04  dt=  37.3ms  words=54,288,384
[E05   436/1548 G   6627|CLM] train=4.0732  mask=14.6%  norm=1.054  lr=1.56e-04  dt=  37.4ms  words=54,296,576
[E05   437/1548 G   6628|CLM] train=4.2858  mask=14.6%  norm=0.930  lr=1.56e-04  dt=  37.1ms  words=54,304,768
[E05   438/1548 G   6629|CLM] train=4.2863  mask=14.6%  norm=0.831  lr=1.56e-04  dt=  37.0ms  words=54,312,960
[E05   439/1548 G   6630|CLM] train=3.5983  mask=14.6%  norm=0.802  lr=1.56e-04  dt=  37.2ms  words=54,321,152
[E05   440/1548 G   6631|CLM] train=4.9230  mask=14.6%  norm=1.026  lr=1.56e-04  dt=  37.2ms  words=54,329,344
[E05   441/1548 G   6632|CLM] train=4.2155  mask=14.6%  norm=1.035  lr=1.56e-04  dt=  37.2ms  words=54,337,536
[E05   442/1548 G   6633|CLM] train=2.3742  mask=14.6%  norm=0.982  lr=1.56e-04  dt=  37.0ms  words=54,345,728
[E05   443/1548 G   6634|CLM] train=2.5687  mask=14.6%  norm=0.833  lr=1.56e-04  dt=  37.0ms  words=54,353,920
[E05   444/1548 G   6635|CLM] train=4.7494  mask=14.6%  norm=1.803  lr=1.56e-04  dt=  37.0ms  words=54,362,112
[E05   445/1548 G   6636|CLM] train=4.5943  mask=14.6%  norm=0.828  lr=1.56e-04  dt=  37.1ms  words=54,370,304
[E05   446/1548 G   6637|CLM] train=3.9953  mask=14.6%  norm=0.745  lr=1.56e-04  dt=  37.1ms  words=54,378,496
[E05   447/1548 G   6638|CLM] train=3.8335  mask=14.6%  norm=0.873  lr=1.56e-04  dt=  37.2ms  words=54,386,688
[E05   448/1548 G   6639|CLM] train=2.1674  mask=14.6%  norm=0.698  lr=1.56e-04  dt=  37.2ms  words=54,394,880
[E05   449/1548 G   6640|CLM] train=4.1662  mask=14.6%  norm=0.905  lr=1.56e-04  dt=  36.9ms  words=54,403,072
[E05   450/1548 G   6641|CLM] train=3.9728  mask=14.6%  norm=1.225  lr=1.56e-04  dt=  37.2ms  words=54,411,264
[E05   451/1548 G   6642|CLM] train=3.8473  mask=14.6%  norm=0.766  lr=1.56e-04  dt=  37.3ms  words=54,419,456
[E05   452/1548 G   6643|CLM] train=2.4861  mask=14.6%  norm=0.754  lr=1.56e-04  dt=  36.9ms  words=54,427,648
[E05   453/1548 G   6644|CLM] train=2.1681  mask=14.6%  norm=0.915  lr=1.55e-04  dt=  37.0ms  words=54,435,840
[E05   454/1548 G   6645|CLM] train=4.7055  mask=14.6%  norm=0.846  lr=1.55e-04  dt=  37.0ms  words=54,444,032
[E05   455/1548 G   6646|CLM] train=4.4180  mask=14.6%  norm=0.849  lr=1.55e-04  dt=  37.1ms  words=54,452,224
[E05   456/1548 G   6647|CLM] train=2.4608  mask=14.6%  norm=0.757  lr=1.55e-04  dt=  36.9ms  words=54,460,416
[E05   457/1548 G   6648|CLM] train=2.5046  mask=14.6%  norm=0.720  lr=1.55e-04  dt=  37.0ms  words=54,468,608
[E05   458/1548 G   6649|CLM] train=2.1643  mask=14.6%  norm=0.718  lr=1.55e-04  dt=  37.3ms  words=54,476,800
[E05   459/1548 G   6650|CLM] train=4.3175  mask=14.6%  norm=0.988  lr=1.55e-04  dt=  37.1ms  words=54,484,992
[E05   460/1548 G   6651|CLM] train=2.7334  mask=14.6%  norm=0.734  lr=1.55e-04  dt=  37.0ms  words=54,493,184
[E05   461/1548 G   6652|CLM] train=2.4431  mask=14.6%  norm=1.221  lr=1.55e-04  dt=  37.1ms  words=54,501,376
[E05   462/1548 G   6653|CLM] train=2.6029  mask=14.6%  norm=0.837  lr=1.55e-04  dt=  37.0ms  words=54,509,568
[E05   463/1548 G   6654|CLM] train=4.1535  mask=14.6%  norm=0.931  lr=1.55e-04  dt=  37.3ms  words=54,517,760
[E05   464/1548 G   6655|CLM] train=3.5705  mask=14.6%  norm=0.762  lr=1.55e-04  dt=  37.0ms  words=54,525,952
[E05   465/1548 G   6656|CLM] train=2.4633  mask=14.6%  norm=0.670  lr=1.55e-04  dt=  37.2ms  words=54,534,144
[E05   466/1548 G   6657|CLM] train=5.2183  mask=14.6%  norm=1.732  lr=1.55e-04  dt=  37.0ms  words=54,542,336
[E05   467/1548 G   6658|CLM] train=4.0023  mask=14.6%  norm=0.823  lr=1.55e-04  dt=  37.0ms  words=54,550,528
[E05   468/1548 G   6659|CLM] train=4.3077  mask=14.6%  norm=0.795  lr=1.55e-04  dt=  37.0ms  words=54,558,720
[E05   469/1548 G   6660|CLM] train=4.8882  mask=14.6%  norm=1.034  lr=1.55e-04  dt=  37.2ms  words=54,566,912
[E05   470/1548 G   6661|CLM] train=4.0742  mask=14.6%  norm=0.639  lr=1.55e-04  dt=  37.1ms  words=54,575,104
[E05   471/1548 G   6662|CLM] train=2.3603  mask=14.6%  norm=1.447  lr=1.55e-04  dt=  37.2ms  words=54,583,296
[E05   472/1548 G   6663|CLM] train=4.3564  mask=14.6%  norm=0.748  lr=1.55e-04  dt=  37.1ms  words=54,591,488
[E05   473/1548 G   6664|CLM] train=3.5936  mask=14.6%  norm=0.716  lr=1.55e-04  dt=  36.9ms  words=54,599,680
[E05   474/1548 G   6665|CLM] train=4.0011  mask=14.6%  norm=0.705  lr=1.55e-04  dt=  37.0ms  words=54,607,872
[E05   475/1548 G   6666|CLM] train=2.6335  mask=14.6%  norm=0.721  lr=1.55e-04  dt=  37.2ms  words=54,616,064
[E05   476/1548 G   6667|CLM] train=2.6418  mask=14.6%  norm=0.655  lr=1.55e-04  dt=  37.0ms  words=54,624,256
[E05   477/1548 G   6668|CLM] train=3.8098  mask=14.6%  norm=0.807  lr=1.55e-04  dt=  37.1ms  words=54,632,448
[E05   478/1548 G   6669|CLM] train=4.5753  mask=14.6%  norm=0.837  lr=1.55e-04  dt=  37.2ms  words=54,640,640
[E05   479/1548 G   6670|CLM] train=5.2137  mask=14.6%  norm=1.207  lr=1.54e-04  dt=  37.2ms  words=54,648,832
[E05   480/1548 G   6671|CLM] train=4.0240  mask=14.6%  norm=0.733  lr=1.54e-04  dt=  37.1ms  words=54,657,024
[E05   481/1548 G   6672|CLM] train=4.4693  mask=14.6%  norm=0.796  lr=1.54e-04  dt=  37.0ms  words=54,665,216
[E05   482/1548 G   6673|CLM] train=4.3965  mask=14.6%  norm=0.837  lr=1.54e-04  dt=  37.2ms  words=54,673,408
[E05   483/1548 G   6674|CLM] train=2.1602  mask=14.6%  norm=0.928  lr=1.54e-04  dt=  37.0ms  words=54,681,600
[E05   484/1548 G   6675|CLM] train=1.9986  mask=14.6%  norm=0.636  lr=1.54e-04  dt=  37.0ms  words=54,689,792
[E05   485/1548 G   6676|CLM] train=4.4449  mask=14.6%  norm=0.852  lr=1.54e-04  dt=  37.0ms  words=54,697,984
[E05   486/1548 G   6677|CLM] train=1.9050  mask=14.6%  norm=0.580  lr=1.54e-04  dt=  37.2ms  words=54,706,176
[E05   487/1548 G   6678|CLM] train=2.5480  mask=14.6%  norm=0.609  lr=1.54e-04  dt=  37.3ms  words=54,714,368
[E05   488/1548 G   6679|CLM] train=2.1939  mask=14.6%  norm=0.601  lr=1.54e-04  dt=  37.4ms  words=54,722,560
[E05   489/1548 G   6680|CLM] train=4.0770  mask=14.6%  norm=0.798  lr=1.54e-04  dt=  37.6ms  words=54,730,752
[E05   490/1548 G   6681|CLM] train=4.5535  mask=14.6%  norm=1.234  lr=1.54e-04  dt=  37.3ms  words=54,738,944
[E05   491/1548 G   6682|CLM] train=2.5400  mask=14.6%  norm=0.715  lr=1.54e-04  dt=  37.4ms  words=54,747,136
[E05   492/1548 G   6683|CLM] train=2.5391  mask=14.6%  norm=1.137  lr=1.54e-04  dt=  37.2ms  words=54,755,328
[E05   493/1548 G   6684|CLM] train=4.9501  mask=14.6%  norm=1.170  lr=1.54e-04  dt=  37.2ms  words=54,763,520
[E05   494/1548 G   6685|CLM] train=2.2227  mask=14.6%  norm=0.788  lr=1.54e-04  dt=  37.2ms  words=54,771,712
[E05   495/1548 G   6686|CLM] train=4.1764  mask=14.6%  norm=0.841  lr=1.54e-04  dt=  37.1ms  words=54,779,904
[E05   496/1548 G   6687|CLM] train=4.2992  mask=14.6%  norm=0.872  lr=1.54e-04  dt=  37.3ms  words=54,788,096
[E05   497/1548 G   6688|CLM] train=4.7128  mask=14.6%  norm=0.889  lr=1.54e-04  dt=  36.9ms  words=54,796,288
[E05   498/1548 G   6689|CLM] train=2.1395  mask=14.6%  norm=0.729  lr=1.54e-04  dt=  37.1ms  words=54,804,480
[E05   499/1548 G   6690|CLM] train=4.0896  mask=14.6%  norm=0.744  lr=1.54e-04  dt=  37.1ms  words=54,812,672
[E05   500/1548 G   6691|CLM] train=2.1825  mask=14.6%  norm=0.719  lr=1.54e-04  dt=  37.1ms  words=54,820,864
[E05   501/1548 G   6692|CLM] train=4.4890  mask=14.6%  norm=1.210  lr=1.54e-04  dt=  37.2ms  words=54,829,056
[E05   502/1548 G   6693|CLM] train=3.9616  mask=14.6%  norm=0.726  lr=1.54e-04  dt=  37.1ms  words=54,837,248
[E05   503/1548 G   6694|CLM] train=3.9325  mask=14.6%  norm=0.833  lr=1.54e-04  dt=  37.2ms  words=54,845,440
[E05   504/1548 G   6695|CLM] train=3.8902  mask=14.6%  norm=0.814  lr=1.54e-04  dt=  37.4ms  words=54,853,632
[E05   505/1548 G   6696|CLM] train=4.2341  mask=14.6%  norm=1.057  lr=1.53e-04  dt=  38.8ms  words=54,861,824
[E05   506/1548 G   6697|CLM] train=2.3514  mask=14.6%  norm=0.817  lr=1.53e-04  dt=  38.5ms  words=54,870,016
[E05   507/1548 G   6698|CLM] train=4.3257  mask=14.6%  norm=0.729  lr=1.53e-04  dt=  37.3ms  words=54,878,208
[E05   508/1548 G   6699|CLM] train=4.5599  mask=14.6%  norm=0.786  lr=1.53e-04  dt=  38.5ms  words=54,886,400
[E05   509/1548 G   6700|CLM] train=4.7593  mask=14.6%  norm=0.993  lr=1.53e-04  dt=  38.9ms  words=54,894,592
[E05   510/1548 G   6701|CLM] train=1.9244  mask=14.6%  norm=0.713  lr=1.53e-04  dt=  38.3ms  words=54,902,784
[E05   511/1548 G   6702|CLM] train=4.3332  mask=14.6%  norm=0.758  lr=1.53e-04  dt=  37.0ms  words=54,910,976
[E05   512/1548 G   6703|CLM] train=2.3647  mask=14.6%  norm=0.671  lr=1.53e-04  dt=  37.0ms  words=54,919,168
[E05   513/1548 G   6704|CLM] train=4.0442  mask=14.6%  norm=0.840  lr=1.53e-04  dt=  37.4ms  words=54,927,360
[E05   514/1548 G   6705|CLM] train=3.9642  mask=14.6%  norm=0.698  lr=1.53e-04  dt=  37.3ms  words=54,935,552
[E05   515/1548 G   6706|CLM] train=4.2882  mask=14.6%  norm=0.774  lr=1.53e-04  dt=  37.2ms  words=54,943,744
[E05   516/1548 G   6707|CLM] train=4.2470  mask=14.6%  norm=0.982  lr=1.53e-04  dt=  37.0ms  words=54,951,936
[E05   517/1548 G   6708|CLM] train=4.2079  mask=14.6%  norm=0.729  lr=1.53e-04  dt=  45.7ms  words=54,960,128
[E05   518/1548 G   6709|CLM] train=2.3387  mask=14.6%  norm=0.679  lr=1.53e-04  dt=  46.8ms  words=54,968,320
[E05   519/1548 G   6710|CLM] train=2.2338  mask=14.6%  norm=0.980  lr=1.53e-04  dt=  46.9ms  words=54,976,512
[E05   520/1548 G   6711|CLM] train=4.7104  mask=14.6%  norm=0.779  lr=1.53e-04  dt=  46.4ms  words=54,984,704
[E05   521/1548 G   6712|CLM] train=4.3526  mask=14.6%  norm=0.811  lr=1.53e-04  dt=  42.8ms  words=54,992,896
[E05   522/1548 G   6713|CLM] train=2.7006  mask=14.6%  norm=0.793  lr=1.53e-04  dt=  37.0ms  words=55,001,088
[E05   523/1548 G   6714|CLM] train=3.0901  mask=14.6%  norm=0.753  lr=1.53e-04  dt=  36.9ms  words=55,009,280
[E05   524/1548 G   6715|CLM] train=2.2242  mask=14.6%  norm=0.626  lr=1.53e-04  dt=  37.1ms  words=55,017,472
[E05   525/1548 G   6716|CLM] train=3.8589  mask=14.6%  norm=1.006  lr=1.53e-04  dt=  37.0ms  words=55,025,664
[E05   526/1548 G   6717|CLM] train=4.2613  mask=14.6%  norm=0.905  lr=1.53e-04  dt=  36.9ms  words=55,033,856
[E05   527/1548 G   6718|CLM] train=3.6130  mask=14.6%  norm=0.767  lr=1.53e-04  dt=  36.9ms  words=55,042,048
[E05   528/1548 G   6719|CLM] train=4.1452  mask=14.6%  norm=1.487  lr=1.53e-04  dt=  37.0ms  words=55,050,240
[E05   529/1548 G   6720|CLM] train=2.4943  mask=14.6%  norm=0.804  lr=1.53e-04  dt=  37.0ms  words=55,058,432
[E05   530/1548 G   6721|CLM] train=4.5572  mask=14.6%  norm=0.951  lr=1.53e-04  dt=  37.0ms  words=55,066,624
[E05   531/1548 G   6722|CLM] train=4.1112  mask=14.6%  norm=0.755  lr=1.52e-04  dt=  36.9ms  words=55,074,816
[E05   532/1548 G   6723|CLM] train=3.9289  mask=14.6%  norm=0.824  lr=1.52e-04  dt=  37.0ms  words=55,083,008
[E05   533/1548 G   6724|CLM] train=4.0462  mask=14.6%  norm=0.889  lr=1.52e-04  dt=  37.0ms  words=55,091,200
[E05   534/1548 G   6725|CLM] train=4.2159  mask=14.6%  norm=0.874  lr=1.52e-04  dt=  36.9ms  words=55,099,392
[E05   535/1548 G   6726|CLM] train=2.7344  mask=14.6%  norm=0.646  lr=1.52e-04  dt=  36.8ms  words=55,107,584
[E05   536/1548 G   6727|CLM] train=2.6589  mask=14.6%  norm=0.924  lr=1.52e-04  dt=  36.9ms  words=55,115,776
[E05   537/1548 G   6728|CLM] train=3.5567  mask=14.6%  norm=0.743  lr=1.52e-04  dt=  37.1ms  words=55,123,968
[E05   538/1548 G   6729|CLM] train=2.7986  mask=14.6%  norm=1.444  lr=1.52e-04  dt=  37.0ms  words=55,132,160
[E05   539/1548 G   6730|CLM] train=3.9984  mask=14.6%  norm=1.018  lr=1.52e-04  dt=  37.2ms  words=55,140,352
[E05   540/1548 G   6731|CLM] train=2.2465  mask=14.6%  norm=0.686  lr=1.52e-04  dt=  37.2ms  words=55,148,544
[E05   541/1548 G   6732|CLM] train=3.5405  mask=14.6%  norm=0.686  lr=1.52e-04  dt=  36.8ms  words=55,156,736
[E05   542/1548 G   6733|CLM] train=2.4585  mask=14.6%  norm=0.802  lr=1.52e-04  dt=  37.1ms  words=55,164,928
[E05   543/1548 G   6734|CLM] train=3.7393  mask=14.6%  norm=0.726  lr=1.52e-04  dt=  36.9ms  words=55,173,120
[E05   544/1548 G   6735|CLM] train=2.3484  mask=14.6%  norm=0.642  lr=1.52e-04  dt=  37.0ms  words=55,181,312
[E05   545/1548 G   6736|CLM] train=4.8489  mask=14.6%  norm=1.007  lr=1.52e-04  dt=  36.9ms  words=55,189,504
[E05   546/1548 G   6737|CLM] train=2.5102  mask=14.6%  norm=0.672  lr=1.52e-04  dt=  36.9ms  words=55,197,696
[E05   547/1548 G   6738|CLM] train=2.3685  mask=14.6%  norm=0.961  lr=1.52e-04  dt=  36.9ms  words=55,205,888
[E05   548/1548 G   6739|CLM] train=4.1775  mask=14.6%  norm=0.896  lr=1.52e-04  dt=  36.9ms  words=55,214,080
[E05   549/1548 G   6740|CLM] train=2.1911  mask=14.6%  norm=0.958  lr=1.52e-04  dt=  37.0ms  words=55,222,272
[E05   550/1548 G   6741|CLM] train=2.5644  mask=14.6%  norm=0.733  lr=1.52e-04  dt=  36.9ms  words=55,230,464
[E05   551/1548 G   6742|CLM] train=3.5314  mask=14.6%  norm=0.675  lr=1.52e-04  dt=  37.0ms  words=55,238,656
[E05   552/1548 G   6743|CLM] train=2.1141  mask=14.6%  norm=0.894  lr=1.52e-04  dt=  37.1ms  words=55,246,848
[E05   553/1548 G   6744|CLM] train=2.1254  mask=14.6%  norm=0.818  lr=1.52e-04  dt=  36.8ms  words=55,255,040
[E05   554/1548 G   6745|CLM] train=5.0180  mask=14.6%  norm=0.895  lr=1.52e-04  dt=  36.7ms  words=55,263,232
[E05   555/1548 G   6746|CLM] train=3.8892  mask=14.6%  norm=0.747  lr=1.52e-04  dt=  37.1ms  words=55,271,424
[E05   556/1548 G   6747|CLM] train=4.8000  mask=14.6%  norm=0.989  lr=1.52e-04  dt=  37.0ms  words=55,279,616
[E05   557/1548 G   6748|CLM] train=2.7851  mask=14.6%  norm=0.791  lr=1.51e-04  dt=  37.0ms  words=55,287,808
[E05   558/1548 G   6749|CLM] train=4.2044  mask=14.6%  norm=0.761  lr=1.51e-04  dt=  37.4ms  words=55,296,000
[E05   559/1548 G   6750|CLM] train=3.7566  mask=14.5%  norm=0.795  lr=1.51e-04  dt=  37.1ms  words=55,304,192
[E05   560/1548 G   6751|CLM] train=2.5310  mask=14.5%  norm=0.871  lr=1.51e-04  dt=  36.9ms  words=55,312,384
[E05   561/1548 G   6752|CLM] train=2.6532  mask=14.5%  norm=0.817  lr=1.51e-04  dt=  36.9ms  words=55,320,576
[E05   562/1548 G   6753|CLM] train=4.5756  mask=14.5%  norm=1.091  lr=1.51e-04  dt=  36.9ms  words=55,328,768
[E05   563/1548 G   6754|CLM] train=4.7188  mask=14.5%  norm=0.969  lr=1.51e-04  dt=  37.1ms  words=55,336,960
[E05   564/1548 G   6755|CLM] train=4.6684  mask=14.5%  norm=0.984  lr=1.51e-04  dt=  36.9ms  words=55,345,152
[E05   565/1548 G   6756|CLM] train=4.8514  mask=14.5%  norm=0.919  lr=1.51e-04  dt=  36.9ms  words=55,353,344
[E05   566/1548 G   6757|CLM] train=3.5991  mask=14.5%  norm=0.716  lr=1.51e-04  dt=  36.8ms  words=55,361,536
[E05   567/1548 G   6758|CLM] train=2.2354  mask=14.5%  norm=0.738  lr=1.51e-04  dt=  37.0ms  words=55,369,728
[E05   568/1548 G   6759|CLM] train=4.7921  mask=14.5%  norm=1.060  lr=1.51e-04  dt=  36.8ms  words=55,377,920
[E05   569/1548 G   6760|CLM] train=4.5211  mask=14.5%  norm=0.817  lr=1.51e-04  dt=  37.1ms  words=55,386,112
[E05   570/1548 G   6761|CLM] train=3.9506  mask=14.5%  norm=0.830  lr=1.51e-04  dt=  36.9ms  words=55,394,304
[E05   571/1548 G   6762|CLM] train=2.5125  mask=14.5%  norm=0.786  lr=1.51e-04  dt=  36.9ms  words=55,402,496
[E05   572/1548 G   6763|CLM] train=2.2082  mask=14.5%  norm=0.837  lr=1.51e-04  dt=  36.8ms  words=55,410,688
[E05   573/1548 G   6764|CLM] train=4.5681  mask=14.5%  norm=1.158  lr=1.51e-04  dt=  36.8ms  words=55,418,880
[E05   574/1548 G   6765|CLM] train=4.4749  mask=14.5%  norm=0.954  lr=1.51e-04  dt=  36.9ms  words=55,427,072
[E05   575/1548 G   6766|CLM] train=4.0957  mask=14.5%  norm=0.887  lr=1.51e-04  dt=  37.1ms  words=55,435,264
[E05   576/1548 G   6767|CLM] train=4.4964  mask=14.5%  norm=0.856  lr=1.51e-04  dt=  36.9ms  words=55,443,456
[E05   577/1548 G   6768|CLM] train=4.1150  mask=14.5%  norm=1.028  lr=1.51e-04  dt=  36.8ms  words=55,451,648
[E05   578/1548 G   6769|CLM] train=4.2080  mask=14.5%  norm=1.214  lr=1.51e-04  dt=  36.8ms  words=55,459,840
[E05   579/1548 G   6770|CLM] train=2.3426  mask=14.5%  norm=0.825  lr=1.51e-04  dt=  37.1ms  words=55,468,032
[E05   580/1548 G   6771|CLM] train=2.6416  mask=14.5%  norm=0.787  lr=1.51e-04  dt=  36.8ms  words=55,476,224
[E05   581/1548 G   6772|CLM] train=4.4860  mask=14.5%  norm=0.850  lr=1.51e-04  dt=  37.0ms  words=55,484,416
[E05   582/1548 G   6773|CLM] train=2.6368  mask=14.5%  norm=0.682  lr=1.51e-04  dt=  37.1ms  words=55,492,608
[E05   583/1548 G   6774|CLM] train=3.9648  mask=14.5%  norm=0.896  lr=1.50e-04  dt=  37.0ms  words=55,500,800
[E05   584/1548 G   6775|CLM] train=2.2875  mask=14.5%  norm=0.823  lr=1.50e-04  dt=  36.9ms  words=55,508,992
[E05   585/1548 G   6776|CLM] train=2.3280  mask=14.5%  norm=0.775  lr=1.50e-04  dt=  36.9ms  words=55,517,184
[E05   586/1548 G   6777|CLM] train=4.5722  mask=14.5%  norm=1.092  lr=1.50e-04  dt=  36.7ms  words=55,525,376
[E05   587/1548 G   6778|CLM] train=2.2236  mask=14.5%  norm=0.670  lr=1.50e-04  dt=  37.0ms  words=55,533,568
[E05   588/1548 G   6779|CLM] train=2.3392  mask=14.5%  norm=0.722  lr=1.50e-04  dt=  36.8ms  words=55,541,760
[E05   589/1548 G   6780|CLM] train=4.4361  mask=14.5%  norm=0.834  lr=1.50e-04  dt=  36.8ms  words=55,549,952
[E05   590/1548 G   6781|CLM] train=2.3566  mask=14.5%  norm=0.746  lr=1.50e-04  dt=  36.9ms  words=55,558,144
[E05   591/1548 G   6782|CLM] train=2.4270  mask=14.5%  norm=0.643  lr=1.50e-04  dt=  36.9ms  words=55,566,336
[E05   592/1548 G   6783|CLM] train=2.5428  mask=14.5%  norm=0.848  lr=1.50e-04  dt=  36.9ms  words=55,574,528
[E05   593/1548 G   6784|CLM] train=4.3084  mask=14.5%  norm=1.149  lr=1.50e-04  dt=  37.0ms  words=55,582,720
[E05   594/1548 G   6785|CLM] train=3.9703  mask=14.5%  norm=0.780  lr=1.50e-04  dt=  36.9ms  words=55,590,912
[E05   595/1548 G   6786|CLM] train=4.3662  mask=14.5%  norm=0.870  lr=1.50e-04  dt=  37.1ms  words=55,599,104
[E05   596/1548 G   6787|CLM] train=4.3637  mask=14.5%  norm=0.993  lr=1.50e-04  dt=  37.0ms  words=55,607,296
[E05   597/1548 G   6788|CLM] train=2.7333  mask=14.5%  norm=0.892  lr=1.50e-04  dt=  36.9ms  words=55,615,488
[E05   598/1548 G   6789|CLM] train=4.2721  mask=14.5%  norm=0.885  lr=1.50e-04  dt=  36.8ms  words=55,623,680
[E05   599/1548 G   6790|CLM] train=2.3292  mask=14.5%  norm=0.673  lr=1.50e-04  dt=  37.1ms  words=55,631,872
[E05   600/1548 G   6791|CLM] train=4.2212  mask=14.5%  norm=0.841  lr=1.50e-04  dt=  36.9ms  words=55,640,064
[E05   601/1548 G   6792|CLM] train=4.2878  mask=14.5%  norm=0.760  lr=1.50e-04  dt=  36.7ms  words=55,648,256
[E05   602/1548 G   6793|CLM] train=2.8290  mask=14.5%  norm=0.723  lr=1.50e-04  dt=  36.9ms  words=55,656,448
[E05   603/1548 G   6794|CLM] train=3.6370  mask=14.5%  norm=0.721  lr=1.50e-04  dt=  37.2ms  words=55,664,640
[E05   604/1548 G   6795|CLM] train=4.1335  mask=14.5%  norm=0.815  lr=1.50e-04  dt=  36.9ms  words=55,672,832
[E05   605/1548 G   6796|CLM] train=2.5083  mask=14.5%  norm=0.676  lr=1.50e-04  dt=  36.8ms  words=55,681,024
[E05   606/1548 G   6797|CLM] train=2.4524  mask=14.5%  norm=0.646  lr=1.50e-04  dt=  36.9ms  words=55,689,216
[E05   607/1548 G   6798|CLM] train=4.2931  mask=14.5%  norm=0.926  lr=1.50e-04  dt=  36.9ms  words=55,697,408
[E05   608/1548 G   6799|CLM] train=5.2443  mask=14.5%  norm=1.242  lr=1.50e-04  dt=  36.8ms  words=55,705,600
[E05   609/1548 G   6800|CLM] train=4.4846  mask=14.5%  norm=0.999  lr=1.49e-04  dt=  37.1ms  words=55,713,792
[E05   610/1548 G   6801|CLM] train=2.3027  mask=14.5%  norm=0.702  lr=1.49e-04  dt=  37.2ms  words=55,721,984
[E05   611/1548 G   6802|CLM] train=4.2807  mask=14.5%  norm=0.891  lr=1.49e-04  dt=  36.9ms  words=55,730,176
[E05   612/1548 G   6803|CLM] train=4.0363  mask=14.5%  norm=1.186  lr=1.49e-04  dt=  36.9ms  words=55,738,368
[E05   613/1548 G   6804|CLM] train=3.9469  mask=14.5%  norm=0.786  lr=1.49e-04  dt=  36.9ms  words=55,746,560
[E05   614/1548 G   6805|CLM] train=2.7150  mask=14.5%  norm=0.627  lr=1.49e-04  dt=  37.1ms  words=55,754,752
[E05   615/1548 G   6806|CLM] train=5.0578  mask=14.5%  norm=1.172  lr=1.49e-04  dt=  36.9ms  words=55,762,944
[E05   616/1548 G   6807|CLM] train=2.1915  mask=14.5%  norm=0.804  lr=1.49e-04  dt=  36.9ms  words=55,771,136
[E05   617/1548 G   6808|CLM] train=3.7637  mask=14.5%  norm=0.775  lr=1.49e-04  dt=  37.0ms  words=55,779,328
[E05   618/1548 G   6809|CLM] train=2.6396  mask=14.5%  norm=0.642  lr=1.49e-04  dt=  37.0ms  words=55,787,520
[E05   619/1548 G   6810|CLM] train=4.4629  mask=14.5%  norm=1.017  lr=1.49e-04  dt=  36.8ms  words=55,795,712
[E05   620/1548 G   6811|CLM] train=2.5421  mask=14.5%  norm=0.705  lr=1.49e-04  dt=  36.8ms  words=55,803,904
[E05   621/1548 G   6812|CLM] train=3.9259  mask=14.5%  norm=0.788  lr=1.49e-04  dt=  37.0ms  words=55,812,096
[E05   622/1548 G   6813|CLM] train=4.2239  mask=14.5%  norm=0.789  lr=1.49e-04  dt=  37.1ms  words=55,820,288
[E05   623/1548 G   6814|CLM] train=4.1280  mask=14.5%  norm=0.732  lr=1.49e-04  dt=  37.1ms  words=55,828,480
[E05   624/1548 G   6815|CLM] train=4.5567  mask=14.5%  norm=1.165  lr=1.49e-04  dt=  37.0ms  words=55,836,672
[E05   625/1548 G   6816|CLM] train=2.0893  mask=14.5%  norm=0.762  lr=1.49e-04  dt=  36.8ms  words=55,844,864
[E05   626/1548 G   6817|CLM] train=3.8017  mask=14.5%  norm=0.850  lr=1.49e-04  dt=  36.9ms  words=55,853,056
[E05   627/1548 G   6818|CLM] train=4.9933  mask=14.5%  norm=1.168  lr=1.49e-04  dt=  36.9ms  words=55,861,248
[E05   628/1548 G   6819|CLM] train=2.4163  mask=14.5%  norm=0.628  lr=1.49e-04  dt=  36.8ms  words=55,869,440
[E05   629/1548 G   6820|CLM] train=4.5213  mask=14.5%  norm=0.851  lr=1.49e-04  dt=  36.8ms  words=55,877,632
[E05   630/1548 G   6821|CLM] train=2.8154  mask=14.5%  norm=0.745  lr=1.49e-04  dt=  37.0ms  words=55,885,824
[E05   631/1548 G   6822|CLM] train=4.5179  mask=14.5%  norm=0.829  lr=1.49e-04  dt=  36.9ms  words=55,894,016
[E05   632/1548 G   6823|CLM] train=2.1799  mask=14.5%  norm=0.680  lr=1.49e-04  dt=  36.8ms  words=55,902,208
[E05   633/1548 G   6824|CLM] train=4.2096  mask=14.5%  norm=0.851  lr=1.49e-04  dt=  36.9ms  words=55,910,400
[E05   634/1548 G   6825|CLM] train=4.0885  mask=14.5%  norm=0.766  lr=1.49e-04  dt=  37.0ms  words=55,918,592
[E05   635/1548 G   6826|CLM] train=3.7028  mask=14.5%  norm=0.906  lr=1.48e-04  dt=  36.8ms  words=55,926,784
[E05   636/1548 G   6827|CLM] train=3.8396  mask=14.5%  norm=0.732  lr=1.48e-04  dt=  37.3ms  words=55,934,976
[E05   637/1548 G   6828|CLM] train=3.4665  mask=14.5%  norm=0.799  lr=1.48e-04  dt=  39.2ms  words=55,943,168
[E05   638/1548 G   6829|CLM] train=4.1427  mask=14.5%  norm=0.768  lr=1.48e-04  dt=  45.8ms  words=55,951,360
[E05   639/1548 G   6830|CLM] train=2.3057  mask=14.5%  norm=0.749  lr=1.48e-04  dt=  37.3ms  words=55,959,552
[E05   640/1548 G   6831|CLM] train=4.4490  mask=14.5%  norm=0.755  lr=1.48e-04  dt=  37.1ms  words=55,967,744
[E05   641/1548 G   6832|CLM] train=2.3778  mask=14.5%  norm=0.667  lr=1.48e-04  dt=  37.8ms  words=55,975,936
[E05   642/1548 G   6833|CLM] train=2.3930  mask=14.5%  norm=0.827  lr=1.48e-04  dt=  37.6ms  words=55,984,128
[E05   643/1548 G   6834|CLM] train=2.4570  mask=14.5%  norm=0.678  lr=1.48e-04  dt=  38.6ms  words=55,992,320
[E05   644/1548 G   6835|CLM] train=3.7503  mask=14.5%  norm=0.907  lr=1.48e-04  dt=  39.3ms  words=56,000,512
[E05   645/1548 G   6836|CLM] train=2.0669  mask=14.5%  norm=0.658  lr=1.48e-04  dt=  38.4ms  words=56,008,704
[E05   646/1548 G   6837|CLM] train=4.1544  mask=14.5%  norm=0.898  lr=1.48e-04  dt=  38.7ms  words=56,016,896
[E05   647/1548 G   6838|CLM] train=4.1070  mask=14.5%  norm=0.901  lr=1.48e-04  dt=  38.0ms  words=56,025,088
[E05   648/1548 G   6839|CLM] train=4.6238  mask=14.5%  norm=0.822  lr=1.48e-04  dt=  45.9ms  words=56,033,280
[E05   649/1548 G   6840|CLM] train=3.7849  mask=14.5%  norm=0.765  lr=1.48e-04  dt=  37.2ms  words=56,041,472
[E05   650/1548 G   6841|CLM] train=3.9549  mask=14.5%  norm=0.721  lr=1.48e-04  dt=  37.3ms  words=56,049,664
[E05   651/1548 G   6842|CLM] train=4.1558  mask=14.5%  norm=0.851  lr=1.48e-04  dt=  37.5ms  words=56,057,856
[E05   652/1548 G   6843|CLM] train=4.5635  mask=14.5%  norm=1.009  lr=1.48e-04  dt=  38.0ms  words=56,066,048
[E05   653/1548 G   6844|CLM] train=3.6946  mask=14.5%  norm=0.757  lr=1.48e-04  dt=  39.9ms  words=56,074,240
[E05   654/1548 G   6845|CLM] train=4.0864  mask=14.5%  norm=0.687  lr=1.48e-04  dt=  39.6ms  words=56,082,432
[E05   655/1548 G   6846|CLM] train=2.4103  mask=14.5%  norm=1.137  lr=1.48e-04  dt=  39.5ms  words=56,090,624
[E05   656/1548 G   6847|CLM] train=4.0255  mask=14.5%  norm=0.863  lr=1.48e-04  dt=  37.2ms  words=56,098,816
[E05   657/1548 G   6848|CLM] train=2.5092  mask=14.5%  norm=0.754  lr=1.48e-04  dt=  37.0ms  words=56,107,008
[E05   658/1548 G   6849|CLM] train=2.0650  mask=14.5%  norm=0.808  lr=1.48e-04  dt=  37.0ms  words=56,115,200
[E05   659/1548 G   6850|CLM] train=2.3619  mask=14.5%  norm=0.701  lr=1.48e-04  dt=  37.0ms  words=56,123,392
[E05   660/1548 G   6851|CLM] train=2.3342  mask=14.5%  norm=0.860  lr=1.47e-04  dt=  37.3ms  words=56,131,584
[E05   661/1548 G   6852|CLM] train=2.9052  mask=14.5%  norm=1.161  lr=1.47e-04  dt=  37.3ms  words=56,139,776
[E05   662/1548 G   6853|CLM] train=4.5569  mask=14.5%  norm=0.884  lr=1.47e-04  dt=  37.1ms  words=56,147,968
[E05   663/1548 G   6854|CLM] train=2.4503  mask=14.5%  norm=0.610  lr=1.47e-04  dt=  42.9ms  words=56,156,160
[E05   664/1548 G   6855|CLM] train=3.5920  mask=14.5%  norm=0.850  lr=1.47e-04  dt=  42.7ms  words=56,164,352
[E05   665/1548 G   6856|CLM] train=3.7386  mask=14.5%  norm=0.855  lr=1.47e-04  dt=  39.8ms  words=56,172,544
[E05   666/1548 G   6857|CLM] train=4.6786  mask=14.5%  norm=0.913  lr=1.47e-04  dt=  37.7ms  words=56,180,736
[E05   667/1548 G   6858|CLM] train=2.4648  mask=14.5%  norm=0.762  lr=1.47e-04  dt=  38.1ms  words=56,188,928
[E05   668/1548 G   6859|CLM] train=3.7365  mask=14.5%  norm=0.744  lr=1.47e-04  dt=  37.3ms  words=56,197,120
[E05   669/1548 G   6860|CLM] train=4.4657  mask=14.5%  norm=1.132  lr=1.47e-04  dt=  38.4ms  words=56,205,312
[E05   670/1548 G   6861|CLM] train=4.6103  mask=14.5%  norm=0.994  lr=1.47e-04  dt=  37.3ms  words=56,213,504
[E05   671/1548 G   6862|CLM] train=4.2389  mask=14.5%  norm=0.957  lr=1.47e-04  dt=  37.7ms  words=56,221,696
[E05   672/1548 G   6863|CLM] train=4.1643  mask=14.5%  norm=0.750  lr=1.47e-04  dt=  37.9ms  words=56,229,888
[E05   673/1548 G   6864|CLM] train=2.2237  mask=14.5%  norm=0.744  lr=1.47e-04  dt=  38.7ms  words=56,238,080
[E05   674/1548 G   6865|CLM] train=3.7134  mask=14.5%  norm=0.809  lr=1.47e-04  dt=  37.7ms  words=56,246,272
[E05   675/1548 G   6866|CLM] train=2.0356  mask=14.5%  norm=0.814  lr=1.47e-04  dt=  37.3ms  words=56,254,464
[E05   676/1548 G   6867|CLM] train=2.1742  mask=14.5%  norm=0.807  lr=1.47e-04  dt=  37.5ms  words=56,262,656
[E05   677/1548 G   6868|CLM] train=2.5502  mask=14.5%  norm=0.658  lr=1.47e-04  dt=  38.9ms  words=56,270,848
[E05   678/1548 G   6869|CLM] train=4.4745  mask=14.5%  norm=0.947  lr=1.47e-04  dt=  37.6ms  words=56,279,040
[E05   679/1548 G   6870|CLM] train=4.5268  mask=14.5%  norm=0.874  lr=1.47e-04  dt=  37.3ms  words=56,287,232
[E05   680/1548 G   6871|CLM] train=4.1423  mask=14.5%  norm=0.811  lr=1.47e-04  dt=  37.2ms  words=56,295,424
[E05   681/1548 G   6872|CLM] train=2.3959  mask=14.5%  norm=0.753  lr=1.47e-04  dt=  37.3ms  words=56,303,616
[E05   682/1548 G   6873|CLM] train=4.3362  mask=14.5%  norm=0.854  lr=1.47e-04  dt=  37.0ms  words=56,311,808
[E05   683/1548 G   6874|CLM] train=4.9748  mask=14.4%  norm=1.012  lr=1.47e-04  dt=  37.2ms  words=56,320,000
[E05   684/1548 G   6875|CLM] train=4.0595  mask=14.4%  norm=0.693  lr=1.47e-04  dt=  37.5ms  words=56,328,192
[E05   685/1548 G   6876|CLM] train=4.1781  mask=14.4%  norm=0.801  lr=1.47e-04  dt=  36.9ms  words=56,336,384
[E05   686/1548 G   6877|CLM] train=1.9544  mask=14.4%  norm=0.679  lr=1.46e-04  dt=  37.2ms  words=56,344,576
[E05   687/1548 G   6878|CLM] train=2.5102  mask=14.4%  norm=0.814  lr=1.46e-04  dt=  37.5ms  words=56,352,768
[E05   688/1548 G   6879|CLM] train=4.1537  mask=14.4%  norm=1.066  lr=1.46e-04  dt=  37.2ms  words=56,360,960
[E05   689/1548 G   6880|CLM] train=3.4982  mask=14.4%  norm=0.777  lr=1.46e-04  dt=  37.2ms  words=56,369,152
[E05   690/1548 G   6881|CLM] train=2.3523  mask=14.4%  norm=0.747  lr=1.46e-04  dt=  37.2ms  words=56,377,344
[E05   691/1548 G   6882|CLM] train=3.4441  mask=14.4%  norm=0.790  lr=1.46e-04  dt=  37.2ms  words=56,385,536
[E05   692/1548 G   6883|CLM] train=4.3309  mask=14.4%  norm=0.872  lr=1.46e-04  dt=  37.2ms  words=56,393,728
[E05   693/1548 G   6884|CLM] train=4.3166  mask=14.4%  norm=0.954  lr=1.46e-04  dt=  37.0ms  words=56,401,920
[E05   694/1548 G   6885|CLM] train=3.4724  mask=14.4%  norm=3.837  lr=1.46e-04  dt=  37.3ms  words=56,410,112
[E05   695/1548 G   6886|CLM] train=5.3609  mask=14.4%  norm=1.359  lr=1.46e-04  dt=  37.3ms  words=56,418,304
[E05   696/1548 G   6887|CLM] train=2.5602  mask=14.4%  norm=1.056  lr=1.46e-04  dt=  37.1ms  words=56,426,496
[E05   697/1548 G   6888|CLM] train=4.3419  mask=14.4%  norm=0.839  lr=1.46e-04  dt=  37.0ms  words=56,434,688
[E05   698/1548 G   6889|CLM] train=4.7696  mask=14.4%  norm=1.027  lr=1.46e-04  dt=  37.5ms  words=56,442,880
[E05   699/1548 G   6890|CLM] train=4.6640  mask=14.4%  norm=0.822  lr=1.46e-04  dt=  37.4ms  words=56,451,072
[E05   700/1548 G   6891|CLM] train=4.4755  mask=14.4%  norm=0.999  lr=1.46e-04  dt=  37.5ms  words=56,459,264
[E05   701/1548 G   6892|CLM] train=3.9874  mask=14.4%  norm=1.786  lr=1.46e-04  dt=  37.6ms  words=56,467,456
[E05   702/1548 G   6893|CLM] train=2.2567  mask=14.4%  norm=0.939  lr=1.46e-04  dt=  37.5ms  words=56,475,648
[E05   703/1548 G   6894|CLM] train=4.1391  mask=14.4%  norm=0.846  lr=1.46e-04  dt=  37.6ms  words=56,483,840
[E05   704/1548 G   6895|CLM] train=2.5025  mask=14.4%  norm=0.884  lr=1.46e-04  dt=  37.7ms  words=56,492,032
[E05   705/1548 G   6896|CLM] train=3.9614  mask=14.4%  norm=0.851  lr=1.46e-04  dt=  37.1ms  words=56,500,224
[E05   706/1548 G   6897|CLM] train=4.3426  mask=14.4%  norm=1.466  lr=1.46e-04  dt=  37.3ms  words=56,508,416
[E05   707/1548 G   6898|CLM] train=2.1150  mask=14.4%  norm=0.649  lr=1.46e-04  dt=  36.9ms  words=56,516,608
[E05   708/1548 G   6899|CLM] train=3.7965  mask=14.4%  norm=0.914  lr=1.46e-04  dt=  36.9ms  words=56,524,800
[E05   709/1548 G   6900|CLM] train=1.4898  mask=14.4%  norm=0.597  lr=1.46e-04  dt=  37.3ms  words=56,532,992
[E05   710/1548 G   6901|CLM] train=2.8208  mask=14.4%  norm=0.703  lr=1.46e-04  dt=  37.1ms  words=56,541,184
[E05   711/1548 G   6902|CLM] train=4.0010  mask=14.4%  norm=0.761  lr=1.46e-04  dt=  37.1ms  words=56,549,376
[E05   712/1548 G   6903|CLM] train=4.0483  mask=14.4%  norm=0.903  lr=1.45e-04  dt=  37.0ms  words=56,557,568
[E05   713/1548 G   6904|CLM] train=2.5520  mask=14.4%  norm=1.711  lr=1.45e-04  dt=  37.1ms  words=56,565,760
[E05   714/1548 G   6905|CLM] train=3.7709  mask=14.4%  norm=0.797  lr=1.45e-04  dt=  37.2ms  words=56,573,952
[E05   715/1548 G   6906|CLM] train=4.8834  mask=14.4%  norm=1.363  lr=1.45e-04  dt=  37.1ms  words=56,582,144
[E05   716/1548 G   6907|CLM] train=3.6132  mask=14.4%  norm=0.752  lr=1.45e-04  dt=  37.4ms  words=56,590,336
[E05   717/1548 G   6908|CLM] train=4.2049  mask=14.4%  norm=0.999  lr=1.45e-04  dt=  37.2ms  words=56,598,528
[E05   718/1548 G   6909|CLM] train=4.2046  mask=14.4%  norm=0.800  lr=1.45e-04  dt=  37.1ms  words=56,606,720
[E05   719/1548 G   6910|CLM] train=4.5055  mask=14.4%  norm=0.897  lr=1.45e-04  dt=  37.1ms  words=56,614,912
[E05   720/1548 G   6911|CLM] train=3.3850  mask=14.4%  norm=0.739  lr=1.45e-04  dt=  38.2ms  words=56,623,104
[E05   721/1548 G   6912|CLM] train=2.0224  mask=14.4%  norm=0.671  lr=1.45e-04  dt=  37.3ms  words=56,631,296
[E05   722/1548 G   6913|CLM] train=4.4753  mask=14.4%  norm=0.861  lr=1.45e-04  dt=  37.0ms  words=56,639,488
[E05   723/1548 G   6914|CLM] train=2.8325  mask=14.4%  norm=0.716  lr=1.45e-04  dt=  37.2ms  words=56,647,680
[E05   724/1548 G   6915|CLM] train=5.5017  mask=14.4%  norm=2.494  lr=1.45e-04  dt=  37.2ms  words=56,655,872
[E05   725/1548 G   6916|CLM] train=3.8308  mask=14.4%  norm=0.847  lr=1.45e-04  dt=  37.0ms  words=56,664,064
[E05   726/1548 G   6917|CLM] train=2.1919  mask=14.4%  norm=0.726  lr=1.45e-04  dt=  36.9ms  words=56,672,256
[E05   727/1548 G   6918|CLM] train=4.8556  mask=14.4%  norm=0.806  lr=1.45e-04  dt=  38.7ms  words=56,680,448
[E05   728/1548 G   6919|CLM] train=2.3759  mask=14.4%  norm=0.719  lr=1.45e-04  dt=  37.0ms  words=56,688,640
[E05   729/1548 G   6920|CLM] train=4.4173  mask=14.4%  norm=0.911  lr=1.45e-04  dt=  37.6ms  words=56,696,832
[E05   730/1548 G   6921|CLM] train=5.0823  mask=14.4%  norm=0.896  lr=1.45e-04  dt=  37.3ms  words=56,705,024
[E05   731/1548 G   6922|CLM] train=1.9438  mask=14.4%  norm=0.919  lr=1.45e-04  dt=  37.6ms  words=56,713,216
[E05   732/1548 G   6923|CLM] train=5.5159  mask=14.4%  norm=1.214  lr=1.45e-04  dt=  37.2ms  words=56,721,408
[E05   733/1548 G   6924|CLM] train=4.2030  mask=14.4%  norm=0.930  lr=1.45e-04  dt=  37.2ms  words=56,729,600
[E05   734/1548 G   6925|CLM] train=2.1888  mask=14.4%  norm=0.905  lr=1.45e-04  dt=  37.1ms  words=56,737,792
[E05   735/1548 G   6926|CLM] train=2.7203  mask=14.4%  norm=0.677  lr=1.45e-04  dt=  37.2ms  words=56,745,984
[E05   736/1548 G   6927|CLM] train=3.9611  mask=14.4%  norm=0.859  lr=1.45e-04  dt=  37.1ms  words=56,754,176
[E05   737/1548 G   6928|CLM] train=4.4787  mask=14.4%  norm=0.847  lr=1.45e-04  dt=  37.1ms  words=56,762,368
[E05   738/1548 G   6929|CLM] train=3.9772  mask=14.4%  norm=0.843  lr=1.44e-04  dt=  37.2ms  words=56,770,560
[E05   739/1548 G   6930|CLM] train=5.5888  mask=14.4%  norm=1.087  lr=1.44e-04  dt=  37.2ms  words=56,778,752
[E05   740/1548 G   6931|CLM] train=2.2413  mask=14.4%  norm=0.776  lr=1.44e-04  dt=  37.1ms  words=56,786,944
[E05   741/1548 G   6932|CLM] train=2.2152  mask=14.4%  norm=0.675  lr=1.44e-04  dt=  37.1ms  words=56,795,136
[E05   742/1548 G   6933|CLM] train=2.2748  mask=14.4%  norm=1.209  lr=1.44e-04  dt=  37.3ms  words=56,803,328
[E05   743/1548 G   6934|CLM] train=4.5486  mask=14.4%  norm=0.955  lr=1.44e-04  dt=  37.1ms  words=56,811,520
[E05   744/1548 G   6935|CLM] train=2.3176  mask=14.4%  norm=0.713  lr=1.44e-04  dt=  37.4ms  words=56,819,712
[E05   745/1548 G   6936|CLM] train=5.0559  mask=14.4%  norm=1.109  lr=1.44e-04  dt=  37.0ms  words=56,827,904
[E05   746/1548 G   6937|CLM] train=3.9254  mask=14.4%  norm=0.739  lr=1.44e-04  dt=  37.2ms  words=56,836,096
[E05   747/1548 G   6938|CLM] train=2.1262  mask=14.4%  norm=0.790  lr=1.44e-04  dt=  37.1ms  words=56,844,288
[E05   748/1548 G   6939|CLM] train=1.9905  mask=14.4%  norm=0.694  lr=1.44e-04  dt=  37.1ms  words=56,852,480
[E05   749/1548 G   6940|CLM] train=4.2796  mask=14.4%  norm=0.823  lr=1.44e-04  dt=  37.3ms  words=56,860,672
[E05   750/1548 G   6941|CLM] train=4.5734  mask=14.4%  norm=0.797  lr=1.44e-04  dt=  36.9ms  words=56,868,864
[E05   751/1548 G   6942|CLM] train=4.1456  mask=14.4%  norm=0.697  lr=1.44e-04  dt=  37.3ms  words=56,877,056
[E05   752/1548 G   6943|CLM] train=2.1501  mask=14.4%  norm=0.691  lr=1.44e-04  dt=  37.2ms  words=56,885,248
[E05   753/1548 G   6944|CLM] train=4.2869  mask=14.4%  norm=0.848  lr=1.44e-04  dt=  37.1ms  words=56,893,440
[E05   754/1548 G   6945|CLM] train=4.3515  mask=14.4%  norm=0.832  lr=1.44e-04  dt=  37.2ms  words=56,901,632
[E05   755/1548 G   6946|CLM] train=4.3401  mask=14.4%  norm=0.935  lr=1.44e-04  dt=  37.3ms  words=56,909,824
[E05   756/1548 G   6947|CLM] train=2.3378  mask=14.4%  norm=0.649  lr=1.44e-04  dt=  37.1ms  words=56,918,016
[E05   757/1548 G   6948|CLM] train=2.0665  mask=14.4%  norm=0.622  lr=1.44e-04  dt=  37.0ms  words=56,926,208
[E05   758/1548 G   6949|CLM] train=2.5928  mask=14.4%  norm=0.792  lr=1.44e-04  dt=  37.1ms  words=56,934,400
[E05   759/1548 G   6950|CLM] train=5.0018  mask=14.4%  norm=1.575  lr=1.44e-04  dt=  37.4ms  words=56,942,592
[E05   760/1548 G   6951|CLM] train=4.0127  mask=14.4%  norm=0.809  lr=1.44e-04  dt=  37.0ms  words=56,950,784
[E05   761/1548 G   6952|CLM] train=2.5031  mask=14.4%  norm=0.657  lr=1.44e-04  dt=  37.1ms  words=56,958,976
[E05   762/1548 G   6953|CLM] train=3.9948  mask=14.4%  norm=0.837  lr=1.44e-04  dt=  37.1ms  words=56,967,168
[E05   763/1548 G   6954|CLM] train=4.7034  mask=14.4%  norm=0.837  lr=1.44e-04  dt=  37.0ms  words=56,975,360
[E05   764/1548 G   6955|CLM] train=2.3323  mask=14.4%  norm=1.206  lr=1.43e-04  dt=  37.1ms  words=56,983,552
[E05   765/1548 G   6956|CLM] train=2.2915  mask=14.4%  norm=0.577  lr=1.43e-04  dt=  37.2ms  words=56,991,744
[E05   766/1548 G   6957|CLM] train=2.2480  mask=14.4%  norm=0.906  lr=1.43e-04  dt=  37.2ms  words=56,999,936
[E05   767/1548 G   6958|CLM] train=2.5001  mask=14.4%  norm=0.692  lr=1.43e-04  dt=  37.1ms  words=57,008,128
[E05   768/1548 G   6959|CLM] train=5.2524  mask=14.4%  norm=1.046  lr=1.43e-04  dt=  37.5ms  words=57,016,320
[E05   769/1548 G   6960|CLM] train=3.9550  mask=14.4%  norm=0.982  lr=1.43e-04  dt=  37.2ms  words=57,024,512
[E05   770/1548 G   6961|CLM] train=4.4624  mask=14.4%  norm=1.117  lr=1.43e-04  dt=  47.3ms  words=57,032,704
[E05   771/1548 G   6962|CLM] train=2.4246  mask=14.4%  norm=0.705  lr=1.43e-04  dt=  45.6ms  words=57,040,896
[E05   772/1548 G   6963|CLM] train=4.2022  mask=14.4%  norm=0.770  lr=1.43e-04  dt=  37.8ms  words=57,049,088
[E05   773/1548 G   6964|CLM] train=4.8779  mask=14.4%  norm=1.460  lr=1.43e-04  dt=  37.1ms  words=57,057,280
[E05   774/1548 G   6965|CLM] train=2.1943  mask=14.4%  norm=0.890  lr=1.43e-04  dt=  47.5ms  words=57,065,472
[E05   775/1548 G   6966|CLM] train=4.3306  mask=14.4%  norm=0.868  lr=1.43e-04  dt=  41.1ms  words=57,073,664
[E05   776/1548 G   6967|CLM] train=3.7824  mask=14.4%  norm=0.819  lr=1.43e-04  dt=  37.5ms  words=57,081,856
[E05   777/1548 G   6968|CLM] train=4.3062  mask=14.4%  norm=0.801  lr=1.43e-04  dt=  39.1ms  words=57,090,048
[E05   778/1548 G   6969|CLM] train=4.1254  mask=14.4%  norm=0.811  lr=1.43e-04  dt=  43.0ms  words=57,098,240
[E05   779/1548 G   6970|CLM] train=2.2538  mask=14.4%  norm=0.735  lr=1.43e-04  dt=  38.3ms  words=57,106,432
[E05   780/1548 G   6971|CLM] train=4.0849  mask=14.4%  norm=0.804  lr=1.43e-04  dt=  40.6ms  words=57,114,624
[E05   781/1548 G   6972|CLM] train=2.0245  mask=14.4%  norm=0.994  lr=1.43e-04  dt=  46.5ms  words=57,122,816
[E05   782/1548 G   6973|CLM] train=2.7124  mask=14.4%  norm=0.698  lr=1.43e-04  dt=  45.0ms  words=57,131,008
[E05   783/1548 G   6974|CLM] train=4.0965  mask=14.4%  norm=0.741  lr=1.43e-04  dt=  46.7ms  words=57,139,200
[E05   784/1548 G   6975|CLM] train=2.8012  mask=14.4%  norm=0.705  lr=1.43e-04  dt=  37.0ms  words=57,147,392
[E05   785/1548 G   6976|CLM] train=2.2393  mask=14.4%  norm=1.026  lr=1.43e-04  dt=  37.2ms  words=57,155,584
[E05   786/1548 G   6977|CLM] train=2.5669  mask=14.4%  norm=0.742  lr=1.43e-04  dt=  38.6ms  words=57,163,776
[E05   787/1548 G   6978|CLM] train=3.8591  mask=14.4%  norm=1.265  lr=1.43e-04  dt=  42.8ms  words=57,171,968
[E05   788/1548 G   6979|CLM] train=2.1664  mask=14.4%  norm=0.686  lr=1.43e-04  dt=  38.7ms  words=57,180,160
[E05   789/1548 G   6980|CLM] train=4.2119  mask=14.4%  norm=0.996  lr=1.43e-04  dt=  38.3ms  words=57,188,352
[E05   790/1548 G   6981|CLM] train=3.5298  mask=14.4%  norm=0.857  lr=1.42e-04  dt=  41.5ms  words=57,196,544
[E05   791/1548 G   6982|CLM] train=4.2913  mask=14.4%  norm=0.795  lr=1.42e-04  dt=  37.3ms  words=57,204,736
[E05   792/1548 G   6983|CLM] train=2.3479  mask=14.4%  norm=0.738  lr=1.42e-04  dt=  46.5ms  words=57,212,928
[E05   793/1548 G   6984|CLM] train=4.2748  mask=14.4%  norm=2.059  lr=1.42e-04  dt=  44.3ms  words=57,221,120
[E05   794/1548 G   6985|CLM] train=2.1531  mask=14.4%  norm=0.867  lr=1.42e-04  dt=  37.5ms  words=57,229,312
[E05   795/1548 G   6986|CLM] train=3.9961  mask=14.4%  norm=0.830  lr=1.42e-04  dt=  37.6ms  words=57,237,504
[E05   796/1548 G   6987|CLM] train=4.2169  mask=14.4%  norm=1.000  lr=1.42e-04  dt=  37.5ms  words=57,245,696
[E05   797/1548 G   6988|CLM] train=4.4426  mask=14.4%  norm=0.802  lr=1.42e-04  dt=  37.5ms  words=57,253,888
[E05   798/1548 G   6989|CLM] train=4.3139  mask=14.4%  norm=0.887  lr=1.42e-04  dt=  37.1ms  words=57,262,080
[E05   799/1548 G   6990|CLM] train=1.7810  mask=14.4%  norm=1.034  lr=1.42e-04  dt=  37.3ms  words=57,270,272
[E05   800/1548 G   6991|CLM] train=4.0944  mask=14.4%  norm=0.797  lr=1.42e-04  dt=  37.2ms  words=57,278,464
[E05   801/1548 G   6992|CLM] train=3.7723  mask=14.4%  norm=0.826  lr=1.42e-04  dt=  37.1ms  words=57,286,656
[E05   802/1548 G   6993|CLM] train=4.2726  mask=14.4%  norm=0.898  lr=1.42e-04  dt=  37.1ms  words=57,294,848
[E05   803/1548 G   6994|CLM] train=2.6681  mask=14.4%  norm=0.772  lr=1.42e-04  dt=  37.2ms  words=57,303,040
[E05   804/1548 G   6995|CLM] train=4.2009  mask=14.4%  norm=0.724  lr=1.42e-04  dt=  37.2ms  words=57,311,232
[E05   805/1548 G   6996|CLM] train=4.0770  mask=14.4%  norm=1.013  lr=1.42e-04  dt=  37.1ms  words=57,319,424
[E05   806/1548 G   6997|CLM] train=4.2231  mask=14.3%  norm=0.805  lr=1.42e-04  dt=  37.1ms  words=57,327,616
[E05   807/1548 G   6998|CLM] train=2.4164  mask=14.3%  norm=0.942  lr=1.42e-04  dt=  37.1ms  words=57,335,808
[E05   808/1548 G   6999|CLM] train=4.1745  mask=14.3%  norm=0.876  lr=1.42e-04  dt=  36.9ms  words=57,344,000
[E05   809/1548 G   7000|CLM] train=4.7685  mask=14.3%  norm=0.907  lr=1.42e-04  dt=  36.9ms  words=57,352,192
[E05   810/1548 G   7001|CLM] train=4.0701  mask=14.3%  norm=0.798  lr=1.42e-04  dt=  37.1ms  words=57,360,384
[E05   811/1548 G   7002|CLM] train=2.7387  mask=14.3%  norm=0.789  lr=1.42e-04  dt=  37.1ms  words=57,368,576
[E05   812/1548 G   7003|CLM] train=3.9068  mask=14.3%  norm=0.801  lr=1.42e-04  dt=  37.1ms  words=57,376,768
[E05   813/1548 G   7004|CLM] train=2.2332  mask=14.3%  norm=0.650  lr=1.42e-04  dt=  37.2ms  words=57,384,960
[E05   814/1548 G   7005|CLM] train=3.9144  mask=14.3%  norm=0.849  lr=1.42e-04  dt=  37.0ms  words=57,393,152
[E05   815/1548 G   7006|CLM] train=4.5093  mask=14.3%  norm=0.851  lr=1.42e-04  dt=  36.9ms  words=57,401,344
[E05   816/1548 G   7007|CLM] train=3.3198  mask=14.3%  norm=0.743  lr=1.41e-04  dt=  37.1ms  words=57,409,536
[E05   817/1548 G   7008|CLM] train=4.6790  mask=14.3%  norm=0.876  lr=1.41e-04  dt=  37.1ms  words=57,417,728
[E05   818/1548 G   7009|CLM] train=4.2634  mask=14.3%  norm=0.847  lr=1.41e-04  dt=  37.1ms  words=57,425,920
[E05   819/1548 G   7010|CLM] train=4.2744  mask=14.3%  norm=0.854  lr=1.41e-04  dt=  37.1ms  words=57,434,112
[E05   820/1548 G   7011|CLM] train=2.2130  mask=14.3%  norm=0.698  lr=1.41e-04  dt=  37.1ms  words=57,442,304
[E05   821/1548 G   7012|CLM] train=2.0856  mask=14.3%  norm=0.671  lr=1.41e-04  dt=  37.0ms  words=57,450,496
[E05   822/1548 G   7013|CLM] train=3.7624  mask=14.3%  norm=0.869  lr=1.41e-04  dt=  36.9ms  words=57,458,688
[E05   823/1548 G   7014|CLM] train=4.2405  mask=14.3%  norm=0.750  lr=1.41e-04  dt=  37.0ms  words=57,466,880
[E05   824/1548 G   7015|CLM] train=4.9953  mask=14.3%  norm=1.178  lr=1.41e-04  dt=  37.1ms  words=57,475,072
[E05   825/1548 G   7016|CLM] train=5.6692  mask=14.3%  norm=1.365  lr=1.41e-04  dt=  37.0ms  words=57,483,264
[E05   826/1548 G   7017|CLM] train=2.0468  mask=14.3%  norm=0.925  lr=1.41e-04  dt=  37.2ms  words=57,491,456
[E05   827/1548 G   7018|CLM] train=4.4276  mask=14.3%  norm=0.845  lr=1.41e-04  dt=  37.2ms  words=57,499,648
[E05   828/1548 G   7019|CLM] train=4.2114  mask=14.3%  norm=0.755  lr=1.41e-04  dt=  37.0ms  words=57,507,840
[E05   829/1548 G   7020|CLM] train=2.1971  mask=14.3%  norm=0.701  lr=1.41e-04  dt=  37.0ms  words=57,516,032
[E05   830/1548 G   7021|CLM] train=2.5130  mask=14.3%  norm=1.010  lr=1.41e-04  dt=  37.1ms  words=57,524,224
[E05   831/1548 G   7022|CLM] train=3.8987  mask=14.3%  norm=0.990  lr=1.41e-04  dt=  37.0ms  words=57,532,416
[E05   832/1548 G   7023|CLM] train=2.5876  mask=14.3%  norm=0.715  lr=1.41e-04  dt=  36.8ms  words=57,540,608
[E05   833/1548 G   7024|CLM] train=4.0494  mask=14.3%  norm=0.745  lr=1.41e-04  dt=  37.0ms  words=57,548,800
[E05   834/1548 G   7025|CLM] train=3.0460  mask=14.3%  norm=2.955  lr=1.41e-04  dt=  37.4ms  words=57,556,992
[E05   835/1548 G   7026|CLM] train=2.5411  mask=14.3%  norm=1.277  lr=1.41e-04  dt=  37.1ms  words=57,565,184
[E05   836/1548 G   7027|CLM] train=2.6213  mask=14.3%  norm=0.704  lr=1.41e-04  dt=  37.0ms  words=57,573,376
[E05   837/1548 G   7028|CLM] train=4.1640  mask=14.3%  norm=0.829  lr=1.41e-04  dt=  37.1ms  words=57,581,568
[E05   838/1548 G   7029|CLM] train=4.9352  mask=14.3%  norm=2.526  lr=1.41e-04  dt=  37.0ms  words=57,589,760
[E05   839/1548 G   7030|CLM] train=4.4171  mask=14.3%  norm=0.993  lr=1.41e-04  dt=  37.1ms  words=57,597,952
[E05   840/1548 G   7031|CLM] train=4.5741  mask=14.3%  norm=0.863  lr=1.41e-04  dt=  37.1ms  words=57,606,144
[E05   841/1548 G   7032|CLM] train=2.2588  mask=14.3%  norm=0.735  lr=1.41e-04  dt=  37.2ms  words=57,614,336
[E05   842/1548 G   7033|CLM] train=4.3680  mask=14.3%  norm=0.799  lr=1.40e-04  dt=  37.1ms  words=57,622,528
[E05   843/1548 G   7034|CLM] train=2.6187  mask=14.3%  norm=0.786  lr=1.40e-04  dt=  37.0ms  words=57,630,720
[E05   844/1548 G   7035|CLM] train=4.2750  mask=14.3%  norm=0.806  lr=1.40e-04  dt=  36.9ms  words=57,638,912
[E05   845/1548 G   7036|CLM] train=5.1234  mask=14.3%  norm=0.896  lr=1.40e-04  dt=  37.0ms  words=57,647,104
[E05   846/1548 G   7037|CLM] train=3.4720  mask=14.3%  norm=0.947  lr=1.40e-04  dt=  37.0ms  words=57,655,296
[E05   847/1548 G   7038|CLM] train=4.0594  mask=14.3%  norm=0.939  lr=1.40e-04  dt=  37.2ms  words=57,663,488
[E05   848/1548 G   7039|CLM] train=2.4073  mask=14.3%  norm=0.805  lr=1.40e-04  dt=  37.1ms  words=57,671,680
[E05   849/1548 G   7040|CLM] train=2.5296  mask=14.3%  norm=0.801  lr=1.40e-04  dt=  37.2ms  words=57,679,872
[E05   850/1548 G   7041|CLM] train=2.3228  mask=14.3%  norm=0.754  lr=1.40e-04  dt=  36.9ms  words=57,688,064
[E05   851/1548 G   7042|CLM] train=4.4426  mask=14.3%  norm=1.076  lr=1.40e-04  dt=  36.9ms  words=57,696,256
[E05   852/1548 G   7043|CLM] train=4.2236  mask=14.3%  norm=0.859  lr=1.40e-04  dt=  37.1ms  words=57,704,448
[E05   853/1548 G   7044|CLM] train=4.1769  mask=14.3%  norm=0.779  lr=1.40e-04  dt=  37.2ms  words=57,712,640
[E05   854/1548 G   7045|CLM] train=2.2741  mask=14.3%  norm=0.640  lr=1.40e-04  dt=  37.2ms  words=57,720,832
[E05   855/1548 G   7046|CLM] train=3.6385  mask=14.3%  norm=0.743  lr=1.40e-04  dt=  37.2ms  words=57,729,024
[E05   856/1548 G   7047|CLM] train=4.5639  mask=14.3%  norm=1.106  lr=1.40e-04  dt=  36.9ms  words=57,737,216
[E05   857/1548 G   7048|CLM] train=4.1867  mask=14.3%  norm=0.836  lr=1.40e-04  dt=  36.9ms  words=57,745,408
[E05   858/1548 G   7049|CLM] train=4.7299  mask=14.3%  norm=1.029  lr=1.40e-04  dt=  37.0ms  words=57,753,600
[E05   859/1548 G   7050|CLM] train=2.4074  mask=14.3%  norm=0.749  lr=1.40e-04  dt=  37.1ms  words=57,761,792
[E05   860/1548 G   7051|CLM] train=2.1600  mask=14.3%  norm=0.832  lr=1.40e-04  dt=  37.1ms  words=57,769,984
[E05   861/1548 G   7052|CLM] train=2.3607  mask=14.3%  norm=0.838  lr=1.40e-04  dt=  37.1ms  words=57,778,176
[E05   862/1548 G   7053|CLM] train=4.1805  mask=14.3%  norm=0.870  lr=1.40e-04  dt=  37.0ms  words=57,786,368
[E05   863/1548 G   7054|CLM] train=3.7021  mask=14.3%  norm=0.823  lr=1.40e-04  dt=  36.9ms  words=57,794,560
[E05   864/1548 G   7055|CLM] train=2.0252  mask=14.3%  norm=0.840  lr=1.40e-04  dt=  37.0ms  words=57,802,752
[E05   865/1548 G   7056|CLM] train=4.0896  mask=14.3%  norm=1.032  lr=1.40e-04  dt=  37.0ms  words=57,810,944
[E05   866/1548 G   7057|CLM] train=2.3048  mask=14.3%  norm=0.715  lr=1.40e-04  dt=  37.0ms  words=57,819,136
[E05   867/1548 G   7058|CLM] train=2.3246  mask=14.3%  norm=0.766  lr=1.40e-04  dt=  36.9ms  words=57,827,328
[E05   868/1548 G   7059|CLM] train=2.4789  mask=14.3%  norm=0.733  lr=1.40e-04  dt=  36.8ms  words=57,835,520
[E05   869/1548 G   7060|CLM] train=4.8580  mask=14.3%  norm=1.228  lr=1.39e-04  dt=  37.0ms  words=57,843,712
[E05   870/1548 G   7061|CLM] train=3.9567  mask=14.3%  norm=0.821  lr=1.39e-04  dt=  37.0ms  words=57,851,904
[E05   871/1548 G   7062|CLM] train=4.8461  mask=14.3%  norm=1.014  lr=1.39e-04  dt=  36.9ms  words=57,860,096
[E05   872/1548 G   7063|CLM] train=4.4173  mask=14.3%  norm=0.786  lr=1.39e-04  dt=  36.9ms  words=57,868,288
[E05   873/1548 G   7064|CLM] train=3.9606  mask=14.3%  norm=0.783  lr=1.39e-04  dt=  36.9ms  words=57,876,480
[E05   874/1548 G   7065|CLM] train=4.2621  mask=14.3%  norm=0.929  lr=1.39e-04  dt=  37.0ms  words=57,884,672
[E05   875/1548 G   7066|CLM] train=4.2806  mask=14.3%  norm=0.833  lr=1.39e-04  dt=  36.9ms  words=57,892,864
[E05   876/1548 G   7067|CLM] train=2.2500  mask=14.3%  norm=0.816  lr=1.39e-04  dt=  37.2ms  words=57,901,056
[E05   877/1548 G   7068|CLM] train=4.3374  mask=14.3%  norm=1.002  lr=1.39e-04  dt=  37.1ms  words=57,909,248
[E05   878/1548 G   7069|CLM] train=2.1892  mask=14.3%  norm=0.777  lr=1.39e-04  dt=  37.1ms  words=57,917,440
[E05   879/1548 G   7070|CLM] train=2.8477  mask=14.3%  norm=0.943  lr=1.39e-04  dt=  37.1ms  words=57,925,632
[E05   880/1548 G   7071|CLM] train=3.0286  mask=14.3%  norm=0.753  lr=1.39e-04  dt=  37.0ms  words=57,933,824
[E05   881/1548 G   7072|CLM] train=5.3908  mask=14.3%  norm=1.449  lr=1.39e-04  dt=  37.0ms  words=57,942,016
[E05   882/1548 G   7073|CLM] train=2.0865  mask=14.3%  norm=1.048  lr=1.39e-04  dt=  37.2ms  words=57,950,208
[E05   883/1548 G   7074|CLM] train=2.4522  mask=14.3%  norm=0.725  lr=1.39e-04  dt=  37.1ms  words=57,958,400
[E05   884/1548 G   7075|CLM] train=4.4604  mask=14.3%  norm=0.870  lr=1.39e-04  dt=  37.1ms  words=57,966,592
[E05   885/1548 G   7076|CLM] train=4.2512  mask=14.3%  norm=0.834  lr=1.39e-04  dt=  37.0ms  words=57,974,784
[E05   886/1548 G   7077|CLM] train=4.9493  mask=14.3%  norm=0.935  lr=1.39e-04  dt=  38.0ms  words=57,982,976
[E05   887/1548 G   7078|CLM] train=2.6094  mask=14.3%  norm=0.867  lr=1.39e-04  dt=  37.4ms  words=57,991,168
[E05   888/1548 G   7079|CLM] train=4.1514  mask=14.3%  norm=0.879  lr=1.39e-04  dt=  37.2ms  words=57,999,360
[E05   889/1548 G   7080|CLM] train=2.2246  mask=14.3%  norm=0.727  lr=1.39e-04  dt=  37.0ms  words=58,007,552
[E05   890/1548 G   7081|CLM] train=2.1336  mask=14.3%  norm=0.704  lr=1.39e-04  dt=  37.2ms  words=58,015,744
[E05   891/1548 G   7082|CLM] train=4.4176  mask=14.3%  norm=1.376  lr=1.39e-04  dt=  37.2ms  words=58,023,936
[E05   892/1548 G   7083|CLM] train=2.3160  mask=14.3%  norm=0.814  lr=1.39e-04  dt=  37.1ms  words=58,032,128
[E05   893/1548 G   7084|CLM] train=3.5957  mask=14.3%  norm=0.811  lr=1.39e-04  dt=  37.2ms  words=58,040,320
[E05   894/1548 G   7085|CLM] train=2.5674  mask=14.3%  norm=0.905  lr=1.39e-04  dt=  37.0ms  words=58,048,512
[E05   895/1548 G   7086|CLM] train=4.0941  mask=14.3%  norm=0.831  lr=1.38e-04  dt=  37.0ms  words=58,056,704
[E05   896/1548 G   7087|CLM] train=3.9894  mask=14.3%  norm=0.854  lr=1.38e-04  dt=  37.0ms  words=58,064,896
[E05   897/1548 G   7088|CLM] train=2.5834  mask=14.3%  norm=0.751  lr=1.38e-04  dt=  37.1ms  words=58,073,088
[E05   898/1548 G   7089|CLM] train=4.0997  mask=14.3%  norm=0.991  lr=1.38e-04  dt=  37.1ms  words=58,081,280
[E05   899/1548 G   7090|CLM] train=2.4136  mask=14.3%  norm=0.778  lr=1.38e-04  dt=  37.1ms  words=58,089,472
[E05   900/1548 G   7091|CLM] train=4.2068  mask=14.3%  norm=0.823  lr=1.38e-04  dt=  37.2ms  words=58,097,664
[E05   901/1548 G   7092|CLM] train=1.7732  mask=14.3%  norm=0.630  lr=1.38e-04  dt=  37.9ms  words=58,105,856
[E05   902/1548 G   7093|CLM] train=2.1476  mask=14.3%  norm=0.777  lr=1.38e-04  dt=  42.7ms  words=58,114,048
[E05   903/1548 G   7094|CLM] train=4.4749  mask=14.3%  norm=0.762  lr=1.38e-04  dt=  41.9ms  words=58,122,240
[E05   904/1548 G   7095|CLM] train=3.9305  mask=14.3%  norm=0.996  lr=1.38e-04  dt=  37.8ms  words=58,130,432
[E05   905/1548 G   7096|CLM] train=4.3758  mask=14.3%  norm=0.761  lr=1.38e-04  dt=  37.2ms  words=58,138,624
[E05   906/1548 G   7097|CLM] train=2.2610  mask=14.3%  norm=0.779  lr=1.38e-04  dt=  37.9ms  words=58,146,816
[E05   907/1548 G   7098|CLM] train=4.1371  mask=14.3%  norm=0.878  lr=1.38e-04  dt=  37.1ms  words=58,155,008
[E05   908/1548 G   7099|CLM] train=4.3222  mask=14.3%  norm=0.941  lr=1.38e-04  dt=  38.0ms  words=58,163,200
[E05   909/1548 G   7100|CLM] train=4.6314  mask=14.3%  norm=0.865  lr=1.38e-04  dt=  37.4ms  words=58,171,392
[E05   910/1548 G   7101|CLM] train=4.3751  mask=14.3%  norm=0.847  lr=1.38e-04  dt=  37.1ms  words=58,179,584
[E05   911/1548 G   7102|CLM] train=4.4082  mask=14.3%  norm=0.865  lr=1.38e-04  dt=  37.6ms  words=58,187,776
[E05   912/1548 G   7103|CLM] train=4.0353  mask=14.3%  norm=0.833  lr=1.38e-04  dt=  37.4ms  words=58,195,968
[E05   913/1548 G   7104|CLM] train=2.3877  mask=14.3%  norm=0.681  lr=1.38e-04  dt=  36.9ms  words=58,204,160
[E05   914/1548 G   7105|CLM] train=5.2592  mask=14.3%  norm=1.184  lr=1.38e-04  dt=  37.0ms  words=58,212,352
[E05   915/1548 G   7106|CLM] train=3.8227  mask=14.3%  norm=0.872  lr=1.38e-04  dt=  37.4ms  words=58,220,544
[E05   916/1548 G   7107|CLM] train=4.0999  mask=14.3%  norm=0.803  lr=1.38e-04  dt=  37.1ms  words=58,228,736
[E05   917/1548 G   7108|CLM] train=4.5930  mask=14.3%  norm=1.126  lr=1.38e-04  dt=  37.1ms  words=58,236,928
[E05   918/1548 G   7109|CLM] train=2.2021  mask=14.3%  norm=0.775  lr=1.38e-04  dt=  37.1ms  words=58,245,120
[E05   919/1548 G   7110|CLM] train=4.1855  mask=14.3%  norm=0.877  lr=1.38e-04  dt=  36.9ms  words=58,253,312
[E05   920/1548 G   7111|CLM] train=3.7905  mask=14.3%  norm=0.774  lr=1.38e-04  dt=  36.9ms  words=58,261,504
[E05   921/1548 G   7112|CLM] train=2.3600  mask=14.3%  norm=0.874  lr=1.37e-04  dt=  37.1ms  words=58,269,696
[E05   922/1548 G   7113|CLM] train=4.2293  mask=14.3%  norm=0.774  lr=1.37e-04  dt=  37.1ms  words=58,277,888
[E05   923/1548 G   7114|CLM] train=1.8168  mask=14.3%  norm=0.794  lr=1.37e-04  dt=  37.0ms  words=58,286,080
[E05   924/1548 G   7115|CLM] train=2.3230  mask=14.3%  norm=0.653  lr=1.37e-04  dt=  37.0ms  words=58,294,272
[E05   925/1548 G   7116|CLM] train=2.0856  mask=14.3%  norm=0.756  lr=1.37e-04  dt=  37.2ms  words=58,302,464
[E05   926/1548 G   7117|CLM] train=3.7710  mask=14.3%  norm=0.776  lr=1.37e-04  dt=  36.9ms  words=58,310,656
[E05   927/1548 G   7118|CLM] train=2.3247  mask=14.3%  norm=0.591  lr=1.37e-04  dt=  37.0ms  words=58,318,848
[E05   928/1548 G   7119|CLM] train=4.2007  mask=14.3%  norm=0.918  lr=1.37e-04  dt=  38.3ms  words=58,327,040
[E05   929/1548 G   7120|CLM] train=4.8908  mask=14.3%  norm=0.888  lr=1.37e-04  dt=  38.0ms  words=58,335,232
[E05   930/1548 G   7121|CLM] train=3.9584  mask=14.2%  norm=0.889  lr=1.37e-04  dt=  38.0ms  words=58,343,424
[E05   931/1548 G   7122|CLM] train=2.4763  mask=14.2%  norm=0.864  lr=1.37e-04  dt=  37.7ms  words=58,351,616
[E05   932/1548 G   7123|CLM] train=3.9444  mask=14.2%  norm=0.744  lr=1.37e-04  dt=  37.3ms  words=58,359,808
[E05   933/1548 G   7124|CLM] train=3.9862  mask=14.2%  norm=0.756  lr=1.37e-04  dt= 451.3ms  words=58,368,000
[E05   934/1548 G   7125|CLM] train=2.2511  mask=14.2%  norm=0.920  lr=1.37e-04  dt=  43.1ms  words=58,376,192
[E05   935/1548 G   7126|CLM] train=2.1778  mask=14.2%  norm=0.774  lr=1.37e-04  dt=  37.8ms  words=58,384,384
[E05   936/1548 G   7127|CLM] train=2.7287  mask=14.2%  norm=0.661  lr=1.37e-04  dt=  37.5ms  words=58,392,576
[E05   937/1548 G   7128|CLM] train=4.3186  mask=14.2%  norm=0.950  lr=1.37e-04  dt=  37.1ms  words=58,400,768
[E05   938/1548 G   7129|CLM] train=2.1917  mask=14.2%  norm=0.699  lr=1.37e-04  dt=  38.1ms  words=58,408,960
[E05   939/1548 G   7130|CLM] train=4.3398  mask=14.2%  norm=0.834  lr=1.37e-04  dt=  38.1ms  words=58,417,152
[E05   940/1548 G   7131|CLM] train=4.4572  mask=14.2%  norm=0.846  lr=1.37e-04  dt=  37.6ms  words=58,425,344
[E05   941/1548 G   7132|CLM] train=3.8230  mask=14.2%  norm=0.918  lr=1.37e-04  dt=  37.6ms  words=58,433,536
[E05   942/1548 G   7133|CLM] train=4.0244  mask=14.2%  norm=0.764  lr=1.37e-04  dt=  37.6ms  words=58,441,728
[E05   943/1548 G   7134|CLM] train=2.2185  mask=14.2%  norm=0.743  lr=1.37e-04  dt=  37.4ms  words=58,449,920
[E05   944/1548 G   7135|CLM] train=2.5550  mask=14.2%  norm=0.675  lr=1.37e-04  dt=  37.6ms  words=58,458,112
[E05   945/1548 G   7136|CLM] train=2.8148  mask=14.2%  norm=0.802  lr=1.37e-04  dt=  37.2ms  words=58,466,304
[E05   946/1548 G   7137|CLM] train=4.4770  mask=14.2%  norm=0.773  lr=1.37e-04  dt=  37.2ms  words=58,474,496
[E05   947/1548 G   7138|CLM] train=3.6256  mask=14.2%  norm=0.886  lr=1.36e-04  dt=  37.4ms  words=58,482,688
[E05   948/1548 G   7139|CLM] train=2.0891  mask=14.2%  norm=0.889  lr=1.36e-04  dt=  37.1ms  words=58,490,880
[E05   949/1548 G   7140|CLM] train=2.5916  mask=14.2%  norm=2.071  lr=1.36e-04  dt=  37.2ms  words=58,499,072
[E05   950/1548 G   7141|CLM] train=3.9418  mask=14.2%  norm=0.808  lr=1.36e-04  dt=  36.8ms  words=58,507,264
[E05   951/1548 G   7142|CLM] train=5.1445  mask=14.2%  norm=1.383  lr=1.36e-04  dt=  37.0ms  words=58,515,456
[E05   952/1548 G   7143|CLM] train=4.2985  mask=14.2%  norm=0.997  lr=1.36e-04  dt=  37.3ms  words=58,523,648
[E05   953/1548 G   7144|CLM] train=4.3185  mask=14.2%  norm=0.835  lr=1.36e-04  dt=  37.0ms  words=58,531,840
[E05   954/1548 G   7145|CLM] train=2.2654  mask=14.2%  norm=0.754  lr=1.36e-04  dt=  37.2ms  words=58,540,032
[E05   955/1548 G   7146|CLM] train=2.0508  mask=14.2%  norm=0.768  lr=1.36e-04  dt=  37.6ms  words=58,548,224
[E05   956/1548 G   7147|CLM] train=4.7221  mask=14.2%  norm=1.327  lr=1.36e-04  dt=  38.2ms  words=58,556,416
[E05   957/1548 G   7148|CLM] train=2.1732  mask=14.2%  norm=0.696  lr=1.36e-04  dt=  36.9ms  words=58,564,608
[E05   958/1548 G   7149|CLM] train=2.0690  mask=14.2%  norm=0.731  lr=1.36e-04  dt=  37.6ms  words=58,572,800
[E05   959/1548 G   7150|CLM] train=2.4411  mask=14.2%  norm=0.794  lr=1.36e-04  dt=  37.1ms  words=58,580,992
[E05   960/1548 G   7151|CLM] train=4.4290  mask=14.2%  norm=1.778  lr=1.36e-04  dt=  37.0ms  words=58,589,184
[E05   961/1548 G   7152|CLM] train=4.4031  mask=14.2%  norm=0.897  lr=1.36e-04  dt=  37.0ms  words=58,597,376
[E05   962/1548 G   7153|CLM] train=2.3863  mask=14.2%  norm=1.300  lr=1.36e-04  dt=  37.2ms  words=58,605,568
[E05   963/1548 G   7154|CLM] train=4.7407  mask=14.2%  norm=0.904  lr=1.36e-04  dt=  37.2ms  words=58,613,760
[E05   964/1548 G   7155|CLM] train=4.1076  mask=14.2%  norm=0.831  lr=1.36e-04  dt=  37.0ms  words=58,621,952
[E05   965/1548 G   7156|CLM] train=4.5413  mask=14.2%  norm=0.875  lr=1.36e-04  dt=  37.1ms  words=58,630,144
[E05   966/1548 G   7157|CLM] train=4.0520  mask=14.2%  norm=0.845  lr=1.36e-04  dt=  37.2ms  words=58,638,336
[E05   967/1548 G   7158|CLM] train=4.1779  mask=14.2%  norm=1.187  lr=1.36e-04  dt=  37.0ms  words=58,646,528
[E05   968/1548 G   7159|CLM] train=3.6023  mask=14.2%  norm=0.804  lr=1.36e-04  dt=  37.4ms  words=58,654,720
[E05   969/1548 G   7160|CLM] train=2.5197  mask=14.2%  norm=0.781  lr=1.36e-04  dt=  37.2ms  words=58,662,912
[E05   970/1548 G   7161|CLM] train=3.6962  mask=14.2%  norm=0.667  lr=1.36e-04  dt=  37.1ms  words=58,671,104
[E05   971/1548 G   7162|CLM] train=3.7019  mask=14.2%  norm=0.816  lr=1.36e-04  dt=  36.9ms  words=58,679,296
[E05   972/1548 G   7163|CLM] train=3.9255  mask=14.2%  norm=0.946  lr=1.36e-04  dt=  37.1ms  words=58,687,488
[E05   973/1548 G   7164|CLM] train=2.1501  mask=14.2%  norm=0.936  lr=1.35e-04  dt=  37.3ms  words=58,695,680
[E05   974/1548 G   7165|CLM] train=4.1592  mask=14.2%  norm=0.845  lr=1.35e-04  dt=  37.0ms  words=58,703,872
[E05   975/1548 G   7166|CLM] train=3.8972  mask=14.2%  norm=0.897  lr=1.35e-04  dt=  37.1ms  words=58,712,064
[E05   976/1548 G   7167|CLM] train=4.8681  mask=14.2%  norm=1.179  lr=1.35e-04  dt=  37.1ms  words=58,720,256
[E05   977/1548 G   7168|CLM] train=4.2831  mask=14.2%  norm=0.897  lr=1.35e-04  dt=  36.9ms  words=58,728,448
[E05   978/1548 G   7169|CLM] train=2.0264  mask=14.2%  norm=0.760  lr=1.35e-04  dt=  37.3ms  words=58,736,640
[E05   979/1548 G   7170|CLM] train=4.2364  mask=14.2%  norm=1.263  lr=1.35e-04  dt=  37.2ms  words=58,744,832
[E05   980/1548 G   7171|CLM] train=2.6774  mask=14.2%  norm=0.781  lr=1.35e-04  dt=  37.0ms  words=58,753,024
[E05   981/1548 G   7172|CLM] train=2.2695  mask=14.2%  norm=0.865  lr=1.35e-04  dt=  37.0ms  words=58,761,216
[E05   982/1548 G   7173|CLM] train=2.2886  mask=14.2%  norm=0.859  lr=1.35e-04  dt=  37.7ms  words=58,769,408
[E05   983/1548 G   7174|CLM] train=4.2482  mask=14.2%  norm=0.991  lr=1.35e-04  dt=  37.2ms  words=58,777,600
[E05   984/1548 G   7175|CLM] train=4.4962  mask=14.2%  norm=1.268  lr=1.35e-04  dt=  37.0ms  words=58,785,792
[E05   985/1548 G   7176|CLM] train=2.2198  mask=14.2%  norm=0.839  lr=1.35e-04  dt=  36.9ms  words=58,793,984
[E05   986/1548 G   7177|CLM] train=3.3810  mask=14.2%  norm=0.722  lr=1.35e-04  dt=  37.3ms  words=58,802,176
[E05   987/1548 G   7178|CLM] train=3.6359  mask=14.2%  norm=0.791  lr=1.35e-04  dt=  37.0ms  words=58,810,368
[E05   988/1548 G   7179|CLM] train=3.4045  mask=14.2%  norm=0.696  lr=1.35e-04  dt=  37.2ms  words=58,818,560
[E05   989/1548 G   7180|CLM] train=3.9106  mask=14.2%  norm=0.848  lr=1.35e-04  dt=  37.1ms  words=58,826,752
[E05   990/1548 G   7181|CLM] train=4.6854  mask=14.2%  norm=1.174  lr=1.35e-04  dt=  36.9ms  words=58,834,944
[E05   991/1548 G   7182|CLM] train=2.2579  mask=14.2%  norm=0.980  lr=1.35e-04  dt=  37.0ms  words=58,843,136
[E05   992/1548 G   7183|CLM] train=4.8785  mask=14.2%  norm=0.971  lr=1.35e-04  dt=  37.1ms  words=58,851,328
[E05   993/1548 G   7184|CLM] train=4.6340  mask=14.2%  norm=0.958  lr=1.35e-04  dt=  37.1ms  words=58,859,520
[E05   994/1548 G   7185|CLM] train=4.0182  mask=14.2%  norm=0.916  lr=1.35e-04  dt=  37.0ms  words=58,867,712
[E05   995/1548 G   7186|CLM] train=2.7429  mask=14.2%  norm=0.749  lr=1.35e-04  dt=  37.2ms  words=58,875,904
[E05   996/1548 G   7187|CLM] train=4.1734  mask=14.2%  norm=0.899  lr=1.35e-04  dt=  37.2ms  words=58,884,096
[E05   997/1548 G   7188|CLM] train=3.7807  mask=14.2%  norm=1.005  lr=1.35e-04  dt=  36.9ms  words=58,892,288
[E05   998/1548 G   7189|CLM] train=2.3740  mask=14.2%  norm=1.076  lr=1.35e-04  dt=  36.8ms  words=58,900,480
[E05   999/1548 G   7190|CLM] train=4.4469  mask=14.2%  norm=1.012  lr=1.34e-04  dt=  37.0ms  words=58,908,672
[E05  1000/1548 G   7191|CLM] train=5.0726  mask=14.2%  norm=1.589  lr=1.34e-04  dt=  37.0ms  words=58,916,864
[E05  1001/1548 G   7192|CLM] train=2.8398  mask=14.2%  norm=0.718  lr=1.34e-04  dt=  36.9ms  words=58,925,056
[E05  1002/1548 G   7193|CLM] train=4.5670  mask=14.2%  norm=0.915  lr=1.34e-04  dt=  36.9ms  words=58,933,248
[E05  1003/1548 G   7194|CLM] train=3.7475  mask=14.2%  norm=0.747  lr=1.34e-04  dt=  37.0ms  words=58,941,440
[E05  1004/1548 G   7195|CLM] train=3.8258  mask=14.2%  norm=0.780  lr=1.34e-04  dt=  37.0ms  words=58,949,632
[E05  1005/1548 G   7196|CLM] train=2.2903  mask=14.2%  norm=0.597  lr=1.34e-04  dt=  36.9ms  words=58,957,824
[E05  1006/1548 G   7197|CLM] train=2.2655  mask=14.2%  norm=0.659  lr=1.34e-04  dt=  37.1ms  words=58,966,016
[E05  1007/1548 G   7198|CLM] train=3.7703  mask=14.2%  norm=0.813  lr=1.34e-04  dt=  37.2ms  words=58,974,208
[E05  1008/1548 G   7199|CLM] train=4.7565  mask=14.2%  norm=0.973  lr=1.34e-04  dt=  37.1ms  words=58,982,400
[E05  1009/1548 G   7200|CLM] train=4.1435  mask=14.2%  norm=0.868  lr=1.34e-04  dt=  37.0ms  words=58,990,592
[E05  1010/1548 G   7201|CLM] train=4.4318  mask=14.2%  norm=0.904  lr=1.34e-04  dt=  37.2ms  words=58,998,784
[E05  1011/1548 G   7202|CLM] train=2.5818  mask=14.2%  norm=0.688  lr=1.34e-04  dt=  37.2ms  words=59,006,976
[E05  1012/1548 G   7203|CLM] train=2.3192  mask=14.2%  norm=0.665  lr=1.34e-04  dt=  37.0ms  words=59,015,168
[E05  1013/1548 G   7204|CLM] train=5.5831  mask=14.2%  norm=1.422  lr=1.34e-04  dt=  37.2ms  words=59,023,360
[E05  1014/1548 G   7205|CLM] train=4.1767  mask=14.2%  norm=1.464  lr=1.34e-04  dt=  37.1ms  words=59,031,552
[E05  1015/1548 G   7206|CLM] train=2.3073  mask=14.2%  norm=0.803  lr=1.34e-04  dt=  36.9ms  words=59,039,744
[E05  1016/1548 G   7207|CLM] train=2.1839  mask=14.2%  norm=0.797  lr=1.34e-04  dt=  37.0ms  words=59,047,936
[E05  1017/1548 G   7208|CLM] train=3.6341  mask=14.2%  norm=0.753  lr=1.34e-04  dt=  37.0ms  words=59,056,128
[E05  1018/1548 G   7209|CLM] train=4.8885  mask=14.2%  norm=0.913  lr=1.34e-04  dt=  37.1ms  words=59,064,320
[E05  1019/1548 G   7210|CLM] train=4.1671  mask=14.2%  norm=0.889  lr=1.34e-04  dt=  37.1ms  words=59,072,512
[E05  1020/1548 G   7211|CLM] train=4.0195  mask=14.2%  norm=0.820  lr=1.34e-04  dt=  37.1ms  words=59,080,704
[E05  1021/1548 G   7212|CLM] train=3.8937  mask=14.2%  norm=0.858  lr=1.34e-04  dt=  37.2ms  words=59,088,896
[E05  1022/1548 G   7213|CLM] train=2.3929  mask=14.2%  norm=0.782  lr=1.34e-04  dt=  37.0ms  words=59,097,088
[E05  1023/1548 G   7214|CLM] train=2.1542  mask=14.2%  norm=0.631  lr=1.34e-04  dt=  37.0ms  words=59,105,280
[E05  1024/1548 G   7215|CLM] train=2.3627  mask=14.2%  norm=0.875  lr=1.34e-04  dt=  37.0ms  words=59,113,472
[E05  1025/1548 G   7216|CLM] train=3.5604  mask=14.2%  norm=0.685  lr=1.33e-04  dt=  37.8ms  words=59,121,664
[E05  1026/1548 G   7217|CLM] train=4.3863  mask=14.2%  norm=0.781  lr=1.33e-04  dt=  42.1ms  words=59,129,856
[E05  1027/1548 G   7218|CLM] train=4.5631  mask=14.2%  norm=0.796  lr=1.33e-04  dt=  39.6ms  words=59,138,048
[E05  1028/1548 G   7219|CLM] train=2.5666  mask=14.2%  norm=0.666  lr=1.33e-04  dt=  43.7ms  words=59,146,240
[E05  1029/1548 G   7220|CLM] train=3.9208  mask=14.2%  norm=0.892  lr=1.33e-04  dt=  44.2ms  words=59,154,432
[E05  1030/1548 G   7221|CLM] train=4.8692  mask=14.2%  norm=0.934  lr=1.33e-04  dt=  42.9ms  words=59,162,624
[E05  1031/1548 G   7222|CLM] train=2.5183  mask=14.2%  norm=0.791  lr=1.33e-04  dt=  41.8ms  words=59,170,816
[E05  1032/1548 G   7223|CLM] train=4.0702  mask=14.2%  norm=0.966  lr=1.33e-04  dt=  38.7ms  words=59,179,008
[E05  1033/1548 G   7224|CLM] train=2.0894  mask=14.2%  norm=0.723  lr=1.33e-04  dt=  41.6ms  words=59,187,200
[E05  1034/1548 G   7225|CLM] train=4.3503  mask=14.2%  norm=1.046  lr=1.33e-04  dt=  37.0ms  words=59,195,392
[E05  1035/1548 G   7226|CLM] train=4.1974  mask=14.2%  norm=0.947  lr=1.33e-04  dt=  37.1ms  words=59,203,584
[E05  1036/1548 G   7227|CLM] train=2.6121  mask=14.2%  norm=0.703  lr=1.33e-04  dt=  38.2ms  words=59,211,776
[E05  1037/1548 G   7228|CLM] train=2.1579  mask=14.2%  norm=0.795  lr=1.33e-04  dt=  45.4ms  words=59,219,968
[E05  1038/1548 G   7229|CLM] train=3.9886  mask=14.2%  norm=1.026  lr=1.33e-04  dt=  37.4ms  words=59,228,160
[E05  1039/1548 G   7230|CLM] train=4.2127  mask=14.2%  norm=0.937  lr=1.33e-04  dt=  37.0ms  words=59,236,352
[E05  1040/1548 G   7231|CLM] train=2.1962  mask=14.2%  norm=0.616  lr=1.33e-04  dt=  41.3ms  words=59,244,544
[E05  1041/1548 G   7232|CLM] train=4.0901  mask=14.2%  norm=0.815  lr=1.33e-04  dt=  37.1ms  words=59,252,736
[E05  1042/1548 G   7233|CLM] train=4.7739  mask=14.2%  norm=1.007  lr=1.33e-04  dt=  37.1ms  words=59,260,928
[E05  1043/1548 G   7234|CLM] train=4.2393  mask=14.2%  norm=0.942  lr=1.33e-04  dt=  36.9ms  words=59,269,120
[E05  1044/1548 G   7235|CLM] train=4.6636  mask=14.2%  norm=0.982  lr=1.33e-04  dt=  38.5ms  words=59,277,312
[E05  1045/1548 G   7236|CLM] train=2.3376  mask=14.2%  norm=0.836  lr=1.33e-04  dt=  42.3ms  words=59,285,504
[E05  1046/1548 G   7237|CLM] train=2.7417  mask=14.2%  norm=0.945  lr=1.33e-04  dt=  42.9ms  words=59,293,696
[E05  1047/1548 G   7238|CLM] train=3.9748  mask=14.2%  norm=0.805  lr=1.33e-04  dt=  37.3ms  words=59,301,888
[E05  1048/1548 G   7239|CLM] train=2.1112  mask=14.2%  norm=0.854  lr=1.33e-04  dt=  37.1ms  words=59,310,080
[E05  1049/1548 G   7240|CLM] train=2.3016  mask=14.2%  norm=0.589  lr=1.33e-04  dt=  37.2ms  words=59,318,272
[E05  1050/1548 G   7241|CLM] train=3.7183  mask=14.2%  norm=0.845  lr=1.33e-04  dt=  37.1ms  words=59,326,464
[E05  1051/1548 G   7242|CLM] train=3.9912  mask=14.2%  norm=0.721  lr=1.33e-04  dt=  37.2ms  words=59,334,656
[E05  1052/1548 G   7243|CLM] train=2.6410  mask=14.2%  norm=0.709  lr=1.32e-04  dt=  37.1ms  words=59,342,848
[E05  1053/1548 G   7244|CLM] train=3.9142  mask=14.2%  norm=0.797  lr=1.32e-04  dt=  37.1ms  words=59,351,040
[E05  1054/1548 G   7245|CLM] train=2.2345  mask=14.1%  norm=0.652  lr=1.32e-04  dt=  37.2ms  words=59,359,232
[E05  1055/1548 G   7246|CLM] train=3.7903  mask=14.1%  norm=0.688  lr=1.32e-04  dt=  37.0ms  words=59,367,424
[E05  1056/1548 G   7247|CLM] train=2.3002  mask=14.1%  norm=0.810  lr=1.32e-04  dt=  36.9ms  words=59,375,616
[E05  1057/1548 G   7248|CLM] train=4.3544  mask=14.1%  norm=0.929  lr=1.32e-04  dt=  36.9ms  words=59,383,808
[E05  1058/1548 G   7249|CLM] train=2.4054  mask=14.1%  norm=0.654  lr=1.32e-04  dt=  37.1ms  words=59,392,000
[E05  1059/1548 G   7250|CLM] train=3.6906  mask=14.1%  norm=0.854  lr=1.32e-04  dt=  36.9ms  words=59,400,192
[E05  1060/1548 G   7251|CLM] train=4.5232  mask=14.1%  norm=1.010  lr=1.32e-04  dt=  37.0ms  words=59,408,384
[E05  1061/1548 G   7252|CLM] train=4.3062  mask=14.1%  norm=0.931  lr=1.32e-04  dt=  37.0ms  words=59,416,576
[E05  1062/1548 G   7253|CLM] train=3.7729  mask=14.1%  norm=0.870  lr=1.32e-04  dt=  37.9ms  words=59,424,768
[E05  1063/1548 G   7254|CLM] train=2.7221  mask=14.1%  norm=0.803  lr=1.32e-04  dt=  37.0ms  words=59,432,960
[E05  1064/1548 G   7255|CLM] train=2.0727  mask=14.1%  norm=0.740  lr=1.32e-04  dt=  37.0ms  words=59,441,152
[E05  1065/1548 G   7256|CLM] train=2.3098  mask=14.1%  norm=0.616  lr=1.32e-04  dt=  37.3ms  words=59,449,344
[E05  1066/1548 G   7257|CLM] train=3.8631  mask=14.1%  norm=0.891  lr=1.32e-04  dt=  37.0ms  words=59,457,536
[E05  1067/1548 G   7258|CLM] train=3.9617  mask=14.1%  norm=0.877  lr=1.32e-04  dt=  37.1ms  words=59,465,728
[E05  1068/1548 G   7259|CLM] train=3.8556  mask=14.1%  norm=0.747  lr=1.32e-04  dt=  37.1ms  words=59,473,920
[E05  1069/1548 G   7260|CLM] train=2.6684  mask=14.1%  norm=0.739  lr=1.32e-04  dt=  36.9ms  words=59,482,112
[E05  1070/1548 G   7261|CLM] train=2.3346  mask=14.1%  norm=0.682  lr=1.32e-04  dt=  37.0ms  words=59,490,304
[E05  1071/1548 G   7262|CLM] train=4.8081  mask=14.1%  norm=1.610  lr=1.32e-04  dt=  37.0ms  words=59,498,496
[E05  1072/1548 G   7263|CLM] train=2.7879  mask=14.1%  norm=0.663  lr=1.32e-04  dt=  37.1ms  words=59,506,688
[E05  1073/1548 G   7264|CLM] train=3.9225  mask=14.1%  norm=0.680  lr=1.32e-04  dt=  37.1ms  words=59,514,880
[E05  1074/1548 G   7265|CLM] train=3.6988  mask=14.1%  norm=1.124  lr=1.32e-04  dt=  37.4ms  words=59,523,072
[E05  1075/1548 G   7266|CLM] train=5.0684  mask=14.1%  norm=1.312  lr=1.32e-04  dt=  37.2ms  words=59,531,264
[E05  1076/1548 G   7267|CLM] train=4.1821  mask=14.1%  norm=0.867  lr=1.32e-04  dt=  37.0ms  words=59,539,456
[E05  1077/1548 G   7268|CLM] train=2.8208  mask=14.1%  norm=0.990  lr=1.32e-04  dt=  37.1ms  words=59,547,648
[E05  1078/1548 G   7269|CLM] train=4.3004  mask=14.1%  norm=0.767  lr=1.31e-04  dt=  37.1ms  words=59,555,840
[E05  1079/1548 G   7270|CLM] train=3.9607  mask=14.1%  norm=0.723  lr=1.31e-04  dt=  37.1ms  words=59,564,032
[E05  1080/1548 G   7271|CLM] train=2.2289  mask=14.1%  norm=0.640  lr=1.31e-04  dt=  37.0ms  words=59,572,224
[E05  1081/1548 G   7272|CLM] train=5.0022  mask=14.1%  norm=2.558  lr=1.31e-04  dt=  37.0ms  words=59,580,416
[E05  1082/1548 G   7273|CLM] train=2.4317  mask=14.1%  norm=0.705  lr=1.31e-04  dt=  37.0ms  words=59,588,608
[E05  1083/1548 G   7274|CLM] train=2.2993  mask=14.1%  norm=0.778  lr=1.31e-04  dt=  37.1ms  words=59,596,800
[E05  1084/1548 G   7275|CLM] train=1.5565  mask=14.1%  norm=0.581  lr=1.31e-04  dt=  37.0ms  words=59,604,992
[E05  1085/1548 G   7276|CLM] train=4.2324  mask=14.1%  norm=0.728  lr=1.31e-04  dt=  37.2ms  words=59,613,184
[E05  1086/1548 G   7277|CLM] train=2.1664  mask=14.1%  norm=0.720  lr=1.31e-04  dt=  37.0ms  words=59,621,376
[E05  1087/1548 G   7278|CLM] train=4.0689  mask=14.1%  norm=0.888  lr=1.31e-04  dt=  36.8ms  words=59,629,568
[E05  1088/1548 G   7279|CLM] train=2.4249  mask=14.1%  norm=0.903  lr=1.31e-04  dt=  37.0ms  words=59,637,760
[E05  1089/1548 G   7280|CLM] train=2.1221  mask=14.1%  norm=0.767  lr=1.31e-04  dt=  37.3ms  words=59,645,952
[E05  1090/1548 G   7281|CLM] train=4.0904  mask=14.1%  norm=0.713  lr=1.31e-04  dt=  37.2ms  words=59,654,144
[E05  1091/1548 G   7282|CLM] train=4.8431  mask=14.1%  norm=0.835  lr=1.31e-04  dt=  37.2ms  words=59,662,336
[E05  1092/1548 G   7283|CLM] train=3.8060  mask=14.1%  norm=0.905  lr=1.31e-04  dt=  37.2ms  words=59,670,528
[E05  1093/1548 G   7284|CLM] train=3.5438  mask=14.1%  norm=0.700  lr=1.31e-04  dt=  37.2ms  words=59,678,720
[E05  1094/1548 G   7285|CLM] train=2.3517  mask=14.1%  norm=0.774  lr=1.31e-04  dt=  37.2ms  words=59,686,912
[E05  1095/1548 G   7286|CLM] train=5.1357  mask=14.1%  norm=5.942  lr=1.31e-04  dt=  37.1ms  words=59,695,104
[E05  1096/1548 G   7287|CLM] train=2.4391  mask=14.1%  norm=0.971  lr=1.31e-04  dt=  38.0ms  words=59,703,296
[E05  1097/1548 G   7288|CLM] train=3.8012  mask=14.1%  norm=0.873  lr=1.31e-04  dt=  37.4ms  words=59,711,488
[E05  1098/1548 G   7289|CLM] train=5.1991  mask=14.1%  norm=1.367  lr=1.31e-04  dt=  37.1ms  words=59,719,680
[E05  1099/1548 G   7290|CLM] train=5.2484  mask=14.1%  norm=0.920  lr=1.31e-04  dt=  37.1ms  words=59,727,872
[E05  1100/1548 G   7291|CLM] train=2.5082  mask=14.1%  norm=0.635  lr=1.31e-04  dt=  37.0ms  words=59,736,064
[E05  1101/1548 G   7292|CLM] train=2.2923  mask=14.1%  norm=0.668  lr=1.31e-04  dt=  37.3ms  words=59,744,256
[E05  1102/1548 G   7293|CLM] train=2.3709  mask=14.1%  norm=0.695  lr=1.31e-04  dt=  37.1ms  words=59,752,448
[E05  1103/1548 G   7294|CLM] train=3.8320  mask=14.1%  norm=0.864  lr=1.31e-04  dt=  37.2ms  words=59,760,640
[E05  1104/1548 G   7295|CLM] train=4.4599  mask=14.1%  norm=0.881  lr=1.30e-04  dt=  37.1ms  words=59,768,832
[E05  1105/1548 G   7296|CLM] train=4.3431  mask=14.1%  norm=0.842  lr=1.30e-04  dt=  36.9ms  words=59,777,024
[E05  1106/1548 G   7297|CLM] train=2.2713  mask=14.1%  norm=0.704  lr=1.30e-04  dt=  36.8ms  words=59,785,216
[E05  1107/1548 G   7298|CLM] train=2.4365  mask=14.1%  norm=0.958  lr=1.30e-04  dt=  37.1ms  words=59,793,408
[E05  1108/1548 G   7299|CLM] train=4.6531  mask=14.1%  norm=0.937  lr=1.30e-04  dt=  37.1ms  words=59,801,600
[E05  1109/1548 G   7300|CLM] train=2.3799  mask=14.1%  norm=0.707  lr=1.30e-04  dt=  37.2ms  words=59,809,792
[E05  1110/1548 G   7301|CLM] train=4.2612  mask=14.1%  norm=0.814  lr=1.30e-04  dt=  37.0ms  words=59,817,984
[E05  1111/1548 G   7302|CLM] train=4.3776  mask=14.1%  norm=0.766  lr=1.30e-04  dt=  37.1ms  words=59,826,176
[E05  1112/1548 G   7303|CLM] train=3.8806  mask=14.1%  norm=0.846  lr=1.30e-04  dt=  37.0ms  words=59,834,368
[E05  1113/1548 G   7304|CLM] train=2.6436  mask=14.1%  norm=0.777  lr=1.30e-04  dt=  36.9ms  words=59,842,560
[E05  1114/1548 G   7305|CLM] train=4.2887  mask=14.1%  norm=0.948  lr=1.30e-04  dt=  37.0ms  words=59,850,752
[E05  1115/1548 G   7306|CLM] train=4.8525  mask=14.1%  norm=0.876  lr=1.30e-04  dt=  37.2ms  words=59,858,944
[E05  1116/1548 G   7307|CLM] train=2.1381  mask=14.1%  norm=0.653  lr=1.30e-04  dt=  37.0ms  words=59,867,136
[E05  1117/1548 G   7308|CLM] train=3.5118  mask=14.1%  norm=0.805  lr=1.30e-04  dt=  37.2ms  words=59,875,328
[E05  1118/1548 G   7309|CLM] train=2.2796  mask=14.1%  norm=0.723  lr=1.30e-04  dt=  37.1ms  words=59,883,520
[E05  1119/1548 G   7310|CLM] train=4.8736  mask=14.1%  norm=1.044  lr=1.30e-04  dt=  37.1ms  words=59,891,712
[E05  1120/1548 G   7311|CLM] train=2.2530  mask=14.1%  norm=0.682  lr=1.30e-04  dt=  37.0ms  words=59,899,904
[E05  1121/1548 G   7312|CLM] train=4.2862  mask=14.1%  norm=1.021  lr=1.30e-04  dt=  37.2ms  words=59,908,096
[E05  1122/1548 G   7313|CLM] train=4.3878  mask=14.1%  norm=0.791  lr=1.30e-04  dt=  37.1ms  words=59,916,288
[E05  1123/1548 G   7314|CLM] train=2.5803  mask=14.1%  norm=0.726  lr=1.30e-04  dt=  37.1ms  words=59,924,480
[E05  1124/1548 G   7315|CLM] train=3.4497  mask=14.1%  norm=0.717  lr=1.30e-04  dt=  37.1ms  words=59,932,672
[E05  1125/1548 G   7316|CLM] train=4.7860  mask=14.1%  norm=1.685  lr=1.30e-04  dt=  37.1ms  words=59,940,864
[E05  1126/1548 G   7317|CLM] train=3.8903  mask=14.1%  norm=0.797  lr=1.30e-04  dt=  37.0ms  words=59,949,056
[E05  1127/1548 G   7318|CLM] train=4.4642  mask=14.1%  norm=0.868  lr=1.30e-04  dt=  37.0ms  words=59,957,248
[E05  1128/1548 G   7319|CLM] train=2.3043  mask=14.1%  norm=1.133  lr=1.30e-04  dt=  37.6ms  words=59,965,440
[E05  1129/1548 G   7320|CLM] train=2.2934  mask=14.1%  norm=0.689  lr=1.30e-04  dt=  37.0ms  words=59,973,632
[E05  1130/1548 G   7321|CLM] train=2.0863  mask=14.1%  norm=0.660  lr=1.30e-04  dt=  37.0ms  words=59,981,824
[E05  1131/1548 G   7322|CLM] train=4.0694  mask=14.1%  norm=0.816  lr=1.29e-04  dt=  37.1ms  words=59,990,016
[E05  1132/1548 G   7323|CLM] train=4.0805  mask=14.1%  norm=0.855  lr=1.29e-04  dt=  37.1ms  words=59,998,208
[E05  1133/1548 G   7324|CLM] train=4.0597  mask=14.1%  norm=0.898  lr=1.29e-04  dt=  37.0ms  words=60,006,400

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_60M'...
[Checkpoint] Checkpoint 'chck_60M' successfully saved.
[E05  1134/1548 G   7325|CLM] train=5.0319  mask=14.1%  norm=2.593  lr=1.29e-04  dt=  37.8ms  words=60,014,592
[E05  1135/1548 G   7326|CLM] train=2.7415  mask=14.1%  norm=0.692  lr=1.29e-04  dt=  38.0ms  words=60,022,784
[E05  1136/1548 G   7327|CLM] train=3.7298  mask=14.1%  norm=0.780  lr=1.29e-04  dt=  37.0ms  words=60,030,976
[E05  1137/1548 G   7328|CLM] train=4.4869  mask=14.1%  norm=0.867  lr=1.29e-04  dt=  37.4ms  words=60,039,168
[E05  1138/1548 G   7329|CLM] train=4.2910  mask=14.1%  norm=0.934  lr=1.29e-04  dt=  36.8ms  words=60,047,360
[E05  1139/1548 G   7330|CLM] train=2.1800  mask=14.1%  norm=0.831  lr=1.29e-04  dt=  36.9ms  words=60,055,552
[E05  1140/1548 G   7331|CLM] train=4.3420  mask=14.1%  norm=0.878  lr=1.29e-04  dt=  37.0ms  words=60,063,744
[E05  1141/1548 G   7332|CLM] train=2.2229  mask=14.1%  norm=0.697  lr=1.29e-04  dt=  37.0ms  words=60,071,936
[E05  1142/1548 G   7333|CLM] train=4.1612  mask=14.1%  norm=0.805  lr=1.29e-04  dt=  37.0ms  words=60,080,128
[E05  1143/1548 G   7334|CLM] train=2.9074  mask=14.1%  norm=0.723  lr=1.29e-04  dt=  37.0ms  words=60,088,320
[E05  1144/1548 G   7335|CLM] train=4.1986  mask=14.1%  norm=0.835  lr=1.29e-04  dt=  37.2ms  words=60,096,512
[E05  1145/1548 G   7336|CLM] train=3.9867  mask=14.1%  norm=1.055  lr=1.29e-04  dt=  37.0ms  words=60,104,704
[E05  1146/1548 G   7337|CLM] train=3.9972  mask=14.1%  norm=0.775  lr=1.29e-04  dt=  36.9ms  words=60,112,896
[E05  1147/1548 G   7338|CLM] train=4.3417  mask=14.1%  norm=0.910  lr=1.29e-04  dt=  37.0ms  words=60,121,088
[E05  1148/1548 G   7339|CLM] train=4.0352  mask=14.1%  norm=0.748  lr=1.29e-04  dt=  37.0ms  words=60,129,280
[E05  1149/1548 G   7340|CLM] train=4.6434  mask=14.1%  norm=0.879  lr=1.29e-04  dt=  37.1ms  words=60,137,472
[E05  1150/1548 G   7341|CLM] train=2.5278  mask=14.1%  norm=0.758  lr=1.29e-04  dt=  36.9ms  words=60,145,664
[E05  1151/1548 G   7342|CLM] train=1.8944  mask=14.1%  norm=0.690  lr=1.29e-04  dt=  39.4ms  words=60,153,856
[E05  1152/1548 G   7343|CLM] train=2.2700  mask=14.1%  norm=0.745  lr=1.29e-04  dt=  37.4ms  words=60,162,048
[E05  1153/1548 G   7344|CLM] train=3.9147  mask=14.1%  norm=0.773  lr=1.29e-04  dt=  38.1ms  words=60,170,240
[E05  1154/1548 G   7345|CLM] train=3.7277  mask=14.1%  norm=0.822  lr=1.29e-04  dt=  38.1ms  words=60,178,432
[E05  1155/1548 G   7346|CLM] train=2.5671  mask=14.1%  norm=0.710  lr=1.29e-04  dt=  37.9ms  words=60,186,624
[E05  1156/1548 G   7347|CLM] train=5.1063  mask=14.1%  norm=0.901  lr=1.29e-04  dt=  38.0ms  words=60,194,816
[E05  1157/1548 G   7348|CLM] train=2.5689  mask=14.1%  norm=0.830  lr=1.28e-04  dt=  37.5ms  words=60,203,008
[E05  1158/1548 G   7349|CLM] train=2.1628  mask=14.1%  norm=0.893  lr=1.28e-04  dt=  37.5ms  words=60,211,200
[E05  1159/1548 G   7350|CLM] train=2.2834  mask=14.1%  norm=0.725  lr=1.28e-04  dt=  37.2ms  words=60,219,392
[E05  1160/1548 G   7351|CLM] train=2.6753  mask=14.1%  norm=0.966  lr=1.28e-04  dt=  36.9ms  words=60,227,584
[E05  1161/1548 G   7352|CLM] train=2.2924  mask=14.1%  norm=0.845  lr=1.28e-04  dt=  38.7ms  words=60,235,776
[E05  1162/1548 G   7353|CLM] train=4.4459  mask=14.1%  norm=0.921  lr=1.28e-04  dt=  44.5ms  words=60,243,968
[E05  1163/1548 G   7354|CLM] train=4.3563  mask=14.1%  norm=0.938  lr=1.28e-04  dt=  37.0ms  words=60,252,160
[E05  1164/1548 G   7355|CLM] train=2.3377  mask=14.1%  norm=0.695  lr=1.28e-04  dt=  37.1ms  words=60,260,352
[E05  1165/1548 G   7356|CLM] train=4.1981  mask=14.1%  norm=0.852  lr=1.28e-04  dt=  46.4ms  words=60,268,544
[E05  1166/1548 G   7357|CLM] train=4.6130  mask=14.1%  norm=0.932  lr=1.28e-04  dt=  43.1ms  words=60,276,736
[E05  1167/1548 G   7358|CLM] train=2.3272  mask=14.1%  norm=0.699  lr=1.28e-04  dt=  39.4ms  words=60,284,928
[E05  1168/1548 G   7359|CLM] train=1.8047  mask=14.1%  norm=0.742  lr=1.28e-04  dt=  37.1ms  words=60,293,120
[E05  1169/1548 G   7360|CLM] train=4.4524  mask=14.1%  norm=0.844  lr=1.28e-04  dt=  37.7ms  words=60,301,312
[E05  1170/1548 G   7361|CLM] train=4.0664  mask=14.1%  norm=1.020  lr=1.28e-04  dt=  37.3ms  words=60,309,504
[E05  1171/1548 G   7362|CLM] train=2.5974  mask=14.1%  norm=0.849  lr=1.28e-04  dt=  37.0ms  words=60,317,696
[E05  1172/1548 G   7363|CLM] train=2.5293  mask=14.1%  norm=0.804  lr=1.28e-04  dt=  37.1ms  words=60,325,888
[E05  1173/1548 G   7364|CLM] train=2.5984  mask=14.1%  norm=0.747  lr=1.28e-04  dt=  37.5ms  words=60,334,080
[E05  1174/1548 G   7365|CLM] train=4.2099  mask=14.1%  norm=0.945  lr=1.28e-04  dt=  37.5ms  words=60,342,272
[E05  1175/1548 G   7366|CLM] train=4.2496  mask=14.1%  norm=0.712  lr=1.28e-04  dt=  37.5ms  words=60,350,464
[E05  1176/1548 G   7367|CLM] train=4.2989  mask=14.1%  norm=0.935  lr=1.28e-04  dt=  37.7ms  words=60,358,656
[E05  1177/1548 G   7368|CLM] train=4.3783  mask=14.1%  norm=0.887  lr=1.28e-04  dt=  38.2ms  words=60,366,848
[E05  1178/1548 G   7369|CLM] train=4.6164  mask=14.0%  norm=0.844  lr=1.28e-04  dt=  38.9ms  words=60,375,040
[E05  1179/1548 G   7370|CLM] train=3.4879  mask=14.0%  norm=1.308  lr=1.28e-04  dt=  41.4ms  words=60,383,232
[E05  1180/1548 G   7371|CLM] train=2.1245  mask=14.0%  norm=0.761  lr=1.28e-04  dt=  37.0ms  words=60,391,424
[E05  1181/1548 G   7372|CLM] train=4.5597  mask=14.0%  norm=0.926  lr=1.28e-04  dt=  37.7ms  words=60,399,616
[E05  1182/1548 G   7373|CLM] train=4.1904  mask=14.0%  norm=0.744  lr=1.28e-04  dt=  38.1ms  words=60,407,808
[E05  1183/1548 G   7374|CLM] train=2.0408  mask=14.0%  norm=0.742  lr=1.28e-04  dt=  37.8ms  words=60,416,000
[E05  1184/1548 G   7375|CLM] train=4.8271  mask=14.0%  norm=1.034  lr=1.27e-04  dt=  37.6ms  words=60,424,192
[E05  1185/1548 G   7376|CLM] train=2.5464  mask=14.0%  norm=0.696  lr=1.27e-04  dt=  37.9ms  words=60,432,384
[E05  1186/1548 G   7377|CLM] train=2.2724  mask=14.0%  norm=0.910  lr=1.27e-04  dt=  42.8ms  words=60,440,576
[E05  1187/1548 G   7378|CLM] train=2.2140  mask=14.0%  norm=0.667  lr=1.27e-04  dt=  42.9ms  words=60,448,768
[E05  1188/1548 G   7379|CLM] train=4.1432  mask=14.0%  norm=0.699  lr=1.27e-04  dt=  41.5ms  words=60,456,960
[E05  1189/1548 G   7380|CLM] train=3.8772  mask=14.0%  norm=0.993  lr=1.27e-04  dt=  38.0ms  words=60,465,152
[E05  1190/1548 G   7381|CLM] train=4.3571  mask=14.0%  norm=1.438  lr=1.27e-04  dt=  37.1ms  words=60,473,344
[E05  1191/1548 G   7382|CLM] train=3.7012  mask=14.0%  norm=0.730  lr=1.27e-04  dt=  37.3ms  words=60,481,536
[E05  1192/1548 G   7383|CLM] train=2.1086  mask=14.0%  norm=0.603  lr=1.27e-04  dt=  37.6ms  words=60,489,728
[E05  1193/1548 G   7384|CLM] train=5.0531  mask=14.0%  norm=0.989  lr=1.27e-04  dt=  37.2ms  words=60,497,920
[E05  1194/1548 G   7385|CLM] train=2.3173  mask=14.0%  norm=0.730  lr=1.27e-04  dt=  37.2ms  words=60,506,112
[E05  1195/1548 G   7386|CLM] train=2.1054  mask=14.0%  norm=0.865  lr=1.27e-04  dt=  37.4ms  words=60,514,304
[E05  1196/1548 G   7387|CLM] train=4.4969  mask=14.0%  norm=0.929  lr=1.27e-04  dt=  36.8ms  words=60,522,496
[E05  1197/1548 G   7388|CLM] train=2.3513  mask=14.0%  norm=0.652  lr=1.27e-04  dt=  38.7ms  words=60,530,688
[E05  1198/1548 G   7389|CLM] train=4.2073  mask=14.0%  norm=0.814  lr=1.27e-04  dt=  42.8ms  words=60,538,880
[E05  1199/1548 G   7390|CLM] train=4.0486  mask=14.0%  norm=0.946  lr=1.27e-04  dt=  37.1ms  words=60,547,072
[E05  1200/1548 G   7391|CLM] train=4.3552  mask=14.0%  norm=0.985  lr=1.27e-04  dt=  37.1ms  words=60,555,264
[E05  1201/1548 G   7392|CLM] train=4.3172  mask=14.0%  norm=0.854  lr=1.27e-04  dt=  38.0ms  words=60,563,456
[E05  1202/1548 G   7393|CLM] train=4.5823  mask=14.0%  norm=0.917  lr=1.27e-04  dt=  37.0ms  words=60,571,648
[E05  1203/1548 G   7394|CLM] train=3.9418  mask=14.0%  norm=0.894  lr=1.27e-04  dt=  37.0ms  words=60,579,840
[E05  1204/1548 G   7395|CLM] train=4.6820  mask=14.0%  norm=1.358  lr=1.27e-04  dt=  37.2ms  words=60,588,032
[E05  1205/1548 G   7396|CLM] train=5.2042  mask=14.0%  norm=2.922  lr=1.27e-04  dt=  37.0ms  words=60,596,224
[E05  1206/1548 G   7397|CLM] train=2.3922  mask=14.0%  norm=0.819  lr=1.27e-04  dt=  36.9ms  words=60,604,416
[E05  1207/1548 G   7398|CLM] train=4.5085  mask=14.0%  norm=1.008  lr=1.27e-04  dt=  36.9ms  words=60,612,608
[E05  1208/1548 G   7399|CLM] train=2.2106  mask=14.0%  norm=0.878  lr=1.27e-04  dt=  37.0ms  words=60,620,800
[E05  1209/1548 G   7400|CLM] train=2.3481  mask=14.0%  norm=0.813  lr=1.27e-04  dt=  37.0ms  words=60,628,992
[E05  1210/1548 G   7401|CLM] train=2.5348  mask=14.0%  norm=0.686  lr=1.26e-04  dt=  36.9ms  words=60,637,184
[E05  1211/1548 G   7402|CLM] train=4.1871  mask=14.0%  norm=0.915  lr=1.26e-04  dt=  37.0ms  words=60,645,376
[E05  1212/1548 G   7403|CLM] train=2.1270  mask=14.0%  norm=0.695  lr=1.26e-04  dt=  37.3ms  words=60,653,568
[E05  1213/1548 G   7404|CLM] train=2.5045  mask=14.0%  norm=0.602  lr=1.26e-04  dt=  37.0ms  words=60,661,760
[E05  1214/1548 G   7405|CLM] train=2.5905  mask=14.0%  norm=0.751  lr=1.26e-04  dt=  36.8ms  words=60,669,952
[E05  1215/1548 G   7406|CLM] train=2.3556  mask=14.0%  norm=0.586  lr=1.26e-04  dt=  37.2ms  words=60,678,144
[E05  1216/1548 G   7407|CLM] train=4.4113  mask=14.0%  norm=0.873  lr=1.26e-04  dt=  37.1ms  words=60,686,336
[E05  1217/1548 G   7408|CLM] train=2.6669  mask=14.0%  norm=0.659  lr=1.26e-04  dt=  37.0ms  words=60,694,528
[E05  1218/1548 G   7409|CLM] train=4.3849  mask=14.0%  norm=1.085  lr=1.26e-04  dt=  37.0ms  words=60,702,720
[E05  1219/1548 G   7410|CLM] train=2.6159  mask=14.0%  norm=0.827  lr=1.26e-04  dt=  37.0ms  words=60,710,912
[E05  1220/1548 G   7411|CLM] train=1.7929  mask=14.0%  norm=0.683  lr=1.26e-04  dt=  36.9ms  words=60,719,104
[E05  1221/1548 G   7412|CLM] train=4.2888  mask=14.0%  norm=0.846  lr=1.26e-04  dt=  36.8ms  words=60,727,296
[E05  1222/1548 G   7413|CLM] train=2.5032  mask=14.0%  norm=0.841  lr=1.26e-04  dt=  36.9ms  words=60,735,488
[E05  1223/1548 G   7414|CLM] train=3.9372  mask=14.0%  norm=0.792  lr=1.26e-04  dt=  36.9ms  words=60,743,680
[E05  1224/1548 G   7415|CLM] train=2.2604  mask=14.0%  norm=0.634  lr=1.26e-04  dt=  37.1ms  words=60,751,872
[E05  1225/1548 G   7416|CLM] train=4.4903  mask=14.0%  norm=0.911  lr=1.26e-04  dt=  36.8ms  words=60,760,064
[E05  1226/1548 G   7417|CLM] train=2.1532  mask=14.0%  norm=0.874  lr=1.26e-04  dt=  36.9ms  words=60,768,256
[E05  1227/1548 G   7418|CLM] train=4.0139  mask=14.0%  norm=0.959  lr=1.26e-04  dt=  37.1ms  words=60,776,448
[E05  1228/1548 G   7419|CLM] train=3.8392  mask=14.0%  norm=0.865  lr=1.26e-04  dt=  37.4ms  words=60,784,640
[E05  1229/1548 G   7420|CLM] train=3.6992  mask=14.0%  norm=0.772  lr=1.26e-04  dt=  37.0ms  words=60,792,832
[E05  1230/1548 G   7421|CLM] train=3.9612  mask=14.0%  norm=0.861  lr=1.26e-04  dt=  37.0ms  words=60,801,024
[E05  1231/1548 G   7422|CLM] train=2.5843  mask=14.0%  norm=0.686  lr=1.26e-04  dt=  37.1ms  words=60,809,216
[E05  1232/1548 G   7423|CLM] train=2.1956  mask=14.0%  norm=0.715  lr=1.26e-04  dt=  37.0ms  words=60,817,408
[E05  1233/1548 G   7424|CLM] train=1.9517  mask=14.0%  norm=0.752  lr=1.26e-04  dt=  36.9ms  words=60,825,600
[E05  1234/1548 G   7425|CLM] train=2.6960  mask=14.0%  norm=0.725  lr=1.26e-04  dt=  36.9ms  words=60,833,792
[E05  1235/1548 G   7426|CLM] train=4.1009  mask=14.0%  norm=0.901  lr=1.26e-04  dt=  37.1ms  words=60,841,984
[E05  1236/1548 G   7427|CLM] train=3.2010  mask=14.0%  norm=0.737  lr=1.26e-04  dt=  36.9ms  words=60,850,176
[E05  1237/1548 G   7428|CLM] train=2.4673  mask=14.0%  norm=0.613  lr=1.25e-04  dt=  36.9ms  words=60,858,368
[E05  1238/1548 G   7429|CLM] train=2.2619  mask=14.0%  norm=0.687  lr=1.25e-04  dt=  36.8ms  words=60,866,560
[E05  1239/1548 G   7430|CLM] train=4.0932  mask=14.0%  norm=0.937  lr=1.25e-04  dt=  37.0ms  words=60,874,752
[E05  1240/1548 G   7431|CLM] train=2.0814  mask=14.0%  norm=0.912  lr=1.25e-04  dt=  37.0ms  words=60,882,944
[E05  1241/1548 G   7432|CLM] train=2.8261  mask=14.0%  norm=0.668  lr=1.25e-04  dt=  36.8ms  words=60,891,136
[E05  1242/1548 G   7433|CLM] train=3.6032  mask=14.0%  norm=0.774  lr=1.25e-04  dt=  37.7ms  words=60,899,328
[E05  1243/1548 G   7434|CLM] train=2.1384  mask=14.0%  norm=0.652  lr=1.25e-04  dt=  37.2ms  words=60,907,520
[E05  1244/1548 G   7435|CLM] train=4.0891  mask=14.0%  norm=0.840  lr=1.25e-04  dt=  36.9ms  words=60,915,712
[E05  1245/1548 G   7436|CLM] train=3.9184  mask=14.0%  norm=0.764  lr=1.25e-04  dt=  37.6ms  words=60,923,904
[E05  1246/1548 G   7437|CLM] train=4.4479  mask=14.0%  norm=0.802  lr=1.25e-04  dt=  37.9ms  words=60,932,096
[E05  1247/1548 G   7438|CLM] train=4.6840  mask=14.0%  norm=0.933  lr=1.25e-04  dt=  37.1ms  words=60,940,288
[E05  1248/1548 G   7439|CLM] train=4.6719  mask=14.0%  norm=0.939  lr=1.25e-04  dt=  37.0ms  words=60,948,480
[E05  1249/1548 G   7440|CLM] train=4.3731  mask=14.0%  norm=1.040  lr=1.25e-04  dt=  37.0ms  words=60,956,672
[E05  1250/1548 G   7441|CLM] train=4.7209  mask=14.0%  norm=0.881  lr=1.25e-04  dt=  36.8ms  words=60,964,864
[E05  1251/1548 G   7442|CLM] train=1.7208  mask=14.0%  norm=0.737  lr=1.25e-04  dt=  37.0ms  words=60,973,056
[E05  1252/1548 G   7443|CLM] train=2.2939  mask=14.0%  norm=0.952  lr=1.25e-04  dt=  37.1ms  words=60,981,248
[E05  1253/1548 G   7444|CLM] train=3.9541  mask=14.0%  norm=0.746  lr=1.25e-04  dt=  36.9ms  words=60,989,440
[E05  1254/1548 G   7445|CLM] train=4.3165  mask=14.0%  norm=0.822  lr=1.25e-04  dt=  36.8ms  words=60,997,632
[E05  1255/1548 G   7446|CLM] train=4.2777  mask=14.0%  norm=0.874  lr=1.25e-04  dt=  37.7ms  words=61,005,824
[E05  1256/1548 G   7447|CLM] train=2.7317  mask=14.0%  norm=0.836  lr=1.25e-04  dt=  37.0ms  words=61,014,016
[E05  1257/1548 G   7448|CLM] train=2.3183  mask=14.0%  norm=0.753  lr=1.25e-04  dt=  37.0ms  words=61,022,208
[E05  1258/1548 G   7449|CLM] train=2.1885  mask=14.0%  norm=0.879  lr=1.25e-04  dt=  36.8ms  words=61,030,400
[E05  1259/1548 G   7450|CLM] train=2.4923  mask=14.0%  norm=0.672  lr=1.25e-04  dt=  37.6ms  words=61,038,592
[E05  1260/1548 G   7451|CLM] train=4.3697  mask=14.0%  norm=0.844  lr=1.25e-04  dt=  37.0ms  words=61,046,784
[E05  1261/1548 G   7452|CLM] train=2.5298  mask=14.0%  norm=0.659  lr=1.25e-04  dt=  37.0ms  words=61,054,976
[E05  1262/1548 G   7453|CLM] train=5.3675  mask=14.0%  norm=1.516  lr=1.25e-04  dt=  37.1ms  words=61,063,168
[E05  1263/1548 G   7454|CLM] train=2.3743  mask=14.0%  norm=0.819  lr=1.24e-04  dt=  37.0ms  words=61,071,360
[E05  1264/1548 G   7455|CLM] train=2.5128  mask=14.0%  norm=0.635  lr=1.24e-04  dt=  36.8ms  words=61,079,552
[E05  1265/1548 G   7456|CLM] train=4.1752  mask=14.0%  norm=1.070  lr=1.24e-04  dt=  37.0ms  words=61,087,744
[E05  1266/1548 G   7457|CLM] train=3.6616  mask=14.0%  norm=0.884  lr=1.24e-04  dt=  37.1ms  words=61,095,936
[E05  1267/1548 G   7458|CLM] train=2.1325  mask=14.0%  norm=0.731  lr=1.24e-04  dt=  36.9ms  words=61,104,128
[E05  1268/1548 G   7459|CLM] train=3.5887  mask=14.0%  norm=0.849  lr=1.24e-04  dt=  37.0ms  words=61,112,320
[E05  1269/1548 G   7460|CLM] train=4.1920  mask=14.0%  norm=0.862  lr=1.24e-04  dt=  37.0ms  words=61,120,512
[E05  1270/1548 G   7461|CLM] train=4.9648  mask=14.0%  norm=0.936  lr=1.24e-04  dt=  37.0ms  words=61,128,704
[E05  1271/1548 G   7462|CLM] train=4.2325  mask=14.0%  norm=0.924  lr=1.24e-04  dt=  37.1ms  words=61,136,896
[E05  1272/1548 G   7463|CLM] train=3.9304  mask=14.0%  norm=0.735  lr=1.24e-04  dt=  37.0ms  words=61,145,088
[E05  1273/1548 G   7464|CLM] train=2.4515  mask=14.0%  norm=0.691  lr=1.24e-04  dt=  37.3ms  words=61,153,280
[E05  1274/1548 G   7465|CLM] train=4.5921  mask=14.0%  norm=0.800  lr=1.24e-04  dt=  36.8ms  words=61,161,472
[E05  1275/1548 G   7466|CLM] train=4.2201  mask=14.0%  norm=0.892  lr=1.24e-04  dt=  36.8ms  words=61,169,664
[E05  1276/1548 G   7467|CLM] train=3.8373  mask=14.0%  norm=0.783  lr=1.24e-04  dt=  36.9ms  words=61,177,856
[E05  1277/1548 G   7468|CLM] train=4.1866  mask=14.0%  norm=0.892  lr=1.24e-04  dt=  37.1ms  words=61,186,048
[E05  1278/1548 G   7469|CLM] train=3.7402  mask=14.0%  norm=0.770  lr=1.24e-04  dt=  36.8ms  words=61,194,240
[E05  1279/1548 G   7470|CLM] train=4.1329  mask=14.0%  norm=0.975  lr=1.24e-04  dt=  36.9ms  words=61,202,432
[E05  1280/1548 G   7471|CLM] train=2.4217  mask=14.0%  norm=0.759  lr=1.24e-04  dt=  37.0ms  words=61,210,624
[E05  1281/1548 G   7472|CLM] train=2.4922  mask=14.0%  norm=0.928  lr=1.24e-04  dt=  37.0ms  words=61,218,816
[E05  1282/1548 G   7473|CLM] train=2.3096  mask=14.0%  norm=0.758  lr=1.24e-04  dt=  37.4ms  words=61,227,008
[E05  1283/1548 G   7474|CLM] train=2.7659  mask=14.0%  norm=0.769  lr=1.24e-04  dt=  37.0ms  words=61,235,200
[E05  1284/1548 G   7475|CLM] train=4.5101  mask=14.0%  norm=0.942  lr=1.24e-04  dt=  47.0ms  words=61,243,392
[E05  1285/1548 G   7476|CLM] train=2.1868  mask=14.0%  norm=0.916  lr=1.24e-04  dt=  42.6ms  words=61,251,584
[E05  1286/1548 G   7477|CLM] train=4.2314  mask=14.0%  norm=1.035  lr=1.24e-04  dt=  37.1ms  words=61,259,776
[E05  1287/1548 G   7478|CLM] train=2.4646  mask=14.0%  norm=0.706  lr=1.24e-04  dt=  45.6ms  words=61,267,968
[E05  1288/1548 G   7479|CLM] train=2.5757  mask=14.0%  norm=0.721  lr=1.24e-04  dt=  39.8ms  words=61,276,160
[E05  1289/1548 G   7480|CLM] train=2.1581  mask=14.0%  norm=0.640  lr=1.24e-04  dt=  41.5ms  words=61,284,352
[E05  1290/1548 G   7481|CLM] train=2.0396  mask=14.0%  norm=0.724  lr=1.23e-04  dt=  43.1ms  words=61,292,544
[E05  1291/1548 G   7482|CLM] train=2.3333  mask=14.0%  norm=0.667  lr=1.23e-04  dt=  43.3ms  words=61,300,736
[E05  1292/1548 G   7483|CLM] train=4.8176  mask=14.0%  norm=0.810  lr=1.23e-04  dt=  43.1ms  words=61,308,928
[E05  1293/1548 G   7484|CLM] train=1.9487  mask=14.0%  norm=0.564  lr=1.23e-04  dt=  42.4ms  words=61,317,120
[E05  1294/1548 G   7485|CLM] train=4.3315  mask=14.0%  norm=0.830  lr=1.23e-04  dt=  42.7ms  words=61,325,312
[E05  1295/1548 G   7486|CLM] train=3.9196  mask=14.0%  norm=0.833  lr=1.23e-04  dt=  41.1ms  words=61,333,504
[E05  1296/1548 G   7487|CLM] train=4.2686  mask=14.0%  norm=0.778  lr=1.23e-04  dt=  36.9ms  words=61,341,696
[E05  1297/1548 G   7488|CLM] train=3.7174  mask=14.0%  norm=0.786  lr=1.23e-04  dt=  36.9ms  words=61,349,888
[E05  1298/1548 G   7489|CLM] train=4.4329  mask=14.0%  norm=0.976  lr=1.23e-04  dt=  37.1ms  words=61,358,080
[E05  1299/1548 G   7490|CLM] train=2.5334  mask=14.0%  norm=0.859  lr=1.23e-04  dt=  38.5ms  words=61,366,272
[E05  1300/1548 G   7491|CLM] train=2.2937  mask=14.0%  norm=0.855  lr=1.23e-04  dt=  42.5ms  words=61,374,464
[E05  1301/1548 G   7492|CLM] train=2.3330  mask=14.0%  norm=0.741  lr=1.23e-04  dt=  41.9ms  words=61,382,656
[E05  1302/1548 G   7493|CLM] train=2.3810  mask=13.9%  norm=0.783  lr=1.23e-04  dt=  38.3ms  words=61,390,848
[E05  1303/1548 G   7494|CLM] train=4.1017  mask=13.9%  norm=0.887  lr=1.23e-04  dt=  37.9ms  words=61,399,040
[E05  1304/1548 G   7495|CLM] train=3.8172  mask=13.9%  norm=1.024  lr=1.23e-04  dt=  37.6ms  words=61,407,232
[E05  1305/1548 G   7496|CLM] train=3.7512  mask=13.9%  norm=0.690  lr=1.23e-04  dt=  37.3ms  words=61,415,424
[E05  1306/1548 G   7497|CLM] train=2.1120  mask=13.9%  norm=0.863  lr=1.23e-04  dt=  37.0ms  words=61,423,616
[E05  1307/1548 G   7498|CLM] train=4.3618  mask=13.9%  norm=0.839  lr=1.23e-04  dt=  39.0ms  words=61,431,808
[E05  1308/1548 G   7499|CLM] train=2.1657  mask=13.9%  norm=0.636  lr=1.23e-04  dt=  37.3ms  words=61,440,000
[E05  1309/1548 G   7500|CLM] train=2.2200  mask=13.9%  norm=0.675  lr=1.23e-04  dt=  36.9ms  words=61,448,192
[E05  1310/1548 G   7501|CLM] train=4.1953  mask=13.9%  norm=0.871  lr=1.23e-04  dt=  37.4ms  words=61,456,384
[E05  1311/1548 G   7502|CLM] train=3.9417  mask=13.9%  norm=0.848  lr=1.23e-04  dt=  37.1ms  words=61,464,576
[E05  1312/1548 G   7503|CLM] train=5.1654  mask=13.9%  norm=1.109  lr=1.23e-04  dt=  36.8ms  words=61,472,768
[E05  1313/1548 G   7504|CLM] train=4.0647  mask=13.9%  norm=0.816  lr=1.23e-04  dt=  37.0ms  words=61,480,960
[E05  1314/1548 G   7505|CLM] train=2.1436  mask=13.9%  norm=0.735  lr=1.23e-04  dt=  37.0ms  words=61,489,152
[E05  1315/1548 G   7506|CLM] train=4.0047  mask=13.9%  norm=0.904  lr=1.23e-04  dt=  37.1ms  words=61,497,344
[E05  1316/1548 G   7507|CLM] train=3.7890  mask=13.9%  norm=0.843  lr=1.23e-04  dt=  36.9ms  words=61,505,536
[E05  1317/1548 G   7508|CLM] train=4.4807  mask=13.9%  norm=0.852  lr=1.22e-04  dt=  37.0ms  words=61,513,728
[E05  1318/1548 G   7509|CLM] train=1.8943  mask=13.9%  norm=0.670  lr=1.22e-04  dt=  36.9ms  words=61,521,920
[E05  1319/1548 G   7510|CLM] train=2.6258  mask=13.9%  norm=0.730  lr=1.22e-04  dt=  37.1ms  words=61,530,112
[E05  1320/1548 G   7511|CLM] train=2.6443  mask=13.9%  norm=0.756  lr=1.22e-04  dt=  36.8ms  words=61,538,304
[E05  1321/1548 G   7512|CLM] train=2.1514  mask=13.9%  norm=0.821  lr=1.22e-04  dt=  37.1ms  words=61,546,496
[E05  1322/1548 G   7513|CLM] train=4.2386  mask=13.9%  norm=0.814  lr=1.22e-04  dt=  37.1ms  words=61,554,688
[E05  1323/1548 G   7514|CLM] train=4.5107  mask=13.9%  norm=1.109  lr=1.22e-04  dt=  36.9ms  words=61,562,880
[E05  1324/1548 G   7515|CLM] train=4.2992  mask=13.9%  norm=0.804  lr=1.22e-04  dt=  37.4ms  words=61,571,072
[E05  1325/1548 G   7516|CLM] train=2.0630  mask=13.9%  norm=0.690  lr=1.22e-04  dt=  37.2ms  words=61,579,264
[E05  1326/1548 G   7517|CLM] train=2.4194  mask=13.9%  norm=0.618  lr=1.22e-04  dt=  37.0ms  words=61,587,456
[E05  1327/1548 G   7518|CLM] train=4.2356  mask=13.9%  norm=1.245  lr=1.22e-04  dt=  37.0ms  words=61,595,648
[E05  1328/1548 G   7519|CLM] train=2.3827  mask=13.9%  norm=0.683  lr=1.22e-04  dt=  37.0ms  words=61,603,840
[E05  1329/1548 G   7520|CLM] train=2.3426  mask=13.9%  norm=0.855  lr=1.22e-04  dt=  37.0ms  words=61,612,032
[E05  1330/1548 G   7521|CLM] train=4.3916  mask=13.9%  norm=0.909  lr=1.22e-04  dt=  36.9ms  words=61,620,224
[E05  1331/1548 G   7522|CLM] train=4.0575  mask=13.9%  norm=0.929  lr=1.22e-04  dt=  36.8ms  words=61,628,416
[E05  1332/1548 G   7523|CLM] train=2.6355  mask=13.9%  norm=0.739  lr=1.22e-04  dt=  37.0ms  words=61,636,608
[E05  1333/1548 G   7524|CLM] train=2.0752  mask=13.9%  norm=0.694  lr=1.22e-04  dt=  37.0ms  words=61,644,800
[E05  1334/1548 G   7525|CLM] train=2.1809  mask=13.9%  norm=0.599  lr=1.22e-04  dt=  37.0ms  words=61,652,992
[E05  1335/1548 G   7526|CLM] train=3.4710  mask=13.9%  norm=0.769  lr=1.22e-04  dt=  36.9ms  words=61,661,184
[E05  1336/1548 G   7527|CLM] train=2.1510  mask=13.9%  norm=0.603  lr=1.22e-04  dt=  36.9ms  words=61,669,376
[E05  1337/1548 G   7528|CLM] train=2.9031  mask=13.9%  norm=0.693  lr=1.22e-04  dt=  37.1ms  words=61,677,568
[E05  1338/1548 G   7529|CLM] train=3.8605  mask=13.9%  norm=0.710  lr=1.22e-04  dt=  36.8ms  words=61,685,760
[E05  1339/1548 G   7530|CLM] train=2.5730  mask=13.9%  norm=0.660  lr=1.22e-04  dt=  36.8ms  words=61,693,952
[E05  1340/1548 G   7531|CLM] train=3.8889  mask=13.9%  norm=0.773  lr=1.22e-04  dt=  37.0ms  words=61,702,144
[E05  1341/1548 G   7532|CLM] train=2.3301  mask=13.9%  norm=0.838  lr=1.22e-04  dt=  37.1ms  words=61,710,336
[E05  1342/1548 G   7533|CLM] train=5.0422  mask=13.9%  norm=0.957  lr=1.22e-04  dt=  36.8ms  words=61,718,528
[E05  1343/1548 G   7534|CLM] train=2.2522  mask=13.9%  norm=0.677  lr=1.21e-04  dt=  36.9ms  words=61,726,720
[E05  1344/1548 G   7535|CLM] train=2.3009  mask=13.9%  norm=0.800  lr=1.21e-04  dt=  36.9ms  words=61,734,912
[E05  1345/1548 G   7536|CLM] train=4.0113  mask=13.9%  norm=1.539  lr=1.21e-04  dt=  36.9ms  words=61,743,104
[E05  1346/1548 G   7537|CLM] train=3.8840  mask=13.9%  norm=1.148  lr=1.21e-04  dt=  37.3ms  words=61,751,296
[E05  1347/1548 G   7538|CLM] train=4.2731  mask=13.9%  norm=0.907  lr=1.21e-04  dt=  37.3ms  words=61,759,488
[E05  1348/1548 G   7539|CLM] train=4.2070  mask=13.9%  norm=0.954  lr=1.21e-04  dt=  37.2ms  words=61,767,680
[E05  1349/1548 G   7540|CLM] train=4.6228  mask=13.9%  norm=1.154  lr=1.21e-04  dt=  36.9ms  words=61,775,872
[E05  1350/1548 G   7541|CLM] train=3.9627  mask=13.9%  norm=0.920  lr=1.21e-04  dt=  36.9ms  words=61,784,064
[E05  1351/1548 G   7542|CLM] train=4.6722  mask=13.9%  norm=1.103  lr=1.21e-04  dt=  36.9ms  words=61,792,256
[E05  1352/1548 G   7543|CLM] train=2.1864  mask=13.9%  norm=0.809  lr=1.21e-04  dt=  37.1ms  words=61,800,448
[E05  1353/1548 G   7544|CLM] train=4.0937  mask=13.9%  norm=0.794  lr=1.21e-04  dt=  36.9ms  words=61,808,640
[E05  1354/1548 G   7545|CLM] train=3.8505  mask=13.9%  norm=0.715  lr=1.21e-04  dt=  37.0ms  words=61,816,832
[E05  1355/1548 G   7546|CLM] train=1.8822  mask=13.9%  norm=0.700  lr=1.21e-04  dt=  36.9ms  words=61,825,024
[E05  1356/1548 G   7547|CLM] train=5.2068  mask=13.9%  norm=0.913  lr=1.21e-04  dt=  37.1ms  words=61,833,216
[E05  1357/1548 G   7548|CLM] train=3.8993  mask=13.9%  norm=0.920  lr=1.21e-04  dt=  37.2ms  words=61,841,408
[E05  1358/1548 G   7549|CLM] train=4.0886  mask=13.9%  norm=0.880  lr=1.21e-04  dt=  37.0ms  words=61,849,600
[E05  1359/1548 G   7550|CLM] train=4.4723  mask=13.9%  norm=0.882  lr=1.21e-04  dt=  37.1ms  words=61,857,792
[E05  1360/1548 G   7551|CLM] train=3.0296  mask=13.9%  norm=0.746  lr=1.21e-04  dt=  37.0ms  words=61,865,984
[E05  1361/1548 G   7552|CLM] train=2.6585  mask=13.9%  norm=0.724  lr=1.21e-04  dt=  36.9ms  words=61,874,176
[E05  1362/1548 G   7553|CLM] train=4.3906  mask=13.9%  norm=0.940  lr=1.21e-04  dt=  37.0ms  words=61,882,368
[E05  1363/1548 G   7554|CLM] train=4.6581  mask=13.9%  norm=0.863  lr=1.21e-04  dt=  37.0ms  words=61,890,560
[E05  1364/1548 G   7555|CLM] train=4.1523  mask=13.9%  norm=0.793  lr=1.21e-04  dt=  37.0ms  words=61,898,752
[E05  1365/1548 G   7556|CLM] train=4.5581  mask=13.9%  norm=0.929  lr=1.21e-04  dt=  36.8ms  words=61,906,944
[E05  1366/1548 G   7557|CLM] train=2.3718  mask=13.9%  norm=0.710  lr=1.21e-04  dt=  37.2ms  words=61,915,136
[E05  1367/1548 G   7558|CLM] train=2.1626  mask=13.9%  norm=0.814  lr=1.21e-04  dt=  37.1ms  words=61,923,328
[E05  1368/1548 G   7559|CLM] train=3.6455  mask=13.9%  norm=0.726  lr=1.21e-04  dt=  37.1ms  words=61,931,520
[E05  1369/1548 G   7560|CLM] train=2.3732  mask=13.9%  norm=0.682  lr=1.21e-04  dt=  37.0ms  words=61,939,712
[E05  1370/1548 G   7561|CLM] train=2.4434  mask=13.9%  norm=0.839  lr=1.20e-04  dt=  37.0ms  words=61,947,904
[E05  1371/1548 G   7562|CLM] train=2.4564  mask=13.9%  norm=1.021  lr=1.20e-04  dt=  37.0ms  words=61,956,096
[E05  1372/1548 G   7563|CLM] train=4.0407  mask=13.9%  norm=0.748  lr=1.20e-04  dt=  36.8ms  words=61,964,288
[E05  1373/1548 G   7564|CLM] train=4.3592  mask=13.9%  norm=1.042  lr=1.20e-04  dt=  37.0ms  words=61,972,480
[E05  1374/1548 G   7565|CLM] train=3.9435  mask=13.9%  norm=0.710  lr=1.20e-04  dt=  36.9ms  words=61,980,672
[E05  1375/1548 G   7566|CLM] train=2.3154  mask=13.9%  norm=0.606  lr=1.20e-04  dt=  37.0ms  words=61,988,864
[E05  1376/1548 G   7567|CLM] train=2.9509  mask=13.9%  norm=1.000  lr=1.20e-04  dt=  36.9ms  words=61,997,056
[E05  1377/1548 G   7568|CLM] train=4.4499  mask=13.9%  norm=0.810  lr=1.20e-04  dt=  36.9ms  words=62,005,248
[E05  1378/1548 G   7569|CLM] train=4.9378  mask=13.9%  norm=1.036  lr=1.20e-04  dt=  36.9ms  words=62,013,440
[E05  1379/1548 G   7570|CLM] train=3.7190  mask=13.9%  norm=0.846  lr=1.20e-04  dt=  36.9ms  words=62,021,632
[E05  1380/1548 G   7571|CLM] train=4.4134  mask=13.9%  norm=0.887  lr=1.20e-04  dt=  37.2ms  words=62,029,824
[E05  1381/1548 G   7572|CLM] train=4.2556  mask=13.9%  norm=0.810  lr=1.20e-04  dt=  36.9ms  words=62,038,016
[E05  1382/1548 G   7573|CLM] train=4.8331  mask=13.9%  norm=0.906  lr=1.20e-04  dt=  36.9ms  words=62,046,208
[E05  1383/1548 G   7574|CLM] train=3.9511  mask=13.9%  norm=0.939  lr=1.20e-04  dt=  36.8ms  words=62,054,400
[E05  1384/1548 G   7575|CLM] train=4.1385  mask=13.9%  norm=0.931  lr=1.20e-04  dt=  36.7ms  words=62,062,592
[E05  1385/1548 G   7576|CLM] train=2.4379  mask=13.9%  norm=0.712  lr=1.20e-04  dt=  37.0ms  words=62,070,784
[E05  1386/1548 G   7577|CLM] train=4.3220  mask=13.9%  norm=0.754  lr=1.20e-04  dt=  36.9ms  words=62,078,976
[E05  1387/1548 G   7578|CLM] train=2.4460  mask=13.9%  norm=0.842  lr=1.20e-04  dt=  36.9ms  words=62,087,168
[E05  1388/1548 G   7579|CLM] train=3.9821  mask=13.9%  norm=0.853  lr=1.20e-04  dt=  36.8ms  words=62,095,360
[E05  1389/1548 G   7580|CLM] train=3.7659  mask=13.9%  norm=0.783  lr=1.20e-04  dt=  37.1ms  words=62,103,552
[E05  1390/1548 G   7581|CLM] train=3.6754  mask=13.9%  norm=0.828  lr=1.20e-04  dt=  36.9ms  words=62,111,744
[E05  1391/1548 G   7582|CLM] train=4.4942  mask=13.9%  norm=0.835  lr=1.20e-04  dt=  36.9ms  words=62,119,936
[E05  1392/1548 G   7583|CLM] train=3.4768  mask=13.9%  norm=0.759  lr=1.20e-04  dt=  36.9ms  words=62,128,128
[E05  1393/1548 G   7584|CLM] train=2.3539  mask=13.9%  norm=1.772  lr=1.20e-04  dt=  36.9ms  words=62,136,320
[E05  1394/1548 G   7585|CLM] train=2.2874  mask=13.9%  norm=0.663  lr=1.20e-04  dt=  36.9ms  words=62,144,512
[E05  1395/1548 G   7586|CLM] train=4.5113  mask=13.9%  norm=0.938  lr=1.20e-04  dt=  37.0ms  words=62,152,704
[E05  1396/1548 G   7587|CLM] train=2.2926  mask=13.9%  norm=0.722  lr=1.20e-04  dt=  37.0ms  words=62,160,896
[E05  1397/1548 G   7588|CLM] train=4.6981  mask=13.9%  norm=0.913  lr=1.19e-04  dt=  36.9ms  words=62,169,088
[E05  1398/1548 G   7589|CLM] train=2.4939  mask=13.9%  norm=0.703  lr=1.19e-04  dt=  37.0ms  words=62,177,280
[E05  1399/1548 G   7590|CLM] train=2.8032  mask=13.9%  norm=0.798  lr=1.19e-04  dt=  37.3ms  words=62,185,472
[E05  1400/1548 G   7591|CLM] train=4.4781  mask=13.9%  norm=0.820  lr=1.19e-04  dt=  37.1ms  words=62,193,664
[E05  1401/1548 G   7592|CLM] train=4.2465  mask=13.9%  norm=1.134  lr=1.19e-04  dt=  38.5ms  words=62,201,856
[E05  1402/1548 G   7593|CLM] train=4.3826  mask=13.9%  norm=0.765  lr=1.19e-04  dt=  37.4ms  words=62,210,048
[E05  1403/1548 G   7594|CLM] train=2.0082  mask=13.9%  norm=0.671  lr=1.19e-04  dt=  37.3ms  words=62,218,240
[E05  1404/1548 G   7595|CLM] train=2.3578  mask=13.9%  norm=0.705  lr=1.19e-04  dt=  37.6ms  words=62,226,432
[E05  1405/1548 G   7596|CLM] train=4.4059  mask=13.9%  norm=0.943  lr=1.19e-04  dt=  37.3ms  words=62,234,624
[E05  1406/1548 G   7597|CLM] train=5.4605  mask=13.9%  norm=1.093  lr=1.19e-04  dt=  37.2ms  words=62,242,816
[E05  1407/1548 G   7598|CLM] train=2.0535  mask=13.9%  norm=0.755  lr=1.19e-04  dt=  37.0ms  words=62,251,008
[E05  1408/1548 G   7599|CLM] train=4.4266  mask=13.9%  norm=0.813  lr=1.19e-04  dt=  36.9ms  words=62,259,200
[E05  1409/1548 G   7600|CLM] train=3.9006  mask=13.9%  norm=0.973  lr=1.19e-04  dt=  37.3ms  words=62,267,392
[E05  1410/1548 G   7601|CLM] train=4.4304  mask=13.9%  norm=0.855  lr=1.19e-04  dt=  36.8ms  words=62,275,584
[E05  1411/1548 G   7602|CLM] train=4.6844  mask=13.9%  norm=0.966  lr=1.19e-04  dt=  37.0ms  words=62,283,776
[E05  1412/1548 G   7603|CLM] train=3.9450  mask=13.9%  norm=0.800  lr=1.19e-04  dt=  36.8ms  words=62,291,968
[E05  1413/1548 G   7604|CLM] train=2.1885  mask=13.9%  norm=0.777  lr=1.19e-04  dt=  36.9ms  words=62,300,160
[E05  1414/1548 G   7605|CLM] train=3.8469  mask=13.9%  norm=0.822  lr=1.19e-04  dt=  37.0ms  words=62,308,352
[E05  1415/1548 G   7606|CLM] train=2.7664  mask=13.9%  norm=0.830  lr=1.19e-04  dt=  37.0ms  words=62,316,544
[E05  1416/1548 G   7607|CLM] train=2.3272  mask=13.9%  norm=0.761  lr=1.19e-04  dt=  37.7ms  words=62,324,736
[E05  1417/1548 G   7608|CLM] train=1.6679  mask=13.9%  norm=0.873  lr=1.19e-04  dt=  37.3ms  words=62,332,928
[E05  1418/1548 G   7609|CLM] train=4.3929  mask=13.9%  norm=1.180  lr=1.19e-04  dt=  43.2ms  words=62,341,120
[E05  1419/1548 G   7610|CLM] train=2.0084  mask=13.9%  norm=0.822  lr=1.19e-04  dt=  38.3ms  words=62,349,312
[E05  1420/1548 G   7611|CLM] train=5.0486  mask=13.9%  norm=1.689  lr=1.19e-04  dt=  45.9ms  words=62,357,504
[E05  1421/1548 G   7612|CLM] train=4.1269  mask=13.9%  norm=0.977  lr=1.19e-04  dt=  46.2ms  words=62,365,696
[E05  1422/1548 G   7613|CLM] train=4.3869  mask=13.9%  norm=0.934  lr=1.19e-04  dt=  37.1ms  words=62,373,888
[E05  1423/1548 G   7614|CLM] train=4.3315  mask=13.9%  norm=1.034  lr=1.19e-04  dt=  43.9ms  words=62,382,080
[E05  1424/1548 G   7615|CLM] train=2.4630  mask=13.9%  norm=0.750  lr=1.18e-04  dt=  45.4ms  words=62,390,272
[E05  1425/1548 G   7616|CLM] train=4.3443  mask=13.9%  norm=0.846  lr=1.18e-04  dt=  43.6ms  words=62,398,464
[E05  1426/1548 G   7617|CLM] train=3.5493  mask=13.8%  norm=0.714  lr=1.18e-04  dt=  42.6ms  words=62,406,656
[E05  1427/1548 G   7618|CLM] train=4.0546  mask=13.8%  norm=0.839  lr=1.18e-04  dt=  46.1ms  words=62,414,848
[E05  1428/1548 G   7619|CLM] train=4.5254  mask=13.8%  norm=0.944  lr=1.18e-04  dt=  46.0ms  words=62,423,040
[E05  1429/1548 G   7620|CLM] train=2.1497  mask=13.8%  norm=0.788  lr=1.18e-04  dt=  44.2ms  words=62,431,232
[E05  1430/1548 G   7621|CLM] train=5.1870  mask=13.8%  norm=1.038  lr=1.18e-04  dt=  38.6ms  words=62,439,424
[E05  1431/1548 G   7622|CLM] train=4.2524  mask=13.8%  norm=0.849  lr=1.18e-04  dt=  37.1ms  words=62,447,616
[E05  1432/1548 G   7623|CLM] train=4.2679  mask=13.8%  norm=0.958  lr=1.18e-04  dt=  46.3ms  words=62,455,808
[E05  1433/1548 G   7624|CLM] train=2.2420  mask=13.8%  norm=0.736  lr=1.18e-04  dt=  37.2ms  words=62,464,000
[E05  1434/1548 G   7625|CLM] train=4.1581  mask=13.8%  norm=0.793  lr=1.18e-04  dt=  36.8ms  words=62,472,192
[E05  1435/1548 G   7626|CLM] train=3.9294  mask=13.8%  norm=0.685  lr=1.18e-04  dt=  36.8ms  words=62,480,384
[E05  1436/1548 G   7627|CLM] train=4.1041  mask=13.8%  norm=0.791  lr=1.18e-04  dt=  40.4ms  words=62,488,576
[E05  1437/1548 G   7628|CLM] train=2.5755  mask=13.8%  norm=0.876  lr=1.18e-04  dt=  45.8ms  words=62,496,768
[E05  1438/1548 G   7629|CLM] train=2.2703  mask=13.8%  norm=0.846  lr=1.18e-04  dt=  37.0ms  words=62,504,960
[E05  1439/1548 G   7630|CLM] train=4.2229  mask=13.8%  norm=0.904  lr=1.18e-04  dt=  39.3ms  words=62,513,152
[E05  1440/1548 G   7631|CLM] train=2.8499  mask=13.8%  norm=0.891  lr=1.18e-04  dt=  43.9ms  words=62,521,344
[E05  1441/1548 G   7632|CLM] train=4.7883  mask=13.8%  norm=0.894  lr=1.18e-04  dt=  48.2ms  words=62,529,536
[E05  1442/1548 G   7633|CLM] train=4.7426  mask=13.8%  norm=1.458  lr=1.18e-04  dt=  42.6ms  words=62,537,728
[E05  1443/1548 G   7634|CLM] train=4.0825  mask=13.8%  norm=0.946  lr=1.18e-04  dt=  37.3ms  words=62,545,920
[E05  1444/1548 G   7635|CLM] train=2.5346  mask=13.8%  norm=1.677  lr=1.18e-04  dt=  43.5ms  words=62,554,112
[E05  1445/1548 G   7636|CLM] train=2.2641  mask=13.8%  norm=0.824  lr=1.18e-04  dt=  40.2ms  words=62,562,304
[E05  1446/1548 G   7637|CLM] train=4.7107  mask=13.8%  norm=0.915  lr=1.18e-04  dt=  42.9ms  words=62,570,496
[E05  1447/1548 G   7638|CLM] train=3.9367  mask=13.8%  norm=0.941  lr=1.18e-04  dt=  37.1ms  words=62,578,688
[E05  1448/1548 G   7639|CLM] train=3.9463  mask=13.8%  norm=0.694  lr=1.18e-04  dt=  37.3ms  words=62,586,880
[E05  1449/1548 G   7640|CLM] train=3.6030  mask=13.8%  norm=0.779  lr=1.18e-04  dt=  37.4ms  words=62,595,072
[E05  1450/1548 G   7641|CLM] train=4.0577  mask=13.8%  norm=0.932  lr=1.18e-04  dt=  37.0ms  words=62,603,264
[E05  1451/1548 G   7642|CLM] train=3.6043  mask=13.8%  norm=0.741  lr=1.17e-04  dt=  37.2ms  words=62,611,456
[E05  1452/1548 G   7643|CLM] train=4.8340  mask=13.8%  norm=1.006  lr=1.17e-04  dt=  37.1ms  words=62,619,648
[E05  1453/1548 G   7644|CLM] train=1.9862  mask=13.8%  norm=0.715  lr=1.17e-04  dt=  37.6ms  words=62,627,840
[E05  1454/1548 G   7645|CLM] train=4.4368  mask=13.8%  norm=0.810  lr=1.17e-04  dt=  37.3ms  words=62,636,032
[E05  1455/1548 G   7646|CLM] train=5.2042  mask=13.8%  norm=1.377  lr=1.17e-04  dt=  37.4ms  words=62,644,224
[E05  1456/1548 G   7647|CLM] train=2.7022  mask=13.8%  norm=0.848  lr=1.17e-04  dt=  36.9ms  words=62,652,416
[E05  1457/1548 G   7648|CLM] train=4.0471  mask=13.8%  norm=1.135  lr=1.17e-04  dt=  37.6ms  words=62,660,608
[E05  1458/1548 G   7649|CLM] train=3.8291  mask=13.8%  norm=0.822  lr=1.17e-04  dt=  37.1ms  words=62,668,800
[E05  1459/1548 G   7650|CLM] train=3.9546  mask=13.8%  norm=0.907  lr=1.17e-04  dt=  37.1ms  words=62,676,992
[E05  1460/1548 G   7651|CLM] train=4.1117  mask=13.8%  norm=0.938  lr=1.17e-04  dt=  37.1ms  words=62,685,184
[E05  1461/1548 G   7652|CLM] train=4.0236  mask=13.8%  norm=0.859  lr=1.17e-04  dt=  37.1ms  words=62,693,376
[E05  1462/1548 G   7653|CLM] train=4.8201  mask=13.8%  norm=0.773  lr=1.17e-04  dt=  37.1ms  words=62,701,568
[E05  1463/1548 G   7654|CLM] train=2.1796  mask=13.8%  norm=0.945  lr=1.17e-04  dt=  37.0ms  words=62,709,760
[E05  1464/1548 G   7655|CLM] train=2.4525  mask=13.8%  norm=0.728  lr=1.17e-04  dt=  37.1ms  words=62,717,952
[E05  1465/1548 G   7656|CLM] train=3.8439  mask=13.8%  norm=0.785  lr=1.17e-04  dt=  37.7ms  words=62,726,144
[E05  1466/1548 G   7657|CLM] train=4.6250  mask=13.8%  norm=0.772  lr=1.17e-04  dt=  37.5ms  words=62,734,336
[E05  1467/1548 G   7658|CLM] train=3.7710  mask=13.8%  norm=0.806  lr=1.17e-04  dt=  37.4ms  words=62,742,528
[E05  1468/1548 G   7659|CLM] train=4.3284  mask=13.8%  norm=1.079  lr=1.17e-04  dt=  37.2ms  words=62,750,720
[E05  1469/1548 G   7660|CLM] train=1.9652  mask=13.8%  norm=0.806  lr=1.17e-04  dt=  37.1ms  words=62,758,912
[E05  1470/1548 G   7661|CLM] train=4.4629  mask=13.8%  norm=0.948  lr=1.17e-04  dt=  36.9ms  words=62,767,104
[E05  1471/1548 G   7662|CLM] train=2.1841  mask=13.8%  norm=0.689  lr=1.17e-04  dt=  37.0ms  words=62,775,296
[E05  1472/1548 G   7663|CLM] train=2.2462  mask=13.8%  norm=0.671  lr=1.17e-04  dt=  36.8ms  words=62,783,488
[E05  1473/1548 G   7664|CLM] train=2.3659  mask=13.8%  norm=0.734  lr=1.17e-04  dt=  37.1ms  words=62,791,680
[E05  1474/1548 G   7665|CLM] train=3.8659  mask=13.8%  norm=0.772  lr=1.17e-04  dt=  37.1ms  words=62,799,872
[E05  1475/1548 G   7666|CLM] train=2.5899  mask=13.8%  norm=0.855  lr=1.17e-04  dt=  37.7ms  words=62,808,064
[E05  1476/1548 G   7667|CLM] train=4.2348  mask=13.8%  norm=0.782  lr=1.17e-04  dt=  37.2ms  words=62,816,256
[E05  1477/1548 G   7668|CLM] train=2.3189  mask=13.8%  norm=0.620  lr=1.17e-04  dt=  37.2ms  words=62,824,448
[E05  1478/1548 G   7669|CLM] train=4.4636  mask=13.8%  norm=0.951  lr=1.16e-04  dt=  37.5ms  words=62,832,640
[E05  1479/1548 G   7670|CLM] train=3.5322  mask=13.8%  norm=0.693  lr=1.16e-04  dt=  37.9ms  words=62,840,832
[E05  1480/1548 G   7671|CLM] train=3.7771  mask=13.8%  norm=0.711  lr=1.16e-04  dt=  37.2ms  words=62,849,024
[E05  1481/1548 G   7672|CLM] train=3.7054  mask=13.8%  norm=0.688  lr=1.16e-04  dt=  37.4ms  words=62,857,216
[E05  1482/1548 G   7673|CLM] train=3.9251  mask=13.8%  norm=0.858  lr=1.16e-04  dt=  37.3ms  words=62,865,408
[E05  1483/1548 G   7674|CLM] train=4.5552  mask=13.8%  norm=2.546  lr=1.16e-04  dt=  37.4ms  words=62,873,600
[E05  1484/1548 G   7675|CLM] train=2.5257  mask=13.8%  norm=1.012  lr=1.16e-04  dt=  37.4ms  words=62,881,792
[E05  1485/1548 G   7676|CLM] train=4.4839  mask=13.8%  norm=0.795  lr=1.16e-04  dt=  37.2ms  words=62,889,984
[E05  1486/1548 G   7677|CLM] train=4.3092  mask=13.8%  norm=0.907  lr=1.16e-04  dt=  37.2ms  words=62,898,176
[E05  1487/1548 G   7678|CLM] train=4.0167  mask=13.8%  norm=0.841  lr=1.16e-04  dt=  38.2ms  words=62,906,368
[E05  1488/1548 G   7679|CLM] train=4.5503  mask=13.8%  norm=0.945  lr=1.16e-04  dt=  37.2ms  words=62,914,560
[E05  1489/1548 G   7680|CLM] train=3.4263  mask=13.8%  norm=0.778  lr=1.16e-04  dt=  37.0ms  words=62,922,752
[E05  1490/1548 G   7681|CLM] train=2.6714  mask=13.8%  norm=0.794  lr=1.16e-04  dt=  37.8ms  words=62,930,944
[E05  1491/1548 G   7682|CLM] train=3.9717  mask=13.8%  norm=0.875  lr=1.16e-04  dt=  37.2ms  words=62,939,136
[E05  1492/1548 G   7683|CLM] train=4.4388  mask=13.8%  norm=0.960  lr=1.16e-04  dt=  37.4ms  words=62,947,328
[E05  1493/1548 G   7684|CLM] train=2.5208  mask=13.8%  norm=0.721  lr=1.16e-04  dt=  37.3ms  words=62,955,520
[E05  1494/1548 G   7685|CLM] train=4.1812  mask=13.8%  norm=0.761  lr=1.16e-04  dt=  37.1ms  words=62,963,712
[E05  1495/1548 G   7686|CLM] train=4.1468  mask=13.8%  norm=0.860  lr=1.16e-04  dt=  37.5ms  words=62,971,904
[E05  1496/1548 G   7687|CLM] train=4.1815  mask=13.8%  norm=0.786  lr=1.16e-04  dt=  37.3ms  words=62,980,096
[E05  1497/1548 G   7688|CLM] train=1.9404  mask=13.8%  norm=0.724  lr=1.16e-04  dt=  37.4ms  words=62,988,288
[E05  1498/1548 G   7689|CLM] train=4.2066  mask=13.8%  norm=0.873  lr=1.16e-04  dt=  37.3ms  words=62,996,480
[E05  1499/1548 G   7690|CLM] train=4.5454  mask=13.8%  norm=0.753  lr=1.16e-04  dt=  37.1ms  words=63,004,672
[E05  1500/1548 G   7691|CLM] train=4.2772  mask=13.8%  norm=0.915  lr=1.16e-04  dt=  37.4ms  words=63,012,864
[E05  1501/1548 G   7692|CLM] train=4.1856  mask=13.8%  norm=0.900  lr=1.16e-04  dt=  37.2ms  words=63,021,056
[E05  1502/1548 G   7693|CLM] train=3.8075  mask=13.8%  norm=0.819  lr=1.16e-04  dt=  37.0ms  words=63,029,248
[E05  1503/1548 G   7694|CLM] train=4.1186  mask=13.8%  norm=0.733  lr=1.16e-04  dt=  37.4ms  words=63,037,440
[E05  1504/1548 G   7695|CLM] train=4.2252  mask=13.8%  norm=0.977  lr=1.16e-04  dt=  37.0ms  words=63,045,632
[E05  1505/1548 G   7696|CLM] train=2.3658  mask=13.8%  norm=0.747  lr=1.15e-04  dt=  37.4ms  words=63,053,824
[E05  1506/1548 G   7697|CLM] train=3.3381  mask=13.8%  norm=1.977  lr=1.15e-04  dt=  37.6ms  words=63,062,016
[E05  1507/1548 G   7698|CLM] train=3.7658  mask=13.8%  norm=0.715  lr=1.15e-04  dt=  37.0ms  words=63,070,208
[E05  1508/1548 G   7699|CLM] train=3.6887  mask=13.8%  norm=0.786  lr=1.15e-04  dt=  37.1ms  words=63,078,400
[E05  1509/1548 G   7700|CLM] train=2.2946  mask=13.8%  norm=0.908  lr=1.15e-04  dt=  37.9ms  words=63,086,592
[E05  1510/1548 G   7701|CLM] train=3.9264  mask=13.8%  norm=0.707  lr=1.15e-04  dt=  36.8ms  words=63,094,784
[E05  1511/1548 G   7702|CLM] train=4.1242  mask=13.8%  norm=0.786  lr=1.15e-04  dt=  37.8ms  words=63,102,976
[E05  1512/1548 G   7703|CLM] train=2.2481  mask=13.8%  norm=0.657  lr=1.15e-04  dt=  36.8ms  words=63,111,168
[E05  1513/1548 G   7704|CLM] train=2.4032  mask=13.8%  norm=0.711  lr=1.15e-04  dt=  37.0ms  words=63,119,360
[E05  1514/1548 G   7705|CLM] train=2.4191  mask=13.8%  norm=0.849  lr=1.15e-04  dt=  37.3ms  words=63,127,552
[E05  1515/1548 G   7706|CLM] train=4.2832  mask=13.8%  norm=0.908  lr=1.15e-04  dt=  36.8ms  words=63,135,744
[E05  1516/1548 G   7707|CLM] train=4.1291  mask=13.8%  norm=1.001  lr=1.15e-04  dt=  36.9ms  words=63,143,936
[E05  1517/1548 G   7708|CLM] train=4.4360  mask=13.8%  norm=0.969  lr=1.15e-04  dt=  37.0ms  words=63,152,128
[E05  1518/1548 G   7709|CLM] train=4.2785  mask=13.8%  norm=0.798  lr=1.15e-04  dt=  37.9ms  words=63,160,320
[E05  1519/1548 G   7710|CLM] train=4.2707  mask=13.8%  norm=0.950  lr=1.15e-04  dt=  37.2ms  words=63,168,512
[E05  1520/1548 G   7711|CLM] train=4.1934  mask=13.8%  norm=0.992  lr=1.15e-04  dt=  37.1ms  words=63,176,704
[E05  1521/1548 G   7712|CLM] train=2.7042  mask=13.8%  norm=0.764  lr=1.15e-04  dt=  37.0ms  words=63,184,896
[E05  1522/1548 G   7713|CLM] train=3.7476  mask=13.8%  norm=0.836  lr=1.15e-04  dt=  37.6ms  words=63,193,088
[E05  1523/1548 G   7714|CLM] train=2.1439  mask=13.8%  norm=0.792  lr=1.15e-04  dt=  37.2ms  words=63,201,280
[E05  1524/1548 G   7715|CLM] train=2.2255  mask=13.8%  norm=0.881  lr=1.15e-04  dt=  37.7ms  words=63,209,472
[E05  1525/1548 G   7716|CLM] train=3.7384  mask=13.8%  norm=1.036  lr=1.15e-04  dt=  37.0ms  words=63,217,664
[E05  1526/1548 G   7717|CLM] train=2.6121  mask=13.8%  norm=0.709  lr=1.15e-04  dt=  37.1ms  words=63,225,856
[E05  1527/1548 G   7718|CLM] train=2.1100  mask=13.8%  norm=0.788  lr=1.15e-04  dt=  36.8ms  words=63,234,048
[E05  1528/1548 G   7719|CLM] train=2.1344  mask=13.8%  norm=0.672  lr=1.15e-04  dt=  36.8ms  words=63,242,240
[E05  1529/1548 G   7720|CLM] train=4.3577  mask=13.8%  norm=0.888  lr=1.15e-04  dt=  37.0ms  words=63,250,432
[E05  1530/1548 G   7721|CLM] train=2.6629  mask=13.8%  norm=0.710  lr=1.15e-04  dt=  37.0ms  words=63,258,624
[E05  1531/1548 G   7722|CLM] train=3.8953  mask=13.8%  norm=0.959  lr=1.15e-04  dt=  37.7ms  words=63,266,816
[E05  1532/1548 G   7723|CLM] train=4.4424  mask=13.8%  norm=1.121  lr=1.14e-04  dt=  37.1ms  words=63,275,008
[E05  1533/1548 G   7724|CLM] train=4.4446  mask=13.8%  norm=1.260  lr=1.14e-04  dt=  37.1ms  words=63,283,200
[E05  1534/1548 G   7725|CLM] train=2.2383  mask=13.8%  norm=0.787  lr=1.14e-04  dt=  36.9ms  words=63,291,392
[E05  1535/1548 G   7726|CLM] train=2.2641  mask=13.8%  norm=0.926  lr=1.14e-04  dt=  36.8ms  words=63,299,584
[E05  1536/1548 G   7727|CLM] train=2.8356  mask=13.8%  norm=0.835  lr=1.14e-04  dt=  36.9ms  words=63,307,776
[E05  1537/1548 G   7728|CLM] train=2.1689  mask=13.8%  norm=0.709  lr=1.14e-04  dt=  37.0ms  words=63,315,968
[E05  1538/1548 G   7729|CLM] train=3.9898  mask=13.8%  norm=1.062  lr=1.14e-04  dt=  36.8ms  words=63,324,160
[E05  1539/1548 G   7730|CLM] train=2.0891  mask=13.8%  norm=0.674  lr=1.14e-04  dt=  36.8ms  words=63,332,352
[E05  1540/1548 G   7731|CLM] train=2.2119  mask=13.8%  norm=0.657  lr=1.14e-04  dt=  36.8ms  words=63,340,544
[E05  1541/1548 G   7732|CLM] train=2.2286  mask=13.8%  norm=0.737  lr=1.14e-04  dt=  37.0ms  words=63,348,736
[E05  1542/1548 G   7733|CLM] train=4.2902  mask=13.8%  norm=0.861  lr=1.14e-04  dt=  36.8ms  words=63,356,928
[E05  1543/1548 G   7734|CLM] train=4.6319  mask=13.8%  norm=1.137  lr=1.14e-04  dt=  36.9ms  words=63,365,120
[E05  1544/1548 G   7735|CLM] train=2.7933  mask=13.8%  norm=0.729  lr=1.14e-04  dt=  37.0ms  words=63,373,312
[E05  1545/1548 G   7736|CLM] train=4.2563  mask=13.8%  norm=0.833  lr=1.14e-04  dt=  37.0ms  words=63,381,504
[E05  1546/1548 G   7737|CLM] train=4.4748  mask=13.8%  norm=0.747  lr=1.14e-04  dt=  36.8ms  words=63,389,696
[E05  1547/1548 G   7738|CLM] train=4.3009  mask=13.8%  norm=1.095  lr=1.14e-04  dt=  36.9ms  words=63,397,888
[E05  1548/1548 G   7739|CLM] train=3.6103  mask=13.8%  norm=0.786  lr=1.14e-04  dt=  36.9ms  words=63,406,080
[E06     1/1548 G   7740|CLM] train=3.9960  mask=13.8%  norm=0.865  lr=1.14e-04  dt=  37.0ms  words=63,414,272
[E06     2/1548 G   7741|CLM] train=2.1911  mask=13.7%  norm=0.698  lr=1.14e-04  dt=  36.9ms  words=63,422,464
[E06     3/1548 G   7742|CLM] train=2.2584  mask=13.7%  norm=0.716  lr=1.14e-04  dt=  37.3ms  words=63,430,656
[E06     4/1548 G   7743|CLM] train=4.3207  mask=13.7%  norm=0.778  lr=1.14e-04  dt=  37.1ms  words=63,438,848
[E06     5/1548 G   7744|CLM] train=3.9943  mask=13.7%  norm=0.721  lr=1.14e-04  dt=  37.0ms  words=63,447,040
[E06     6/1548 G   7745|CLM] train=4.3603  mask=13.7%  norm=0.853  lr=1.14e-04  dt=  36.9ms  words=63,455,232
[E06     7/1548 G   7746|CLM] train=2.3436  mask=13.7%  norm=0.638  lr=1.14e-04  dt=  36.7ms  words=63,463,424
[E06     8/1548 G   7747|CLM] train=2.2486  mask=13.7%  norm=0.803  lr=1.14e-04  dt=  37.6ms  words=63,471,616
[E06     9/1548 G   7748|CLM] train=4.4329  mask=13.7%  norm=1.102  lr=1.14e-04  dt=  37.0ms  words=63,479,808
[E06    10/1548 G   7749|CLM] train=3.8736  mask=13.7%  norm=1.069  lr=1.14e-04  dt=  37.4ms  words=63,488,000
[E06    11/1548 G   7750|CLM] train=4.0403  mask=13.7%  norm=0.797  lr=1.13e-04  dt=  37.0ms  words=63,496,192
[E06    12/1548 G   7751|CLM] train=4.4522  mask=13.7%  norm=0.849  lr=1.13e-04  dt=  36.9ms  words=63,504,384
[E06    13/1548 G   7752|CLM] train=2.2172  mask=13.7%  norm=0.671  lr=1.13e-04  dt=  36.7ms  words=63,512,576
[E06    14/1548 G   7753|CLM] train=4.4983  mask=13.7%  norm=1.024  lr=1.13e-04  dt=  37.0ms  words=63,520,768
[E06    15/1548 G   7754|CLM] train=2.3506  mask=13.7%  norm=0.672  lr=1.13e-04  dt=  37.6ms  words=63,528,960
[E06    16/1548 G   7755|CLM] train=4.1093  mask=13.7%  norm=0.905  lr=1.13e-04  dt=  36.8ms  words=63,537,152
[E06    17/1548 G   7756|CLM] train=2.0750  mask=13.7%  norm=0.659  lr=1.13e-04  dt=  37.0ms  words=63,545,344
[E06    18/1548 G   7757|CLM] train=4.2354  mask=13.7%  norm=0.863  lr=1.13e-04  dt=  37.2ms  words=63,553,536
[E06    19/1548 G   7758|CLM] train=4.5293  mask=13.7%  norm=0.940  lr=1.13e-04  dt=  37.0ms  words=63,561,728
[E06    20/1548 G   7759|CLM] train=2.1405  mask=13.7%  norm=1.078  lr=1.13e-04  dt=  36.8ms  words=63,569,920
[E06    21/1548 G   7760|CLM] train=4.5966  mask=13.7%  norm=1.057  lr=1.13e-04  dt=  36.9ms  words=63,578,112
[E06    22/1548 G   7761|CLM] train=4.1718  mask=13.7%  norm=0.977  lr=1.13e-04  dt=  37.0ms  words=63,586,304
[E06    23/1548 G   7762|CLM] train=4.0734  mask=13.7%  norm=0.974  lr=1.13e-04  dt=  37.1ms  words=63,594,496
[E06    24/1548 G   7763|CLM] train=2.4975  mask=13.7%  norm=0.739  lr=1.13e-04  dt=  37.4ms  words=63,602,688
[E06    25/1548 G   7764|CLM] train=2.1951  mask=13.7%  norm=0.821  lr=1.13e-04  dt=  37.1ms  words=63,610,880
[E06    26/1548 G   7765|CLM] train=2.2730  mask=13.7%  norm=0.736  lr=1.13e-04  dt=  37.0ms  words=63,619,072
[E06    27/1548 G   7766|CLM] train=3.8800  mask=13.7%  norm=0.970  lr=1.13e-04  dt=  36.9ms  words=63,627,264
[E06    28/1548 G   7767|CLM] train=2.4141  mask=13.7%  norm=0.832  lr=1.13e-04  dt=  37.0ms  words=63,635,456
[E06    29/1548 G   7768|CLM] train=2.4441  mask=13.7%  norm=0.744  lr=1.13e-04  dt=  37.0ms  words=63,643,648
[E06    30/1548 G   7769|CLM] train=3.9273  mask=13.7%  norm=0.852  lr=1.13e-04  dt=  36.9ms  words=63,651,840
[E06    31/1548 G   7770|CLM] train=4.0555  mask=13.7%  norm=1.002  lr=1.13e-04  dt=  36.8ms  words=63,660,032
[E06    32/1548 G   7771|CLM] train=4.5771  mask=13.7%  norm=0.861  lr=1.13e-04  dt=  36.9ms  words=63,668,224
[E06    33/1548 G   7772|CLM] train=3.9274  mask=13.7%  norm=0.792  lr=1.13e-04  dt=  37.0ms  words=63,676,416
[E06    34/1548 G   7773|CLM] train=4.1509  mask=13.7%  norm=0.785  lr=1.13e-04  dt=  36.8ms  words=63,684,608
[E06    35/1548 G   7774|CLM] train=2.2886  mask=13.7%  norm=0.904  lr=1.13e-04  dt=  36.9ms  words=63,692,800
[E06    36/1548 G   7775|CLM] train=3.6529  mask=13.7%  norm=0.779  lr=1.13e-04  dt=  37.0ms  words=63,700,992
[E06    37/1548 G   7776|CLM] train=2.4117  mask=13.7%  norm=0.955  lr=1.13e-04  dt=  37.1ms  words=63,709,184
[E06    38/1548 G   7777|CLM] train=3.8462  mask=13.7%  norm=1.469  lr=1.12e-04  dt=  36.9ms  words=63,717,376
[E06    39/1548 G   7778|CLM] train=4.1794  mask=13.7%  norm=0.882  lr=1.12e-04  dt=  37.2ms  words=63,725,568
[E06    40/1548 G   7779|CLM] train=2.3512  mask=13.7%  norm=0.662  lr=1.12e-04  dt=  36.7ms  words=63,733,760
[E06    41/1548 G   7780|CLM] train=5.2050  mask=13.7%  norm=1.575  lr=1.12e-04  dt=  36.8ms  words=63,741,952
[E06    42/1548 G   7781|CLM] train=2.4399  mask=13.7%  norm=0.781  lr=1.12e-04  dt=  36.9ms  words=63,750,144
[E06    43/1548 G   7782|CLM] train=2.5522  mask=13.7%  norm=0.860  lr=1.12e-04  dt=  36.9ms  words=63,758,336
[E06    44/1548 G   7783|CLM] train=4.7345  mask=13.7%  norm=0.959  lr=1.12e-04  dt=  37.0ms  words=63,766,528
[E06    45/1548 G   7784|CLM] train=4.1946  mask=13.7%  norm=0.923  lr=1.12e-04  dt=  37.0ms  words=63,774,720
[E06    46/1548 G   7785|CLM] train=1.9545  mask=13.7%  norm=0.786  lr=1.12e-04  dt=  36.8ms  words=63,782,912
[E06    47/1548 G   7786|CLM] train=4.3315  mask=13.7%  norm=0.883  lr=1.12e-04  dt=  36.7ms  words=63,791,104
[E06    48/1548 G   7787|CLM] train=2.1442  mask=13.7%  norm=0.681  lr=1.12e-04  dt=  36.9ms  words=63,799,296
[E06    49/1548 G   7788|CLM] train=4.6094  mask=13.7%  norm=1.079  lr=1.12e-04  dt=  37.0ms  words=63,807,488
[E06    50/1548 G   7789|CLM] train=4.1543  mask=13.7%  norm=0.893  lr=1.12e-04  dt=  36.8ms  words=63,815,680
[E06    51/1548 G   7790|CLM] train=4.1829  mask=13.7%  norm=0.899  lr=1.12e-04  dt=  37.3ms  words=63,823,872
[E06    52/1548 G   7791|CLM] train=2.1329  mask=13.7%  norm=0.763  lr=1.12e-04  dt=  36.8ms  words=63,832,064
[E06    53/1548 G   7792|CLM] train=2.8079  mask=13.7%  norm=0.713  lr=1.12e-04  dt=  36.9ms  words=63,840,256
[E06    54/1548 G   7793|CLM] train=2.1609  mask=13.7%  norm=0.692  lr=1.12e-04  dt=  36.8ms  words=63,848,448
[E06    55/1548 G   7794|CLM] train=2.3192  mask=13.7%  norm=0.637  lr=1.12e-04  dt=  36.9ms  words=63,856,640
[E06    56/1548 G   7795|CLM] train=3.8919  mask=13.7%  norm=0.773  lr=1.12e-04  dt=  36.9ms  words=63,864,832
[E06    57/1548 G   7796|CLM] train=4.1637  mask=13.7%  norm=0.870  lr=1.12e-04  dt=  36.9ms  words=63,873,024
[E06    58/1548 G   7797|CLM] train=2.3304  mask=13.7%  norm=0.790  lr=1.12e-04  dt=  36.9ms  words=63,881,216
[E06    59/1548 G   7798|CLM] train=2.6561  mask=13.7%  norm=0.908  lr=1.12e-04  dt=  36.8ms  words=63,889,408
[E06    60/1548 G   7799|CLM] train=4.2566  mask=13.7%  norm=0.937  lr=1.12e-04  dt=  36.9ms  words=63,897,600
[E06    61/1548 G   7800|CLM] train=1.9715  mask=13.7%  norm=0.722  lr=1.12e-04  dt=  37.1ms  words=63,905,792
[E06    62/1548 G   7801|CLM] train=3.8585  mask=13.7%  norm=0.723  lr=1.12e-04  dt=  36.9ms  words=63,913,984
[E06    63/1548 G   7802|CLM] train=4.9519  mask=13.7%  norm=1.089  lr=1.12e-04  dt=  36.8ms  words=63,922,176
[E06    64/1548 G   7803|CLM] train=4.6897  mask=13.7%  norm=1.082  lr=1.12e-04  dt=  36.8ms  words=63,930,368
[E06    65/1548 G   7804|CLM] train=3.8638  mask=13.7%  norm=0.757  lr=1.11e-04  dt=  37.0ms  words=63,938,560
[E06    66/1548 G   7805|CLM] train=3.8696  mask=13.7%  norm=0.701  lr=1.11e-04  dt=  37.1ms  words=63,946,752
[E06    67/1548 G   7806|CLM] train=4.0373  mask=13.7%  norm=0.827  lr=1.11e-04  dt=  37.1ms  words=63,954,944
[E06    68/1548 G   7807|CLM] train=4.2630  mask=13.7%  norm=0.787  lr=1.11e-04  dt=  36.9ms  words=63,963,136
[E06    69/1548 G   7808|CLM] train=3.8411  mask=13.7%  norm=0.714  lr=1.11e-04  dt=  37.5ms  words=63,971,328
[E06    70/1548 G   7809|CLM] train=2.4357  mask=13.7%  norm=0.732  lr=1.11e-04  dt=  37.3ms  words=63,979,520
[E06    71/1548 G   7810|CLM] train=3.4505  mask=13.7%  norm=0.702  lr=1.11e-04  dt=  37.8ms  words=63,987,712
[E06    72/1548 G   7811|CLM] train=3.4075  mask=13.7%  norm=0.680  lr=1.11e-04  dt=  37.6ms  words=63,995,904
[E06    73/1548 G   7812|CLM] train=4.2716  mask=13.7%  norm=0.857  lr=1.11e-04  dt=  37.0ms  words=64,004,096
[E06    74/1548 G   7813|CLM] train=4.0242  mask=13.7%  norm=0.781  lr=1.11e-04  dt=  37.0ms  words=64,012,288
[E06    75/1548 G   7814|CLM] train=2.5800  mask=13.7%  norm=0.757  lr=1.11e-04  dt=  36.9ms  words=64,020,480
[E06    76/1548 G   7815|CLM] train=4.1933  mask=13.7%  norm=0.786  lr=1.11e-04  dt=  36.9ms  words=64,028,672
[E06    77/1548 G   7816|CLM] train=4.2827  mask=13.7%  norm=0.828  lr=1.11e-04  dt=  36.9ms  words=64,036,864
[E06    78/1548 G   7817|CLM] train=4.7873  mask=13.7%  norm=0.838  lr=1.11e-04  dt=  37.0ms  words=64,045,056
[E06    79/1548 G   7818|CLM] train=2.0754  mask=13.7%  norm=0.751  lr=1.11e-04  dt=  36.9ms  words=64,053,248
[E06    80/1548 G   7819|CLM] train=4.3422  mask=13.7%  norm=0.941  lr=1.11e-04  dt=  36.8ms  words=64,061,440
[E06    81/1548 G   7820|CLM] train=4.5738  mask=13.7%  norm=0.804  lr=1.11e-04  dt=  37.0ms  words=64,069,632
[E06    82/1548 G   7821|CLM] train=4.9250  mask=13.7%  norm=1.251  lr=1.11e-04  dt=  37.0ms  words=64,077,824
[E06    83/1548 G   7822|CLM] train=4.5263  mask=13.7%  norm=0.881  lr=1.11e-04  dt=  36.9ms  words=64,086,016
[E06    84/1548 G   7823|CLM] train=4.2647  mask=13.7%  norm=0.879  lr=1.11e-04  dt=  36.9ms  words=64,094,208
[E06    85/1548 G   7824|CLM] train=4.0992  mask=13.7%  norm=0.877  lr=1.11e-04  dt=  36.9ms  words=64,102,400
[E06    86/1548 G   7825|CLM] train=4.2037  mask=13.7%  norm=0.817  lr=1.11e-04  dt=  37.1ms  words=64,110,592
[E06    87/1548 G   7826|CLM] train=2.2679  mask=13.7%  norm=0.937  lr=1.11e-04  dt=  36.8ms  words=64,118,784
[E06    88/1548 G   7827|CLM] train=4.5644  mask=13.7%  norm=0.949  lr=1.11e-04  dt=  36.9ms  words=64,126,976
[E06    89/1548 G   7828|CLM] train=3.8703  mask=13.7%  norm=0.774  lr=1.11e-04  dt=  36.9ms  words=64,135,168
[E06    90/1548 G   7829|CLM] train=4.1004  mask=13.7%  norm=0.702  lr=1.11e-04  dt=  37.0ms  words=64,143,360
[E06    91/1548 G   7830|CLM] train=5.0364  mask=13.7%  norm=1.266  lr=1.11e-04  dt=  37.0ms  words=64,151,552
[E06    92/1548 G   7831|CLM] train=4.0238  mask=13.7%  norm=0.855  lr=1.11e-04  dt=  37.0ms  words=64,159,744
[E06    93/1548 G   7832|CLM] train=2.4899  mask=13.7%  norm=0.985  lr=1.10e-04  dt=  36.8ms  words=64,167,936
[E06    94/1548 G   7833|CLM] train=4.1771  mask=13.7%  norm=0.825  lr=1.10e-04  dt=  37.0ms  words=64,176,128
[E06    95/1548 G   7834|CLM] train=4.0460  mask=13.7%  norm=0.819  lr=1.10e-04  dt=  36.8ms  words=64,184,320
[E06    96/1548 G   7835|CLM] train=2.3111  mask=13.7%  norm=0.846  lr=1.10e-04  dt=  37.0ms  words=64,192,512
[E06    97/1548 G   7836|CLM] train=3.5421  mask=13.7%  norm=0.818  lr=1.10e-04  dt=  37.0ms  words=64,200,704
[E06    98/1548 G   7837|CLM] train=2.3983  mask=13.7%  norm=0.637  lr=1.10e-04  dt=  37.0ms  words=64,208,896
[E06    99/1548 G   7838|CLM] train=2.7120  mask=13.7%  norm=0.700  lr=1.10e-04  dt=  36.9ms  words=64,217,088
[E06   100/1548 G   7839|CLM] train=3.8375  mask=13.7%  norm=0.927  lr=1.10e-04  dt=  36.8ms  words=64,225,280
[E06   101/1548 G   7840|CLM] train=4.6426  mask=13.7%  norm=1.791  lr=1.10e-04  dt=  36.9ms  words=64,233,472
[E06   102/1548 G   7841|CLM] train=3.7519  mask=13.7%  norm=0.799  lr=1.10e-04  dt=  37.0ms  words=64,241,664
[E06   103/1548 G   7842|CLM] train=4.4586  mask=13.7%  norm=0.802  lr=1.10e-04  dt=  36.8ms  words=64,249,856
[E06   104/1548 G   7843|CLM] train=4.0513  mask=13.7%  norm=0.979  lr=1.10e-04  dt=  36.8ms  words=64,258,048
[E06   105/1548 G   7844|CLM] train=5.3969  mask=13.7%  norm=1.457  lr=1.10e-04  dt=  36.9ms  words=64,266,240
[E06   106/1548 G   7845|CLM] train=3.6974  mask=13.7%  norm=0.830  lr=1.10e-04  dt=  37.0ms  words=64,274,432
[E06   107/1548 G   7846|CLM] train=2.5732  mask=13.7%  norm=0.765  lr=1.10e-04  dt=  36.8ms  words=64,282,624
[E06   108/1548 G   7847|CLM] train=3.8564  mask=13.7%  norm=0.964  lr=1.10e-04  dt=  36.8ms  words=64,290,816
[E06   109/1548 G   7848|CLM] train=3.8438  mask=13.7%  norm=0.821  lr=1.10e-04  dt=  36.9ms  words=64,299,008
[E06   110/1548 G   7849|CLM] train=2.1448  mask=13.7%  norm=0.821  lr=1.10e-04  dt=  37.0ms  words=64,307,200
[E06   111/1548 G   7850|CLM] train=4.0779  mask=13.7%  norm=0.810  lr=1.10e-04  dt=  36.9ms  words=64,315,392
[E06   112/1548 G   7851|CLM] train=3.6767  mask=13.7%  norm=0.835  lr=1.10e-04  dt=  36.9ms  words=64,323,584
[E06   113/1548 G   7852|CLM] train=4.0900  mask=13.7%  norm=0.744  lr=1.10e-04  dt=  36.8ms  words=64,331,776
[E06   114/1548 G   7853|CLM] train=4.9085  mask=13.7%  norm=1.636  lr=1.10e-04  dt=  37.0ms  words=64,339,968
[E06   115/1548 G   7854|CLM] train=1.6878  mask=13.7%  norm=0.920  lr=1.10e-04  dt=  36.8ms  words=64,348,160
[E06   116/1548 G   7855|CLM] train=5.0899  mask=13.7%  norm=1.027  lr=1.10e-04  dt=  36.9ms  words=64,356,352
[E06   117/1548 G   7856|CLM] train=4.6787  mask=13.7%  norm=1.037  lr=1.10e-04  dt=  36.9ms  words=64,364,544
[E06   118/1548 G   7857|CLM] train=2.2948  mask=13.7%  norm=0.861  lr=1.10e-04  dt=  38.1ms  words=64,372,736
[E06   119/1548 G   7858|CLM] train=2.7908  mask=13.7%  norm=1.265  lr=1.10e-04  dt=  37.1ms  words=64,380,928
[E06   120/1548 G   7859|CLM] train=4.7033  mask=13.7%  norm=0.974  lr=1.09e-04  dt=  37.3ms  words=64,389,120
[E06   121/1548 G   7860|CLM] train=4.1411  mask=13.7%  norm=0.922  lr=1.09e-04  dt=  37.4ms  words=64,397,312
[E06   122/1548 G   7861|CLM] train=4.4912  mask=13.7%  norm=0.848  lr=1.09e-04  dt=  36.9ms  words=64,405,504
[E06   123/1548 G   7862|CLM] train=4.0398  mask=13.7%  norm=0.791  lr=1.09e-04  dt=  37.1ms  words=64,413,696
[E06   124/1548 G   7863|CLM] train=4.1020  mask=13.7%  norm=0.938  lr=1.09e-04  dt=  37.9ms  words=64,421,888
[E06   125/1548 G   7864|CLM] train=2.4805  mask=13.6%  norm=0.815  lr=1.09e-04  dt=  39.9ms  words=64,430,080
[E06   126/1548 G   7865|CLM] train=3.8368  mask=13.6%  norm=0.767  lr=1.09e-04  dt=  41.1ms  words=64,438,272
[E06   127/1548 G   7866|CLM] train=4.0754  mask=13.6%  norm=0.898  lr=1.09e-04  dt=  39.1ms  words=64,446,464
[E06   128/1548 G   7867|CLM] train=3.8648  mask=13.6%  norm=0.725  lr=1.09e-04  dt=  37.5ms  words=64,454,656
[E06   129/1548 G   7868|CLM] train=4.6897  mask=13.6%  norm=1.022  lr=1.09e-04  dt=  37.8ms  words=64,462,848
[E06   130/1548 G   7869|CLM] train=4.6073  mask=13.6%  norm=0.999  lr=1.09e-04  dt=  45.6ms  words=64,471,040
[E06   131/1548 G   7870|CLM] train=2.5308  mask=13.6%  norm=1.003  lr=1.09e-04  dt=  46.0ms  words=64,479,232
[E06   132/1548 G   7871|CLM] train=3.9020  mask=13.6%  norm=0.915  lr=1.09e-04  dt=  43.8ms  words=64,487,424
[E06   133/1548 G   7872|CLM] train=3.8998  mask=13.6%  norm=0.782  lr=1.09e-04  dt=  39.3ms  words=64,495,616
[E06   134/1548 G   7873|CLM] train=3.5352  mask=13.6%  norm=0.814  lr=1.09e-04  dt=  36.9ms  words=64,503,808
[E06   135/1548 G   7874|CLM] train=2.2438  mask=13.6%  norm=0.679  lr=1.09e-04  dt=  37.0ms  words=64,512,000
[E06   136/1548 G   7875|CLM] train=2.3073  mask=13.6%  norm=0.639  lr=1.09e-04  dt=  36.9ms  words=64,520,192
[E06   137/1548 G   7876|CLM] train=4.4287  mask=13.6%  norm=0.977  lr=1.09e-04  dt=  45.4ms  words=64,528,384
[E06   138/1548 G   7877|CLM] train=2.4030  mask=13.6%  norm=0.710  lr=1.09e-04  dt=  37.2ms  words=64,536,576
[E06   139/1548 G   7878|CLM] train=4.4701  mask=13.6%  norm=0.877  lr=1.09e-04  dt=  45.3ms  words=64,544,768
[E06   140/1548 G   7879|CLM] train=1.8881  mask=13.6%  norm=0.885  lr=1.09e-04  dt=  46.1ms  words=64,552,960
[E06   141/1548 G   7880|CLM] train=2.2995  mask=13.6%  norm=0.707  lr=1.09e-04  dt=  38.4ms  words=64,561,152
[E06   142/1548 G   7881|CLM] train=3.5342  mask=13.6%  norm=0.966  lr=1.09e-04  dt=  36.5ms  words=64,569,344
[E06   143/1548 G   7882|CLM] train=4.5498  mask=13.6%  norm=0.849  lr=1.09e-04  dt=  36.5ms  words=64,577,536
[E06   144/1548 G   7883|CLM] train=2.2776  mask=13.6%  norm=0.754  lr=1.09e-04  dt=  37.1ms  words=64,585,728
[E06   145/1548 G   7884|CLM] train=3.3263  mask=13.6%  norm=0.767  lr=1.09e-04  dt=  36.7ms  words=64,593,920
[E06   146/1548 G   7885|CLM] train=5.0457  mask=13.6%  norm=0.909  lr=1.09e-04  dt=  36.7ms  words=64,602,112
[E06   147/1548 G   7886|CLM] train=3.9896  mask=13.6%  norm=0.701  lr=1.09e-04  dt=  41.0ms  words=64,610,304
[E06   148/1548 G   7887|CLM] train=4.6121  mask=13.6%  norm=0.984  lr=1.08e-04  dt=  43.1ms  words=64,618,496
[E06   149/1548 G   7888|CLM] train=3.2721  mask=13.6%  norm=0.670  lr=1.08e-04  dt=  40.0ms  words=64,626,688
[E06   150/1548 G   7889|CLM] train=4.2888  mask=13.6%  norm=0.807  lr=1.08e-04  dt=  38.1ms  words=64,634,880
[E06   151/1548 G   7890|CLM] train=3.8063  mask=13.6%  norm=0.834  lr=1.08e-04  dt=  40.0ms  words=64,643,072
[E06   152/1548 G   7891|CLM] train=4.1803  mask=13.6%  norm=0.901  lr=1.08e-04  dt=  44.1ms  words=64,651,264
[E06   153/1548 G   7892|CLM] train=1.9647  mask=13.6%  norm=0.771  lr=1.08e-04  dt=  37.1ms  words=64,659,456
[E06   154/1548 G   7893|CLM] train=4.2575  mask=13.6%  norm=0.846  lr=1.08e-04  dt=  38.3ms  words=64,667,648
[E06   155/1548 G   7894|CLM] train=3.4799  mask=13.6%  norm=0.865  lr=1.08e-04  dt=  43.1ms  words=64,675,840
[E06   156/1548 G   7895|CLM] train=1.5911  mask=13.6%  norm=0.706  lr=1.08e-04  dt=  41.7ms  words=64,684,032
[E06   157/1548 G   7896|CLM] train=4.4952  mask=13.6%  norm=0.950  lr=1.08e-04  dt=  37.5ms  words=64,692,224
[E06   158/1548 G   7897|CLM] train=4.5518  mask=13.6%  norm=0.976  lr=1.08e-04  dt=  39.5ms  words=64,700,416
[E06   159/1548 G   7898|CLM] train=3.9925  mask=13.6%  norm=0.776  lr=1.08e-04  dt=  43.4ms  words=64,708,608
[E06   160/1548 G   7899|CLM] train=3.4155  mask=13.6%  norm=0.794  lr=1.08e-04  dt=  41.4ms  words=64,716,800
[E06   161/1548 G   7900|CLM] train=2.3511  mask=13.6%  norm=0.680  lr=1.08e-04  dt=  38.2ms  words=64,724,992
[E06   162/1548 G   7901|CLM] train=2.0259  mask=13.6%  norm=0.683  lr=1.08e-04  dt=  47.3ms  words=64,733,184
[E06   163/1548 G   7902|CLM] train=1.9468  mask=13.6%  norm=0.584  lr=1.08e-04  dt=  39.1ms  words=64,741,376
[E06   164/1548 G   7903|CLM] train=4.5378  mask=13.6%  norm=0.947  lr=1.08e-04  dt=  46.8ms  words=64,749,568
[E06   165/1548 G   7904|CLM] train=3.8343  mask=13.6%  norm=0.845  lr=1.08e-04  dt=  39.9ms  words=64,757,760
[E06   166/1548 G   7905|CLM] train=4.1103  mask=13.6%  norm=0.785  lr=1.08e-04  dt=  37.6ms  words=64,765,952
[E06   167/1548 G   7906|CLM] train=4.9717  mask=13.6%  norm=1.578  lr=1.08e-04  dt=  37.3ms  words=64,774,144
[E06   168/1548 G   7907|CLM] train=4.6200  mask=13.6%  norm=2.267  lr=1.08e-04  dt=  37.7ms  words=64,782,336
[E06   169/1548 G   7908|CLM] train=3.8630  mask=13.6%  norm=0.837  lr=1.08e-04  dt=  37.0ms  words=64,790,528
[E06   170/1548 G   7909|CLM] train=4.6262  mask=13.6%  norm=0.921  lr=1.08e-04  dt=  37.0ms  words=64,798,720
[E06   171/1548 G   7910|CLM] train=1.9935  mask=13.6%  norm=0.767  lr=1.08e-04  dt=  37.6ms  words=64,806,912
[E06   172/1548 G   7911|CLM] train=2.1525  mask=13.6%  norm=0.673  lr=1.08e-04  dt=  37.1ms  words=64,815,104
[E06   173/1548 G   7912|CLM] train=4.0640  mask=13.6%  norm=0.899  lr=1.08e-04  dt=  37.1ms  words=64,823,296
[E06   174/1548 G   7913|CLM] train=2.6513  mask=13.6%  norm=0.773  lr=1.08e-04  dt=  37.4ms  words=64,831,488
[E06   175/1548 G   7914|CLM] train=2.0723  mask=13.6%  norm=0.899  lr=1.07e-04  dt=  36.9ms  words=64,839,680
[E06   176/1548 G   7915|CLM] train=3.8172  mask=13.6%  norm=0.761  lr=1.07e-04  dt=  37.4ms  words=64,847,872
[E06   177/1548 G   7916|CLM] train=4.0343  mask=13.6%  norm=0.795  lr=1.07e-04  dt=  36.9ms  words=64,856,064
[E06   178/1548 G   7917|CLM] train=4.5891  mask=13.6%  norm=1.404  lr=1.07e-04  dt=  36.9ms  words=64,864,256
[E06   179/1548 G   7918|CLM] train=3.4465  mask=13.6%  norm=0.725  lr=1.07e-04  dt=  36.9ms  words=64,872,448
[E06   180/1548 G   7919|CLM] train=3.9469  mask=13.6%  norm=0.850  lr=1.07e-04  dt=  36.9ms  words=64,880,640
[E06   181/1548 G   7920|CLM] train=4.4039  mask=13.6%  norm=0.891  lr=1.07e-04  dt=  37.1ms  words=64,888,832
[E06   182/1548 G   7921|CLM] train=4.3126  mask=13.6%  norm=2.084  lr=1.07e-04  dt=  37.0ms  words=64,897,024
[E06   183/1548 G   7922|CLM] train=4.1261  mask=13.6%  norm=1.046  lr=1.07e-04  dt=  36.9ms  words=64,905,216
[E06   184/1548 G   7923|CLM] train=4.6653  mask=13.6%  norm=1.391  lr=1.07e-04  dt=  37.0ms  words=64,913,408
[E06   185/1548 G   7924|CLM] train=3.5062  mask=13.6%  norm=0.714  lr=1.07e-04  dt=  36.8ms  words=64,921,600
[E06   186/1548 G   7925|CLM] train=3.5482  mask=13.6%  norm=0.753  lr=1.07e-04  dt=  36.8ms  words=64,929,792
[E06   187/1548 G   7926|CLM] train=2.3705  mask=13.6%  norm=0.718  lr=1.07e-04  dt=  36.9ms  words=64,937,984
[E06   188/1548 G   7927|CLM] train=3.4823  mask=13.6%  norm=0.742  lr=1.07e-04  dt=  37.1ms  words=64,946,176
[E06   189/1548 G   7928|CLM] train=2.4188  mask=13.6%  norm=0.870  lr=1.07e-04  dt=  36.8ms  words=64,954,368
[E06   190/1548 G   7929|CLM] train=4.6286  mask=13.6%  norm=0.900  lr=1.07e-04  dt=  36.8ms  words=64,962,560
[E06   191/1548 G   7930|CLM] train=1.4379  mask=13.6%  norm=0.631  lr=1.07e-04  dt=  36.9ms  words=64,970,752
[E06   192/1548 G   7931|CLM] train=3.5501  mask=13.6%  norm=0.847  lr=1.07e-04  dt=  36.9ms  words=64,978,944
[E06   193/1548 G   7932|CLM] train=2.2708  mask=13.6%  norm=0.750  lr=1.07e-04  dt=  36.8ms  words=64,987,136
[E06   194/1548 G   7933|CLM] train=2.1068  mask=13.6%  norm=0.809  lr=1.07e-04  dt=  36.8ms  words=64,995,328
[E06   195/1548 G   7934|CLM] train=3.8228  mask=13.6%  norm=0.876  lr=1.07e-04  dt=  36.9ms  words=65,003,520
[E06   196/1548 G   7935|CLM] train=2.2160  mask=13.6%  norm=1.082  lr=1.07e-04  dt=  37.0ms  words=65,011,712
[E06   197/1548 G   7936|CLM] train=3.6476  mask=13.6%  norm=0.716  lr=1.07e-04  dt=  37.0ms  words=65,019,904
[E06   198/1548 G   7937|CLM] train=4.2342  mask=13.6%  norm=0.905  lr=1.07e-04  dt=  36.9ms  words=65,028,096
[E06   199/1548 G   7938|CLM] train=3.8415  mask=13.6%  norm=0.880  lr=1.07e-04  dt=  36.8ms  words=65,036,288
[E06   200/1548 G   7939|CLM] train=4.0936  mask=13.6%  norm=0.840  lr=1.07e-04  dt=  37.1ms  words=65,044,480
[E06   201/1548 G   7940|CLM] train=4.1829  mask=13.6%  norm=0.980  lr=1.07e-04  dt=  36.9ms  words=65,052,672
[E06   202/1548 G   7941|CLM] train=4.0940  mask=13.6%  norm=0.864  lr=1.07e-04  dt=  36.9ms  words=65,060,864
[E06   203/1548 G   7942|CLM] train=3.4188  mask=13.6%  norm=0.728  lr=1.06e-04  dt=  36.9ms  words=65,069,056
[E06   204/1548 G   7943|CLM] train=2.1285  mask=13.6%  norm=0.834  lr=1.06e-04  dt=  37.1ms  words=65,077,248
[E06   205/1548 G   7944|CLM] train=2.4353  mask=13.6%  norm=0.720  lr=1.06e-04  dt=  36.9ms  words=65,085,440
[E06   206/1548 G   7945|CLM] train=3.3901  mask=13.6%  norm=0.718  lr=1.06e-04  dt=  36.8ms  words=65,093,632
[E06   207/1548 G   7946|CLM] train=3.9761  mask=13.6%  norm=0.819  lr=1.06e-04  dt=  36.9ms  words=65,101,824
[E06   208/1548 G   7947|CLM] train=4.4899  mask=13.6%  norm=0.916  lr=1.06e-04  dt=  37.1ms  words=65,110,016
[E06   209/1548 G   7948|CLM] train=4.1580  mask=13.6%  norm=0.966  lr=1.06e-04  dt=  37.0ms  words=65,118,208
[E06   210/1548 G   7949|CLM] train=3.7627  mask=13.6%  norm=0.679  lr=1.06e-04  dt=  36.8ms  words=65,126,400
[E06   211/1548 G   7950|CLM] train=2.1683  mask=13.6%  norm=1.086  lr=1.06e-04  dt=  36.9ms  words=65,134,592
[E06   212/1548 G   7951|CLM] train=2.6375  mask=13.6%  norm=0.719  lr=1.06e-04  dt=  37.0ms  words=65,142,784
[E06   213/1548 G   7952|CLM] train=2.4787  mask=13.6%  norm=0.642  lr=1.06e-04  dt=  36.8ms  words=65,150,976
[E06   214/1548 G   7953|CLM] train=1.9893  mask=13.6%  norm=0.735  lr=1.06e-04  dt=  36.8ms  words=65,159,168
[E06   215/1548 G   7954|CLM] train=2.2145  mask=13.6%  norm=0.700  lr=1.06e-04  dt=  36.9ms  words=65,167,360
[E06   216/1548 G   7955|CLM] train=3.5964  mask=13.6%  norm=0.880  lr=1.06e-04  dt=  37.0ms  words=65,175,552
[E06   217/1548 G   7956|CLM] train=2.2091  mask=13.6%  norm=0.767  lr=1.06e-04  dt=  36.9ms  words=65,183,744
[E06   218/1548 G   7957|CLM] train=2.2293  mask=13.6%  norm=0.704  lr=1.06e-04  dt=  37.0ms  words=65,191,936
[E06   219/1548 G   7958|CLM] train=1.7866  mask=13.6%  norm=0.749  lr=1.06e-04  dt=  36.9ms  words=65,200,128
[E06   220/1548 G   7959|CLM] train=3.8898  mask=13.6%  norm=0.872  lr=1.06e-04  dt=  37.0ms  words=65,208,320
[E06   221/1548 G   7960|CLM] train=2.5765  mask=13.6%  norm=0.643  lr=1.06e-04  dt=  36.9ms  words=65,216,512
[E06   222/1548 G   7961|CLM] train=2.1457  mask=13.6%  norm=0.798  lr=1.06e-04  dt=  37.1ms  words=65,224,704
[E06   223/1548 G   7962|CLM] train=2.4921  mask=13.6%  norm=0.707  lr=1.06e-04  dt=  37.0ms  words=65,232,896
[E06   224/1548 G   7963|CLM] train=3.8829  mask=13.6%  norm=0.869  lr=1.06e-04  dt=  36.8ms  words=65,241,088
[E06   225/1548 G   7964|CLM] train=3.6907  mask=13.6%  norm=0.733  lr=1.06e-04  dt=  36.8ms  words=65,249,280
[E06   226/1548 G   7965|CLM] train=3.9858  mask=13.6%  norm=1.110  lr=1.06e-04  dt=  36.8ms  words=65,257,472
[E06   227/1548 G   7966|CLM] train=4.3740  mask=13.6%  norm=1.020  lr=1.06e-04  dt=  36.9ms  words=65,265,664
[E06   228/1548 G   7967|CLM] train=2.5442  mask=13.6%  norm=0.818  lr=1.06e-04  dt=  37.0ms  words=65,273,856
[E06   229/1548 G   7968|CLM] train=3.9505  mask=13.6%  norm=0.876  lr=1.06e-04  dt=  37.2ms  words=65,282,048
[E06   230/1548 G   7969|CLM] train=4.5135  mask=13.6%  norm=0.961  lr=1.06e-04  dt=  37.0ms  words=65,290,240
[E06   231/1548 G   7970|CLM] train=4.0125  mask=13.6%  norm=0.945  lr=1.05e-04  dt=  36.8ms  words=65,298,432
[E06   232/1548 G   7971|CLM] train=2.5049  mask=13.6%  norm=0.822  lr=1.05e-04  dt=  36.9ms  words=65,306,624
[E06   233/1548 G   7972|CLM] train=2.8308  mask=13.6%  norm=0.720  lr=1.05e-04  dt=  36.8ms  words=65,314,816
[E06   234/1548 G   7973|CLM] train=4.4190  mask=13.6%  norm=0.957  lr=1.05e-04  dt=  36.9ms  words=65,323,008
[E06   235/1548 G   7974|CLM] train=3.3342  mask=13.6%  norm=0.790  lr=1.05e-04  dt=  36.7ms  words=65,331,200
[E06   236/1548 G   7975|CLM] train=3.9103  mask=13.6%  norm=0.780  lr=1.05e-04  dt=  37.3ms  words=65,339,392
[E06   237/1548 G   7976|CLM] train=1.8418  mask=13.6%  norm=0.765  lr=1.05e-04  dt=  36.6ms  words=65,347,584
[E06   238/1548 G   7977|CLM] train=2.1651  mask=13.6%  norm=0.930  lr=1.05e-04  dt=  36.8ms  words=65,355,776
[E06   239/1548 G   7978|CLM] train=1.9102  mask=13.6%  norm=0.843  lr=1.05e-04  dt=  37.0ms  words=65,363,968
[E06   240/1548 G   7979|CLM] train=2.6401  mask=13.6%  norm=1.128  lr=1.05e-04  dt=  37.0ms  words=65,372,160
[E06   241/1548 G   7980|CLM] train=4.9317  mask=13.6%  norm=1.191  lr=1.05e-04  dt=  37.0ms  words=65,380,352
[E06   242/1548 G   7981|CLM] train=2.4332  mask=13.6%  norm=0.926  lr=1.05e-04  dt=  36.9ms  words=65,388,544
[E06   243/1548 G   7982|CLM] train=3.9931  mask=13.6%  norm=0.762  lr=1.05e-04  dt=  36.8ms  words=65,396,736
[E06   244/1548 G   7983|CLM] train=2.2277  mask=13.6%  norm=0.855  lr=1.05e-04  dt=  37.0ms  words=65,404,928
[E06   245/1548 G   7984|CLM] train=4.1374  mask=13.6%  norm=0.927  lr=1.05e-04  dt=  36.8ms  words=65,413,120
[E06   246/1548 G   7985|CLM] train=4.3747  mask=13.6%  norm=0.903  lr=1.05e-04  dt=  37.0ms  words=65,421,312
[E06   247/1548 G   7986|CLM] train=4.6858  mask=13.6%  norm=0.983  lr=1.05e-04  dt=  37.0ms  words=65,429,504
[E06   248/1548 G   7987|CLM] train=2.3827  mask=13.6%  norm=1.188  lr=1.05e-04  dt=  36.9ms  words=65,437,696
[E06   249/1548 G   7988|CLM] train=3.9534  mask=13.5%  norm=0.763  lr=1.05e-04  dt=  37.2ms  words=65,445,888
[E06   250/1548 G   7989|CLM] train=2.1930  mask=13.5%  norm=0.951  lr=1.05e-04  dt=  36.8ms  words=65,454,080
[E06   251/1548 G   7990|CLM] train=2.3460  mask=13.5%  norm=0.805  lr=1.05e-04  dt=  36.9ms  words=65,462,272
[E06   252/1548 G   7991|CLM] train=4.1924  mask=13.5%  norm=1.227  lr=1.05e-04  dt=  37.0ms  words=65,470,464
[E06   253/1548 G   7992|CLM] train=4.2815  mask=13.5%  norm=0.849  lr=1.05e-04  dt=  36.8ms  words=65,478,656
[E06   254/1548 G   7993|CLM] train=2.0709  mask=13.5%  norm=0.645  lr=1.05e-04  dt=  37.0ms  words=65,486,848
[E06   255/1548 G   7994|CLM] train=2.2956  mask=13.5%  norm=0.644  lr=1.05e-04  dt=  36.9ms  words=65,495,040
[E06   256/1548 G   7995|CLM] train=2.5399  mask=13.5%  norm=0.854  lr=1.05e-04  dt=  37.2ms  words=65,503,232
[E06   257/1548 G   7996|CLM] train=2.1517  mask=13.5%  norm=0.617  lr=1.05e-04  dt=  36.7ms  words=65,511,424
[E06   258/1548 G   7997|CLM] train=4.2272  mask=13.5%  norm=0.887  lr=1.05e-04  dt=  37.3ms  words=65,519,616
[E06   259/1548 G   7998|CLM] train=2.7281  mask=13.5%  norm=0.824  lr=1.04e-04  dt=  36.8ms  words=65,527,808
[E06   260/1548 G   7999|CLM] train=4.1547  mask=13.5%  norm=0.871  lr=1.04e-04  dt=  36.8ms  words=65,536,000
[E06   261/1548 G   8000|CLM] train=3.9979  mask=13.5%  norm=1.099  lr=1.04e-04  dt=  36.8ms  words=65,544,192
[E06   262/1548 G   8001|CLM] train=2.4279  mask=13.5%  norm=0.845  lr=1.04e-04  dt=  36.8ms  words=65,552,384
[E06   263/1548 G   8002|CLM] train=4.1411  mask=13.5%  norm=0.927  lr=1.04e-04  dt=  37.0ms  words=65,560,576
[E06   264/1548 G   8003|CLM] train=3.9286  mask=13.5%  norm=0.967  lr=1.04e-04  dt=  36.9ms  words=65,568,768
[E06   265/1548 G   8004|CLM] train=2.3142  mask=13.5%  norm=0.760  lr=1.04e-04  dt=  36.8ms  words=65,576,960
[E06   266/1548 G   8005|CLM] train=3.9078  mask=13.5%  norm=0.903  lr=1.04e-04  dt=  36.9ms  words=65,585,152
[E06   267/1548 G   8006|CLM] train=2.6540  mask=13.5%  norm=0.715  lr=1.04e-04  dt=  36.9ms  words=65,593,344
[E06   268/1548 G   8007|CLM] train=4.1499  mask=13.5%  norm=0.916  lr=1.04e-04  dt=  37.0ms  words=65,601,536
[E06   269/1548 G   8008|CLM] train=4.7075  mask=13.5%  norm=1.032  lr=1.04e-04  dt=  36.9ms  words=65,609,728
[E06   270/1548 G   8009|CLM] train=3.0215  mask=13.5%  norm=0.887  lr=1.04e-04  dt=  36.7ms  words=65,617,920
[E06   271/1548 G   8010|CLM] train=4.1056  mask=13.5%  norm=0.971  lr=1.04e-04  dt=  36.9ms  words=65,626,112
[E06   272/1548 G   8011|CLM] train=2.2668  mask=13.5%  norm=0.789  lr=1.04e-04  dt=  36.9ms  words=65,634,304
[E06   273/1548 G   8012|CLM] train=2.2399  mask=13.5%  norm=0.705  lr=1.04e-04  dt=  36.9ms  words=65,642,496
[E06   274/1548 G   8013|CLM] train=3.8220  mask=13.5%  norm=0.778  lr=1.04e-04  dt=  36.7ms  words=65,650,688
[E06   275/1548 G   8014|CLM] train=2.1846  mask=13.5%  norm=1.112  lr=1.04e-04  dt=  36.8ms  words=65,658,880
[E06   276/1548 G   8015|CLM] train=4.1562  mask=13.5%  norm=1.061  lr=1.04e-04  dt=  36.7ms  words=65,667,072
[E06   277/1548 G   8016|CLM] train=2.5787  mask=13.5%  norm=0.651  lr=1.04e-04  dt=  37.0ms  words=65,675,264
[E06   278/1548 G   8017|CLM] train=4.0938  mask=13.5%  norm=0.912  lr=1.04e-04  dt=  36.7ms  words=65,683,456
[E06   279/1548 G   8018|CLM] train=3.6625  mask=13.5%  norm=0.737  lr=1.04e-04  dt=  36.7ms  words=65,691,648
[E06   280/1548 G   8019|CLM] train=2.1799  mask=13.5%  norm=0.767  lr=1.04e-04  dt=  36.9ms  words=65,699,840
[E06   281/1548 G   8020|CLM] train=4.4835  mask=13.5%  norm=0.904  lr=1.04e-04  dt=  36.9ms  words=65,708,032
[E06   282/1548 G   8021|CLM] train=2.0430  mask=13.5%  norm=0.669  lr=1.04e-04  dt=  36.7ms  words=65,716,224
[E06   283/1548 G   8022|CLM] train=2.1941  mask=13.5%  norm=0.776  lr=1.04e-04  dt=  36.8ms  words=65,724,416
[E06   284/1548 G   8023|CLM] train=4.3913  mask=13.5%  norm=0.955  lr=1.04e-04  dt=  36.8ms  words=65,732,608
[E06   285/1548 G   8024|CLM] train=2.4763  mask=13.5%  norm=0.777  lr=1.04e-04  dt=  36.8ms  words=65,740,800
[E06   286/1548 G   8025|CLM] train=2.2713  mask=13.5%  norm=0.737  lr=1.04e-04  dt=  36.8ms  words=65,748,992
[E06   287/1548 G   8026|CLM] train=2.4422  mask=13.5%  norm=0.889  lr=1.03e-04  dt=  36.7ms  words=65,757,184
[E06   288/1548 G   8027|CLM] train=3.7007  mask=13.5%  norm=0.938  lr=1.03e-04  dt=  36.7ms  words=65,765,376
[E06   289/1548 G   8028|CLM] train=2.7514  mask=13.5%  norm=0.795  lr=1.03e-04  dt=  36.8ms  words=65,773,568
[E06   290/1548 G   8029|CLM] train=3.7438  mask=13.5%  norm=0.810  lr=1.03e-04  dt=  37.0ms  words=65,781,760
[E06   291/1548 G   8030|CLM] train=3.7260  mask=13.5%  norm=0.877  lr=1.03e-04  dt=  36.8ms  words=65,789,952
[E06   292/1548 G   8031|CLM] train=2.2059  mask=13.5%  norm=0.793  lr=1.03e-04  dt=  36.8ms  words=65,798,144
[E06   293/1548 G   8032|CLM] train=2.3975  mask=13.5%  norm=0.752  lr=1.03e-04  dt=  36.9ms  words=65,806,336
[E06   294/1548 G   8033|CLM] train=4.1263  mask=13.5%  norm=0.916  lr=1.03e-04  dt=  37.1ms  words=65,814,528
[E06   295/1548 G   8034|CLM] train=2.1165  mask=13.5%  norm=0.796  lr=1.03e-04  dt=  37.0ms  words=65,822,720
[E06   296/1548 G   8035|CLM] train=2.1437  mask=13.5%  norm=0.752  lr=1.03e-04  dt=  36.9ms  words=65,830,912
[E06   297/1548 G   8036|CLM] train=4.0080  mask=13.5%  norm=1.206  lr=1.03e-04  dt=  36.9ms  words=65,839,104
[E06   298/1548 G   8037|CLM] train=4.3232  mask=13.5%  norm=0.833  lr=1.03e-04  dt=  36.7ms  words=65,847,296
[E06   299/1548 G   8038|CLM] train=4.1501  mask=13.5%  norm=0.825  lr=1.03e-04  dt=  36.9ms  words=65,855,488
[E06   300/1548 G   8039|CLM] train=4.3215  mask=13.5%  norm=0.991  lr=1.03e-04  dt=  36.7ms  words=65,863,680
[E06   301/1548 G   8040|CLM] train=4.0077  mask=13.5%  norm=0.963  lr=1.03e-04  dt=  36.7ms  words=65,871,872
[E06   302/1548 G   8041|CLM] train=1.9781  mask=13.5%  norm=0.753  lr=1.03e-04  dt=  36.8ms  words=65,880,064
[E06   303/1548 G   8042|CLM] train=2.2902  mask=13.5%  norm=0.730  lr=1.03e-04  dt=  36.9ms  words=65,888,256
[E06   304/1548 G   8043|CLM] train=3.7212  mask=13.5%  norm=0.901  lr=1.03e-04  dt=  36.8ms  words=65,896,448
[E06   305/1548 G   8044|CLM] train=2.2596  mask=13.5%  norm=0.785  lr=1.03e-04  dt=  36.7ms  words=65,904,640
[E06   306/1548 G   8045|CLM] train=2.8439  mask=13.5%  norm=1.217  lr=1.03e-04  dt=  36.8ms  words=65,912,832
[E06   307/1548 G   8046|CLM] train=2.5480  mask=13.5%  norm=0.713  lr=1.03e-04  dt=  36.8ms  words=65,921,024
[E06   308/1548 G   8047|CLM] train=2.3825  mask=13.5%  norm=0.751  lr=1.03e-04  dt=  36.8ms  words=65,929,216
[E06   309/1548 G   8048|CLM] train=4.3653  mask=13.5%  norm=0.933  lr=1.03e-04  dt=  36.8ms  words=65,937,408
[E06   310/1548 G   8049|CLM] train=3.8390  mask=13.5%  norm=0.870  lr=1.03e-04  dt=  37.1ms  words=65,945,600
[E06   311/1548 G   8050|CLM] train=4.3641  mask=13.5%  norm=0.908  lr=1.03e-04  dt=  36.7ms  words=65,953,792
[E06   312/1548 G   8051|CLM] train=4.2991  mask=13.5%  norm=0.959  lr=1.03e-04  dt=  36.8ms  words=65,961,984
[E06   313/1548 G   8052|CLM] train=3.9133  mask=13.5%  norm=0.683  lr=1.03e-04  dt=  36.7ms  words=65,970,176
[E06   314/1548 G   8053|CLM] train=2.0119  mask=13.5%  norm=0.718  lr=1.03e-04  dt=  37.1ms  words=65,978,368
[E06   315/1548 G   8054|CLM] train=5.5055  mask=13.5%  norm=1.267  lr=1.02e-04  dt=  37.2ms  words=65,986,560
[E06   316/1548 G   8055|CLM] train=2.0214  mask=13.5%  norm=0.832  lr=1.02e-04  dt=  37.5ms  words=65,994,752
[E06   317/1548 G   8056|CLM] train=2.1857  mask=13.5%  norm=0.672  lr=1.02e-04  dt=  37.0ms  words=66,002,944
[E06   318/1548 G   8057|CLM] train=2.3594  mask=13.5%  norm=0.705  lr=1.02e-04  dt=  37.0ms  words=66,011,136
[E06   319/1548 G   8058|CLM] train=3.9655  mask=13.5%  norm=1.031  lr=1.02e-04  dt=  37.0ms  words=66,019,328
[E06   320/1548 G   8059|CLM] train=2.1212  mask=13.5%  norm=0.628  lr=1.02e-04  dt=  37.0ms  words=66,027,520
[E06   321/1548 G   8060|CLM] train=2.1093  mask=13.5%  norm=0.644  lr=1.02e-04  dt=  37.0ms  words=66,035,712
[E06   322/1548 G   8061|CLM] train=5.3832  mask=13.5%  norm=1.206  lr=1.02e-04  dt=  36.9ms  words=66,043,904
[E06   323/1548 G   8062|CLM] train=4.5509  mask=13.5%  norm=1.352  lr=1.02e-04  dt=  37.0ms  words=66,052,096
[E06   324/1548 G   8063|CLM] train=2.1748  mask=13.5%  norm=0.857  lr=1.02e-04  dt=  36.9ms  words=66,060,288
[E06   325/1548 G   8064|CLM] train=4.3252  mask=13.5%  norm=0.864  lr=1.02e-04  dt=  36.8ms  words=66,068,480
[E06   326/1548 G   8065|CLM] train=4.3309  mask=13.5%  norm=0.867  lr=1.02e-04  dt=  36.8ms  words=66,076,672
[E06   327/1548 G   8066|CLM] train=2.2972  mask=13.5%  norm=0.644  lr=1.02e-04  dt=  37.0ms  words=66,084,864
[E06   328/1548 G   8067|CLM] train=2.5594  mask=13.5%  norm=0.782  lr=1.02e-04  dt=  36.9ms  words=66,093,056
[E06   329/1548 G   8068|CLM] train=4.2265  mask=13.5%  norm=0.834  lr=1.02e-04  dt=  36.7ms  words=66,101,248
[E06   330/1548 G   8069|CLM] train=2.0614  mask=13.5%  norm=0.929  lr=1.02e-04  dt=  36.8ms  words=66,109,440
[E06   331/1548 G   8070|CLM] train=4.1449  mask=13.5%  norm=1.038  lr=1.02e-04  dt=  37.2ms  words=66,117,632
[E06   332/1548 G   8071|CLM] train=2.2917  mask=13.5%  norm=0.707  lr=1.02e-04  dt=  36.9ms  words=66,125,824
[E06   333/1548 G   8072|CLM] train=4.0733  mask=13.5%  norm=0.939  lr=1.02e-04  dt=  36.8ms  words=66,134,016
[E06   334/1548 G   8073|CLM] train=2.6472  mask=13.5%  norm=0.932  lr=1.02e-04  dt=  36.8ms  words=66,142,208
[E06   335/1548 G   8074|CLM] train=4.2870  mask=13.5%  norm=0.858  lr=1.02e-04  dt=  37.0ms  words=66,150,400
[E06   336/1548 G   8075|CLM] train=5.0666  mask=13.5%  norm=1.170  lr=1.02e-04  dt=  36.8ms  words=66,158,592
[E06   337/1548 G   8076|CLM] train=2.1931  mask=13.5%  norm=0.635  lr=1.02e-04  dt=  36.8ms  words=66,166,784
[E06   338/1548 G   8077|CLM] train=3.8313  mask=13.5%  norm=0.873  lr=1.02e-04  dt=  37.0ms  words=66,174,976
[E06   339/1548 G   8078|CLM] train=2.0491  mask=13.5%  norm=0.783  lr=1.02e-04  dt=  36.9ms  words=66,183,168
[E06   340/1548 G   8079|CLM] train=2.4773  mask=13.5%  norm=0.838  lr=1.02e-04  dt=  36.9ms  words=66,191,360
[E06   341/1548 G   8080|CLM] train=2.2363  mask=13.5%  norm=0.640  lr=1.02e-04  dt=  36.7ms  words=66,199,552
[E06   342/1548 G   8081|CLM] train=4.7163  mask=13.5%  norm=0.968  lr=1.02e-04  dt=  36.9ms  words=66,207,744
[E06   343/1548 G   8082|CLM] train=4.3517  mask=13.5%  norm=0.936  lr=1.01e-04  dt=  36.9ms  words=66,215,936
[E06   344/1548 G   8083|CLM] train=4.0979  mask=13.5%  norm=1.005  lr=1.01e-04  dt=  36.9ms  words=66,224,128
[E06   345/1548 G   8084|CLM] train=4.8596  mask=13.5%  norm=2.647  lr=1.01e-04  dt=  36.7ms  words=66,232,320
[E06   346/1548 G   8085|CLM] train=2.6328  mask=13.5%  norm=0.777  lr=1.01e-04  dt=  36.8ms  words=66,240,512
[E06   347/1548 G   8086|CLM] train=2.2362  mask=13.5%  norm=0.717  lr=1.01e-04  dt=  36.7ms  words=66,248,704
[E06   348/1548 G   8087|CLM] train=2.0131  mask=13.5%  norm=0.705  lr=1.01e-04  dt=  36.7ms  words=66,256,896
[E06   349/1548 G   8088|CLM] train=3.5757  mask=13.5%  norm=0.899  lr=1.01e-04  dt=  36.8ms  words=66,265,088
[E06   350/1548 G   8089|CLM] train=3.6831  mask=13.5%  norm=0.922  lr=1.01e-04  dt=  36.7ms  words=66,273,280
[E06   351/1548 G   8090|CLM] train=2.3055  mask=13.5%  norm=0.778  lr=1.01e-04  dt=  36.8ms  words=66,281,472
[E06   352/1548 G   8091|CLM] train=4.3599  mask=13.5%  norm=0.931  lr=1.01e-04  dt=  36.9ms  words=66,289,664
[E06   353/1548 G   8092|CLM] train=3.6824  mask=13.5%  norm=0.825  lr=1.01e-04  dt=  37.0ms  words=66,297,856
[E06   354/1548 G   8093|CLM] train=4.1153  mask=13.5%  norm=0.927  lr=1.01e-04  dt=  36.8ms  words=66,306,048
[E06   355/1548 G   8094|CLM] train=4.3423  mask=13.5%  norm=0.852  lr=1.01e-04  dt=  36.8ms  words=66,314,240
[E06   356/1548 G   8095|CLM] train=2.3346  mask=13.5%  norm=0.781  lr=1.01e-04  dt=  36.9ms  words=66,322,432
[E06   357/1548 G   8096|CLM] train=2.1892  mask=13.5%  norm=0.666  lr=1.01e-04  dt=  37.1ms  words=66,330,624
[E06   358/1548 G   8097|CLM] train=2.4336  mask=13.5%  norm=0.703  lr=1.01e-04  dt=  36.9ms  words=66,338,816
[E06   359/1548 G   8098|CLM] train=4.8221  mask=13.5%  norm=0.959  lr=1.01e-04  dt=  36.9ms  words=66,347,008
[E06   360/1548 G   8099|CLM] train=4.0743  mask=13.5%  norm=0.919  lr=1.01e-04  dt=  36.9ms  words=66,355,200
[E06   361/1548 G   8100|CLM] train=5.0007  mask=13.5%  norm=1.036  lr=1.01e-04  dt=  36.9ms  words=66,363,392
[E06   362/1548 G   8101|CLM] train=3.5299  mask=13.5%  norm=0.812  lr=1.01e-04  dt=  36.8ms  words=66,371,584
[E06   363/1548 G   8102|CLM] train=4.4629  mask=13.5%  norm=1.100  lr=1.01e-04  dt=  36.7ms  words=66,379,776
[E06   364/1548 G   8103|CLM] train=4.9290  mask=13.5%  norm=0.871  lr=1.01e-04  dt=  36.7ms  words=66,387,968
[E06   365/1548 G   8104|CLM] train=2.1325  mask=13.5%  norm=0.651  lr=1.01e-04  dt=  36.7ms  words=66,396,160
[E06   366/1548 G   8105|CLM] train=2.4436  mask=13.5%  norm=0.804  lr=1.01e-04  dt=  36.9ms  words=66,404,352
[E06   367/1548 G   8106|CLM] train=4.1217  mask=13.5%  norm=1.036  lr=1.01e-04  dt=  36.9ms  words=66,412,544
[E06   368/1548 G   8107|CLM] train=3.7796  mask=13.5%  norm=0.938  lr=1.01e-04  dt=  36.7ms  words=66,420,736
[E06   369/1548 G   8108|CLM] train=2.1269  mask=13.5%  norm=0.703  lr=1.01e-04  dt=  36.8ms  words=66,428,928
[E06   370/1548 G   8109|CLM] train=4.7955  mask=13.5%  norm=1.143  lr=1.01e-04  dt=  37.0ms  words=66,437,120
[E06   371/1548 G   8110|CLM] train=5.1244  mask=13.5%  norm=1.110  lr=1.00e-04  dt=  37.0ms  words=66,445,312
[E06   372/1548 G   8111|CLM] train=3.1272  mask=13.5%  norm=2.383  lr=1.00e-04  dt=  36.8ms  words=66,453,504
[E06   373/1548 G   8112|CLM] train=3.1333  mask=13.4%  norm=0.770  lr=1.00e-04  dt=  36.9ms  words=66,461,696
[E06   374/1548 G   8113|CLM] train=4.2007  mask=13.4%  norm=0.873  lr=1.00e-04  dt=  36.9ms  words=66,469,888
[E06   375/1548 G   8114|CLM] train=1.9619  mask=13.4%  norm=0.767  lr=1.00e-04  dt=  36.8ms  words=66,478,080
[E06   376/1548 G   8115|CLM] train=3.9955  mask=13.4%  norm=0.835  lr=1.00e-04  dt=  36.7ms  words=66,486,272
[E06   377/1548 G   8116|CLM] train=2.2693  mask=13.4%  norm=0.661  lr=1.00e-04  dt=  36.6ms  words=66,494,464
[E06   378/1548 G   8117|CLM] train=2.5515  mask=13.4%  norm=0.717  lr=1.00e-04  dt=  36.8ms  words=66,502,656
[E06   379/1548 G   8118|CLM] train=4.4571  mask=13.4%  norm=1.125  lr=1.00e-04  dt=  37.0ms  words=66,510,848
[E06   380/1548 G   8119|CLM] train=3.9427  mask=13.4%  norm=0.917  lr=1.00e-04  dt=  36.8ms  words=66,519,040
[E06   381/1548 G   8120|CLM] train=1.8255  mask=13.4%  norm=0.684  lr=1.00e-04  dt=  36.8ms  words=66,527,232
[E06   382/1548 G   8121|CLM] train=2.0836  mask=13.4%  norm=0.798  lr=1.00e-04  dt=  36.8ms  words=66,535,424
[E06   383/1548 G   8122|CLM] train=4.2737  mask=13.4%  norm=0.944  lr=1.00e-04  dt=  37.0ms  words=66,543,616
[E06   384/1548 G   8123|CLM] train=4.1394  mask=13.4%  norm=0.899  lr=1.00e-04  dt=  36.9ms  words=66,551,808
[E06   385/1548 G   8124|CLM] train=3.9908  mask=13.4%  norm=0.938  lr=1.00e-04  dt=  37.0ms  words=66,560,000
[E06   386/1548 G   8125|CLM] train=3.8132  mask=13.4%  norm=0.764  lr=9.99e-05  dt=  37.3ms  words=66,568,192
[E06   387/1548 G   8126|CLM] train=3.5005  mask=13.4%  norm=0.766  lr=9.99e-05  dt=  37.1ms  words=66,576,384
[E06   388/1548 G   8127|CLM] train=3.9985  mask=13.4%  norm=0.881  lr=9.99e-05  dt=  36.8ms  words=66,584,576
[E06   389/1548 G   8128|CLM] train=3.1152  mask=13.4%  norm=0.670  lr=9.98e-05  dt=  36.7ms  words=66,592,768
[E06   390/1548 G   8129|CLM] train=4.2461  mask=13.4%  norm=0.851  lr=9.98e-05  dt=  36.8ms  words=66,600,960
[E06   391/1548 G   8130|CLM] train=2.3866  mask=13.4%  norm=0.682  lr=9.98e-05  dt=  37.1ms  words=66,609,152
[E06   392/1548 G   8131|CLM] train=4.0313  mask=13.4%  norm=0.801  lr=9.97e-05  dt=  36.9ms  words=66,617,344
[E06   393/1548 G   8132|CLM] train=2.2863  mask=13.4%  norm=0.961  lr=9.97e-05  dt=  36.9ms  words=66,625,536
[E06   394/1548 G   8133|CLM] train=4.6024  mask=13.4%  norm=0.803  lr=9.97e-05  dt=  36.9ms  words=66,633,728
[E06   395/1548 G   8134|CLM] train=4.1283  mask=13.4%  norm=0.960  lr=9.96e-05  dt=  37.0ms  words=66,641,920
[E06   396/1548 G   8135|CLM] train=2.1727  mask=13.4%  norm=0.695  lr=9.96e-05  dt=  36.9ms  words=66,650,112
[E06   397/1548 G   8136|CLM] train=4.9314  mask=13.4%  norm=2.943  lr=9.96e-05  dt=  36.8ms  words=66,658,304
[E06   398/1548 G   8137|CLM] train=1.8453  mask=13.4%  norm=0.714  lr=9.95e-05  dt=  37.0ms  words=66,666,496
[E06   399/1548 G   8138|CLM] train=4.9534  mask=13.4%  norm=0.954  lr=9.95e-05  dt=  37.0ms  words=66,674,688
[E06   400/1548 G   8139|CLM] train=3.7927  mask=13.4%  norm=1.097  lr=9.95e-05  dt= 425.4ms  words=66,682,880
[E06   401/1548 G   8140|CLM] train=4.1147  mask=13.4%  norm=0.826  lr=9.94e-05  dt=  38.8ms  words=66,691,072
[E06   402/1548 G   8141|CLM] train=4.1481  mask=13.4%  norm=1.012  lr=9.94e-05  dt=  37.1ms  words=66,699,264
[E06   403/1548 G   8142|CLM] train=2.3567  mask=13.4%  norm=0.722  lr=9.93e-05  dt=  37.2ms  words=66,707,456
[E06   404/1548 G   8143|CLM] train=3.3979  mask=13.4%  norm=0.719  lr=9.93e-05  dt=  37.0ms  words=66,715,648
[E06   405/1548 G   8144|CLM] train=2.2606  mask=13.4%  norm=0.703  lr=9.93e-05  dt=  36.8ms  words=66,723,840
[E06   406/1548 G   8145|CLM] train=3.7047  mask=13.4%  norm=0.828  lr=9.92e-05  dt=  36.9ms  words=66,732,032
[E06   407/1548 G   8146|CLM] train=4.4758  mask=13.4%  norm=0.950  lr=9.92e-05  dt=  36.9ms  words=66,740,224
[E06   408/1548 G   8147|CLM] train=4.4351  mask=13.4%  norm=2.499  lr=9.92e-05  dt=  37.0ms  words=66,748,416
[E06   409/1548 G   8148|CLM] train=3.9069  mask=13.4%  norm=0.780  lr=9.91e-05  dt=  36.9ms  words=66,756,608
[E06   410/1548 G   8149|CLM] train=4.4835  mask=13.4%  norm=1.184  lr=9.91e-05  dt=  36.8ms  words=66,764,800
[E06   411/1548 G   8150|CLM] train=4.3873  mask=13.4%  norm=0.959  lr=9.91e-05  dt=  37.0ms  words=66,772,992
[E06   412/1548 G   8151|CLM] train=3.6806  mask=13.4%  norm=0.841  lr=9.90e-05  dt=  37.0ms  words=66,781,184
[E06   413/1548 G   8152|CLM] train=3.6981  mask=13.4%  norm=0.769  lr=9.90e-05  dt=  37.0ms  words=66,789,376
[E06   414/1548 G   8153|CLM] train=3.6099  mask=13.4%  norm=0.820  lr=9.90e-05  dt=  36.8ms  words=66,797,568
[E06   415/1548 G   8154|CLM] train=3.9600  mask=13.4%  norm=0.927  lr=9.89e-05  dt=  37.0ms  words=66,805,760
[E06   416/1548 G   8155|CLM] train=4.0592  mask=13.4%  norm=1.082  lr=9.89e-05  dt=  36.9ms  words=66,813,952
[E06   417/1548 G   8156|CLM] train=2.1592  mask=13.4%  norm=0.729  lr=9.89e-05  dt=  36.9ms  words=66,822,144
[E06   418/1548 G   8157|CLM] train=2.7264  mask=13.4%  norm=0.769  lr=9.88e-05  dt=  37.0ms  words=66,830,336
[E06   419/1548 G   8158|CLM] train=4.2605  mask=13.4%  norm=0.942  lr=9.88e-05  dt=  36.9ms  words=66,838,528
[E06   420/1548 G   8159|CLM] train=3.7579  mask=13.4%  norm=0.842  lr=9.87e-05  dt=  37.0ms  words=66,846,720
[E06   421/1548 G   8160|CLM] train=2.5924  mask=13.4%  norm=0.745  lr=9.87e-05  dt=  36.8ms  words=66,854,912
[E06   422/1548 G   8161|CLM] train=2.1550  mask=13.4%  norm=0.679  lr=9.87e-05  dt=  36.6ms  words=66,863,104
[E06   423/1548 G   8162|CLM] train=4.2277  mask=13.4%  norm=0.943  lr=9.86e-05  dt=  36.8ms  words=66,871,296
[E06   424/1548 G   8163|CLM] train=4.0735  mask=13.4%  norm=0.837  lr=9.86e-05  dt=  36.7ms  words=66,879,488
[E06   425/1548 G   8164|CLM] train=1.8154  mask=13.4%  norm=0.752  lr=9.86e-05  dt=  37.0ms  words=66,887,680
[E06   426/1548 G   8165|CLM] train=4.5581  mask=13.4%  norm=1.097  lr=9.85e-05  dt=  36.8ms  words=66,895,872
[E06   427/1548 G   8166|CLM] train=3.8263  mask=13.4%  norm=0.861  lr=9.85e-05  dt=  37.0ms  words=66,904,064
[E06   428/1548 G   8167|CLM] train=2.1332  mask=13.4%  norm=0.668  lr=9.85e-05  dt=  37.1ms  words=66,912,256
[E06   429/1548 G   8168|CLM] train=3.9890  mask=13.4%  norm=0.917  lr=9.84e-05  dt=  37.0ms  words=66,920,448
[E06   430/1548 G   8169|CLM] train=2.3631  mask=13.4%  norm=0.763  lr=9.84e-05  dt=  36.7ms  words=66,928,640
[E06   431/1548 G   8170|CLM] train=2.0154  mask=13.4%  norm=0.711  lr=9.84e-05  dt=  36.9ms  words=66,936,832
[E06   432/1548 G   8171|CLM] train=2.1222  mask=13.4%  norm=0.679  lr=9.83e-05  dt=  36.8ms  words=66,945,024
[E06   433/1548 G   8172|CLM] train=4.1411  mask=13.4%  norm=0.945  lr=9.83e-05  dt=  36.9ms  words=66,953,216
[E06   434/1548 G   8173|CLM] train=4.1066  mask=13.4%  norm=1.145  lr=9.83e-05  dt=  36.8ms  words=66,961,408
[E06   435/1548 G   8174|CLM] train=3.6776  mask=13.4%  norm=0.934  lr=9.82e-05  dt=  36.8ms  words=66,969,600
[E06   436/1548 G   8175|CLM] train=3.3722  mask=13.4%  norm=0.829  lr=9.82e-05  dt=  37.1ms  words=66,977,792
[E06   437/1548 G   8176|CLM] train=4.1796  mask=13.4%  norm=0.892  lr=9.82e-05  dt=  37.0ms  words=66,985,984
[E06   438/1548 G   8177|CLM] train=5.4217  mask=13.4%  norm=1.130  lr=9.81e-05  dt=  36.9ms  words=66,994,176
[E06   439/1548 G   8178|CLM] train=2.0677  mask=13.4%  norm=0.684  lr=9.81e-05  dt=  37.0ms  words=67,002,368
[E06   440/1548 G   8179|CLM] train=5.1313  mask=13.4%  norm=1.024  lr=9.80e-05  dt=  36.8ms  words=67,010,560
[E06   441/1548 G   8180|CLM] train=3.8535  mask=13.4%  norm=0.733  lr=9.80e-05  dt=  37.0ms  words=67,018,752
[E06   442/1548 G   8181|CLM] train=3.7533  mask=13.4%  norm=0.723  lr=9.80e-05  dt=  36.8ms  words=67,026,944
[E06   443/1548 G   8182|CLM] train=4.5928  mask=13.4%  norm=0.990  lr=9.79e-05  dt=  36.9ms  words=67,035,136
[E06   444/1548 G   8183|CLM] train=2.1855  mask=13.4%  norm=0.669  lr=9.79e-05  dt=  36.9ms  words=67,043,328
[E06   445/1548 G   8184|CLM] train=4.1320  mask=13.4%  norm=0.833  lr=9.79e-05  dt=  36.9ms  words=67,051,520
[E06   446/1548 G   8185|CLM] train=2.2454  mask=13.4%  norm=0.692  lr=9.78e-05  dt=  36.9ms  words=67,059,712
[E06   447/1548 G   8186|CLM] train=4.5139  mask=13.4%  norm=0.982  lr=9.78e-05  dt=  36.8ms  words=67,067,904
[E06   448/1548 G   8187|CLM] train=4.0043  mask=13.4%  norm=0.927  lr=9.78e-05  dt=  37.1ms  words=67,076,096
[E06   449/1548 G   8188|CLM] train=4.1327  mask=13.4%  norm=0.858  lr=9.77e-05  dt=  37.0ms  words=67,084,288
[E06   450/1548 G   8189|CLM] train=3.7660  mask=13.4%  norm=1.346  lr=9.77e-05  dt=  36.8ms  words=67,092,480
[E06   451/1548 G   8190|CLM] train=2.1950  mask=13.4%  norm=0.935  lr=9.77e-05  dt=  36.9ms  words=67,100,672
[E06   452/1548 G   8191|CLM] train=2.3622  mask=13.4%  norm=0.726  lr=9.76e-05  dt=  36.9ms  words=67,108,864
[E06   453/1548 G   8192|CLM] train=4.0194  mask=13.4%  norm=0.770  lr=9.76e-05  dt=  37.0ms  words=67,117,056
[E06   454/1548 G   8193|CLM] train=2.1644  mask=13.4%  norm=0.760  lr=9.76e-05  dt=  36.8ms  words=67,125,248
[E06   455/1548 G   8194|CLM] train=4.3344  mask=13.4%  norm=0.817  lr=9.75e-05  dt=  36.8ms  words=67,133,440
[E06   456/1548 G   8195|CLM] train=4.3647  mask=13.4%  norm=1.103  lr=9.75e-05  dt=  36.9ms  words=67,141,632
[E06   457/1548 G   8196|CLM] train=4.5052  mask=13.4%  norm=0.929  lr=9.74e-05  dt=  37.3ms  words=67,149,824
[E06   458/1548 G   8197|CLM] train=2.0760  mask=13.4%  norm=0.909  lr=9.74e-05  dt=  37.3ms  words=67,158,016
[E06   459/1548 G   8198|CLM] train=3.9101  mask=13.4%  norm=1.090  lr=9.74e-05  dt=  36.7ms  words=67,166,208
[E06   460/1548 G   8199|CLM] train=5.6225  mask=13.4%  norm=1.363  lr=9.73e-05  dt=  36.9ms  words=67,174,400
[E06   461/1548 G   8200|CLM] train=2.1404  mask=13.4%  norm=0.702  lr=9.73e-05  dt=  37.2ms  words=67,182,592
[E06   462/1548 G   8201|CLM] train=3.7678  mask=13.4%  norm=0.863  lr=9.73e-05  dt=  36.9ms  words=67,190,784
[E06   463/1548 G   8202|CLM] train=2.2238  mask=13.4%  norm=0.706  lr=9.72e-05  dt=  36.9ms  words=67,198,976
[E06   464/1548 G   8203|CLM] train=3.6865  mask=13.4%  norm=0.891  lr=9.72e-05  dt=  37.3ms  words=67,207,168
[E06   465/1548 G   8204|CLM] train=1.9599  mask=13.4%  norm=0.690  lr=9.72e-05  dt=  37.4ms  words=67,215,360
[E06   466/1548 G   8205|CLM] train=4.2863  mask=13.4%  norm=0.875  lr=9.71e-05  dt=  37.2ms  words=67,223,552
[E06   467/1548 G   8206|CLM] train=4.1399  mask=13.4%  norm=0.893  lr=9.71e-05  dt=  37.3ms  words=67,231,744
[E06   468/1548 G   8207|CLM] train=3.5986  mask=13.4%  norm=0.839  lr=9.71e-05  dt=  37.3ms  words=67,239,936
[E06   469/1548 G   8208|CLM] train=2.0594  mask=13.4%  norm=0.829  lr=9.70e-05  dt=  37.2ms  words=67,248,128
[E06   470/1548 G   8209|CLM] train=2.1738  mask=13.4%  norm=0.720  lr=9.70e-05  dt=  37.3ms  words=67,256,320
[E06   471/1548 G   8210|CLM] train=2.1188  mask=13.4%  norm=0.662  lr=9.70e-05  dt=  37.2ms  words=67,264,512
[E06   472/1548 G   8211|CLM] train=2.2416  mask=13.4%  norm=0.910  lr=9.69e-05  dt=  37.0ms  words=67,272,704
[E06   473/1548 G   8212|CLM] train=2.0834  mask=13.4%  norm=0.744  lr=9.69e-05  dt=  36.9ms  words=67,280,896
[E06   474/1548 G   8213|CLM] train=1.9721  mask=13.4%  norm=0.701  lr=9.69e-05  dt=  37.0ms  words=67,289,088
[E06   475/1548 G   8214|CLM] train=1.7078  mask=13.4%  norm=0.638  lr=9.68e-05  dt=  36.9ms  words=67,297,280
[E06   476/1548 G   8215|CLM] train=4.1318  mask=13.4%  norm=0.849  lr=9.68e-05  dt=  36.9ms  words=67,305,472
[E06   477/1548 G   8216|CLM] train=3.6292  mask=13.4%  norm=0.885  lr=9.67e-05  dt=  37.1ms  words=67,313,664
[E06   478/1548 G   8217|CLM] train=3.8523  mask=13.4%  norm=1.172  lr=9.67e-05  dt=  37.1ms  words=67,321,856
[E06   479/1548 G   8218|CLM] train=2.1171  mask=13.4%  norm=0.724  lr=9.67e-05  dt=  37.1ms  words=67,330,048
[E06   480/1548 G   8219|CLM] train=1.9952  mask=13.4%  norm=0.747  lr=9.66e-05  dt=  37.1ms  words=67,338,240
[E06   481/1548 G   8220|CLM] train=4.1475  mask=13.4%  norm=1.068  lr=9.66e-05  dt=  37.2ms  words=67,346,432
[E06   482/1548 G   8221|CLM] train=3.9531  mask=13.4%  norm=0.848  lr=9.66e-05  dt=  36.9ms  words=67,354,624
[E06   483/1548 G   8222|CLM] train=4.1256  mask=13.4%  norm=0.799  lr=9.65e-05  dt=  37.1ms  words=67,362,816
[E06   484/1548 G   8223|CLM] train=4.7219  mask=13.4%  norm=1.115  lr=9.65e-05  dt=  37.1ms  words=67,371,008
[E06   485/1548 G   8224|CLM] train=4.3993  mask=13.4%  norm=0.859  lr=9.65e-05  dt=  37.0ms  words=67,379,200
[E06   486/1548 G   8225|CLM] train=2.0899  mask=13.4%  norm=0.940  lr=9.64e-05  dt=  37.1ms  words=67,387,392
[E06   487/1548 G   8226|CLM] train=2.5309  mask=13.4%  norm=0.795  lr=9.64e-05  dt=  37.1ms  words=67,395,584
[E06   488/1548 G   8227|CLM] train=4.5375  mask=13.4%  norm=0.916  lr=9.64e-05  dt=  37.2ms  words=67,403,776
[E06   489/1548 G   8228|CLM] train=2.7568  mask=13.4%  norm=0.752  lr=9.63e-05  dt=  37.4ms  words=67,411,968
[E06   490/1548 G   8229|CLM] train=2.1770  mask=13.4%  norm=0.708  lr=9.63e-05  dt=  37.2ms  words=67,420,160
[E06   491/1548 G   8230|CLM] train=4.0912  mask=13.4%  norm=0.764  lr=9.63e-05  dt=  37.2ms  words=67,428,352
[E06   492/1548 G   8231|CLM] train=3.6180  mask=13.4%  norm=0.856  lr=9.62e-05  dt=  36.9ms  words=67,436,544
[E06   493/1548 G   8232|CLM] train=3.3858  mask=13.4%  norm=1.548  lr=9.62e-05  dt=  37.4ms  words=67,444,736
[E06   494/1548 G   8233|CLM] train=2.4390  mask=13.4%  norm=0.748  lr=9.62e-05  dt=  37.2ms  words=67,452,928
[E06   495/1548 G   8234|CLM] train=2.4907  mask=13.4%  norm=0.666  lr=9.61e-05  dt=  37.1ms  words=67,461,120
[E06   496/1548 G   8235|CLM] train=4.7005  mask=13.4%  norm=0.896  lr=9.61e-05  dt=  37.2ms  words=67,469,312
[E06   497/1548 G   8236|CLM] train=3.9152  mask=13.3%  norm=1.075  lr=9.60e-05  dt=  37.5ms  words=67,477,504
[E06   498/1548 G   8237|CLM] train=4.5479  mask=13.3%  norm=0.871  lr=9.60e-05  dt=  37.2ms  words=67,485,696
[E06   499/1548 G   8238|CLM] train=2.2943  mask=13.3%  norm=0.786  lr=9.60e-05  dt=  37.1ms  words=67,493,888
[E06   500/1548 G   8239|CLM] train=4.2473  mask=13.3%  norm=0.770  lr=9.59e-05  dt=  37.3ms  words=67,502,080
[E06   501/1548 G   8240|CLM] train=2.2632  mask=13.3%  norm=0.687  lr=9.59e-05  dt=  37.1ms  words=67,510,272
[E06   502/1548 G   8241|CLM] train=2.2661  mask=13.3%  norm=0.783  lr=9.59e-05  dt=  37.1ms  words=67,518,464
[E06   503/1548 G   8242|CLM] train=2.2364  mask=13.3%  norm=0.744  lr=9.58e-05  dt=  37.1ms  words=67,526,656
[E06   504/1548 G   8243|CLM] train=2.4531  mask=13.3%  norm=0.733  lr=9.58e-05  dt=  37.1ms  words=67,534,848
[E06   505/1548 G   8244|CLM] train=4.1626  mask=13.3%  norm=0.788  lr=9.58e-05  dt=  37.1ms  words=67,543,040
[E06   506/1548 G   8245|CLM] train=5.0576  mask=13.3%  norm=1.255  lr=9.57e-05  dt=  37.0ms  words=67,551,232
[E06   507/1548 G   8246|CLM] train=3.9035  mask=13.3%  norm=0.913  lr=9.57e-05  dt=  37.2ms  words=67,559,424
[E06   508/1548 G   8247|CLM] train=4.4776  mask=13.3%  norm=0.847  lr=9.57e-05  dt=  37.0ms  words=67,567,616
[E06   509/1548 G   8248|CLM] train=2.2678  mask=13.3%  norm=0.752  lr=9.56e-05  dt=  37.1ms  words=67,575,808
[E06   510/1548 G   8249|CLM] train=4.1971  mask=13.3%  norm=0.932  lr=9.56e-05  dt=  37.6ms  words=67,584,000
[E06   511/1548 G   8250|CLM] train=2.1250  mask=13.3%  norm=0.714  lr=9.56e-05  dt=  37.1ms  words=67,592,192
[E06   512/1548 G   8251|CLM] train=3.8651  mask=13.3%  norm=0.779  lr=9.55e-05  dt=  37.1ms  words=67,600,384
[E06   513/1548 G   8252|CLM] train=3.8295  mask=13.3%  norm=0.908  lr=9.55e-05  dt=  37.4ms  words=67,608,576
[E06   514/1548 G   8253|CLM] train=1.9992  mask=13.3%  norm=0.712  lr=9.55e-05  dt=  37.1ms  words=67,616,768
[E06   515/1548 G   8254|CLM] train=4.0263  mask=13.3%  norm=0.790  lr=9.54e-05  dt=  37.0ms  words=67,624,960
[E06   516/1548 G   8255|CLM] train=4.2440  mask=13.3%  norm=0.939  lr=9.54e-05  dt=  37.1ms  words=67,633,152
[E06   517/1548 G   8256|CLM] train=4.3222  mask=13.3%  norm=0.878  lr=9.54e-05  dt=  37.4ms  words=67,641,344
[E06   518/1548 G   8257|CLM] train=3.8358  mask=13.3%  norm=0.701  lr=9.53e-05  dt=  36.9ms  words=67,649,536
[E06   519/1548 G   8258|CLM] train=4.2534  mask=13.3%  norm=0.865  lr=9.53e-05  dt=  37.1ms  words=67,657,728
[E06   520/1548 G   8259|CLM] train=2.7162  mask=13.3%  norm=0.747  lr=9.52e-05  dt=  37.1ms  words=67,665,920
[E06   521/1548 G   8260|CLM] train=1.8773  mask=13.3%  norm=0.761  lr=9.52e-05  dt=  36.9ms  words=67,674,112
[E06   522/1548 G   8261|CLM] train=4.2594  mask=13.3%  norm=0.835  lr=9.52e-05  dt=  37.0ms  words=67,682,304
[E06   523/1548 G   8262|CLM] train=3.7881  mask=13.3%  norm=0.698  lr=9.51e-05  dt=  37.3ms  words=67,690,496
[E06   524/1548 G   8263|CLM] train=3.8523  mask=13.3%  norm=0.897  lr=9.51e-05  dt=  37.1ms  words=67,698,688
[E06   525/1548 G   8264|CLM] train=4.4798  mask=13.3%  norm=0.873  lr=9.51e-05  dt=  37.1ms  words=67,706,880
[E06   526/1548 G   8265|CLM] train=2.1856  mask=13.3%  norm=1.022  lr=9.50e-05  dt=  37.2ms  words=67,715,072
[E06   527/1548 G   8266|CLM] train=4.1320  mask=13.3%  norm=0.848  lr=9.50e-05  dt=  37.7ms  words=67,723,264
[E06   528/1548 G   8267|CLM] train=4.7889  mask=13.3%  norm=1.252  lr=9.50e-05  dt=  37.0ms  words=67,731,456
[E06   529/1548 G   8268|CLM] train=2.8149  mask=13.3%  norm=0.832  lr=9.49e-05  dt=  37.4ms  words=67,739,648
[E06   530/1548 G   8269|CLM] train=3.7500  mask=13.3%  norm=0.830  lr=9.49e-05  dt=  37.1ms  words=67,747,840
[E06   531/1548 G   8270|CLM] train=3.8400  mask=13.3%  norm=0.736  lr=9.49e-05  dt=  37.2ms  words=67,756,032
[E06   532/1548 G   8271|CLM] train=2.5167  mask=13.3%  norm=0.703  lr=9.48e-05  dt=  37.0ms  words=67,764,224
[E06   533/1548 G   8272|CLM] train=3.6088  mask=13.3%  norm=0.921  lr=9.48e-05  dt=  37.0ms  words=67,772,416
[E06   534/1548 G   8273|CLM] train=2.1330  mask=13.3%  norm=0.865  lr=9.48e-05  dt=  36.9ms  words=67,780,608
[E06   535/1548 G   8274|CLM] train=4.0849  mask=13.3%  norm=0.851  lr=9.47e-05  dt=  37.0ms  words=67,788,800
[E06   536/1548 G   8275|CLM] train=3.6921  mask=13.3%  norm=0.918  lr=9.47e-05  dt=  37.3ms  words=67,796,992
[E06   537/1548 G   8276|CLM] train=3.6967  mask=13.3%  norm=0.743  lr=9.47e-05  dt=  38.1ms  words=67,805,184
[E06   538/1548 G   8277|CLM] train=3.8103  mask=13.3%  norm=1.007  lr=9.46e-05  dt=  37.2ms  words=67,813,376
[E06   539/1548 G   8278|CLM] train=2.6531  mask=13.3%  norm=0.658  lr=9.46e-05  dt=  37.3ms  words=67,821,568
[E06   540/1548 G   8279|CLM] train=3.6556  mask=13.3%  norm=0.694  lr=9.46e-05  dt=  37.2ms  words=67,829,760
[E06   541/1548 G   8280|CLM] train=3.2994  mask=13.3%  norm=0.684  lr=9.45e-05  dt=  37.3ms  words=67,837,952
[E06   542/1548 G   8281|CLM] train=3.5389  mask=13.3%  norm=0.700  lr=9.45e-05  dt=  37.3ms  words=67,846,144
[E06   543/1548 G   8282|CLM] train=3.3708  mask=13.3%  norm=0.778  lr=9.45e-05  dt=  37.3ms  words=67,854,336
[E06   544/1548 G   8283|CLM] train=4.0889  mask=13.3%  norm=0.834  lr=9.44e-05  dt=  37.1ms  words=67,862,528
[E06   545/1548 G   8284|CLM] train=3.9732  mask=13.3%  norm=0.786  lr=9.44e-05  dt=  37.1ms  words=67,870,720
[E06   546/1548 G   8285|CLM] train=2.3094  mask=13.3%  norm=1.054  lr=9.43e-05  dt=  37.0ms  words=67,878,912
[E06   547/1548 G   8286|CLM] train=3.6355  mask=13.3%  norm=0.835  lr=9.43e-05  dt=  37.1ms  words=67,887,104
[E06   548/1548 G   8287|CLM] train=4.0144  mask=13.3%  norm=0.899  lr=9.43e-05  dt=  37.1ms  words=67,895,296
[E06   549/1548 G   8288|CLM] train=4.3162  mask=13.3%  norm=1.165  lr=9.42e-05  dt=  37.3ms  words=67,903,488
[E06   550/1548 G   8289|CLM] train=3.6659  mask=13.3%  norm=0.771  lr=9.42e-05  dt=  37.3ms  words=67,911,680
[E06   551/1548 G   8290|CLM] train=2.0850  mask=13.3%  norm=0.614  lr=9.42e-05  dt=  37.3ms  words=67,919,872
[E06   552/1548 G   8291|CLM] train=4.1713  mask=13.3%  norm=0.813  lr=9.41e-05  dt=  37.1ms  words=67,928,064
[E06   553/1548 G   8292|CLM] train=2.4010  mask=13.3%  norm=0.863  lr=9.41e-05  dt=  37.1ms  words=67,936,256
[E06   554/1548 G   8293|CLM] train=3.8012  mask=13.3%  norm=0.886  lr=9.41e-05  dt=  37.3ms  words=67,944,448
[E06   555/1548 G   8294|CLM] train=4.2415  mask=13.3%  norm=0.873  lr=9.40e-05  dt=  37.2ms  words=67,952,640
[E06   556/1548 G   8295|CLM] train=4.7063  mask=13.3%  norm=0.911  lr=9.40e-05  dt=  37.2ms  words=67,960,832
[E06   557/1548 G   8296|CLM] train=4.3103  mask=13.3%  norm=1.109  lr=9.40e-05  dt=  37.4ms  words=67,969,024
[E06   558/1548 G   8297|CLM] train=2.1532  mask=13.3%  norm=0.703  lr=9.39e-05  dt=  37.1ms  words=67,977,216
[E06   559/1548 G   8298|CLM] train=3.7571  mask=13.3%  norm=0.875  lr=9.39e-05  dt=  36.9ms  words=67,985,408
[E06   560/1548 G   8299|CLM] train=2.2750  mask=13.3%  norm=0.756  lr=9.39e-05  dt=  37.0ms  words=67,993,600
[E06   561/1548 G   8300|CLM] train=3.2210  mask=13.3%  norm=2.623  lr=9.38e-05  dt=  37.0ms  words=68,001,792
[E06   562/1548 G   8301|CLM] train=4.4007  mask=13.3%  norm=0.804  lr=9.38e-05  dt=  36.9ms  words=68,009,984
[E06   563/1548 G   8302|CLM] train=2.2549  mask=13.3%  norm=0.959  lr=9.38e-05  dt=  36.9ms  words=68,018,176
[E06   564/1548 G   8303|CLM] train=3.9991  mask=13.3%  norm=0.836  lr=9.37e-05  dt=  37.8ms  words=68,026,368
[E06   565/1548 G   8304|CLM] train=2.1570  mask=13.3%  norm=0.669  lr=9.37e-05  dt=  37.3ms  words=68,034,560
[E06   566/1548 G   8305|CLM] train=4.1819  mask=13.3%  norm=0.880  lr=9.37e-05  dt=  37.1ms  words=68,042,752
[E06   567/1548 G   8306|CLM] train=2.4504  mask=13.3%  norm=0.855  lr=9.36e-05  dt=  37.5ms  words=68,050,944
[E06   568/1548 G   8307|CLM] train=4.3005  mask=13.3%  norm=0.907  lr=9.36e-05  dt=  37.2ms  words=68,059,136
[E06   569/1548 G   8308|CLM] train=4.4057  mask=13.3%  norm=1.057  lr=9.36e-05  dt=  37.1ms  words=68,067,328
[E06   570/1548 G   8309|CLM] train=4.0417  mask=13.3%  norm=0.779  lr=9.35e-05  dt=  37.3ms  words=68,075,520
[E06   571/1548 G   8310|CLM] train=4.1564  mask=13.3%  norm=0.769  lr=9.35e-05  dt=  36.9ms  words=68,083,712
[E06   572/1548 G   8311|CLM] train=3.9582  mask=13.3%  norm=0.805  lr=9.34e-05  dt=  37.0ms  words=68,091,904
[E06   573/1548 G   8312|CLM] train=2.1912  mask=13.3%  norm=0.730  lr=9.34e-05  dt=  36.9ms  words=68,100,096
[E06   574/1548 G   8313|CLM] train=4.5142  mask=13.3%  norm=0.898  lr=9.34e-05  dt=  37.1ms  words=68,108,288
[E06   575/1548 G   8314|CLM] train=3.6884  mask=13.3%  norm=0.743  lr=9.33e-05  dt=  37.2ms  words=68,116,480
[E06   576/1548 G   8315|CLM] train=3.6956  mask=13.3%  norm=0.798  lr=9.33e-05  dt=  37.7ms  words=68,124,672
[E06   577/1548 G   8316|CLM] train=4.2086  mask=13.3%  norm=0.911  lr=9.33e-05  dt=  37.3ms  words=68,132,864
[E06   578/1548 G   8317|CLM] train=2.5054  mask=13.3%  norm=0.739  lr=9.32e-05  dt=  37.2ms  words=68,141,056
[E06   579/1548 G   8318|CLM] train=4.9282  mask=13.3%  norm=0.987  lr=9.32e-05  dt=  37.2ms  words=68,149,248
[E06   580/1548 G   8319|CLM] train=3.4513  mask=13.3%  norm=0.836  lr=9.32e-05  dt=  37.2ms  words=68,157,440
[E06   581/1548 G   8320|CLM] train=4.3800  mask=13.3%  norm=0.757  lr=9.31e-05  dt=  37.1ms  words=68,165,632
[E06   582/1548 G   8321|CLM] train=4.4067  mask=13.3%  norm=0.889  lr=9.31e-05  dt=  37.2ms  words=68,173,824
[E06   583/1548 G   8322|CLM] train=4.1831  mask=13.3%  norm=0.943  lr=9.31e-05  dt=  37.3ms  words=68,182,016
[E06   584/1548 G   8323|CLM] train=3.9382  mask=13.3%  norm=0.857  lr=9.30e-05  dt=  37.5ms  words=68,190,208
[E06   585/1548 G   8324|CLM] train=5.1864  mask=13.3%  norm=1.472  lr=9.30e-05  dt=  37.1ms  words=68,198,400
[E06   586/1548 G   8325|CLM] train=2.0885  mask=13.3%  norm=0.763  lr=9.30e-05  dt=  37.2ms  words=68,206,592
[E06   587/1548 G   8326|CLM] train=3.9648  mask=13.3%  norm=0.816  lr=9.29e-05  dt=  37.2ms  words=68,214,784
[E06   588/1548 G   8327|CLM] train=4.3108  mask=13.3%  norm=0.843  lr=9.29e-05  dt=  37.2ms  words=68,222,976
[E06   589/1548 G   8328|CLM] train=2.5837  mask=13.3%  norm=0.727  lr=9.29e-05  dt=  37.2ms  words=68,231,168
[E06   590/1548 G   8329|CLM] train=4.5141  mask=13.3%  norm=0.887  lr=9.28e-05  dt=  36.9ms  words=68,239,360
[E06   591/1548 G   8330|CLM] train=2.2706  mask=13.3%  norm=0.754  lr=9.28e-05  dt=  37.5ms  words=68,247,552
[E06   592/1548 G   8331|CLM] train=4.0211  mask=13.3%  norm=0.881  lr=9.28e-05  dt=  37.3ms  words=68,255,744
[E06   593/1548 G   8332|CLM] train=2.4255  mask=13.3%  norm=0.909  lr=9.27e-05  dt=  37.0ms  words=68,263,936
[E06   594/1548 G   8333|CLM] train=4.1478  mask=13.3%  norm=0.761  lr=9.27e-05  dt=  37.0ms  words=68,272,128
[E06   595/1548 G   8334|CLM] train=2.5124  mask=13.3%  norm=0.720  lr=9.27e-05  dt=  36.9ms  words=68,280,320
[E06   596/1548 G   8335|CLM] train=4.0174  mask=13.3%  norm=0.924  lr=9.26e-05  dt=  37.2ms  words=68,288,512
[E06   597/1548 G   8336|CLM] train=4.7234  mask=13.3%  norm=1.069  lr=9.26e-05  dt=  37.1ms  words=68,296,704
[E06   598/1548 G   8337|CLM] train=2.2401  mask=13.3%  norm=0.738  lr=9.26e-05  dt=  37.1ms  words=68,304,896
[E06   599/1548 G   8338|CLM] train=3.9013  mask=13.3%  norm=0.844  lr=9.25e-05  dt=  37.1ms  words=68,313,088
[E06   600/1548 G   8339|CLM] train=3.6914  mask=13.3%  norm=0.822  lr=9.25e-05  dt=  36.9ms  words=68,321,280
[E06   601/1548 G   8340|CLM] train=3.9231  mask=13.3%  norm=0.875  lr=9.24e-05  dt=  37.0ms  words=68,329,472
[E06   602/1548 G   8341|CLM] train=4.3637  mask=13.3%  norm=0.818  lr=9.24e-05  dt=  36.9ms  words=68,337,664
[E06   603/1548 G   8342|CLM] train=3.9958  mask=13.3%  norm=1.104  lr=9.24e-05  dt=  37.1ms  words=68,345,856
[E06   604/1548 G   8343|CLM] train=4.1900  mask=13.3%  norm=0.902  lr=9.23e-05  dt=  36.8ms  words=68,354,048
[E06   605/1548 G   8344|CLM] train=2.3863  mask=13.3%  norm=0.711  lr=9.23e-05  dt=  37.1ms  words=68,362,240
[E06   606/1548 G   8345|CLM] train=3.3665  mask=13.3%  norm=0.714  lr=9.23e-05  dt=  37.2ms  words=68,370,432
[E06   607/1548 G   8346|CLM] train=3.6666  mask=13.3%  norm=0.915  lr=9.22e-05  dt=  37.0ms  words=68,378,624
[E06   608/1548 G   8347|CLM] train=3.6660  mask=13.3%  norm=0.861  lr=9.22e-05  dt=  37.0ms  words=68,386,816
[E06   609/1548 G   8348|CLM] train=2.9523  mask=13.3%  norm=0.830  lr=9.22e-05  dt=  37.2ms  words=68,395,008
[E06   610/1548 G   8349|CLM] train=2.3430  mask=13.3%  norm=0.732  lr=9.21e-05  dt=  37.1ms  words=68,403,200
[E06   611/1548 G   8350|CLM] train=4.1985  mask=13.3%  norm=0.943  lr=9.21e-05  dt=  37.0ms  words=68,411,392
[E06   612/1548 G   8351|CLM] train=1.6520  mask=13.3%  norm=0.689  lr=9.21e-05  dt=  37.4ms  words=68,419,584
[E06   613/1548 G   8352|CLM] train=2.2364  mask=13.3%  norm=0.689  lr=9.20e-05  dt=  37.2ms  words=68,427,776
[E06   614/1548 G   8353|CLM] train=4.0356  mask=13.3%  norm=0.859  lr=9.20e-05  dt=  36.9ms  words=68,435,968
[E06   615/1548 G   8354|CLM] train=2.1868  mask=13.3%  norm=0.684  lr=9.20e-05  dt=  36.9ms  words=68,444,160
[E06   616/1548 G   8355|CLM] train=2.3552  mask=13.3%  norm=0.786  lr=9.19e-05  dt=  36.9ms  words=68,452,352
[E06   617/1548 G   8356|CLM] train=4.1551  mask=13.3%  norm=0.802  lr=9.19e-05  dt=  37.1ms  words=68,460,544
[E06   618/1548 G   8357|CLM] train=2.4397  mask=13.3%  norm=0.677  lr=9.19e-05  dt=  37.2ms  words=68,468,736
[E06   619/1548 G   8358|CLM] train=2.0995  mask=13.3%  norm=0.691  lr=9.18e-05  dt=  37.1ms  words=68,476,928
[E06   620/1548 G   8359|CLM] train=3.6262  mask=13.3%  norm=0.766  lr=9.18e-05  dt=  37.2ms  words=68,485,120
[E06   621/1548 G   8360|CLM] train=2.2616  mask=13.2%  norm=0.950  lr=9.18e-05  dt=  37.0ms  words=68,493,312
[E06   622/1548 G   8361|CLM] train=2.1911  mask=13.2%  norm=0.654  lr=9.17e-05  dt=  36.9ms  words=68,501,504
[E06   623/1548 G   8362|CLM] train=2.0842  mask=13.2%  norm=0.621  lr=9.17e-05  dt=  37.0ms  words=68,509,696
[E06   624/1548 G   8363|CLM] train=4.3726  mask=13.2%  norm=0.958  lr=9.17e-05  dt=  37.1ms  words=68,517,888
[E06   625/1548 G   8364|CLM] train=3.2562  mask=13.2%  norm=0.779  lr=9.16e-05  dt=  37.0ms  words=68,526,080
[E06   626/1548 G   8365|CLM] train=4.5127  mask=13.2%  norm=0.961  lr=9.16e-05  dt=  37.1ms  words=68,534,272
[E06   627/1548 G   8366|CLM] train=2.2765  mask=13.2%  norm=0.720  lr=9.16e-05  dt=  37.3ms  words=68,542,464
[E06   628/1548 G   8367|CLM] train=2.1652  mask=13.2%  norm=0.701  lr=9.15e-05  dt=  36.8ms  words=68,550,656
[E06   629/1548 G   8368|CLM] train=2.3682  mask=13.2%  norm=0.741  lr=9.15e-05  dt=  36.7ms  words=68,558,848
[E06   630/1548 G   8369|CLM] train=3.3214  mask=13.2%  norm=0.915  lr=9.15e-05  dt=  37.3ms  words=68,567,040
[E06   631/1548 G   8370|CLM] train=2.1409  mask=13.2%  norm=0.651  lr=9.14e-05  dt=  36.9ms  words=68,575,232
[E06   632/1548 G   8371|CLM] train=2.1655  mask=13.2%  norm=0.881  lr=9.14e-05  dt=  36.8ms  words=68,583,424
[E06   633/1548 G   8372|CLM] train=4.3511  mask=13.2%  norm=0.846  lr=9.14e-05  dt=  36.8ms  words=68,591,616
[E06   634/1548 G   8373|CLM] train=2.6854  mask=13.2%  norm=0.761  lr=9.13e-05  dt=  36.9ms  words=68,599,808
[E06   635/1548 G   8374|CLM] train=4.1511  mask=13.2%  norm=0.840  lr=9.13e-05  dt=  37.0ms  words=68,608,000
[E06   636/1548 G   8375|CLM] train=2.0519  mask=13.2%  norm=0.707  lr=9.12e-05  dt=  36.8ms  words=68,616,192
[E06   637/1548 G   8376|CLM] train=2.2634  mask=13.2%  norm=0.659  lr=9.12e-05  dt=  36.8ms  words=68,624,384
[E06   638/1548 G   8377|CLM] train=2.3476  mask=13.2%  norm=0.844  lr=9.12e-05  dt=  36.9ms  words=68,632,576
[E06   639/1548 G   8378|CLM] train=2.2969  mask=13.2%  norm=0.699  lr=9.11e-05  dt=  36.8ms  words=68,640,768
[E06   640/1548 G   8379|CLM] train=3.6030  mask=13.2%  norm=0.834  lr=9.11e-05  dt=  36.9ms  words=68,648,960
[E06   641/1548 G   8380|CLM] train=2.0668  mask=13.2%  norm=0.806  lr=9.11e-05  dt=  36.7ms  words=68,657,152
[E06   642/1548 G   8381|CLM] train=3.8287  mask=13.2%  norm=0.875  lr=9.10e-05  dt=  36.6ms  words=68,665,344
[E06   643/1548 G   8382|CLM] train=2.3896  mask=13.2%  norm=0.628  lr=9.10e-05  dt=  37.1ms  words=68,673,536
[E06   644/1548 G   8383|CLM] train=2.4169  mask=13.2%  norm=0.715  lr=9.10e-05  dt=  36.9ms  words=68,681,728
[E06   645/1548 G   8384|CLM] train=3.7613  mask=13.2%  norm=0.789  lr=9.09e-05  dt=  36.9ms  words=68,689,920
[E06   646/1548 G   8385|CLM] train=4.0194  mask=13.2%  norm=1.135  lr=9.09e-05  dt=  36.8ms  words=68,698,112
[E06   647/1548 G   8386|CLM] train=4.3448  mask=13.2%  norm=1.139  lr=9.09e-05  dt=  36.9ms  words=68,706,304
[E06   648/1548 G   8387|CLM] train=2.2261  mask=13.2%  norm=0.854  lr=9.08e-05  dt=  36.9ms  words=68,714,496
[E06   649/1548 G   8388|CLM] train=4.1890  mask=13.2%  norm=0.887  lr=9.08e-05  dt=  36.8ms  words=68,722,688
[E06   650/1548 G   8389|CLM] train=1.8268  mask=13.2%  norm=0.619  lr=9.08e-05  dt=  37.2ms  words=68,730,880
[E06   651/1548 G   8390|CLM] train=4.9812  mask=13.2%  norm=1.075  lr=9.07e-05  dt=  37.2ms  words=68,739,072
[E06   652/1548 G   8391|CLM] train=2.3664  mask=13.2%  norm=0.707  lr=9.07e-05  dt=  37.1ms  words=68,747,264
[E06   653/1548 G   8392|CLM] train=2.5893  mask=13.2%  norm=0.734  lr=9.07e-05  dt=  36.9ms  words=68,755,456
[E06   654/1548 G   8393|CLM] train=4.5521  mask=13.2%  norm=0.908  lr=9.06e-05  dt=  36.9ms  words=68,763,648
[E06   655/1548 G   8394|CLM] train=4.8153  mask=13.2%  norm=1.238  lr=9.06e-05  dt=  37.1ms  words=68,771,840
[E06   656/1548 G   8395|CLM] train=3.7860  mask=13.2%  norm=0.863  lr=9.06e-05  dt=  36.9ms  words=68,780,032
[E06   657/1548 G   8396|CLM] train=2.6395  mask=13.2%  norm=0.671  lr=9.05e-05  dt=  37.8ms  words=68,788,224
[E06   658/1548 G   8397|CLM] train=3.7618  mask=13.2%  norm=0.848  lr=9.05e-05  dt=  38.4ms  words=68,796,416
[E06   659/1548 G   8398|CLM] train=4.2113  mask=13.2%  norm=0.867  lr=9.05e-05  dt=  40.1ms  words=68,804,608
[E06   660/1548 G   8399|CLM] train=2.2528  mask=13.2%  norm=0.649  lr=9.04e-05  dt=  37.4ms  words=68,812,800
[E06   661/1548 G   8400|CLM] train=4.0444  mask=13.2%  norm=0.798  lr=9.04e-05  dt=  42.4ms  words=68,820,992
[E06   662/1548 G   8401|CLM] train=3.7578  mask=13.2%  norm=0.776  lr=9.04e-05  dt=  37.4ms  words=68,829,184
[E06   663/1548 G   8402|CLM] train=2.4860  mask=13.2%  norm=0.707  lr=9.03e-05  dt=  39.0ms  words=68,837,376
[E06   664/1548 G   8403|CLM] train=4.2212  mask=13.2%  norm=0.807  lr=9.03e-05  dt=  40.7ms  words=68,845,568
[E06   665/1548 G   8404|CLM] train=4.2320  mask=13.2%  norm=0.930  lr=9.03e-05  dt=  38.4ms  words=68,853,760
[E06   666/1548 G   8405|CLM] train=1.8988  mask=13.2%  norm=0.654  lr=9.02e-05  dt=  41.6ms  words=68,861,952
[E06   667/1548 G   8406|CLM] train=4.2587  mask=13.2%  norm=0.987  lr=9.02e-05  dt=  39.1ms  words=68,870,144
[E06   668/1548 G   8407|CLM] train=4.8084  mask=13.2%  norm=1.141  lr=9.02e-05  dt=  36.8ms  words=68,878,336
[E06   669/1548 G   8408|CLM] train=3.8576  mask=13.2%  norm=0.954  lr=9.01e-05  dt=  37.0ms  words=68,886,528
[E06   670/1548 G   8409|CLM] train=3.9777  mask=13.2%  norm=0.967  lr=9.01e-05  dt=  36.8ms  words=68,894,720
[E06   671/1548 G   8410|CLM] train=2.3671  mask=13.2%  norm=0.889  lr=9.01e-05  dt=  40.9ms  words=68,902,912
[E06   672/1548 G   8411|CLM] train=5.3829  mask=13.2%  norm=1.255  lr=9.00e-05  dt=  45.2ms  words=68,911,104
[E06   673/1548 G   8412|CLM] train=2.2785  mask=13.2%  norm=0.677  lr=9.00e-05  dt=  39.8ms  words=68,919,296
[E06   674/1548 G   8413|CLM] train=4.3468  mask=13.2%  norm=0.977  lr=9.00e-05  dt=  37.1ms  words=68,927,488
[E06   675/1548 G   8414|CLM] train=2.1739  mask=13.2%  norm=0.646  lr=8.99e-05  dt=  36.9ms  words=68,935,680
[E06   676/1548 G   8415|CLM] train=1.6369  mask=13.2%  norm=0.634  lr=8.99e-05  dt=  37.0ms  words=68,943,872
[E06   677/1548 G   8416|CLM] train=4.2213  mask=13.2%  norm=1.030  lr=8.98e-05  dt=  37.4ms  words=68,952,064
[E06   678/1548 G   8417|CLM] train=2.1953  mask=13.2%  norm=0.869  lr=8.98e-05  dt=  37.4ms  words=68,960,256
[E06   679/1548 G   8418|CLM] train=2.3207  mask=13.2%  norm=0.678  lr=8.98e-05  dt=  37.6ms  words=68,968,448
[E06   680/1548 G   8419|CLM] train=4.1841  mask=13.2%  norm=0.939  lr=8.97e-05  dt=  37.8ms  words=68,976,640
[E06   681/1548 G   8420|CLM] train=3.8494  mask=13.2%  norm=0.773  lr=8.97e-05  dt=  37.5ms  words=68,984,832
[E06   682/1548 G   8421|CLM] train=2.6601  mask=13.2%  norm=0.701  lr=8.97e-05  dt=  37.6ms  words=68,993,024
[E06   683/1548 G   8422|CLM] train=4.2598  mask=13.2%  norm=0.938  lr=8.96e-05  dt=  38.1ms  words=69,001,216
[E06   684/1548 G   8423|CLM] train=2.4564  mask=13.2%  norm=0.797  lr=8.96e-05  dt=  38.1ms  words=69,009,408
[E06   685/1548 G   8424|CLM] train=3.9792  mask=13.2%  norm=0.871  lr=8.96e-05  dt=  37.5ms  words=69,017,600
[E06   686/1548 G   8425|CLM] train=4.1067  mask=13.2%  norm=0.881  lr=8.95e-05  dt=  37.3ms  words=69,025,792
[E06   687/1548 G   8426|CLM] train=2.1089  mask=13.2%  norm=0.647  lr=8.95e-05  dt=  37.7ms  words=69,033,984
[E06   688/1548 G   8427|CLM] train=2.0381  mask=13.2%  norm=0.646  lr=8.95e-05  dt=  42.9ms  words=69,042,176
[E06   689/1548 G   8428|CLM] train=2.0104  mask=13.2%  norm=0.707  lr=8.94e-05  dt=  43.4ms  words=69,050,368
[E06   690/1548 G   8429|CLM] train=3.6264  mask=13.2%  norm=0.738  lr=8.94e-05  dt=  36.9ms  words=69,058,560
[E06   691/1548 G   8430|CLM] train=2.3223  mask=13.2%  norm=0.735  lr=8.94e-05  dt=  37.0ms  words=69,066,752
[E06   692/1548 G   8431|CLM] train=2.0837  mask=13.2%  norm=0.750  lr=8.93e-05  dt=  36.9ms  words=69,074,944
[E06   693/1548 G   8432|CLM] train=3.9312  mask=13.2%  norm=0.843  lr=8.93e-05  dt=  37.0ms  words=69,083,136
[E06   694/1548 G   8433|CLM] train=2.0927  mask=13.2%  norm=0.747  lr=8.93e-05  dt=  37.1ms  words=69,091,328
[E06   695/1548 G   8434|CLM] train=2.0786  mask=13.2%  norm=0.609  lr=8.92e-05  dt=  36.9ms  words=69,099,520
[E06   696/1548 G   8435|CLM] train=4.5743  mask=13.2%  norm=0.943  lr=8.92e-05  dt=  36.9ms  words=69,107,712
[E06   697/1548 G   8436|CLM] train=4.4388  mask=13.2%  norm=0.882  lr=8.92e-05  dt=  37.6ms  words=69,115,904
[E06   698/1548 G   8437|CLM] train=4.1515  mask=13.2%  norm=0.869  lr=8.91e-05  dt=  41.2ms  words=69,124,096
[E06   699/1548 G   8438|CLM] train=4.1174  mask=13.2%  norm=0.853  lr=8.91e-05  dt=  38.3ms  words=69,132,288
[E06   700/1548 G   8439|CLM] train=4.0864  mask=13.2%  norm=0.979  lr=8.91e-05  dt=  46.2ms  words=69,140,480
[E06   701/1548 G   8440|CLM] train=2.3431  mask=13.2%  norm=1.041  lr=8.90e-05  dt=  39.5ms  words=69,148,672
[E06   702/1548 G   8441|CLM] train=4.1009  mask=13.2%  norm=0.847  lr=8.90e-05  dt=  47.2ms  words=69,156,864
[E06   703/1548 G   8442|CLM] train=4.6017  mask=13.2%  norm=0.955  lr=8.90e-05  dt=  40.7ms  words=69,165,056
[E06   704/1548 G   8443|CLM] train=3.7486  mask=13.2%  norm=0.991  lr=8.89e-05  dt=  37.2ms  words=69,173,248
[E06   705/1548 G   8444|CLM] train=3.8555  mask=13.2%  norm=0.911  lr=8.89e-05  dt=  37.4ms  words=69,181,440
[E06   706/1548 G   8445|CLM] train=4.4363  mask=13.2%  norm=0.987  lr=8.89e-05  dt=  36.9ms  words=69,189,632
[E06   707/1548 G   8446|CLM] train=2.1941  mask=13.2%  norm=0.720  lr=8.88e-05  dt=  37.0ms  words=69,197,824
[E06   708/1548 G   8447|CLM] train=3.9004  mask=13.2%  norm=0.841  lr=8.88e-05  dt=  37.0ms  words=69,206,016
[E06   709/1548 G   8448|CLM] train=4.1397  mask=13.2%  norm=0.945  lr=8.88e-05  dt=  36.9ms  words=69,214,208
[E06   710/1548 G   8449|CLM] train=2.1057  mask=13.2%  norm=0.653  lr=8.87e-05  dt=  36.9ms  words=69,222,400
[E06   711/1548 G   8450|CLM] train=2.2596  mask=13.2%  norm=0.915  lr=8.87e-05  dt=  36.9ms  words=69,230,592
[E06   712/1548 G   8451|CLM] train=2.0999  mask=13.2%  norm=0.863  lr=8.87e-05  dt=  36.9ms  words=69,238,784
[E06   713/1548 G   8452|CLM] train=4.1715  mask=13.2%  norm=0.858  lr=8.86e-05  dt=  36.8ms  words=69,246,976
[E06   714/1548 G   8453|CLM] train=4.5130  mask=13.2%  norm=1.246  lr=8.86e-05  dt=  36.7ms  words=69,255,168
[E06   715/1548 G   8454|CLM] train=4.8902  mask=13.2%  norm=1.315  lr=8.86e-05  dt=  37.2ms  words=69,263,360
[E06   716/1548 G   8455|CLM] train=4.2010  mask=13.2%  norm=0.851  lr=8.85e-05  dt=  37.0ms  words=69,271,552
[E06   717/1548 G   8456|CLM] train=4.5737  mask=13.2%  norm=1.305  lr=8.85e-05  dt=  37.0ms  words=69,279,744
[E06   718/1548 G   8457|CLM] train=2.3359  mask=13.2%  norm=0.731  lr=8.85e-05  dt=  36.9ms  words=69,287,936
[E06   719/1548 G   8458|CLM] train=2.4790  mask=13.2%  norm=0.780  lr=8.84e-05  dt=  37.2ms  words=69,296,128
[E06   720/1548 G   8459|CLM] train=5.2809  mask=13.2%  norm=1.036  lr=8.84e-05  dt=  36.9ms  words=69,304,320
[E06   721/1548 G   8460|CLM] train=1.9135  mask=13.2%  norm=0.698  lr=8.84e-05  dt=  36.8ms  words=69,312,512
[E06   722/1548 G   8461|CLM] train=2.4447  mask=13.2%  norm=0.743  lr=8.83e-05  dt=  36.9ms  words=69,320,704
[E06   723/1548 G   8462|CLM] train=3.7226  mask=13.2%  norm=0.841  lr=8.83e-05  dt=  37.4ms  words=69,328,896
[E06   724/1548 G   8463|CLM] train=1.8507  mask=13.2%  norm=0.643  lr=8.83e-05  dt=  37.2ms  words=69,337,088
[E06   725/1548 G   8464|CLM] train=2.5714  mask=13.2%  norm=0.818  lr=8.82e-05  dt=  36.8ms  words=69,345,280
[E06   726/1548 G   8465|CLM] train=4.3769  mask=13.2%  norm=0.945  lr=8.82e-05  dt=  37.1ms  words=69,353,472
[E06   727/1548 G   8466|CLM] train=4.3729  mask=13.2%  norm=0.829  lr=8.82e-05  dt=  37.1ms  words=69,361,664
[E06   728/1548 G   8467|CLM] train=2.6426  mask=13.2%  norm=0.689  lr=8.81e-05  dt=  36.8ms  words=69,369,856
[E06   729/1548 G   8468|CLM] train=3.7762  mask=13.2%  norm=0.981  lr=8.81e-05  dt=  37.0ms  words=69,378,048
[E06   730/1548 G   8469|CLM] train=4.2514  mask=13.2%  norm=0.917  lr=8.81e-05  dt=  36.9ms  words=69,386,240
[E06   731/1548 G   8470|CLM] train=4.1764  mask=13.2%  norm=0.820  lr=8.80e-05  dt=  37.0ms  words=69,394,432
[E06   732/1548 G   8471|CLM] train=4.2023  mask=13.2%  norm=0.970  lr=8.80e-05  dt=  36.9ms  words=69,402,624
[E06   733/1548 G   8472|CLM] train=4.6213  mask=13.2%  norm=0.970  lr=8.80e-05  dt=  37.0ms  words=69,410,816
[E06   734/1548 G   8473|CLM] train=2.6993  mask=13.2%  norm=0.736  lr=8.79e-05  dt=  36.9ms  words=69,419,008
[E06   735/1548 G   8474|CLM] train=4.0655  mask=13.2%  norm=0.801  lr=8.79e-05  dt=  37.6ms  words=69,427,200
[E06   736/1548 G   8475|CLM] train=4.0728  mask=13.2%  norm=0.794  lr=8.79e-05  dt=  36.9ms  words=69,435,392
[E06   737/1548 G   8476|CLM] train=2.1596  mask=13.2%  norm=0.789  lr=8.78e-05  dt=  37.1ms  words=69,443,584
[E06   738/1548 G   8477|CLM] train=2.3474  mask=13.2%  norm=0.738  lr=8.78e-05  dt=  37.1ms  words=69,451,776
[E06   739/1548 G   8478|CLM] train=2.1628  mask=13.2%  norm=0.957  lr=8.78e-05  dt=  36.9ms  words=69,459,968
[E06   740/1548 G   8479|CLM] train=2.3309  mask=13.2%  norm=0.817  lr=8.77e-05  dt=  36.8ms  words=69,468,160
[E06   741/1548 G   8480|CLM] train=2.2270  mask=13.2%  norm=0.619  lr=8.77e-05  dt=  36.8ms  words=69,476,352
[E06   742/1548 G   8481|CLM] train=3.4688  mask=13.2%  norm=0.799  lr=8.76e-05  dt=  36.9ms  words=69,484,544
[E06   743/1548 G   8482|CLM] train=4.0567  mask=13.2%  norm=1.077  lr=8.76e-05  dt=  36.9ms  words=69,492,736
[E06   744/1548 G   8483|CLM] train=2.1929  mask=13.2%  norm=0.741  lr=8.76e-05  dt=  36.9ms  words=69,500,928
[E06   745/1548 G   8484|CLM] train=4.6711  mask=13.1%  norm=0.959  lr=8.75e-05  dt=  36.8ms  words=69,509,120
[E06   746/1548 G   8485|CLM] train=3.5578  mask=13.1%  norm=0.775  lr=8.75e-05  dt=  36.9ms  words=69,517,312
[E06   747/1548 G   8486|CLM] train=3.8617  mask=13.1%  norm=0.847  lr=8.75e-05  dt=  36.9ms  words=69,525,504
[E06   748/1548 G   8487|CLM] train=3.9191  mask=13.1%  norm=0.713  lr=8.74e-05  dt=  36.7ms  words=69,533,696
[E06   749/1548 G   8488|CLM] train=2.1468  mask=13.1%  norm=0.923  lr=8.74e-05  dt=  37.1ms  words=69,541,888
[E06   750/1548 G   8489|CLM] train=3.8182  mask=13.1%  norm=0.867  lr=8.74e-05  dt=  37.1ms  words=69,550,080
[E06   751/1548 G   8490|CLM] train=2.2307  mask=13.1%  norm=0.646  lr=8.73e-05  dt=  36.9ms  words=69,558,272
[E06   752/1548 G   8491|CLM] train=3.8132  mask=13.1%  norm=0.787  lr=8.73e-05  dt=  36.8ms  words=69,566,464
[E06   753/1548 G   8492|CLM] train=2.3050  mask=13.1%  norm=0.719  lr=8.73e-05  dt=  36.9ms  words=69,574,656
[E06   754/1548 G   8493|CLM] train=3.8752  mask=13.1%  norm=0.891  lr=8.72e-05  dt=  37.1ms  words=69,582,848
[E06   755/1548 G   8494|CLM] train=3.9041  mask=13.1%  norm=0.804  lr=8.72e-05  dt=  37.1ms  words=69,591,040
[E06   756/1548 G   8495|CLM] train=4.2582  mask=13.1%  norm=0.954  lr=8.72e-05  dt=  37.2ms  words=69,599,232
[E06   757/1548 G   8496|CLM] train=2.1742  mask=13.1%  norm=0.675  lr=8.71e-05  dt=  37.0ms  words=69,607,424
[E06   758/1548 G   8497|CLM] train=3.5936  mask=13.1%  norm=0.874  lr=8.71e-05  dt=  36.9ms  words=69,615,616
[E06   759/1548 G   8498|CLM] train=2.3387  mask=13.1%  norm=0.651  lr=8.71e-05  dt=  36.9ms  words=69,623,808
[E06   760/1548 G   8499|CLM] train=2.7430  mask=13.1%  norm=0.802  lr=8.70e-05  dt=  36.7ms  words=69,632,000
[E06   761/1548 G   8500|CLM] train=2.6404  mask=13.1%  norm=0.750  lr=8.70e-05  dt=  36.8ms  words=69,640,192
[E06   762/1548 G   8501|CLM] train=2.1626  mask=13.1%  norm=0.672  lr=8.70e-05  dt=  36.9ms  words=69,648,384
[E06   763/1548 G   8502|CLM] train=2.2591  mask=13.1%  norm=0.648  lr=8.69e-05  dt=  36.9ms  words=69,656,576
[E06   764/1548 G   8503|CLM] train=2.3720  mask=13.1%  norm=0.717  lr=8.69e-05  dt=  37.0ms  words=69,664,768
[E06   765/1548 G   8504|CLM] train=2.7290  mask=13.1%  norm=0.708  lr=8.69e-05  dt=  36.8ms  words=69,672,960
[E06   766/1548 G   8505|CLM] train=4.3254  mask=13.1%  norm=0.952  lr=8.68e-05  dt=  37.3ms  words=69,681,152
[E06   767/1548 G   8506|CLM] train=2.1398  mask=13.1%  norm=0.815  lr=8.68e-05  dt=  36.9ms  words=69,689,344
[E06   768/1548 G   8507|CLM] train=4.5403  mask=13.1%  norm=0.965  lr=8.68e-05  dt=  37.0ms  words=69,697,536
[E06   769/1548 G   8508|CLM] train=4.2860  mask=13.1%  norm=0.827  lr=8.67e-05  dt=  36.9ms  words=69,705,728
[E06   770/1548 G   8509|CLM] train=1.9205  mask=13.1%  norm=0.740  lr=8.67e-05  dt=  36.9ms  words=69,713,920
[E06   771/1548 G   8510|CLM] train=4.6658  mask=13.1%  norm=1.195  lr=8.67e-05  dt=  36.8ms  words=69,722,112
[E06   772/1548 G   8511|CLM] train=4.4694  mask=13.1%  norm=0.808  lr=8.66e-05  dt=  36.8ms  words=69,730,304
[E06   773/1548 G   8512|CLM] train=4.1520  mask=13.1%  norm=0.833  lr=8.66e-05  dt=  36.7ms  words=69,738,496
[E06   774/1548 G   8513|CLM] train=4.2926  mask=13.1%  norm=0.895  lr=8.66e-05  dt=  37.2ms  words=69,746,688
[E06   775/1548 G   8514|CLM] train=2.2498  mask=13.1%  norm=0.750  lr=8.65e-05  dt=  37.0ms  words=69,754,880
[E06   776/1548 G   8515|CLM] train=4.8062  mask=13.1%  norm=2.219  lr=8.65e-05  dt=  37.4ms  words=69,763,072
[E06   777/1548 G   8516|CLM] train=2.2488  mask=13.1%  norm=0.795  lr=8.65e-05  dt=  37.8ms  words=69,771,264
[E06   778/1548 G   8517|CLM] train=2.7218  mask=13.1%  norm=0.961  lr=8.64e-05  dt=  37.2ms  words=69,779,456
[E06   779/1548 G   8518|CLM] train=4.1633  mask=13.1%  norm=0.865  lr=8.64e-05  dt=  37.4ms  words=69,787,648
[E06   780/1548 G   8519|CLM] train=2.4172  mask=13.1%  norm=0.707  lr=8.64e-05  dt=  37.0ms  words=69,795,840
[E06   781/1548 G   8520|CLM] train=2.7463  mask=13.1%  norm=0.748  lr=8.63e-05  dt=  37.1ms  words=69,804,032
[E06   782/1548 G   8521|CLM] train=4.3170  mask=13.1%  norm=1.081  lr=8.63e-05  dt=  37.3ms  words=69,812,224
[E06   783/1548 G   8522|CLM] train=4.1204  mask=13.1%  norm=1.288  lr=8.63e-05  dt=  37.2ms  words=69,820,416
[E06   784/1548 G   8523|CLM] train=2.0698  mask=13.1%  norm=0.720  lr=8.62e-05  dt=  37.7ms  words=69,828,608
[E06   785/1548 G   8524|CLM] train=2.7254  mask=13.1%  norm=0.696  lr=8.62e-05  dt=  36.8ms  words=69,836,800
[E06   786/1548 G   8525|CLM] train=4.1899  mask=13.1%  norm=0.967  lr=8.62e-05  dt=  36.9ms  words=69,844,992
[E06   787/1548 G   8526|CLM] train=3.4844  mask=13.1%  norm=0.762  lr=8.61e-05  dt=  36.9ms  words=69,853,184
[E06   788/1548 G   8527|CLM] train=2.2355  mask=13.1%  norm=0.747  lr=8.61e-05  dt=  36.8ms  words=69,861,376
[E06   789/1548 G   8528|CLM] train=3.9401  mask=13.1%  norm=0.902  lr=8.61e-05  dt=  37.0ms  words=69,869,568
[E06   790/1548 G   8529|CLM] train=4.1933  mask=13.1%  norm=0.919  lr=8.60e-05  dt=  37.0ms  words=69,877,760
[E06   791/1548 G   8530|CLM] train=2.4261  mask=13.1%  norm=0.708  lr=8.60e-05  dt=  37.0ms  words=69,885,952
[E06   792/1548 G   8531|CLM] train=4.3254  mask=13.1%  norm=0.808  lr=8.60e-05  dt=  36.8ms  words=69,894,144
[E06   793/1548 G   8532|CLM] train=4.0578  mask=13.1%  norm=0.929  lr=8.59e-05  dt=  37.0ms  words=69,902,336
[E06   794/1548 G   8533|CLM] train=2.0667  mask=13.1%  norm=0.725  lr=8.59e-05  dt=  36.9ms  words=69,910,528
[E06   795/1548 G   8534|CLM] train=4.3588  mask=13.1%  norm=0.948  lr=8.59e-05  dt=  36.8ms  words=69,918,720
[E06   796/1548 G   8535|CLM] train=4.2038  mask=13.1%  norm=1.471  lr=8.58e-05  dt=  37.1ms  words=69,926,912
[E06   797/1548 G   8536|CLM] train=3.7418  mask=13.1%  norm=0.900  lr=8.58e-05  dt=  36.9ms  words=69,935,104
[E06   798/1548 G   8537|CLM] train=4.0921  mask=13.1%  norm=0.968  lr=8.58e-05  dt=  36.9ms  words=69,943,296
[E06   799/1548 G   8538|CLM] train=2.0596  mask=13.1%  norm=0.911  lr=8.57e-05  dt=  36.8ms  words=69,951,488
[E06   800/1548 G   8539|CLM] train=2.6265  mask=13.1%  norm=0.670  lr=8.57e-05  dt=  36.9ms  words=69,959,680
[E06   801/1548 G   8540|CLM] train=3.9805  mask=13.1%  norm=1.388  lr=8.57e-05  dt=  36.8ms  words=69,967,872
[E06   802/1548 G   8541|CLM] train=4.4955  mask=13.1%  norm=0.961  lr=8.56e-05  dt=  37.1ms  words=69,976,064
[E06   803/1548 G   8542|CLM] train=1.8997  mask=13.1%  norm=0.632  lr=8.56e-05  dt=  37.1ms  words=69,984,256
[E06   804/1548 G   8543|CLM] train=2.2656  mask=13.1%  norm=0.728  lr=8.56e-05  dt=  37.6ms  words=69,992,448
[E06   805/1548 G   8544|CLM] train=3.8851  mask=13.1%  norm=0.968  lr=8.55e-05  dt=  37.0ms  words=70,000,640

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_70M'...
[Checkpoint] Checkpoint 'chck_70M' successfully saved.
[E06   806/1548 G   8545|CLM] train=3.8920  mask=13.1%  norm=0.844  lr=8.55e-05  dt=  37.8ms  words=70,008,832
[E06   807/1548 G   8546|CLM] train=4.4324  mask=13.1%  norm=0.869  lr=8.55e-05  dt=  37.1ms  words=70,017,024
[E06   808/1548 G   8547|CLM] train=3.9165  mask=13.1%  norm=0.769  lr=8.54e-05  dt=  36.8ms  words=70,025,216
[E06   809/1548 G   8548|CLM] train=3.7742  mask=13.1%  norm=0.971  lr=8.54e-05  dt=  37.0ms  words=70,033,408
[E06   810/1548 G   8549|CLM] train=2.1060  mask=13.1%  norm=0.621  lr=8.54e-05  dt=  36.9ms  words=70,041,600
[E06   811/1548 G   8550|CLM] train=2.5217  mask=13.1%  norm=0.665  lr=8.53e-05  dt=  37.1ms  words=70,049,792
[E06   812/1548 G   8551|CLM] train=4.1433  mask=13.1%  norm=0.776  lr=8.53e-05  dt=  36.8ms  words=70,057,984
[E06   813/1548 G   8552|CLM] train=3.9441  mask=13.1%  norm=1.078  lr=8.53e-05  dt=  36.9ms  words=70,066,176
[E06   814/1548 G   8553|CLM] train=3.8396  mask=13.1%  norm=0.944  lr=8.52e-05  dt=  37.1ms  words=70,074,368
[E06   815/1548 G   8554|CLM] train=4.3972  mask=13.1%  norm=0.866  lr=8.52e-05  dt=  36.9ms  words=70,082,560
[E06   816/1548 G   8555|CLM] train=3.8506  mask=13.1%  norm=0.763  lr=8.52e-05  dt=  36.9ms  words=70,090,752
[E06   817/1548 G   8556|CLM] train=4.1759  mask=13.1%  norm=0.963  lr=8.51e-05  dt=  37.2ms  words=70,098,944
[E06   818/1548 G   8557|CLM] train=4.6992  mask=13.1%  norm=0.985  lr=8.51e-05  dt=  36.8ms  words=70,107,136
[E06   819/1548 G   8558|CLM] train=2.6759  mask=13.1%  norm=0.757  lr=8.51e-05  dt=  37.0ms  words=70,115,328
[E06   820/1548 G   8559|CLM] train=4.0255  mask=13.1%  norm=0.844  lr=8.50e-05  dt=  36.8ms  words=70,123,520
[E06   821/1548 G   8560|CLM] train=4.1076  mask=13.1%  norm=0.847  lr=8.50e-05  dt=  36.8ms  words=70,131,712
[E06   822/1548 G   8561|CLM] train=2.0645  mask=13.1%  norm=0.730  lr=8.50e-05  dt=  36.9ms  words=70,139,904
[E06   823/1548 G   8562|CLM] train=4.2157  mask=13.1%  norm=0.832  lr=8.49e-05  dt=  37.1ms  words=70,148,096
[E06   824/1548 G   8563|CLM] train=4.2979  mask=13.1%  norm=0.846  lr=8.49e-05  dt=  36.8ms  words=70,156,288
[E06   825/1548 G   8564|CLM] train=4.0273  mask=13.1%  norm=0.859  lr=8.49e-05  dt=  36.8ms  words=70,164,480
[E06   826/1548 G   8565|CLM] train=2.7116  mask=13.1%  norm=0.833  lr=8.48e-05  dt=  37.2ms  words=70,172,672
[E06   827/1548 G   8566|CLM] train=3.4821  mask=13.1%  norm=0.811  lr=8.48e-05  dt=  36.9ms  words=70,180,864
[E06   828/1548 G   8567|CLM] train=1.9402  mask=13.1%  norm=0.913  lr=8.48e-05  dt=  36.8ms  words=70,189,056
[E06   829/1548 G   8568|CLM] train=4.5627  mask=13.1%  norm=0.926  lr=8.47e-05  dt=  36.8ms  words=70,197,248
[E06   830/1548 G   8569|CLM] train=4.9954  mask=13.1%  norm=1.042  lr=8.47e-05  dt=  36.8ms  words=70,205,440
[E06   831/1548 G   8570|CLM] train=2.2910  mask=13.1%  norm=0.651  lr=8.47e-05  dt=  37.2ms  words=70,213,632
[E06   832/1548 G   8571|CLM] train=3.5929  mask=13.1%  norm=0.796  lr=8.46e-05  dt=  36.9ms  words=70,221,824
[E06   833/1548 G   8572|CLM] train=1.8973  mask=13.1%  norm=0.791  lr=8.46e-05  dt=  36.8ms  words=70,230,016
[E06   834/1548 G   8573|CLM] train=2.5048  mask=13.1%  norm=0.689  lr=8.46e-05  dt=  36.9ms  words=70,238,208
[E06   835/1548 G   8574|CLM] train=2.4225  mask=13.1%  norm=0.697  lr=8.45e-05  dt=  37.1ms  words=70,246,400
[E06   836/1548 G   8575|CLM] train=4.3341  mask=13.1%  norm=0.989  lr=8.45e-05  dt=  36.9ms  words=70,254,592
[E06   837/1548 G   8576|CLM] train=4.4224  mask=13.1%  norm=0.832  lr=8.45e-05  dt=  36.8ms  words=70,262,784
[E06   838/1548 G   8577|CLM] train=4.7951  mask=13.1%  norm=0.926  lr=8.44e-05  dt=  37.5ms  words=70,270,976
[E06   839/1548 G   8578|CLM] train=2.4194  mask=13.1%  norm=0.728  lr=8.44e-05  dt=  37.0ms  words=70,279,168
[E06   840/1548 G   8579|CLM] train=4.1221  mask=13.1%  norm=0.998  lr=8.44e-05  dt=  36.9ms  words=70,287,360
[E06   841/1548 G   8580|CLM] train=4.0241  mask=13.1%  norm=0.840  lr=8.43e-05  dt=  36.9ms  words=70,295,552
[E06   842/1548 G   8581|CLM] train=2.4238  mask=13.1%  norm=0.705  lr=8.43e-05  dt=  37.1ms  words=70,303,744
[E06   843/1548 G   8582|CLM] train=4.7891  mask=13.1%  norm=1.256  lr=8.43e-05  dt=  37.0ms  words=70,311,936
[E06   844/1548 G   8583|CLM] train=3.5112  mask=13.1%  norm=0.842  lr=8.42e-05  dt=  36.9ms  words=70,320,128
[E06   845/1548 G   8584|CLM] train=4.0654  mask=13.1%  norm=0.841  lr=8.42e-05  dt=  37.0ms  words=70,328,320
[E06   846/1548 G   8585|CLM] train=2.2110  mask=13.1%  norm=0.769  lr=8.42e-05  dt=  37.0ms  words=70,336,512
[E06   847/1548 G   8586|CLM] train=2.4195  mask=13.1%  norm=0.833  lr=8.41e-05  dt=  36.8ms  words=70,344,704
[E06   848/1548 G   8587|CLM] train=2.0328  mask=13.1%  norm=0.804  lr=8.41e-05  dt=  36.8ms  words=70,352,896
[E06   849/1548 G   8588|CLM] train=4.1999  mask=13.1%  norm=0.791  lr=8.41e-05  dt=  37.0ms  words=70,361,088
[E06   850/1548 G   8589|CLM] train=4.3519  mask=13.1%  norm=0.992  lr=8.40e-05  dt=  37.4ms  words=70,369,280
[E06   851/1548 G   8590|CLM] train=2.0937  mask=13.1%  norm=0.684  lr=8.40e-05  dt=  37.2ms  words=70,377,472
[E06   852/1548 G   8591|CLM] train=3.6296  mask=13.1%  norm=0.752  lr=8.40e-05  dt=  37.1ms  words=70,385,664
[E06   853/1548 G   8592|CLM] train=3.5034  mask=13.1%  norm=0.791  lr=8.39e-05  dt=  37.1ms  words=70,393,856
[E06   854/1548 G   8593|CLM] train=4.0941  mask=13.1%  norm=0.796  lr=8.39e-05  dt=  36.8ms  words=70,402,048
[E06   855/1548 G   8594|CLM] train=2.1461  mask=13.1%  norm=0.665  lr=8.39e-05  dt=  36.8ms  words=70,410,240
[E06   856/1548 G   8595|CLM] train=1.8388  mask=13.1%  norm=0.884  lr=8.38e-05  dt=  37.2ms  words=70,418,432
[E06   857/1548 G   8596|CLM] train=2.0911  mask=13.1%  norm=0.741  lr=8.38e-05  dt=  37.2ms  words=70,426,624
[E06   858/1548 G   8597|CLM] train=3.4864  mask=13.1%  norm=0.821  lr=8.38e-05  dt=  37.3ms  words=70,434,816
[E06   859/1548 G   8598|CLM] train=4.9112  mask=13.1%  norm=1.081  lr=8.37e-05  dt=  37.2ms  words=70,443,008
[E06   860/1548 G   8599|CLM] train=2.0029  mask=13.1%  norm=0.687  lr=8.37e-05  dt=  37.1ms  words=70,451,200
[E06   861/1548 G   8600|CLM] train=4.3867  mask=13.1%  norm=1.264  lr=8.37e-05  dt=  36.8ms  words=70,459,392
[E06   862/1548 G   8601|CLM] train=2.0552  mask=13.1%  norm=0.782  lr=8.36e-05  dt=  36.8ms  words=70,467,584
[E06   863/1548 G   8602|CLM] train=3.2025  mask=13.1%  norm=0.749  lr=8.36e-05  dt=  36.8ms  words=70,475,776
[E06   864/1548 G   8603|CLM] train=4.7710  mask=13.1%  norm=0.839  lr=8.36e-05  dt=  36.9ms  words=70,483,968
[E06   865/1548 G   8604|CLM] train=4.4809  mask=13.1%  norm=1.054  lr=8.35e-05  dt=  37.3ms  words=70,492,160
[E06   866/1548 G   8605|CLM] train=4.7003  mask=13.1%  norm=0.950  lr=8.35e-05  dt=  37.0ms  words=70,500,352
[E06   867/1548 G   8606|CLM] train=3.8928  mask=13.1%  norm=0.865  lr=8.35e-05  dt=  37.0ms  words=70,508,544
[E06   868/1548 G   8607|CLM] train=2.3952  mask=13.0%  norm=0.920  lr=8.34e-05  dt=  36.9ms  words=70,516,736
[E06   869/1548 G   8608|CLM] train=5.0520  mask=13.0%  norm=1.072  lr=8.34e-05  dt=  36.8ms  words=70,524,928
[E06   870/1548 G   8609|CLM] train=3.4961  mask=13.0%  norm=0.814  lr=8.34e-05  dt=  36.9ms  words=70,533,120
[E06   871/1548 G   8610|CLM] train=3.8744  mask=13.0%  norm=0.778  lr=8.33e-05  dt=  37.0ms  words=70,541,312
[E06   872/1548 G   8611|CLM] train=3.7146  mask=13.0%  norm=0.816  lr=8.33e-05  dt=  36.8ms  words=70,549,504
[E06   873/1548 G   8612|CLM] train=4.3798  mask=13.0%  norm=0.910  lr=8.33e-05  dt=  36.8ms  words=70,557,696
[E06   874/1548 G   8613|CLM] train=2.6524  mask=13.0%  norm=0.765  lr=8.32e-05  dt=  37.0ms  words=70,565,888
[E06   875/1548 G   8614|CLM] train=4.8849  mask=13.0%  norm=1.030  lr=8.32e-05  dt=  37.0ms  words=70,574,080
[E06   876/1548 G   8615|CLM] train=3.6863  mask=13.0%  norm=0.827  lr=8.32e-05  dt=  36.9ms  words=70,582,272
[E06   877/1548 G   8616|CLM] train=3.7167  mask=13.0%  norm=0.775  lr=8.31e-05  dt=  36.9ms  words=70,590,464
[E06   878/1548 G   8617|CLM] train=4.2676  mask=13.0%  norm=0.932  lr=8.31e-05  dt=  36.9ms  words=70,598,656
[E06   879/1548 G   8618|CLM] train=3.8172  mask=13.0%  norm=0.950  lr=8.31e-05  dt=  37.2ms  words=70,606,848
[E06   880/1548 G   8619|CLM] train=3.8257  mask=13.0%  norm=0.903  lr=8.31e-05  dt=  36.9ms  words=70,615,040
[E06   881/1548 G   8620|CLM] train=4.0948  mask=13.0%  norm=0.980  lr=8.30e-05  dt=  36.8ms  words=70,623,232
[E06   882/1548 G   8621|CLM] train=2.3258  mask=13.0%  norm=0.741  lr=8.30e-05  dt=  36.8ms  words=70,631,424
[E06   883/1548 G   8622|CLM] train=2.3667  mask=13.0%  norm=0.800  lr=8.30e-05  dt=  37.0ms  words=70,639,616
[E06   884/1548 G   8623|CLM] train=4.9035  mask=13.0%  norm=3.386  lr=8.29e-05  dt=  36.8ms  words=70,647,808
[E06   885/1548 G   8624|CLM] train=2.0414  mask=13.0%  norm=0.845  lr=8.29e-05  dt=  36.9ms  words=70,656,000
[E06   886/1548 G   8625|CLM] train=4.3189  mask=13.0%  norm=1.031  lr=8.29e-05  dt=  37.0ms  words=70,664,192
[E06   887/1548 G   8626|CLM] train=3.9993  mask=13.0%  norm=0.831  lr=8.28e-05  dt=  36.9ms  words=70,672,384
[E06   888/1548 G   8627|CLM] train=2.4197  mask=13.0%  norm=0.658  lr=8.28e-05  dt=  36.8ms  words=70,680,576
[E06   889/1548 G   8628|CLM] train=2.0269  mask=13.0%  norm=0.708  lr=8.28e-05  dt=  36.9ms  words=70,688,768
[E06   890/1548 G   8629|CLM] train=3.4856  mask=13.0%  norm=0.759  lr=8.27e-05  dt=  36.9ms  words=70,696,960
[E06   891/1548 G   8630|CLM] train=2.1645  mask=13.0%  norm=0.852  lr=8.27e-05  dt=  37.1ms  words=70,705,152
[E06   892/1548 G   8631|CLM] train=2.6537  mask=13.0%  norm=0.694  lr=8.27e-05  dt=  36.9ms  words=70,713,344
[E06   893/1548 G   8632|CLM] train=4.4928  mask=13.0%  norm=1.080  lr=8.26e-05  dt=  36.9ms  words=70,721,536
[E06   894/1548 G   8633|CLM] train=3.8165  mask=13.0%  norm=0.969  lr=8.26e-05  dt=  36.9ms  words=70,729,728
[E06   895/1548 G   8634|CLM] train=2.2076  mask=13.0%  norm=0.760  lr=8.26e-05  dt=  37.0ms  words=70,737,920
[E06   896/1548 G   8635|CLM] train=2.8426  mask=13.0%  norm=0.831  lr=8.25e-05  dt=  36.9ms  words=70,746,112
[E06   897/1548 G   8636|CLM] train=2.4474  mask=13.0%  norm=0.800  lr=8.25e-05  dt=  36.8ms  words=70,754,304
[E06   898/1548 G   8637|CLM] train=4.9919  mask=13.0%  norm=1.483  lr=8.25e-05  dt=  37.0ms  words=70,762,496
[E06   899/1548 G   8638|CLM] train=5.1181  mask=13.0%  norm=1.046  lr=8.24e-05  dt=  36.9ms  words=70,770,688
[E06   900/1548 G   8639|CLM] train=2.4150  mask=13.0%  norm=0.841  lr=8.24e-05  dt=  36.9ms  words=70,778,880
[E06   901/1548 G   8640|CLM] train=4.0349  mask=13.0%  norm=0.840  lr=8.24e-05  dt=  37.0ms  words=70,787,072
[E06   902/1548 G   8641|CLM] train=4.0177  mask=13.0%  norm=0.875  lr=8.23e-05  dt=  36.9ms  words=70,795,264
[E06   903/1548 G   8642|CLM] train=2.0374  mask=13.0%  norm=0.759  lr=8.23e-05  dt=  37.2ms  words=70,803,456
[E06   904/1548 G   8643|CLM] train=4.8409  mask=13.0%  norm=1.316  lr=8.23e-05  dt=  36.9ms  words=70,811,648
[E06   905/1548 G   8644|CLM] train=4.3790  mask=13.0%  norm=0.920  lr=8.22e-05  dt=  37.2ms  words=70,819,840
[E06   906/1548 G   8645|CLM] train=2.3067  mask=13.0%  norm=0.821  lr=8.22e-05  dt=  37.5ms  words=70,828,032
[E06   907/1548 G   8646|CLM] train=2.5234  mask=13.0%  norm=0.775  lr=8.22e-05  dt=  36.9ms  words=70,836,224
[E06   908/1548 G   8647|CLM] train=4.4678  mask=13.0%  norm=1.101  lr=8.21e-05  dt=  36.8ms  words=70,844,416
[E06   909/1548 G   8648|CLM] train=3.8564  mask=13.0%  norm=0.835  lr=8.21e-05  dt=  37.0ms  words=70,852,608
[E06   910/1548 G   8649|CLM] train=2.3607  mask=13.0%  norm=0.768  lr=8.21e-05  dt=  37.3ms  words=70,860,800
[E06   911/1548 G   8650|CLM] train=2.8008  mask=13.0%  norm=0.727  lr=8.20e-05  dt=  37.0ms  words=70,868,992
[E06   912/1548 G   8651|CLM] train=2.5735  mask=13.0%  norm=0.712  lr=8.20e-05  dt=  37.3ms  words=70,877,184
[E06   913/1548 G   8652|CLM] train=4.3337  mask=13.0%  norm=0.923  lr=8.20e-05  dt=  37.2ms  words=70,885,376
[E06   914/1548 G   8653|CLM] train=2.0633  mask=13.0%  norm=0.732  lr=8.19e-05  dt=  37.1ms  words=70,893,568
[E06   915/1548 G   8654|CLM] train=2.1136  mask=13.0%  norm=0.658  lr=8.19e-05  dt=  36.8ms  words=70,901,760
[E06   916/1548 G   8655|CLM] train=2.7394  mask=13.0%  norm=0.698  lr=8.19e-05  dt=  36.9ms  words=70,909,952
[E06   917/1548 G   8656|CLM] train=4.6695  mask=13.0%  norm=1.009  lr=8.18e-05  dt=  37.0ms  words=70,918,144
[E06   918/1548 G   8657|CLM] train=3.9296  mask=13.0%  norm=0.923  lr=8.18e-05  dt=  36.9ms  words=70,926,336
[E06   919/1548 G   8658|CLM] train=3.7420  mask=13.0%  norm=0.940  lr=8.18e-05  dt=  36.9ms  words=70,934,528
[E06   920/1548 G   8659|CLM] train=3.9150  mask=13.0%  norm=0.869  lr=8.17e-05  dt=  37.0ms  words=70,942,720
[E06   921/1548 G   8660|CLM] train=4.7881  mask=13.0%  norm=1.213  lr=8.17e-05  dt=  37.0ms  words=70,950,912
[E06   922/1548 G   8661|CLM] train=4.6054  mask=13.0%  norm=1.010  lr=8.17e-05  dt=  36.9ms  words=70,959,104
[E06   923/1548 G   8662|CLM] train=3.7609  mask=13.0%  norm=0.849  lr=8.16e-05  dt=  36.8ms  words=70,967,296
[E06   924/1548 G   8663|CLM] train=3.6788  mask=13.0%  norm=0.801  lr=8.16e-05  dt=  37.0ms  words=70,975,488
[E06   925/1548 G   8664|CLM] train=3.6081  mask=13.0%  norm=0.796  lr=8.16e-05  dt=  36.9ms  words=70,983,680
[E06   926/1548 G   8665|CLM] train=2.0655  mask=13.0%  norm=0.717  lr=8.15e-05  dt=  36.8ms  words=70,991,872
[E06   927/1548 G   8666|CLM] train=3.7911  mask=13.0%  norm=0.889  lr=8.15e-05  dt=  36.8ms  words=71,000,064
[E06   928/1548 G   8667|CLM] train=4.0666  mask=13.0%  norm=0.833  lr=8.15e-05  dt=  36.9ms  words=71,008,256
[E06   929/1548 G   8668|CLM] train=3.9270  mask=13.0%  norm=1.064  lr=8.14e-05  dt=  37.0ms  words=71,016,448
[E06   930/1548 G   8669|CLM] train=4.5051  mask=13.0%  norm=0.873  lr=8.14e-05  dt=  37.2ms  words=71,024,640
[E06   931/1548 G   8670|CLM] train=4.2195  mask=13.0%  norm=0.821  lr=8.14e-05  dt=  37.0ms  words=71,032,832
[E06   932/1548 G   8671|CLM] train=3.9541  mask=13.0%  norm=0.777  lr=8.13e-05  dt=  36.9ms  words=71,041,024
[E06   933/1548 G   8672|CLM] train=4.1795  mask=13.0%  norm=0.766  lr=8.13e-05  dt=  37.4ms  words=71,049,216
[E06   934/1548 G   8673|CLM] train=2.2443  mask=13.0%  norm=0.717  lr=8.13e-05  dt=  37.1ms  words=71,057,408
[E06   935/1548 G   8674|CLM] train=4.1006  mask=13.0%  norm=0.958  lr=8.12e-05  dt=  37.4ms  words=71,065,600
[E06   936/1548 G   8675|CLM] train=4.3075  mask=13.0%  norm=0.903  lr=8.12e-05  dt=  37.1ms  words=71,073,792
[E06   937/1548 G   8676|CLM] train=1.9858  mask=13.0%  norm=0.749  lr=8.12e-05  dt=  37.0ms  words=71,081,984
[E06   938/1548 G   8677|CLM] train=2.4368  mask=13.0%  norm=0.755  lr=8.11e-05  dt=  36.9ms  words=71,090,176
[E06   939/1548 G   8678|CLM] train=2.0211  mask=13.0%  norm=0.693  lr=8.11e-05  dt=  37.2ms  words=71,098,368
[E06   940/1548 G   8679|CLM] train=4.5083  mask=13.0%  norm=1.005  lr=8.11e-05  dt=  36.9ms  words=71,106,560
[E06   941/1548 G   8680|CLM] train=4.3851  mask=13.0%  norm=1.100  lr=8.11e-05  dt=  36.8ms  words=71,114,752
[E06   942/1548 G   8681|CLM] train=2.1376  mask=13.0%  norm=0.725  lr=8.10e-05  dt=  36.8ms  words=71,122,944
[E06   943/1548 G   8682|CLM] train=4.2359  mask=13.0%  norm=0.789  lr=8.10e-05  dt=  36.9ms  words=71,131,136
[E06   944/1548 G   8683|CLM] train=4.0893  mask=13.0%  norm=0.833  lr=8.10e-05  dt=  37.9ms  words=71,139,328
[E06   945/1548 G   8684|CLM] train=2.6909  mask=13.0%  norm=0.778  lr=8.09e-05  dt=  36.9ms  words=71,147,520
[E06   946/1548 G   8685|CLM] train=4.6230  mask=13.0%  norm=1.065  lr=8.09e-05  dt=  37.1ms  words=71,155,712
[E06   947/1548 G   8686|CLM] train=3.8355  mask=13.0%  norm=0.807  lr=8.09e-05  dt=  36.9ms  words=71,163,904
[E06   948/1548 G   8687|CLM] train=4.4386  mask=13.0%  norm=0.821  lr=8.08e-05  dt=  36.7ms  words=71,172,096
[E06   949/1548 G   8688|CLM] train=4.4672  mask=13.0%  norm=0.897  lr=8.08e-05  dt=  36.9ms  words=71,180,288
[E06   950/1548 G   8689|CLM] train=4.1895  mask=13.0%  norm=0.835  lr=8.08e-05  dt=  36.9ms  words=71,188,480
[E06   951/1548 G   8690|CLM] train=3.6165  mask=13.0%  norm=0.819  lr=8.07e-05  dt=  36.9ms  words=71,196,672
[E06   952/1548 G   8691|CLM] train=2.1981  mask=13.0%  norm=0.914  lr=8.07e-05  dt=  36.9ms  words=71,204,864
[E06   953/1548 G   8692|CLM] train=4.3920  mask=13.0%  norm=0.799  lr=8.07e-05  dt=  37.0ms  words=71,213,056
[E06   954/1548 G   8693|CLM] train=2.3165  mask=13.0%  norm=0.642  lr=8.06e-05  dt=  37.0ms  words=71,221,248
[E06   955/1548 G   8694|CLM] train=2.4386  mask=13.0%  norm=0.688  lr=8.06e-05  dt=  37.0ms  words=71,229,440
[E06   956/1548 G   8695|CLM] train=4.3846  mask=13.0%  norm=1.088  lr=8.06e-05  dt=  36.9ms  words=71,237,632
[E06   957/1548 G   8696|CLM] train=1.9410  mask=13.0%  norm=0.831  lr=8.05e-05  dt=  36.9ms  words=71,245,824
[E06   958/1548 G   8697|CLM] train=4.7182  mask=13.0%  norm=0.990  lr=8.05e-05  dt=  36.9ms  words=71,254,016
[E06   959/1548 G   8698|CLM] train=3.8097  mask=13.0%  norm=1.000  lr=8.05e-05  dt=  36.9ms  words=71,262,208
[E06   960/1548 G   8699|CLM] train=4.5380  mask=13.0%  norm=0.913  lr=8.04e-05  dt=  36.9ms  words=71,270,400
[E06   961/1548 G   8700|CLM] train=4.0171  mask=13.0%  norm=0.807  lr=8.04e-05  dt=  36.9ms  words=71,278,592
[E06   962/1548 G   8701|CLM] train=2.1094  mask=13.0%  norm=0.822  lr=8.04e-05  dt=  36.9ms  words=71,286,784
[E06   963/1548 G   8702|CLM] train=4.4425  mask=13.0%  norm=1.131  lr=8.03e-05  dt=  36.9ms  words=71,294,976
[E06   964/1548 G   8703|CLM] train=4.5159  mask=13.0%  norm=0.825  lr=8.03e-05  dt=  36.9ms  words=71,303,168
[E06   965/1548 G   8704|CLM] train=3.9359  mask=13.0%  norm=0.786  lr=8.03e-05  dt=  37.5ms  words=71,311,360
[E06   966/1548 G   8705|CLM] train=2.3509  mask=13.0%  norm=0.720  lr=8.02e-05  dt=  39.5ms  words=71,319,552
[E06   967/1548 G   8706|CLM] train=2.1714  mask=13.0%  norm=0.660  lr=8.02e-05  dt=  38.9ms  words=71,327,744
[E06   968/1548 G   8707|CLM] train=4.3089  mask=13.0%  norm=0.882  lr=8.02e-05  dt=  37.2ms  words=71,335,936
[E06   969/1548 G   8708|CLM] train=2.3207  mask=13.0%  norm=0.782  lr=8.01e-05  dt=  37.1ms  words=71,344,128
[E06   970/1548 G   8709|CLM] train=3.9530  mask=13.0%  norm=0.943  lr=8.01e-05  dt=  36.7ms  words=71,352,320
[E06   971/1548 G   8710|CLM] train=3.8700  mask=13.0%  norm=0.903  lr=8.01e-05  dt=  36.8ms  words=71,360,512
[E06   972/1548 G   8711|CLM] train=3.9300  mask=13.0%  norm=0.847  lr=8.00e-05  dt=  36.9ms  words=71,368,704
[E06   973/1548 G   8712|CLM] train=2.7345  mask=13.0%  norm=2.091  lr=8.00e-05  dt=  37.0ms  words=71,376,896
[E06   974/1548 G   8713|CLM] train=1.7359  mask=13.0%  norm=0.793  lr=8.00e-05  dt=  36.8ms  words=71,385,088
[E06   975/1548 G   8714|CLM] train=4.2820  mask=13.0%  norm=0.991  lr=7.99e-05  dt=  36.8ms  words=71,393,280
[E06   976/1548 G   8715|CLM] train=4.0941  mask=13.0%  norm=0.815  lr=7.99e-05  dt=  36.9ms  words=71,401,472
[E06   977/1548 G   8716|CLM] train=4.1689  mask=13.0%  norm=0.891  lr=7.99e-05  dt=  37.0ms  words=71,409,664
[E06   978/1548 G   8717|CLM] train=5.0910  mask=13.0%  norm=4.422  lr=7.98e-05  dt=  36.8ms  words=71,417,856
[E06   979/1548 G   8718|CLM] train=3.9544  mask=13.0%  norm=0.865  lr=7.98e-05  dt=  37.0ms  words=71,426,048
[E06   980/1548 G   8719|CLM] train=4.1458  mask=13.0%  norm=1.091  lr=7.98e-05  dt=  36.9ms  words=71,434,240
[E06   981/1548 G   8720|CLM] train=4.3638  mask=13.0%  norm=0.973  lr=7.98e-05  dt=  37.1ms  words=71,442,432
[E06   982/1548 G   8721|CLM] train=4.2915  mask=13.0%  norm=0.817  lr=7.97e-05  dt=  36.9ms  words=71,450,624
[E06   983/1548 G   8722|CLM] train=4.2017  mask=13.0%  norm=0.955  lr=7.97e-05  dt=  36.8ms  words=71,458,816
[E06   984/1548 G   8723|CLM] train=3.8154  mask=13.0%  norm=0.750  lr=7.97e-05  dt=  36.9ms  words=71,467,008
[E06   985/1548 G   8724|CLM] train=4.3683  mask=13.0%  norm=1.163  lr=7.96e-05  dt=  37.0ms  words=71,475,200
[E06   986/1548 G   8725|CLM] train=4.1105  mask=13.0%  norm=0.925  lr=7.96e-05  dt=  36.9ms  words=71,483,392
[E06   987/1548 G   8726|CLM] train=2.2789  mask=13.0%  norm=0.955  lr=7.96e-05  dt=  37.0ms  words=71,491,584
[E06   988/1548 G   8727|CLM] train=2.5054  mask=13.0%  norm=0.750  lr=7.95e-05  dt=  36.9ms  words=71,499,776
[E06   989/1548 G   8728|CLM] train=2.2309  mask=13.0%  norm=0.883  lr=7.95e-05  dt=  37.0ms  words=71,507,968
[E06   990/1548 G   8729|CLM] train=1.8801  mask=13.0%  norm=0.691  lr=7.95e-05  dt=  36.9ms  words=71,516,160
[E06   991/1548 G   8730|CLM] train=4.3427  mask=13.0%  norm=0.866  lr=7.94e-05  dt=  36.9ms  words=71,524,352
[E06   992/1548 G   8731|CLM] train=4.0783  mask=12.9%  norm=0.933  lr=7.94e-05  dt=  36.8ms  words=71,532,544
[E06   993/1548 G   8732|CLM] train=2.4521  mask=12.9%  norm=1.580  lr=7.94e-05  dt=  37.2ms  words=71,540,736
[E06   994/1548 G   8733|CLM] train=3.3901  mask=12.9%  norm=0.848  lr=7.93e-05  dt=  36.9ms  words=71,548,928
[E06   995/1548 G   8734|CLM] train=3.7239  mask=12.9%  norm=0.813  lr=7.93e-05  dt=  36.8ms  words=71,557,120
[E06   996/1548 G   8735|CLM] train=2.2397  mask=12.9%  norm=0.745  lr=7.93e-05  dt=  36.9ms  words=71,565,312
[E06   997/1548 G   8736|CLM] train=2.1004  mask=12.9%  norm=0.833  lr=7.92e-05  dt=  37.0ms  words=71,573,504
[E06   998/1548 G   8737|CLM] train=3.9518  mask=12.9%  norm=0.831  lr=7.92e-05  dt=  36.8ms  words=71,581,696
[E06   999/1548 G   8738|CLM] train=3.4291  mask=12.9%  norm=0.891  lr=7.92e-05  dt=  36.9ms  words=71,589,888
[E06  1000/1548 G   8739|CLM] train=4.6200  mask=12.9%  norm=0.838  lr=7.91e-05  dt=  37.1ms  words=71,598,080
[E06  1001/1548 G   8740|CLM] train=1.9257  mask=12.9%  norm=0.786  lr=7.91e-05  dt=  37.0ms  words=71,606,272
[E06  1002/1548 G   8741|CLM] train=2.7126  mask=12.9%  norm=0.752  lr=7.91e-05  dt=  36.7ms  words=71,614,464
[E06  1003/1548 G   8742|CLM] train=4.8465  mask=12.9%  norm=1.161  lr=7.90e-05  dt=  36.9ms  words=71,622,656
[E06  1004/1548 G   8743|CLM] train=4.4291  mask=12.9%  norm=1.102  lr=7.90e-05  dt=  36.9ms  words=71,630,848
[E06  1005/1548 G   8744|CLM] train=3.4873  mask=12.9%  norm=1.063  lr=7.90e-05  dt=  37.0ms  words=71,639,040
[E06  1006/1548 G   8745|CLM] train=2.9349  mask=12.9%  norm=0.874  lr=7.89e-05  dt=  36.8ms  words=71,647,232
[E06  1007/1548 G   8746|CLM] train=4.2365  mask=12.9%  norm=0.797  lr=7.89e-05  dt=  36.8ms  words=71,655,424
[E06  1008/1548 G   8747|CLM] train=2.1757  mask=12.9%  norm=0.666  lr=7.89e-05  dt=  36.9ms  words=71,663,616
[E06  1009/1548 G   8748|CLM] train=5.3811  mask=12.9%  norm=1.869  lr=7.88e-05  dt=  37.0ms  words=71,671,808
[E06  1010/1548 G   8749|CLM] train=3.9257  mask=12.9%  norm=0.939  lr=7.88e-05  dt=  36.9ms  words=71,680,000
[E06  1011/1548 G   8750|CLM] train=4.2515  mask=12.9%  norm=0.886  lr=7.88e-05  dt=  36.9ms  words=71,688,192
[E06  1012/1548 G   8751|CLM] train=4.2811  mask=12.9%  norm=0.894  lr=7.87e-05  dt=  36.9ms  words=71,696,384
[E06  1013/1548 G   8752|CLM] train=2.5253  mask=12.9%  norm=0.676  lr=7.87e-05  dt=  37.0ms  words=71,704,576
[E06  1014/1548 G   8753|CLM] train=2.5482  mask=12.9%  norm=0.695  lr=7.87e-05  dt=  36.9ms  words=71,712,768
[E06  1015/1548 G   8754|CLM] train=4.3522  mask=12.9%  norm=0.890  lr=7.87e-05  dt=  36.8ms  words=71,720,960
[E06  1016/1548 G   8755|CLM] train=4.3366  mask=12.9%  norm=0.941  lr=7.86e-05  dt=  36.9ms  words=71,729,152
[E06  1017/1548 G   8756|CLM] train=4.2748  mask=12.9%  norm=0.859  lr=7.86e-05  dt=  37.1ms  words=71,737,344
[E06  1018/1548 G   8757|CLM] train=3.3416  mask=12.9%  norm=0.919  lr=7.86e-05  dt=  36.8ms  words=71,745,536
[E06  1019/1548 G   8758|CLM] train=4.1550  mask=12.9%  norm=0.864  lr=7.85e-05  dt=  36.9ms  words=71,753,728
[E06  1020/1548 G   8759|CLM] train=2.0806  mask=12.9%  norm=0.792  lr=7.85e-05  dt=  37.3ms  words=71,761,920
[E06  1021/1548 G   8760|CLM] train=4.1635  mask=12.9%  norm=0.970  lr=7.85e-05  dt=  37.1ms  words=71,770,112
[E06  1022/1548 G   8761|CLM] train=3.5857  mask=12.9%  norm=0.774  lr=7.84e-05  dt=  36.9ms  words=71,778,304
[E06  1023/1548 G   8762|CLM] train=2.3335  mask=12.9%  norm=0.745  lr=7.84e-05  dt=  36.9ms  words=71,786,496
[E06  1024/1548 G   8763|CLM] train=4.2172  mask=12.9%  norm=1.172  lr=7.84e-05  dt=  36.7ms  words=71,794,688
[E06  1025/1548 G   8764|CLM] train=4.2465  mask=12.9%  norm=0.814  lr=7.83e-05  dt=  37.0ms  words=71,802,880
[E06  1026/1548 G   8765|CLM] train=2.6263  mask=12.9%  norm=0.821  lr=7.83e-05  dt=  36.8ms  words=71,811,072
[E06  1027/1548 G   8766|CLM] train=3.7629  mask=12.9%  norm=0.822  lr=7.83e-05  dt=  36.9ms  words=71,819,264
[E06  1028/1548 G   8767|CLM] train=2.4563  mask=12.9%  norm=0.718  lr=7.82e-05  dt=  36.9ms  words=71,827,456
[E06  1029/1548 G   8768|CLM] train=2.7306  mask=12.9%  norm=0.761  lr=7.82e-05  dt=  37.0ms  words=71,835,648
[E06  1030/1548 G   8769|CLM] train=2.2874  mask=12.9%  norm=0.668  lr=7.82e-05  dt=  36.9ms  words=71,843,840
[E06  1031/1548 G   8770|CLM] train=4.0562  mask=12.9%  norm=0.871  lr=7.81e-05  dt=  36.8ms  words=71,852,032
[E06  1032/1548 G   8771|CLM] train=4.6938  mask=12.9%  norm=1.128  lr=7.81e-05  dt=  36.9ms  words=71,860,224
[E06  1033/1548 G   8772|CLM] train=3.6991  mask=12.9%  norm=0.926  lr=7.81e-05  dt=  36.9ms  words=71,868,416
[E06  1034/1548 G   8773|CLM] train=3.7480  mask=12.9%  norm=0.735  lr=7.80e-05  dt=  36.9ms  words=71,876,608
[E06  1035/1548 G   8774|CLM] train=4.7328  mask=12.9%  norm=0.958  lr=7.80e-05  dt=  36.8ms  words=71,884,800
[E06  1036/1548 G   8775|CLM] train=2.3330  mask=12.9%  norm=0.799  lr=7.80e-05  dt=  37.0ms  words=71,892,992
[E06  1037/1548 G   8776|CLM] train=4.4494  mask=12.9%  norm=0.809  lr=7.79e-05  dt=  37.0ms  words=71,901,184
[E06  1038/1548 G   8777|CLM] train=4.0237  mask=12.9%  norm=0.878  lr=7.79e-05  dt=  36.8ms  words=71,909,376
[E06  1039/1548 G   8778|CLM] train=1.6687  mask=12.9%  norm=0.652  lr=7.79e-05  dt=  36.8ms  words=71,917,568
[E06  1040/1548 G   8779|CLM] train=2.4674  mask=12.9%  norm=0.706  lr=7.78e-05  dt=  36.9ms  words=71,925,760
[E06  1041/1548 G   8780|CLM] train=2.0614  mask=12.9%  norm=0.821  lr=7.78e-05  dt=  37.2ms  words=71,933,952
[E06  1042/1548 G   8781|CLM] train=2.2647  mask=12.9%  norm=0.670  lr=7.78e-05  dt=  36.8ms  words=71,942,144
[E06  1043/1548 G   8782|CLM] train=2.4766  mask=12.9%  norm=0.679  lr=7.78e-05  dt=  36.8ms  words=71,950,336
[E06  1044/1548 G   8783|CLM] train=2.0605  mask=12.9%  norm=0.718  lr=7.77e-05  dt=  36.8ms  words=71,958,528
[E06  1045/1548 G   8784|CLM] train=3.9745  mask=12.9%  norm=0.876  lr=7.77e-05  dt=  37.0ms  words=71,966,720
[E06  1046/1548 G   8785|CLM] train=2.1897  mask=12.9%  norm=0.793  lr=7.77e-05  dt=  36.9ms  words=71,974,912
[E06  1047/1548 G   8786|CLM] train=2.3405  mask=12.9%  norm=0.671  lr=7.76e-05  dt=  37.0ms  words=71,983,104
[E06  1048/1548 G   8787|CLM] train=3.9767  mask=12.9%  norm=1.037  lr=7.76e-05  dt=  36.9ms  words=71,991,296
[E06  1049/1548 G   8788|CLM] train=4.0195  mask=12.9%  norm=0.919  lr=7.76e-05  dt=  37.0ms  words=71,999,488
[E06  1050/1548 G   8789|CLM] train=2.2911  mask=12.9%  norm=0.644  lr=7.75e-05  dt=  36.9ms  words=72,007,680
[E06  1051/1548 G   8790|CLM] train=4.2531  mask=12.9%  norm=0.999  lr=7.75e-05  dt=  36.8ms  words=72,015,872
[E06  1052/1548 G   8791|CLM] train=2.1924  mask=12.9%  norm=0.777  lr=7.75e-05  dt=  36.9ms  words=72,024,064
[E06  1053/1548 G   8792|CLM] train=4.3086  mask=12.9%  norm=0.884  lr=7.74e-05  dt=  37.0ms  words=72,032,256
[E06  1054/1548 G   8793|CLM] train=3.9119  mask=12.9%  norm=0.791  lr=7.74e-05  dt=  36.9ms  words=72,040,448
[E06  1055/1548 G   8794|CLM] train=2.1208  mask=12.9%  norm=0.700  lr=7.74e-05  dt=  36.8ms  words=72,048,640
[E06  1056/1548 G   8795|CLM] train=4.0717  mask=12.9%  norm=0.848  lr=7.73e-05  dt=  36.9ms  words=72,056,832
[E06  1057/1548 G   8796|CLM] train=4.2533  mask=12.9%  norm=0.898  lr=7.73e-05  dt=  37.0ms  words=72,065,024
[E06  1058/1548 G   8797|CLM] train=4.0635  mask=12.9%  norm=1.013  lr=7.73e-05  dt=  36.8ms  words=72,073,216
[E06  1059/1548 G   8798|CLM] train=4.8415  mask=12.9%  norm=0.868  lr=7.72e-05  dt=  36.9ms  words=72,081,408
[E06  1060/1548 G   8799|CLM] train=5.0282  mask=12.9%  norm=1.148  lr=7.72e-05  dt=  36.9ms  words=72,089,600
[E06  1061/1548 G   8800|CLM] train=2.0751  mask=12.9%  norm=0.635  lr=7.72e-05  dt=  37.0ms  words=72,097,792
[E06  1062/1548 G   8801|CLM] train=4.5272  mask=12.9%  norm=0.912  lr=7.71e-05  dt=  36.9ms  words=72,105,984
[E06  1063/1548 G   8802|CLM] train=3.6250  mask=12.9%  norm=0.878  lr=7.71e-05  dt=  36.8ms  words=72,114,176
[E06  1064/1548 G   8803|CLM] train=3.8422  mask=12.9%  norm=0.819  lr=7.71e-05  dt=  36.8ms  words=72,122,368
[E06  1065/1548 G   8804|CLM] train=3.7969  mask=12.9%  norm=0.837  lr=7.71e-05  dt=  36.9ms  words=72,130,560
[E06  1066/1548 G   8805|CLM] train=4.6896  mask=12.9%  norm=0.936  lr=7.70e-05  dt=  37.8ms  words=72,138,752
[E06  1067/1548 G   8806|CLM] train=3.9683  mask=12.9%  norm=0.761  lr=7.70e-05  dt=  36.7ms  words=72,146,944
[E06  1068/1548 G   8807|CLM] train=4.4747  mask=12.9%  norm=1.074  lr=7.70e-05  dt=  36.9ms  words=72,155,136
[E06  1069/1548 G   8808|CLM] train=4.3085  mask=12.9%  norm=1.071  lr=7.69e-05  dt=  36.9ms  words=72,163,328
[E06  1070/1548 G   8809|CLM] train=3.8292  mask=12.9%  norm=0.858  lr=7.69e-05  dt=  36.8ms  words=72,171,520
[E06  1071/1548 G   8810|CLM] train=3.7580  mask=12.9%  norm=0.737  lr=7.69e-05  dt=  36.9ms  words=72,179,712
[E06  1072/1548 G   8811|CLM] train=4.1477  mask=12.9%  norm=0.834  lr=7.68e-05  dt=  36.9ms  words=72,187,904
[E06  1073/1548 G   8812|CLM] train=4.3435  mask=12.9%  norm=0.891  lr=7.68e-05  dt=  37.6ms  words=72,196,096
[E06  1074/1548 G   8813|CLM] train=4.2914  mask=12.9%  norm=0.859  lr=7.68e-05  dt=  38.5ms  words=72,204,288
[E06  1075/1548 G   8814|CLM] train=4.1618  mask=12.9%  norm=0.976  lr=7.67e-05  dt=  37.9ms  words=72,212,480
[E06  1076/1548 G   8815|CLM] train=2.1826  mask=12.9%  norm=0.782  lr=7.67e-05  dt=  42.6ms  words=72,220,672
[E06  1077/1548 G   8816|CLM] train=3.8510  mask=12.9%  norm=0.846  lr=7.67e-05  dt=  36.9ms  words=72,228,864
[E06  1078/1548 G   8817|CLM] train=1.9372  mask=12.9%  norm=0.845  lr=7.66e-05  dt=  36.9ms  words=72,237,056
[E06  1079/1548 G   8818|CLM] train=3.6169  mask=12.9%  norm=0.927  lr=7.66e-05  dt=  37.0ms  words=72,245,248
[E06  1080/1548 G   8819|CLM] train=4.7134  mask=12.9%  norm=1.452  lr=7.66e-05  dt=  37.1ms  words=72,253,440
[E06  1081/1548 G   8820|CLM] train=3.5414  mask=12.9%  norm=0.749  lr=7.65e-05  dt=  36.9ms  words=72,261,632
[E06  1082/1548 G   8821|CLM] train=4.5877  mask=12.9%  norm=1.072  lr=7.65e-05  dt=  37.0ms  words=72,269,824
[E06  1083/1548 G   8822|CLM] train=4.0161  mask=12.9%  norm=0.901  lr=7.65e-05  dt=  36.8ms  words=72,278,016
[E06  1084/1548 G   8823|CLM] train=2.5544  mask=12.9%  norm=0.688  lr=7.64e-05  dt=  36.9ms  words=72,286,208
[E06  1085/1548 G   8824|CLM] train=5.0821  mask=12.9%  norm=0.964  lr=7.64e-05  dt=  36.8ms  words=72,294,400
[E06  1086/1548 G   8825|CLM] train=4.0942  mask=12.9%  norm=0.833  lr=7.64e-05  dt=  36.9ms  words=72,302,592
[E06  1087/1548 G   8826|CLM] train=3.7972  mask=12.9%  norm=0.811  lr=7.64e-05  dt=  37.0ms  words=72,310,784
[E06  1088/1548 G   8827|CLM] train=2.4155  mask=12.9%  norm=0.756  lr=7.63e-05  dt=  37.1ms  words=72,318,976
[E06  1089/1548 G   8828|CLM] train=2.3726  mask=12.9%  norm=0.628  lr=7.63e-05  dt=  37.0ms  words=72,327,168
[E06  1090/1548 G   8829|CLM] train=2.0348  mask=12.9%  norm=0.817  lr=7.63e-05  dt=  36.9ms  words=72,335,360
[E06  1091/1548 G   8830|CLM] train=2.6060  mask=12.9%  norm=0.720  lr=7.62e-05  dt=  36.9ms  words=72,343,552
[E06  1092/1548 G   8831|CLM] train=3.8334  mask=12.9%  norm=0.973  lr=7.62e-05  dt=  37.0ms  words=72,351,744
[E06  1093/1548 G   8832|CLM] train=2.2021  mask=12.9%  norm=0.777  lr=7.62e-05  dt=  37.0ms  words=72,359,936
[E06  1094/1548 G   8833|CLM] train=4.1366  mask=12.9%  norm=0.850  lr=7.61e-05  dt=  37.0ms  words=72,368,128
[E06  1095/1548 G   8834|CLM] train=3.6841  mask=12.9%  norm=0.865  lr=7.61e-05  dt=  37.2ms  words=72,376,320
[E06  1096/1548 G   8835|CLM] train=2.3874  mask=12.9%  norm=1.615  lr=7.61e-05  dt=  36.9ms  words=72,384,512
[E06  1097/1548 G   8836|CLM] train=4.7864  mask=12.9%  norm=1.071  lr=7.60e-05  dt=  37.0ms  words=72,392,704
[E06  1098/1548 G   8837|CLM] train=2.4076  mask=12.9%  norm=0.725  lr=7.60e-05  dt=  36.9ms  words=72,400,896
[E06  1099/1548 G   8838|CLM] train=4.2004  mask=12.9%  norm=0.840  lr=7.60e-05  dt=  37.0ms  words=72,409,088
[E06  1100/1548 G   8839|CLM] train=4.0727  mask=12.9%  norm=0.849  lr=7.59e-05  dt=  36.9ms  words=72,417,280
[E06  1101/1548 G   8840|CLM] train=4.0721  mask=12.9%  norm=0.889  lr=7.59e-05  dt=  37.0ms  words=72,425,472
[E06  1102/1548 G   8841|CLM] train=3.6112  mask=12.9%  norm=1.000  lr=7.59e-05  dt=  36.8ms  words=72,433,664
[E06  1103/1548 G   8842|CLM] train=4.1755  mask=12.9%  norm=0.865  lr=7.58e-05  dt=  37.0ms  words=72,441,856
[E06  1104/1548 G   8843|CLM] train=4.0927  mask=12.9%  norm=0.848  lr=7.58e-05  dt=  36.8ms  words=72,450,048
[E06  1105/1548 G   8844|CLM] train=4.9133  mask=12.9%  norm=1.730  lr=7.58e-05  dt=  36.9ms  words=72,458,240
[E06  1106/1548 G   8845|CLM] train=4.1012  mask=12.9%  norm=1.015  lr=7.57e-05  dt=  36.9ms  words=72,466,432
[E06  1107/1548 G   8846|CLM] train=2.3178  mask=12.9%  norm=0.688  lr=7.57e-05  dt=  37.0ms  words=72,474,624
[E06  1108/1548 G   8847|CLM] train=4.3902  mask=12.9%  norm=1.188  lr=7.57e-05  dt=  37.0ms  words=72,482,816
[E06  1109/1548 G   8848|CLM] train=3.8129  mask=12.9%  norm=0.866  lr=7.57e-05  dt=  37.1ms  words=72,491,008
[E06  1110/1548 G   8849|CLM] train=4.3020  mask=12.9%  norm=0.987  lr=7.56e-05  dt=  36.9ms  words=72,499,200
[E06  1111/1548 G   8850|CLM] train=2.2111  mask=12.9%  norm=0.967  lr=7.56e-05  dt=  37.1ms  words=72,507,392
[E06  1112/1548 G   8851|CLM] train=4.1259  mask=12.9%  norm=0.825  lr=7.56e-05  dt=  36.9ms  words=72,515,584
[E06  1113/1548 G   8852|CLM] train=3.8223  mask=12.9%  norm=0.796  lr=7.55e-05  dt=  36.8ms  words=72,523,776
[E06  1114/1548 G   8853|CLM] train=4.0830  mask=12.9%  norm=0.848  lr=7.55e-05  dt=  36.8ms  words=72,531,968
[E06  1115/1548 G   8854|CLM] train=2.2332  mask=12.9%  norm=0.801  lr=7.55e-05  dt=  37.1ms  words=72,540,160
[E06  1116/1548 G   8855|CLM] train=4.0377  mask=12.8%  norm=1.053  lr=7.54e-05  dt=  36.9ms  words=72,548,352
[E06  1117/1548 G   8856|CLM] train=4.0534  mask=12.8%  norm=0.952  lr=7.54e-05  dt=  36.9ms  words=72,556,544
[E06  1118/1548 G   8857|CLM] train=2.2630  mask=12.8%  norm=0.733  lr=7.54e-05  dt=  36.8ms  words=72,564,736
[E06  1119/1548 G   8858|CLM] train=1.9515  mask=12.8%  norm=0.714  lr=7.53e-05  dt=  37.0ms  words=72,572,928
[E06  1120/1548 G   8859|CLM] train=3.8586  mask=12.8%  norm=0.778  lr=7.53e-05  dt=  36.8ms  words=72,581,120
[E06  1121/1548 G   8860|CLM] train=2.1423  mask=12.8%  norm=0.731  lr=7.53e-05  dt=  37.0ms  words=72,589,312
[E06  1122/1548 G   8861|CLM] train=2.6314  mask=12.8%  norm=0.747  lr=7.52e-05  dt=  37.0ms  words=72,597,504
[E06  1123/1548 G   8862|CLM] train=4.3137  mask=12.8%  norm=0.836  lr=7.52e-05  dt=  37.1ms  words=72,605,696
[E06  1124/1548 G   8863|CLM] train=2.7253  mask=12.8%  norm=0.656  lr=7.52e-05  dt=  36.8ms  words=72,613,888
[E06  1125/1548 G   8864|CLM] train=4.9880  mask=12.8%  norm=0.942  lr=7.51e-05  dt=  36.9ms  words=72,622,080
[E06  1126/1548 G   8865|CLM] train=3.5668  mask=12.8%  norm=0.918  lr=7.51e-05  dt=  36.9ms  words=72,630,272
[E06  1127/1548 G   8866|CLM] train=3.8985  mask=12.8%  norm=1.217  lr=7.51e-05  dt=  36.9ms  words=72,638,464
[E06  1128/1548 G   8867|CLM] train=4.0261  mask=12.8%  norm=0.808  lr=7.51e-05  dt=  37.0ms  words=72,646,656
[E06  1129/1548 G   8868|CLM] train=2.0889  mask=12.8%  norm=0.768  lr=7.50e-05  dt=  36.9ms  words=72,654,848
[E06  1130/1548 G   8869|CLM] train=4.0154  mask=12.8%  norm=1.058  lr=7.50e-05  dt=  36.9ms  words=72,663,040
[E06  1131/1548 G   8870|CLM] train=4.2578  mask=12.8%  norm=0.924  lr=7.50e-05  dt=  36.9ms  words=72,671,232
[E06  1132/1548 G   8871|CLM] train=2.4964  mask=12.8%  norm=0.712  lr=7.49e-05  dt=  36.7ms  words=72,679,424
[E06  1133/1548 G   8872|CLM] train=2.2676  mask=12.8%  norm=0.699  lr=7.49e-05  dt=  36.9ms  words=72,687,616
[E06  1134/1548 G   8873|CLM] train=2.4252  mask=12.8%  norm=0.810  lr=7.49e-05  dt=  36.9ms  words=72,695,808
[E06  1135/1548 G   8874|CLM] train=2.4210  mask=12.8%  norm=0.672  lr=7.48e-05  dt=  37.1ms  words=72,704,000
[E06  1136/1548 G   8875|CLM] train=2.4433  mask=12.8%  norm=1.402  lr=7.48e-05  dt=  36.9ms  words=72,712,192
[E06  1137/1548 G   8876|CLM] train=3.8472  mask=12.8%  norm=0.842  lr=7.48e-05  dt=  36.9ms  words=72,720,384
[E06  1138/1548 G   8877|CLM] train=4.1952  mask=12.8%  norm=0.902  lr=7.47e-05  dt=  36.9ms  words=72,728,576
[E06  1139/1548 G   8878|CLM] train=3.6378  mask=12.8%  norm=0.756  lr=7.47e-05  dt=  36.9ms  words=72,736,768
[E06  1140/1548 G   8879|CLM] train=3.9734  mask=12.8%  norm=0.934  lr=7.47e-05  dt=  36.9ms  words=72,744,960
[E06  1141/1548 G   8880|CLM] train=2.2364  mask=12.8%  norm=0.691  lr=7.46e-05  dt=  36.9ms  words=72,753,152
[E06  1142/1548 G   8881|CLM] train=4.4886  mask=12.8%  norm=1.468  lr=7.46e-05  dt=  37.0ms  words=72,761,344
[E06  1143/1548 G   8882|CLM] train=4.5420  mask=12.8%  norm=1.008  lr=7.46e-05  dt=  37.0ms  words=72,769,536
[E06  1144/1548 G   8883|CLM] train=2.6808  mask=12.8%  norm=0.756  lr=7.45e-05  dt=  36.8ms  words=72,777,728
[E06  1145/1548 G   8884|CLM] train=3.6320  mask=12.8%  norm=0.774  lr=7.45e-05  dt=  36.8ms  words=72,785,920
[E06  1146/1548 G   8885|CLM] train=3.8419  mask=12.8%  norm=0.931  lr=7.45e-05  dt=  36.8ms  words=72,794,112
[E06  1147/1548 G   8886|CLM] train=4.5967  mask=12.8%  norm=1.146  lr=7.45e-05  dt=  36.9ms  words=72,802,304
[E06  1148/1548 G   8887|CLM] train=3.7285  mask=12.8%  norm=0.795  lr=7.44e-05  dt=  36.9ms  words=72,810,496
[E06  1149/1548 G   8888|CLM] train=1.4816  mask=12.8%  norm=0.599  lr=7.44e-05  dt=  37.2ms  words=72,818,688
[E06  1150/1548 G   8889|CLM] train=2.4837  mask=12.8%  norm=0.708  lr=7.44e-05  dt=  36.9ms  words=72,826,880
[E06  1151/1548 G   8890|CLM] train=4.2611  mask=12.8%  norm=0.894  lr=7.43e-05  dt=  36.9ms  words=72,835,072
[E06  1152/1548 G   8891|CLM] train=2.1263  mask=12.8%  norm=0.687  lr=7.43e-05  dt=  36.8ms  words=72,843,264
[E06  1153/1548 G   8892|CLM] train=3.3736  mask=12.8%  norm=0.811  lr=7.43e-05  dt=  36.9ms  words=72,851,456
[E06  1154/1548 G   8893|CLM] train=4.6611  mask=12.8%  norm=1.817  lr=7.42e-05  dt=  36.9ms  words=72,859,648
[E06  1155/1548 G   8894|CLM] train=4.5220  mask=12.8%  norm=1.595  lr=7.42e-05  dt=  37.1ms  words=72,867,840
[E06  1156/1548 G   8895|CLM] train=3.7537  mask=12.8%  norm=0.794  lr=7.42e-05  dt=  36.9ms  words=72,876,032
[E06  1157/1548 G   8896|CLM] train=4.2291  mask=12.8%  norm=1.072  lr=7.41e-05  dt=  36.9ms  words=72,884,224
[E06  1158/1548 G   8897|CLM] train=4.5985  mask=12.8%  norm=0.976  lr=7.41e-05  dt=  36.9ms  words=72,892,416
[E06  1159/1548 G   8898|CLM] train=4.0981  mask=12.8%  norm=0.834  lr=7.41e-05  dt=  37.1ms  words=72,900,608
[E06  1160/1548 G   8899|CLM] train=2.1701  mask=12.8%  norm=0.750  lr=7.40e-05  dt=  36.8ms  words=72,908,800
[E06  1161/1548 G   8900|CLM] train=2.0853  mask=12.8%  norm=0.767  lr=7.40e-05  dt=  36.9ms  words=72,916,992
[E06  1162/1548 G   8901|CLM] train=1.9727  mask=12.8%  norm=0.776  lr=7.40e-05  dt=  37.0ms  words=72,925,184
[E06  1163/1548 G   8902|CLM] train=4.1860  mask=12.8%  norm=1.402  lr=7.40e-05  dt=  37.1ms  words=72,933,376
[E06  1164/1548 G   8903|CLM] train=2.0954  mask=12.8%  norm=0.791  lr=7.39e-05  dt=  36.9ms  words=72,941,568
[E06  1165/1548 G   8904|CLM] train=4.1288  mask=12.8%  norm=0.918  lr=7.39e-05  dt=  37.0ms  words=72,949,760
[E06  1166/1548 G   8905|CLM] train=1.9852  mask=12.8%  norm=0.715  lr=7.39e-05  dt=  36.7ms  words=72,957,952
[E06  1167/1548 G   8906|CLM] train=2.2801  mask=12.8%  norm=0.747  lr=7.38e-05  dt=  37.0ms  words=72,966,144
[E06  1168/1548 G   8907|CLM] train=2.5452  mask=12.8%  norm=0.646  lr=7.38e-05  dt=  36.8ms  words=72,974,336
[E06  1169/1548 G   8908|CLM] train=4.2928  mask=12.8%  norm=0.970  lr=7.38e-05  dt=  36.9ms  words=72,982,528
[E06  1170/1548 G   8909|CLM] train=3.8485  mask=12.8%  norm=0.883  lr=7.37e-05  dt=  36.9ms  words=72,990,720
[E06  1171/1548 G   8910|CLM] train=2.8401  mask=12.8%  norm=0.767  lr=7.37e-05  dt=  37.0ms  words=72,998,912
[E06  1172/1548 G   8911|CLM] train=3.9939  mask=12.8%  norm=0.878  lr=7.37e-05  dt=  36.8ms  words=73,007,104
[E06  1173/1548 G   8912|CLM] train=2.2747  mask=12.8%  norm=0.722  lr=7.36e-05  dt=  37.0ms  words=73,015,296
[E06  1174/1548 G   8913|CLM] train=2.5870  mask=12.8%  norm=0.696  lr=7.36e-05  dt=  36.9ms  words=73,023,488
[E06  1175/1548 G   8914|CLM] train=4.2185  mask=12.8%  norm=0.907  lr=7.36e-05  dt=  37.2ms  words=73,031,680
[E06  1176/1548 G   8915|CLM] train=4.2728  mask=12.8%  norm=0.844  lr=7.35e-05  dt=  37.0ms  words=73,039,872
[E06  1177/1548 G   8916|CLM] train=3.6241  mask=12.8%  norm=0.821  lr=7.35e-05  dt=  36.8ms  words=73,048,064
[E06  1178/1548 G   8917|CLM] train=2.4393  mask=12.8%  norm=1.051  lr=7.35e-05  dt=  36.9ms  words=73,056,256
[E06  1179/1548 G   8918|CLM] train=4.1049  mask=12.8%  norm=0.883  lr=7.35e-05  dt=  37.2ms  words=73,064,448
[E06  1180/1548 G   8919|CLM] train=3.7695  mask=12.8%  norm=0.833  lr=7.34e-05  dt=  36.9ms  words=73,072,640
[E06  1181/1548 G   8920|CLM] train=2.3661  mask=12.8%  norm=0.703  lr=7.34e-05  dt=  37.1ms  words=73,080,832
[E06  1182/1548 G   8921|CLM] train=2.3264  mask=12.8%  norm=0.643  lr=7.34e-05  dt=  38.5ms  words=73,089,024
[E06  1183/1548 G   8922|CLM] train=3.8473  mask=12.8%  norm=0.719  lr=7.33e-05  dt=  46.0ms  words=73,097,216
[E06  1184/1548 G   8923|CLM] train=3.9235  mask=12.8%  norm=0.915  lr=7.33e-05  dt=  42.1ms  words=73,105,408
[E06  1185/1548 G   8924|CLM] train=3.4306  mask=12.8%  norm=0.735  lr=7.33e-05  dt=  37.1ms  words=73,113,600
[E06  1186/1548 G   8925|CLM] train=2.6060  mask=12.8%  norm=0.714  lr=7.32e-05  dt=  37.4ms  words=73,121,792
[E06  1187/1548 G   8926|CLM] train=4.9053  mask=12.8%  norm=0.973  lr=7.32e-05  dt=  36.9ms  words=73,129,984
[E06  1188/1548 G   8927|CLM] train=2.2597  mask=12.8%  norm=0.745  lr=7.32e-05  dt=  37.3ms  words=73,138,176
[E06  1189/1548 G   8928|CLM] train=4.0884  mask=12.8%  norm=0.898  lr=7.31e-05  dt=  37.0ms  words=73,146,368
[E06  1190/1548 G   8929|CLM] train=3.4863  mask=12.8%  norm=0.787  lr=7.31e-05  dt=  37.1ms  words=73,154,560
[E06  1191/1548 G   8930|CLM] train=4.2741  mask=12.8%  norm=0.930  lr=7.31e-05  dt=  37.3ms  words=73,162,752
[E06  1192/1548 G   8931|CLM] train=2.2654  mask=12.8%  norm=0.744  lr=7.30e-05  dt=  50.8ms  words=73,170,944
[E06  1193/1548 G   8932|CLM] train=3.6145  mask=12.8%  norm=0.825  lr=7.30e-05  dt=  37.7ms  words=73,179,136
[E06  1194/1548 G   8933|CLM] train=3.9015  mask=12.8%  norm=0.860  lr=7.30e-05  dt=  37.1ms  words=73,187,328
[E06  1195/1548 G   8934|CLM] train=4.2233  mask=12.8%  norm=0.792  lr=7.30e-05  dt=  40.7ms  words=73,195,520
[E06  1196/1548 G   8935|CLM] train=3.9403  mask=12.8%  norm=0.992  lr=7.29e-05  dt=  37.1ms  words=73,203,712
[E06  1197/1548 G   8936|CLM] train=2.5898  mask=12.8%  norm=0.652  lr=7.29e-05  dt=  37.2ms  words=73,211,904
[E06  1198/1548 G   8937|CLM] train=2.2026  mask=12.8%  norm=0.735  lr=7.29e-05  dt=  37.7ms  words=73,220,096
[E06  1199/1548 G   8938|CLM] train=3.8090  mask=12.8%  norm=0.915  lr=7.28e-05  dt=  37.6ms  words=73,228,288
[E06  1200/1548 G   8939|CLM] train=1.8954  mask=12.8%  norm=0.652  lr=7.28e-05  dt=  37.3ms  words=73,236,480
[E06  1201/1548 G   8940|CLM] train=3.7596  mask=12.8%  norm=0.854  lr=7.28e-05  dt=  37.8ms  words=73,244,672
[E06  1202/1548 G   8941|CLM] train=3.6196  mask=12.8%  norm=0.880  lr=7.27e-05  dt=  37.5ms  words=73,252,864
[E06  1203/1548 G   8942|CLM] train=4.0007  mask=12.8%  norm=0.824  lr=7.27e-05  dt=  41.7ms  words=73,261,056
[E06  1204/1548 G   8943|CLM] train=2.4840  mask=12.8%  norm=0.713  lr=7.27e-05  dt=  42.5ms  words=73,269,248
[E06  1205/1548 G   8944|CLM] train=2.3424  mask=12.8%  norm=0.706  lr=7.26e-05  dt=  42.2ms  words=73,277,440
[E06  1206/1548 G   8945|CLM] train=4.3424  mask=12.8%  norm=0.976  lr=7.26e-05  dt=  38.3ms  words=73,285,632
[E06  1207/1548 G   8946|CLM] train=2.5140  mask=12.8%  norm=0.717  lr=7.26e-05  dt=  39.3ms  words=73,293,824
[E06  1208/1548 G   8947|CLM] train=2.5950  mask=12.8%  norm=0.916  lr=7.26e-05  dt=  37.8ms  words=73,302,016
[E06  1209/1548 G   8948|CLM] train=4.1569  mask=12.8%  norm=0.974  lr=7.25e-05  dt=  38.5ms  words=73,310,208
[E06  1210/1548 G   8949|CLM] train=2.5271  mask=12.8%  norm=0.661  lr=7.25e-05  dt=  41.1ms  words=73,318,400
[E06  1211/1548 G   8950|CLM] train=4.0907  mask=12.8%  norm=0.918  lr=7.25e-05  dt=  37.0ms  words=73,326,592
[E06  1212/1548 G   8951|CLM] train=3.8722  mask=12.8%  norm=0.880  lr=7.24e-05  dt=  39.5ms  words=73,334,784
[E06  1213/1548 G   8952|CLM] train=4.4192  mask=12.8%  norm=1.176  lr=7.24e-05  dt=  39.8ms  words=73,342,976
[E06  1214/1548 G   8953|CLM] train=2.1835  mask=12.8%  norm=0.737  lr=7.24e-05  dt=  40.0ms  words=73,351,168
[E06  1215/1548 G   8954|CLM] train=4.2388  mask=12.8%  norm=0.880  lr=7.23e-05  dt=  37.7ms  words=73,359,360
[E06  1216/1548 G   8955|CLM] train=3.9715  mask=12.8%  norm=0.712  lr=7.23e-05  dt=  37.5ms  words=73,367,552
[E06  1217/1548 G   8956|CLM] train=4.5014  mask=12.8%  norm=0.934  lr=7.23e-05  dt=  40.1ms  words=73,375,744
[E06  1218/1548 G   8957|CLM] train=4.3475  mask=12.8%  norm=0.919  lr=7.22e-05  dt=  41.2ms  words=73,383,936
[E06  1219/1548 G   8958|CLM] train=3.4835  mask=12.8%  norm=0.832  lr=7.22e-05  dt=  39.0ms  words=73,392,128
[E06  1220/1548 G   8959|CLM] train=2.2445  mask=12.8%  norm=0.953  lr=7.22e-05  dt=  42.7ms  words=73,400,320
[E06  1221/1548 G   8960|CLM] train=4.1583  mask=12.8%  norm=0.798  lr=7.21e-05  dt=  39.6ms  words=73,408,512
[E06  1222/1548 G   8961|CLM] train=4.6835  mask=12.8%  norm=0.852  lr=7.21e-05  dt=  41.7ms  words=73,416,704
[E06  1223/1548 G   8962|CLM] train=4.0391  mask=12.8%  norm=0.990  lr=7.21e-05  dt=  37.5ms  words=73,424,896
[E06  1224/1548 G   8963|CLM] train=2.2078  mask=12.8%  norm=0.681  lr=7.21e-05  dt=  40.0ms  words=73,433,088
[E06  1225/1548 G   8964|CLM] train=4.0847  mask=12.8%  norm=0.921  lr=7.20e-05  dt=  42.7ms  words=73,441,280
[E06  1226/1548 G   8965|CLM] train=4.0962  mask=12.8%  norm=0.851  lr=7.20e-05  dt=  44.4ms  words=73,449,472
[E06  1227/1548 G   8966|CLM] train=3.8614  mask=12.8%  norm=0.912  lr=7.20e-05  dt=  43.3ms  words=73,457,664
[E06  1228/1548 G   8967|CLM] train=4.6136  mask=12.8%  norm=1.129  lr=7.19e-05  dt=  43.1ms  words=73,465,856
[E06  1229/1548 G   8968|CLM] train=4.3007  mask=12.8%  norm=0.854  lr=7.19e-05  dt=  40.8ms  words=73,474,048
[E06  1230/1548 G   8969|CLM] train=2.1078  mask=12.8%  norm=0.698  lr=7.19e-05  dt=  41.3ms  words=73,482,240
[E06  1231/1548 G   8970|CLM] train=4.2053  mask=12.8%  norm=0.914  lr=7.18e-05  dt=  37.2ms  words=73,490,432
[E06  1232/1548 G   8971|CLM] train=2.7674  mask=12.8%  norm=0.793  lr=7.18e-05  dt=  38.4ms  words=73,498,624
[E06  1233/1548 G   8972|CLM] train=4.5786  mask=12.8%  norm=0.871  lr=7.18e-05  dt=  36.9ms  words=73,506,816
[E06  1234/1548 G   8973|CLM] train=4.1294  mask=12.8%  norm=0.868  lr=7.17e-05  dt=  36.9ms  words=73,515,008
[E06  1235/1548 G   8974|CLM] train=2.0237  mask=12.8%  norm=0.664  lr=7.17e-05  dt=  37.0ms  words=73,523,200
[E06  1236/1548 G   8975|CLM] train=2.6240  mask=12.8%  norm=0.770  lr=7.17e-05  dt=  37.0ms  words=73,531,392
[E06  1237/1548 G   8976|CLM] train=4.8088  mask=12.8%  norm=1.017  lr=7.17e-05  dt=  37.1ms  words=73,539,584
[E06  1238/1548 G   8977|CLM] train=2.2449  mask=12.8%  norm=0.830  lr=7.16e-05  dt=  37.2ms  words=73,547,776
[E06  1239/1548 G   8978|CLM] train=2.3098  mask=12.8%  norm=0.748  lr=7.16e-05  dt=  37.2ms  words=73,555,968
[E06  1240/1548 G   8979|CLM] train=4.5098  mask=12.7%  norm=0.985  lr=7.16e-05  dt=  37.1ms  words=73,564,160
[E06  1241/1548 G   8980|CLM] train=4.3362  mask=12.7%  norm=1.028  lr=7.15e-05  dt=  37.1ms  words=73,572,352
[E06  1242/1548 G   8981|CLM] train=4.2243  mask=12.7%  norm=1.139  lr=7.15e-05  dt=  37.5ms  words=73,580,544
[E06  1243/1548 G   8982|CLM] train=4.0063  mask=12.7%  norm=0.868  lr=7.15e-05  dt=  37.2ms  words=73,588,736
[E06  1244/1548 G   8983|CLM] train=4.4604  mask=12.7%  norm=2.548  lr=7.14e-05  dt=  37.0ms  words=73,596,928
[E06  1245/1548 G   8984|CLM] train=3.5648  mask=12.7%  norm=0.725  lr=7.14e-05  dt=  37.9ms  words=73,605,120
[E06  1246/1548 G   8985|CLM] train=2.1624  mask=12.7%  norm=0.725  lr=7.14e-05  dt=  37.3ms  words=73,613,312
[E06  1247/1548 G   8986|CLM] train=3.9164  mask=12.7%  norm=0.945  lr=7.13e-05  dt=  37.3ms  words=73,621,504
[E06  1248/1548 G   8987|CLM] train=4.0539  mask=12.7%  norm=0.744  lr=7.13e-05  dt=  37.2ms  words=73,629,696
[E06  1249/1548 G   8988|CLM] train=2.0142  mask=12.7%  norm=0.694  lr=7.13e-05  dt=  37.7ms  words=73,637,888
[E06  1250/1548 G   8989|CLM] train=4.7366  mask=12.7%  norm=1.088  lr=7.13e-05  dt=  37.5ms  words=73,646,080
[E06  1251/1548 G   8990|CLM] train=2.2609  mask=12.7%  norm=0.639  lr=7.12e-05  dt=  37.2ms  words=73,654,272
[E06  1252/1548 G   8991|CLM] train=2.9803  mask=12.7%  norm=0.887  lr=7.12e-05  dt=  37.8ms  words=73,662,464
[E06  1253/1548 G   8992|CLM] train=4.5617  mask=12.7%  norm=0.974  lr=7.12e-05  dt=  37.6ms  words=73,670,656
[E06  1254/1548 G   8993|CLM] train=2.2785  mask=12.7%  norm=0.628  lr=7.11e-05  dt=  37.3ms  words=73,678,848
[E06  1255/1548 G   8994|CLM] train=3.6235  mask=12.7%  norm=0.786  lr=7.11e-05  dt=  37.3ms  words=73,687,040
[E06  1256/1548 G   8995|CLM] train=2.3187  mask=12.7%  norm=0.691  lr=7.11e-05  dt=  37.5ms  words=73,695,232
[E06  1257/1548 G   8996|CLM] train=2.4551  mask=12.7%  norm=0.737  lr=7.10e-05  dt=  37.1ms  words=73,703,424
[E06  1258/1548 G   8997|CLM] train=2.1767  mask=12.7%  norm=0.626  lr=7.10e-05  dt=  37.3ms  words=73,711,616
[E06  1259/1548 G   8998|CLM] train=2.2915  mask=12.7%  norm=0.699  lr=7.10e-05  dt=  37.2ms  words=73,719,808
[E06  1260/1548 G   8999|CLM] train=1.9262  mask=12.7%  norm=0.881  lr=7.09e-05  dt=  37.3ms  words=73,728,000
[E06  1261/1548 G   9000|CLM] train=4.3021  mask=12.7%  norm=0.942  lr=7.09e-05  dt=  37.1ms  words=73,736,192
[E06  1262/1548 G   9001|CLM] train=2.0276  mask=12.7%  norm=0.734  lr=7.09e-05  dt=  37.3ms  words=73,744,384
[E06  1263/1548 G   9002|CLM] train=2.5001  mask=12.7%  norm=0.813  lr=7.09e-05  dt=  37.1ms  words=73,752,576
[E06  1264/1548 G   9003|CLM] train=4.3147  mask=12.7%  norm=0.866  lr=7.08e-05  dt=  37.2ms  words=73,760,768
[E06  1265/1548 G   9004|CLM] train=3.8651  mask=12.7%  norm=0.841  lr=7.08e-05  dt=  37.3ms  words=73,768,960
[E06  1266/1548 G   9005|CLM] train=2.2563  mask=12.7%  norm=0.634  lr=7.08e-05  dt=  37.3ms  words=73,777,152
[E06  1267/1548 G   9006|CLM] train=4.5301  mask=12.7%  norm=1.040  lr=7.07e-05  dt=  37.1ms  words=73,785,344
[E06  1268/1548 G   9007|CLM] train=2.0661  mask=12.7%  norm=0.656  lr=7.07e-05  dt=  37.1ms  words=73,793,536
[E06  1269/1548 G   9008|CLM] train=3.5801  mask=12.7%  norm=0.827  lr=7.07e-05  dt=  37.3ms  words=73,801,728
[E06  1270/1548 G   9009|CLM] train=4.1108  mask=12.7%  norm=1.054  lr=7.06e-05  dt=  37.1ms  words=73,809,920
[E06  1271/1548 G   9010|CLM] train=4.0815  mask=12.7%  norm=0.936  lr=7.06e-05  dt=  37.3ms  words=73,818,112
[E06  1272/1548 G   9011|CLM] train=3.8566  mask=12.7%  norm=0.803  lr=7.06e-05  dt=  37.0ms  words=73,826,304
[E06  1273/1548 G   9012|CLM] train=3.9783  mask=12.7%  norm=0.844  lr=7.05e-05  dt=  37.0ms  words=73,834,496
[E06  1274/1548 G   9013|CLM] train=4.4071  mask=12.7%  norm=0.965  lr=7.05e-05  dt=  37.3ms  words=73,842,688
[E06  1275/1548 G   9014|CLM] train=4.2009  mask=12.7%  norm=0.897  lr=7.05e-05  dt=  37.2ms  words=73,850,880
[E06  1276/1548 G   9015|CLM] train=1.8388  mask=12.7%  norm=0.718  lr=7.05e-05  dt=  37.0ms  words=73,859,072
[E06  1277/1548 G   9016|CLM] train=4.4466  mask=12.7%  norm=1.164  lr=7.04e-05  dt=  37.1ms  words=73,867,264
[E06  1278/1548 G   9017|CLM] train=2.3893  mask=12.7%  norm=0.916  lr=7.04e-05  dt=  38.1ms  words=73,875,456
[E06  1279/1548 G   9018|CLM] train=5.4313  mask=12.7%  norm=3.939  lr=7.04e-05  dt=  37.3ms  words=73,883,648
[E06  1280/1548 G   9019|CLM] train=3.5850  mask=12.7%  norm=0.796  lr=7.03e-05  dt=  37.4ms  words=73,891,840
[E06  1281/1548 G   9020|CLM] train=3.7116  mask=12.7%  norm=0.897  lr=7.03e-05  dt=  37.0ms  words=73,900,032
[E06  1282/1548 G   9021|CLM] train=3.6816  mask=12.7%  norm=0.793  lr=7.03e-05  dt=  37.3ms  words=73,908,224
[E06  1283/1548 G   9022|CLM] train=4.1187  mask=12.7%  norm=0.810  lr=7.02e-05  dt=  37.2ms  words=73,916,416
[E06  1284/1548 G   9023|CLM] train=2.5749  mask=12.7%  norm=0.819  lr=7.02e-05  dt=  37.2ms  words=73,924,608
[E06  1285/1548 G   9024|CLM] train=2.0890  mask=12.7%  norm=0.711  lr=7.02e-05  dt=  37.4ms  words=73,932,800
[E06  1286/1548 G   9025|CLM] train=2.5104  mask=12.7%  norm=0.672  lr=7.01e-05  dt=  37.2ms  words=73,940,992
[E06  1287/1548 G   9026|CLM] train=2.2825  mask=12.7%  norm=0.770  lr=7.01e-05  dt=  37.2ms  words=73,949,184
[E06  1288/1548 G   9027|CLM] train=4.8816  mask=12.7%  norm=1.065  lr=7.01e-05  dt=  37.5ms  words=73,957,376
[E06  1289/1548 G   9028|CLM] train=2.1292  mask=12.7%  norm=0.822  lr=7.01e-05  dt=  37.3ms  words=73,965,568
[E06  1290/1548 G   9029|CLM] train=3.9727  mask=12.7%  norm=0.791  lr=7.00e-05  dt=  37.3ms  words=73,973,760
[E06  1291/1548 G   9030|CLM] train=2.0494  mask=12.7%  norm=0.628  lr=7.00e-05  dt=  37.1ms  words=73,981,952
[E06  1292/1548 G   9031|CLM] train=2.1678  mask=12.7%  norm=0.962  lr=7.00e-05  dt=  37.5ms  words=73,990,144
[E06  1293/1548 G   9032|CLM] train=3.8463  mask=12.7%  norm=0.847  lr=6.99e-05  dt=  37.2ms  words=73,998,336
[E06  1294/1548 G   9033|CLM] train=2.4624  mask=12.7%  norm=0.638  lr=6.99e-05  dt=  37.1ms  words=74,006,528
[E06  1295/1548 G   9034|CLM] train=2.1317  mask=12.7%  norm=0.669  lr=6.99e-05  dt=  37.4ms  words=74,014,720
[E06  1296/1548 G   9035|CLM] train=2.0650  mask=12.7%  norm=0.669  lr=6.98e-05  dt=  37.1ms  words=74,022,912
[E06  1297/1548 G   9036|CLM] train=3.7680  mask=12.7%  norm=0.872  lr=6.98e-05  dt=  37.2ms  words=74,031,104
[E06  1298/1548 G   9037|CLM] train=2.2279  mask=12.7%  norm=0.819  lr=6.98e-05  dt=  37.3ms  words=74,039,296
[E06  1299/1548 G   9038|CLM] train=4.0848  mask=12.7%  norm=0.875  lr=6.98e-05  dt=  37.0ms  words=74,047,488
[E06  1300/1548 G   9039|CLM] train=3.5448  mask=12.7%  norm=1.339  lr=6.97e-05  dt=  37.5ms  words=74,055,680
[E06  1301/1548 G   9040|CLM] train=4.0158  mask=12.7%  norm=0.848  lr=6.97e-05  dt=  37.4ms  words=74,063,872
[E06  1302/1548 G   9041|CLM] train=3.6647  mask=12.7%  norm=0.830  lr=6.97e-05  dt=  37.0ms  words=74,072,064
[E06  1303/1548 G   9042|CLM] train=3.6494  mask=12.7%  norm=0.871  lr=6.96e-05  dt=  37.2ms  words=74,080,256
[E06  1304/1548 G   9043|CLM] train=2.6841  mask=12.7%  norm=0.947  lr=6.96e-05  dt=  37.2ms  words=74,088,448
[E06  1305/1548 G   9044|CLM] train=2.2929  mask=12.7%  norm=0.666  lr=6.96e-05  dt=  37.0ms  words=74,096,640
[E06  1306/1548 G   9045|CLM] train=1.8050  mask=12.7%  norm=0.777  lr=6.95e-05  dt=  37.0ms  words=74,104,832
[E06  1307/1548 G   9046|CLM] train=2.1099  mask=12.7%  norm=0.703  lr=6.95e-05  dt=  37.1ms  words=74,113,024
[E06  1308/1548 G   9047|CLM] train=4.2640  mask=12.7%  norm=0.843  lr=6.95e-05  dt=  37.2ms  words=74,121,216
[E06  1309/1548 G   9048|CLM] train=2.0483  mask=12.7%  norm=0.716  lr=6.94e-05  dt=  37.1ms  words=74,129,408
[E06  1310/1548 G   9049|CLM] train=4.2532  mask=12.7%  norm=0.871  lr=6.94e-05  dt=  37.1ms  words=74,137,600
[E06  1311/1548 G   9050|CLM] train=4.0156  mask=12.7%  norm=0.809  lr=6.94e-05  dt=  37.1ms  words=74,145,792
[E06  1312/1548 G   9051|CLM] train=4.2540  mask=12.7%  norm=0.896  lr=6.94e-05  dt=  37.1ms  words=74,153,984
[E06  1313/1548 G   9052|CLM] train=4.0457  mask=12.7%  norm=0.901  lr=6.93e-05  dt=  37.2ms  words=74,162,176
[E06  1314/1548 G   9053|CLM] train=4.0670  mask=12.7%  norm=0.998  lr=6.93e-05  dt=  37.2ms  words=74,170,368
[E06  1315/1548 G   9054|CLM] train=4.2847  mask=12.7%  norm=0.966  lr=6.93e-05  dt=  37.1ms  words=74,178,560
[E06  1316/1548 G   9055|CLM] train=2.5346  mask=12.7%  norm=0.685  lr=6.92e-05  dt=  36.9ms  words=74,186,752
[E06  1317/1548 G   9056|CLM] train=4.1704  mask=12.7%  norm=0.895  lr=6.92e-05  dt=  37.0ms  words=74,194,944
[E06  1318/1548 G   9057|CLM] train=5.0386  mask=12.7%  norm=1.022  lr=6.92e-05  dt=  37.1ms  words=74,203,136
[E06  1319/1548 G   9058|CLM] train=2.2611  mask=12.7%  norm=0.760  lr=6.91e-05  dt=  37.3ms  words=74,211,328
[E06  1320/1548 G   9059|CLM] train=2.0791  mask=12.7%  norm=0.778  lr=6.91e-05  dt=  37.2ms  words=74,219,520
[E06  1321/1548 G   9060|CLM] train=4.1021  mask=12.7%  norm=0.819  lr=6.91e-05  dt=  37.1ms  words=74,227,712
[E06  1322/1548 G   9061|CLM] train=2.2052  mask=12.7%  norm=0.676  lr=6.91e-05  dt=  37.2ms  words=74,235,904
[E06  1323/1548 G   9062|CLM] train=3.9854  mask=12.7%  norm=0.875  lr=6.90e-05  dt=  37.3ms  words=74,244,096
[E06  1324/1548 G   9063|CLM] train=4.3646  mask=12.7%  norm=0.798  lr=6.90e-05  dt=  37.2ms  words=74,252,288
[E06  1325/1548 G   9064|CLM] train=4.1836  mask=12.7%  norm=1.050  lr=6.90e-05  dt=  37.8ms  words=74,260,480
[E06  1326/1548 G   9065|CLM] train=2.1761  mask=12.7%  norm=0.888  lr=6.89e-05  dt=  37.3ms  words=74,268,672
[E06  1327/1548 G   9066|CLM] train=4.4144  mask=12.7%  norm=1.241  lr=6.89e-05  dt=  37.4ms  words=74,276,864
[E06  1328/1548 G   9067|CLM] train=4.0295  mask=12.7%  norm=0.807  lr=6.89e-05  dt=  36.9ms  words=74,285,056
[E06  1329/1548 G   9068|CLM] train=3.8559  mask=12.7%  norm=0.754  lr=6.88e-05  dt=  37.0ms  words=74,293,248
[E06  1330/1548 G   9069|CLM] train=4.5785  mask=12.7%  norm=0.989  lr=6.88e-05  dt=  37.2ms  words=74,301,440
[E06  1331/1548 G   9070|CLM] train=4.2329  mask=12.7%  norm=1.071  lr=6.88e-05  dt=  37.2ms  words=74,309,632
[E06  1332/1548 G   9071|CLM] train=3.9396  mask=12.7%  norm=0.725  lr=6.88e-05  dt=  37.3ms  words=74,317,824
[E06  1333/1548 G   9072|CLM] train=4.1347  mask=12.7%  norm=0.857  lr=6.87e-05  dt=  37.3ms  words=74,326,016
[E06  1334/1548 G   9073|CLM] train=2.0275  mask=12.7%  norm=0.775  lr=6.87e-05  dt=  37.1ms  words=74,334,208
[E06  1335/1548 G   9074|CLM] train=3.5044  mask=12.7%  norm=0.792  lr=6.87e-05  dt=  37.2ms  words=74,342,400
[E06  1336/1548 G   9075|CLM] train=4.0715  mask=12.7%  norm=1.067  lr=6.86e-05  dt=  37.1ms  words=74,350,592
[E06  1337/1548 G   9076|CLM] train=2.0803  mask=12.7%  norm=0.747  lr=6.86e-05  dt=  37.2ms  words=74,358,784
[E06  1338/1548 G   9077|CLM] train=3.6629  mask=12.7%  norm=0.855  lr=6.86e-05  dt=  37.2ms  words=74,366,976
[E06  1339/1548 G   9078|CLM] train=4.0705  mask=12.7%  norm=0.851  lr=6.85e-05  dt=  37.3ms  words=74,375,168
[E06  1340/1548 G   9079|CLM] train=1.9906  mask=12.7%  norm=0.845  lr=6.85e-05  dt=  37.0ms  words=74,383,360
[E06  1341/1548 G   9080|CLM] train=2.0900  mask=12.7%  norm=0.736  lr=6.85e-05  dt=  37.3ms  words=74,391,552
[E06  1342/1548 G   9081|CLM] train=3.9580  mask=12.7%  norm=1.055  lr=6.84e-05  dt=  37.2ms  words=74,399,744
[E06  1343/1548 G   9082|CLM] train=4.4122  mask=12.7%  norm=0.801  lr=6.84e-05  dt=  37.1ms  words=74,407,936
[E06  1344/1548 G   9083|CLM] train=3.8813  mask=12.7%  norm=0.757  lr=6.84e-05  dt=  37.4ms  words=74,416,128
[E06  1345/1548 G   9084|CLM] train=3.9696  mask=12.7%  norm=0.765  lr=6.84e-05  dt=  37.3ms  words=74,424,320
[E06  1346/1548 G   9085|CLM] train=2.4441  mask=12.7%  norm=0.662  lr=6.83e-05  dt=  37.1ms  words=74,432,512
[E06  1347/1548 G   9086|CLM] train=4.1520  mask=12.7%  norm=0.844  lr=6.83e-05  dt=  37.3ms  words=74,440,704
[E06  1348/1548 G   9087|CLM] train=4.3494  mask=12.7%  norm=0.927  lr=6.83e-05  dt=  37.3ms  words=74,448,896
[E06  1349/1548 G   9088|CLM] train=2.1233  mask=12.7%  norm=0.899  lr=6.82e-05  dt=  37.1ms  words=74,457,088
[E06  1350/1548 G   9089|CLM] train=3.3569  mask=12.7%  norm=0.819  lr=6.82e-05  dt=  37.2ms  words=74,465,280
[E06  1351/1548 G   9090|CLM] train=3.7309  mask=12.7%  norm=0.840  lr=6.82e-05  dt=  37.4ms  words=74,473,472
[E06  1352/1548 G   9091|CLM] train=3.7072  mask=12.7%  norm=0.826  lr=6.81e-05  dt=  37.1ms  words=74,481,664
[E06  1353/1548 G   9092|CLM] train=2.2804  mask=12.7%  norm=0.744  lr=6.81e-05  dt=  37.1ms  words=74,489,856
[E06  1354/1548 G   9093|CLM] train=4.8409  mask=12.7%  norm=2.555  lr=6.81e-05  dt=  37.1ms  words=74,498,048
[E06  1355/1548 G   9094|CLM] train=2.2682  mask=12.7%  norm=0.754  lr=6.81e-05  dt=  37.2ms  words=74,506,240
[E06  1356/1548 G   9095|CLM] train=2.1965  mask=12.7%  norm=0.643  lr=6.80e-05  dt=  37.3ms  words=74,514,432
[E06  1357/1548 G   9096|CLM] train=4.3008  mask=12.7%  norm=0.936  lr=6.80e-05  dt=  37.1ms  words=74,522,624
[E06  1358/1548 G   9097|CLM] train=3.7006  mask=12.7%  norm=0.850  lr=6.80e-05  dt=  37.1ms  words=74,530,816
[E06  1359/1548 G   9098|CLM] train=3.9641  mask=12.7%  norm=0.919  lr=6.79e-05  dt=  37.2ms  words=74,539,008
[E06  1360/1548 G   9099|CLM] train=2.2858  mask=12.7%  norm=0.810  lr=6.79e-05  dt=  37.1ms  words=74,547,200
[E06  1361/1548 G   9100|CLM] train=4.3024  mask=12.7%  norm=0.927  lr=6.79e-05  dt=  37.3ms  words=74,555,392
[E06  1362/1548 G   9101|CLM] train=2.3934  mask=12.7%  norm=0.665  lr=6.78e-05  dt=  36.9ms  words=74,563,584
[E06  1363/1548 G   9102|CLM] train=2.0485  mask=12.7%  norm=0.791  lr=6.78e-05  dt=  37.2ms  words=74,571,776
[E06  1364/1548 G   9103|CLM] train=2.3627  mask=12.6%  norm=0.666  lr=6.78e-05  dt=  37.2ms  words=74,579,968
[E06  1365/1548 G   9104|CLM] train=3.4734  mask=12.6%  norm=0.772  lr=6.78e-05  dt=  37.2ms  words=74,588,160
[E06  1366/1548 G   9105|CLM] train=4.8079  mask=12.6%  norm=1.008  lr=6.77e-05  dt=  37.0ms  words=74,596,352
[E06  1367/1548 G   9106|CLM] train=5.2255  mask=12.6%  norm=1.091  lr=6.77e-05  dt=  37.1ms  words=74,604,544
[E06  1368/1548 G   9107|CLM] train=3.8607  mask=12.6%  norm=0.922  lr=6.77e-05  dt=  37.4ms  words=74,612,736
[E06  1369/1548 G   9108|CLM] train=3.9250  mask=12.6%  norm=0.793  lr=6.76e-05  dt=  37.1ms  words=74,620,928
[E06  1370/1548 G   9109|CLM] train=4.0231  mask=12.6%  norm=0.968  lr=6.76e-05  dt=  37.3ms  words=74,629,120
[E06  1371/1548 G   9110|CLM] train=4.1856  mask=12.6%  norm=0.914  lr=6.76e-05  dt=  37.1ms  words=74,637,312
[E06  1372/1548 G   9111|CLM] train=4.3648  mask=12.6%  norm=0.942  lr=6.75e-05  dt=  37.1ms  words=74,645,504
[E06  1373/1548 G   9112|CLM] train=4.7314  mask=12.6%  norm=0.870  lr=6.75e-05  dt=  37.3ms  words=74,653,696
[E06  1374/1548 G   9113|CLM] train=2.1437  mask=12.6%  norm=0.670  lr=6.75e-05  dt=  37.1ms  words=74,661,888
[E06  1375/1548 G   9114|CLM] train=2.1881  mask=12.6%  norm=0.894  lr=6.75e-05  dt=  37.1ms  words=74,670,080
[E06  1376/1548 G   9115|CLM] train=4.0157  mask=12.6%  norm=0.883  lr=6.74e-05  dt=  37.2ms  words=74,678,272
[E06  1377/1548 G   9116|CLM] train=2.0635  mask=12.6%  norm=0.617  lr=6.74e-05  dt=  37.3ms  words=74,686,464
[E06  1378/1548 G   9117|CLM] train=4.1378  mask=12.6%  norm=0.813  lr=6.74e-05  dt=  37.0ms  words=74,694,656
[E06  1379/1548 G   9118|CLM] train=2.2404  mask=12.6%  norm=0.740  lr=6.73e-05  dt=  37.0ms  words=74,702,848
[E06  1380/1548 G   9119|CLM] train=3.8610  mask=12.6%  norm=1.131  lr=6.73e-05  dt=  37.4ms  words=74,711,040
[E06  1381/1548 G   9120|CLM] train=2.0512  mask=12.6%  norm=0.846  lr=6.73e-05  dt=  37.2ms  words=74,719,232
[E06  1382/1548 G   9121|CLM] train=4.4427  mask=12.6%  norm=0.997  lr=6.72e-05  dt=  37.0ms  words=74,727,424
[E06  1383/1548 G   9122|CLM] train=4.1493  mask=12.6%  norm=0.847  lr=6.72e-05  dt=  37.0ms  words=74,735,616
[E06  1384/1548 G   9123|CLM] train=3.3133  mask=12.6%  norm=0.847  lr=6.72e-05  dt=  37.0ms  words=74,743,808
[E06  1385/1548 G   9124|CLM] train=4.4747  mask=12.6%  norm=1.208  lr=6.72e-05  dt=  37.1ms  words=74,752,000
[E06  1386/1548 G   9125|CLM] train=2.5519  mask=12.6%  norm=0.908  lr=6.71e-05  dt=  37.1ms  words=74,760,192
[E06  1387/1548 G   9126|CLM] train=4.7094  mask=12.6%  norm=1.167  lr=6.71e-05  dt=  37.3ms  words=74,768,384
[E06  1388/1548 G   9127|CLM] train=4.9500  mask=12.6%  norm=1.271  lr=6.71e-05  dt=  37.1ms  words=74,776,576
[E06  1389/1548 G   9128|CLM] train=3.8223  mask=12.6%  norm=0.869  lr=6.70e-05  dt=  37.0ms  words=74,784,768
[E06  1390/1548 G   9129|CLM] train=2.6340  mask=12.6%  norm=0.811  lr=6.70e-05  dt=  37.1ms  words=74,792,960
[E06  1391/1548 G   9130|CLM] train=3.8483  mask=12.6%  norm=0.933  lr=6.70e-05  dt=  37.4ms  words=74,801,152
[E06  1392/1548 G   9131|CLM] train=2.0432  mask=12.6%  norm=0.788  lr=6.69e-05  dt=  37.0ms  words=74,809,344
[E06  1393/1548 G   9132|CLM] train=4.2169  mask=12.6%  norm=0.874  lr=6.69e-05  dt=  37.2ms  words=74,817,536
[E06  1394/1548 G   9133|CLM] train=3.7472  mask=12.6%  norm=0.836  lr=6.69e-05  dt=  37.4ms  words=74,825,728
[E06  1395/1548 G   9134|CLM] train=3.7988  mask=12.6%  norm=0.889  lr=6.69e-05  dt=  37.2ms  words=74,833,920
[E06  1396/1548 G   9135|CLM] train=4.1128  mask=12.6%  norm=1.599  lr=6.68e-05  dt=  37.3ms  words=74,842,112
[E06  1397/1548 G   9136|CLM] train=3.8580  mask=12.6%  norm=0.829  lr=6.68e-05  dt=  37.6ms  words=74,850,304
[E06  1398/1548 G   9137|CLM] train=4.7012  mask=12.6%  norm=0.986  lr=6.68e-05  dt=  37.5ms  words=74,858,496
[E06  1399/1548 G   9138|CLM] train=4.2754  mask=12.6%  norm=1.010  lr=6.67e-05  dt=  37.5ms  words=74,866,688
[E06  1400/1548 G   9139|CLM] train=1.7272  mask=12.6%  norm=0.657  lr=6.67e-05  dt=  37.0ms  words=74,874,880
[E06  1401/1548 G   9140|CLM] train=1.8531  mask=12.6%  norm=0.714  lr=6.67e-05  dt=  37.3ms  words=74,883,072
[E06  1402/1548 G   9141|CLM] train=2.3762  mask=12.6%  norm=0.696  lr=6.67e-05  dt=  39.3ms  words=74,891,264
[E06  1403/1548 G   9142|CLM] train=2.1502  mask=12.6%  norm=0.696  lr=6.66e-05  dt=  37.2ms  words=74,899,456
[E06  1404/1548 G   9143|CLM] train=2.5924  mask=12.6%  norm=0.710  lr=6.66e-05  dt=  37.1ms  words=74,907,648
[E06  1405/1548 G   9144|CLM] train=4.6958  mask=12.6%  norm=0.889  lr=6.66e-05  dt=  37.1ms  words=74,915,840
[E06  1406/1548 G   9145|CLM] train=4.7596  mask=12.6%  norm=1.233  lr=6.65e-05  dt=  37.0ms  words=74,924,032
[E06  1407/1548 G   9146|CLM] train=4.0865  mask=12.6%  norm=0.810  lr=6.65e-05  dt=  37.2ms  words=74,932,224
[E06  1408/1548 G   9147|CLM] train=4.2359  mask=12.6%  norm=0.941  lr=6.65e-05  dt=  36.9ms  words=74,940,416
[E06  1409/1548 G   9148|CLM] train=3.8552  mask=12.6%  norm=0.814  lr=6.64e-05  dt=  37.6ms  words=74,948,608
[E06  1410/1548 G   9149|CLM] train=4.6414  mask=12.6%  norm=0.975  lr=6.64e-05  dt=  37.5ms  words=74,956,800
[E06  1411/1548 G   9150|CLM] train=4.3577  mask=12.6%  norm=0.995  lr=6.64e-05  dt=  37.2ms  words=74,964,992
[E06  1412/1548 G   9151|CLM] train=4.9110  mask=12.6%  norm=2.633  lr=6.64e-05  dt=  37.0ms  words=74,973,184
[E06  1413/1548 G   9152|CLM] train=3.8414  mask=12.6%  norm=0.740  lr=6.63e-05  dt=  37.1ms  words=74,981,376
[E06  1414/1548 G   9153|CLM] train=4.0284  mask=12.6%  norm=1.234  lr=6.63e-05  dt=  37.3ms  words=74,989,568
[E06  1415/1548 G   9154|CLM] train=3.4465  mask=12.6%  norm=0.693  lr=6.63e-05  dt=  36.9ms  words=74,997,760
[E06  1416/1548 G   9155|CLM] train=2.4029  mask=12.6%  norm=0.911  lr=6.62e-05  dt=  36.9ms  words=75,005,952
[E06  1417/1548 G   9156|CLM] train=3.4400  mask=12.6%  norm=0.766  lr=6.62e-05  dt=  37.1ms  words=75,014,144
[E06  1418/1548 G   9157|CLM] train=2.5370  mask=12.6%  norm=0.728  lr=6.62e-05  dt=  37.0ms  words=75,022,336
[E06  1419/1548 G   9158|CLM] train=3.5743  mask=12.6%  norm=0.933  lr=6.61e-05  dt=  37.1ms  words=75,030,528
[E06  1420/1548 G   9159|CLM] train=2.1524  mask=12.6%  norm=0.809  lr=6.61e-05  dt=  37.2ms  words=75,038,720
[E06  1421/1548 G   9160|CLM] train=4.0424  mask=12.6%  norm=0.823  lr=6.61e-05  dt=  37.1ms  words=75,046,912
[E06  1422/1548 G   9161|CLM] train=4.3431  mask=12.6%  norm=0.795  lr=6.61e-05  dt=  36.9ms  words=75,055,104
[E06  1423/1548 G   9162|CLM] train=2.2378  mask=12.6%  norm=0.720  lr=6.60e-05  dt=  37.0ms  words=75,063,296
[E06  1424/1548 G   9163|CLM] train=1.8395  mask=12.6%  norm=0.666  lr=6.60e-05  dt=  37.1ms  words=75,071,488
[E06  1425/1548 G   9164|CLM] train=3.4647  mask=12.6%  norm=0.854  lr=6.60e-05  dt=  37.0ms  words=75,079,680
[E06  1426/1548 G   9165|CLM] train=2.6005  mask=12.6%  norm=0.830  lr=6.59e-05  dt=  37.2ms  words=75,087,872
[E06  1427/1548 G   9166|CLM] train=4.6860  mask=12.6%  norm=0.954  lr=6.59e-05  dt=  37.2ms  words=75,096,064
[E06  1428/1548 G   9167|CLM] train=2.6109  mask=12.6%  norm=0.746  lr=6.59e-05  dt=  36.9ms  words=75,104,256
[E06  1429/1548 G   9168|CLM] train=2.2293  mask=12.6%  norm=0.665  lr=6.59e-05  dt=  37.0ms  words=75,112,448
[E06  1430/1548 G   9169|CLM] train=3.6859  mask=12.6%  norm=0.910  lr=6.58e-05  dt=  37.0ms  words=75,120,640
[E06  1431/1548 G   9170|CLM] train=2.2552  mask=12.6%  norm=0.630  lr=6.58e-05  dt=  37.2ms  words=75,128,832
[E06  1432/1548 G   9171|CLM] train=3.7771  mask=12.6%  norm=0.841  lr=6.58e-05  dt=  36.9ms  words=75,137,024
[E06  1433/1548 G   9172|CLM] train=4.7674  mask=12.6%  norm=1.053  lr=6.57e-05  dt=  37.3ms  words=75,145,216
[E06  1434/1548 G   9173|CLM] train=2.5637  mask=12.6%  norm=0.730  lr=6.57e-05  dt=  37.1ms  words=75,153,408
[E06  1435/1548 G   9174|CLM] train=3.7305  mask=12.6%  norm=0.792  lr=6.57e-05  dt=  37.1ms  words=75,161,600
[E06  1436/1548 G   9175|CLM] train=5.0291  mask=12.6%  norm=1.036  lr=6.56e-05  dt=  36.9ms  words=75,169,792
[E06  1437/1548 G   9176|CLM] train=4.7513  mask=12.6%  norm=1.111  lr=6.56e-05  dt=  37.0ms  words=75,177,984
[E06  1438/1548 G   9177|CLM] train=4.1244  mask=12.6%  norm=0.991  lr=6.56e-05  dt=  37.1ms  words=75,186,176
[E06  1439/1548 G   9178|CLM] train=4.2887  mask=12.6%  norm=0.854  lr=6.56e-05  dt=  36.9ms  words=75,194,368
[E06  1440/1548 G   9179|CLM] train=4.1470  mask=12.6%  norm=0.872  lr=6.55e-05  dt=  37.2ms  words=75,202,560
[E06  1441/1548 G   9180|CLM] train=4.2433  mask=12.6%  norm=0.944  lr=6.55e-05  dt=  37.6ms  words=75,210,752
[E06  1442/1548 G   9181|CLM] train=4.1701  mask=12.6%  norm=0.926  lr=6.55e-05  dt=  36.9ms  words=75,218,944
[E06  1443/1548 G   9182|CLM] train=3.5559  mask=12.6%  norm=0.857  lr=6.54e-05  dt=  37.0ms  words=75,227,136
[E06  1444/1548 G   9183|CLM] train=2.2093  mask=12.6%  norm=0.689  lr=6.54e-05  dt=  36.9ms  words=75,235,328
[E06  1445/1548 G   9184|CLM] train=2.1061  mask=12.6%  norm=0.635  lr=6.54e-05  dt=  37.2ms  words=75,243,520
[E06  1446/1548 G   9185|CLM] train=2.6249  mask=12.6%  norm=0.851  lr=6.53e-05  dt=  37.0ms  words=75,251,712
[E06  1447/1548 G   9186|CLM] train=3.6957  mask=12.6%  norm=0.720  lr=6.53e-05  dt=  37.1ms  words=75,259,904
[E06  1448/1548 G   9187|CLM] train=2.0675  mask=12.6%  norm=0.633  lr=6.53e-05  dt=  37.6ms  words=75,268,096
[E06  1449/1548 G   9188|CLM] train=3.7430  mask=12.6%  norm=0.904  lr=6.53e-05  dt=  37.1ms  words=75,276,288
[E06  1450/1548 G   9189|CLM] train=2.0611  mask=12.6%  norm=0.638  lr=6.52e-05  dt=  37.0ms  words=75,284,480
[E06  1451/1548 G   9190|CLM] train=1.9705  mask=12.6%  norm=0.751  lr=6.52e-05  dt=  37.3ms  words=75,292,672
[E06  1452/1548 G   9191|CLM] train=3.9308  mask=12.6%  norm=0.916  lr=6.52e-05  dt=  37.0ms  words=75,300,864
[E06  1453/1548 G   9192|CLM] train=1.9393  mask=12.6%  norm=0.756  lr=6.51e-05  dt=  37.3ms  words=75,309,056
[E06  1454/1548 G   9193|CLM] train=3.9189  mask=12.6%  norm=0.911  lr=6.51e-05  dt=  37.1ms  words=75,317,248
[E06  1455/1548 G   9194|CLM] train=3.7672  mask=12.6%  norm=0.918  lr=6.51e-05  dt=  37.1ms  words=75,325,440
[E06  1456/1548 G   9195|CLM] train=2.1181  mask=12.6%  norm=0.709  lr=6.51e-05  dt=  36.9ms  words=75,333,632
[E06  1457/1548 G   9196|CLM] train=4.2648  mask=12.6%  norm=0.868  lr=6.50e-05  dt=  37.1ms  words=75,341,824
[E06  1458/1548 G   9197|CLM] train=4.3352  mask=12.6%  norm=0.892  lr=6.50e-05  dt=  37.1ms  words=75,350,016
[E06  1459/1548 G   9198|CLM] train=1.6952  mask=12.6%  norm=0.685  lr=6.50e-05  dt=  37.2ms  words=75,358,208
[E06  1460/1548 G   9199|CLM] train=2.4268  mask=12.6%  norm=0.712  lr=6.49e-05  dt=  37.1ms  words=75,366,400
[E06  1461/1548 G   9200|CLM] train=4.0306  mask=12.6%  norm=0.803  lr=6.49e-05  dt=  37.2ms  words=75,374,592
[E06  1462/1548 G   9201|CLM] train=4.4103  mask=12.6%  norm=2.081  lr=6.49e-05  dt=  37.0ms  words=75,382,784
[E06  1463/1548 G   9202|CLM] train=2.6149  mask=12.6%  norm=0.733  lr=6.48e-05  dt=  37.1ms  words=75,390,976
[E06  1464/1548 G   9203|CLM] train=3.9570  mask=12.6%  norm=0.769  lr=6.48e-05  dt=  37.2ms  words=75,399,168
[E06  1465/1548 G   9204|CLM] train=3.8412  mask=12.6%  norm=0.877  lr=6.48e-05  dt=  37.2ms  words=75,407,360
[E06  1466/1548 G   9205|CLM] train=3.9430  mask=12.6%  norm=0.784  lr=6.48e-05  dt=  36.9ms  words=75,415,552
[E06  1467/1548 G   9206|CLM] train=4.6985  mask=12.6%  norm=0.894  lr=6.47e-05  dt=  37.1ms  words=75,423,744
[E06  1468/1548 G   9207|CLM] train=4.3615  mask=12.6%  norm=0.958  lr=6.47e-05  dt=  37.3ms  words=75,431,936
[E06  1469/1548 G   9208|CLM] train=3.4087  mask=12.6%  norm=0.798  lr=6.47e-05  dt=  37.1ms  words=75,440,128
[E06  1470/1548 G   9209|CLM] train=2.4145  mask=12.6%  norm=0.710  lr=6.46e-05  dt=  37.0ms  words=75,448,320
[E06  1471/1548 G   9210|CLM] train=2.5079  mask=12.6%  norm=0.699  lr=6.46e-05  dt=  37.4ms  words=75,456,512
[E06  1472/1548 G   9211|CLM] train=2.3462  mask=12.6%  norm=0.671  lr=6.46e-05  dt=  37.0ms  words=75,464,704
[E06  1473/1548 G   9212|CLM] train=4.1777  mask=12.6%  norm=0.949  lr=6.46e-05  dt=  37.0ms  words=75,472,896
[E06  1474/1548 G   9213|CLM] train=2.4087  mask=12.6%  norm=0.648  lr=6.45e-05  dt=  37.2ms  words=75,481,088
[E06  1475/1548 G   9214|CLM] train=2.1433  mask=12.6%  norm=0.633  lr=6.45e-05  dt=  37.3ms  words=75,489,280
[E06  1476/1548 G   9215|CLM] train=2.3274  mask=12.6%  norm=0.687  lr=6.45e-05  dt=  37.0ms  words=75,497,472
[E06  1477/1548 G   9216|CLM] train=3.6903  mask=12.6%  norm=0.929  lr=6.44e-05  dt=  37.0ms  words=75,505,664
[E06  1478/1548 G   9217|CLM] train=4.3223  mask=12.6%  norm=0.910  lr=6.44e-05  dt=  37.0ms  words=75,513,856
[E06  1479/1548 G   9218|CLM] train=2.5600  mask=12.6%  norm=0.923  lr=6.44e-05  dt=  36.9ms  words=75,522,048
[E06  1480/1548 G   9219|CLM] train=2.4373  mask=12.6%  norm=0.726  lr=6.43e-05  dt=  37.4ms  words=75,530,240
[E06  1481/1548 G   9220|CLM] train=3.4328  mask=12.6%  norm=0.752  lr=6.43e-05  dt=  37.3ms  words=75,538,432
[E06  1482/1548 G   9221|CLM] train=2.3090  mask=12.6%  norm=0.694  lr=6.43e-05  dt=  37.0ms  words=75,546,624
[E06  1483/1548 G   9222|CLM] train=3.8601  mask=12.6%  norm=0.833  lr=6.43e-05  dt=  36.9ms  words=75,554,816
[E06  1484/1548 G   9223|CLM] train=2.5101  mask=12.6%  norm=0.762  lr=6.42e-05  dt=  36.9ms  words=75,563,008
[E06  1485/1548 G   9224|CLM] train=4.1935  mask=12.6%  norm=1.038  lr=6.42e-05  dt=  37.1ms  words=75,571,200
[E06  1486/1548 G   9225|CLM] train=2.4257  mask=12.6%  norm=0.721  lr=6.42e-05  dt=  37.0ms  words=75,579,392
[E06  1487/1548 G   9226|CLM] train=4.6282  mask=12.6%  norm=0.934  lr=6.41e-05  dt=  37.3ms  words=75,587,584
[E06  1488/1548 G   9227|CLM] train=2.4467  mask=12.5%  norm=0.680  lr=6.41e-05  dt=  37.6ms  words=75,595,776
[E06  1489/1548 G   9228|CLM] train=2.0925  mask=12.5%  norm=0.668  lr=6.41e-05  dt=  38.3ms  words=75,603,968
[E06  1490/1548 G   9229|CLM] train=4.0860  mask=12.5%  norm=0.968  lr=6.41e-05  dt=  37.1ms  words=75,612,160
[E06  1491/1548 G   9230|CLM] train=4.0317  mask=12.5%  norm=0.784  lr=6.40e-05  dt= 444.1ms  words=75,620,352
[E06  1492/1548 G   9231|CLM] train=4.1766  mask=12.5%  norm=0.849  lr=6.40e-05  dt=  39.0ms  words=75,628,544
[E06  1493/1548 G   9232|CLM] train=2.2844  mask=12.5%  norm=0.750  lr=6.40e-05  dt=  37.4ms  words=75,636,736
[E06  1494/1548 G   9233|CLM] train=3.5752  mask=12.5%  norm=0.853  lr=6.39e-05  dt=  37.1ms  words=75,644,928
[E06  1495/1548 G   9234|CLM] train=3.6985  mask=12.5%  norm=0.862  lr=6.39e-05  dt=  37.0ms  words=75,653,120
[E06  1496/1548 G   9235|CLM] train=2.1556  mask=12.5%  norm=1.036  lr=6.39e-05  dt=  37.6ms  words=75,661,312
[E06  1497/1548 G   9236|CLM] train=3.6259  mask=12.5%  norm=0.787  lr=6.39e-05  dt=  37.0ms  words=75,669,504
[E06  1498/1548 G   9237|CLM] train=1.5824  mask=12.5%  norm=0.777  lr=6.38e-05  dt=  37.2ms  words=75,677,696
[E06  1499/1548 G   9238|CLM] train=4.2414  mask=12.5%  norm=0.940  lr=6.38e-05  dt=  37.1ms  words=75,685,888
[E06  1500/1548 G   9239|CLM] train=3.3442  mask=12.5%  norm=0.792  lr=6.38e-05  dt=  37.2ms  words=75,694,080
[E06  1501/1548 G   9240|CLM] train=2.2435  mask=12.5%  norm=0.816  lr=6.37e-05  dt=  37.2ms  words=75,702,272
[E06  1502/1548 G   9241|CLM] train=2.3375  mask=12.5%  norm=0.690  lr=6.37e-05  dt=  37.4ms  words=75,710,464
[E06  1503/1548 G   9242|CLM] train=4.1308  mask=12.5%  norm=0.996  lr=6.37e-05  dt=  37.4ms  words=75,718,656
[E06  1504/1548 G   9243|CLM] train=3.7730  mask=12.5%  norm=0.763  lr=6.36e-05  dt=  37.2ms  words=75,726,848
[E06  1505/1548 G   9244|CLM] train=3.7320  mask=12.5%  norm=0.885  lr=6.36e-05  dt=  37.1ms  words=75,735,040
[E06  1506/1548 G   9245|CLM] train=4.1754  mask=12.5%  norm=0.836  lr=6.36e-05  dt=  37.2ms  words=75,743,232
[E06  1507/1548 G   9246|CLM] train=2.4080  mask=12.5%  norm=0.672  lr=6.36e-05  dt=  37.1ms  words=75,751,424
[E06  1508/1548 G   9247|CLM] train=3.9402  mask=12.5%  norm=0.770  lr=6.35e-05  dt=  37.2ms  words=75,759,616
[E06  1509/1548 G   9248|CLM] train=2.4032  mask=12.5%  norm=0.783  lr=6.35e-05  dt=  37.4ms  words=75,767,808
[E06  1510/1548 G   9249|CLM] train=2.1004  mask=12.5%  norm=0.946  lr=6.35e-05  dt=  37.3ms  words=75,776,000
[E06  1511/1548 G   9250|CLM] train=4.3206  mask=12.5%  norm=0.902  lr=6.34e-05  dt=  37.3ms  words=75,784,192
[E06  1512/1548 G   9251|CLM] train=4.1533  mask=12.5%  norm=0.867  lr=6.34e-05  dt=  37.4ms  words=75,792,384
[E06  1513/1548 G   9252|CLM] train=4.3113  mask=12.5%  norm=0.832  lr=6.34e-05  dt=  37.2ms  words=75,800,576
[E06  1514/1548 G   9253|CLM] train=1.9937  mask=12.5%  norm=0.883  lr=6.34e-05  dt=  37.2ms  words=75,808,768
[E06  1515/1548 G   9254|CLM] train=4.5599  mask=12.5%  norm=0.828  lr=6.33e-05  dt=  37.2ms  words=75,816,960
[E06  1516/1548 G   9255|CLM] train=2.0677  mask=12.5%  norm=0.641  lr=6.33e-05  dt=  37.1ms  words=75,825,152
[E06  1517/1548 G   9256|CLM] train=4.4810  mask=12.5%  norm=0.939  lr=6.33e-05  dt=  37.3ms  words=75,833,344
[E06  1518/1548 G   9257|CLM] train=1.9679  mask=12.5%  norm=0.825  lr=6.32e-05  dt=  37.3ms  words=75,841,536
[E06  1519/1548 G   9258|CLM] train=3.6440  mask=12.5%  norm=0.929  lr=6.32e-05  dt=  37.2ms  words=75,849,728
[E06  1520/1548 G   9259|CLM] train=4.0147  mask=12.5%  norm=0.794  lr=6.32e-05  dt=  37.2ms  words=75,857,920
[E06  1521/1548 G   9260|CLM] train=4.2958  mask=12.5%  norm=0.999  lr=6.32e-05  dt=  37.1ms  words=75,866,112
[E06  1522/1548 G   9261|CLM] train=2.5564  mask=12.5%  norm=0.693  lr=6.31e-05  dt=  37.3ms  words=75,874,304
[E06  1523/1548 G   9262|CLM] train=4.1160  mask=12.5%  norm=0.961  lr=6.31e-05  dt=  37.5ms  words=75,882,496
[E06  1524/1548 G   9263|CLM] train=4.3384  mask=12.5%  norm=0.977  lr=6.31e-05  dt=  37.0ms  words=75,890,688
[E06  1525/1548 G   9264|CLM] train=4.1140  mask=12.5%  norm=0.867  lr=6.30e-05  dt=  37.2ms  words=75,898,880
[E06  1526/1548 G   9265|CLM] train=4.3400  mask=12.5%  norm=0.848  lr=6.30e-05  dt=  37.3ms  words=75,907,072
[E06  1527/1548 G   9266|CLM] train=1.9604  mask=12.5%  norm=0.690  lr=6.30e-05  dt=  37.0ms  words=75,915,264
[E06  1528/1548 G   9267|CLM] train=3.6594  mask=12.5%  norm=0.922  lr=6.30e-05  dt=  37.3ms  words=75,923,456
[E06  1529/1548 G   9268|CLM] train=2.0556  mask=12.5%  norm=0.721  lr=6.29e-05  dt=  37.2ms  words=75,931,648
[E06  1530/1548 G   9269|CLM] train=4.4792  mask=12.5%  norm=0.982  lr=6.29e-05  dt=  37.0ms  words=75,939,840
[E06  1531/1548 G   9270|CLM] train=3.9749  mask=12.5%  norm=0.948  lr=6.29e-05  dt=  37.0ms  words=75,948,032
[E06  1532/1548 G   9271|CLM] train=4.1896  mask=12.5%  norm=0.917  lr=6.28e-05  dt=  37.0ms  words=75,956,224
[E06  1533/1548 G   9272|CLM] train=1.8226  mask=12.5%  norm=0.762  lr=6.28e-05  dt=  37.1ms  words=75,964,416
[E06  1534/1548 G   9273|CLM] train=4.6317  mask=12.5%  norm=0.893  lr=6.28e-05  dt=  37.1ms  words=75,972,608
[E06  1535/1548 G   9274|CLM] train=3.5476  mask=12.5%  norm=0.802  lr=6.28e-05  dt=  37.4ms  words=75,980,800
[E06  1536/1548 G   9275|CLM] train=3.8185  mask=12.5%  norm=0.974  lr=6.27e-05  dt=  37.3ms  words=75,988,992
[E06  1537/1548 G   9276|CLM] train=3.5746  mask=12.5%  norm=0.738  lr=6.27e-05  dt=  37.4ms  words=75,997,184
[E06  1538/1548 G   9277|CLM] train=2.4614  mask=12.5%  norm=0.831  lr=6.27e-05  dt=  36.9ms  words=76,005,376
[E06  1539/1548 G   9278|CLM] train=4.0553  mask=12.5%  norm=0.849  lr=6.26e-05  dt=  37.2ms  words=76,013,568
[E06  1540/1548 G   9279|CLM] train=4.0430  mask=12.5%  norm=0.831  lr=6.26e-05  dt=  37.1ms  words=76,021,760
[E06  1541/1548 G   9280|CLM] train=2.2610  mask=12.5%  norm=0.750  lr=6.26e-05  dt=  37.3ms  words=76,029,952
[E06  1542/1548 G   9281|CLM] train=3.7391  mask=12.5%  norm=0.827  lr=6.25e-05  dt=  37.5ms  words=76,038,144
[E06  1543/1548 G   9282|CLM] train=3.8724  mask=12.5%  norm=0.964  lr=6.25e-05  dt=  37.2ms  words=76,046,336
[E06  1544/1548 G   9283|CLM] train=4.0641  mask=12.5%  norm=0.872  lr=6.25e-05  dt=  37.3ms  words=76,054,528
[E06  1545/1548 G   9284|CLM] train=3.9489  mask=12.5%  norm=0.825  lr=6.25e-05  dt=  37.5ms  words=76,062,720
[E06  1546/1548 G   9285|CLM] train=2.3129  mask=12.5%  norm=0.894  lr=6.24e-05  dt=  37.2ms  words=76,070,912
[E06  1547/1548 G   9286|CLM] train=4.1873  mask=12.5%  norm=0.892  lr=6.24e-05  dt=  37.3ms  words=76,079,104
[E06  1548/1548 G   9287|CLM] train=3.9487  mask=12.5%  norm=0.836  lr=6.24e-05  dt=  37.3ms  words=76,087,296
[E07     1/1548 G   9288|CLM] train=3.7779  mask=12.5%  norm=0.980  lr=6.23e-05  dt=  37.4ms  words=76,095,488
[E07     2/1548 G   9289|CLM] train=2.1833  mask=12.5%  norm=0.736  lr=6.23e-05  dt=  37.4ms  words=76,103,680
[E07     3/1548 G   9290|CLM] train=2.5678  mask=12.5%  norm=0.933  lr=6.23e-05  dt=  37.0ms  words=76,111,872
[E07     4/1548 G   9291|CLM] train=4.5378  mask=12.5%  norm=1.178  lr=6.23e-05  dt=  37.4ms  words=76,120,064
[E07     5/1548 G   9292|CLM] train=3.8894  mask=12.5%  norm=0.830  lr=6.22e-05  dt=  37.5ms  words=76,128,256
[E07     6/1548 G   9293|CLM] train=4.2109  mask=12.5%  norm=0.869  lr=6.22e-05  dt=  37.3ms  words=76,136,448
[E07     7/1548 G   9294|CLM] train=3.7225  mask=12.5%  norm=0.831  lr=6.22e-05  dt=  37.3ms  words=76,144,640
[E07     8/1548 G   9295|CLM] train=2.0303  mask=12.5%  norm=0.773  lr=6.21e-05  dt=  37.2ms  words=76,152,832
[E07     9/1548 G   9296|CLM] train=4.0387  mask=12.5%  norm=0.955  lr=6.21e-05  dt=  37.2ms  words=76,161,024
[E07    10/1548 G   9297|CLM] train=2.0033  mask=12.5%  norm=0.590  lr=6.21e-05  dt=  37.4ms  words=76,169,216
[E07    11/1548 G   9298|CLM] train=2.1165  mask=12.5%  norm=0.732  lr=6.21e-05  dt=  37.3ms  words=76,177,408
[E07    12/1548 G   9299|CLM] train=4.1133  mask=12.5%  norm=0.793  lr=6.20e-05  dt=  37.2ms  words=76,185,600
[E07    13/1548 G   9300|CLM] train=2.4796  mask=12.5%  norm=0.634  lr=6.20e-05  dt=  37.2ms  words=76,193,792
[E07    14/1548 G   9301|CLM] train=3.9670  mask=12.5%  norm=1.031  lr=6.20e-05  dt=  37.3ms  words=76,201,984
[E07    15/1548 G   9302|CLM] train=3.7815  mask=12.5%  norm=0.861  lr=6.19e-05  dt=  37.3ms  words=76,210,176
[E07    16/1548 G   9303|CLM] train=3.7961  mask=12.5%  norm=0.880  lr=6.19e-05  dt=  37.4ms  words=76,218,368
[E07    17/1548 G   9304|CLM] train=2.0989  mask=12.5%  norm=0.599  lr=6.19e-05  dt=  37.2ms  words=76,226,560
[E07    18/1548 G   9305|CLM] train=3.9801  mask=12.5%  norm=0.796  lr=6.19e-05  dt=  37.2ms  words=76,234,752
[E07    19/1548 G   9306|CLM] train=4.2363  mask=12.5%  norm=0.841  lr=6.18e-05  dt=  37.2ms  words=76,242,944
[E07    20/1548 G   9307|CLM] train=4.2185  mask=12.5%  norm=0.833  lr=6.18e-05  dt=  37.5ms  words=76,251,136
[E07    21/1548 G   9308|CLM] train=1.7140  mask=12.5%  norm=0.686  lr=6.18e-05  dt=  37.1ms  words=76,259,328
[E07    22/1548 G   9309|CLM] train=2.2307  mask=12.5%  norm=0.703  lr=6.17e-05  dt=  37.1ms  words=76,267,520
[E07    23/1548 G   9310|CLM] train=2.1268  mask=12.5%  norm=0.626  lr=6.17e-05  dt=  37.2ms  words=76,275,712
[E07    24/1548 G   9311|CLM] train=2.2603  mask=12.5%  norm=0.659  lr=6.17e-05  dt=  37.1ms  words=76,283,904
[E07    25/1548 G   9312|CLM] train=3.7539  mask=12.5%  norm=0.861  lr=6.17e-05  dt=  37.2ms  words=76,292,096
[E07    26/1548 G   9313|CLM] train=2.0795  mask=12.5%  norm=0.837  lr=6.16e-05  dt=  37.2ms  words=76,300,288
[E07    27/1548 G   9314|CLM] train=2.1529  mask=12.5%  norm=0.805  lr=6.16e-05  dt=  37.0ms  words=76,308,480
[E07    28/1548 G   9315|CLM] train=4.0682  mask=12.5%  norm=0.846  lr=6.16e-05  dt=  37.1ms  words=76,316,672
[E07    29/1548 G   9316|CLM] train=4.2072  mask=12.5%  norm=0.810  lr=6.15e-05  dt=  37.1ms  words=76,324,864
[E07    30/1548 G   9317|CLM] train=2.0644  mask=12.5%  norm=0.662  lr=6.15e-05  dt=  37.2ms  words=76,333,056
[E07    31/1548 G   9318|CLM] train=4.1337  mask=12.5%  norm=0.879  lr=6.15e-05  dt=  37.0ms  words=76,341,248
[E07    32/1548 G   9319|CLM] train=3.4315  mask=12.5%  norm=0.770  lr=6.15e-05  dt=  37.3ms  words=76,349,440
[E07    33/1548 G   9320|CLM] train=3.5489  mask=12.5%  norm=0.786  lr=6.14e-05  dt=  37.1ms  words=76,357,632
[E07    34/1548 G   9321|CLM] train=4.2043  mask=12.5%  norm=0.805  lr=6.14e-05  dt=  37.1ms  words=76,365,824
[E07    35/1548 G   9322|CLM] train=2.2054  mask=12.5%  norm=0.856  lr=6.14e-05  dt=  37.3ms  words=76,374,016
[E07    36/1548 G   9323|CLM] train=2.1028  mask=12.5%  norm=0.693  lr=6.13e-05  dt=  37.2ms  words=76,382,208
[E07    37/1548 G   9324|CLM] train=2.4886  mask=12.5%  norm=0.719  lr=6.13e-05  dt=  36.9ms  words=76,390,400
[E07    38/1548 G   9325|CLM] train=2.4076  mask=12.5%  norm=0.762  lr=6.13e-05  dt=  36.9ms  words=76,398,592
[E07    39/1548 G   9326|CLM] train=1.8625  mask=12.5%  norm=0.879  lr=6.13e-05  dt=  36.9ms  words=76,406,784
[E07    40/1548 G   9327|CLM] train=4.1514  mask=12.5%  norm=0.865  lr=6.12e-05  dt=  37.2ms  words=76,414,976
[E07    41/1548 G   9328|CLM] train=2.2931  mask=12.5%  norm=0.724  lr=6.12e-05  dt=  37.1ms  words=76,423,168
[E07    42/1548 G   9329|CLM] train=2.1136  mask=12.5%  norm=0.776  lr=6.12e-05  dt=  37.2ms  words=76,431,360
[E07    43/1548 G   9330|CLM] train=3.9109  mask=12.5%  norm=0.911  lr=6.11e-05  dt=  37.6ms  words=76,439,552
[E07    44/1548 G   9331|CLM] train=1.7623  mask=12.5%  norm=0.841  lr=6.11e-05  dt=  37.2ms  words=76,447,744
[E07    45/1548 G   9332|CLM] train=4.6356  mask=12.5%  norm=0.907  lr=6.11e-05  dt=  37.6ms  words=76,455,936
[E07    46/1548 G   9333|CLM] train=4.8083  mask=12.5%  norm=0.860  lr=6.11e-05  dt=  38.2ms  words=76,464,128
[E07    47/1548 G   9334|CLM] train=4.2182  mask=12.5%  norm=0.878  lr=6.10e-05  dt=  38.8ms  words=76,472,320
[E07    48/1548 G   9335|CLM] train=3.7727  mask=12.5%  norm=0.889  lr=6.10e-05  dt=  37.2ms  words=76,480,512
[E07    49/1548 G   9336|CLM] train=2.0492  mask=12.5%  norm=0.770  lr=6.10e-05  dt=  37.0ms  words=76,488,704
[E07    50/1548 G   9337|CLM] train=4.4093  mask=12.5%  norm=0.923  lr=6.09e-05  dt=  37.3ms  words=76,496,896
[E07    51/1548 G   9338|CLM] train=2.0534  mask=12.5%  norm=0.793  lr=6.09e-05  dt=  37.1ms  words=76,505,088
[E07    52/1548 G   9339|CLM] train=2.5616  mask=12.5%  norm=0.848  lr=6.09e-05  dt=  37.2ms  words=76,513,280
[E07    53/1548 G   9340|CLM] train=2.0439  mask=12.5%  norm=0.814  lr=6.09e-05  dt=  37.1ms  words=76,521,472
[E07    54/1548 G   9341|CLM] train=1.9956  mask=12.5%  norm=0.741  lr=6.08e-05  dt=  37.0ms  words=76,529,664
[E07    55/1548 G   9342|CLM] train=1.9453  mask=12.5%  norm=0.730  lr=6.08e-05  dt=  37.3ms  words=76,537,856
[E07    56/1548 G   9343|CLM] train=2.5162  mask=12.5%  norm=0.744  lr=6.08e-05  dt=  37.3ms  words=76,546,048
[E07    57/1548 G   9344|CLM] train=3.8535  mask=12.5%  norm=0.859  lr=6.07e-05  dt=  37.0ms  words=76,554,240
[E07    58/1548 G   9345|CLM] train=3.7982  mask=12.5%  norm=0.822  lr=6.07e-05  dt=  37.3ms  words=76,562,432
[E07    59/1548 G   9346|CLM] train=3.7811  mask=12.5%  norm=0.900  lr=6.07e-05  dt=  37.2ms  words=76,570,624
[E07    60/1548 G   9347|CLM] train=3.8604  mask=12.5%  norm=0.939  lr=6.07e-05  dt=  37.1ms  words=76,578,816
[E07    61/1548 G   9348|CLM] train=1.7771  mask=12.5%  norm=0.717  lr=6.06e-05  dt=  37.0ms  words=76,587,008
[E07    62/1548 G   9349|CLM] train=4.0992  mask=12.5%  norm=1.046  lr=6.06e-05  dt=  37.0ms  words=76,595,200
[E07    63/1548 G   9350|CLM] train=3.7459  mask=12.4%  norm=0.766  lr=6.06e-05  dt=  37.1ms  words=76,603,392
[E07    64/1548 G   9351|CLM] train=4.5400  mask=12.4%  norm=0.880  lr=6.05e-05  dt=  37.1ms  words=76,611,584
[E07    65/1548 G   9352|CLM] train=2.2162  mask=12.4%  norm=0.742  lr=6.05e-05  dt=  37.2ms  words=76,619,776
[E07    66/1548 G   9353|CLM] train=4.3774  mask=12.4%  norm=0.982  lr=6.05e-05  dt=  37.2ms  words=76,627,968
[E07    67/1548 G   9354|CLM] train=3.5913  mask=12.4%  norm=0.852  lr=6.05e-05  dt=  36.9ms  words=76,636,160
[E07    68/1548 G   9355|CLM] train=3.3555  mask=12.4%  norm=0.770  lr=6.04e-05  dt=  36.9ms  words=76,644,352
[E07    69/1548 G   9356|CLM] train=3.7208  mask=12.4%  norm=0.852  lr=6.04e-05  dt=  37.2ms  words=76,652,544
[E07    70/1548 G   9357|CLM] train=4.3779  mask=12.4%  norm=1.164  lr=6.04e-05  dt=  37.2ms  words=76,660,736
[E07    71/1548 G   9358|CLM] train=4.3562  mask=12.4%  norm=0.870  lr=6.04e-05  dt=  37.2ms  words=76,668,928
[E07    72/1548 G   9359|CLM] train=2.6063  mask=12.4%  norm=0.697  lr=6.03e-05  dt=  37.1ms  words=76,677,120
[E07    73/1548 G   9360|CLM] train=2.0922  mask=12.4%  norm=0.679  lr=6.03e-05  dt=  37.2ms  words=76,685,312
[E07    74/1548 G   9361|CLM] train=4.4276  mask=12.4%  norm=1.076  lr=6.03e-05  dt=  37.2ms  words=76,693,504
[E07    75/1548 G   9362|CLM] train=4.4200  mask=12.4%  norm=0.985  lr=6.02e-05  dt=  37.1ms  words=76,701,696
[E07    76/1548 G   9363|CLM] train=4.9733  mask=12.4%  norm=0.942  lr=6.02e-05  dt=  37.1ms  words=76,709,888
[E07    77/1548 G   9364|CLM] train=2.3553  mask=12.4%  norm=0.639  lr=6.02e-05  dt=  37.1ms  words=76,718,080
[E07    78/1548 G   9365|CLM] train=4.7038  mask=12.4%  norm=1.159  lr=6.02e-05  dt=  37.1ms  words=76,726,272
[E07    79/1548 G   9366|CLM] train=2.1784  mask=12.4%  norm=0.934  lr=6.01e-05  dt=  37.3ms  words=76,734,464
[E07    80/1548 G   9367|CLM] train=2.7029  mask=12.4%  norm=0.758  lr=6.01e-05  dt=  37.1ms  words=76,742,656
[E07    81/1548 G   9368|CLM] train=1.7905  mask=12.4%  norm=0.635  lr=6.01e-05  dt=  37.0ms  words=76,750,848
[E07    82/1548 G   9369|CLM] train=3.7394  mask=12.4%  norm=0.827  lr=6.00e-05  dt=  37.4ms  words=76,759,040
[E07    83/1548 G   9370|CLM] train=3.7512  mask=12.4%  norm=0.860  lr=6.00e-05  dt=  37.1ms  words=76,767,232
[E07    84/1548 G   9371|CLM] train=3.4162  mask=12.4%  norm=0.833  lr=6.00e-05  dt=  37.0ms  words=76,775,424
[E07    85/1548 G   9372|CLM] train=3.9661  mask=12.4%  norm=1.015  lr=6.00e-05  dt=  37.2ms  words=76,783,616
[E07    86/1548 G   9373|CLM] train=3.8187  mask=12.4%  norm=0.747  lr=5.99e-05  dt=  37.1ms  words=76,791,808
[E07    87/1548 G   9374|CLM] train=2.1779  mask=12.4%  norm=0.691  lr=5.99e-05  dt=  37.0ms  words=76,800,000
[E07    88/1548 G   9375|CLM] train=4.0215  mask=12.4%  norm=0.806  lr=5.99e-05  dt=  37.2ms  words=76,808,192
[E07    89/1548 G   9376|CLM] train=4.3272  mask=12.4%  norm=1.021  lr=5.98e-05  dt=  37.2ms  words=76,816,384
[E07    90/1548 G   9377|CLM] train=2.1293  mask=12.4%  norm=0.806  lr=5.98e-05  dt=  37.1ms  words=76,824,576
[E07    91/1548 G   9378|CLM] train=2.3424  mask=12.4%  norm=0.693  lr=5.98e-05  dt=  37.3ms  words=76,832,768
[E07    92/1548 G   9379|CLM] train=3.7858  mask=12.4%  norm=0.769  lr=5.98e-05  dt=  37.3ms  words=76,840,960
[E07    93/1548 G   9380|CLM] train=3.9364  mask=12.4%  norm=0.810  lr=5.97e-05  dt=  37.0ms  words=76,849,152
[E07    94/1548 G   9381|CLM] train=4.3560  mask=12.4%  norm=1.578  lr=5.97e-05  dt=  36.9ms  words=76,857,344
[E07    95/1548 G   9382|CLM] train=2.2143  mask=12.4%  norm=0.652  lr=5.97e-05  dt=  37.0ms  words=76,865,536
[E07    96/1548 G   9383|CLM] train=2.2802  mask=12.4%  norm=0.730  lr=5.96e-05  dt=  37.2ms  words=76,873,728
[E07    97/1548 G   9384|CLM] train=4.0330  mask=12.4%  norm=0.843  lr=5.96e-05  dt=  37.1ms  words=76,881,920
[E07    98/1548 G   9385|CLM] train=3.4114  mask=12.4%  norm=0.828  lr=5.96e-05  dt=  37.2ms  words=76,890,112
[E07    99/1548 G   9386|CLM] train=2.2253  mask=12.4%  norm=0.740  lr=5.96e-05  dt=  38.2ms  words=76,898,304
[E07   100/1548 G   9387|CLM] train=3.4960  mask=12.4%  norm=0.715  lr=5.95e-05  dt=  38.9ms  words=76,906,496
[E07   101/1548 G   9388|CLM] train=3.6127  mask=12.4%  norm=0.829  lr=5.95e-05  dt=  37.3ms  words=76,914,688
[E07   102/1548 G   9389|CLM] train=4.2233  mask=12.4%  norm=0.872  lr=5.95e-05  dt=  37.2ms  words=76,922,880
[E07   103/1548 G   9390|CLM] train=3.8573  mask=12.4%  norm=0.756  lr=5.95e-05  dt=  37.3ms  words=76,931,072
[E07   104/1548 G   9391|CLM] train=4.0205  mask=12.4%  norm=0.789  lr=5.94e-05  dt=  37.2ms  words=76,939,264
[E07   105/1548 G   9392|CLM] train=2.0478  mask=12.4%  norm=0.769  lr=5.94e-05  dt=  37.2ms  words=76,947,456
[E07   106/1548 G   9393|CLM] train=3.8578  mask=12.4%  norm=1.422  lr=5.94e-05  dt=  37.2ms  words=76,955,648
[E07   107/1548 G   9394|CLM] train=5.3600  mask=12.4%  norm=1.152  lr=5.93e-05  dt=  37.0ms  words=76,963,840
[E07   108/1548 G   9395|CLM] train=4.1830  mask=12.4%  norm=0.854  lr=5.93e-05  dt=  37.2ms  words=76,972,032
[E07   109/1548 G   9396|CLM] train=3.3505  mask=12.4%  norm=0.744  lr=5.93e-05  dt=  37.2ms  words=76,980,224
[E07   110/1548 G   9397|CLM] train=2.0932  mask=12.4%  norm=0.725  lr=5.93e-05  dt=  37.0ms  words=76,988,416
[E07   111/1548 G   9398|CLM] train=3.6241  mask=12.4%  norm=0.780  lr=5.92e-05  dt=  36.9ms  words=76,996,608
[E07   112/1548 G   9399|CLM] train=2.3600  mask=12.4%  norm=0.644  lr=5.92e-05  dt=  37.0ms  words=77,004,800
[E07   113/1548 G   9400|CLM] train=2.5919  mask=12.4%  norm=0.850  lr=5.92e-05  dt=  37.1ms  words=77,012,992
[E07   114/1548 G   9401|CLM] train=4.5324  mask=12.4%  norm=0.955  lr=5.91e-05  dt=  37.2ms  words=77,021,184
[E07   115/1548 G   9402|CLM] train=4.3405  mask=12.4%  norm=2.185  lr=5.91e-05  dt=  37.3ms  words=77,029,376
[E07   116/1548 G   9403|CLM] train=4.3964  mask=12.4%  norm=0.903  lr=5.91e-05  dt=  37.1ms  words=77,037,568
[E07   117/1548 G   9404|CLM] train=3.7164  mask=12.4%  norm=0.830  lr=5.91e-05  dt=  37.0ms  words=77,045,760
[E07   118/1548 G   9405|CLM] train=4.2473  mask=12.4%  norm=0.844  lr=5.90e-05  dt=  37.1ms  words=77,053,952
[E07   119/1548 G   9406|CLM] train=4.0370  mask=12.4%  norm=0.973  lr=5.90e-05  dt=  37.2ms  words=77,062,144
[E07   120/1548 G   9407|CLM] train=1.9753  mask=12.4%  norm=0.792  lr=5.90e-05  dt=  37.2ms  words=77,070,336
[E07   121/1548 G   9408|CLM] train=2.5897  mask=12.4%  norm=0.698  lr=5.89e-05  dt=  37.0ms  words=77,078,528
[E07   122/1548 G   9409|CLM] train=3.7399  mask=12.4%  norm=1.005  lr=5.89e-05  dt=  37.0ms  words=77,086,720
[E07   123/1548 G   9410|CLM] train=2.4286  mask=12.4%  norm=0.914  lr=5.89e-05  dt=  37.5ms  words=77,094,912
[E07   124/1548 G   9411|CLM] train=1.9698  mask=12.4%  norm=0.819  lr=5.89e-05  dt=  37.1ms  words=77,103,104
[E07   125/1548 G   9412|CLM] train=4.0980  mask=12.4%  norm=0.892  lr=5.88e-05  dt=  37.1ms  words=77,111,296
[E07   126/1548 G   9413|CLM] train=2.0976  mask=12.4%  norm=1.095  lr=5.88e-05  dt=  37.1ms  words=77,119,488
[E07   127/1548 G   9414|CLM] train=3.8909  mask=12.4%  norm=0.820  lr=5.88e-05  dt=  37.3ms  words=77,127,680
[E07   128/1548 G   9415|CLM] train=4.0012  mask=12.4%  norm=1.601  lr=5.88e-05  dt=  37.1ms  words=77,135,872
[E07   129/1548 G   9416|CLM] train=2.3745  mask=12.4%  norm=0.789  lr=5.87e-05  dt=  37.3ms  words=77,144,064
[E07   130/1548 G   9417|CLM] train=4.0150  mask=12.4%  norm=0.854  lr=5.87e-05  dt=  37.0ms  words=77,152,256
[E07   131/1548 G   9418|CLM] train=3.9368  mask=12.4%  norm=0.812  lr=5.87e-05  dt=  37.4ms  words=77,160,448
[E07   132/1548 G   9419|CLM] train=2.2451  mask=12.4%  norm=0.706  lr=5.86e-05  dt=  37.2ms  words=77,168,640
[E07   133/1548 G   9420|CLM] train=2.4550  mask=12.4%  norm=0.924  lr=5.86e-05  dt=  37.1ms  words=77,176,832
[E07   134/1548 G   9421|CLM] train=3.9915  mask=12.4%  norm=0.867  lr=5.86e-05  dt=  37.3ms  words=77,185,024
[E07   135/1548 G   9422|CLM] train=4.3776  mask=12.4%  norm=0.872  lr=5.86e-05  dt=  37.3ms  words=77,193,216
[E07   136/1548 G   9423|CLM] train=4.3552  mask=12.4%  norm=0.881  lr=5.85e-05  dt=  37.1ms  words=77,201,408
[E07   137/1548 G   9424|CLM] train=1.9983  mask=12.4%  norm=0.687  lr=5.85e-05  dt=  37.0ms  words=77,209,600
[E07   138/1548 G   9425|CLM] train=3.5420  mask=12.4%  norm=0.842  lr=5.85e-05  dt=  37.3ms  words=77,217,792
[E07   139/1548 G   9426|CLM] train=2.4606  mask=12.4%  norm=0.671  lr=5.84e-05  dt=  37.1ms  words=77,225,984
[E07   140/1548 G   9427|CLM] train=3.9610  mask=12.4%  norm=0.845  lr=5.84e-05  dt=  37.1ms  words=77,234,176
[E07   141/1548 G   9428|CLM] train=4.0025  mask=12.4%  norm=0.811  lr=5.84e-05  dt=  37.1ms  words=77,242,368
[E07   142/1548 G   9429|CLM] train=4.0857  mask=12.4%  norm=0.864  lr=5.84e-05  dt=  37.1ms  words=77,250,560
[E07   143/1548 G   9430|CLM] train=4.9239  mask=12.4%  norm=0.988  lr=5.83e-05  dt=  37.1ms  words=77,258,752
[E07   144/1548 G   9431|CLM] train=4.0688  mask=12.4%  norm=1.369  lr=5.83e-05  dt=  37.1ms  words=77,266,944
[E07   145/1548 G   9432|CLM] train=2.0199  mask=12.4%  norm=0.712  lr=5.83e-05  dt=  37.2ms  words=77,275,136
[E07   146/1548 G   9433|CLM] train=4.1188  mask=12.4%  norm=0.851  lr=5.83e-05  dt=  37.0ms  words=77,283,328
[E07   147/1548 G   9434|CLM] train=2.5173  mask=12.4%  norm=0.677  lr=5.82e-05  dt=  37.3ms  words=77,291,520
[E07   148/1548 G   9435|CLM] train=3.8551  mask=12.4%  norm=0.906  lr=5.82e-05  dt=  38.2ms  words=77,299,712
[E07   149/1548 G   9436|CLM] train=4.0739  mask=12.4%  norm=0.901  lr=5.82e-05  dt=  37.2ms  words=77,307,904
[E07   150/1548 G   9437|CLM] train=2.5777  mask=12.4%  norm=0.690  lr=5.81e-05  dt=  37.8ms  words=77,316,096
[E07   151/1548 G   9438|CLM] train=3.8931  mask=12.4%  norm=0.926  lr=5.81e-05  dt=  39.1ms  words=77,324,288
[E07   152/1548 G   9439|CLM] train=2.7670  mask=12.4%  norm=1.039  lr=5.81e-05  dt=  37.8ms  words=77,332,480
[E07   153/1548 G   9440|CLM] train=3.8137  mask=12.4%  norm=0.800  lr=5.81e-05  dt=  37.8ms  words=77,340,672
[E07   154/1548 G   9441|CLM] train=2.6445  mask=12.4%  norm=0.702  lr=5.80e-05  dt=  37.7ms  words=77,348,864
[E07   155/1548 G   9442|CLM] train=2.2765  mask=12.4%  norm=0.730  lr=5.80e-05  dt=  37.5ms  words=77,357,056
[E07   156/1548 G   9443|CLM] train=4.0694  mask=12.4%  norm=0.861  lr=5.80e-05  dt=  37.4ms  words=77,365,248
[E07   157/1548 G   9444|CLM] train=3.4716  mask=12.4%  norm=0.781  lr=5.79e-05  dt=  37.1ms  words=77,373,440
[E07   158/1548 G   9445|CLM] train=4.0214  mask=12.4%  norm=0.828  lr=5.79e-05  dt=  37.2ms  words=77,381,632
[E07   159/1548 G   9446|CLM] train=2.3333  mask=12.4%  norm=0.803  lr=5.79e-05  dt=  37.1ms  words=77,389,824
[E07   160/1548 G   9447|CLM] train=3.8471  mask=12.4%  norm=0.751  lr=5.79e-05  dt=  37.2ms  words=77,398,016
[E07   161/1548 G   9448|CLM] train=4.0162  mask=12.4%  norm=0.966  lr=5.78e-05  dt=  37.2ms  words=77,406,208
[E07   162/1548 G   9449|CLM] train=2.2108  mask=12.4%  norm=0.712  lr=5.78e-05  dt=  37.2ms  words=77,414,400
[E07   163/1548 G   9450|CLM] train=3.7834  mask=12.4%  norm=0.726  lr=5.78e-05  dt=  37.2ms  words=77,422,592
[E07   164/1548 G   9451|CLM] train=3.9987  mask=12.4%  norm=0.848  lr=5.78e-05  dt=  37.1ms  words=77,430,784
[E07   165/1548 G   9452|CLM] train=2.8464  mask=12.4%  norm=0.825  lr=5.77e-05  dt=  37.2ms  words=77,438,976
[E07   166/1548 G   9453|CLM] train=2.2564  mask=12.4%  norm=0.773  lr=5.77e-05  dt=  37.3ms  words=77,447,168
[E07   167/1548 G   9454|CLM] train=4.3702  mask=12.4%  norm=1.280  lr=5.77e-05  dt=  37.2ms  words=77,455,360
[E07   168/1548 G   9455|CLM] train=2.0823  mask=12.4%  norm=0.709  lr=5.76e-05  dt=  37.2ms  words=77,463,552
[E07   169/1548 G   9456|CLM] train=2.0336  mask=12.4%  norm=0.726  lr=5.76e-05  dt=  37.2ms  words=77,471,744
[E07   170/1548 G   9457|CLM] train=2.3659  mask=12.4%  norm=0.722  lr=5.76e-05  dt=  37.0ms  words=77,479,936
[E07   171/1548 G   9458|CLM] train=2.3656  mask=12.4%  norm=0.654  lr=5.76e-05  dt=  37.3ms  words=77,488,128
[E07   172/1548 G   9459|CLM] train=2.3825  mask=12.4%  norm=0.702  lr=5.75e-05  dt=  37.4ms  words=77,496,320
[E07   173/1548 G   9460|CLM] train=1.9016  mask=12.4%  norm=0.844  lr=5.75e-05  dt=  37.0ms  words=77,504,512
[E07   174/1548 G   9461|CLM] train=3.7952  mask=12.4%  norm=0.865  lr=5.75e-05  dt=  37.3ms  words=77,512,704
[E07   175/1548 G   9462|CLM] train=4.2324  mask=12.4%  norm=1.040  lr=5.75e-05  dt=  37.3ms  words=77,520,896
[E07   176/1548 G   9463|CLM] train=1.8494  mask=12.4%  norm=0.595  lr=5.74e-05  dt=  37.1ms  words=77,529,088
[E07   177/1548 G   9464|CLM] train=2.0527  mask=12.4%  norm=0.734  lr=5.74e-05  dt=  37.1ms  words=77,537,280
[E07   178/1548 G   9465|CLM] train=3.5341  mask=12.4%  norm=0.868  lr=5.74e-05  dt=  37.3ms  words=77,545,472
[E07   179/1548 G   9466|CLM] train=4.3632  mask=12.4%  norm=0.931  lr=5.73e-05  dt=  37.2ms  words=77,553,664
[E07   180/1548 G   9467|CLM] train=3.7621  mask=12.4%  norm=0.808  lr=5.73e-05  dt=  37.1ms  words=77,561,856
[E07   181/1548 G   9468|CLM] train=4.4348  mask=12.4%  norm=0.915  lr=5.73e-05  dt=  37.0ms  words=77,570,048
[E07   182/1548 G   9469|CLM] train=4.0326  mask=12.4%  norm=0.890  lr=5.73e-05  dt=  37.2ms  words=77,578,240
[E07   183/1548 G   9470|CLM] train=3.2589  mask=12.4%  norm=0.854  lr=5.72e-05  dt=  37.1ms  words=77,586,432
[E07   184/1548 G   9471|CLM] train=2.2005  mask=12.4%  norm=0.655  lr=5.72e-05  dt=  37.2ms  words=77,594,624
[E07   185/1548 G   9472|CLM] train=2.5497  mask=12.4%  norm=0.758  lr=5.72e-05  dt=  37.1ms  words=77,602,816
[E07   186/1548 G   9473|CLM] train=2.4314  mask=12.4%  norm=0.696  lr=5.71e-05  dt=  37.0ms  words=77,611,008
[E07   187/1548 G   9474|CLM] train=3.5922  mask=12.3%  norm=1.314  lr=5.71e-05  dt=  37.3ms  words=77,619,200
[E07   188/1548 G   9475|CLM] train=2.0084  mask=12.3%  norm=0.707  lr=5.71e-05  dt=  37.3ms  words=77,627,392
[E07   189/1548 G   9476|CLM] train=3.9277  mask=12.3%  norm=0.827  lr=5.71e-05  dt=  37.1ms  words=77,635,584
[E07   190/1548 G   9477|CLM] train=2.1818  mask=12.3%  norm=0.806  lr=5.70e-05  dt=  37.2ms  words=77,643,776
[E07   191/1548 G   9478|CLM] train=4.0869  mask=12.3%  norm=0.940  lr=5.70e-05  dt=  37.3ms  words=77,651,968
[E07   192/1548 G   9479|CLM] train=4.1835  mask=12.3%  norm=0.857  lr=5.70e-05  dt=  37.1ms  words=77,660,160
[E07   193/1548 G   9480|CLM] train=3.8021  mask=12.3%  norm=0.775  lr=5.70e-05  dt=  37.0ms  words=77,668,352
[E07   194/1548 G   9481|CLM] train=4.2153  mask=12.3%  norm=0.936  lr=5.69e-05  dt=  37.1ms  words=77,676,544
[E07   195/1548 G   9482|CLM] train=2.6626  mask=12.3%  norm=0.710  lr=5.69e-05  dt=  37.3ms  words=77,684,736
[E07   196/1548 G   9483|CLM] train=3.4969  mask=12.3%  norm=0.856  lr=5.69e-05  dt=  37.2ms  words=77,692,928
[E07   197/1548 G   9484|CLM] train=1.8174  mask=12.3%  norm=0.662  lr=5.68e-05  dt=  37.2ms  words=77,701,120
[E07   198/1548 G   9485|CLM] train=4.0296  mask=12.3%  norm=0.889  lr=5.68e-05  dt=  37.1ms  words=77,709,312
[E07   199/1548 G   9486|CLM] train=4.4746  mask=12.3%  norm=0.895  lr=5.68e-05  dt=  37.2ms  words=77,717,504
[E07   200/1548 G   9487|CLM] train=3.3770  mask=12.3%  norm=0.738  lr=5.68e-05  dt=  37.1ms  words=77,725,696
[E07   201/1548 G   9488|CLM] train=3.7260  mask=12.3%  norm=0.805  lr=5.67e-05  dt=  37.2ms  words=77,733,888
[E07   202/1548 G   9489|CLM] train=3.8169  mask=12.3%  norm=0.909  lr=5.67e-05  dt=  37.0ms  words=77,742,080
[E07   203/1548 G   9490|CLM] train=4.0824  mask=12.3%  norm=0.940  lr=5.67e-05  dt=  37.1ms  words=77,750,272
[E07   204/1548 G   9491|CLM] train=3.5371  mask=12.3%  norm=0.848  lr=5.67e-05  dt=  37.3ms  words=77,758,464
[E07   205/1548 G   9492|CLM] train=1.9974  mask=12.3%  norm=0.733  lr=5.66e-05  dt=  37.2ms  words=77,766,656
[E07   206/1548 G   9493|CLM] train=3.5130  mask=12.3%  norm=0.826  lr=5.66e-05  dt=  37.3ms  words=77,774,848
[E07   207/1548 G   9494|CLM] train=3.8950  mask=12.3%  norm=0.777  lr=5.66e-05  dt=  37.4ms  words=77,783,040
[E07   208/1548 G   9495|CLM] train=4.5331  mask=12.3%  norm=1.125  lr=5.65e-05  dt=  37.2ms  words=77,791,232
[E07   209/1548 G   9496|CLM] train=3.7925  mask=12.3%  norm=0.981  lr=5.65e-05  dt=  37.3ms  words=77,799,424
[E07   210/1548 G   9497|CLM] train=2.4855  mask=12.3%  norm=0.694  lr=5.65e-05  dt=  37.3ms  words=77,807,616
[E07   211/1548 G   9498|CLM] train=3.9807  mask=12.3%  norm=0.802  lr=5.65e-05  dt=  37.1ms  words=77,815,808
[E07   212/1548 G   9499|CLM] train=2.3377  mask=12.3%  norm=0.644  lr=5.64e-05  dt=  37.0ms  words=77,824,000
[E07   213/1548 G   9500|CLM] train=3.9117  mask=12.3%  norm=0.810  lr=5.64e-05  dt=  37.3ms  words=77,832,192
[E07   214/1548 G   9501|CLM] train=2.1637  mask=12.3%  norm=0.691  lr=5.64e-05  dt=  37.2ms  words=77,840,384
[E07   215/1548 G   9502|CLM] train=4.0520  mask=12.3%  norm=0.850  lr=5.64e-05  dt=  37.1ms  words=77,848,576
[E07   216/1548 G   9503|CLM] train=3.9693  mask=12.3%  norm=0.821  lr=5.63e-05  dt=  37.1ms  words=77,856,768
[E07   217/1548 G   9504|CLM] train=3.7057  mask=12.3%  norm=0.818  lr=5.63e-05  dt=  37.2ms  words=77,864,960
[E07   218/1548 G   9505|CLM] train=4.2410  mask=12.3%  norm=1.232  lr=5.63e-05  dt=  37.1ms  words=77,873,152
[E07   219/1548 G   9506|CLM] train=2.0496  mask=12.3%  norm=0.716  lr=5.62e-05  dt=  37.1ms  words=77,881,344
[E07   220/1548 G   9507|CLM] train=4.2543  mask=12.3%  norm=1.174  lr=5.62e-05  dt=  37.2ms  words=77,889,536
[E07   221/1548 G   9508|CLM] train=2.6619  mask=12.3%  norm=0.743  lr=5.62e-05  dt=  37.2ms  words=77,897,728
[E07   222/1548 G   9509|CLM] train=4.0580  mask=12.3%  norm=0.891  lr=5.62e-05  dt=  37.1ms  words=77,905,920
[E07   223/1548 G   9510|CLM] train=3.8155  mask=12.3%  norm=0.810  lr=5.61e-05  dt=  37.2ms  words=77,914,112
[E07   224/1548 G   9511|CLM] train=2.9355  mask=12.3%  norm=0.772  lr=5.61e-05  dt=  37.0ms  words=77,922,304
[E07   225/1548 G   9512|CLM] train=2.5487  mask=12.3%  norm=0.720  lr=5.61e-05  dt=  37.0ms  words=77,930,496
[E07   226/1548 G   9513|CLM] train=4.3050  mask=12.3%  norm=1.032  lr=5.61e-05  dt=  37.3ms  words=77,938,688
[E07   227/1548 G   9514|CLM] train=2.1183  mask=12.3%  norm=0.709  lr=5.60e-05  dt=  37.2ms  words=77,946,880
[E07   228/1548 G   9515|CLM] train=3.9980  mask=12.3%  norm=0.899  lr=5.60e-05  dt=  37.1ms  words=77,955,072
[E07   229/1548 G   9516|CLM] train=3.5553  mask=12.3%  norm=0.857  lr=5.60e-05  dt=  37.1ms  words=77,963,264
[E07   230/1548 G   9517|CLM] train=3.7711  mask=12.3%  norm=0.873  lr=5.59e-05  dt=  37.4ms  words=77,971,456
[E07   231/1548 G   9518|CLM] train=2.3178  mask=12.3%  norm=0.703  lr=5.59e-05  dt=  37.3ms  words=77,979,648
[E07   232/1548 G   9519|CLM] train=3.4107  mask=12.3%  norm=0.751  lr=5.59e-05  dt=  37.4ms  words=77,987,840
[E07   233/1548 G   9520|CLM] train=2.1337  mask=12.3%  norm=0.824  lr=5.59e-05  dt=  37.4ms  words=77,996,032
[E07   234/1548 G   9521|CLM] train=4.1034  mask=12.3%  norm=0.861  lr=5.58e-05  dt=  37.4ms  words=78,004,224
[E07   235/1548 G   9522|CLM] train=4.0076  mask=12.3%  norm=0.857  lr=5.58e-05  dt=  37.3ms  words=78,012,416
[E07   236/1548 G   9523|CLM] train=4.1581  mask=12.3%  norm=0.967  lr=5.58e-05  dt=  37.1ms  words=78,020,608
[E07   237/1548 G   9524|CLM] train=2.1295  mask=12.3%  norm=0.842  lr=5.58e-05  dt=  37.2ms  words=78,028,800
[E07   238/1548 G   9525|CLM] train=2.1953  mask=12.3%  norm=0.757  lr=5.57e-05  dt=  37.2ms  words=78,036,992
[E07   239/1548 G   9526|CLM] train=3.7123  mask=12.3%  norm=0.863  lr=5.57e-05  dt=  37.1ms  words=78,045,184
[E07   240/1548 G   9527|CLM] train=4.0083  mask=12.3%  norm=0.932  lr=5.57e-05  dt=  37.1ms  words=78,053,376
[E07   241/1548 G   9528|CLM] train=4.6147  mask=12.3%  norm=0.920  lr=5.57e-05  dt=  37.3ms  words=78,061,568
[E07   242/1548 G   9529|CLM] train=4.3663  mask=12.3%  norm=1.000  lr=5.56e-05  dt=  37.1ms  words=78,069,760
[E07   243/1548 G   9530|CLM] train=2.0907  mask=12.3%  norm=0.694  lr=5.56e-05  dt=  37.2ms  words=78,077,952
[E07   244/1548 G   9531|CLM] train=2.0077  mask=12.3%  norm=0.708  lr=5.56e-05  dt=  37.0ms  words=78,086,144
[E07   245/1548 G   9532|CLM] train=4.2603  mask=12.3%  norm=0.929  lr=5.55e-05  dt=  37.3ms  words=78,094,336
[E07   246/1548 G   9533|CLM] train=2.0223  mask=12.3%  norm=0.686  lr=5.55e-05  dt=  37.1ms  words=78,102,528
[E07   247/1548 G   9534|CLM] train=3.6765  mask=12.3%  norm=1.126  lr=5.55e-05  dt=  37.2ms  words=78,110,720
[E07   248/1548 G   9535|CLM] train=4.6012  mask=12.3%  norm=1.022  lr=5.55e-05  dt=  37.2ms  words=78,118,912
[E07   249/1548 G   9536|CLM] train=4.2085  mask=12.3%  norm=0.920  lr=5.54e-05  dt=  37.4ms  words=78,127,104
[E07   250/1548 G   9537|CLM] train=2.2164  mask=12.3%  norm=0.715  lr=5.54e-05  dt=  37.1ms  words=78,135,296
[E07   251/1548 G   9538|CLM] train=4.0181  mask=12.3%  norm=0.913  lr=5.54e-05  dt=  37.1ms  words=78,143,488
[E07   252/1548 G   9539|CLM] train=2.1331  mask=12.3%  norm=0.679  lr=5.54e-05  dt=  37.2ms  words=78,151,680
[E07   253/1548 G   9540|CLM] train=4.3229  mask=12.3%  norm=0.859  lr=5.53e-05  dt=  37.2ms  words=78,159,872
[E07   254/1548 G   9541|CLM] train=2.1300  mask=12.3%  norm=0.683  lr=5.53e-05  dt=  37.2ms  words=78,168,064
[E07   255/1548 G   9542|CLM] train=3.5843  mask=12.3%  norm=0.822  lr=5.53e-05  dt=  37.0ms  words=78,176,256
[E07   256/1548 G   9543|CLM] train=2.4010  mask=12.3%  norm=0.618  lr=5.52e-05  dt=  37.3ms  words=78,184,448
[E07   257/1548 G   9544|CLM] train=1.9637  mask=12.3%  norm=0.717  lr=5.52e-05  dt=  37.2ms  words=78,192,640
[E07   258/1548 G   9545|CLM] train=3.8428  mask=12.3%  norm=0.802  lr=5.52e-05  dt=  37.1ms  words=78,200,832
[E07   259/1548 G   9546|CLM] train=4.9994  mask=12.3%  norm=1.797  lr=5.52e-05  dt=  37.0ms  words=78,209,024
[E07   260/1548 G   9547|CLM] train=3.5843  mask=12.3%  norm=0.930  lr=5.51e-05  dt=  37.3ms  words=78,217,216
[E07   261/1548 G   9548|CLM] train=1.9761  mask=12.3%  norm=0.655  lr=5.51e-05  dt=  37.2ms  words=78,225,408
[E07   262/1548 G   9549|CLM] train=4.0267  mask=12.3%  norm=0.940  lr=5.51e-05  dt=  37.3ms  words=78,233,600
[E07   263/1548 G   9550|CLM] train=4.2354  mask=12.3%  norm=0.900  lr=5.51e-05  dt=  37.4ms  words=78,241,792
[E07   264/1548 G   9551|CLM] train=4.1962  mask=12.3%  norm=0.996  lr=5.50e-05  dt=  38.5ms  words=78,249,984
[E07   265/1548 G   9552|CLM] train=2.0347  mask=12.3%  norm=0.870  lr=5.50e-05  dt=  41.5ms  words=78,258,176
[E07   266/1548 G   9553|CLM] train=3.3239  mask=12.3%  norm=0.711  lr=5.50e-05  dt=  41.5ms  words=78,266,368
[E07   267/1548 G   9554|CLM] train=4.0672  mask=12.3%  norm=0.859  lr=5.49e-05  dt=  37.4ms  words=78,274,560
[E07   268/1548 G   9555|CLM] train=2.3500  mask=12.3%  norm=0.766  lr=5.49e-05  dt=  37.2ms  words=78,282,752
[E07   269/1548 G   9556|CLM] train=4.1195  mask=12.3%  norm=0.889  lr=5.49e-05  dt=  37.3ms  words=78,290,944
[E07   270/1548 G   9557|CLM] train=5.2704  mask=12.3%  norm=1.107  lr=5.49e-05  dt=  37.6ms  words=78,299,136
[E07   271/1548 G   9558|CLM] train=2.0201  mask=12.3%  norm=0.745  lr=5.48e-05  dt=  37.3ms  words=78,307,328
[E07   272/1548 G   9559|CLM] train=1.9641  mask=12.3%  norm=0.764  lr=5.48e-05  dt=  37.1ms  words=78,315,520
[E07   273/1548 G   9560|CLM] train=4.5068  mask=12.3%  norm=0.890  lr=5.48e-05  dt=  38.1ms  words=78,323,712
[E07   274/1548 G   9561|CLM] train=4.4855  mask=12.3%  norm=1.081  lr=5.48e-05  dt=  37.0ms  words=78,331,904
[E07   275/1548 G   9562|CLM] train=2.4106  mask=12.3%  norm=0.698  lr=5.47e-05  dt=  37.2ms  words=78,340,096
[E07   276/1548 G   9563|CLM] train=2.5085  mask=12.3%  norm=0.720  lr=5.47e-05  dt=  37.3ms  words=78,348,288
[E07   277/1548 G   9564|CLM] train=2.1074  mask=12.3%  norm=0.736  lr=5.47e-05  dt=  37.1ms  words=78,356,480
[E07   278/1548 G   9565|CLM] train=4.5190  mask=12.3%  norm=0.997  lr=5.47e-05  dt=  37.1ms  words=78,364,672
[E07   279/1548 G   9566|CLM] train=2.0030  mask=12.3%  norm=0.777  lr=5.46e-05  dt=  37.4ms  words=78,372,864
[E07   280/1548 G   9567|CLM] train=2.3787  mask=12.3%  norm=0.760  lr=5.46e-05  dt=  38.9ms  words=78,381,056
[E07   281/1548 G   9568|CLM] train=3.4288  mask=12.3%  norm=0.815  lr=5.46e-05  dt=  42.6ms  words=78,389,248
[E07   282/1548 G   9569|CLM] train=2.0272  mask=12.3%  norm=0.775  lr=5.45e-05  dt=  42.3ms  words=78,397,440
[E07   283/1548 G   9570|CLM] train=2.1918  mask=12.3%  norm=0.727  lr=5.45e-05  dt=  37.9ms  words=78,405,632
[E07   284/1548 G   9571|CLM] train=4.6846  mask=12.3%  norm=0.929  lr=5.45e-05  dt=  37.2ms  words=78,413,824
[E07   285/1548 G   9572|CLM] train=2.0390  mask=12.3%  norm=0.783  lr=5.45e-05  dt=  38.8ms  words=78,422,016
[E07   286/1548 G   9573|CLM] train=3.9925  mask=12.3%  norm=0.891  lr=5.44e-05  dt=  39.9ms  words=78,430,208
[E07   287/1548 G   9574|CLM] train=2.3300  mask=12.3%  norm=0.627  lr=5.44e-05  dt=  39.7ms  words=78,438,400
[E07   288/1548 G   9575|CLM] train=2.9126  mask=12.3%  norm=0.860  lr=5.44e-05  dt=  43.3ms  words=78,446,592
[E07   289/1548 G   9576|CLM] train=2.6751  mask=12.3%  norm=0.650  lr=5.44e-05  dt=  40.7ms  words=78,454,784
[E07   290/1548 G   9577|CLM] train=4.2509  mask=12.3%  norm=1.012  lr=5.43e-05  dt=  39.3ms  words=78,462,976
[E07   291/1548 G   9578|CLM] train=4.1214  mask=12.3%  norm=0.878  lr=5.43e-05  dt=  39.8ms  words=78,471,168
[E07   292/1548 G   9579|CLM] train=4.0729  mask=12.3%  norm=0.957  lr=5.43e-05  dt=  38.9ms  words=78,479,360
[E07   293/1548 G   9580|CLM] train=4.0241  mask=12.3%  norm=1.099  lr=5.43e-05  dt=  44.8ms  words=78,487,552
[E07   294/1548 G   9581|CLM] train=3.9600  mask=12.3%  norm=0.781  lr=5.42e-05  dt=  38.0ms  words=78,495,744
[E07   295/1548 G   9582|CLM] train=1.9975  mask=12.3%  norm=0.744  lr=5.42e-05  dt=  41.0ms  words=78,503,936
[E07   296/1548 G   9583|CLM] train=3.8192  mask=12.3%  norm=1.065  lr=5.42e-05  dt=  39.2ms  words=78,512,128
[E07   297/1548 G   9584|CLM] train=2.2832  mask=12.3%  norm=0.685  lr=5.41e-05  dt=  43.7ms  words=78,520,320
[E07   298/1548 G   9585|CLM] train=4.4643  mask=12.3%  norm=1.155  lr=5.41e-05  dt=  40.0ms  words=78,528,512
[E07   299/1548 G   9586|CLM] train=2.3134  mask=12.3%  norm=0.798  lr=5.41e-05  dt=  42.4ms  words=78,536,704
[E07   300/1548 G   9587|CLM] train=4.4566  mask=12.3%  norm=0.964  lr=5.41e-05  dt=  37.7ms  words=78,544,896
[E07   301/1548 G   9588|CLM] train=2.1283  mask=12.3%  norm=0.842  lr=5.40e-05  dt=  37.7ms  words=78,553,088
[E07   302/1548 G   9589|CLM] train=2.4455  mask=12.3%  norm=0.699  lr=5.40e-05  dt=  37.5ms  words=78,561,280
[E07   303/1548 G   9590|CLM] train=2.3114  mask=12.3%  norm=0.679  lr=5.40e-05  dt=  37.3ms  words=78,569,472
[E07   304/1548 G   9591|CLM] train=3.5200  mask=12.3%  norm=0.748  lr=5.40e-05  dt=  38.1ms  words=78,577,664
[E07   305/1548 G   9592|CLM] train=4.1091  mask=12.3%  norm=0.880  lr=5.39e-05  dt=  39.0ms  words=78,585,856
[E07   306/1548 G   9593|CLM] train=1.9431  mask=12.3%  norm=0.728  lr=5.39e-05  dt=  37.5ms  words=78,594,048
[E07   307/1548 G   9594|CLM] train=2.5715  mask=12.3%  norm=0.744  lr=5.39e-05  dt=  41.7ms  words=78,602,240
[E07   308/1548 G   9595|CLM] train=2.0997  mask=12.3%  norm=0.636  lr=5.39e-05  dt=  44.3ms  words=78,610,432
[E07   309/1548 G   9596|CLM] train=3.5670  mask=12.3%  norm=0.943  lr=5.38e-05  dt=  41.6ms  words=78,618,624
[E07   310/1548 G   9597|CLM] train=3.7806  mask=12.3%  norm=0.821  lr=5.38e-05  dt=  37.7ms  words=78,626,816
[E07   311/1548 G   9598|CLM] train=3.4266  mask=12.2%  norm=0.782  lr=5.38e-05  dt=  37.4ms  words=78,635,008
[E07   312/1548 G   9599|CLM] train=4.0198  mask=12.2%  norm=0.874  lr=5.38e-05  dt=  37.2ms  words=78,643,200
[E07   313/1548 G   9600|CLM] train=2.5297  mask=12.2%  norm=0.668  lr=5.37e-05  dt=  37.1ms  words=78,651,392
[E07   314/1548 G   9601|CLM] train=1.8933  mask=12.2%  norm=0.709  lr=5.37e-05  dt=  36.9ms  words=78,659,584
[E07   315/1548 G   9602|CLM] train=2.3701  mask=12.2%  norm=0.700  lr=5.37e-05  dt=  37.1ms  words=78,667,776
[E07   316/1548 G   9603|CLM] train=3.8250  mask=12.2%  norm=0.929  lr=5.36e-05  dt=  37.1ms  words=78,675,968
[E07   317/1548 G   9604|CLM] train=3.8795  mask=12.2%  norm=1.006  lr=5.36e-05  dt=  36.9ms  words=78,684,160
[E07   318/1548 G   9605|CLM] train=4.3970  mask=12.2%  norm=0.845  lr=5.36e-05  dt=  36.9ms  words=78,692,352
[E07   319/1548 G   9606|CLM] train=2.3227  mask=12.2%  norm=0.744  lr=5.36e-05  dt=  36.9ms  words=78,700,544
[E07   320/1548 G   9607|CLM] train=4.1617  mask=12.2%  norm=0.849  lr=5.35e-05  dt=  37.0ms  words=78,708,736
[E07   321/1548 G   9608|CLM] train=3.9348  mask=12.2%  norm=1.011  lr=5.35e-05  dt=  37.6ms  words=78,716,928
[E07   322/1548 G   9609|CLM] train=4.7171  mask=12.2%  norm=1.694  lr=5.35e-05  dt=  37.1ms  words=78,725,120
[E07   323/1548 G   9610|CLM] train=2.0335  mask=12.2%  norm=0.620  lr=5.35e-05  dt=  37.1ms  words=78,733,312
[E07   324/1548 G   9611|CLM] train=3.8373  mask=12.2%  norm=0.920  lr=5.34e-05  dt=  37.1ms  words=78,741,504
[E07   325/1548 G   9612|CLM] train=3.8700  mask=12.2%  norm=0.956  lr=5.34e-05  dt=  37.2ms  words=78,749,696
[E07   326/1548 G   9613|CLM] train=2.3597  mask=12.2%  norm=1.258  lr=5.34e-05  dt=  37.0ms  words=78,757,888
[E07   327/1548 G   9614|CLM] train=4.2338  mask=12.2%  norm=0.943  lr=5.34e-05  dt=  37.0ms  words=78,766,080
[E07   328/1548 G   9615|CLM] train=2.1914  mask=12.2%  norm=0.712  lr=5.33e-05  dt=  36.8ms  words=78,774,272
[E07   329/1548 G   9616|CLM] train=3.5993  mask=12.2%  norm=0.883  lr=5.33e-05  dt=  36.8ms  words=78,782,464
[E07   330/1548 G   9617|CLM] train=3.5131  mask=12.2%  norm=0.842  lr=5.33e-05  dt=  37.1ms  words=78,790,656
[E07   331/1548 G   9618|CLM] train=3.6249  mask=12.2%  norm=0.836  lr=5.32e-05  dt=  36.9ms  words=78,798,848
[E07   332/1548 G   9619|CLM] train=4.0781  mask=12.2%  norm=0.886  lr=5.32e-05  dt=  37.0ms  words=78,807,040
[E07   333/1548 G   9620|CLM] train=3.7313  mask=12.2%  norm=0.848  lr=5.32e-05  dt=  36.9ms  words=78,815,232
[E07   334/1548 G   9621|CLM] train=3.7321  mask=12.2%  norm=0.851  lr=5.32e-05  dt=  37.6ms  words=78,823,424
[E07   335/1548 G   9622|CLM] train=4.2642  mask=12.2%  norm=0.978  lr=5.31e-05  dt=  37.3ms  words=78,831,616
[E07   336/1548 G   9623|CLM] train=3.8075  mask=12.2%  norm=1.073  lr=5.31e-05  dt=  36.9ms  words=78,839,808
[E07   337/1548 G   9624|CLM] train=2.1663  mask=12.2%  norm=0.712  lr=5.31e-05  dt=  37.0ms  words=78,848,000
[E07   338/1548 G   9625|CLM] train=4.6628  mask=12.2%  norm=1.199  lr=5.31e-05  dt=  36.8ms  words=78,856,192
[E07   339/1548 G   9626|CLM] train=3.9150  mask=12.2%  norm=0.837  lr=5.30e-05  dt=  37.1ms  words=78,864,384
[E07   340/1548 G   9627|CLM] train=4.1737  mask=12.2%  norm=0.980  lr=5.30e-05  dt=  37.2ms  words=78,872,576
[E07   341/1548 G   9628|CLM] train=1.7789  mask=12.2%  norm=0.758  lr=5.30e-05  dt=  37.0ms  words=78,880,768
[E07   342/1548 G   9629|CLM] train=1.9904  mask=12.2%  norm=0.755  lr=5.30e-05  dt=  37.0ms  words=78,888,960
[E07   343/1548 G   9630|CLM] train=4.5594  mask=12.2%  norm=1.077  lr=5.29e-05  dt=  37.0ms  words=78,897,152
[E07   344/1548 G   9631|CLM] train=2.0380  mask=12.2%  norm=0.732  lr=5.29e-05  dt=  37.4ms  words=78,905,344
[E07   345/1548 G   9632|CLM] train=3.5096  mask=12.2%  norm=0.849  lr=5.29e-05  dt=  36.9ms  words=78,913,536
[E07   346/1548 G   9633|CLM] train=3.7399  mask=12.2%  norm=0.768  lr=5.29e-05  dt=  37.2ms  words=78,921,728
[E07   347/1548 G   9634|CLM] train=2.3177  mask=12.2%  norm=0.796  lr=5.28e-05  dt=  37.1ms  words=78,929,920
[E07   348/1548 G   9635|CLM] train=4.6111  mask=12.2%  norm=1.007  lr=5.28e-05  dt=  37.0ms  words=78,938,112
[E07   349/1548 G   9636|CLM] train=2.2960  mask=12.2%  norm=0.732  lr=5.28e-05  dt=  36.9ms  words=78,946,304
[E07   350/1548 G   9637|CLM] train=4.3102  mask=12.2%  norm=0.978  lr=5.27e-05  dt=  37.0ms  words=78,954,496
[E07   351/1548 G   9638|CLM] train=4.1467  mask=12.2%  norm=0.878  lr=5.27e-05  dt=  37.3ms  words=78,962,688
[E07   352/1548 G   9639|CLM] train=3.5289  mask=12.2%  norm=0.785  lr=5.27e-05  dt=  37.0ms  words=78,970,880
[E07   353/1548 G   9640|CLM] train=4.0878  mask=12.2%  norm=0.966  lr=5.27e-05  dt=  36.9ms  words=78,979,072
[E07   354/1548 G   9641|CLM] train=4.6144  mask=12.2%  norm=0.909  lr=5.26e-05  dt=  37.3ms  words=78,987,264
[E07   355/1548 G   9642|CLM] train=2.0700  mask=12.2%  norm=0.738  lr=5.26e-05  dt=  37.1ms  words=78,995,456
[E07   356/1548 G   9643|CLM] train=2.0254  mask=12.2%  norm=0.723  lr=5.26e-05  dt=  36.9ms  words=79,003,648
[E07   357/1548 G   9644|CLM] train=3.8956  mask=12.2%  norm=1.116  lr=5.26e-05  dt=  37.1ms  words=79,011,840
[E07   358/1548 G   9645|CLM] train=4.8987  mask=12.2%  norm=0.896  lr=5.25e-05  dt=  37.0ms  words=79,020,032
[E07   359/1548 G   9646|CLM] train=3.9597  mask=12.2%  norm=0.843  lr=5.25e-05  dt=  37.1ms  words=79,028,224
[E07   360/1548 G   9647|CLM] train=3.9174  mask=12.2%  norm=0.759  lr=5.25e-05  dt=  37.7ms  words=79,036,416
[E07   361/1548 G   9648|CLM] train=4.3105  mask=12.2%  norm=1.139  lr=5.25e-05  dt=  37.4ms  words=79,044,608
[E07   362/1548 G   9649|CLM] train=3.6539  mask=12.2%  norm=0.847  lr=5.24e-05  dt=  37.3ms  words=79,052,800
[E07   363/1548 G   9650|CLM] train=2.0604  mask=12.2%  norm=0.626  lr=5.24e-05  dt=  37.0ms  words=79,060,992
[E07   364/1548 G   9651|CLM] train=4.8807  mask=12.2%  norm=1.304  lr=5.24e-05  dt=  37.1ms  words=79,069,184
[E07   365/1548 G   9652|CLM] train=2.6671  mask=12.2%  norm=0.758  lr=5.24e-05  dt=  37.1ms  words=79,077,376
[E07   366/1548 G   9653|CLM] train=2.6663  mask=12.2%  norm=0.701  lr=5.23e-05  dt=  37.5ms  words=79,085,568
[E07   367/1548 G   9654|CLM] train=5.0690  mask=12.2%  norm=1.420  lr=5.23e-05  dt=  37.6ms  words=79,093,760
[E07   368/1548 G   9655|CLM] train=3.5028  mask=12.2%  norm=0.905  lr=5.23e-05  dt=  37.1ms  words=79,101,952
[E07   369/1548 G   9656|CLM] train=2.2371  mask=12.2%  norm=0.726  lr=5.23e-05  dt=  37.2ms  words=79,110,144
[E07   370/1548 G   9657|CLM] train=2.2682  mask=12.2%  norm=0.648  lr=5.22e-05  dt=  37.2ms  words=79,118,336
[E07   371/1548 G   9658|CLM] train=4.2034  mask=12.2%  norm=0.894  lr=5.22e-05  dt=  37.2ms  words=79,126,528
[E07   372/1548 G   9659|CLM] train=2.1011  mask=12.2%  norm=0.686  lr=5.22e-05  dt=  37.1ms  words=79,134,720
[E07   373/1548 G   9660|CLM] train=4.0039  mask=12.2%  norm=0.826  lr=5.21e-05  dt=  37.3ms  words=79,142,912
[E07   374/1548 G   9661|CLM] train=3.6548  mask=12.2%  norm=0.857  lr=5.21e-05  dt=  37.0ms  words=79,151,104
[E07   375/1548 G   9662|CLM] train=4.8731  mask=12.2%  norm=0.957  lr=5.21e-05  dt=  37.1ms  words=79,159,296
[E07   376/1548 G   9663|CLM] train=3.6852  mask=12.2%  norm=0.797  lr=5.21e-05  dt=  37.2ms  words=79,167,488
[E07   377/1548 G   9664|CLM] train=2.5737  mask=12.2%  norm=0.701  lr=5.20e-05  dt=  37.1ms  words=79,175,680
[E07   378/1548 G   9665|CLM] train=3.8983  mask=12.2%  norm=0.790  lr=5.20e-05  dt=  37.2ms  words=79,183,872
[E07   379/1548 G   9666|CLM] train=3.7934  mask=12.2%  norm=0.800  lr=5.20e-05  dt=  37.1ms  words=79,192,064
[E07   380/1548 G   9667|CLM] train=4.2344  mask=12.2%  norm=0.978  lr=5.20e-05  dt=  37.0ms  words=79,200,256
[E07   381/1548 G   9668|CLM] train=4.5034  mask=12.2%  norm=0.810  lr=5.19e-05  dt=  37.0ms  words=79,208,448
[E07   382/1548 G   9669|CLM] train=2.1171  mask=12.2%  norm=0.811  lr=5.19e-05  dt=  37.3ms  words=79,216,640
[E07   383/1548 G   9670|CLM] train=3.9609  mask=12.2%  norm=0.908  lr=5.19e-05  dt=  37.2ms  words=79,224,832
[E07   384/1548 G   9671|CLM] train=4.1959  mask=12.2%  norm=0.835  lr=5.19e-05  dt=  37.0ms  words=79,233,024
[E07   385/1548 G   9672|CLM] train=4.2671  mask=12.2%  norm=0.958  lr=5.18e-05  dt=  37.0ms  words=79,241,216
[E07   386/1548 G   9673|CLM] train=1.8966  mask=12.2%  norm=0.775  lr=5.18e-05  dt=  37.0ms  words=79,249,408
[E07   387/1548 G   9674|CLM] train=2.2256  mask=12.2%  norm=0.741  lr=5.18e-05  dt=  37.1ms  words=79,257,600
[E07   388/1548 G   9675|CLM] train=2.1170  mask=12.2%  norm=0.769  lr=5.18e-05  dt=  37.2ms  words=79,265,792
[E07   389/1548 G   9676|CLM] train=4.4344  mask=12.2%  norm=0.931  lr=5.17e-05  dt=  37.7ms  words=79,273,984
[E07   390/1548 G   9677|CLM] train=4.0859  mask=12.2%  norm=0.807  lr=5.17e-05  dt=  37.1ms  words=79,282,176
[E07   391/1548 G   9678|CLM] train=3.8133  mask=12.2%  norm=0.886  lr=5.17e-05  dt=  37.1ms  words=79,290,368
[E07   392/1548 G   9679|CLM] train=4.0871  mask=12.2%  norm=0.898  lr=5.17e-05  dt=  37.0ms  words=79,298,560
[E07   393/1548 G   9680|CLM] train=4.0177  mask=12.2%  norm=0.853  lr=5.16e-05  dt=  37.3ms  words=79,306,752
[E07   394/1548 G   9681|CLM] train=3.9173  mask=12.2%  norm=0.856  lr=5.16e-05  dt=  37.3ms  words=79,314,944
[E07   395/1548 G   9682|CLM] train=2.1653  mask=12.2%  norm=0.702  lr=5.16e-05  dt=  37.1ms  words=79,323,136
[E07   396/1548 G   9683|CLM] train=4.0236  mask=12.2%  norm=0.962  lr=5.16e-05  dt=  37.1ms  words=79,331,328
[E07   397/1548 G   9684|CLM] train=4.1921  mask=12.2%  norm=0.950  lr=5.15e-05  dt=  37.2ms  words=79,339,520
[E07   398/1548 G   9685|CLM] train=4.5537  mask=12.2%  norm=0.968  lr=5.15e-05  dt=  37.3ms  words=79,347,712
[E07   399/1548 G   9686|CLM] train=4.6393  mask=12.2%  norm=1.341  lr=5.15e-05  dt=  37.2ms  words=79,355,904
[E07   400/1548 G   9687|CLM] train=4.0432  mask=12.2%  norm=0.816  lr=5.14e-05  dt=  37.2ms  words=79,364,096
[E07   401/1548 G   9688|CLM] train=2.5355  mask=12.2%  norm=0.663  lr=5.14e-05  dt=  37.1ms  words=79,372,288
[E07   402/1548 G   9689|CLM] train=2.0673  mask=12.2%  norm=0.805  lr=5.14e-05  dt=  37.2ms  words=79,380,480
[E07   403/1548 G   9690|CLM] train=3.7922  mask=12.2%  norm=0.937  lr=5.14e-05  dt=  37.2ms  words=79,388,672
[E07   404/1548 G   9691|CLM] train=3.8418  mask=12.2%  norm=0.797  lr=5.13e-05  dt=  37.0ms  words=79,396,864
[E07   405/1548 G   9692|CLM] train=4.9006  mask=12.2%  norm=1.080  lr=5.13e-05  dt=  37.5ms  words=79,405,056
[E07   406/1548 G   9693|CLM] train=2.2022  mask=12.2%  norm=0.730  lr=5.13e-05  dt=  37.2ms  words=79,413,248
[E07   407/1548 G   9694|CLM] train=2.0418  mask=12.2%  norm=0.987  lr=5.13e-05  dt=  37.2ms  words=79,421,440
[E07   408/1548 G   9695|CLM] train=3.5381  mask=12.2%  norm=0.902  lr=5.12e-05  dt=  37.0ms  words=79,429,632
[E07   409/1548 G   9696|CLM] train=2.1293  mask=12.2%  norm=0.759  lr=5.12e-05  dt=  37.2ms  words=79,437,824
[E07   410/1548 G   9697|CLM] train=3.7238  mask=12.2%  norm=0.939  lr=5.12e-05  dt=  37.1ms  words=79,446,016
[E07   411/1548 G   9698|CLM] train=2.1286  mask=12.2%  norm=0.688  lr=5.12e-05  dt=  37.1ms  words=79,454,208
[E07   412/1548 G   9699|CLM] train=4.5347  mask=12.2%  norm=0.858  lr=5.11e-05  dt=  37.1ms  words=79,462,400
[E07   413/1548 G   9700|CLM] train=2.1984  mask=12.2%  norm=0.820  lr=5.11e-05  dt=  37.0ms  words=79,470,592
[E07   414/1548 G   9701|CLM] train=3.9744  mask=12.2%  norm=0.820  lr=5.11e-05  dt=  36.9ms  words=79,478,784
[E07   415/1548 G   9702|CLM] train=4.6785  mask=12.2%  norm=0.853  lr=5.11e-05  dt=  37.1ms  words=79,486,976
[E07   416/1548 G   9703|CLM] train=4.5441  mask=12.2%  norm=1.110  lr=5.10e-05  dt=  37.4ms  words=79,495,168
[E07   417/1548 G   9704|CLM] train=3.9925  mask=12.2%  norm=0.905  lr=5.10e-05  dt=  37.1ms  words=79,503,360
[E07   418/1548 G   9705|CLM] train=3.8836  mask=12.2%  norm=0.818  lr=5.10e-05  dt=  37.2ms  words=79,511,552
[E07   419/1548 G   9706|CLM] train=2.4184  mask=12.2%  norm=0.702  lr=5.10e-05  dt=  37.4ms  words=79,519,744
[E07   420/1548 G   9707|CLM] train=2.1172  mask=12.2%  norm=0.690  lr=5.09e-05  dt=  37.5ms  words=79,527,936
[E07   421/1548 G   9708|CLM] train=4.4004  mask=12.2%  norm=0.875  lr=5.09e-05  dt=  37.0ms  words=79,536,128
[E07   422/1548 G   9709|CLM] train=3.5201  mask=12.2%  norm=0.818  lr=5.09e-05  dt=  37.2ms  words=79,544,320
[E07   423/1548 G   9710|CLM] train=2.1379  mask=12.2%  norm=0.688  lr=5.09e-05  dt=  37.1ms  words=79,552,512
[E07   424/1548 G   9711|CLM] train=2.2275  mask=12.2%  norm=0.695  lr=5.08e-05  dt=  37.1ms  words=79,560,704
[E07   425/1548 G   9712|CLM] train=4.0969  mask=12.2%  norm=0.825  lr=5.08e-05  dt=  37.2ms  words=79,568,896
[E07   426/1548 G   9713|CLM] train=3.9080  mask=12.2%  norm=0.818  lr=5.08e-05  dt=  37.2ms  words=79,577,088
[E07   427/1548 G   9714|CLM] train=3.8655  mask=12.2%  norm=0.870  lr=5.08e-05  dt=  37.1ms  words=79,585,280
[E07   428/1548 G   9715|CLM] train=1.8668  mask=12.2%  norm=0.775  lr=5.07e-05  dt=  37.6ms  words=79,593,472
[E07   429/1548 G   9716|CLM] train=2.0625  mask=12.2%  norm=0.810  lr=5.07e-05  dt=  37.1ms  words=79,601,664
[E07   430/1548 G   9717|CLM] train=2.1961  mask=12.2%  norm=0.687  lr=5.07e-05  dt=  37.1ms  words=79,609,856
[E07   431/1548 G   9718|CLM] train=2.2815  mask=12.2%  norm=0.746  lr=5.07e-05  dt=  37.3ms  words=79,618,048
[E07   432/1548 G   9719|CLM] train=4.7080  mask=12.2%  norm=1.254  lr=5.06e-05  dt=  37.4ms  words=79,626,240
[E07   433/1548 G   9720|CLM] train=3.8845  mask=12.2%  norm=0.850  lr=5.06e-05  dt=  37.1ms  words=79,634,432
[E07   434/1548 G   9721|CLM] train=3.2118  mask=12.2%  norm=0.871  lr=5.06e-05  dt=  37.1ms  words=79,642,624
[E07   435/1548 G   9722|CLM] train=2.3169  mask=12.1%  norm=0.718  lr=5.05e-05  dt=  37.1ms  words=79,650,816
[E07   436/1548 G   9723|CLM] train=2.0507  mask=12.1%  norm=0.658  lr=5.05e-05  dt=  37.2ms  words=79,659,008
[E07   437/1548 G   9724|CLM] train=2.1659  mask=12.1%  norm=0.710  lr=5.05e-05  dt=  37.3ms  words=79,667,200
[E07   438/1548 G   9725|CLM] train=4.2848  mask=12.1%  norm=0.898  lr=5.05e-05  dt=  37.0ms  words=79,675,392
[E07   439/1548 G   9726|CLM] train=2.0090  mask=12.1%  norm=0.731  lr=5.04e-05  dt=  37.0ms  words=79,683,584
[E07   440/1548 G   9727|CLM] train=3.8051  mask=12.1%  norm=0.747  lr=5.04e-05  dt=  37.0ms  words=79,691,776
[E07   441/1548 G   9728|CLM] train=1.9180  mask=12.1%  norm=0.775  lr=5.04e-05  dt=  37.0ms  words=79,699,968
[E07   442/1548 G   9729|CLM] train=4.0229  mask=12.1%  norm=0.860  lr=5.04e-05  dt=  37.2ms  words=79,708,160
[E07   443/1548 G   9730|CLM] train=2.4625  mask=12.1%  norm=0.721  lr=5.03e-05  dt=  37.3ms  words=79,716,352
[E07   444/1548 G   9731|CLM] train=4.1786  mask=12.1%  norm=0.865  lr=5.03e-05  dt=  37.2ms  words=79,724,544
[E07   445/1548 G   9732|CLM] train=3.9223  mask=12.1%  norm=0.936  lr=5.03e-05  dt=  36.9ms  words=79,732,736
[E07   446/1548 G   9733|CLM] train=4.8841  mask=12.1%  norm=1.075  lr=5.03e-05  dt=  36.9ms  words=79,740,928
[E07   447/1548 G   9734|CLM] train=4.1967  mask=12.1%  norm=0.871  lr=5.02e-05  dt=  37.6ms  words=79,749,120
[E07   448/1548 G   9735|CLM] train=4.0299  mask=12.1%  norm=0.874  lr=5.02e-05  dt=  37.2ms  words=79,757,312
[E07   449/1548 G   9736|CLM] train=2.4461  mask=12.1%  norm=0.732  lr=5.02e-05  dt=  37.0ms  words=79,765,504
[E07   450/1548 G   9737|CLM] train=3.8401  mask=12.1%  norm=0.862  lr=5.02e-05  dt=  37.0ms  words=79,773,696
[E07   451/1548 G   9738|CLM] train=4.3594  mask=12.1%  norm=0.902  lr=5.01e-05  dt=  36.9ms  words=79,781,888
[E07   452/1548 G   9739|CLM] train=3.5550  mask=12.1%  norm=0.770  lr=5.01e-05  dt=  37.1ms  words=79,790,080
[E07   453/1548 G   9740|CLM] train=4.2694  mask=12.1%  norm=0.828  lr=5.01e-05  dt=  37.1ms  words=79,798,272
[E07   454/1548 G   9741|CLM] train=3.8931  mask=12.1%  norm=0.887  lr=5.01e-05  dt=  37.2ms  words=79,806,464
[E07   455/1548 G   9742|CLM] train=3.9646  mask=12.1%  norm=0.821  lr=5.00e-05  dt=  37.1ms  words=79,814,656
[E07   456/1548 G   9743|CLM] train=4.3047  mask=12.1%  norm=0.886  lr=5.00e-05  dt=  37.0ms  words=79,822,848
[E07   457/1548 G   9744|CLM] train=3.8008  mask=12.1%  norm=0.960  lr=5.00e-05  dt=  36.9ms  words=79,831,040
[E07   458/1548 G   9745|CLM] train=4.0187  mask=12.1%  norm=0.896  lr=5.00e-05  dt=  37.2ms  words=79,839,232
[E07   459/1548 G   9746|CLM] train=4.3605  mask=12.1%  norm=0.881  lr=4.99e-05  dt=  37.2ms  words=79,847,424
[E07   460/1548 G   9747|CLM] train=2.0889  mask=12.1%  norm=0.670  lr=4.99e-05  dt=  37.4ms  words=79,855,616
[E07   461/1548 G   9748|CLM] train=4.1318  mask=12.1%  norm=0.877  lr=4.99e-05  dt=  37.3ms  words=79,863,808
[E07   462/1548 G   9749|CLM] train=3.9846  mask=12.1%  norm=0.864  lr=4.99e-05  dt=  37.3ms  words=79,872,000
[E07   463/1548 G   9750|CLM] train=3.8843  mask=12.1%  norm=0.897  lr=4.98e-05  dt=  37.2ms  words=79,880,192
[E07   464/1548 G   9751|CLM] train=4.2146  mask=12.1%  norm=0.763  lr=4.98e-05  dt=  37.9ms  words=79,888,384
[E07   465/1548 G   9752|CLM] train=2.0599  mask=12.1%  norm=0.838  lr=4.98e-05  dt=  37.4ms  words=79,896,576
[E07   466/1548 G   9753|CLM] train=1.9821  mask=12.1%  norm=0.814  lr=4.98e-05  dt=  37.5ms  words=79,904,768
[E07   467/1548 G   9754|CLM] train=4.2837  mask=12.1%  norm=1.191  lr=4.97e-05  dt=  37.2ms  words=79,912,960
[E07   468/1548 G   9755|CLM] train=1.8602  mask=12.1%  norm=0.760  lr=4.97e-05  dt=  37.5ms  words=79,921,152
[E07   469/1548 G   9756|CLM] train=2.3904  mask=12.1%  norm=0.703  lr=4.97e-05  dt=  37.1ms  words=79,929,344
[E07   470/1548 G   9757|CLM] train=2.1900  mask=12.1%  norm=0.721  lr=4.97e-05  dt=  37.5ms  words=79,937,536
[E07   471/1548 G   9758|CLM] train=2.3531  mask=12.1%  norm=0.766  lr=4.96e-05  dt=  37.1ms  words=79,945,728
[E07   472/1548 G   9759|CLM] train=3.4379  mask=12.1%  norm=0.871  lr=4.96e-05  dt=  37.4ms  words=79,953,920
[E07   473/1548 G   9760|CLM] train=1.9221  mask=12.1%  norm=0.754  lr=4.96e-05  dt=  37.1ms  words=79,962,112
[E07   474/1548 G   9761|CLM] train=4.0541  mask=12.1%  norm=0.836  lr=4.96e-05  dt=  37.2ms  words=79,970,304
[E07   475/1548 G   9762|CLM] train=4.5165  mask=12.1%  norm=1.047  lr=4.95e-05  dt=  37.0ms  words=79,978,496
[E07   476/1548 G   9763|CLM] train=4.3908  mask=12.1%  norm=1.136  lr=4.95e-05  dt=  37.1ms  words=79,986,688
[E07   477/1548 G   9764|CLM] train=4.5991  mask=12.1%  norm=0.972  lr=4.95e-05  dt=  37.0ms  words=79,994,880
[E07   478/1548 G   9765|CLM] train=2.4281  mask=12.1%  norm=0.767  lr=4.95e-05  dt=  37.2ms  words=80,003,072

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_80M'...
[Checkpoint] Checkpoint 'chck_80M' successfully saved.
[E07   479/1548 G   9766|CLM] train=2.0565  mask=12.1%  norm=0.658  lr=4.94e-05  dt=  37.7ms  words=80,011,264
[E07   480/1548 G   9767|CLM] train=2.5714  mask=12.1%  norm=0.683  lr=4.94e-05  dt=  37.2ms  words=80,019,456
[E07   481/1548 G   9768|CLM] train=2.2469  mask=12.1%  norm=0.687  lr=4.94e-05  dt=  37.2ms  words=80,027,648
[E07   482/1548 G   9769|CLM] train=3.9258  mask=12.1%  norm=0.849  lr=4.94e-05  dt=  37.1ms  words=80,035,840
[E07   483/1548 G   9770|CLM] train=3.6177  mask=12.1%  norm=0.889  lr=4.93e-05  dt=  37.0ms  words=80,044,032
[E07   484/1548 G   9771|CLM] train=3.6220  mask=12.1%  norm=0.777  lr=4.93e-05  dt=  37.0ms  words=80,052,224
[E07   485/1548 G   9772|CLM] train=2.2683  mask=12.1%  norm=0.689  lr=4.93e-05  dt=  37.1ms  words=80,060,416
[E07   486/1548 G   9773|CLM] train=4.0617  mask=12.1%  norm=1.039  lr=4.93e-05  dt=  36.9ms  words=80,068,608
[E07   487/1548 G   9774|CLM] train=3.9477  mask=12.1%  norm=0.902  lr=4.92e-05  dt=  37.7ms  words=80,076,800
[E07   488/1548 G   9775|CLM] train=4.6101  mask=12.1%  norm=1.113  lr=4.92e-05  dt=  37.1ms  words=80,084,992
[E07   489/1548 G   9776|CLM] train=4.0182  mask=12.1%  norm=0.937  lr=4.92e-05  dt=  37.3ms  words=80,093,184
[E07   490/1548 G   9777|CLM] train=2.3858  mask=12.1%  norm=0.739  lr=4.92e-05  dt=  37.3ms  words=80,101,376
[E07   491/1548 G   9778|CLM] train=4.4435  mask=12.1%  norm=1.616  lr=4.91e-05  dt=  37.4ms  words=80,109,568
[E07   492/1548 G   9779|CLM] train=2.0750  mask=12.1%  norm=0.640  lr=4.91e-05  dt=  37.1ms  words=80,117,760
[E07   493/1548 G   9780|CLM] train=2.2824  mask=12.1%  norm=0.755  lr=4.91e-05  dt=  37.2ms  words=80,125,952
[E07   494/1548 G   9781|CLM] train=3.3975  mask=12.1%  norm=0.844  lr=4.91e-05  dt=  37.3ms  words=80,134,144
[E07   495/1548 G   9782|CLM] train=3.9118  mask=12.1%  norm=0.903  lr=4.90e-05  dt=  37.2ms  words=80,142,336
[E07   496/1548 G   9783|CLM] train=4.1835  mask=12.1%  norm=0.817  lr=4.90e-05  dt=  37.1ms  words=80,150,528
[E07   497/1548 G   9784|CLM] train=2.5727  mask=12.1%  norm=0.709  lr=4.90e-05  dt=  37.2ms  words=80,158,720
[E07   498/1548 G   9785|CLM] train=3.7083  mask=12.1%  norm=1.294  lr=4.90e-05  dt=  37.0ms  words=80,166,912
[E07   499/1548 G   9786|CLM] train=4.1607  mask=12.1%  norm=0.839  lr=4.89e-05  dt=  37.0ms  words=80,175,104
[E07   500/1548 G   9787|CLM] train=3.6521  mask=12.1%  norm=0.839  lr=4.89e-05  dt=  36.9ms  words=80,183,296
[E07   501/1548 G   9788|CLM] train=2.2187  mask=12.1%  norm=0.696  lr=4.89e-05  dt=  37.1ms  words=80,191,488
[E07   502/1548 G   9789|CLM] train=4.2461  mask=12.1%  norm=0.893  lr=4.89e-05  dt=  37.1ms  words=80,199,680
[E07   503/1548 G   9790|CLM] train=4.1953  mask=12.1%  norm=0.891  lr=4.88e-05  dt=  37.3ms  words=80,207,872
[E07   504/1548 G   9791|CLM] train=3.8004  mask=12.1%  norm=0.937  lr=4.88e-05  dt=  37.2ms  words=80,216,064
[E07   505/1548 G   9792|CLM] train=2.2918  mask=12.1%  norm=0.838  lr=4.88e-05  dt=  36.9ms  words=80,224,256
[E07   506/1548 G   9793|CLM] train=2.1446  mask=12.1%  norm=0.746  lr=4.88e-05  dt=  37.0ms  words=80,232,448
[E07   507/1548 G   9794|CLM] train=4.0812  mask=12.1%  norm=0.943  lr=4.87e-05  dt=  37.3ms  words=80,240,640
[E07   508/1548 G   9795|CLM] train=2.1712  mask=12.1%  norm=0.724  lr=4.87e-05  dt=  37.1ms  words=80,248,832
[E07   509/1548 G   9796|CLM] train=3.5161  mask=12.1%  norm=0.881  lr=4.87e-05  dt=  37.0ms  words=80,257,024
[E07   510/1548 G   9797|CLM] train=4.0790  mask=12.1%  norm=0.816  lr=4.87e-05  dt=  37.1ms  words=80,265,216
[E07   511/1548 G   9798|CLM] train=3.2156  mask=12.1%  norm=0.840  lr=4.86e-05  dt=  37.2ms  words=80,273,408
[E07   512/1548 G   9799|CLM] train=2.0423  mask=12.1%  norm=0.648  lr=4.86e-05  dt=  37.2ms  words=80,281,600
[E07   513/1548 G   9800|CLM] train=4.1802  mask=12.1%  norm=0.823  lr=4.86e-05  dt=  37.4ms  words=80,289,792
[E07   514/1548 G   9801|CLM] train=1.9140  mask=12.1%  norm=0.765  lr=4.86e-05  dt=  37.1ms  words=80,297,984
[E07   515/1548 G   9802|CLM] train=2.4984  mask=12.1%  norm=0.689  lr=4.85e-05  dt=  37.0ms  words=80,306,176
[E07   516/1548 G   9803|CLM] train=3.7738  mask=12.1%  norm=0.863  lr=4.85e-05  dt=  37.4ms  words=80,314,368
[E07   517/1548 G   9804|CLM] train=3.7692  mask=12.1%  norm=1.111  lr=4.85e-05  dt=  37.2ms  words=80,322,560
[E07   518/1548 G   9805|CLM] train=2.2248  mask=12.1%  norm=0.793  lr=4.85e-05  dt=  37.2ms  words=80,330,752
[E07   519/1548 G   9806|CLM] train=3.9627  mask=12.1%  norm=0.808  lr=4.84e-05  dt=  37.2ms  words=80,338,944
[E07   520/1548 G   9807|CLM] train=3.3066  mask=12.1%  norm=0.741  lr=4.84e-05  dt=  37.1ms  words=80,347,136
[E07   521/1548 G   9808|CLM] train=4.4018  mask=12.1%  norm=0.924  lr=4.84e-05  dt=  37.0ms  words=80,355,328
[E07   522/1548 G   9809|CLM] train=3.6325  mask=12.1%  norm=0.872  lr=4.84e-05  dt=  37.0ms  words=80,363,520
[E07   523/1548 G   9810|CLM] train=4.1096  mask=12.1%  norm=1.013  lr=4.83e-05  dt=  37.0ms  words=80,371,712
[E07   524/1548 G   9811|CLM] train=4.4769  mask=12.1%  norm=0.982  lr=4.83e-05  dt=  37.2ms  words=80,379,904
[E07   525/1548 G   9812|CLM] train=3.7106  mask=12.1%  norm=0.936  lr=4.83e-05  dt=  37.1ms  words=80,388,096
[E07   526/1548 G   9813|CLM] train=1.3685  mask=12.1%  norm=0.640  lr=4.83e-05  dt=  37.1ms  words=80,396,288
[E07   527/1548 G   9814|CLM] train=1.9899  mask=12.1%  norm=0.756  lr=4.82e-05  dt=  37.0ms  words=80,404,480
[E07   528/1548 G   9815|CLM] train=3.5745  mask=12.1%  norm=0.833  lr=4.82e-05  dt=  37.0ms  words=80,412,672
[E07   529/1548 G   9816|CLM] train=3.5991  mask=12.1%  norm=0.910  lr=4.82e-05  dt=  36.9ms  words=80,420,864
[E07   530/1548 G   9817|CLM] train=1.6635  mask=12.1%  norm=0.688  lr=4.82e-05  dt=  36.9ms  words=80,429,056
[E07   531/1548 G   9818|CLM] train=4.2087  mask=12.1%  norm=0.908  lr=4.81e-05  dt=  37.1ms  words=80,437,248
[E07   532/1548 G   9819|CLM] train=1.8787  mask=12.1%  norm=0.804  lr=4.81e-05  dt=  36.9ms  words=80,445,440
[E07   533/1548 G   9820|CLM] train=1.7611  mask=12.1%  norm=0.654  lr=4.81e-05  dt=  36.9ms  words=80,453,632
[E07   534/1548 G   9821|CLM] train=2.7281  mask=12.1%  norm=0.968  lr=4.81e-05  dt=  37.0ms  words=80,461,824
[E07   535/1548 G   9822|CLM] train=4.1074  mask=12.1%  norm=0.946  lr=4.80e-05  dt=  37.0ms  words=80,470,016
[E07   536/1548 G   9823|CLM] train=3.7414  mask=12.1%  norm=0.858  lr=4.80e-05  dt=  36.9ms  words=80,478,208
[E07   537/1548 G   9824|CLM] train=3.9936  mask=12.1%  norm=0.903  lr=4.80e-05  dt=  36.8ms  words=80,486,400
[E07   538/1548 G   9825|CLM] train=1.9279  mask=12.1%  norm=0.760  lr=4.80e-05  dt=  37.0ms  words=80,494,592
[E07   539/1548 G   9826|CLM] train=4.0798  mask=12.1%  norm=0.804  lr=4.79e-05  dt=  37.0ms  words=80,502,784
[E07   540/1548 G   9827|CLM] train=2.3825  mask=12.1%  norm=0.734  lr=4.79e-05  dt=  36.9ms  words=80,510,976
[E07   541/1548 G   9828|CLM] train=2.2914  mask=12.1%  norm=0.701  lr=4.79e-05  dt=  36.8ms  words=80,519,168
[E07   542/1548 G   9829|CLM] train=3.6599  mask=12.1%  norm=0.828  lr=4.79e-05  dt=  36.9ms  words=80,527,360
[E07   543/1548 G   9830|CLM] train=4.8433  mask=12.1%  norm=1.014  lr=4.78e-05  dt=  37.1ms  words=80,535,552
[E07   544/1548 G   9831|CLM] train=4.2425  mask=12.1%  norm=0.880  lr=4.78e-05  dt=  37.0ms  words=80,543,744
[E07   545/1548 G   9832|CLM] train=5.1373  mask=12.1%  norm=1.060  lr=4.78e-05  dt=  37.3ms  words=80,551,936
[E07   546/1548 G   9833|CLM] train=4.2714  mask=12.1%  norm=0.928  lr=4.78e-05  dt=  37.0ms  words=80,560,128
[E07   547/1548 G   9834|CLM] train=2.0997  mask=12.1%  norm=0.689  lr=4.77e-05  dt=  37.0ms  words=80,568,320
[E07   548/1548 G   9835|CLM] train=3.8159  mask=12.1%  norm=0.927  lr=4.77e-05  dt=  36.9ms  words=80,576,512
[E07   549/1548 G   9836|CLM] train=2.3951  mask=12.1%  norm=0.820  lr=4.77e-05  dt=  37.0ms  words=80,584,704
[E07   550/1548 G   9837|CLM] train=4.4439  mask=12.1%  norm=0.906  lr=4.77e-05  dt=  37.1ms  words=80,592,896
[E07   551/1548 G   9838|CLM] train=3.7524  mask=12.1%  norm=0.830  lr=4.76e-05  dt=  36.9ms  words=80,601,088
[E07   552/1548 G   9839|CLM] train=3.9969  mask=12.1%  norm=0.911  lr=4.76e-05  dt=  36.9ms  words=80,609,280
[E07   553/1548 G   9840|CLM] train=4.6403  mask=12.1%  norm=1.290  lr=4.76e-05  dt=  36.9ms  words=80,617,472
[E07   554/1548 G   9841|CLM] train=4.1411  mask=12.1%  norm=0.886  lr=4.76e-05  dt=  37.1ms  words=80,625,664
[E07   555/1548 G   9842|CLM] train=4.4228  mask=12.1%  norm=0.868  lr=4.75e-05  dt=  36.9ms  words=80,633,856
[E07   556/1548 G   9843|CLM] train=2.3184  mask=12.1%  norm=0.701  lr=4.75e-05  dt=  36.8ms  words=80,642,048
[E07   557/1548 G   9844|CLM] train=2.7845  mask=12.1%  norm=0.776  lr=4.75e-05  dt=  36.9ms  words=80,650,240
[E07   558/1548 G   9845|CLM] train=2.2283  mask=12.1%  norm=0.804  lr=4.75e-05  dt=  37.1ms  words=80,658,432
[E07   559/1548 G   9846|CLM] train=2.2487  mask=12.0%  norm=0.706  lr=4.74e-05  dt=  36.8ms  words=80,666,624
[E07   560/1548 G   9847|CLM] train=4.9483  mask=12.0%  norm=0.904  lr=4.74e-05  dt=  36.9ms  words=80,674,816
[E07   561/1548 G   9848|CLM] train=3.5855  mask=12.0%  norm=0.866  lr=4.74e-05  dt=  36.9ms  words=80,683,008
[E07   562/1548 G   9849|CLM] train=3.3849  mask=12.0%  norm=1.013  lr=4.74e-05  dt=  37.1ms  words=80,691,200
[E07   563/1548 G   9850|CLM] train=4.0257  mask=12.0%  norm=0.936  lr=4.73e-05  dt=  37.5ms  words=80,699,392
[E07   564/1548 G   9851|CLM] train=3.8700  mask=12.0%  norm=0.947  lr=4.73e-05  dt=  37.1ms  words=80,707,584
[E07   565/1548 G   9852|CLM] train=2.2020  mask=12.0%  norm=0.712  lr=4.73e-05  dt=  37.2ms  words=80,715,776
[E07   566/1548 G   9853|CLM] train=3.2869  mask=12.0%  norm=0.831  lr=4.73e-05  dt=  37.2ms  words=80,723,968
[E07   567/1548 G   9854|CLM] train=2.1388  mask=12.0%  norm=0.756  lr=4.72e-05  dt=  37.0ms  words=80,732,160
[E07   568/1548 G   9855|CLM] train=3.7159  mask=12.0%  norm=0.791  lr=4.72e-05  dt=  37.1ms  words=80,740,352
[E07   569/1548 G   9856|CLM] train=4.6108  mask=12.0%  norm=1.051  lr=4.72e-05  dt=  37.0ms  words=80,748,544
[E07   570/1548 G   9857|CLM] train=2.5478  mask=12.0%  norm=0.752  lr=4.72e-05  dt=  37.3ms  words=80,756,736
[E07   571/1548 G   9858|CLM] train=2.1051  mask=12.0%  norm=0.779  lr=4.72e-05  dt=  37.0ms  words=80,764,928
[E07   572/1548 G   9859|CLM] train=3.6661  mask=12.0%  norm=0.944  lr=4.71e-05  dt=  37.1ms  words=80,773,120
[E07   573/1548 G   9860|CLM] train=2.2578  mask=12.0%  norm=0.778  lr=4.71e-05  dt=  36.9ms  words=80,781,312
[E07   574/1548 G   9861|CLM] train=3.6198  mask=12.0%  norm=0.793  lr=4.71e-05  dt=  37.1ms  words=80,789,504
[E07   575/1548 G   9862|CLM] train=3.6555  mask=12.0%  norm=0.863  lr=4.71e-05  dt=  37.1ms  words=80,797,696
[E07   576/1548 G   9863|CLM] train=3.9216  mask=12.0%  norm=0.898  lr=4.70e-05  dt=  37.3ms  words=80,805,888
[E07   577/1548 G   9864|CLM] train=3.8140  mask=12.0%  norm=0.906  lr=4.70e-05  dt=  37.2ms  words=80,814,080
[E07   578/1548 G   9865|CLM] train=4.1916  mask=12.0%  norm=0.981  lr=4.70e-05  dt=  37.4ms  words=80,822,272
[E07   579/1548 G   9866|CLM] train=4.3249  mask=12.0%  norm=0.829  lr=4.70e-05  dt=  37.3ms  words=80,830,464
[E07   580/1548 G   9867|CLM] train=3.4922  mask=12.0%  norm=0.797  lr=4.69e-05  dt=  37.0ms  words=80,838,656
[E07   581/1548 G   9868|CLM] train=2.1643  mask=12.0%  norm=0.778  lr=4.69e-05  dt=  37.1ms  words=80,846,848
[E07   582/1548 G   9869|CLM] train=2.1299  mask=12.0%  norm=1.026  lr=4.69e-05  dt=  37.0ms  words=80,855,040
[E07   583/1548 G   9870|CLM] train=4.0064  mask=12.0%  norm=0.961  lr=4.69e-05  dt=  36.9ms  words=80,863,232
[E07   584/1548 G   9871|CLM] train=3.3833  mask=12.0%  norm=0.840  lr=4.68e-05  dt=  37.0ms  words=80,871,424
[E07   585/1548 G   9872|CLM] train=4.2668  mask=12.0%  norm=0.938  lr=4.68e-05  dt=  37.0ms  words=80,879,616
[E07   586/1548 G   9873|CLM] train=4.0310  mask=12.0%  norm=0.867  lr=4.68e-05  dt=  36.9ms  words=80,887,808
[E07   587/1548 G   9874|CLM] train=2.1683  mask=12.0%  norm=0.635  lr=4.68e-05  dt=  36.8ms  words=80,896,000
[E07   588/1548 G   9875|CLM] train=3.4808  mask=12.0%  norm=0.746  lr=4.67e-05  dt=  37.0ms  words=80,904,192
[E07   589/1548 G   9876|CLM] train=4.0904  mask=12.0%  norm=0.874  lr=4.67e-05  dt=  37.1ms  words=80,912,384
[E07   590/1548 G   9877|CLM] train=4.4528  mask=12.0%  norm=0.863  lr=4.67e-05  dt=  36.9ms  words=80,920,576
[E07   591/1548 G   9878|CLM] train=4.0916  mask=12.0%  norm=0.957  lr=4.67e-05  dt=  36.8ms  words=80,928,768
[E07   592/1548 G   9879|CLM] train=2.2615  mask=12.0%  norm=0.792  lr=4.66e-05  dt=  36.9ms  words=80,936,960
[E07   593/1548 G   9880|CLM] train=4.0361  mask=12.0%  norm=1.162  lr=4.66e-05  dt=  37.1ms  words=80,945,152
[E07   594/1548 G   9881|CLM] train=3.9206  mask=12.0%  norm=0.825  lr=4.66e-05  dt=  36.9ms  words=80,953,344
[E07   595/1548 G   9882|CLM] train=2.6017  mask=12.0%  norm=0.732  lr=4.66e-05  dt=  36.9ms  words=80,961,536
[E07   596/1548 G   9883|CLM] train=2.2653  mask=12.0%  norm=0.715  lr=4.65e-05  dt=  36.9ms  words=80,969,728
[E07   597/1548 G   9884|CLM] train=2.2774  mask=12.0%  norm=0.677  lr=4.65e-05  dt=  37.1ms  words=80,977,920
[E07   598/1548 G   9885|CLM] train=3.9043  mask=12.0%  norm=0.870  lr=4.65e-05  dt=  36.7ms  words=80,986,112
[E07   599/1548 G   9886|CLM] train=3.9880  mask=12.0%  norm=0.971  lr=4.65e-05  dt=  37.0ms  words=80,994,304
[E07   600/1548 G   9887|CLM] train=4.6019  mask=12.0%  norm=0.842  lr=4.64e-05  dt=  36.8ms  words=81,002,496
[E07   601/1548 G   9888|CLM] train=1.7879  mask=12.0%  norm=0.686  lr=4.64e-05  dt=  37.0ms  words=81,010,688
[E07   602/1548 G   9889|CLM] train=2.1605  mask=12.0%  norm=0.907  lr=4.64e-05  dt=  36.8ms  words=81,018,880
[E07   603/1548 G   9890|CLM] train=3.8915  mask=12.0%  norm=0.865  lr=4.64e-05  dt=  36.8ms  words=81,027,072
[E07   604/1548 G   9891|CLM] train=4.7122  mask=12.0%  norm=1.218  lr=4.63e-05  dt=  37.1ms  words=81,035,264
[E07   605/1548 G   9892|CLM] train=4.2124  mask=12.0%  norm=0.877  lr=4.63e-05  dt=  37.1ms  words=81,043,456
[E07   606/1548 G   9893|CLM] train=2.6906  mask=12.0%  norm=0.773  lr=4.63e-05  dt=  36.8ms  words=81,051,648
[E07   607/1548 G   9894|CLM] train=3.6460  mask=12.0%  norm=0.956  lr=4.63e-05  dt=  36.8ms  words=81,059,840
[E07   608/1548 G   9895|CLM] train=3.5553  mask=12.0%  norm=0.767  lr=4.63e-05  dt=  37.0ms  words=81,068,032
[E07   609/1548 G   9896|CLM] train=4.2584  mask=12.0%  norm=0.865  lr=4.62e-05  dt=  37.1ms  words=81,076,224
[E07   610/1548 G   9897|CLM] train=2.1831  mask=12.0%  norm=0.703  lr=4.62e-05  dt=  36.9ms  words=81,084,416
[E07   611/1548 G   9898|CLM] train=2.0263  mask=12.0%  norm=0.660  lr=4.62e-05  dt=  37.5ms  words=81,092,608
[E07   612/1548 G   9899|CLM] train=2.2044  mask=12.0%  norm=0.741  lr=4.62e-05  dt=  37.1ms  words=81,100,800
[E07   613/1548 G   9900|CLM] train=3.6358  mask=12.0%  norm=0.857  lr=4.61e-05  dt=  37.2ms  words=81,108,992
[E07   614/1548 G   9901|CLM] train=4.3341  mask=12.0%  norm=1.019  lr=4.61e-05  dt=  37.2ms  words=81,117,184
[E07   615/1548 G   9902|CLM] train=2.1736  mask=12.0%  norm=0.632  lr=4.61e-05  dt=  37.3ms  words=81,125,376
[E07   616/1548 G   9903|CLM] train=3.5681  mask=12.0%  norm=0.867  lr=4.61e-05  dt=  37.3ms  words=81,133,568
[E07   617/1548 G   9904|CLM] train=3.8395  mask=12.0%  norm=0.913  lr=4.60e-05  dt=  37.0ms  words=81,141,760
[E07   618/1548 G   9905|CLM] train=2.1010  mask=12.0%  norm=0.704  lr=4.60e-05  dt=  37.6ms  words=81,149,952
[E07   619/1548 G   9906|CLM] train=2.3281  mask=12.0%  norm=0.876  lr=4.60e-05  dt=  36.9ms  words=81,158,144
[E07   620/1548 G   9907|CLM] train=3.9490  mask=12.0%  norm=1.050  lr=4.60e-05  dt=  37.0ms  words=81,166,336
[E07   621/1548 G   9908|CLM] train=3.6765  mask=12.0%  norm=0.816  lr=4.59e-05  dt=  37.0ms  words=81,174,528
[E07   622/1548 G   9909|CLM] train=2.2752  mask=12.0%  norm=0.725  lr=4.59e-05  dt=  37.0ms  words=81,182,720
[E07   623/1548 G   9910|CLM] train=2.2626  mask=12.0%  norm=0.793  lr=4.59e-05  dt=  36.8ms  words=81,190,912
[E07   624/1548 G   9911|CLM] train=4.0263  mask=12.0%  norm=0.982  lr=4.59e-05  dt=  36.9ms  words=81,199,104
[E07   625/1548 G   9912|CLM] train=3.6027  mask=12.0%  norm=0.856  lr=4.58e-05  dt=  37.1ms  words=81,207,296
[E07   626/1548 G   9913|CLM] train=4.1416  mask=12.0%  norm=0.820  lr=4.58e-05  dt=  37.1ms  words=81,215,488
[E07   627/1548 G   9914|CLM] train=4.6488  mask=12.0%  norm=1.711  lr=4.58e-05  dt=  37.2ms  words=81,223,680
[E07   628/1548 G   9915|CLM] train=4.1914  mask=12.0%  norm=0.874  lr=4.58e-05  dt=  37.0ms  words=81,231,872
[E07   629/1548 G   9916|CLM] train=3.6774  mask=12.0%  norm=0.929  lr=4.57e-05  dt=  37.6ms  words=81,240,064
[E07   630/1548 G   9917|CLM] train=3.5354  mask=12.0%  norm=0.826  lr=4.57e-05  dt=  37.3ms  words=81,248,256
[E07   631/1548 G   9918|CLM] train=2.2256  mask=12.0%  norm=0.780  lr=4.57e-05  dt=  37.3ms  words=81,256,448
[E07   632/1548 G   9919|CLM] train=2.1661  mask=12.0%  norm=0.695  lr=4.57e-05  dt=  37.1ms  words=81,264,640
[E07   633/1548 G   9920|CLM] train=4.0516  mask=12.0%  norm=0.968  lr=4.56e-05  dt=  37.1ms  words=81,272,832
[E07   634/1548 G   9921|CLM] train=5.2484  mask=12.0%  norm=1.102  lr=4.56e-05  dt=  37.1ms  words=81,281,024
[E07   635/1548 G   9922|CLM] train=2.6770  mask=12.0%  norm=0.776  lr=4.56e-05  dt=  37.2ms  words=81,289,216
[E07   636/1548 G   9923|CLM] train=3.9818  mask=12.0%  norm=0.901  lr=4.56e-05  dt=  36.9ms  words=81,297,408
[E07   637/1548 G   9924|CLM] train=3.9875  mask=12.0%  norm=0.799  lr=4.56e-05  dt=  37.0ms  words=81,305,600
[E07   638/1548 G   9925|CLM] train=2.4172  mask=12.0%  norm=0.699  lr=4.55e-05  dt=  36.9ms  words=81,313,792
[E07   639/1548 G   9926|CLM] train=4.1798  mask=12.0%  norm=0.900  lr=4.55e-05  dt=  36.9ms  words=81,321,984
[E07   640/1548 G   9927|CLM] train=4.4300  mask=12.0%  norm=0.920  lr=4.55e-05  dt=  36.8ms  words=81,330,176
[E07   641/1548 G   9928|CLM] train=4.1904  mask=12.0%  norm=0.860  lr=4.55e-05  dt=  37.0ms  words=81,338,368
[E07   642/1548 G   9929|CLM] train=2.0139  mask=12.0%  norm=0.748  lr=4.54e-05  dt=  36.9ms  words=81,346,560
[E07   643/1548 G   9930|CLM] train=2.0785  mask=12.0%  norm=0.651  lr=4.54e-05  dt=  37.0ms  words=81,354,752
[E07   644/1548 G   9931|CLM] train=2.4430  mask=12.0%  norm=0.741  lr=4.54e-05  dt=  36.9ms  words=81,362,944
[E07   645/1548 G   9932|CLM] train=4.5164  mask=12.0%  norm=0.899  lr=4.54e-05  dt=  36.9ms  words=81,371,136
[E07   646/1548 G   9933|CLM] train=4.1063  mask=12.0%  norm=0.955  lr=4.53e-05  dt=  36.9ms  words=81,379,328
[E07   647/1548 G   9934|CLM] train=1.8370  mask=12.0%  norm=0.648  lr=4.53e-05  dt=  37.1ms  words=81,387,520
[E07   648/1548 G   9935|CLM] train=4.1235  mask=12.0%  norm=0.902  lr=4.53e-05  dt=  37.0ms  words=81,395,712
[E07   649/1548 G   9936|CLM] train=4.1711  mask=12.0%  norm=1.306  lr=4.53e-05  dt=  36.8ms  words=81,403,904
[E07   650/1548 G   9937|CLM] train=2.1051  mask=12.0%  norm=0.706  lr=4.52e-05  dt=  36.9ms  words=81,412,096
[E07   651/1548 G   9938|CLM] train=2.3587  mask=12.0%  norm=0.794  lr=4.52e-05  dt=  37.0ms  words=81,420,288
[E07   652/1548 G   9939|CLM] train=4.1188  mask=12.0%  norm=0.876  lr=4.52e-05  dt=  36.9ms  words=81,428,480
[E07   653/1548 G   9940|CLM] train=3.7073  mask=12.0%  norm=0.898  lr=4.52e-05  dt=  36.9ms  words=81,436,672
[E07   654/1548 G   9941|CLM] train=3.8048  mask=12.0%  norm=0.854  lr=4.51e-05  dt=  36.8ms  words=81,444,864
[E07   655/1548 G   9942|CLM] train=3.7532  mask=12.0%  norm=1.062  lr=4.51e-05  dt=  37.1ms  words=81,453,056
[E07   656/1548 G   9943|CLM] train=3.7073  mask=12.0%  norm=0.792  lr=4.51e-05  dt=  36.9ms  words=81,461,248
[E07   657/1548 G   9944|CLM] train=1.9158  mask=12.0%  norm=0.678  lr=4.51e-05  dt=  37.0ms  words=81,469,440
[E07   658/1548 G   9945|CLM] train=3.9946  mask=12.0%  norm=0.898  lr=4.51e-05  dt=  37.2ms  words=81,477,632
[E07   659/1548 G   9946|CLM] train=4.0023  mask=12.0%  norm=1.013  lr=4.50e-05  dt=  37.0ms  words=81,485,824
[E07   660/1548 G   9947|CLM] train=4.1548  mask=12.0%  norm=0.868  lr=4.50e-05  dt=  37.0ms  words=81,494,016
[E07   661/1548 G   9948|CLM] train=2.2779  mask=12.0%  norm=0.678  lr=4.50e-05  dt=  37.1ms  words=81,502,208
[E07   662/1548 G   9949|CLM] train=2.8799  mask=12.0%  norm=0.720  lr=4.50e-05  dt=  37.2ms  words=81,510,400
[E07   663/1548 G   9950|CLM] train=4.6164  mask=12.0%  norm=0.979  lr=4.49e-05  dt=  36.9ms  words=81,518,592
[E07   664/1548 G   9951|CLM] train=1.9260  mask=12.0%  norm=0.716  lr=4.49e-05  dt=  36.9ms  words=81,526,784
[E07   665/1548 G   9952|CLM] train=4.0533  mask=12.0%  norm=0.837  lr=4.49e-05  dt=  37.1ms  words=81,534,976
[E07   666/1548 G   9953|CLM] train=3.8352  mask=12.0%  norm=0.927  lr=4.49e-05  dt=  37.1ms  words=81,543,168
[E07   667/1548 G   9954|CLM] train=4.2326  mask=12.0%  norm=0.927  lr=4.48e-05  dt=  37.1ms  words=81,551,360
[E07   668/1548 G   9955|CLM] train=1.8801  mask=12.0%  norm=0.754  lr=4.48e-05  dt=  37.1ms  words=81,559,552
[E07   669/1548 G   9956|CLM] train=2.9675  mask=12.0%  norm=2.082  lr=4.48e-05  dt=  37.0ms  words=81,567,744
[E07   670/1548 G   9957|CLM] train=2.2301  mask=12.0%  norm=0.725  lr=4.48e-05  dt=  37.0ms  words=81,575,936
[E07   671/1548 G   9958|CLM] train=3.6089  mask=12.0%  norm=0.888  lr=4.47e-05  dt=  37.0ms  words=81,584,128
[E07   672/1548 G   9959|CLM] train=4.0753  mask=12.0%  norm=0.853  lr=4.47e-05  dt=  37.0ms  words=81,592,320
[E07   673/1548 G   9960|CLM] train=4.0036  mask=12.0%  norm=0.871  lr=4.47e-05  dt=  37.0ms  words=81,600,512
[E07   674/1548 G   9961|CLM] train=4.4575  mask=12.0%  norm=0.952  lr=4.47e-05  dt=  36.9ms  words=81,608,704
[E07   675/1548 G   9962|CLM] train=2.1774  mask=12.0%  norm=0.699  lr=4.47e-05  dt=  37.1ms  words=81,616,896
[E07   676/1548 G   9963|CLM] train=2.5484  mask=12.0%  norm=0.738  lr=4.46e-05  dt=  36.8ms  words=81,625,088
[E07   677/1548 G   9964|CLM] train=4.7185  mask=12.0%  norm=1.272  lr=4.46e-05  dt=  37.0ms  words=81,633,280
[E07   678/1548 G   9965|CLM] train=2.4884  mask=12.0%  norm=0.681  lr=4.46e-05  dt=  36.8ms  words=81,641,472
[E07   679/1548 G   9966|CLM] train=3.9132  mask=12.0%  norm=0.762  lr=4.46e-05  dt=  36.9ms  words=81,649,664
[E07   680/1548 G   9967|CLM] train=3.8444  mask=12.0%  norm=0.891  lr=4.45e-05  dt=  36.9ms  words=81,657,856
[E07   681/1548 G   9968|CLM] train=3.4744  mask=12.0%  norm=0.746  lr=4.45e-05  dt=  37.3ms  words=81,666,048
[E07   682/1548 G   9969|CLM] train=4.5989  mask=12.0%  norm=1.055  lr=4.45e-05  dt=  37.1ms  words=81,674,240
[E07   683/1548 G   9970|CLM] train=4.3791  mask=11.9%  norm=0.972  lr=4.45e-05  dt=  37.3ms  words=81,682,432
[E07   684/1548 G   9971|CLM] train=4.2487  mask=11.9%  norm=0.812  lr=4.44e-05  dt=  37.5ms  words=81,690,624
[E07   685/1548 G   9972|CLM] train=4.2342  mask=11.9%  norm=0.936  lr=4.44e-05  dt=  36.9ms  words=81,698,816
[E07   686/1548 G   9973|CLM] train=4.0970  mask=11.9%  norm=0.972  lr=4.44e-05  dt=  37.0ms  words=81,707,008
[E07   687/1548 G   9974|CLM] train=4.3011  mask=11.9%  norm=1.007  lr=4.44e-05  dt=  37.0ms  words=81,715,200
[E07   688/1548 G   9975|CLM] train=2.0100  mask=11.9%  norm=0.706  lr=4.43e-05  dt=  37.0ms  words=81,723,392
[E07   689/1548 G   9976|CLM] train=3.8312  mask=11.9%  norm=0.925  lr=4.43e-05  dt=  37.0ms  words=81,731,584
[E07   690/1548 G   9977|CLM] train=2.3701  mask=11.9%  norm=0.900  lr=4.43e-05  dt=  37.0ms  words=81,739,776
[E07   691/1548 G   9978|CLM] train=2.5635  mask=11.9%  norm=1.124  lr=4.43e-05  dt=  37.0ms  words=81,747,968
[E07   692/1548 G   9979|CLM] train=2.2768  mask=11.9%  norm=0.685  lr=4.43e-05  dt=  36.9ms  words=81,756,160
[E07   693/1548 G   9980|CLM] train=4.4277  mask=11.9%  norm=1.210  lr=4.42e-05  dt=  36.8ms  words=81,764,352
[E07   694/1548 G   9981|CLM] train=2.0601  mask=11.9%  norm=0.650  lr=4.42e-05  dt=  37.0ms  words=81,772,544
[E07   695/1548 G   9982|CLM] train=2.1521  mask=11.9%  norm=0.645  lr=4.42e-05  dt=  37.0ms  words=81,780,736
[E07   696/1548 G   9983|CLM] train=1.7769  mask=11.9%  norm=0.701  lr=4.42e-05  dt=  36.8ms  words=81,788,928
[E07   697/1548 G   9984|CLM] train=4.8028  mask=11.9%  norm=1.085  lr=4.41e-05  dt=  37.1ms  words=81,797,120
[E07   698/1548 G   9985|CLM] train=3.9246  mask=11.9%  norm=1.016  lr=4.41e-05  dt=  36.8ms  words=81,805,312
[E07   699/1548 G   9986|CLM] train=4.1068  mask=11.9%  norm=1.082  lr=4.41e-05  dt=  37.0ms  words=81,813,504
[E07   700/1548 G   9987|CLM] train=4.8426  mask=11.9%  norm=1.108  lr=4.41e-05  dt=  36.8ms  words=81,821,696
[E07   701/1548 G   9988|CLM] train=4.8009  mask=11.9%  norm=0.907  lr=4.40e-05  dt=  36.8ms  words=81,829,888
[E07   702/1548 G   9989|CLM] train=4.2919  mask=11.9%  norm=0.869  lr=4.40e-05  dt=  37.1ms  words=81,838,080
[E07   703/1548 G   9990|CLM] train=2.2095  mask=11.9%  norm=0.761  lr=4.40e-05  dt=  36.9ms  words=81,846,272
[E07   704/1548 G   9991|CLM] train=3.4094  mask=11.9%  norm=0.895  lr=4.40e-05  dt=  36.9ms  words=81,854,464
[E07   705/1548 G   9992|CLM] train=4.1931  mask=11.9%  norm=0.900  lr=4.39e-05  dt=  36.8ms  words=81,862,656
[E07   706/1548 G   9993|CLM] train=4.0082  mask=11.9%  norm=0.858  lr=4.39e-05  dt=  36.9ms  words=81,870,848
[E07   707/1548 G   9994|CLM] train=4.3787  mask=11.9%  norm=0.908  lr=4.39e-05  dt=  36.9ms  words=81,879,040
[E07   708/1548 G   9995|CLM] train=3.6805  mask=11.9%  norm=1.034  lr=4.39e-05  dt=  36.9ms  words=81,887,232
[E07   709/1548 G   9996|CLM] train=2.2968  mask=11.9%  norm=0.697  lr=4.39e-05  dt=  36.8ms  words=81,895,424
[E07   710/1548 G   9997|CLM] train=3.7787  mask=11.9%  norm=0.806  lr=4.38e-05  dt=  36.9ms  words=81,903,616
[E07   711/1548 G   9998|CLM] train=2.1827  mask=11.9%  norm=0.746  lr=4.38e-05  dt=  37.1ms  words=81,911,808
[E07   712/1548 G   9999|CLM] train=3.9653  mask=11.9%  norm=0.853  lr=4.38e-05  dt=  36.9ms  words=81,920,000
[E07   713/1548 G  10000|CLM] train=2.1971  mask=11.9%  norm=0.662  lr=4.38e-05  dt=  36.8ms  words=81,928,192
[E07   714/1548 G  10001|CLM] train=2.2354  mask=11.9%  norm=0.695  lr=4.37e-05  dt=  36.8ms  words=81,936,384
[E07   715/1548 G  10002|CLM] train=3.2331  mask=11.9%  norm=0.869  lr=4.37e-05  dt=  36.9ms  words=81,944,576
[E07   716/1548 G  10003|CLM] train=3.5725  mask=11.9%  norm=0.862  lr=4.37e-05  dt=  36.9ms  words=81,952,768
[E07   717/1548 G  10004|CLM] train=2.0180  mask=11.9%  norm=0.760  lr=4.37e-05  dt=  37.0ms  words=81,960,960
[E07   718/1548 G  10005|CLM] train=4.0291  mask=11.9%  norm=1.086  lr=4.36e-05  dt=  37.0ms  words=81,969,152
[E07   719/1548 G  10006|CLM] train=2.6100  mask=11.9%  norm=0.751  lr=4.36e-05  dt=  37.2ms  words=81,977,344
[E07   720/1548 G  10007|CLM] train=4.2739  mask=11.9%  norm=0.878  lr=4.36e-05  dt=  37.0ms  words=81,985,536
[E07   721/1548 G  10008|CLM] train=3.2812  mask=11.9%  norm=0.736  lr=4.36e-05  dt=  36.7ms  words=81,993,728
[E07   722/1548 G  10009|CLM] train=2.3133  mask=11.9%  norm=0.710  lr=4.36e-05  dt=  37.1ms  words=82,001,920
[E07   723/1548 G  10010|CLM] train=3.8327  mask=11.9%  norm=0.809  lr=4.35e-05  dt=  37.0ms  words=82,010,112
[E07   724/1548 G  10011|CLM] train=3.5093  mask=11.9%  norm=0.824  lr=4.35e-05  dt=  36.8ms  words=82,018,304
[E07   725/1548 G  10012|CLM] train=2.5572  mask=11.9%  norm=0.742  lr=4.35e-05  dt=  37.0ms  words=82,026,496
[E07   726/1548 G  10013|CLM] train=2.4551  mask=11.9%  norm=0.689  lr=4.35e-05  dt=  36.9ms  words=82,034,688
[E07   727/1548 G  10014|CLM] train=1.9846  mask=11.9%  norm=0.777  lr=4.34e-05  dt=  37.0ms  words=82,042,880
[E07   728/1548 G  10015|CLM] train=2.1434  mask=11.9%  norm=0.679  lr=4.34e-05  dt=  37.0ms  words=82,051,072
[E07   729/1548 G  10016|CLM] train=2.6816  mask=11.9%  norm=0.728  lr=4.34e-05  dt=  37.2ms  words=82,059,264
[E07   730/1548 G  10017|CLM] train=3.6832  mask=11.9%  norm=0.911  lr=4.34e-05  dt=  37.1ms  words=82,067,456
[E07   731/1548 G  10018|CLM] train=1.8329  mask=11.9%  norm=0.718  lr=4.33e-05  dt=  36.9ms  words=82,075,648
[E07   732/1548 G  10019|CLM] train=2.5506  mask=11.9%  norm=0.759  lr=4.33e-05  dt=  37.0ms  words=82,083,840
[E07   733/1548 G  10020|CLM] train=4.6880  mask=11.9%  norm=1.091  lr=4.33e-05  dt=  37.0ms  words=82,092,032
[E07   734/1548 G  10021|CLM] train=3.8898  mask=11.9%  norm=0.842  lr=4.33e-05  dt=  37.1ms  words=82,100,224
[E07   735/1548 G  10022|CLM] train=2.4637  mask=11.9%  norm=0.753  lr=4.33e-05  dt=  36.9ms  words=82,108,416
[E07   736/1548 G  10023|CLM] train=3.8255  mask=11.9%  norm=1.045  lr=4.32e-05  dt=  36.8ms  words=82,116,608
[E07   737/1548 G  10024|CLM] train=2.2690  mask=11.9%  norm=0.802  lr=4.32e-05  dt=  37.5ms  words=82,124,800
[E07   738/1548 G  10025|CLM] train=2.4154  mask=11.9%  norm=0.709  lr=4.32e-05  dt=  37.0ms  words=82,132,992
[E07   739/1548 G  10026|CLM] train=4.3871  mask=11.9%  norm=1.097  lr=4.32e-05  dt=  37.0ms  words=82,141,184
[E07   740/1548 G  10027|CLM] train=4.1290  mask=11.9%  norm=0.863  lr=4.31e-05  dt=  37.1ms  words=82,149,376
[E07   741/1548 G  10028|CLM] train=3.9706  mask=11.9%  norm=0.872  lr=4.31e-05  dt=  37.1ms  words=82,157,568
[E07   742/1548 G  10029|CLM] train=2.3788  mask=11.9%  norm=1.310  lr=4.31e-05  dt=  36.9ms  words=82,165,760
[E07   743/1548 G  10030|CLM] train=4.0681  mask=11.9%  norm=0.936  lr=4.31e-05  dt=  36.8ms  words=82,173,952
[E07   744/1548 G  10031|CLM] train=3.6942  mask=11.9%  norm=1.016  lr=4.30e-05  dt=  36.9ms  words=82,182,144
[E07   745/1548 G  10032|CLM] train=4.3996  mask=11.9%  norm=1.055  lr=4.30e-05  dt=  37.0ms  words=82,190,336
[E07   746/1548 G  10033|CLM] train=2.1275  mask=11.9%  norm=0.685  lr=4.30e-05  dt=  36.9ms  words=82,198,528
[E07   747/1548 G  10034|CLM] train=4.3608  mask=11.9%  norm=0.897  lr=4.30e-05  dt=  36.9ms  words=82,206,720
[E07   748/1548 G  10035|CLM] train=2.0644  mask=11.9%  norm=0.732  lr=4.30e-05  dt=  36.9ms  words=82,214,912
[E07   749/1548 G  10036|CLM] train=4.3127  mask=11.9%  norm=1.129  lr=4.29e-05  dt=  37.0ms  words=82,223,104
[E07   750/1548 G  10037|CLM] train=4.4596  mask=11.9%  norm=1.040  lr=4.29e-05  dt=  36.9ms  words=82,231,296
[E07   751/1548 G  10038|CLM] train=4.4691  mask=11.9%  norm=1.026  lr=4.29e-05  dt=  36.8ms  words=82,239,488
[E07   752/1548 G  10039|CLM] train=4.2221  mask=11.9%  norm=0.987  lr=4.29e-05  dt=  36.9ms  words=82,247,680
[E07   753/1548 G  10040|CLM] train=4.0364  mask=11.9%  norm=0.893  lr=4.28e-05  dt=  37.0ms  words=82,255,872
[E07   754/1548 G  10041|CLM] train=2.6219  mask=11.9%  norm=0.728  lr=4.28e-05  dt=  37.0ms  words=82,264,064
[E07   755/1548 G  10042|CLM] train=3.6639  mask=11.9%  norm=0.937  lr=4.28e-05  dt=  37.2ms  words=82,272,256
[E07   756/1548 G  10043|CLM] train=3.7212  mask=11.9%  norm=0.849  lr=4.28e-05  dt=  39.0ms  words=82,280,448
[E07   757/1548 G  10044|CLM] train=2.1139  mask=11.9%  norm=0.669  lr=4.27e-05  dt=  37.2ms  words=82,288,640
[E07   758/1548 G  10045|CLM] train=5.2074  mask=11.9%  norm=1.935  lr=4.27e-05  dt=  37.1ms  words=82,296,832
[E07   759/1548 G  10046|CLM] train=3.8828  mask=11.9%  norm=0.864  lr=4.27e-05  dt=  37.0ms  words=82,305,024
[E07   760/1548 G  10047|CLM] train=2.3040  mask=11.9%  norm=0.712  lr=4.27e-05  dt=  37.4ms  words=82,313,216
[E07   761/1548 G  10048|CLM] train=3.5385  mask=11.9%  norm=0.861  lr=4.27e-05  dt=  37.0ms  words=82,321,408
[E07   762/1548 G  10049|CLM] train=2.4578  mask=11.9%  norm=0.720  lr=4.26e-05  dt=  37.1ms  words=82,329,600
[E07   763/1548 G  10050|CLM] train=4.1186  mask=11.9%  norm=0.843  lr=4.26e-05  dt=  36.8ms  words=82,337,792
[E07   764/1548 G  10051|CLM] train=2.1859  mask=11.9%  norm=0.646  lr=4.26e-05  dt=  37.0ms  words=82,345,984
[E07   765/1548 G  10052|CLM] train=2.0545  mask=11.9%  norm=0.760  lr=4.26e-05  dt=  37.0ms  words=82,354,176
[E07   766/1548 G  10053|CLM] train=4.2194  mask=11.9%  norm=0.917  lr=4.25e-05  dt=  36.9ms  words=82,362,368
[E07   767/1548 G  10054|CLM] train=3.5778  mask=11.9%  norm=0.846  lr=4.25e-05  dt=  37.3ms  words=82,370,560
[E07   768/1548 G  10055|CLM] train=4.2674  mask=11.9%  norm=1.223  lr=4.25e-05  dt=  37.1ms  words=82,378,752
[E07   769/1548 G  10056|CLM] train=3.7000  mask=11.9%  norm=0.866  lr=4.25e-05  dt=  37.1ms  words=82,386,944
[E07   770/1548 G  10057|CLM] train=2.3843  mask=11.9%  norm=0.711  lr=4.24e-05  dt=  37.6ms  words=82,395,136
[E07   771/1548 G  10058|CLM] train=4.1934  mask=11.9%  norm=0.990  lr=4.24e-05  dt=  37.8ms  words=82,403,328
[E07   772/1548 G  10059|CLM] train=3.3005  mask=11.9%  norm=0.814  lr=4.24e-05  dt=  37.2ms  words=82,411,520
[E07   773/1548 G  10060|CLM] train=2.1197  mask=11.9%  norm=0.679  lr=4.24e-05  dt=  37.5ms  words=82,419,712
[E07   774/1548 G  10061|CLM] train=4.9790  mask=11.9%  norm=0.922  lr=4.24e-05  dt=  37.2ms  words=82,427,904
[E07   775/1548 G  10062|CLM] train=2.1069  mask=11.9%  norm=0.802  lr=4.23e-05  dt=  37.2ms  words=82,436,096
[E07   776/1548 G  10063|CLM] train=3.4490  mask=11.9%  norm=0.941  lr=4.23e-05  dt=  37.6ms  words=82,444,288
[E07   777/1548 G  10064|CLM] train=2.1729  mask=11.9%  norm=0.690  lr=4.23e-05  dt=  37.0ms  words=82,452,480
[E07   778/1548 G  10065|CLM] train=1.9849  mask=11.9%  norm=0.727  lr=4.23e-05  dt=  37.0ms  words=82,460,672
[E07   779/1548 G  10066|CLM] train=1.8482  mask=11.9%  norm=0.697  lr=4.22e-05  dt=  36.9ms  words=82,468,864
[E07   780/1548 G  10067|CLM] train=2.0476  mask=11.9%  norm=0.695  lr=4.22e-05  dt=  37.1ms  words=82,477,056
[E07   781/1548 G  10068|CLM] train=2.1471  mask=11.9%  norm=0.784  lr=4.22e-05  dt=  37.1ms  words=82,485,248
[E07   782/1548 G  10069|CLM] train=2.4167  mask=11.9%  norm=0.713  lr=4.22e-05  dt=  38.1ms  words=82,493,440
[E07   783/1548 G  10070|CLM] train=4.4781  mask=11.9%  norm=1.019  lr=4.22e-05  dt=  37.5ms  words=82,501,632
[E07   784/1548 G  10071|CLM] train=4.0098  mask=11.9%  norm=0.967  lr=4.21e-05  dt=  37.1ms  words=82,509,824
[E07   785/1548 G  10072|CLM] train=3.7139  mask=11.9%  norm=0.781  lr=4.21e-05  dt=  38.2ms  words=82,518,016
[E07   786/1548 G  10073|CLM] train=4.1350  mask=11.9%  norm=0.964  lr=4.21e-05  dt=  37.0ms  words=82,526,208
[E07   787/1548 G  10074|CLM] train=4.4389  mask=11.9%  norm=1.024  lr=4.21e-05  dt=  37.4ms  words=82,534,400
[E07   788/1548 G  10075|CLM] train=2.5704  mask=11.9%  norm=0.745  lr=4.20e-05  dt=  37.1ms  words=82,542,592
[E07   789/1548 G  10076|CLM] train=2.1060  mask=11.9%  norm=0.825  lr=4.20e-05  dt=  37.0ms  words=82,550,784
[E07   790/1548 G  10077|CLM] train=1.8361  mask=11.9%  norm=0.672  lr=4.20e-05  dt=  37.1ms  words=82,558,976
[E07   791/1548 G  10078|CLM] train=2.2352  mask=11.9%  norm=0.741  lr=4.20e-05  dt=  37.9ms  words=82,567,168
[E07   792/1548 G  10079|CLM] train=4.0717  mask=11.9%  norm=1.061  lr=4.19e-05  dt=  37.5ms  words=82,575,360
[E07   793/1548 G  10080|CLM] train=2.3672  mask=11.9%  norm=0.825  lr=4.19e-05  dt=  38.1ms  words=82,583,552
[E07   794/1548 G  10081|CLM] train=4.7710  mask=11.9%  norm=0.964  lr=4.19e-05  dt=  37.2ms  words=82,591,744
[E07   795/1548 G  10082|CLM] train=3.7144  mask=11.9%  norm=0.849  lr=4.19e-05  dt=  43.8ms  words=82,599,936
[E07   796/1548 G  10083|CLM] train=4.5205  mask=11.9%  norm=0.941  lr=4.19e-05  dt=  46.2ms  words=82,608,128
[E07   797/1548 G  10084|CLM] train=2.0890  mask=11.9%  norm=0.701  lr=4.18e-05  dt=  46.5ms  words=82,616,320
[E07   798/1548 G  10085|CLM] train=3.6598  mask=11.9%  norm=0.912  lr=4.18e-05  dt=  46.6ms  words=82,624,512
[E07   799/1548 G  10086|CLM] train=3.5998  mask=11.9%  norm=0.922  lr=4.18e-05  dt=  43.6ms  words=82,632,704
[E07   800/1548 G  10087|CLM] train=1.9959  mask=11.9%  norm=0.744  lr=4.18e-05  dt=  38.3ms  words=82,640,896
[E07   801/1548 G  10088|CLM] train=1.9743  mask=11.9%  norm=0.807  lr=4.17e-05  dt=  39.1ms  words=82,649,088
[E07   802/1548 G  10089|CLM] train=2.2204  mask=11.9%  norm=0.715  lr=4.17e-05  dt=  37.6ms  words=82,657,280
[E07   803/1548 G  10090|CLM] train=2.1689  mask=11.9%  norm=0.787  lr=4.17e-05  dt=  37.7ms  words=82,665,472
[E07   804/1548 G  10091|CLM] train=4.1961  mask=11.9%  norm=0.999  lr=4.17e-05  dt=  37.5ms  words=82,673,664
[E07   805/1548 G  10092|CLM] train=4.3315  mask=11.9%  norm=0.908  lr=4.17e-05  dt=  37.1ms  words=82,681,856
[E07   806/1548 G  10093|CLM] train=2.4422  mask=11.8%  norm=0.651  lr=4.16e-05  dt=  37.0ms  words=82,690,048
[E07   807/1548 G  10094|CLM] train=3.7745  mask=11.8%  norm=0.792  lr=4.16e-05  dt=  36.9ms  words=82,698,240
[E07   808/1548 G  10095|CLM] train=4.0279  mask=11.8%  norm=0.871  lr=4.16e-05  dt=  36.9ms  words=82,706,432
[E07   809/1548 G  10096|CLM] train=2.2131  mask=11.8%  norm=0.723  lr=4.16e-05  dt=  37.4ms  words=82,714,624
[E07   810/1548 G  10097|CLM] train=2.3325  mask=11.8%  norm=0.708  lr=4.15e-05  dt=  37.0ms  words=82,722,816
[E07   811/1548 G  10098|CLM] train=3.8753  mask=11.8%  norm=0.746  lr=4.15e-05  dt=  37.1ms  words=82,731,008
[E07   812/1548 G  10099|CLM] train=1.9722  mask=11.8%  norm=0.689  lr=4.15e-05  dt=  37.1ms  words=82,739,200
[E07   813/1548 G  10100|CLM] train=2.5364  mask=11.8%  norm=0.884  lr=4.15e-05  dt=  37.0ms  words=82,747,392
[E07   814/1548 G  10101|CLM] train=4.2389  mask=11.8%  norm=1.144  lr=4.15e-05  dt=  36.8ms  words=82,755,584
[E07   815/1548 G  10102|CLM] train=1.8030  mask=11.8%  norm=0.814  lr=4.14e-05  dt=  37.1ms  words=82,763,776
[E07   816/1548 G  10103|CLM] train=3.7869  mask=11.8%  norm=0.753  lr=4.14e-05  dt=  37.1ms  words=82,771,968
[E07   817/1548 G  10104|CLM] train=4.1976  mask=11.8%  norm=0.892  lr=4.14e-05  dt=  36.8ms  words=82,780,160
[E07   818/1548 G  10105|CLM] train=2.2576  mask=11.8%  norm=0.735  lr=4.14e-05  dt=  38.3ms  words=82,788,352
[E07   819/1548 G  10106|CLM] train=3.1196  mask=11.8%  norm=0.780  lr=4.13e-05  dt=  37.5ms  words=82,796,544
[E07   820/1548 G  10107|CLM] train=4.0022  mask=11.8%  norm=0.877  lr=4.13e-05  dt=  37.7ms  words=82,804,736
[E07   821/1548 G  10108|CLM] train=1.9825  mask=11.8%  norm=0.726  lr=4.13e-05  dt=  37.8ms  words=82,812,928
[E07   822/1548 G  10109|CLM] train=2.0675  mask=11.8%  norm=0.666  lr=4.13e-05  dt=  43.0ms  words=82,821,120
[E07   823/1548 G  10110|CLM] train=3.5611  mask=11.8%  norm=0.849  lr=4.13e-05  dt=  39.7ms  words=82,829,312
[E07   824/1548 G  10111|CLM] train=4.4769  mask=11.8%  norm=1.064  lr=4.12e-05  dt=  43.6ms  words=82,837,504
[E07   825/1548 G  10112|CLM] train=4.4206  mask=11.8%  norm=0.954  lr=4.12e-05  dt=  41.8ms  words=82,845,696
[E07   826/1548 G  10113|CLM] train=2.0137  mask=11.8%  norm=0.698  lr=4.12e-05  dt=  38.0ms  words=82,853,888
[E07   827/1548 G  10114|CLM] train=2.1983  mask=11.8%  norm=0.754  lr=4.12e-05  dt=  37.1ms  words=82,862,080
[E07   828/1548 G  10115|CLM] train=4.2820  mask=11.8%  norm=0.875  lr=4.11e-05  dt=  38.2ms  words=82,870,272
[E07   829/1548 G  10116|CLM] train=2.1916  mask=11.8%  norm=0.724  lr=4.11e-05  dt=  44.8ms  words=82,878,464
[E07   830/1548 G  10117|CLM] train=2.2154  mask=11.8%  norm=0.650  lr=4.11e-05  dt=  37.1ms  words=82,886,656
[E07   831/1548 G  10118|CLM] train=4.4178  mask=11.8%  norm=0.823  lr=4.11e-05  dt=  37.0ms  words=82,894,848
[E07   832/1548 G  10119|CLM] train=3.8253  mask=11.8%  norm=0.935  lr=4.10e-05  dt=  37.0ms  words=82,903,040
[E07   833/1548 G  10120|CLM] train=2.3102  mask=11.8%  norm=0.707  lr=4.10e-05  dt=  36.9ms  words=82,911,232
[E07   834/1548 G  10121|CLM] train=2.5640  mask=11.8%  norm=0.913  lr=4.10e-05  dt=  37.3ms  words=82,919,424
[E07   835/1548 G  10122|CLM] train=4.6011  mask=11.8%  norm=1.061  lr=4.10e-05  dt=  36.8ms  words=82,927,616
[E07   836/1548 G  10123|CLM] train=3.9942  mask=11.8%  norm=0.916  lr=4.10e-05  dt=  36.8ms  words=82,935,808
[E07   837/1548 G  10124|CLM] train=2.1697  mask=11.8%  norm=0.694  lr=4.09e-05  dt=  36.8ms  words=82,944,000
[E07   838/1548 G  10125|CLM] train=2.4459  mask=11.8%  norm=0.685  lr=4.09e-05  dt=  37.4ms  words=82,952,192
[E07   839/1548 G  10126|CLM] train=3.8860  mask=11.8%  norm=0.840  lr=4.09e-05  dt=  37.0ms  words=82,960,384
[E07   840/1548 G  10127|CLM] train=3.7998  mask=11.8%  norm=0.908  lr=4.09e-05  dt=  37.1ms  words=82,968,576
[E07   841/1548 G  10128|CLM] train=3.7800  mask=11.8%  norm=0.938  lr=4.08e-05  dt=  36.9ms  words=82,976,768
[E07   842/1548 G  10129|CLM] train=4.2581  mask=11.8%  norm=0.961  lr=4.08e-05  dt=  36.8ms  words=82,984,960
[E07   843/1548 G  10130|CLM] train=2.6104  mask=11.8%  norm=0.783  lr=4.08e-05  dt=  37.0ms  words=82,993,152
[E07   844/1548 G  10131|CLM] train=4.2259  mask=11.8%  norm=0.924  lr=4.08e-05  dt=  37.1ms  words=83,001,344
[E07   845/1548 G  10132|CLM] train=2.3869  mask=11.8%  norm=0.718  lr=4.08e-05  dt=  37.3ms  words=83,009,536
[E07   846/1548 G  10133|CLM] train=4.2710  mask=11.8%  norm=0.931  lr=4.07e-05  dt=  38.4ms  words=83,017,728
[E07   847/1548 G  10134|CLM] train=4.6979  mask=11.8%  norm=1.001  lr=4.07e-05  dt=  36.8ms  words=83,025,920
[E07   848/1548 G  10135|CLM] train=4.1279  mask=11.8%  norm=0.883  lr=4.07e-05  dt=  37.0ms  words=83,034,112
[E07   849/1548 G  10136|CLM] train=4.2587  mask=11.8%  norm=1.222  lr=4.07e-05  dt=  37.2ms  words=83,042,304
[E07   850/1548 G  10137|CLM] train=3.9563  mask=11.8%  norm=0.963  lr=4.07e-05  dt=  37.1ms  words=83,050,496
[E07   851/1548 G  10138|CLM] train=3.8014  mask=11.8%  norm=0.845  lr=4.06e-05  dt=  37.3ms  words=83,058,688
[E07   852/1548 G  10139|CLM] train=2.1792  mask=11.8%  norm=0.822  lr=4.06e-05  dt=  37.1ms  words=83,066,880
[E07   853/1548 G  10140|CLM] train=1.5782  mask=11.8%  norm=0.645  lr=4.06e-05  dt=  37.0ms  words=83,075,072
[E07   854/1548 G  10141|CLM] train=3.6886  mask=11.8%  norm=0.813  lr=4.06e-05  dt=  36.9ms  words=83,083,264
[E07   855/1548 G  10142|CLM] train=4.9335  mask=11.8%  norm=1.158  lr=4.05e-05  dt=  37.4ms  words=83,091,456
[E07   856/1548 G  10143|CLM] train=3.3941  mask=11.8%  norm=0.899  lr=4.05e-05  dt=  37.3ms  words=83,099,648
[E07   857/1548 G  10144|CLM] train=3.5584  mask=11.8%  norm=0.862  lr=4.05e-05  dt=  37.0ms  words=83,107,840
[E07   858/1548 G  10145|CLM] train=4.1710  mask=11.8%  norm=0.907  lr=4.05e-05  dt=  37.1ms  words=83,116,032
[E07   859/1548 G  10146|CLM] train=2.3939  mask=11.8%  norm=0.702  lr=4.05e-05  dt=  36.9ms  words=83,124,224
[E07   860/1548 G  10147|CLM] train=2.1638  mask=11.8%  norm=0.713  lr=4.04e-05  dt=  37.1ms  words=83,132,416
[E07   861/1548 G  10148|CLM] train=2.3707  mask=11.8%  norm=0.689  lr=4.04e-05  dt=  37.0ms  words=83,140,608
[E07   862/1548 G  10149|CLM] train=2.0613  mask=11.8%  norm=0.766  lr=4.04e-05  dt=  37.2ms  words=83,148,800
[E07   863/1548 G  10150|CLM] train=4.8203  mask=11.8%  norm=1.121  lr=4.04e-05  dt=  37.1ms  words=83,156,992
[E07   864/1548 G  10151|CLM] train=1.9590  mask=11.8%  norm=0.722  lr=4.03e-05  dt=  37.0ms  words=83,165,184
[E07   865/1548 G  10152|CLM] train=3.5572  mask=11.8%  norm=0.994  lr=4.03e-05  dt=  36.9ms  words=83,173,376
[E07   866/1548 G  10153|CLM] train=4.2191  mask=11.8%  norm=0.955  lr=4.03e-05  dt=  37.1ms  words=83,181,568
[E07   867/1548 G  10154|CLM] train=3.8834  mask=11.8%  norm=0.771  lr=4.03e-05  dt=  37.0ms  words=83,189,760
[E07   868/1548 G  10155|CLM] train=2.0590  mask=11.8%  norm=0.634  lr=4.03e-05  dt=  37.7ms  words=83,197,952
[E07   869/1548 G  10156|CLM] train=3.5571  mask=11.8%  norm=0.798  lr=4.02e-05  dt=  37.1ms  words=83,206,144
[E07   870/1548 G  10157|CLM] train=4.0929  mask=11.8%  norm=0.968  lr=4.02e-05  dt=  37.1ms  words=83,214,336
[E07   871/1548 G  10158|CLM] train=2.2441  mask=11.8%  norm=0.710  lr=4.02e-05  dt=  36.9ms  words=83,222,528
[E07   872/1548 G  10159|CLM] train=2.0567  mask=11.8%  norm=0.918  lr=4.02e-05  dt=  36.9ms  words=83,230,720
[E07   873/1548 G  10160|CLM] train=3.8206  mask=11.8%  norm=0.883  lr=4.01e-05  dt=  37.0ms  words=83,238,912
[E07   874/1548 G  10161|CLM] train=2.6840  mask=11.8%  norm=0.821  lr=4.01e-05  dt=  37.1ms  words=83,247,104
[E07   875/1548 G  10162|CLM] train=2.5943  mask=11.8%  norm=0.726  lr=4.01e-05  dt=  36.8ms  words=83,255,296
[E07   876/1548 G  10163|CLM] train=2.3112  mask=11.8%  norm=0.734  lr=4.01e-05  dt=  37.1ms  words=83,263,488
[E07   877/1548 G  10164|CLM] train=1.9342  mask=11.8%  norm=0.757  lr=4.01e-05  dt=  37.1ms  words=83,271,680
[E07   878/1548 G  10165|CLM] train=3.3734  mask=11.8%  norm=0.772  lr=4.00e-05  dt=  37.4ms  words=83,279,872
[E07   879/1548 G  10166|CLM] train=2.1785  mask=11.8%  norm=0.688  lr=4.00e-05  dt=  38.5ms  words=83,288,064
[E07   880/1548 G  10167|CLM] train=3.7966  mask=11.8%  norm=0.895  lr=4.00e-05  dt=  37.0ms  words=83,296,256
[E07   881/1548 G  10168|CLM] train=4.1254  mask=11.8%  norm=1.044  lr=4.00e-05  dt=  36.9ms  words=83,304,448
[E07   882/1548 G  10169|CLM] train=4.8725  mask=11.8%  norm=1.029  lr=3.99e-05  dt=  36.9ms  words=83,312,640
[E07   883/1548 G  10170|CLM] train=3.6887  mask=11.8%  norm=1.104  lr=3.99e-05  dt=  37.0ms  words=83,320,832
[E07   884/1548 G  10171|CLM] train=1.8355  mask=11.8%  norm=0.743  lr=3.99e-05  dt=  36.9ms  words=83,329,024
[E07   885/1548 G  10172|CLM] train=3.7146  mask=11.8%  norm=0.840  lr=3.99e-05  dt=  36.8ms  words=83,337,216
[E07   886/1548 G  10173|CLM] train=2.2409  mask=11.8%  norm=0.743  lr=3.99e-05  dt=  37.7ms  words=83,345,408
[E07   887/1548 G  10174|CLM] train=2.2243  mask=11.8%  norm=0.965  lr=3.98e-05  dt=  37.0ms  words=83,353,600
[E07   888/1548 G  10175|CLM] train=4.0790  mask=11.8%  norm=0.983  lr=3.98e-05  dt=  37.1ms  words=83,361,792
[E07   889/1548 G  10176|CLM] train=2.0769  mask=11.8%  norm=0.750  lr=3.98e-05  dt=  37.1ms  words=83,369,984
[E07   890/1548 G  10177|CLM] train=1.9452  mask=11.8%  norm=0.673  lr=3.98e-05  dt=  38.0ms  words=83,378,176
[E07   891/1548 G  10178|CLM] train=4.3700  mask=11.8%  norm=0.901  lr=3.98e-05  dt=  39.0ms  words=83,386,368
[E07   892/1548 G  10179|CLM] train=3.7662  mask=11.8%  norm=0.779  lr=3.97e-05  dt=  45.1ms  words=83,394,560
[E07   893/1548 G  10180|CLM] train=4.0307  mask=11.8%  norm=0.846  lr=3.97e-05  dt=  37.1ms  words=83,402,752
[E07   894/1548 G  10181|CLM] train=2.0149  mask=11.8%  norm=0.734  lr=3.97e-05  dt=  37.4ms  words=83,410,944
[E07   895/1548 G  10182|CLM] train=4.3186  mask=11.8%  norm=0.941  lr=3.97e-05  dt=  37.3ms  words=83,419,136
[E07   896/1548 G  10183|CLM] train=4.2187  mask=11.8%  norm=0.998  lr=3.96e-05  dt=  37.1ms  words=83,427,328
[E07   897/1548 G  10184|CLM] train=4.0115  mask=11.8%  norm=0.836  lr=3.96e-05  dt=  37.2ms  words=83,435,520
[E07   898/1548 G  10185|CLM] train=3.2620  mask=11.8%  norm=0.982  lr=3.96e-05  dt=  36.8ms  words=83,443,712
[E07   899/1548 G  10186|CLM] train=4.4159  mask=11.8%  norm=0.966  lr=3.96e-05  dt=  36.8ms  words=83,451,904
[E07   900/1548 G  10187|CLM] train=2.5342  mask=11.8%  norm=0.722  lr=3.96e-05  dt=  37.0ms  words=83,460,096
[E07   901/1548 G  10188|CLM] train=2.1053  mask=11.8%  norm=0.669  lr=3.95e-05  dt=  37.1ms  words=83,468,288
[E07   902/1548 G  10189|CLM] train=2.2320  mask=11.8%  norm=0.688  lr=3.95e-05  dt=  36.9ms  words=83,476,480
[E07   903/1548 G  10190|CLM] train=3.7811  mask=11.8%  norm=0.873  lr=3.95e-05  dt=  36.9ms  words=83,484,672
[E07   904/1548 G  10191|CLM] train=4.0589  mask=11.8%  norm=1.270  lr=3.95e-05  dt=  37.0ms  words=83,492,864
[E07   905/1548 G  10192|CLM] train=3.9129  mask=11.8%  norm=0.815  lr=3.94e-05  dt=  38.4ms  words=83,501,056
[E07   906/1548 G  10193|CLM] train=3.6173  mask=11.8%  norm=0.857  lr=3.94e-05  dt=  37.0ms  words=83,509,248
[E07   907/1548 G  10194|CLM] train=3.9021  mask=11.8%  norm=0.783  lr=3.94e-05  dt=  36.9ms  words=83,517,440
[E07   908/1548 G  10195|CLM] train=3.2352  mask=11.8%  norm=0.743  lr=3.94e-05  dt=  37.0ms  words=83,525,632
[E07   909/1548 G  10196|CLM] train=2.1462  mask=11.8%  norm=0.680  lr=3.94e-05  dt=  36.7ms  words=83,533,824
[E07   910/1548 G  10197|CLM] train=2.1926  mask=11.8%  norm=0.760  lr=3.93e-05  dt=  37.0ms  words=83,542,016
[E07   911/1548 G  10198|CLM] train=3.7364  mask=11.8%  norm=1.002  lr=3.93e-05  dt=  37.0ms  words=83,550,208
[E07   912/1548 G  10199|CLM] train=2.0633  mask=11.8%  norm=0.670  lr=3.93e-05  dt=  36.9ms  words=83,558,400
[E07   913/1548 G  10200|CLM] train=2.2670  mask=11.8%  norm=0.928  lr=3.93e-05  dt=  37.2ms  words=83,566,592
[E07   914/1548 G  10201|CLM] train=3.6202  mask=11.8%  norm=0.838  lr=3.93e-05  dt=  37.6ms  words=83,574,784
[E07   915/1548 G  10202|CLM] train=4.1998  mask=11.8%  norm=0.932  lr=3.92e-05  dt=  37.2ms  words=83,582,976
[E07   916/1548 G  10203|CLM] train=3.7519  mask=11.8%  norm=0.815  lr=3.92e-05  dt=  37.2ms  words=83,591,168
[E07   917/1548 G  10204|CLM] train=4.0898  mask=11.8%  norm=0.847  lr=3.92e-05  dt=  37.1ms  words=83,599,360
[E07   918/1548 G  10205|CLM] train=2.7831  mask=11.8%  norm=0.893  lr=3.92e-05  dt=  37.1ms  words=83,607,552
[E07   919/1548 G  10206|CLM] train=4.1256  mask=11.8%  norm=0.830  lr=3.91e-05  dt=  37.7ms  words=83,615,744
[E07   920/1548 G  10207|CLM] train=4.0746  mask=11.8%  norm=1.081  lr=3.91e-05  dt=  37.4ms  words=83,623,936
[E07   921/1548 G  10208|CLM] train=4.4085  mask=11.8%  norm=0.946  lr=3.91e-05  dt=  42.1ms  words=83,632,128
[E07   922/1548 G  10209|CLM] train=2.3508  mask=11.8%  norm=0.769  lr=3.91e-05  dt=  42.2ms  words=83,640,320
[E07   923/1548 G  10210|CLM] train=3.5414  mask=11.8%  norm=0.896  lr=3.91e-05  dt=  40.5ms  words=83,648,512
[E07   924/1548 G  10211|CLM] train=3.7654  mask=11.8%  norm=0.810  lr=3.90e-05  dt=  37.1ms  words=83,656,704
[E07   925/1548 G  10212|CLM] train=3.6140  mask=11.8%  norm=0.933  lr=3.90e-05  dt=  37.2ms  words=83,664,896
[E07   926/1548 G  10213|CLM] train=1.9776  mask=11.8%  norm=0.784  lr=3.90e-05  dt=  37.1ms  words=83,673,088
[E07   927/1548 G  10214|CLM] train=4.1140  mask=11.8%  norm=0.932  lr=3.90e-05  dt=  37.1ms  words=83,681,280
[E07   928/1548 G  10215|CLM] train=2.2084  mask=11.8%  norm=0.664  lr=3.90e-05  dt=  37.1ms  words=83,689,472
[E07   929/1548 G  10216|CLM] train=4.2548  mask=11.8%  norm=0.960  lr=3.89e-05  dt=  37.4ms  words=83,697,664
[E07   930/1548 G  10217|CLM] train=2.1168  mask=11.7%  norm=0.683  lr=3.89e-05  dt=  37.2ms  words=83,705,856
[E07   931/1548 G  10218|CLM] train=4.0215  mask=11.7%  norm=0.861  lr=3.89e-05  dt=  37.5ms  words=83,714,048
[E07   932/1548 G  10219|CLM] train=2.1324  mask=11.7%  norm=0.744  lr=3.89e-05  dt=  37.0ms  words=83,722,240
[E07   933/1548 G  10220|CLM] train=3.7929  mask=11.7%  norm=0.859  lr=3.88e-05  dt=  36.9ms  words=83,730,432
[E07   934/1548 G  10221|CLM] train=4.1096  mask=11.7%  norm=0.845  lr=3.88e-05  dt=  37.1ms  words=83,738,624
[E07   935/1548 G  10222|CLM] train=4.2099  mask=11.7%  norm=0.904  lr=3.88e-05  dt=  37.1ms  words=83,746,816
[E07   936/1548 G  10223|CLM] train=4.1383  mask=11.7%  norm=1.041  lr=3.88e-05  dt=  37.1ms  words=83,755,008
[E07   937/1548 G  10224|CLM] train=4.4528  mask=11.7%  norm=0.847  lr=3.88e-05  dt=  36.8ms  words=83,763,200
[E07   938/1548 G  10225|CLM] train=2.0265  mask=11.7%  norm=0.717  lr=3.87e-05  dt=  36.9ms  words=83,771,392
[E07   939/1548 G  10226|CLM] train=2.1206  mask=11.7%  norm=0.756  lr=3.87e-05  dt=  36.9ms  words=83,779,584
[E07   940/1548 G  10227|CLM] train=2.1549  mask=11.7%  norm=0.735  lr=3.87e-05  dt=  37.1ms  words=83,787,776
[E07   941/1548 G  10228|CLM] train=4.1005  mask=11.7%  norm=0.870  lr=3.87e-05  dt=  36.8ms  words=83,795,968
[E07   942/1548 G  10229|CLM] train=2.2953  mask=11.7%  norm=0.684  lr=3.87e-05  dt=  37.2ms  words=83,804,160
[E07   943/1548 G  10230|CLM] train=2.3756  mask=11.7%  norm=0.685  lr=3.86e-05  dt=  36.9ms  words=83,812,352
[E07   944/1548 G  10231|CLM] train=3.6467  mask=11.7%  norm=0.895  lr=3.86e-05  dt=  36.8ms  words=83,820,544
[E07   945/1548 G  10232|CLM] train=4.1187  mask=11.7%  norm=1.067  lr=3.86e-05  dt=  36.9ms  words=83,828,736
[E07   946/1548 G  10233|CLM] train=4.0686  mask=11.7%  norm=0.890  lr=3.86e-05  dt=  36.9ms  words=83,836,928
[E07   947/1548 G  10234|CLM] train=2.3791  mask=11.7%  norm=0.678  lr=3.85e-05  dt=  37.0ms  words=83,845,120
[E07   948/1548 G  10235|CLM] train=2.4748  mask=11.7%  norm=0.768  lr=3.85e-05  dt=  36.8ms  words=83,853,312
[E07   949/1548 G  10236|CLM] train=4.1863  mask=11.7%  norm=0.858  lr=3.85e-05  dt=  36.8ms  words=83,861,504
[E07   950/1548 G  10237|CLM] train=3.7454  mask=11.7%  norm=0.912  lr=3.85e-05  dt=  36.9ms  words=83,869,696
[E07   951/1548 G  10238|CLM] train=4.3984  mask=11.7%  norm=1.125  lr=3.85e-05  dt=  36.9ms  words=83,877,888
[E07   952/1548 G  10239|CLM] train=3.9584  mask=11.7%  norm=0.850  lr=3.84e-05  dt=  37.0ms  words=83,886,080
[E07   953/1548 G  10240|CLM] train=3.7663  mask=11.7%  norm=0.902  lr=3.84e-05  dt=  36.8ms  words=83,894,272
[E07   954/1548 G  10241|CLM] train=4.0111  mask=11.7%  norm=0.998  lr=3.84e-05  dt=  37.0ms  words=83,902,464
[E07   955/1548 G  10242|CLM] train=3.5109  mask=11.7%  norm=0.844  lr=3.84e-05  dt=  36.9ms  words=83,910,656
[E07   956/1548 G  10243|CLM] train=3.2266  mask=11.7%  norm=0.833  lr=3.84e-05  dt=  36.9ms  words=83,918,848
[E07   957/1548 G  10244|CLM] train=2.1454  mask=11.7%  norm=0.778  lr=3.83e-05  dt=  36.8ms  words=83,927,040
[E07   958/1548 G  10245|CLM] train=2.2517  mask=11.7%  norm=0.693  lr=3.83e-05  dt=  36.9ms  words=83,935,232
[E07   959/1548 G  10246|CLM] train=5.3281  mask=11.7%  norm=1.121  lr=3.83e-05  dt=  37.0ms  words=83,943,424
[E07   960/1548 G  10247|CLM] train=4.6212  mask=11.7%  norm=0.910  lr=3.83e-05  dt=  36.9ms  words=83,951,616
[E07   961/1548 G  10248|CLM] train=4.1262  mask=11.7%  norm=1.208  lr=3.82e-05  dt=  36.8ms  words=83,959,808
[E07   962/1548 G  10249|CLM] train=1.5327  mask=11.7%  norm=0.728  lr=3.82e-05  dt=  36.9ms  words=83,968,000
[E07   963/1548 G  10250|CLM] train=2.0563  mask=11.7%  norm=0.674  lr=3.82e-05  dt=  37.0ms  words=83,976,192
[E07   964/1548 G  10251|CLM] train=1.9721  mask=11.7%  norm=0.720  lr=3.82e-05  dt=  36.9ms  words=83,984,384
[E07   965/1548 G  10252|CLM] train=2.2733  mask=11.7%  norm=0.712  lr=3.82e-05  dt=  36.8ms  words=83,992,576
[E07   966/1548 G  10253|CLM] train=3.8649  mask=11.7%  norm=1.029  lr=3.81e-05  dt=  36.9ms  words=84,000,768
[E07   967/1548 G  10254|CLM] train=2.2180  mask=11.7%  norm=0.701  lr=3.81e-05  dt=  36.9ms  words=84,008,960
[E07   968/1548 G  10255|CLM] train=3.9324  mask=11.7%  norm=0.837  lr=3.81e-05  dt=  36.9ms  words=84,017,152
[E07   969/1548 G  10256|CLM] train=2.0290  mask=11.7%  norm=0.915  lr=3.81e-05  dt=  37.0ms  words=84,025,344
[E07   970/1548 G  10257|CLM] train=3.2889  mask=11.7%  norm=0.832  lr=3.81e-05  dt=  37.0ms  words=84,033,536
[E07   971/1548 G  10258|CLM] train=4.5471  mask=11.7%  norm=1.064  lr=3.80e-05  dt=  37.1ms  words=84,041,728
[E07   972/1548 G  10259|CLM] train=3.7136  mask=11.7%  norm=0.797  lr=3.80e-05  dt=  36.9ms  words=84,049,920
[E07   973/1548 G  10260|CLM] train=3.6988  mask=11.7%  norm=0.934  lr=3.80e-05  dt=  36.8ms  words=84,058,112
[E07   974/1548 G  10261|CLM] train=4.0139  mask=11.7%  norm=0.877  lr=3.80e-05  dt=  36.8ms  words=84,066,304
[E07   975/1548 G  10262|CLM] train=4.0311  mask=11.7%  norm=0.864  lr=3.80e-05  dt=  37.0ms  words=84,074,496
[E07   976/1548 G  10263|CLM] train=3.7787  mask=11.7%  norm=0.801  lr=3.79e-05  dt=  36.9ms  words=84,082,688
[E07   977/1548 G  10264|CLM] train=2.0036  mask=11.7%  norm=0.753  lr=3.79e-05  dt=  36.9ms  words=84,090,880
[E07   978/1548 G  10265|CLM] train=2.2863  mask=11.7%  norm=0.717  lr=3.79e-05  dt=  36.9ms  words=84,099,072
[E07   979/1548 G  10266|CLM] train=3.6306  mask=11.7%  norm=0.885  lr=3.79e-05  dt=  37.1ms  words=84,107,264
[E07   980/1548 G  10267|CLM] train=3.7333  mask=11.7%  norm=1.040  lr=3.78e-05  dt=  36.8ms  words=84,115,456
[E07   981/1548 G  10268|CLM] train=4.7161  mask=11.7%  norm=2.337  lr=3.78e-05  dt=  36.8ms  words=84,123,648
[E07   982/1548 G  10269|CLM] train=3.3185  mask=11.7%  norm=0.776  lr=3.78e-05  dt=  37.0ms  words=84,131,840
[E07   983/1548 G  10270|CLM] train=4.6568  mask=11.7%  norm=1.012  lr=3.78e-05  dt=  36.9ms  words=84,140,032
[E07   984/1548 G  10271|CLM] train=2.4910  mask=11.7%  norm=0.764  lr=3.78e-05  dt=  36.9ms  words=84,148,224
[E07   985/1548 G  10272|CLM] train=2.2689  mask=11.7%  norm=0.683  lr=3.77e-05  dt=  36.8ms  words=84,156,416
[E07   986/1548 G  10273|CLM] train=1.7641  mask=11.7%  norm=0.703  lr=3.77e-05  dt=  36.8ms  words=84,164,608
[E07   987/1548 G  10274|CLM] train=4.3080  mask=11.7%  norm=0.877  lr=3.77e-05  dt=  36.8ms  words=84,172,800
[E07   988/1548 G  10275|CLM] train=4.3904  mask=11.7%  norm=1.278  lr=3.77e-05  dt=  36.9ms  words=84,180,992
[E07   989/1548 G  10276|CLM] train=3.8710  mask=11.7%  norm=1.075  lr=3.77e-05  dt=  36.7ms  words=84,189,184
[E07   990/1548 G  10277|CLM] train=3.6600  mask=11.7%  norm=0.847  lr=3.76e-05  dt=  36.9ms  words=84,197,376
[E07   991/1548 G  10278|CLM] train=2.0332  mask=11.7%  norm=0.779  lr=3.76e-05  dt=  36.8ms  words=84,205,568
[E07   992/1548 G  10279|CLM] train=2.3124  mask=11.7%  norm=0.862  lr=3.76e-05  dt=  37.0ms  words=84,213,760
[E07   993/1548 G  10280|CLM] train=2.2087  mask=11.7%  norm=0.679  lr=3.76e-05  dt=  36.8ms  words=84,221,952
[E07   994/1548 G  10281|CLM] train=3.8211  mask=11.7%  norm=0.746  lr=3.76e-05  dt=  36.8ms  words=84,230,144
[E07   995/1548 G  10282|CLM] train=1.9607  mask=11.7%  norm=0.714  lr=3.75e-05  dt=  36.8ms  words=84,238,336
[E07   996/1548 G  10283|CLM] train=5.3275  mask=11.7%  norm=2.271  lr=3.75e-05  dt=  37.2ms  words=84,246,528
[E07   997/1548 G  10284|CLM] train=4.9487  mask=11.7%  norm=1.083  lr=3.75e-05  dt=  36.9ms  words=84,254,720
[E07   998/1548 G  10285|CLM] train=2.3868  mask=11.7%  norm=0.745  lr=3.75e-05  dt=  37.3ms  words=84,262,912
[E07   999/1548 G  10286|CLM] train=3.1827  mask=11.7%  norm=0.722  lr=3.75e-05  dt=  36.9ms  words=84,271,104
[E07  1000/1548 G  10287|CLM] train=2.6841  mask=11.7%  norm=0.747  lr=3.74e-05  dt=  37.1ms  words=84,279,296
[E07  1001/1548 G  10288|CLM] train=1.8654  mask=11.7%  norm=0.792  lr=3.74e-05  dt=  36.8ms  words=84,287,488
[E07  1002/1548 G  10289|CLM] train=3.7281  mask=11.7%  norm=0.814  lr=3.74e-05  dt=  36.8ms  words=84,295,680
[E07  1003/1548 G  10290|CLM] train=3.2052  mask=11.7%  norm=0.763  lr=3.74e-05  dt=  36.7ms  words=84,303,872
[E07  1004/1548 G  10291|CLM] train=4.2627  mask=11.7%  norm=0.926  lr=3.73e-05  dt=  36.8ms  words=84,312,064
[E07  1005/1548 G  10292|CLM] train=4.1571  mask=11.7%  norm=0.954  lr=3.73e-05  dt=  36.8ms  words=84,320,256
[E07  1006/1548 G  10293|CLM] train=3.6498  mask=11.7%  norm=0.953  lr=3.73e-05  dt=  36.8ms  words=84,328,448
[E07  1007/1548 G  10294|CLM] train=2.0857  mask=11.7%  norm=0.659  lr=3.73e-05  dt=  36.9ms  words=84,336,640
[E07  1008/1548 G  10295|CLM] train=3.9273  mask=11.7%  norm=0.914  lr=3.73e-05  dt=  37.0ms  words=84,344,832
[E07  1009/1548 G  10296|CLM] train=3.8056  mask=11.7%  norm=0.835  lr=3.72e-05  dt=  36.8ms  words=84,353,024
[E07  1010/1548 G  10297|CLM] train=2.2572  mask=11.7%  norm=0.815  lr=3.72e-05  dt=  36.9ms  words=84,361,216
[E07  1011/1548 G  10298|CLM] train=3.7756  mask=11.7%  norm=0.825  lr=3.72e-05  dt=  37.0ms  words=84,369,408
[E07  1012/1548 G  10299|CLM] train=4.2585  mask=11.7%  norm=0.978  lr=3.72e-05  dt=  36.9ms  words=84,377,600
[E07  1013/1548 G  10300|CLM] train=4.0963  mask=11.7%  norm=0.929  lr=3.72e-05  dt=  36.8ms  words=84,385,792
[E07  1014/1548 G  10301|CLM] train=4.0624  mask=11.7%  norm=0.873  lr=3.71e-05  dt=  36.9ms  words=84,393,984
[E07  1015/1548 G  10302|CLM] train=3.9560  mask=11.7%  norm=0.830  lr=3.71e-05  dt=  38.7ms  words=84,402,176
[E07  1016/1548 G  10303|CLM] train=4.7966  mask=11.7%  norm=1.136  lr=3.71e-05  dt=  37.3ms  words=84,410,368
[E07  1017/1548 G  10304|CLM] train=4.1068  mask=11.7%  norm=0.976  lr=3.71e-05  dt=  37.0ms  words=84,418,560
[E07  1018/1548 G  10305|CLM] train=4.6771  mask=11.7%  norm=1.090  lr=3.71e-05  dt=  37.0ms  words=84,426,752
[E07  1019/1548 G  10306|CLM] train=3.6669  mask=11.7%  norm=0.797  lr=3.70e-05  dt=  36.9ms  words=84,434,944
[E07  1020/1548 G  10307|CLM] train=2.4186  mask=11.7%  norm=0.847  lr=3.70e-05  dt=  36.9ms  words=84,443,136
[E07  1021/1548 G  10308|CLM] train=2.3394  mask=11.7%  norm=0.824  lr=3.70e-05  dt=  37.0ms  words=84,451,328
[E07  1022/1548 G  10309|CLM] train=3.7506  mask=11.7%  norm=0.919  lr=3.70e-05  dt=  37.9ms  words=84,459,520
[E07  1023/1548 G  10310|CLM] train=2.1515  mask=11.7%  norm=0.970  lr=3.70e-05  dt=  37.0ms  words=84,467,712
[E07  1024/1548 G  10311|CLM] train=3.9753  mask=11.7%  norm=0.981  lr=3.69e-05  dt=  36.9ms  words=84,475,904
[E07  1025/1548 G  10312|CLM] train=2.3515  mask=11.7%  norm=0.751  lr=3.69e-05  dt=  37.0ms  words=84,484,096
[E07  1026/1548 G  10313|CLM] train=2.4137  mask=11.7%  norm=0.984  lr=3.69e-05  dt=  36.9ms  words=84,492,288
[E07  1027/1548 G  10314|CLM] train=2.1981  mask=11.7%  norm=0.711  lr=3.69e-05  dt=  37.5ms  words=84,500,480
[E07  1028/1548 G  10315|CLM] train=2.5067  mask=11.7%  norm=0.795  lr=3.69e-05  dt=  37.1ms  words=84,508,672
[E07  1029/1548 G  10316|CLM] train=2.6495  mask=11.7%  norm=1.845  lr=3.68e-05  dt=  37.0ms  words=84,516,864
[E07  1030/1548 G  10317|CLM] train=4.1767  mask=11.7%  norm=0.882  lr=3.68e-05  dt=  37.3ms  words=84,525,056
[E07  1031/1548 G  10318|CLM] train=4.6267  mask=11.7%  norm=0.934  lr=3.68e-05  dt=  37.0ms  words=84,533,248
[E07  1032/1548 G  10319|CLM] train=2.6171  mask=11.7%  norm=0.831  lr=3.68e-05  dt=  37.2ms  words=84,541,440
[E07  1033/1548 G  10320|CLM] train=2.1904  mask=11.7%  norm=0.716  lr=3.67e-05  dt=  36.9ms  words=84,549,632
[E07  1034/1548 G  10321|CLM] train=1.7747  mask=11.7%  norm=0.689  lr=3.67e-05  dt=  37.2ms  words=84,557,824
[E07  1035/1548 G  10322|CLM] train=1.9663  mask=11.7%  norm=0.761  lr=3.67e-05  dt=  36.9ms  words=84,566,016
[E07  1036/1548 G  10323|CLM] train=4.6930  mask=11.7%  norm=1.100  lr=3.67e-05  dt=  37.2ms  words=84,574,208
[E07  1037/1548 G  10324|CLM] train=2.1649  mask=11.7%  norm=0.684  lr=3.67e-05  dt=  37.0ms  words=84,582,400
[E07  1038/1548 G  10325|CLM] train=4.2772  mask=11.7%  norm=0.891  lr=3.66e-05  dt=  37.3ms  words=84,590,592
[E07  1039/1548 G  10326|CLM] train=3.7316  mask=11.7%  norm=0.890  lr=3.66e-05  dt=  36.9ms  words=84,598,784
[E07  1040/1548 G  10327|CLM] train=4.1265  mask=11.7%  norm=0.962  lr=3.66e-05  dt=  37.0ms  words=84,606,976
[E07  1041/1548 G  10328|CLM] train=3.6017  mask=11.7%  norm=0.898  lr=3.66e-05  dt=  36.9ms  words=84,615,168
[E07  1042/1548 G  10329|CLM] train=4.8595  mask=11.7%  norm=1.357  lr=3.66e-05  dt=  37.2ms  words=84,623,360
[E07  1043/1548 G  10330|CLM] train=3.6184  mask=11.7%  norm=0.883  lr=3.65e-05  dt=  37.1ms  words=84,631,552
[E07  1044/1548 G  10331|CLM] train=2.5668  mask=11.7%  norm=0.715  lr=3.65e-05  dt=  37.3ms  words=84,639,744
[E07  1045/1548 G  10332|CLM] train=4.1379  mask=11.7%  norm=0.854  lr=3.65e-05  dt=  37.0ms  words=84,647,936
[E07  1046/1548 G  10333|CLM] train=1.7503  mask=11.7%  norm=0.703  lr=3.65e-05  dt=  37.0ms  words=84,656,128
[E07  1047/1548 G  10334|CLM] train=4.5272  mask=11.7%  norm=0.989  lr=3.65e-05  dt=  37.1ms  words=84,664,320
[E07  1048/1548 G  10335|CLM] train=1.9107  mask=11.7%  norm=0.751  lr=3.64e-05  dt=  36.9ms  words=84,672,512
[E07  1049/1548 G  10336|CLM] train=4.7608  mask=11.7%  norm=1.378  lr=3.64e-05  dt=  36.9ms  words=84,680,704
[E07  1050/1548 G  10337|CLM] train=2.3559  mask=11.7%  norm=0.827  lr=3.64e-05  dt=  36.9ms  words=84,688,896
[E07  1051/1548 G  10338|CLM] train=3.8479  mask=11.7%  norm=0.916  lr=3.64e-05  dt=  37.0ms  words=84,697,088
[E07  1052/1548 G  10339|CLM] train=4.4659  mask=11.7%  norm=1.047  lr=3.64e-05  dt=  37.2ms  words=84,705,280
[E07  1053/1548 G  10340|CLM] train=3.3019  mask=11.7%  norm=0.723  lr=3.63e-05  dt=  37.0ms  words=84,713,472
[E07  1054/1548 G  10341|CLM] train=4.0584  mask=11.6%  norm=0.886  lr=3.63e-05  dt=  37.2ms  words=84,721,664
[E07  1055/1548 G  10342|CLM] train=2.0336  mask=11.6%  norm=0.765  lr=3.63e-05  dt=  37.0ms  words=84,729,856
[E07  1056/1548 G  10343|CLM] train=1.8489  mask=11.6%  norm=0.739  lr=3.63e-05  dt=  37.3ms  words=84,738,048
[E07  1057/1548 G  10344|CLM] train=5.0870  mask=11.6%  norm=1.452  lr=3.63e-05  dt=  36.8ms  words=84,746,240
[E07  1058/1548 G  10345|CLM] train=2.2492  mask=11.6%  norm=0.761  lr=3.62e-05  dt=  36.9ms  words=84,754,432
[E07  1059/1548 G  10346|CLM] train=4.4212  mask=11.6%  norm=1.008  lr=3.62e-05  dt=  37.2ms  words=84,762,624
[E07  1060/1548 G  10347|CLM] train=3.5926  mask=11.6%  norm=0.873  lr=3.62e-05  dt=  36.9ms  words=84,770,816
[E07  1061/1548 G  10348|CLM] train=3.9383  mask=11.6%  norm=1.177  lr=3.62e-05  dt=  37.2ms  words=84,779,008
[E07  1062/1548 G  10349|CLM] train=4.9097  mask=11.6%  norm=1.174  lr=3.62e-05  dt=  37.0ms  words=84,787,200
[E07  1063/1548 G  10350|CLM] train=3.9302  mask=11.6%  norm=0.883  lr=3.61e-05  dt=  37.2ms  words=84,795,392
[E07  1064/1548 G  10351|CLM] train=3.6148  mask=11.6%  norm=0.806  lr=3.61e-05  dt=  37.0ms  words=84,803,584
[E07  1065/1548 G  10352|CLM] train=3.3636  mask=11.6%  norm=0.785  lr=3.61e-05  dt=  37.1ms  words=84,811,776
[E07  1066/1548 G  10353|CLM] train=4.1346  mask=11.6%  norm=0.883  lr=3.61e-05  dt=  37.1ms  words=84,819,968
[E07  1067/1548 G  10354|CLM] train=4.1436  mask=11.6%  norm=1.015  lr=3.61e-05  dt=  37.0ms  words=84,828,160
[E07  1068/1548 G  10355|CLM] train=3.9891  mask=11.6%  norm=0.881  lr=3.60e-05  dt=  36.9ms  words=84,836,352
[E07  1069/1548 G  10356|CLM] train=4.0794  mask=11.6%  norm=0.934  lr=3.60e-05  dt=  37.3ms  words=84,844,544
[E07  1070/1548 G  10357|CLM] train=4.2109  mask=11.6%  norm=0.917  lr=3.60e-05  dt=  37.2ms  words=84,852,736
[E07  1071/1548 G  10358|CLM] train=2.0210  mask=11.6%  norm=0.703  lr=3.60e-05  dt=  36.8ms  words=84,860,928
[E07  1072/1548 G  10359|CLM] train=4.0669  mask=11.6%  norm=0.863  lr=3.60e-05  dt=  37.8ms  words=84,869,120
[E07  1073/1548 G  10360|CLM] train=3.7474  mask=11.6%  norm=0.865  lr=3.59e-05  dt=  38.2ms  words=84,877,312
[E07  1074/1548 G  10361|CLM] train=4.2314  mask=11.6%  norm=0.882  lr=3.59e-05  dt=  37.6ms  words=84,885,504
[E07  1075/1548 G  10362|CLM] train=1.7910  mask=11.6%  norm=0.747  lr=3.59e-05  dt=  38.0ms  words=84,893,696
[E07  1076/1548 G  10363|CLM] train=3.8062  mask=11.6%  norm=0.842  lr=3.59e-05  dt=  37.8ms  words=84,901,888
[E07  1077/1548 G  10364|CLM] train=2.5517  mask=11.6%  norm=0.801  lr=3.59e-05  dt=  38.1ms  words=84,910,080
[E07  1078/1548 G  10365|CLM] train=2.2866  mask=11.6%  norm=0.708  lr=3.58e-05  dt=  37.2ms  words=84,918,272
[E07  1079/1548 G  10366|CLM] train=2.6200  mask=11.6%  norm=0.710  lr=3.58e-05  dt=  38.5ms  words=84,926,464
[E07  1080/1548 G  10367|CLM] train=2.6613  mask=11.6%  norm=0.765  lr=3.58e-05  dt=  37.7ms  words=84,934,656
[E07  1081/1548 G  10368|CLM] train=1.6806  mask=11.6%  norm=0.695  lr=3.58e-05  dt=  37.6ms  words=84,942,848
[E07  1082/1548 G  10369|CLM] train=4.0605  mask=11.6%  norm=1.009  lr=3.58e-05  dt= 440.4ms  words=84,951,040
[E07  1083/1548 G  10370|CLM] train=4.0149  mask=11.6%  norm=0.906  lr=3.57e-05  dt=  39.1ms  words=84,959,232
[E07  1084/1548 G  10371|CLM] train=2.1886  mask=11.6%  norm=0.672  lr=3.57e-05  dt=  37.5ms  words=84,967,424
[E07  1085/1548 G  10372|CLM] train=2.2654  mask=11.6%  norm=0.789  lr=3.57e-05  dt=  37.4ms  words=84,975,616
[E07  1086/1548 G  10373|CLM] train=4.2609  mask=11.6%  norm=0.904  lr=3.57e-05  dt=  37.4ms  words=84,983,808
[E07  1087/1548 G  10374|CLM] train=3.2878  mask=11.6%  norm=0.822  lr=3.57e-05  dt=  37.2ms  words=84,992,000
[E07  1088/1548 G  10375|CLM] train=4.2462  mask=11.6%  norm=0.861  lr=3.56e-05  dt=  37.2ms  words=85,000,192
[E07  1089/1548 G  10376|CLM] train=3.9430  mask=11.6%  norm=0.970  lr=3.56e-05  dt=  37.3ms  words=85,008,384
[E07  1090/1548 G  10377|CLM] train=2.6676  mask=11.6%  norm=0.764  lr=3.56e-05  dt=  37.0ms  words=85,016,576
[E07  1091/1548 G  10378|CLM] train=2.0608  mask=11.6%  norm=0.692  lr=3.56e-05  dt=  37.2ms  words=85,024,768
[E07  1092/1548 G  10379|CLM] train=3.7487  mask=11.6%  norm=0.938  lr=3.56e-05  dt=  37.2ms  words=85,032,960
[E07  1093/1548 G  10380|CLM] train=2.4754  mask=11.6%  norm=0.738  lr=3.55e-05  dt=  37.3ms  words=85,041,152
[E07  1094/1548 G  10381|CLM] train=1.8997  mask=11.6%  norm=0.714  lr=3.55e-05  dt=  37.3ms  words=85,049,344
[E07  1095/1548 G  10382|CLM] train=1.5022  mask=11.6%  norm=0.632  lr=3.55e-05  dt=  37.2ms  words=85,057,536
[E07  1096/1548 G  10383|CLM] train=2.3658  mask=11.6%  norm=0.963  lr=3.55e-05  dt=  37.7ms  words=85,065,728
[E07  1097/1548 G  10384|CLM] train=2.1490  mask=11.6%  norm=0.683  lr=3.55e-05  dt=  37.4ms  words=85,073,920
[E07  1098/1548 G  10385|CLM] train=2.5860  mask=11.6%  norm=0.716  lr=3.54e-05  dt=  37.2ms  words=85,082,112
[E07  1099/1548 G  10386|CLM] train=4.3527  mask=11.6%  norm=0.898  lr=3.54e-05  dt=  37.0ms  words=85,090,304
[E07  1100/1548 G  10387|CLM] train=4.6066  mask=11.6%  norm=0.956  lr=3.54e-05  dt=  37.2ms  words=85,098,496
[E07  1101/1548 G  10388|CLM] train=1.9950  mask=11.6%  norm=0.688  lr=3.54e-05  dt=  37.1ms  words=85,106,688
[E07  1102/1548 G  10389|CLM] train=2.2030  mask=11.6%  norm=0.681  lr=3.54e-05  dt=  37.0ms  words=85,114,880
[E07  1103/1548 G  10390|CLM] train=2.3421  mask=11.6%  norm=0.693  lr=3.53e-05  dt=  37.4ms  words=85,123,072
[E07  1104/1548 G  10391|CLM] train=4.6669  mask=11.6%  norm=1.096  lr=3.53e-05  dt=  37.4ms  words=85,131,264
[E07  1105/1548 G  10392|CLM] train=2.6380  mask=11.6%  norm=0.698  lr=3.53e-05  dt=  37.2ms  words=85,139,456
[E07  1106/1548 G  10393|CLM] train=4.2679  mask=11.6%  norm=0.899  lr=3.53e-05  dt=  37.3ms  words=85,147,648
[E07  1107/1548 G  10394|CLM] train=1.8626  mask=11.6%  norm=0.599  lr=3.53e-05  dt=  37.2ms  words=85,155,840
[E07  1108/1548 G  10395|CLM] train=4.0215  mask=11.6%  norm=0.944  lr=3.52e-05  dt=  37.3ms  words=85,164,032
[E07  1109/1548 G  10396|CLM] train=2.3666  mask=11.6%  norm=0.741  lr=3.52e-05  dt=  37.2ms  words=85,172,224
[E07  1110/1548 G  10397|CLM] train=1.9170  mask=11.6%  norm=0.770  lr=3.52e-05  dt=  37.0ms  words=85,180,416
[E07  1111/1548 G  10398|CLM] train=3.9867  mask=11.6%  norm=0.934  lr=3.52e-05  dt=  37.2ms  words=85,188,608
[E07  1112/1548 G  10399|CLM] train=4.0681  mask=11.6%  norm=0.851  lr=3.52e-05  dt=  37.2ms  words=85,196,800
[E07  1113/1548 G  10400|CLM] train=3.9452  mask=11.6%  norm=0.914  lr=3.51e-05  dt=  37.5ms  words=85,204,992
[E07  1114/1548 G  10401|CLM] train=2.1857  mask=11.6%  norm=0.911  lr=3.51e-05  dt=  37.1ms  words=85,213,184
[E07  1115/1548 G  10402|CLM] train=4.2745  mask=11.6%  norm=0.942  lr=3.51e-05  dt=  37.3ms  words=85,221,376
[E07  1116/1548 G  10403|CLM] train=3.9325  mask=11.6%  norm=0.938  lr=3.51e-05  dt=  37.0ms  words=85,229,568
[E07  1117/1548 G  10404|CLM] train=3.9702  mask=11.6%  norm=0.892  lr=3.51e-05  dt=  37.0ms  words=85,237,760
[E07  1118/1548 G  10405|CLM] train=2.1529  mask=11.6%  norm=0.727  lr=3.50e-05  dt=  36.9ms  words=85,245,952
[E07  1119/1548 G  10406|CLM] train=3.9381  mask=11.6%  norm=0.909  lr=3.50e-05  dt=  37.1ms  words=85,254,144
[E07  1120/1548 G  10407|CLM] train=4.0925  mask=11.6%  norm=1.256  lr=3.50e-05  dt=  37.0ms  words=85,262,336
[E07  1121/1548 G  10408|CLM] train=2.5162  mask=11.6%  norm=0.763  lr=3.50e-05  dt=  36.9ms  words=85,270,528
[E07  1122/1548 G  10409|CLM] train=2.1345  mask=11.6%  norm=0.764  lr=3.50e-05  dt=  37.0ms  words=85,278,720
[E07  1123/1548 G  10410|CLM] train=3.9489  mask=11.6%  norm=0.840  lr=3.49e-05  dt=  37.0ms  words=85,286,912
[E07  1124/1548 G  10411|CLM] train=3.9414  mask=11.6%  norm=0.893  lr=3.49e-05  dt=  37.1ms  words=85,295,104
[E07  1125/1548 G  10412|CLM] train=3.5661  mask=11.6%  norm=0.896  lr=3.49e-05  dt=  37.0ms  words=85,303,296
[E07  1126/1548 G  10413|CLM] train=4.5116  mask=11.6%  norm=0.902  lr=3.49e-05  dt=  36.9ms  words=85,311,488
[E07  1127/1548 G  10414|CLM] train=3.9554  mask=11.6%  norm=0.956  lr=3.49e-05  dt=  37.3ms  words=85,319,680
[E07  1128/1548 G  10415|CLM] train=3.6188  mask=11.6%  norm=0.822  lr=3.48e-05  dt=  36.9ms  words=85,327,872
[E07  1129/1548 G  10416|CLM] train=3.6062  mask=11.6%  norm=0.727  lr=3.48e-05  dt=  36.9ms  words=85,336,064
[E07  1130/1548 G  10417|CLM] train=1.9491  mask=11.6%  norm=0.731  lr=3.48e-05  dt=  36.9ms  words=85,344,256
[E07  1131/1548 G  10418|CLM] train=2.4173  mask=11.6%  norm=0.669  lr=3.48e-05  dt=  37.1ms  words=85,352,448
[E07  1132/1548 G  10419|CLM] train=4.0792  mask=11.6%  norm=0.886  lr=3.48e-05  dt=  36.8ms  words=85,360,640
[E07  1133/1548 G  10420|CLM] train=2.5731  mask=11.6%  norm=0.694  lr=3.47e-05  dt=  36.9ms  words=85,368,832
[E07  1134/1548 G  10421|CLM] train=2.3123  mask=11.6%  norm=0.743  lr=3.47e-05  dt=  36.9ms  words=85,377,024
[E07  1135/1548 G  10422|CLM] train=2.1484  mask=11.6%  norm=0.672  lr=3.47e-05  dt=  37.4ms  words=85,385,216
[E07  1136/1548 G  10423|CLM] train=3.9431  mask=11.6%  norm=1.283  lr=3.47e-05  dt=  37.0ms  words=85,393,408
[E07  1137/1548 G  10424|CLM] train=1.9879  mask=11.6%  norm=0.681  lr=3.47e-05  dt=  37.0ms  words=85,401,600
[E07  1138/1548 G  10425|CLM] train=3.7858  mask=11.6%  norm=0.960  lr=3.46e-05  dt=  37.2ms  words=85,409,792
[E07  1139/1548 G  10426|CLM] train=3.7604  mask=11.6%  norm=0.904  lr=3.46e-05  dt=  37.2ms  words=85,417,984
[E07  1140/1548 G  10427|CLM] train=4.0636  mask=11.6%  norm=0.995  lr=3.46e-05  dt=  36.9ms  words=85,426,176
[E07  1141/1548 G  10428|CLM] train=3.6348  mask=11.6%  norm=0.789  lr=3.46e-05  dt=  37.4ms  words=85,434,368
[E07  1142/1548 G  10429|CLM] train=2.0209  mask=11.6%  norm=0.636  lr=3.46e-05  dt=  37.2ms  words=85,442,560
[E07  1143/1548 G  10430|CLM] train=4.9580  mask=11.6%  norm=1.088  lr=3.45e-05  dt=  36.9ms  words=85,450,752
[E07  1144/1548 G  10431|CLM] train=3.8924  mask=11.6%  norm=0.994  lr=3.45e-05  dt=  36.9ms  words=85,458,944
[E07  1145/1548 G  10432|CLM] train=4.1743  mask=11.6%  norm=0.891  lr=3.45e-05  dt=  37.8ms  words=85,467,136
[E07  1146/1548 G  10433|CLM] train=4.7028  mask=11.6%  norm=1.039  lr=3.45e-05  dt=  37.1ms  words=85,475,328
[E07  1147/1548 G  10434|CLM] train=3.9007  mask=11.6%  norm=0.832  lr=3.45e-05  dt=  36.9ms  words=85,483,520
[E07  1148/1548 G  10435|CLM] train=2.0331  mask=11.6%  norm=0.731  lr=3.44e-05  dt=  37.0ms  words=85,491,712
[E07  1149/1548 G  10436|CLM] train=4.1410  mask=11.6%  norm=0.880  lr=3.44e-05  dt=  36.9ms  words=85,499,904
[E07  1150/1548 G  10437|CLM] train=3.6199  mask=11.6%  norm=0.872  lr=3.44e-05  dt=  36.9ms  words=85,508,096
[E07  1151/1548 G  10438|CLM] train=4.4284  mask=11.6%  norm=0.945  lr=3.44e-05  dt=  37.0ms  words=85,516,288
[E07  1152/1548 G  10439|CLM] train=2.0451  mask=11.6%  norm=0.705  lr=3.44e-05  dt=  37.7ms  words=85,524,480
[E07  1153/1548 G  10440|CLM] train=1.9405  mask=11.6%  norm=0.831  lr=3.43e-05  dt=  37.0ms  words=85,532,672
[E07  1154/1548 G  10441|CLM] train=2.1919  mask=11.6%  norm=0.820  lr=3.43e-05  dt=  37.0ms  words=85,540,864
[E07  1155/1548 G  10442|CLM] train=3.8834  mask=11.6%  norm=0.929  lr=3.43e-05  dt=  37.1ms  words=85,549,056
[E07  1156/1548 G  10443|CLM] train=3.8013  mask=11.6%  norm=1.014  lr=3.43e-05  dt=  36.9ms  words=85,557,248
[E07  1157/1548 G  10444|CLM] train=2.4376  mask=11.6%  norm=0.648  lr=3.43e-05  dt=  37.0ms  words=85,565,440
[E07  1158/1548 G  10445|CLM] train=3.9851  mask=11.6%  norm=0.897  lr=3.43e-05  dt=  37.2ms  words=85,573,632
[E07  1159/1548 G  10446|CLM] train=3.6690  mask=11.6%  norm=0.910  lr=3.42e-05  dt=  42.2ms  words=85,581,824
[E07  1160/1548 G  10447|CLM] train=3.5573  mask=11.6%  norm=0.772  lr=3.42e-05  dt=  37.1ms  words=85,590,016
[E07  1161/1548 G  10448|CLM] train=3.7103  mask=11.6%  norm=0.802  lr=3.42e-05  dt=  37.1ms  words=85,598,208
[E07  1162/1548 G  10449|CLM] train=2.4968  mask=11.6%  norm=0.780  lr=3.42e-05  dt=  36.9ms  words=85,606,400
[E07  1163/1548 G  10450|CLM] train=4.2046  mask=11.6%  norm=0.924  lr=3.42e-05  dt=  37.1ms  words=85,614,592
[E07  1164/1548 G  10451|CLM] train=1.9549  mask=11.6%  norm=0.688  lr=3.41e-05  dt=  37.1ms  words=85,622,784
[E07  1165/1548 G  10452|CLM] train=4.4756  mask=11.6%  norm=0.953  lr=3.41e-05  dt=  37.0ms  words=85,630,976
[E07  1166/1548 G  10453|CLM] train=2.7487  mask=11.6%  norm=0.793  lr=3.41e-05  dt=  37.1ms  words=85,639,168
[E07  1167/1548 G  10454|CLM] train=2.1069  mask=11.6%  norm=0.674  lr=3.41e-05  dt=  37.2ms  words=85,647,360
[E07  1168/1548 G  10455|CLM] train=3.7930  mask=11.6%  norm=1.033  lr=3.41e-05  dt=  36.9ms  words=85,655,552
[E07  1169/1548 G  10456|CLM] train=4.0602  mask=11.6%  norm=1.040  lr=3.40e-05  dt=  37.2ms  words=85,663,744
[E07  1170/1548 G  10457|CLM] train=3.4060  mask=11.6%  norm=0.831  lr=3.40e-05  dt=  37.0ms  words=85,671,936
[E07  1171/1548 G  10458|CLM] train=4.0383  mask=11.6%  norm=0.914  lr=3.40e-05  dt=  37.1ms  words=85,680,128
[E07  1172/1548 G  10459|CLM] train=3.8675  mask=11.6%  norm=0.909  lr=3.40e-05  dt=  37.1ms  words=85,688,320
[E07  1173/1548 G  10460|CLM] train=4.4968  mask=11.6%  norm=0.844  lr=3.40e-05  dt=  36.9ms  words=85,696,512
[E07  1174/1548 G  10461|CLM] train=3.9490  mask=11.6%  norm=0.792  lr=3.39e-05  dt=  37.0ms  words=85,704,704
[E07  1175/1548 G  10462|CLM] train=4.4637  mask=11.6%  norm=0.859  lr=3.39e-05  dt=  37.1ms  words=85,712,896
[E07  1176/1548 G  10463|CLM] train=2.0940  mask=11.6%  norm=0.849  lr=3.39e-05  dt=  37.0ms  words=85,721,088
[E07  1177/1548 G  10464|CLM] train=3.6537  mask=11.6%  norm=0.919  lr=3.39e-05  dt=  36.9ms  words=85,729,280
[E07  1178/1548 G  10465|CLM] train=4.4048  mask=11.5%  norm=0.912  lr=3.39e-05  dt=  36.9ms  words=85,737,472
[E07  1179/1548 G  10466|CLM] train=4.1343  mask=11.5%  norm=0.922  lr=3.38e-05  dt=  37.0ms  words=85,745,664
[E07  1180/1548 G  10467|CLM] train=3.9842  mask=11.5%  norm=0.869  lr=3.38e-05  dt=  37.3ms  words=85,753,856
[E07  1181/1548 G  10468|CLM] train=2.3835  mask=11.5%  norm=0.747  lr=3.38e-05  dt=  37.0ms  words=85,762,048
[E07  1182/1548 G  10469|CLM] train=4.3454  mask=11.5%  norm=1.023  lr=3.38e-05  dt=  37.1ms  words=85,770,240
[E07  1183/1548 G  10470|CLM] train=4.3309  mask=11.5%  norm=0.962  lr=3.38e-05  dt=  36.9ms  words=85,778,432
[E07  1184/1548 G  10471|CLM] train=3.4527  mask=11.5%  norm=0.797  lr=3.38e-05  dt=  36.9ms  words=85,786,624
[E07  1185/1548 G  10472|CLM] train=2.0749  mask=11.5%  norm=0.667  lr=3.37e-05  dt=  36.9ms  words=85,794,816
[E07  1186/1548 G  10473|CLM] train=3.6850  mask=11.5%  norm=0.821  lr=3.37e-05  dt=  37.0ms  words=85,803,008
[E07  1187/1548 G  10474|CLM] train=2.2273  mask=11.5%  norm=0.683  lr=3.37e-05  dt=  36.8ms  words=85,811,200
[E07  1188/1548 G  10475|CLM] train=3.8492  mask=11.5%  norm=0.931  lr=3.37e-05  dt=  36.8ms  words=85,819,392
[E07  1189/1548 G  10476|CLM] train=2.2180  mask=11.5%  norm=0.652  lr=3.37e-05  dt=  37.1ms  words=85,827,584
[E07  1190/1548 G  10477|CLM] train=4.2760  mask=11.5%  norm=0.828  lr=3.36e-05  dt=  37.0ms  words=85,835,776
[E07  1191/1548 G  10478|CLM] train=3.9422  mask=11.5%  norm=0.855  lr=3.36e-05  dt=  36.8ms  words=85,843,968
[E07  1192/1548 G  10479|CLM] train=3.9031  mask=11.5%  norm=0.910  lr=3.36e-05  dt=  36.9ms  words=85,852,160
[E07  1193/1548 G  10480|CLM] train=3.8903  mask=11.5%  norm=0.813  lr=3.36e-05  dt=  37.0ms  words=85,860,352
[E07  1194/1548 G  10481|CLM] train=3.9475  mask=11.5%  norm=0.880  lr=3.36e-05  dt=  37.0ms  words=85,868,544
[E07  1195/1548 G  10482|CLM] train=4.0807  mask=11.5%  norm=0.931  lr=3.35e-05  dt=  36.9ms  words=85,876,736
[E07  1196/1548 G  10483|CLM] train=4.7599  mask=11.5%  norm=1.477  lr=3.35e-05  dt=  36.7ms  words=85,884,928
[E07  1197/1548 G  10484|CLM] train=2.0574  mask=11.5%  norm=0.764  lr=3.35e-05  dt=  37.0ms  words=85,893,120
[E07  1198/1548 G  10485|CLM] train=2.1808  mask=11.5%  norm=0.684  lr=3.35e-05  dt=  37.0ms  words=85,901,312
[E07  1199/1548 G  10486|CLM] train=4.3488  mask=11.5%  norm=0.871  lr=3.35e-05  dt=  36.9ms  words=85,909,504
[E07  1200/1548 G  10487|CLM] train=4.1966  mask=11.5%  norm=0.889  lr=3.34e-05  dt=  37.0ms  words=85,917,696
[E07  1201/1548 G  10488|CLM] train=2.0760  mask=11.5%  norm=0.752  lr=3.34e-05  dt=  36.8ms  words=85,925,888
[E07  1202/1548 G  10489|CLM] train=3.8277  mask=11.5%  norm=0.887  lr=3.34e-05  dt=  37.5ms  words=85,934,080
[E07  1203/1548 G  10490|CLM] train=3.4486  mask=11.5%  norm=0.865  lr=3.34e-05  dt=  36.8ms  words=85,942,272
[E07  1204/1548 G  10491|CLM] train=4.0403  mask=11.5%  norm=0.997  lr=3.34e-05  dt=  36.9ms  words=85,950,464
[E07  1205/1548 G  10492|CLM] train=3.7054  mask=11.5%  norm=0.955  lr=3.34e-05  dt=  36.9ms  words=85,958,656
[E07  1206/1548 G  10493|CLM] train=4.0097  mask=11.5%  norm=1.003  lr=3.33e-05  dt=  37.0ms  words=85,966,848
[E07  1207/1548 G  10494|CLM] train=3.7109  mask=11.5%  norm=0.844  lr=3.33e-05  dt=  37.0ms  words=85,975,040
[E07  1208/1548 G  10495|CLM] train=1.5812  mask=11.5%  norm=0.657  lr=3.33e-05  dt=  37.0ms  words=85,983,232
[E07  1209/1548 G  10496|CLM] train=3.5723  mask=11.5%  norm=0.799  lr=3.33e-05  dt=  37.1ms  words=85,991,424
[E07  1210/1548 G  10497|CLM] train=4.0759  mask=11.5%  norm=0.847  lr=3.33e-05  dt=  36.9ms  words=85,999,616
[E07  1211/1548 G  10498|CLM] train=2.2179  mask=11.5%  norm=0.755  lr=3.32e-05  dt=  36.9ms  words=86,007,808
[E07  1212/1548 G  10499|CLM] train=4.1052  mask=11.5%  norm=0.895  lr=3.32e-05  dt=  37.0ms  words=86,016,000
[E07  1213/1548 G  10500|CLM] train=3.3837  mask=11.5%  norm=0.715  lr=3.32e-05  dt=  37.0ms  words=86,024,192
[E07  1214/1548 G  10501|CLM] train=4.0293  mask=11.5%  norm=0.924  lr=3.32e-05  dt=  36.8ms  words=86,032,384
[E07  1215/1548 G  10502|CLM] train=3.6326  mask=11.5%  norm=0.873  lr=3.32e-05  dt=  36.9ms  words=86,040,576
[E07  1216/1548 G  10503|CLM] train=2.1784  mask=11.5%  norm=0.753  lr=3.31e-05  dt=  37.2ms  words=86,048,768
[E07  1217/1548 G  10504|CLM] train=1.5889  mask=11.5%  norm=0.905  lr=3.31e-05  dt=  37.3ms  words=86,056,960
[E07  1218/1548 G  10505|CLM] train=2.2135  mask=11.5%  norm=0.650  lr=3.31e-05  dt=  37.0ms  words=86,065,152
[E07  1219/1548 G  10506|CLM] train=5.2552  mask=11.5%  norm=1.241  lr=3.31e-05  dt=  37.0ms  words=86,073,344
[E07  1220/1548 G  10507|CLM] train=2.0044  mask=11.5%  norm=0.730  lr=3.31e-05  dt=  37.2ms  words=86,081,536
[E07  1221/1548 G  10508|CLM] train=4.7916  mask=11.5%  norm=1.031  lr=3.30e-05  dt=  36.9ms  words=86,089,728
[E07  1222/1548 G  10509|CLM] train=2.0586  mask=11.5%  norm=0.660  lr=3.30e-05  dt=  36.8ms  words=86,097,920
[E07  1223/1548 G  10510|CLM] train=2.3812  mask=11.5%  norm=0.753  lr=3.30e-05  dt=  37.0ms  words=86,106,112
[E07  1224/1548 G  10511|CLM] train=4.1231  mask=11.5%  norm=0.933  lr=3.30e-05  dt=  37.0ms  words=86,114,304
[E07  1225/1548 G  10512|CLM] train=2.3685  mask=11.5%  norm=0.740  lr=3.30e-05  dt=  36.8ms  words=86,122,496
[E07  1226/1548 G  10513|CLM] train=4.0204  mask=11.5%  norm=1.069  lr=3.30e-05  dt=  37.0ms  words=86,130,688
[E07  1227/1548 G  10514|CLM] train=2.3590  mask=11.5%  norm=0.768  lr=3.29e-05  dt=  36.7ms  words=86,138,880
[E07  1228/1548 G  10515|CLM] train=3.1421  mask=11.5%  norm=0.785  lr=3.29e-05  dt=  36.7ms  words=86,147,072
[E07  1229/1548 G  10516|CLM] train=1.7276  mask=11.5%  norm=0.641  lr=3.29e-05  dt=  36.5ms  words=86,155,264
[E07  1230/1548 G  10517|CLM] train=3.6741  mask=11.5%  norm=0.882  lr=3.29e-05  dt=  36.6ms  words=86,163,456
[E07  1231/1548 G  10518|CLM] train=4.1103  mask=11.5%  norm=0.919  lr=3.29e-05  dt=  36.8ms  words=86,171,648
[E07  1232/1548 G  10519|CLM] train=3.5006  mask=11.5%  norm=1.067  lr=3.28e-05  dt=  36.7ms  words=86,179,840
[E07  1233/1548 G  10520|CLM] train=4.0698  mask=11.5%  norm=0.852  lr=3.28e-05  dt=  36.6ms  words=86,188,032
[E07  1234/1548 G  10521|CLM] train=4.1968  mask=11.5%  norm=0.923  lr=3.28e-05  dt=  36.6ms  words=86,196,224
[E07  1235/1548 G  10522|CLM] train=2.3525  mask=11.5%  norm=0.711  lr=3.28e-05  dt=  36.7ms  words=86,204,416
[E07  1236/1548 G  10523|CLM] train=4.5554  mask=11.5%  norm=0.898  lr=3.28e-05  dt=  36.7ms  words=86,212,608
[E07  1237/1548 G  10524|CLM] train=2.2869  mask=11.5%  norm=0.719  lr=3.27e-05  dt=  36.5ms  words=86,220,800
[E07  1238/1548 G  10525|CLM] train=4.0230  mask=11.5%  norm=1.007  lr=3.27e-05  dt=  36.7ms  words=86,228,992
[E07  1239/1548 G  10526|CLM] train=4.1067  mask=11.5%  norm=0.923  lr=3.27e-05  dt=  36.7ms  words=86,237,184
[E07  1240/1548 G  10527|CLM] train=2.7747  mask=11.5%  norm=0.758  lr=3.27e-05  dt=  36.5ms  words=86,245,376
[E07  1241/1548 G  10528|CLM] train=5.1500  mask=11.5%  norm=1.096  lr=3.27e-05  dt=  36.6ms  words=86,253,568
[E07  1242/1548 G  10529|CLM] train=3.9491  mask=11.5%  norm=0.904  lr=3.27e-05  dt=  36.6ms  words=86,261,760
[E07  1243/1548 G  10530|CLM] train=4.2041  mask=11.5%  norm=0.940  lr=3.26e-05  dt=  37.2ms  words=86,269,952
[E07  1244/1548 G  10531|CLM] train=4.0768  mask=11.5%  norm=0.835  lr=3.26e-05  dt=  36.5ms  words=86,278,144
[E07  1245/1548 G  10532|CLM] train=2.2509  mask=11.5%  norm=0.810  lr=3.26e-05  dt=  36.6ms  words=86,286,336
[E07  1246/1548 G  10533|CLM] train=3.8791  mask=11.5%  norm=0.856  lr=3.26e-05  dt=  36.8ms  words=86,294,528
[E07  1247/1548 G  10534|CLM] train=4.5845  mask=11.5%  norm=1.073  lr=3.26e-05  dt=  36.7ms  words=86,302,720
[E07  1248/1548 G  10535|CLM] train=4.6711  mask=11.5%  norm=0.914  lr=3.25e-05  dt=  36.5ms  words=86,310,912
[E07  1249/1548 G  10536|CLM] train=3.7525  mask=11.5%  norm=0.875  lr=3.25e-05  dt=  36.6ms  words=86,319,104
[E07  1250/1548 G  10537|CLM] train=2.5128  mask=11.5%  norm=0.665  lr=3.25e-05  dt=  36.8ms  words=86,327,296
[E07  1251/1548 G  10538|CLM] train=2.2242  mask=11.5%  norm=0.631  lr=3.25e-05  dt=  36.7ms  words=86,335,488
[E07  1252/1548 G  10539|CLM] train=4.2893  mask=11.5%  norm=0.887  lr=3.25e-05  dt=  36.6ms  words=86,343,680
[E07  1253/1548 G  10540|CLM] train=4.5524  mask=11.5%  norm=2.190  lr=3.25e-05  dt=  36.4ms  words=86,351,872
[E07  1254/1548 G  10541|CLM] train=2.3281  mask=11.5%  norm=0.647  lr=3.24e-05  dt=  36.7ms  words=86,360,064
[E07  1255/1548 G  10542|CLM] train=3.9805  mask=11.5%  norm=0.859  lr=3.24e-05  dt=  36.5ms  words=86,368,256
[E07  1256/1548 G  10543|CLM] train=2.2836  mask=11.5%  norm=0.708  lr=3.24e-05  dt=  36.6ms  words=86,376,448
[E07  1257/1548 G  10544|CLM] train=4.3476  mask=11.5%  norm=0.872  lr=3.24e-05  dt=  36.8ms  words=86,384,640
[E07  1258/1548 G  10545|CLM] train=2.2870  mask=11.5%  norm=0.940  lr=3.24e-05  dt=  36.7ms  words=86,392,832
[E07  1259/1548 G  10546|CLM] train=3.4019  mask=11.5%  norm=0.786  lr=3.23e-05  dt=  36.6ms  words=86,401,024
[E07  1260/1548 G  10547|CLM] train=3.7947  mask=11.5%  norm=0.851  lr=3.23e-05  dt=  36.7ms  words=86,409,216
[E07  1261/1548 G  10548|CLM] train=3.9675  mask=11.5%  norm=0.938  lr=3.23e-05  dt=  36.8ms  words=86,417,408
[E07  1262/1548 G  10549|CLM] train=2.6677  mask=11.5%  norm=0.717  lr=3.23e-05  dt=  36.7ms  words=86,425,600
[E07  1263/1548 G  10550|CLM] train=3.9164  mask=11.5%  norm=0.910  lr=3.23e-05  dt=  36.4ms  words=86,433,792
[E07  1264/1548 G  10551|CLM] train=2.2416  mask=11.5%  norm=0.697  lr=3.22e-05  dt=  36.6ms  words=86,441,984
[E07  1265/1548 G  10552|CLM] train=2.0201  mask=11.5%  norm=0.672  lr=3.22e-05  dt=  36.8ms  words=86,450,176
[E07  1266/1548 G  10553|CLM] train=3.4507  mask=11.5%  norm=0.934  lr=3.22e-05  dt=  36.7ms  words=86,458,368
[E07  1267/1548 G  10554|CLM] train=4.4184  mask=11.5%  norm=1.011  lr=3.22e-05  dt=  36.5ms  words=86,466,560
[E07  1268/1548 G  10555|CLM] train=2.4604  mask=11.5%  norm=0.713  lr=3.22e-05  dt=  36.7ms  words=86,474,752
[E07  1269/1548 G  10556|CLM] train=2.1972  mask=11.5%  norm=0.775  lr=3.22e-05  dt=  36.7ms  words=86,482,944
[E07  1270/1548 G  10557|CLM] train=1.9157  mask=11.5%  norm=0.790  lr=3.21e-05  dt=  36.5ms  words=86,491,136
[E07  1271/1548 G  10558|CLM] train=3.7685  mask=11.5%  norm=0.896  lr=3.21e-05  dt=  37.0ms  words=86,499,328
[E07  1272/1548 G  10559|CLM] train=4.6056  mask=11.5%  norm=0.961  lr=3.21e-05  dt=  36.9ms  words=86,507,520
[E07  1273/1548 G  10560|CLM] train=2.1492  mask=11.5%  norm=0.705  lr=3.21e-05  dt=  36.9ms  words=86,515,712
[E07  1274/1548 G  10561|CLM] train=4.3698  mask=11.5%  norm=1.128  lr=3.21e-05  dt=  36.8ms  words=86,523,904
[E07  1275/1548 G  10562|CLM] train=1.8885  mask=11.5%  norm=0.716  lr=3.20e-05  dt=  36.9ms  words=86,532,096
[E07  1276/1548 G  10563|CLM] train=3.4572  mask=11.5%  norm=0.813  lr=3.20e-05  dt=  37.0ms  words=86,540,288
[E07  1277/1548 G  10564|CLM] train=4.3282  mask=11.5%  norm=0.834  lr=3.20e-05  dt=  36.8ms  words=86,548,480
[E07  1278/1548 G  10565|CLM] train=3.8447  mask=11.5%  norm=0.818  lr=3.20e-05  dt=  36.8ms  words=86,556,672
[E07  1279/1548 G  10566|CLM] train=4.3942  mask=11.5%  norm=1.145  lr=3.20e-05  dt=  36.8ms  words=86,564,864
[E07  1280/1548 G  10567|CLM] train=4.0966  mask=11.5%  norm=0.867  lr=3.20e-05  dt=  37.0ms  words=86,573,056
[E07  1281/1548 G  10568|CLM] train=3.7951  mask=11.5%  norm=0.977  lr=3.19e-05  dt=  37.3ms  words=86,581,248
[E07  1282/1548 G  10569|CLM] train=3.5976  mask=11.5%  norm=0.924  lr=3.19e-05  dt=  37.1ms  words=86,589,440
[E07  1283/1548 G  10570|CLM] train=2.1506  mask=11.5%  norm=0.693  lr=3.19e-05  dt=  37.0ms  words=86,597,632
[E07  1284/1548 G  10571|CLM] train=4.7534  mask=11.5%  norm=0.935  lr=3.19e-05  dt=  37.8ms  words=86,605,824
[E07  1285/1548 G  10572|CLM] train=1.9799  mask=11.5%  norm=0.796  lr=3.19e-05  dt=  37.5ms  words=86,614,016
[E07  1286/1548 G  10573|CLM] train=4.1554  mask=11.5%  norm=0.937  lr=3.18e-05  dt=  37.2ms  words=86,622,208
[E07  1287/1548 G  10574|CLM] train=2.4655  mask=11.5%  norm=0.773  lr=3.18e-05  dt=  36.9ms  words=86,630,400
[E07  1288/1548 G  10575|CLM] train=4.4171  mask=11.5%  norm=0.968  lr=3.18e-05  dt=  37.1ms  words=86,638,592
[E07  1289/1548 G  10576|CLM] train=4.1753  mask=11.5%  norm=1.070  lr=3.18e-05  dt=  37.0ms  words=86,646,784
[E07  1290/1548 G  10577|CLM] train=3.7737  mask=11.5%  norm=0.821  lr=3.18e-05  dt=  36.9ms  words=86,654,976
[E07  1291/1548 G  10578|CLM] train=4.2076  mask=11.5%  norm=0.864  lr=3.18e-05  dt=  37.0ms  words=86,663,168
[E07  1292/1548 G  10579|CLM] train=2.0104  mask=11.5%  norm=0.759  lr=3.17e-05  dt=  36.9ms  words=86,671,360
[E07  1293/1548 G  10580|CLM] train=4.5242  mask=11.5%  norm=1.028  lr=3.17e-05  dt=  37.0ms  words=86,679,552
[E07  1294/1548 G  10581|CLM] train=4.0616  mask=11.5%  norm=0.876  lr=3.17e-05  dt=  37.0ms  words=86,687,744
[E07  1295/1548 G  10582|CLM] train=4.2483  mask=11.5%  norm=0.880  lr=3.17e-05  dt=  36.9ms  words=86,695,936
[E07  1296/1548 G  10583|CLM] train=3.6836  mask=11.5%  norm=0.881  lr=3.17e-05  dt=  36.8ms  words=86,704,128
[E07  1297/1548 G  10584|CLM] train=3.4084  mask=11.5%  norm=1.227  lr=3.16e-05  dt=  37.4ms  words=86,712,320
[E07  1298/1548 G  10585|CLM] train=4.1121  mask=11.5%  norm=0.891  lr=3.16e-05  dt=  36.9ms  words=86,720,512
[E07  1299/1548 G  10586|CLM] train=2.0991  mask=11.5%  norm=0.839  lr=3.16e-05  dt=  37.3ms  words=86,728,704
[E07  1300/1548 G  10587|CLM] train=2.5913  mask=11.5%  norm=0.883  lr=3.16e-05  dt=  37.1ms  words=86,736,896
[E07  1301/1548 G  10588|CLM] train=2.5144  mask=11.5%  norm=0.725  lr=3.16e-05  dt=  37.3ms  words=86,745,088
[E07  1302/1548 G  10589|CLM] train=4.0569  mask=11.4%  norm=0.896  lr=3.16e-05  dt=  36.8ms  words=86,753,280
[E07  1303/1548 G  10590|CLM] train=4.2577  mask=11.4%  norm=0.897  lr=3.15e-05  dt=  36.9ms  words=86,761,472
[E07  1304/1548 G  10591|CLM] train=4.2317  mask=11.4%  norm=0.868  lr=3.15e-05  dt=  37.1ms  words=86,769,664
[E07  1305/1548 G  10592|CLM] train=4.0302  mask=11.4%  norm=0.834  lr=3.15e-05  dt=  37.0ms  words=86,777,856
[E07  1306/1548 G  10593|CLM] train=4.1453  mask=11.4%  norm=0.858  lr=3.15e-05  dt=  37.1ms  words=86,786,048
[E07  1307/1548 G  10594|CLM] train=3.4305  mask=11.4%  norm=0.763  lr=3.15e-05  dt=  37.0ms  words=86,794,240
[E07  1308/1548 G  10595|CLM] train=4.0160  mask=11.4%  norm=1.024  lr=3.14e-05  dt=  37.1ms  words=86,802,432
[E07  1309/1548 G  10596|CLM] train=4.3266  mask=11.4%  norm=0.996  lr=3.14e-05  dt=  36.9ms  words=86,810,624
[E07  1310/1548 G  10597|CLM] train=4.2807  mask=11.4%  norm=0.901  lr=3.14e-05  dt=  37.0ms  words=86,818,816
[E07  1311/1548 G  10598|CLM] train=4.2079  mask=11.4%  norm=0.876  lr=3.14e-05  dt=  37.2ms  words=86,827,008
[E07  1312/1548 G  10599|CLM] train=3.4213  mask=11.4%  norm=0.828  lr=3.14e-05  dt=  37.4ms  words=86,835,200
[E07  1313/1548 G  10600|CLM] train=1.9316  mask=11.4%  norm=0.788  lr=3.14e-05  dt=  36.9ms  words=86,843,392
[E07  1314/1548 G  10601|CLM] train=2.2530  mask=11.4%  norm=0.791  lr=3.13e-05  dt=  37.2ms  words=86,851,584
[E07  1315/1548 G  10602|CLM] train=3.0496  mask=11.4%  norm=1.801  lr=3.13e-05  dt=  36.8ms  words=86,859,776
[E07  1316/1548 G  10603|CLM] train=2.3162  mask=11.4%  norm=0.909  lr=3.13e-05  dt=  36.9ms  words=86,867,968
[E07  1317/1548 G  10604|CLM] train=2.1194  mask=11.4%  norm=0.711  lr=3.13e-05  dt=  37.1ms  words=86,876,160
[E07  1318/1548 G  10605|CLM] train=3.7918  mask=11.4%  norm=0.871  lr=3.13e-05  dt=  37.1ms  words=86,884,352
[E07  1319/1548 G  10606|CLM] train=2.2965  mask=11.4%  norm=0.676  lr=3.12e-05  dt=  36.9ms  words=86,892,544
[E07  1320/1548 G  10607|CLM] train=3.7381  mask=11.4%  norm=0.993  lr=3.12e-05  dt=  37.0ms  words=86,900,736
[E07  1321/1548 G  10608|CLM] train=3.9911  mask=11.4%  norm=0.869  lr=3.12e-05  dt=  36.8ms  words=86,908,928
[E07  1322/1548 G  10609|CLM] train=2.4314  mask=11.4%  norm=0.880  lr=3.12e-05  dt=  37.2ms  words=86,917,120
[E07  1323/1548 G  10610|CLM] train=2.4756  mask=11.4%  norm=0.830  lr=3.12e-05  dt=  37.1ms  words=86,925,312
[E07  1324/1548 G  10611|CLM] train=3.6286  mask=11.4%  norm=0.790  lr=3.12e-05  dt=  37.4ms  words=86,933,504
[E07  1325/1548 G  10612|CLM] train=3.8749  mask=11.4%  norm=1.124  lr=3.11e-05  dt=  37.2ms  words=86,941,696
[E07  1326/1548 G  10613|CLM] train=4.2622  mask=11.4%  norm=0.954  lr=3.11e-05  dt=  37.2ms  words=86,949,888
[E07  1327/1548 G  10614|CLM] train=2.0301  mask=11.4%  norm=0.715  lr=3.11e-05  dt=  37.3ms  words=86,958,080
[E07  1328/1548 G  10615|CLM] train=4.0615  mask=11.4%  norm=0.837  lr=3.11e-05  dt=  37.0ms  words=86,966,272
[E07  1329/1548 G  10616|CLM] train=2.2794  mask=11.4%  norm=0.682  lr=3.11e-05  dt=  37.0ms  words=86,974,464
[E07  1330/1548 G  10617|CLM] train=2.4015  mask=11.4%  norm=0.699  lr=3.11e-05  dt=  36.9ms  words=86,982,656
[E07  1331/1548 G  10618|CLM] train=4.0548  mask=11.4%  norm=1.050  lr=3.10e-05  dt=  36.8ms  words=86,990,848
[E07  1332/1548 G  10619|CLM] train=3.7126  mask=11.4%  norm=0.778  lr=3.10e-05  dt=  37.0ms  words=86,999,040
[E07  1333/1548 G  10620|CLM] train=4.0121  mask=11.4%  norm=0.874  lr=3.10e-05  dt=  36.9ms  words=87,007,232
[E07  1334/1548 G  10621|CLM] train=2.0136  mask=11.4%  norm=0.686  lr=3.10e-05  dt=  36.9ms  words=87,015,424
[E07  1335/1548 G  10622|CLM] train=4.1204  mask=11.4%  norm=1.070  lr=3.10e-05  dt=  37.0ms  words=87,023,616
[E07  1336/1548 G  10623|CLM] train=3.8801  mask=11.4%  norm=0.955  lr=3.09e-05  dt=  37.0ms  words=87,031,808
[E07  1337/1548 G  10624|CLM] train=3.6143  mask=11.4%  norm=0.857  lr=3.09e-05  dt=  36.9ms  words=87,040,000
[E07  1338/1548 G  10625|CLM] train=4.1719  mask=11.4%  norm=0.878  lr=3.09e-05  dt=  37.2ms  words=87,048,192
[E07  1339/1548 G  10626|CLM] train=4.0194  mask=11.4%  norm=0.790  lr=3.09e-05  dt=  37.5ms  words=87,056,384
[E07  1340/1548 G  10627|CLM] train=3.3928  mask=11.4%  norm=0.820  lr=3.09e-05  dt=  37.1ms  words=87,064,576
[E07  1341/1548 G  10628|CLM] train=4.1672  mask=11.4%  norm=0.901  lr=3.09e-05  dt=  36.7ms  words=87,072,768
[E07  1342/1548 G  10629|CLM] train=3.9534  mask=11.4%  norm=1.024  lr=3.08e-05  dt=  37.0ms  words=87,080,960
[E07  1343/1548 G  10630|CLM] train=4.8042  mask=11.4%  norm=1.229  lr=3.08e-05  dt=  37.0ms  words=87,089,152
[E07  1344/1548 G  10631|CLM] train=4.6952  mask=11.4%  norm=1.119  lr=3.08e-05  dt=  36.8ms  words=87,097,344
[E07  1345/1548 G  10632|CLM] train=1.6627  mask=11.4%  norm=0.686  lr=3.08e-05  dt=  36.9ms  words=87,105,536
[E07  1346/1548 G  10633|CLM] train=4.0844  mask=11.4%  norm=0.900  lr=3.08e-05  dt=  37.1ms  words=87,113,728
[E07  1347/1548 G  10634|CLM] train=3.5301  mask=11.4%  norm=0.883  lr=3.07e-05  dt=  37.0ms  words=87,121,920
[E07  1348/1548 G  10635|CLM] train=2.0545  mask=11.4%  norm=0.915  lr=3.07e-05  dt=  36.9ms  words=87,130,112
[E07  1349/1548 G  10636|CLM] train=2.3712  mask=11.4%  norm=0.723  lr=3.07e-05  dt=  36.8ms  words=87,138,304
[E07  1350/1548 G  10637|CLM] train=4.1394  mask=11.4%  norm=0.924  lr=3.07e-05  dt=  37.1ms  words=87,146,496
[E07  1351/1548 G  10638|CLM] train=4.1730  mask=11.4%  norm=0.845  lr=3.07e-05  dt=  37.5ms  words=87,154,688
[E07  1352/1548 G  10639|CLM] train=2.1776  mask=11.4%  norm=0.709  lr=3.07e-05  dt=  36.8ms  words=87,162,880
[E07  1353/1548 G  10640|CLM] train=2.5081  mask=11.4%  norm=0.883  lr=3.06e-05  dt=  37.1ms  words=87,171,072
[E07  1354/1548 G  10641|CLM] train=4.4908  mask=11.4%  norm=1.053  lr=3.06e-05  dt=  37.1ms  words=87,179,264
[E07  1355/1548 G  10642|CLM] train=2.0179  mask=11.4%  norm=0.628  lr=3.06e-05  dt=  36.9ms  words=87,187,456
[E07  1356/1548 G  10643|CLM] train=3.5455  mask=11.4%  norm=0.907  lr=3.06e-05  dt=  37.2ms  words=87,195,648
[E07  1357/1548 G  10644|CLM] train=2.4143  mask=11.4%  norm=0.735  lr=3.06e-05  dt=  36.9ms  words=87,203,840
[E07  1358/1548 G  10645|CLM] train=4.9570  mask=11.4%  norm=1.176  lr=3.06e-05  dt=  37.0ms  words=87,212,032
[E07  1359/1548 G  10646|CLM] train=4.0438  mask=11.4%  norm=0.847  lr=3.05e-05  dt=  37.5ms  words=87,220,224
[E07  1360/1548 G  10647|CLM] train=2.1109  mask=11.4%  norm=0.691  lr=3.05e-05  dt=  36.8ms  words=87,228,416
[E07  1361/1548 G  10648|CLM] train=4.0377  mask=11.4%  norm=1.094  lr=3.05e-05  dt=  37.2ms  words=87,236,608
[E07  1362/1548 G  10649|CLM] train=4.4510  mask=11.4%  norm=0.962  lr=3.05e-05  dt=  37.0ms  words=87,244,800
[E07  1363/1548 G  10650|CLM] train=4.3631  mask=11.4%  norm=1.231  lr=3.05e-05  dt=  36.8ms  words=87,252,992
[E07  1364/1548 G  10651|CLM] train=3.6660  mask=11.4%  norm=0.860  lr=3.05e-05  dt=  36.8ms  words=87,261,184
[E07  1365/1548 G  10652|CLM] train=3.7632  mask=11.4%  norm=0.846  lr=3.04e-05  dt=  36.9ms  words=87,269,376
[E07  1366/1548 G  10653|CLM] train=1.8147  mask=11.4%  norm=0.811  lr=3.04e-05  dt=  36.9ms  words=87,277,568
[E07  1367/1548 G  10654|CLM] train=3.7015  mask=11.4%  norm=0.818  lr=3.04e-05  dt=  37.1ms  words=87,285,760
[E07  1368/1548 G  10655|CLM] train=4.4986  mask=11.4%  norm=0.902  lr=3.04e-05  dt=  36.9ms  words=87,293,952
[E07  1369/1548 G  10656|CLM] train=2.5083  mask=11.4%  norm=0.722  lr=3.04e-05  dt=  36.9ms  words=87,302,144
[E07  1370/1548 G  10657|CLM] train=4.6142  mask=11.4%  norm=0.935  lr=3.03e-05  dt=  36.9ms  words=87,310,336
[E07  1371/1548 G  10658|CLM] train=3.7708  mask=11.4%  norm=0.831  lr=3.03e-05  dt=  36.9ms  words=87,318,528
[E07  1372/1548 G  10659|CLM] train=4.1089  mask=11.4%  norm=0.861  lr=3.03e-05  dt=  36.7ms  words=87,326,720
[E07  1373/1548 G  10660|CLM] train=2.0606  mask=11.4%  norm=0.671  lr=3.03e-05  dt=  37.0ms  words=87,334,912
[E07  1374/1548 G  10661|CLM] train=1.6387  mask=11.4%  norm=0.660  lr=3.03e-05  dt=  36.9ms  words=87,343,104
[E07  1375/1548 G  10662|CLM] train=1.9926  mask=11.4%  norm=0.749  lr=3.03e-05  dt=  36.8ms  words=87,351,296
[E07  1376/1548 G  10663|CLM] train=4.3705  mask=11.4%  norm=1.101  lr=3.02e-05  dt=  36.9ms  words=87,359,488
[E07  1377/1548 G  10664|CLM] train=3.9744  mask=11.4%  norm=0.923  lr=3.02e-05  dt=  37.1ms  words=87,367,680
[E07  1378/1548 G  10665|CLM] train=2.1330  mask=11.4%  norm=0.712  lr=3.02e-05  dt=  37.4ms  words=87,375,872
[E07  1379/1548 G  10666|CLM] train=4.0493  mask=11.4%  norm=0.922  lr=3.02e-05  dt=  37.0ms  words=87,384,064
[E07  1380/1548 G  10667|CLM] train=2.4011  mask=11.4%  norm=0.694  lr=3.02e-05  dt=  37.3ms  words=87,392,256
[E07  1381/1548 G  10668|CLM] train=2.5532  mask=11.4%  norm=0.654  lr=3.02e-05  dt=  37.3ms  words=87,400,448
[E07  1382/1548 G  10669|CLM] train=3.9467  mask=11.4%  norm=0.904  lr=3.01e-05  dt=  37.2ms  words=87,408,640
[E07  1383/1548 G  10670|CLM] train=3.5894  mask=11.4%  norm=0.919  lr=3.01e-05  dt=  37.1ms  words=87,416,832
[E07  1384/1548 G  10671|CLM] train=4.8148  mask=11.4%  norm=1.395  lr=3.01e-05  dt=  37.0ms  words=87,425,024
[E07  1385/1548 G  10672|CLM] train=4.1903  mask=11.4%  norm=0.820  lr=3.01e-05  dt=  37.6ms  words=87,433,216
[E07  1386/1548 G  10673|CLM] train=4.1936  mask=11.4%  norm=0.886  lr=3.01e-05  dt=  37.3ms  words=87,441,408
[E07  1387/1548 G  10674|CLM] train=2.2198  mask=11.4%  norm=0.700  lr=3.01e-05  dt=  37.0ms  words=87,449,600
[E07  1388/1548 G  10675|CLM] train=3.8815  mask=11.4%  norm=0.918  lr=3.00e-05  dt=  37.2ms  words=87,457,792
[E07  1389/1548 G  10676|CLM] train=2.0903  mask=11.4%  norm=0.659  lr=3.00e-05  dt=  37.2ms  words=87,465,984
[E07  1390/1548 G  10677|CLM] train=2.4777  mask=11.4%  norm=0.707  lr=3.00e-05  dt=  37.0ms  words=87,474,176
[E07  1391/1548 G  10678|CLM] train=4.0414  mask=11.4%  norm=0.875  lr=3.00e-05  dt=  37.0ms  words=87,482,368
[E07  1392/1548 G  10679|CLM] train=3.9064  mask=11.4%  norm=0.901  lr=3.00e-05  dt=  37.0ms  words=87,490,560
[E07  1393/1548 G  10680|CLM] train=1.8250  mask=11.4%  norm=0.719  lr=2.99e-05  dt=  37.5ms  words=87,498,752
[E07  1394/1548 G  10681|CLM] train=2.0076  mask=11.4%  norm=0.632  lr=2.99e-05  dt=  37.0ms  words=87,506,944
[E07  1395/1548 G  10682|CLM] train=4.4369  mask=11.4%  norm=0.967  lr=2.99e-05  dt=  37.0ms  words=87,515,136
[E07  1396/1548 G  10683|CLM] train=2.1957  mask=11.4%  norm=0.712  lr=2.99e-05  dt=  37.1ms  words=87,523,328
[E07  1397/1548 G  10684|CLM] train=3.6869  mask=11.4%  norm=0.961  lr=2.99e-05  dt=  36.9ms  words=87,531,520
[E07  1398/1548 G  10685|CLM] train=2.4706  mask=11.4%  norm=0.784  lr=2.99e-05  dt=  36.9ms  words=87,539,712
[E07  1399/1548 G  10686|CLM] train=2.1197  mask=11.4%  norm=0.742  lr=2.98e-05  dt=  37.0ms  words=87,547,904
[E07  1400/1548 G  10687|CLM] train=2.3503  mask=11.4%  norm=0.735  lr=2.98e-05  dt=  37.0ms  words=87,556,096
[E07  1401/1548 G  10688|CLM] train=3.6665  mask=11.4%  norm=0.780  lr=2.98e-05  dt=  37.0ms  words=87,564,288
[E07  1402/1548 G  10689|CLM] train=3.8621  mask=11.4%  norm=0.936  lr=2.98e-05  dt=  36.8ms  words=87,572,480
[E07  1403/1548 G  10690|CLM] train=1.4300  mask=11.4%  norm=0.606  lr=2.98e-05  dt=  36.9ms  words=87,580,672
[E07  1404/1548 G  10691|CLM] train=1.9250  mask=11.4%  norm=0.710  lr=2.98e-05  dt=  37.0ms  words=87,588,864
[E07  1405/1548 G  10692|CLM] train=4.0618  mask=11.4%  norm=0.892  lr=2.97e-05  dt=  37.6ms  words=87,597,056
[E07  1406/1548 G  10693|CLM] train=2.3016  mask=11.4%  norm=0.678  lr=2.97e-05  dt=  37.0ms  words=87,605,248
[E07  1407/1548 G  10694|CLM] train=3.8327  mask=11.4%  norm=0.867  lr=2.97e-05  dt=  37.1ms  words=87,613,440
[E07  1408/1548 G  10695|CLM] train=4.2730  mask=11.4%  norm=0.948  lr=2.97e-05  dt=  37.0ms  words=87,621,632
[E07  1409/1548 G  10696|CLM] train=3.5098  mask=11.4%  norm=0.908  lr=2.97e-05  dt=  36.9ms  words=87,629,824
[E07  1410/1548 G  10697|CLM] train=3.8938  mask=11.4%  norm=1.042  lr=2.97e-05  dt=  36.9ms  words=87,638,016
[E07  1411/1548 G  10698|CLM] train=3.9808  mask=11.4%  norm=0.844  lr=2.96e-05  dt=  37.1ms  words=87,646,208
[E07  1412/1548 G  10699|CLM] train=3.8878  mask=11.4%  norm=0.827  lr=2.96e-05  dt=  36.9ms  words=87,654,400
[E07  1413/1548 G  10700|CLM] train=3.8781  mask=11.4%  norm=0.788  lr=2.96e-05  dt=  36.8ms  words=87,662,592
[E07  1414/1548 G  10701|CLM] train=3.7102  mask=11.4%  norm=0.920  lr=2.96e-05  dt=  36.9ms  words=87,670,784
[E07  1415/1548 G  10702|CLM] train=4.4728  mask=11.4%  norm=0.999  lr=2.96e-05  dt=  36.9ms  words=87,678,976
[E07  1416/1548 G  10703|CLM] train=3.2916  mask=11.4%  norm=0.830  lr=2.96e-05  dt=  36.9ms  words=87,687,168
[E07  1417/1548 G  10704|CLM] train=4.0742  mask=11.4%  norm=0.938  lr=2.95e-05  dt=  36.7ms  words=87,695,360
[E07  1418/1548 G  10705|CLM] train=3.8954  mask=11.4%  norm=0.968  lr=2.95e-05  dt=  37.4ms  words=87,703,552
[E07  1419/1548 G  10706|CLM] train=4.0912  mask=11.4%  norm=0.928  lr=2.95e-05  dt=  36.9ms  words=87,711,744
[E07  1420/1548 G  10707|CLM] train=4.5758  mask=11.4%  norm=1.235  lr=2.95e-05  dt=  37.2ms  words=87,719,936
[E07  1421/1548 G  10708|CLM] train=1.9597  mask=11.4%  norm=0.731  lr=2.95e-05  dt=  36.9ms  words=87,728,128
[E07  1422/1548 G  10709|CLM] train=3.2382  mask=11.4%  norm=0.904  lr=2.95e-05  dt=  37.1ms  words=87,736,320
[E07  1423/1548 G  10710|CLM] train=4.6011  mask=11.4%  norm=0.933  lr=2.94e-05  dt=  36.9ms  words=87,744,512
[E07  1424/1548 G  10711|CLM] train=4.6885  mask=11.4%  norm=0.897  lr=2.94e-05  dt=  37.0ms  words=87,752,704
[E07  1425/1548 G  10712|CLM] train=2.2654  mask=11.4%  norm=0.777  lr=2.94e-05  dt=  37.1ms  words=87,760,896
[E07  1426/1548 G  10713|CLM] train=2.3794  mask=11.3%  norm=0.801  lr=2.94e-05  dt=  37.1ms  words=87,769,088
[E07  1427/1548 G  10714|CLM] train=3.9474  mask=11.3%  norm=0.829  lr=2.94e-05  dt=  36.8ms  words=87,777,280
[E07  1428/1548 G  10715|CLM] train=3.5986  mask=11.3%  norm=0.863  lr=2.94e-05  dt=  36.9ms  words=87,785,472
[E07  1429/1548 G  10716|CLM] train=2.9896  mask=11.3%  norm=0.750  lr=2.93e-05  dt=  36.9ms  words=87,793,664
[E07  1430/1548 G  10717|CLM] train=3.7911  mask=11.3%  norm=0.835  lr=2.93e-05  dt=  37.0ms  words=87,801,856
[E07  1431/1548 G  10718|CLM] train=3.9786  mask=11.3%  norm=0.991  lr=2.93e-05  dt=  36.8ms  words=87,810,048
[E07  1432/1548 G  10719|CLM] train=2.3527  mask=11.3%  norm=0.724  lr=2.93e-05  dt=  37.3ms  words=87,818,240
[E07  1433/1548 G  10720|CLM] train=2.0457  mask=11.3%  norm=0.895  lr=2.93e-05  dt=  37.4ms  words=87,826,432
[E07  1434/1548 G  10721|CLM] train=4.1977  mask=11.3%  norm=0.930  lr=2.92e-05  dt=  38.1ms  words=87,834,624
[E07  1435/1548 G  10722|CLM] train=4.1599  mask=11.3%  norm=0.815  lr=2.92e-05  dt=  39.3ms  words=87,842,816
[E07  1436/1548 G  10723|CLM] train=3.8027  mask=11.3%  norm=0.875  lr=2.92e-05  dt=  39.4ms  words=87,851,008
[E07  1437/1548 G  10724|CLM] train=4.2895  mask=11.3%  norm=0.947  lr=2.92e-05  dt=  41.3ms  words=87,859,200
[E07  1438/1548 G  10725|CLM] train=4.0569  mask=11.3%  norm=0.857  lr=2.92e-05  dt=  37.7ms  words=87,867,392
[E07  1439/1548 G  10726|CLM] train=4.1518  mask=11.3%  norm=0.923  lr=2.92e-05  dt=  38.2ms  words=87,875,584
[E07  1440/1548 G  10727|CLM] train=5.4872  mask=11.3%  norm=1.438  lr=2.91e-05  dt=  37.2ms  words=87,883,776
[E07  1441/1548 G  10728|CLM] train=2.6284  mask=11.3%  norm=0.768  lr=2.91e-05  dt=  37.7ms  words=87,891,968
[E07  1442/1548 G  10729|CLM] train=2.2211  mask=11.3%  norm=0.835  lr=2.91e-05  dt=  37.3ms  words=87,900,160
[E07  1443/1548 G  10730|CLM] train=2.3460  mask=11.3%  norm=0.904  lr=2.91e-05  dt=  41.5ms  words=87,908,352
[E07  1444/1548 G  10731|CLM] train=1.9902  mask=11.3%  norm=0.877  lr=2.91e-05  dt=  36.8ms  words=87,916,544
[E07  1445/1548 G  10732|CLM] train=4.2841  mask=11.3%  norm=0.928  lr=2.91e-05  dt=  37.0ms  words=87,924,736
[E07  1446/1548 G  10733|CLM] train=3.3544  mask=11.3%  norm=0.926  lr=2.90e-05  dt=  37.4ms  words=87,932,928
[E07  1447/1548 G  10734|CLM] train=4.3429  mask=11.3%  norm=0.881  lr=2.90e-05  dt=  43.8ms  words=87,941,120
[E07  1448/1548 G  10735|CLM] train=2.1843  mask=11.3%  norm=0.724  lr=2.90e-05  dt=  37.4ms  words=87,949,312
[E07  1449/1548 G  10736|CLM] train=2.4753  mask=11.3%  norm=0.735  lr=2.90e-05  dt=  36.6ms  words=87,957,504
[E07  1450/1548 G  10737|CLM] train=4.1835  mask=11.3%  norm=0.908  lr=2.90e-05  dt=  36.9ms  words=87,965,696
[E07  1451/1548 G  10738|CLM] train=2.4807  mask=11.3%  norm=0.753  lr=2.90e-05  dt=  36.8ms  words=87,973,888
[E07  1452/1548 G  10739|CLM] train=4.8938  mask=11.3%  norm=1.121  lr=2.89e-05  dt=  36.8ms  words=87,982,080
[E07  1453/1548 G  10740|CLM] train=4.7795  mask=11.3%  norm=1.104  lr=2.89e-05  dt=  36.7ms  words=87,990,272
[E07  1454/1548 G  10741|CLM] train=4.2940  mask=11.3%  norm=1.075  lr=2.89e-05  dt=  36.7ms  words=87,998,464
[E07  1455/1548 G  10742|CLM] train=3.9581  mask=11.3%  norm=1.039  lr=2.89e-05  dt=  36.8ms  words=88,006,656
[E07  1456/1548 G  10743|CLM] train=3.5987  mask=11.3%  norm=0.880  lr=2.89e-05  dt=  36.8ms  words=88,014,848
[E07  1457/1548 G  10744|CLM] train=3.4205  mask=11.3%  norm=0.803  lr=2.89e-05  dt=  36.9ms  words=88,023,040
[E07  1458/1548 G  10745|CLM] train=4.1530  mask=11.3%  norm=0.928  lr=2.88e-05  dt=  36.8ms  words=88,031,232
[E07  1459/1548 G  10746|CLM] train=3.6666  mask=11.3%  norm=0.930  lr=2.88e-05  dt=  36.8ms  words=88,039,424
[E07  1460/1548 G  10747|CLM] train=2.3769  mask=11.3%  norm=0.945  lr=2.88e-05  dt=  36.8ms  words=88,047,616
[E07  1461/1548 G  10748|CLM] train=2.1128  mask=11.3%  norm=0.724  lr=2.88e-05  dt=  36.9ms  words=88,055,808
[E07  1462/1548 G  10749|CLM] train=4.2601  mask=11.3%  norm=0.861  lr=2.88e-05  dt=  36.7ms  words=88,064,000
[E07  1463/1548 G  10750|CLM] train=4.2106  mask=11.3%  norm=1.014  lr=2.88e-05  dt=  36.7ms  words=88,072,192
[E07  1464/1548 G  10751|CLM] train=3.7812  mask=11.3%  norm=0.820  lr=2.87e-05  dt=  36.9ms  words=88,080,384
[E07  1465/1548 G  10752|CLM] train=3.9404  mask=11.3%  norm=0.854  lr=2.87e-05  dt=  36.8ms  words=88,088,576
[E07  1466/1548 G  10753|CLM] train=4.3543  mask=11.3%  norm=0.837  lr=2.87e-05  dt=  36.8ms  words=88,096,768
[E07  1467/1548 G  10754|CLM] train=3.6028  mask=11.3%  norm=0.864  lr=2.87e-05  dt=  36.8ms  words=88,104,960
[E07  1468/1548 G  10755|CLM] train=2.3354  mask=11.3%  norm=0.654  lr=2.87e-05  dt=  36.9ms  words=88,113,152
[E07  1469/1548 G  10756|CLM] train=4.9708  mask=11.3%  norm=2.907  lr=2.87e-05  dt=  36.9ms  words=88,121,344
[E07  1470/1548 G  10757|CLM] train=4.6344  mask=11.3%  norm=0.906  lr=2.86e-05  dt=  36.9ms  words=88,129,536
[E07  1471/1548 G  10758|CLM] train=3.3705  mask=11.3%  norm=0.773  lr=2.86e-05  dt=  36.9ms  words=88,137,728
[E07  1472/1548 G  10759|CLM] train=2.1937  mask=11.3%  norm=0.738  lr=2.86e-05  dt=  36.8ms  words=88,145,920
[E07  1473/1548 G  10760|CLM] train=4.3778  mask=11.3%  norm=0.967  lr=2.86e-05  dt=  37.0ms  words=88,154,112
[E07  1474/1548 G  10761|CLM] train=4.2362  mask=11.3%  norm=0.898  lr=2.86e-05  dt=  37.2ms  words=88,162,304
[E07  1475/1548 G  10762|CLM] train=3.6834  mask=11.3%  norm=0.800  lr=2.86e-05  dt=  37.0ms  words=88,170,496
[E07  1476/1548 G  10763|CLM] train=4.4822  mask=11.3%  norm=1.003  lr=2.85e-05  dt=  37.2ms  words=88,178,688
[E07  1477/1548 G  10764|CLM] train=2.3486  mask=11.3%  norm=0.710  lr=2.85e-05  dt=  37.3ms  words=88,186,880
[E07  1478/1548 G  10765|CLM] train=2.0968  mask=11.3%  norm=0.734  lr=2.85e-05  dt=  37.0ms  words=88,195,072
[E07  1479/1548 G  10766|CLM] train=4.2300  mask=11.3%  norm=0.851  lr=2.85e-05  dt=  37.0ms  words=88,203,264
[E07  1480/1548 G  10767|CLM] train=1.9640  mask=11.3%  norm=0.714  lr=2.85e-05  dt=  37.1ms  words=88,211,456
[E07  1481/1548 G  10768|CLM] train=3.6952  mask=11.3%  norm=0.870  lr=2.85e-05  dt=  37.0ms  words=88,219,648
[E07  1482/1548 G  10769|CLM] train=2.4664  mask=11.3%  norm=0.699  lr=2.85e-05  dt=  37.0ms  words=88,227,840
[E07  1483/1548 G  10770|CLM] train=4.3589  mask=11.3%  norm=0.996  lr=2.84e-05  dt=  37.1ms  words=88,236,032
[E07  1484/1548 G  10771|CLM] train=4.0126  mask=11.3%  norm=1.150  lr=2.84e-05  dt=  37.2ms  words=88,244,224
[E07  1485/1548 G  10772|CLM] train=2.2853  mask=11.3%  norm=0.671  lr=2.84e-05  dt=  37.2ms  words=88,252,416
[E07  1486/1548 G  10773|CLM] train=2.1087  mask=11.3%  norm=0.837  lr=2.84e-05  dt=  37.0ms  words=88,260,608
[E07  1487/1548 G  10774|CLM] train=3.9723  mask=11.3%  norm=0.908  lr=2.84e-05  dt=  37.0ms  words=88,268,800
[E07  1488/1548 G  10775|CLM] train=3.8517  mask=11.3%  norm=0.819  lr=2.84e-05  dt=  36.7ms  words=88,276,992
[E07  1489/1548 G  10776|CLM] train=3.9586  mask=11.3%  norm=0.841  lr=2.83e-05  dt=  36.8ms  words=88,285,184
[E07  1490/1548 G  10777|CLM] train=3.4127  mask=11.3%  norm=0.777  lr=2.83e-05  dt=  36.9ms  words=88,293,376
[E07  1491/1548 G  10778|CLM] train=2.6354  mask=11.3%  norm=0.808  lr=2.83e-05  dt=  37.0ms  words=88,301,568
[E07  1492/1548 G  10779|CLM] train=2.1709  mask=11.3%  norm=0.837  lr=2.83e-05  dt=  36.9ms  words=88,309,760
[E07  1493/1548 G  10780|CLM] train=3.9802  mask=11.3%  norm=0.906  lr=2.83e-05  dt=  36.9ms  words=88,317,952
[E07  1494/1548 G  10781|CLM] train=2.0139  mask=11.3%  norm=0.816  lr=2.83e-05  dt=  36.9ms  words=88,326,144
[E07  1495/1548 G  10782|CLM] train=4.4812  mask=11.3%  norm=1.095  lr=2.82e-05  dt=  37.0ms  words=88,334,336
[E07  1496/1548 G  10783|CLM] train=4.0723  mask=11.3%  norm=0.871  lr=2.82e-05  dt=  36.9ms  words=88,342,528
[E07  1497/1548 G  10784|CLM] train=3.4088  mask=11.3%  norm=0.825  lr=2.82e-05  dt=  36.9ms  words=88,350,720
[E07  1498/1548 G  10785|CLM] train=2.0690  mask=11.3%  norm=0.691  lr=2.82e-05  dt=  36.9ms  words=88,358,912
[E07  1499/1548 G  10786|CLM] train=3.4541  mask=11.3%  norm=0.801  lr=2.82e-05  dt=  37.0ms  words=88,367,104
[E07  1500/1548 G  10787|CLM] train=4.6797  mask=11.3%  norm=1.047  lr=2.82e-05  dt=  37.0ms  words=88,375,296
[E07  1501/1548 G  10788|CLM] train=3.8541  mask=11.3%  norm=0.868  lr=2.81e-05  dt=  36.9ms  words=88,383,488
[E07  1502/1548 G  10789|CLM] train=3.7123  mask=11.3%  norm=0.904  lr=2.81e-05  dt=  36.8ms  words=88,391,680
[E07  1503/1548 G  10790|CLM] train=3.8441  mask=11.3%  norm=0.876  lr=2.81e-05  dt=  37.0ms  words=88,399,872
[E07  1504/1548 G  10791|CLM] train=3.3969  mask=11.3%  norm=0.791  lr=2.81e-05  dt=  36.8ms  words=88,408,064
[E07  1505/1548 G  10792|CLM] train=2.2202  mask=11.3%  norm=0.745  lr=2.81e-05  dt=  36.9ms  words=88,416,256
[E07  1506/1548 G  10793|CLM] train=2.2669  mask=11.3%  norm=0.704  lr=2.81e-05  dt=  37.0ms  words=88,424,448
[E07  1507/1548 G  10794|CLM] train=2.4660  mask=11.3%  norm=0.727  lr=2.80e-05  dt=  37.0ms  words=88,432,640
[E07  1508/1548 G  10795|CLM] train=2.7400  mask=11.3%  norm=0.786  lr=2.80e-05  dt=  36.8ms  words=88,440,832
[E07  1509/1548 G  10796|CLM] train=4.0086  mask=11.3%  norm=0.880  lr=2.80e-05  dt=  37.0ms  words=88,449,024
[E07  1510/1548 G  10797|CLM] train=4.0394  mask=11.3%  norm=0.950  lr=2.80e-05  dt=  36.9ms  words=88,457,216
[E07  1511/1548 G  10798|CLM] train=4.7376  mask=11.3%  norm=1.638  lr=2.80e-05  dt=  37.1ms  words=88,465,408
[E07  1512/1548 G  10799|CLM] train=2.4265  mask=11.3%  norm=0.718  lr=2.80e-05  dt=  36.8ms  words=88,473,600
[E07  1513/1548 G  10800|CLM] train=2.3355  mask=11.3%  norm=0.753  lr=2.79e-05  dt=  37.0ms  words=88,481,792
[E07  1514/1548 G  10801|CLM] train=4.2108  mask=11.3%  norm=0.960  lr=2.79e-05  dt=  37.0ms  words=88,489,984
[E07  1515/1548 G  10802|CLM] train=1.6214  mask=11.3%  norm=0.715  lr=2.79e-05  dt=  37.0ms  words=88,498,176
[E07  1516/1548 G  10803|CLM] train=3.9205  mask=11.3%  norm=0.906  lr=2.79e-05  dt=  37.0ms  words=88,506,368
[E07  1517/1548 G  10804|CLM] train=3.7449  mask=11.3%  norm=0.900  lr=2.79e-05  dt=  37.1ms  words=88,514,560
[E07  1518/1548 G  10805|CLM] train=3.7224  mask=11.3%  norm=0.842  lr=2.79e-05  dt=  37.1ms  words=88,522,752
[E07  1519/1548 G  10806|CLM] train=4.2556  mask=11.3%  norm=0.930  lr=2.79e-05  dt=  37.0ms  words=88,530,944
[E07  1520/1548 G  10807|CLM] train=4.1613  mask=11.3%  norm=0.975  lr=2.78e-05  dt=  36.9ms  words=88,539,136
[E07  1521/1548 G  10808|CLM] train=4.1495  mask=11.3%  norm=0.939  lr=2.78e-05  dt=  37.0ms  words=88,547,328
[E07  1522/1548 G  10809|CLM] train=4.1362  mask=11.3%  norm=0.900  lr=2.78e-05  dt=  37.2ms  words=88,555,520
[E07  1523/1548 G  10810|CLM] train=3.5396  mask=11.3%  norm=0.819  lr=2.78e-05  dt=  37.2ms  words=88,563,712
[E07  1524/1548 G  10811|CLM] train=4.5694  mask=11.3%  norm=1.049  lr=2.78e-05  dt=  37.0ms  words=88,571,904
[E07  1525/1548 G  10812|CLM] train=1.9900  mask=11.3%  norm=0.966  lr=2.78e-05  dt=  37.2ms  words=88,580,096
[E07  1526/1548 G  10813|CLM] train=4.2481  mask=11.3%  norm=0.951  lr=2.77e-05  dt=  37.0ms  words=88,588,288
[E07  1527/1548 G  10814|CLM] train=2.2859  mask=11.3%  norm=1.245  lr=2.77e-05  dt=  37.1ms  words=88,596,480
[E07  1528/1548 G  10815|CLM] train=2.0229  mask=11.3%  norm=0.661  lr=2.77e-05  dt=  37.0ms  words=88,604,672
[E07  1529/1548 G  10816|CLM] train=3.5349  mask=11.3%  norm=0.918  lr=2.77e-05  dt=  37.1ms  words=88,612,864
[E07  1530/1548 G  10817|CLM] train=4.5854  mask=11.3%  norm=0.952  lr=2.77e-05  dt=  37.1ms  words=88,621,056
[E07  1531/1548 G  10818|CLM] train=3.7941  mask=11.3%  norm=0.818  lr=2.77e-05  dt=  37.1ms  words=88,629,248
[E07  1532/1548 G  10819|CLM] train=3.2390  mask=11.3%  norm=0.809  lr=2.76e-05  dt=  37.0ms  words=88,637,440
[E07  1533/1548 G  10820|CLM] train=4.7455  mask=11.3%  norm=1.086  lr=2.76e-05  dt=  37.1ms  words=88,645,632
[E07  1534/1548 G  10821|CLM] train=1.9838  mask=11.3%  norm=0.770  lr=2.76e-05  dt=  37.0ms  words=88,653,824
[E07  1535/1548 G  10822|CLM] train=2.1988  mask=11.3%  norm=0.700  lr=2.76e-05  dt=  37.0ms  words=88,662,016
[E07  1536/1548 G  10823|CLM] train=4.0868  mask=11.3%  norm=0.812  lr=2.76e-05  dt=  37.2ms  words=88,670,208
[E07  1537/1548 G  10824|CLM] train=2.4228  mask=11.3%  norm=0.733  lr=2.76e-05  dt=  36.9ms  words=88,678,400
[E07  1538/1548 G  10825|CLM] train=3.5562  mask=11.3%  norm=0.834  lr=2.75e-05  dt=  37.2ms  words=88,686,592
[E07  1539/1548 G  10826|CLM] train=4.5737  mask=11.3%  norm=0.958  lr=2.75e-05  dt=  37.2ms  words=88,694,784
[E07  1540/1548 G  10827|CLM] train=3.9794  mask=11.3%  norm=0.955  lr=2.75e-05  dt=  37.0ms  words=88,702,976
[E07  1541/1548 G  10828|CLM] train=3.5500  mask=11.3%  norm=0.830  lr=2.75e-05  dt=  37.7ms  words=88,711,168
[E07  1542/1548 G  10829|CLM] train=1.8817  mask=11.3%  norm=0.766  lr=2.75e-05  dt=  37.6ms  words=88,719,360
[E07  1543/1548 G  10830|CLM] train=2.7249  mask=11.3%  norm=0.744  lr=2.75e-05  dt=  37.2ms  words=88,727,552
[E07  1544/1548 G  10831|CLM] train=2.0769  mask=11.3%  norm=0.704  lr=2.75e-05  dt=  37.3ms  words=88,735,744
[E07  1545/1548 G  10832|CLM] train=4.3905  mask=11.3%  norm=1.014  lr=2.74e-05  dt=  37.1ms  words=88,743,936
[E07  1546/1548 G  10833|CLM] train=3.8715  mask=11.3%  norm=0.884  lr=2.74e-05  dt=  36.9ms  words=88,752,128
[E07  1547/1548 G  10834|CLM] train=3.6137  mask=11.3%  norm=0.884  lr=2.74e-05  dt=  36.8ms  words=88,760,320
[E07  1548/1548 G  10835|CLM] train=2.1432  mask=11.3%  norm=0.664  lr=2.74e-05  dt=  36.9ms  words=88,768,512
[E08     1/1548 G  10836|CLM] train=4.3183  mask=11.2%  norm=1.034  lr=2.74e-05  dt=  37.1ms  words=88,776,704
[E08     2/1548 G  10837|CLM] train=2.5663  mask=11.2%  norm=0.783  lr=2.74e-05  dt=  36.9ms  words=88,784,896
[E08     3/1548 G  10838|CLM] train=4.4313  mask=11.2%  norm=0.845  lr=2.73e-05  dt=  37.1ms  words=88,793,088
[E08     4/1548 G  10839|CLM] train=4.5293  mask=11.2%  norm=0.876  lr=2.73e-05  dt=  37.2ms  words=88,801,280
[E08     5/1548 G  10840|CLM] train=2.1012  mask=11.2%  norm=0.735  lr=2.73e-05  dt=  37.2ms  words=88,809,472
[E08     6/1548 G  10841|CLM] train=3.5719  mask=11.2%  norm=0.800  lr=2.73e-05  dt=  37.3ms  words=88,817,664
[E08     7/1548 G  10842|CLM] train=2.4654  mask=11.2%  norm=0.703  lr=2.73e-05  dt=  37.2ms  words=88,825,856
[E08     8/1548 G  10843|CLM] train=2.4660  mask=11.2%  norm=0.782  lr=2.73e-05  dt=  37.1ms  words=88,834,048
[E08     9/1548 G  10844|CLM] train=3.6951  mask=11.2%  norm=0.841  lr=2.72e-05  dt=  37.1ms  words=88,842,240
[E08    10/1548 G  10845|CLM] train=3.3457  mask=11.2%  norm=0.835  lr=2.72e-05  dt=  37.2ms  words=88,850,432
[E08    11/1548 G  10846|CLM] train=1.6222  mask=11.2%  norm=0.704  lr=2.72e-05  dt=  37.0ms  words=88,858,624
[E08    12/1548 G  10847|CLM] train=3.9108  mask=11.2%  norm=0.882  lr=2.72e-05  dt=  37.0ms  words=88,866,816
[E08    13/1548 G  10848|CLM] train=2.0890  mask=11.2%  norm=0.678  lr=2.72e-05  dt=  37.1ms  words=88,875,008
[E08    14/1548 G  10849|CLM] train=1.8151  mask=11.2%  norm=0.695  lr=2.72e-05  dt=  37.1ms  words=88,883,200
[E08    15/1548 G  10850|CLM] train=3.7947  mask=11.2%  norm=0.823  lr=2.72e-05  dt=  37.2ms  words=88,891,392
[E08    16/1548 G  10851|CLM] train=3.7194  mask=11.2%  norm=0.860  lr=2.71e-05  dt=  37.1ms  words=88,899,584
[E08    17/1548 G  10852|CLM] train=2.3451  mask=11.2%  norm=0.703  lr=2.71e-05  dt=  37.2ms  words=88,907,776
[E08    18/1548 G  10853|CLM] train=3.5255  mask=11.2%  norm=0.838  lr=2.71e-05  dt=  36.9ms  words=88,915,968
[E08    19/1548 G  10854|CLM] train=4.2171  mask=11.2%  norm=0.882  lr=2.71e-05  dt=  37.0ms  words=88,924,160
[E08    20/1548 G  10855|CLM] train=2.6206  mask=11.2%  norm=0.710  lr=2.71e-05  dt=  37.0ms  words=88,932,352
[E08    21/1548 G  10856|CLM] train=4.2510  mask=11.2%  norm=0.908  lr=2.71e-05  dt=  37.1ms  words=88,940,544
[E08    22/1548 G  10857|CLM] train=2.6890  mask=11.2%  norm=0.765  lr=2.70e-05  dt=  36.9ms  words=88,948,736
[E08    23/1548 G  10858|CLM] train=3.5708  mask=11.2%  norm=0.835  lr=2.70e-05  dt=  36.8ms  words=88,956,928
[E08    24/1548 G  10859|CLM] train=3.6733  mask=11.2%  norm=0.859  lr=2.70e-05  dt=  37.0ms  words=88,965,120
[E08    25/1548 G  10860|CLM] train=4.1302  mask=11.2%  norm=1.005  lr=2.70e-05  dt=  37.1ms  words=88,973,312
[E08    26/1548 G  10861|CLM] train=2.2091  mask=11.2%  norm=0.766  lr=2.70e-05  dt=  36.9ms  words=88,981,504
[E08    27/1548 G  10862|CLM] train=3.7126  mask=11.2%  norm=0.796  lr=2.70e-05  dt=  37.2ms  words=88,989,696
[E08    28/1548 G  10863|CLM] train=4.1027  mask=11.2%  norm=0.871  lr=2.70e-05  dt=  37.2ms  words=88,997,888
[E08    29/1548 G  10864|CLM] train=5.0035  mask=11.2%  norm=1.466  lr=2.69e-05  dt=  37.0ms  words=89,006,080
[E08    30/1548 G  10865|CLM] train=2.1817  mask=11.2%  norm=0.762  lr=2.69e-05  dt=  36.8ms  words=89,014,272
[E08    31/1548 G  10866|CLM] train=4.8691  mask=11.2%  norm=1.121  lr=2.69e-05  dt=  37.0ms  words=89,022,464
[E08    32/1548 G  10867|CLM] train=2.1570  mask=11.2%  norm=0.726  lr=2.69e-05  dt=  37.1ms  words=89,030,656
[E08    33/1548 G  10868|CLM] train=4.3034  mask=11.2%  norm=0.872  lr=2.69e-05  dt=  37.4ms  words=89,038,848
[E08    34/1548 G  10869|CLM] train=3.4745  mask=11.2%  norm=0.885  lr=2.69e-05  dt=  37.0ms  words=89,047,040
[E08    35/1548 G  10870|CLM] train=4.1375  mask=11.2%  norm=0.860  lr=2.68e-05  dt=  37.1ms  words=89,055,232
[E08    36/1548 G  10871|CLM] train=1.9594  mask=11.2%  norm=0.730  lr=2.68e-05  dt=  36.8ms  words=89,063,424
[E08    37/1548 G  10872|CLM] train=4.3931  mask=11.2%  norm=0.893  lr=2.68e-05  dt=  37.0ms  words=89,071,616
[E08    38/1548 G  10873|CLM] train=4.0672  mask=11.2%  norm=0.873  lr=2.68e-05  dt=  36.9ms  words=89,079,808
[E08    39/1548 G  10874|CLM] train=2.3887  mask=11.2%  norm=0.661  lr=2.68e-05  dt=  37.1ms  words=89,088,000
[E08    40/1548 G  10875|CLM] train=4.0721  mask=11.2%  norm=0.990  lr=2.68e-05  dt=  36.9ms  words=89,096,192
[E08    41/1548 G  10876|CLM] train=1.9053  mask=11.2%  norm=0.701  lr=2.68e-05  dt=  36.9ms  words=89,104,384
[E08    42/1548 G  10877|CLM] train=2.1565  mask=11.2%  norm=0.655  lr=2.67e-05  dt=  37.0ms  words=89,112,576
[E08    43/1548 G  10878|CLM] train=3.9265  mask=11.2%  norm=0.827  lr=2.67e-05  dt=  37.2ms  words=89,120,768
[E08    44/1548 G  10879|CLM] train=3.4784  mask=11.2%  norm=0.751  lr=2.67e-05  dt=  37.0ms  words=89,128,960
[E08    45/1548 G  10880|CLM] train=3.3393  mask=11.2%  norm=0.850  lr=2.67e-05  dt=  37.1ms  words=89,137,152
[E08    46/1548 G  10881|CLM] train=3.5706  mask=11.2%  norm=0.933  lr=2.67e-05  dt=  37.1ms  words=89,145,344
[E08    47/1548 G  10882|CLM] train=4.1737  mask=11.2%  norm=0.909  lr=2.67e-05  dt=  37.1ms  words=89,153,536
[E08    48/1548 G  10883|CLM] train=3.6006  mask=11.2%  norm=0.830  lr=2.66e-05  dt=  37.1ms  words=89,161,728
[E08    49/1548 G  10884|CLM] train=4.1893  mask=11.2%  norm=0.973  lr=2.66e-05  dt=  37.6ms  words=89,169,920
[E08    50/1548 G  10885|CLM] train=2.4300  mask=11.2%  norm=0.797  lr=2.66e-05  dt=  36.9ms  words=89,178,112
[E08    51/1548 G  10886|CLM] train=2.1880  mask=11.2%  norm=0.615  lr=2.66e-05  dt=  37.0ms  words=89,186,304
[E08    52/1548 G  10887|CLM] train=2.1742  mask=11.2%  norm=0.738  lr=2.66e-05  dt=  36.9ms  words=89,194,496
[E08    53/1548 G  10888|CLM] train=4.7256  mask=11.2%  norm=0.958  lr=2.66e-05  dt=  37.1ms  words=89,202,688
[E08    54/1548 G  10889|CLM] train=3.8909  mask=11.2%  norm=0.834  lr=2.66e-05  dt=  36.8ms  words=89,210,880
[E08    55/1548 G  10890|CLM] train=4.0553  mask=11.2%  norm=0.914  lr=2.65e-05  dt=  37.0ms  words=89,219,072
[E08    56/1548 G  10891|CLM] train=3.5995  mask=11.2%  norm=0.769  lr=2.65e-05  dt=  36.8ms  words=89,227,264
[E08    57/1548 G  10892|CLM] train=3.8830  mask=11.2%  norm=0.830  lr=2.65e-05  dt=  37.1ms  words=89,235,456
[E08    58/1548 G  10893|CLM] train=4.6456  mask=11.2%  norm=1.382  lr=2.65e-05  dt=  36.8ms  words=89,243,648
[E08    59/1548 G  10894|CLM] train=3.8555  mask=11.2%  norm=0.902  lr=2.65e-05  dt=  36.9ms  words=89,251,840
[E08    60/1548 G  10895|CLM] train=4.0348  mask=11.2%  norm=0.940  lr=2.65e-05  dt=  36.9ms  words=89,260,032
[E08    61/1548 G  10896|CLM] train=3.9293  mask=11.2%  norm=0.809  lr=2.64e-05  dt=  37.3ms  words=89,268,224
[E08    62/1548 G  10897|CLM] train=3.7305  mask=11.2%  norm=0.787  lr=2.64e-05  dt=  37.1ms  words=89,276,416
[E08    63/1548 G  10898|CLM] train=3.6038  mask=11.2%  norm=1.057  lr=2.64e-05  dt=  37.1ms  words=89,284,608
[E08    64/1548 G  10899|CLM] train=2.1419  mask=11.2%  norm=0.752  lr=2.64e-05  dt=  37.1ms  words=89,292,800
[E08    65/1548 G  10900|CLM] train=3.6751  mask=11.2%  norm=0.907  lr=2.64e-05  dt=  36.9ms  words=89,300,992
[E08    66/1548 G  10901|CLM] train=2.0044  mask=11.2%  norm=0.639  lr=2.64e-05  dt=  36.9ms  words=89,309,184
[E08    67/1548 G  10902|CLM] train=4.3409  mask=11.2%  norm=0.921  lr=2.64e-05  dt=  37.1ms  words=89,317,376
[E08    68/1548 G  10903|CLM] train=3.8427  mask=11.2%  norm=0.878  lr=2.63e-05  dt=  37.0ms  words=89,325,568
[E08    69/1548 G  10904|CLM] train=2.1816  mask=11.2%  norm=0.687  lr=2.63e-05  dt=  36.9ms  words=89,333,760
[E08    70/1548 G  10905|CLM] train=4.3506  mask=11.2%  norm=1.026  lr=2.63e-05  dt=  36.8ms  words=89,341,952
[E08    71/1548 G  10906|CLM] train=2.1446  mask=11.2%  norm=0.760  lr=2.63e-05  dt=  36.9ms  words=89,350,144
[E08    72/1548 G  10907|CLM] train=3.4585  mask=11.2%  norm=0.845  lr=2.63e-05  dt=  37.1ms  words=89,358,336
[E08    73/1548 G  10908|CLM] train=3.9941  mask=11.2%  norm=0.790  lr=2.63e-05  dt=  36.9ms  words=89,366,528
[E08    74/1548 G  10909|CLM] train=1.8750  mask=11.2%  norm=0.729  lr=2.63e-05  dt=  37.0ms  words=89,374,720
[E08    75/1548 G  10910|CLM] train=2.0095  mask=11.2%  norm=0.708  lr=2.62e-05  dt=  37.4ms  words=89,382,912
[E08    76/1548 G  10911|CLM] train=4.5526  mask=11.2%  norm=0.930  lr=2.62e-05  dt=  37.2ms  words=89,391,104
[E08    77/1548 G  10912|CLM] train=1.9773  mask=11.2%  norm=0.699  lr=2.62e-05  dt=  36.9ms  words=89,399,296
[E08    78/1548 G  10913|CLM] train=2.0089  mask=11.2%  norm=0.697  lr=2.62e-05  dt=  37.4ms  words=89,407,488
[E08    79/1548 G  10914|CLM] train=2.0276  mask=11.2%  norm=0.757  lr=2.62e-05  dt=  36.9ms  words=89,415,680
[E08    80/1548 G  10915|CLM] train=3.6680  mask=11.2%  norm=0.995  lr=2.62e-05  dt=  37.5ms  words=89,423,872
[E08    81/1548 G  10916|CLM] train=2.3951  mask=11.2%  norm=0.757  lr=2.61e-05  dt=  37.0ms  words=89,432,064
[E08    82/1548 G  10917|CLM] train=4.1496  mask=11.2%  norm=0.873  lr=2.61e-05  dt=  37.0ms  words=89,440,256
[E08    83/1548 G  10918|CLM] train=1.8010  mask=11.2%  norm=0.717  lr=2.61e-05  dt=  36.9ms  words=89,448,448
[E08    84/1548 G  10919|CLM] train=2.4497  mask=11.2%  norm=0.684  lr=2.61e-05  dt=  37.1ms  words=89,456,640
[E08    85/1548 G  10920|CLM] train=2.3326  mask=11.2%  norm=1.155  lr=2.61e-05  dt=  37.5ms  words=89,464,832
[E08    86/1548 G  10921|CLM] train=3.8634  mask=11.2%  norm=0.894  lr=2.61e-05  dt=  36.8ms  words=89,473,024
[E08    87/1548 G  10922|CLM] train=4.0390  mask=11.2%  norm=0.908  lr=2.61e-05  dt=  36.9ms  words=89,481,216
[E08    88/1548 G  10923|CLM] train=1.9838  mask=11.2%  norm=0.623  lr=2.60e-05  dt=  36.9ms  words=89,489,408
[E08    89/1548 G  10924|CLM] train=3.9764  mask=11.2%  norm=0.870  lr=2.60e-05  dt=  37.1ms  words=89,497,600
[E08    90/1548 G  10925|CLM] train=3.9219  mask=11.2%  norm=1.022  lr=2.60e-05  dt=  36.9ms  words=89,505,792
[E08    91/1548 G  10926|CLM] train=1.8112  mask=11.2%  norm=0.879  lr=2.60e-05  dt=  36.9ms  words=89,513,984
[E08    92/1548 G  10927|CLM] train=1.7280  mask=11.2%  norm=0.731  lr=2.60e-05  dt=  36.8ms  words=89,522,176
[E08    93/1548 G  10928|CLM] train=3.8656  mask=11.2%  norm=0.763  lr=2.60e-05  dt=  37.1ms  words=89,530,368
[E08    94/1548 G  10929|CLM] train=4.1366  mask=11.2%  norm=0.944  lr=2.60e-05  dt=  37.1ms  words=89,538,560
[E08    95/1548 G  10930|CLM] train=4.8900  mask=11.2%  norm=1.163  lr=2.59e-05  dt=  37.0ms  words=89,546,752
[E08    96/1548 G  10931|CLM] train=3.7312  mask=11.2%  norm=0.805  lr=2.59e-05  dt=  37.1ms  words=89,554,944
[E08    97/1548 G  10932|CLM] train=3.6612  mask=11.2%  norm=0.820  lr=2.59e-05  dt=  37.0ms  words=89,563,136
[E08    98/1548 G  10933|CLM] train=4.3126  mask=11.2%  norm=1.023  lr=2.59e-05  dt=  37.0ms  words=89,571,328
[E08    99/1548 G  10934|CLM] train=3.5505  mask=11.2%  norm=0.795  lr=2.59e-05  dt=  37.1ms  words=89,579,520
[E08   100/1548 G  10935|CLM] train=4.1344  mask=11.2%  norm=0.910  lr=2.59e-05  dt=  37.2ms  words=89,587,712
[E08   101/1548 G  10936|CLM] train=3.9732  mask=11.2%  norm=0.906  lr=2.58e-05  dt=  37.8ms  words=89,595,904
[E08   102/1548 G  10937|CLM] train=4.0403  mask=11.2%  norm=0.899  lr=2.58e-05  dt=  38.7ms  words=89,604,096
[E08   103/1548 G  10938|CLM] train=3.6550  mask=11.2%  norm=0.891  lr=2.58e-05  dt=  37.2ms  words=89,612,288
[E08   104/1548 G  10939|CLM] train=4.0991  mask=11.2%  norm=0.936  lr=2.58e-05  dt=  37.3ms  words=89,620,480
[E08   105/1548 G  10940|CLM] train=4.0072  mask=11.2%  norm=0.969  lr=2.58e-05  dt=  37.0ms  words=89,628,672
[E08   106/1548 G  10941|CLM] train=3.5349  mask=11.2%  norm=0.808  lr=2.58e-05  dt=  37.0ms  words=89,636,864
[E08   107/1548 G  10942|CLM] train=1.9025  mask=11.2%  norm=0.725  lr=2.58e-05  dt=  37.1ms  words=89,645,056
[E08   108/1548 G  10943|CLM] train=2.2100  mask=11.2%  norm=0.695  lr=2.57e-05  dt=  37.1ms  words=89,653,248
[E08   109/1548 G  10944|CLM] train=3.9819  mask=11.2%  norm=0.800  lr=2.57e-05  dt=  36.8ms  words=89,661,440
[E08   110/1548 G  10945|CLM] train=3.5190  mask=11.2%  norm=0.805  lr=2.57e-05  dt=  36.9ms  words=89,669,632
[E08   111/1548 G  10946|CLM] train=3.5516  mask=11.2%  norm=0.861  lr=2.57e-05  dt=  36.9ms  words=89,677,824
[E08   112/1548 G  10947|CLM] train=1.6720  mask=11.2%  norm=0.738  lr=2.57e-05  dt=  37.1ms  words=89,686,016
[E08   113/1548 G  10948|CLM] train=2.0750  mask=11.2%  norm=0.650  lr=2.57e-05  dt=  36.9ms  words=89,694,208
[E08   114/1548 G  10949|CLM] train=3.2169  mask=11.2%  norm=0.859  lr=2.57e-05  dt=  37.4ms  words=89,702,400
[E08   115/1548 G  10950|CLM] train=2.6394  mask=11.2%  norm=0.743  lr=2.56e-05  dt=  37.1ms  words=89,710,592
[E08   116/1548 G  10951|CLM] train=3.9814  mask=11.2%  norm=0.867  lr=2.56e-05  dt=  37.2ms  words=89,718,784
[E08   117/1548 G  10952|CLM] train=2.3096  mask=11.2%  norm=0.762  lr=2.56e-05  dt=  37.0ms  words=89,726,976
[E08   118/1548 G  10953|CLM] train=2.1271  mask=11.2%  norm=0.702  lr=2.56e-05  dt=  36.9ms  words=89,735,168
[E08   119/1548 G  10954|CLM] train=4.0303  mask=11.2%  norm=0.826  lr=2.56e-05  dt=  37.0ms  words=89,743,360
[E08   120/1548 G  10955|CLM] train=4.3304  mask=11.2%  norm=0.899  lr=2.56e-05  dt=  36.8ms  words=89,751,552
[E08   121/1548 G  10956|CLM] train=3.9028  mask=11.2%  norm=0.838  lr=2.56e-05  dt=  36.9ms  words=89,759,744
[E08   122/1548 G  10957|CLM] train=3.9450  mask=11.2%  norm=0.960  lr=2.55e-05  dt=  36.8ms  words=89,767,936
[E08   123/1548 G  10958|CLM] train=4.3141  mask=11.2%  norm=0.960  lr=2.55e-05  dt=  37.0ms  words=89,776,128
[E08   124/1548 G  10959|CLM] train=4.2431  mask=11.2%  norm=1.048  lr=2.55e-05  dt=  36.9ms  words=89,784,320
[E08   125/1548 G  10960|CLM] train=1.4721  mask=11.1%  norm=0.610  lr=2.55e-05  dt=  37.0ms  words=89,792,512
[E08   126/1548 G  10961|CLM] train=1.7954  mask=11.1%  norm=0.684  lr=2.55e-05  dt=  37.2ms  words=89,800,704
[E08   127/1548 G  10962|CLM] train=2.1469  mask=11.1%  norm=0.674  lr=2.55e-05  dt=  37.2ms  words=89,808,896
[E08   128/1548 G  10963|CLM] train=2.3309  mask=11.1%  norm=0.726  lr=2.55e-05  dt=  37.0ms  words=89,817,088
[E08   129/1548 G  10964|CLM] train=1.9753  mask=11.1%  norm=0.677  lr=2.54e-05  dt=  37.0ms  words=89,825,280
[E08   130/1548 G  10965|CLM] train=3.9969  mask=11.1%  norm=0.980  lr=2.54e-05  dt=  37.0ms  words=89,833,472
[E08   131/1548 G  10966|CLM] train=2.3697  mask=11.1%  norm=0.834  lr=2.54e-05  dt=  36.8ms  words=89,841,664
[E08   132/1548 G  10967|CLM] train=2.6392  mask=11.1%  norm=0.705  lr=2.54e-05  dt=  36.9ms  words=89,849,856
[E08   133/1548 G  10968|CLM] train=4.3739  mask=11.1%  norm=1.173  lr=2.54e-05  dt=  37.0ms  words=89,858,048
[E08   134/1548 G  10969|CLM] train=3.9612  mask=11.1%  norm=0.882  lr=2.54e-05  dt=  37.0ms  words=89,866,240
[E08   135/1548 G  10970|CLM] train=2.3318  mask=11.1%  norm=0.686  lr=2.53e-05  dt=  37.1ms  words=89,874,432
[E08   136/1548 G  10971|CLM] train=2.4633  mask=11.1%  norm=0.743  lr=2.53e-05  dt=  37.0ms  words=89,882,624
[E08   137/1548 G  10972|CLM] train=3.5572  mask=11.1%  norm=0.828  lr=2.53e-05  dt=  37.1ms  words=89,890,816
[E08   138/1548 G  10973|CLM] train=3.8323  mask=11.1%  norm=0.935  lr=2.53e-05  dt=  37.0ms  words=89,899,008
[E08   139/1548 G  10974|CLM] train=3.3734  mask=11.1%  norm=0.785  lr=2.53e-05  dt=  37.1ms  words=89,907,200
[E08   140/1548 G  10975|CLM] train=1.8950  mask=11.1%  norm=0.746  lr=2.53e-05  dt=  37.0ms  words=89,915,392
[E08   141/1548 G  10976|CLM] train=3.5090  mask=11.1%  norm=0.782  lr=2.53e-05  dt=  37.4ms  words=89,923,584
[E08   142/1548 G  10977|CLM] train=3.5809  mask=11.1%  norm=0.870  lr=2.52e-05  dt=  37.1ms  words=89,931,776
[E08   143/1548 G  10978|CLM] train=2.1656  mask=11.1%  norm=0.750  lr=2.52e-05  dt=  37.1ms  words=89,939,968
[E08   144/1548 G  10979|CLM] train=2.0650  mask=11.1%  norm=0.823  lr=2.52e-05  dt=  37.2ms  words=89,948,160
[E08   145/1548 G  10980|CLM] train=3.2289  mask=11.1%  norm=0.777  lr=2.52e-05  dt=  36.9ms  words=89,956,352
[E08   146/1548 G  10981|CLM] train=1.9439  mask=11.1%  norm=0.872  lr=2.52e-05  dt=  37.0ms  words=89,964,544
[E08   147/1548 G  10982|CLM] train=4.3716  mask=11.1%  norm=0.856  lr=2.52e-05  dt=  37.2ms  words=89,972,736
[E08   148/1548 G  10983|CLM] train=2.6290  mask=11.1%  norm=0.733  lr=2.52e-05  dt=  37.0ms  words=89,980,928
[E08   149/1548 G  10984|CLM] train=3.6681  mask=11.1%  norm=0.834  lr=2.51e-05  dt=  36.9ms  words=89,989,120
[E08   150/1548 G  10985|CLM] train=4.0066  mask=11.1%  norm=0.851  lr=2.51e-05  dt=  37.4ms  words=89,997,312
[E08   151/1548 G  10986|CLM] train=3.6465  mask=11.1%  norm=0.831  lr=2.51e-05  dt=  37.3ms  words=90,005,504

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_90M'...
[Checkpoint] Checkpoint 'chck_90M' successfully saved.
[E08   152/1548 G  10987|CLM] train=1.7574  mask=11.1%  norm=0.661  lr=2.51e-05  dt=  37.8ms  words=90,013,696
[E08   153/1548 G  10988|CLM] train=1.8492  mask=11.1%  norm=0.717  lr=2.51e-05  dt=  37.0ms  words=90,021,888
[E08   154/1548 G  10989|CLM] train=3.5272  mask=11.1%  norm=0.910  lr=2.51e-05  dt=  37.3ms  words=90,030,080
[E08   155/1548 G  10990|CLM] train=2.5455  mask=11.1%  norm=0.727  lr=2.51e-05  dt=  37.3ms  words=90,038,272
[E08   156/1548 G  10991|CLM] train=3.9501  mask=11.1%  norm=0.861  lr=2.50e-05  dt=  37.1ms  words=90,046,464
[E08   157/1548 G  10992|CLM] train=3.9454  mask=11.1%  norm=0.901  lr=2.50e-05  dt=  37.1ms  words=90,054,656
[E08   158/1548 G  10993|CLM] train=4.1330  mask=11.1%  norm=0.876  lr=2.50e-05  dt=  37.9ms  words=90,062,848
[E08   159/1548 G  10994|CLM] train=2.4407  mask=11.1%  norm=0.741  lr=2.50e-05  dt=  37.3ms  words=90,071,040
[E08   160/1548 G  10995|CLM] train=2.2955  mask=11.1%  norm=0.814  lr=2.50e-05  dt=  37.1ms  words=90,079,232
[E08   161/1548 G  10996|CLM] train=5.1625  mask=11.1%  norm=1.078  lr=2.50e-05  dt=  37.1ms  words=90,087,424
[E08   162/1548 G  10997|CLM] train=5.0817  mask=11.1%  norm=1.051  lr=2.50e-05  dt=  40.3ms  words=90,095,616
[E08   163/1548 G  10998|CLM] train=4.3246  mask=11.1%  norm=0.897  lr=2.49e-05  dt=  37.1ms  words=90,103,808
[E08   164/1548 G  10999|CLM] train=3.4781  mask=11.1%  norm=0.795  lr=2.49e-05  dt=  37.1ms  words=90,112,000
[E08   165/1548 G  11000|CLM] train=4.3027  mask=11.1%  norm=0.952  lr=2.49e-05  dt=  37.0ms  words=90,120,192
[E08   166/1548 G  11001|CLM] train=2.3750  mask=11.1%  norm=0.685  lr=2.49e-05  dt=  37.0ms  words=90,128,384
[E08   167/1548 G  11002|CLM] train=3.8078  mask=11.1%  norm=0.817  lr=2.49e-05  dt=  37.2ms  words=90,136,576
[E08   168/1548 G  11003|CLM] train=1.5462  mask=11.1%  norm=0.669  lr=2.49e-05  dt=  37.2ms  words=90,144,768
[E08   169/1548 G  11004|CLM] train=3.9016  mask=11.1%  norm=0.869  lr=2.49e-05  dt=  37.2ms  words=90,152,960
[E08   170/1548 G  11005|CLM] train=2.1549  mask=11.1%  norm=0.714  lr=2.48e-05  dt=  37.2ms  words=90,161,152
[E08   171/1548 G  11006|CLM] train=3.9747  mask=11.1%  norm=0.987  lr=2.48e-05  dt=  37.0ms  words=90,169,344
[E08   172/1548 G  11007|CLM] train=4.4214  mask=11.1%  norm=0.860  lr=2.48e-05  dt=  36.9ms  words=90,177,536
[E08   173/1548 G  11008|CLM] train=4.3141  mask=11.1%  norm=1.125  lr=2.48e-05  dt=  36.9ms  words=90,185,728
[E08   174/1548 G  11009|CLM] train=1.6972  mask=11.1%  norm=0.664  lr=2.48e-05  dt=  37.1ms  words=90,193,920
[E08   175/1548 G  11010|CLM] train=3.3714  mask=11.1%  norm=0.872  lr=2.48e-05  dt=  37.1ms  words=90,202,112
[E08   176/1548 G  11011|CLM] train=3.3957  mask=11.1%  norm=0.846  lr=2.48e-05  dt=  37.1ms  words=90,210,304
[E08   177/1548 G  11012|CLM] train=4.0751  mask=11.1%  norm=0.939  lr=2.48e-05  dt=  37.2ms  words=90,218,496
[E08   178/1548 G  11013|CLM] train=4.0435  mask=11.1%  norm=0.902  lr=2.47e-05  dt=  37.1ms  words=90,226,688
[E08   179/1548 G  11014|CLM] train=1.7232  mask=11.1%  norm=0.681  lr=2.47e-05  dt=  37.0ms  words=90,234,880
[E08   180/1548 G  11015|CLM] train=4.4961  mask=11.1%  norm=1.187  lr=2.47e-05  dt=  36.9ms  words=90,243,072
[E08   181/1548 G  11016|CLM] train=3.9772  mask=11.1%  norm=1.189  lr=2.47e-05  dt=  37.0ms  words=90,251,264
[E08   182/1548 G  11017|CLM] train=2.1372  mask=11.1%  norm=0.777  lr=2.47e-05  dt=  37.1ms  words=90,259,456
[E08   183/1548 G  11018|CLM] train=2.0704  mask=11.1%  norm=0.729  lr=2.47e-05  dt=  37.1ms  words=90,267,648
[E08   184/1548 G  11019|CLM] train=4.6183  mask=11.1%  norm=1.008  lr=2.47e-05  dt=  37.4ms  words=90,275,840
[E08   185/1548 G  11020|CLM] train=3.9081  mask=11.1%  norm=0.830  lr=2.46e-05  dt=  37.0ms  words=90,284,032
[E08   186/1548 G  11021|CLM] train=3.8208  mask=11.1%  norm=0.892  lr=2.46e-05  dt=  37.0ms  words=90,292,224
[E08   187/1548 G  11022|CLM] train=4.3541  mask=11.1%  norm=1.129  lr=2.46e-05  dt=  37.4ms  words=90,300,416
[E08   188/1548 G  11023|CLM] train=3.7322  mask=11.1%  norm=0.735  lr=2.46e-05  dt=  37.2ms  words=90,308,608
[E08   189/1548 G  11024|CLM] train=3.9371  mask=11.1%  norm=0.931  lr=2.46e-05  dt=  37.5ms  words=90,316,800
[E08   190/1548 G  11025|CLM] train=4.0199  mask=11.1%  norm=0.863  lr=2.46e-05  dt=  37.2ms  words=90,324,992
[E08   191/1548 G  11026|CLM] train=2.0183  mask=11.1%  norm=0.850  lr=2.46e-05  dt=  37.0ms  words=90,333,184
[E08   192/1548 G  11027|CLM] train=4.3416  mask=11.1%  norm=0.926  lr=2.45e-05  dt=  36.9ms  words=90,341,376
[E08   193/1548 G  11028|CLM] train=3.5933  mask=11.1%  norm=0.857  lr=2.45e-05  dt=  37.0ms  words=90,349,568
[E08   194/1548 G  11029|CLM] train=3.5902  mask=11.1%  norm=0.791  lr=2.45e-05  dt=  37.1ms  words=90,357,760
[E08   195/1548 G  11030|CLM] train=4.3068  mask=11.1%  norm=1.055  lr=2.45e-05  dt=  37.2ms  words=90,365,952
[E08   196/1548 G  11031|CLM] train=4.4780  mask=11.1%  norm=0.894  lr=2.45e-05  dt=  37.2ms  words=90,374,144
[E08   197/1548 G  11032|CLM] train=2.0081  mask=11.1%  norm=0.695  lr=2.45e-05  dt=  37.2ms  words=90,382,336
[E08   198/1548 G  11033|CLM] train=4.2994  mask=11.1%  norm=0.877  lr=2.45e-05  dt=  36.9ms  words=90,390,528
[E08   199/1548 G  11034|CLM] train=3.9048  mask=11.1%  norm=0.992  lr=2.44e-05  dt=  37.2ms  words=90,398,720
[E08   200/1548 G  11035|CLM] train=2.9909  mask=11.1%  norm=1.338  lr=2.44e-05  dt=  37.3ms  words=90,406,912
[E08   201/1548 G  11036|CLM] train=2.0053  mask=11.1%  norm=0.707  lr=2.44e-05  dt=  37.0ms  words=90,415,104
[E08   202/1548 G  11037|CLM] train=3.2569  mask=11.1%  norm=0.738  lr=2.44e-05  dt=  37.3ms  words=90,423,296
[E08   203/1548 G  11038|CLM] train=4.0609  mask=11.1%  norm=0.893  lr=2.44e-05  dt=  38.2ms  words=90,431,488
[E08   204/1548 G  11039|CLM] train=3.8972  mask=11.1%  norm=0.839  lr=2.44e-05  dt=  38.4ms  words=90,439,680
[E08   205/1548 G  11040|CLM] train=4.1513  mask=11.1%  norm=0.883  lr=2.44e-05  dt=  37.1ms  words=90,447,872
[E08   206/1548 G  11041|CLM] train=1.9704  mask=11.1%  norm=0.773  lr=2.43e-05  dt=  37.1ms  words=90,456,064
[E08   207/1548 G  11042|CLM] train=2.6200  mask=11.1%  norm=0.738  lr=2.43e-05  dt=  37.1ms  words=90,464,256
[E08   208/1548 G  11043|CLM] train=4.0355  mask=11.1%  norm=0.831  lr=2.43e-05  dt=  37.2ms  words=90,472,448
[E08   209/1548 G  11044|CLM] train=4.1221  mask=11.1%  norm=0.903  lr=2.43e-05  dt=  36.9ms  words=90,480,640
[E08   210/1548 G  11045|CLM] train=2.0971  mask=11.1%  norm=0.758  lr=2.43e-05  dt=  36.9ms  words=90,488,832
[E08   211/1548 G  11046|CLM] train=3.8910  mask=11.1%  norm=0.829  lr=2.43e-05  dt=  37.1ms  words=90,497,024
[E08   212/1548 G  11047|CLM] train=4.1574  mask=11.1%  norm=0.966  lr=2.43e-05  dt=  37.2ms  words=90,505,216
[E08   213/1548 G  11048|CLM] train=2.0778  mask=11.1%  norm=0.681  lr=2.43e-05  dt=  37.0ms  words=90,513,408
[E08   214/1548 G  11049|CLM] train=1.9357  mask=11.1%  norm=0.718  lr=2.42e-05  dt=  37.1ms  words=90,521,600
[E08   215/1548 G  11050|CLM] train=4.6036  mask=11.1%  norm=1.014  lr=2.42e-05  dt=  37.7ms  words=90,529,792
[E08   216/1548 G  11051|CLM] train=3.7265  mask=11.1%  norm=0.926  lr=2.42e-05  dt=  37.0ms  words=90,537,984
[E08   217/1548 G  11052|CLM] train=4.1831  mask=11.1%  norm=0.923  lr=2.42e-05  dt=  37.1ms  words=90,546,176
[E08   218/1548 G  11053|CLM] train=3.2129  mask=11.1%  norm=0.731  lr=2.42e-05  dt=  37.1ms  words=90,554,368
[E08   219/1548 G  11054|CLM] train=3.7836  mask=11.1%  norm=0.984  lr=2.42e-05  dt=  36.9ms  words=90,562,560
[E08   220/1548 G  11055|CLM] train=2.2072  mask=11.1%  norm=0.715  lr=2.42e-05  dt=  37.0ms  words=90,570,752
[E08   221/1548 G  11056|CLM] train=3.8571  mask=11.1%  norm=0.815  lr=2.41e-05  dt=  37.1ms  words=90,578,944
[E08   222/1548 G  11057|CLM] train=3.3085  mask=11.1%  norm=0.738  lr=2.41e-05  dt=  37.1ms  words=90,587,136
[E08   223/1548 G  11058|CLM] train=4.4050  mask=11.1%  norm=1.033  lr=2.41e-05  dt=  37.1ms  words=90,595,328
[E08   224/1548 G  11059|CLM] train=4.1484  mask=11.1%  norm=1.157  lr=2.41e-05  dt=  37.2ms  words=90,603,520
[E08   225/1548 G  11060|CLM] train=3.7340  mask=11.1%  norm=0.923  lr=2.41e-05  dt=  37.2ms  words=90,611,712
[E08   226/1548 G  11061|CLM] train=2.0951  mask=11.1%  norm=0.826  lr=2.41e-05  dt=  37.0ms  words=90,619,904
[E08   227/1548 G  11062|CLM] train=3.6423  mask=11.1%  norm=0.876  lr=2.41e-05  dt=  37.2ms  words=90,628,096
[E08   228/1548 G  11063|CLM] train=4.2423  mask=11.1%  norm=0.867  lr=2.40e-05  dt=  37.3ms  words=90,636,288
[E08   229/1548 G  11064|CLM] train=4.0665  mask=11.1%  norm=0.916  lr=2.40e-05  dt=  37.1ms  words=90,644,480
[E08   230/1548 G  11065|CLM] train=3.7504  mask=11.1%  norm=0.886  lr=2.40e-05  dt=  37.0ms  words=90,652,672
[E08   231/1548 G  11066|CLM] train=3.8747  mask=11.1%  norm=0.900  lr=2.40e-05  dt=  36.8ms  words=90,660,864
[E08   232/1548 G  11067|CLM] train=3.6478  mask=11.1%  norm=0.957  lr=2.40e-05  dt=  37.2ms  words=90,669,056
[E08   233/1548 G  11068|CLM] train=3.7865  mask=11.1%  norm=0.907  lr=2.40e-05  dt=  37.1ms  words=90,677,248
[E08   234/1548 G  11069|CLM] train=4.0721  mask=11.1%  norm=0.905  lr=2.40e-05  dt=  37.1ms  words=90,685,440
[E08   235/1548 G  11070|CLM] train=4.7000  mask=11.1%  norm=0.986  lr=2.40e-05  dt=  37.2ms  words=90,693,632
[E08   236/1548 G  11071|CLM] train=4.1570  mask=11.1%  norm=0.925  lr=2.39e-05  dt=  37.0ms  words=90,701,824
[E08   237/1548 G  11072|CLM] train=3.6244  mask=11.1%  norm=1.015  lr=2.39e-05  dt=  36.9ms  words=90,710,016
[E08   238/1548 G  11073|CLM] train=4.2191  mask=11.1%  norm=0.915  lr=2.39e-05  dt=  37.0ms  words=90,718,208
[E08   239/1548 G  11074|CLM] train=2.5253  mask=11.1%  norm=0.724  lr=2.39e-05  dt=  37.1ms  words=90,726,400
[E08   240/1548 G  11075|CLM] train=2.3181  mask=11.1%  norm=0.747  lr=2.39e-05  dt=  37.0ms  words=90,734,592
[E08   241/1548 G  11076|CLM] train=3.7771  mask=11.1%  norm=0.860  lr=2.39e-05  dt=  37.2ms  words=90,742,784
[E08   242/1548 G  11077|CLM] train=1.5937  mask=11.1%  norm=0.659  lr=2.39e-05  dt=  37.4ms  words=90,750,976
[E08   243/1548 G  11078|CLM] train=3.7244  mask=11.1%  norm=0.818  lr=2.38e-05  dt=  37.1ms  words=90,759,168
[E08   244/1548 G  11079|CLM] train=2.0744  mask=11.1%  norm=0.729  lr=2.38e-05  dt=  37.2ms  words=90,767,360
[E08   245/1548 G  11080|CLM] train=2.0008  mask=11.1%  norm=0.735  lr=2.38e-05  dt=  37.2ms  words=90,775,552
[E08   246/1548 G  11081|CLM] train=3.7581  mask=11.1%  norm=0.838  lr=2.38e-05  dt=  36.9ms  words=90,783,744
[E08   247/1548 G  11082|CLM] train=4.0658  mask=11.1%  norm=0.825  lr=2.38e-05  dt=  37.0ms  words=90,791,936
[E08   248/1548 G  11083|CLM] train=4.1552  mask=11.1%  norm=0.885  lr=2.38e-05  dt=  37.1ms  words=90,800,128
[E08   249/1548 G  11084|CLM] train=2.1577  mask=11.0%  norm=0.760  lr=2.38e-05  dt=  37.1ms  words=90,808,320
[E08   250/1548 G  11085|CLM] train=4.4143  mask=11.0%  norm=1.018  lr=2.38e-05  dt=  37.1ms  words=90,816,512
[E08   251/1548 G  11086|CLM] train=1.7994  mask=11.0%  norm=0.746  lr=2.37e-05  dt=  37.1ms  words=90,824,704
[E08   252/1548 G  11087|CLM] train=3.8574  mask=11.0%  norm=0.905  lr=2.37e-05  dt=  37.1ms  words=90,832,896
[E08   253/1548 G  11088|CLM] train=4.3196  mask=11.0%  norm=0.957  lr=2.37e-05  dt=  37.0ms  words=90,841,088
[E08   254/1548 G  11089|CLM] train=4.3628  mask=11.0%  norm=0.960  lr=2.37e-05  dt=  37.2ms  words=90,849,280
[E08   255/1548 G  11090|CLM] train=3.9328  mask=11.0%  norm=0.855  lr=2.37e-05  dt=  37.2ms  words=90,857,472
[E08   256/1548 G  11091|CLM] train=3.9009  mask=11.0%  norm=0.863  lr=2.37e-05  dt=  37.0ms  words=90,865,664
[E08   257/1548 G  11092|CLM] train=1.8938  mask=11.0%  norm=0.784  lr=2.37e-05  dt=  37.0ms  words=90,873,856
[E08   258/1548 G  11093|CLM] train=2.3160  mask=11.0%  norm=0.707  lr=2.36e-05  dt=  37.0ms  words=90,882,048
[E08   259/1548 G  11094|CLM] train=3.9783  mask=11.0%  norm=0.896  lr=2.36e-05  dt=  37.1ms  words=90,890,240
[E08   260/1548 G  11095|CLM] train=4.1292  mask=11.0%  norm=0.891  lr=2.36e-05  dt=  36.9ms  words=90,898,432
[E08   261/1548 G  11096|CLM] train=3.9938  mask=11.0%  norm=0.904  lr=2.36e-05  dt=  36.9ms  words=90,906,624
[E08   262/1548 G  11097|CLM] train=2.6611  mask=11.0%  norm=0.792  lr=2.36e-05  dt=  36.9ms  words=90,914,816
[E08   263/1548 G  11098|CLM] train=3.7353  mask=11.0%  norm=0.866  lr=2.36e-05  dt=  37.1ms  words=90,923,008
[E08   264/1548 G  11099|CLM] train=2.3013  mask=11.0%  norm=0.824  lr=2.36e-05  dt=  37.0ms  words=90,931,200
[E08   265/1548 G  11100|CLM] train=2.2472  mask=11.0%  norm=0.837  lr=2.36e-05  dt=  37.5ms  words=90,939,392
[E08   266/1548 G  11101|CLM] train=3.8662  mask=11.0%  norm=0.848  lr=2.35e-05  dt=  37.1ms  words=90,947,584
[E08   267/1548 G  11102|CLM] train=3.6460  mask=11.0%  norm=0.882  lr=2.35e-05  dt=  36.9ms  words=90,955,776
[E08   268/1548 G  11103|CLM] train=3.6079  mask=11.0%  norm=0.894  lr=2.35e-05  dt=  37.6ms  words=90,963,968
[E08   269/1548 G  11104|CLM] train=3.8445  mask=11.0%  norm=0.832  lr=2.35e-05  dt=  37.4ms  words=90,972,160
[E08   270/1548 G  11105|CLM] train=2.0338  mask=11.0%  norm=0.638  lr=2.35e-05  dt=  37.9ms  words=90,980,352
[E08   271/1548 G  11106|CLM] train=3.9479  mask=11.0%  norm=0.960  lr=2.35e-05  dt=  37.0ms  words=90,988,544
[E08   272/1548 G  11107|CLM] train=2.0355  mask=11.0%  norm=0.660  lr=2.35e-05  dt=  37.2ms  words=90,996,736
[E08   273/1548 G  11108|CLM] train=1.9563  mask=11.0%  norm=0.743  lr=2.34e-05  dt=  37.0ms  words=91,004,928
[E08   274/1548 G  11109|CLM] train=3.7835  mask=11.0%  norm=0.750  lr=2.34e-05  dt=  37.1ms  words=91,013,120
[E08   275/1548 G  11110|CLM] train=3.8005  mask=11.0%  norm=0.834  lr=2.34e-05  dt=  37.1ms  words=91,021,312
[E08   276/1548 G  11111|CLM] train=2.1438  mask=11.0%  norm=0.882  lr=2.34e-05  dt=  37.0ms  words=91,029,504
[E08   277/1548 G  11112|CLM] train=2.3857  mask=11.0%  norm=0.719  lr=2.34e-05  dt=  36.9ms  words=91,037,696
[E08   278/1548 G  11113|CLM] train=3.7003  mask=11.0%  norm=0.907  lr=2.34e-05  dt=  36.9ms  words=91,045,888
[E08   279/1548 G  11114|CLM] train=3.7565  mask=11.0%  norm=0.990  lr=2.34e-05  dt=  37.0ms  words=91,054,080
[E08   280/1548 G  11115|CLM] train=3.6572  mask=11.0%  norm=0.794  lr=2.34e-05  dt=  37.0ms  words=91,062,272
[E08   281/1548 G  11116|CLM] train=3.7309  mask=11.0%  norm=0.942  lr=2.33e-05  dt=  36.9ms  words=91,070,464
[E08   282/1548 G  11117|CLM] train=2.2726  mask=11.0%  norm=0.725  lr=2.33e-05  dt=  36.9ms  words=91,078,656
[E08   283/1548 G  11118|CLM] train=3.4901  mask=11.0%  norm=0.873  lr=2.33e-05  dt=  37.0ms  words=91,086,848
[E08   284/1548 G  11119|CLM] train=1.9560  mask=11.0%  norm=0.727  lr=2.33e-05  dt=  37.1ms  words=91,095,040
[E08   285/1548 G  11120|CLM] train=2.8772  mask=11.0%  norm=0.856  lr=2.33e-05  dt=  37.2ms  words=91,103,232
[E08   286/1548 G  11121|CLM] train=4.6081  mask=11.0%  norm=1.739  lr=2.33e-05  dt=  37.1ms  words=91,111,424
[E08   287/1548 G  11122|CLM] train=3.4615  mask=11.0%  norm=0.918  lr=2.33e-05  dt=  37.2ms  words=91,119,616
[E08   288/1548 G  11123|CLM] train=3.9818  mask=11.0%  norm=0.852  lr=2.33e-05  dt=  37.1ms  words=91,127,808
[E08   289/1548 G  11124|CLM] train=2.1812  mask=11.0%  norm=0.681  lr=2.32e-05  dt=  37.3ms  words=91,136,000
[E08   290/1548 G  11125|CLM] train=4.2027  mask=11.0%  norm=0.913  lr=2.32e-05  dt=  37.0ms  words=91,144,192
[E08   291/1548 G  11126|CLM] train=2.2531  mask=11.0%  norm=0.722  lr=2.32e-05  dt=  37.2ms  words=91,152,384
[E08   292/1548 G  11127|CLM] train=2.2493  mask=11.0%  norm=0.685  lr=2.32e-05  dt=  37.3ms  words=91,160,576
[E08   293/1548 G  11128|CLM] train=3.7366  mask=11.0%  norm=0.967  lr=2.32e-05  dt=  36.9ms  words=91,168,768
[E08   294/1548 G  11129|CLM] train=2.1530  mask=11.0%  norm=0.704  lr=2.32e-05  dt=  38.4ms  words=91,176,960
[E08   295/1548 G  11130|CLM] train=3.5661  mask=11.0%  norm=0.905  lr=2.32e-05  dt=  37.4ms  words=91,185,152
[E08   296/1548 G  11131|CLM] train=4.6360  mask=11.0%  norm=0.926  lr=2.31e-05  dt=  37.3ms  words=91,193,344
[E08   297/1548 G  11132|CLM] train=3.7840  mask=11.0%  norm=0.950  lr=2.31e-05  dt=  36.9ms  words=91,201,536
[E08   298/1548 G  11133|CLM] train=4.1620  mask=11.0%  norm=1.206  lr=2.31e-05  dt=  37.3ms  words=91,209,728
[E08   299/1548 G  11134|CLM] train=3.5427  mask=11.0%  norm=0.884  lr=2.31e-05  dt=  36.9ms  words=91,217,920
[E08   300/1548 G  11135|CLM] train=2.3441  mask=11.0%  norm=0.703  lr=2.31e-05  dt=  37.3ms  words=91,226,112
[E08   301/1548 G  11136|CLM] train=1.9379  mask=11.0%  norm=0.717  lr=2.31e-05  dt=  37.4ms  words=91,234,304
[E08   302/1548 G  11137|CLM] train=2.0935  mask=11.0%  norm=0.668  lr=2.31e-05  dt=  36.8ms  words=91,242,496
[E08   303/1548 G  11138|CLM] train=2.5108  mask=11.0%  norm=0.810  lr=2.31e-05  dt=  37.1ms  words=91,250,688
[E08   304/1548 G  11139|CLM] train=2.2107  mask=11.0%  norm=0.713  lr=2.30e-05  dt=  37.7ms  words=91,258,880
[E08   305/1548 G  11140|CLM] train=3.8405  mask=11.0%  norm=0.859  lr=2.30e-05  dt=  37.8ms  words=91,267,072
[E08   306/1548 G  11141|CLM] train=2.0486  mask=11.0%  norm=0.776  lr=2.30e-05  dt=  37.3ms  words=91,275,264
[E08   307/1548 G  11142|CLM] train=3.8044  mask=11.0%  norm=0.885  lr=2.30e-05  dt=  37.4ms  words=91,283,456
[E08   308/1548 G  11143|CLM] train=2.2855  mask=11.0%  norm=0.668  lr=2.30e-05  dt=  37.2ms  words=91,291,648
[E08   309/1548 G  11144|CLM] train=3.6231  mask=11.0%  norm=0.874  lr=2.30e-05  dt=  37.0ms  words=91,299,840
[E08   310/1548 G  11145|CLM] train=2.2478  mask=11.0%  norm=0.729  lr=2.30e-05  dt=  37.6ms  words=91,308,032
[E08   311/1548 G  11146|CLM] train=2.1366  mask=11.0%  norm=0.747  lr=2.30e-05  dt=  37.4ms  words=91,316,224
[E08   312/1548 G  11147|CLM] train=3.6939  mask=11.0%  norm=0.902  lr=2.29e-05  dt=  37.2ms  words=91,324,416
[E08   313/1548 G  11148|CLM] train=3.4896  mask=11.0%  norm=0.875  lr=2.29e-05  dt=  36.9ms  words=91,332,608
[E08   314/1548 G  11149|CLM] train=1.9407  mask=11.0%  norm=0.789  lr=2.29e-05  dt=  37.0ms  words=91,340,800
[E08   315/1548 G  11150|CLM] train=2.0912  mask=11.0%  norm=0.658  lr=2.29e-05  dt=  37.1ms  words=91,348,992
[E08   316/1548 G  11151|CLM] train=4.3634  mask=11.0%  norm=0.839  lr=2.29e-05  dt=  37.2ms  words=91,357,184
[E08   317/1548 G  11152|CLM] train=1.9972  mask=11.0%  norm=0.709  lr=2.29e-05  dt=  37.0ms  words=91,365,376
[E08   318/1548 G  11153|CLM] train=3.9953  mask=11.0%  norm=0.990  lr=2.29e-05  dt=  37.2ms  words=91,373,568
[E08   319/1548 G  11154|CLM] train=3.7566  mask=11.0%  norm=0.829  lr=2.29e-05  dt=  37.2ms  words=91,381,760
[E08   320/1548 G  11155|CLM] train=4.3039  mask=11.0%  norm=0.901  lr=2.28e-05  dt=  37.2ms  words=91,389,952
[E08   321/1548 G  11156|CLM] train=4.6269  mask=11.0%  norm=1.248  lr=2.28e-05  dt=  36.9ms  words=91,398,144
[E08   322/1548 G  11157|CLM] train=3.4424  mask=11.0%  norm=1.070  lr=2.28e-05  dt=  37.6ms  words=91,406,336
[E08   323/1548 G  11158|CLM] train=4.1257  mask=11.0%  norm=0.989  lr=2.28e-05  dt=  37.2ms  words=91,414,528
[E08   324/1548 G  11159|CLM] train=1.7707  mask=11.0%  norm=0.739  lr=2.28e-05  dt=  37.0ms  words=91,422,720
[E08   325/1548 G  11160|CLM] train=3.5944  mask=11.0%  norm=0.866  lr=2.28e-05  dt=  36.9ms  words=91,430,912
[E08   326/1548 G  11161|CLM] train=4.1991  mask=11.0%  norm=1.016  lr=2.28e-05  dt=  37.1ms  words=91,439,104
[E08   327/1548 G  11162|CLM] train=4.6410  mask=11.0%  norm=1.090  lr=2.28e-05  dt=  37.1ms  words=91,447,296
[E08   328/1548 G  11163|CLM] train=4.1010  mask=11.0%  norm=0.880  lr=2.27e-05  dt=  37.4ms  words=91,455,488
[E08   329/1548 G  11164|CLM] train=2.3916  mask=11.0%  norm=0.786  lr=2.27e-05  dt=  37.3ms  words=91,463,680
[E08   330/1548 G  11165|CLM] train=2.1486  mask=11.0%  norm=0.676  lr=2.27e-05  dt=  37.1ms  words=91,471,872
[E08   331/1548 G  11166|CLM] train=2.1775  mask=11.0%  norm=0.749  lr=2.27e-05  dt=  37.1ms  words=91,480,064
[E08   332/1548 G  11167|CLM] train=4.1865  mask=11.0%  norm=0.908  lr=2.27e-05  dt=  37.4ms  words=91,488,256
[E08   333/1548 G  11168|CLM] train=2.3800  mask=11.0%  norm=0.908  lr=2.27e-05  dt=  36.9ms  words=91,496,448
[E08   334/1548 G  11169|CLM] train=3.6583  mask=11.0%  norm=0.825  lr=2.27e-05  dt=  37.3ms  words=91,504,640
[E08   335/1548 G  11170|CLM] train=4.1502  mask=11.0%  norm=0.995  lr=2.27e-05  dt=  37.4ms  words=91,512,832
[E08   336/1548 G  11171|CLM] train=4.7407  mask=11.0%  norm=1.027  lr=2.26e-05  dt=  37.4ms  words=91,521,024
[E08   337/1548 G  11172|CLM] train=4.0276  mask=11.0%  norm=0.890  lr=2.26e-05  dt=  37.2ms  words=91,529,216
[E08   338/1548 G  11173|CLM] train=3.8933  mask=11.0%  norm=0.967  lr=2.26e-05  dt=  37.3ms  words=91,537,408
[E08   339/1548 G  11174|CLM] train=1.9166  mask=11.0%  norm=0.702  lr=2.26e-05  dt=  37.3ms  words=91,545,600
[E08   340/1548 G  11175|CLM] train=2.0049  mask=11.0%  norm=0.669  lr=2.26e-05  dt=  37.4ms  words=91,553,792
[E08   341/1548 G  11176|CLM] train=2.8406  mask=11.0%  norm=0.776  lr=2.26e-05  dt=  37.2ms  words=91,561,984
[E08   342/1548 G  11177|CLM] train=3.9314  mask=11.0%  norm=1.478  lr=2.26e-05  dt=  37.2ms  words=91,570,176
[E08   343/1548 G  11178|CLM] train=4.4239  mask=11.0%  norm=0.888  lr=2.26e-05  dt=  37.1ms  words=91,578,368
[E08   344/1548 G  11179|CLM] train=3.7365  mask=11.0%  norm=0.840  lr=2.25e-05  dt=  37.2ms  words=91,586,560
[E08   345/1548 G  11180|CLM] train=1.9206  mask=11.0%  norm=0.746  lr=2.25e-05  dt=  36.9ms  words=91,594,752
[E08   346/1548 G  11181|CLM] train=3.5426  mask=11.0%  norm=0.836  lr=2.25e-05  dt=  36.9ms  words=91,602,944
[E08   347/1548 G  11182|CLM] train=3.6363  mask=11.0%  norm=0.909  lr=2.25e-05  dt=  36.9ms  words=91,611,136
[E08   348/1548 G  11183|CLM] train=4.2977  mask=11.0%  norm=0.898  lr=2.25e-05  dt=  37.2ms  words=91,619,328
[E08   349/1548 G  11184|CLM] train=3.5486  mask=11.0%  norm=0.825  lr=2.25e-05  dt=  37.1ms  words=91,627,520
[E08   350/1548 G  11185|CLM] train=3.6212  mask=11.0%  norm=0.893  lr=2.25e-05  dt=  37.2ms  words=91,635,712
[E08   351/1548 G  11186|CLM] train=3.8675  mask=11.0%  norm=0.840  lr=2.25e-05  dt=  37.1ms  words=91,643,904
[E08   352/1548 G  11187|CLM] train=3.9535  mask=11.0%  norm=0.978  lr=2.24e-05  dt=  37.0ms  words=91,652,096
[E08   353/1548 G  11188|CLM] train=4.4448  mask=11.0%  norm=0.908  lr=2.24e-05  dt=  37.0ms  words=91,660,288
[E08   354/1548 G  11189|CLM] train=4.4737  mask=11.0%  norm=0.878  lr=2.24e-05  dt=  37.3ms  words=91,668,480
[E08   355/1548 G  11190|CLM] train=3.6494  mask=11.0%  norm=0.862  lr=2.24e-05  dt=  37.1ms  words=91,676,672
[E08   356/1548 G  11191|CLM] train=3.5411  mask=11.0%  norm=0.923  lr=2.24e-05  dt=  37.0ms  words=91,684,864
[E08   357/1548 G  11192|CLM] train=3.4299  mask=11.0%  norm=0.798  lr=2.24e-05  dt=  37.0ms  words=91,693,056
[E08   358/1548 G  11193|CLM] train=3.6823  mask=11.0%  norm=0.903  lr=2.24e-05  dt=  37.1ms  words=91,701,248
[E08   359/1548 G  11194|CLM] train=1.7229  mask=11.0%  norm=0.673  lr=2.24e-05  dt=  36.9ms  words=91,709,440
[E08   360/1548 G  11195|CLM] train=2.1215  mask=11.0%  norm=0.755  lr=2.23e-05  dt=  37.0ms  words=91,717,632
[E08   361/1548 G  11196|CLM] train=2.2580  mask=11.0%  norm=0.691  lr=2.23e-05  dt=  37.1ms  words=91,725,824
[E08   362/1548 G  11197|CLM] train=2.0248  mask=11.0%  norm=0.750  lr=2.23e-05  dt=  37.1ms  words=91,734,016
[E08   363/1548 G  11198|CLM] train=1.9602  mask=11.0%  norm=0.773  lr=2.23e-05  dt=  37.2ms  words=91,742,208
[E08   364/1548 G  11199|CLM] train=1.9556  mask=11.0%  norm=0.767  lr=2.23e-05  dt=  37.5ms  words=91,750,400
[E08   365/1548 G  11200|CLM] train=2.2031  mask=11.0%  norm=0.703  lr=2.23e-05  dt=  37.4ms  words=91,758,592
[E08   366/1548 G  11201|CLM] train=2.9691  mask=11.0%  norm=0.754  lr=2.23e-05  dt=  36.9ms  words=91,766,784
[E08   367/1548 G  11202|CLM] train=2.2547  mask=11.0%  norm=0.696  lr=2.23e-05  dt=  36.9ms  words=91,774,976
[E08   368/1548 G  11203|CLM] train=3.1938  mask=11.0%  norm=0.871  lr=2.22e-05  dt=  37.1ms  words=91,783,168
[E08   369/1548 G  11204|CLM] train=4.0246  mask=11.0%  norm=0.838  lr=2.22e-05  dt=  36.9ms  words=91,791,360
[E08   370/1548 G  11205|CLM] train=2.0466  mask=11.0%  norm=0.702  lr=2.22e-05  dt=  37.1ms  words=91,799,552
[E08   371/1548 G  11206|CLM] train=4.0434  mask=11.0%  norm=1.163  lr=2.22e-05  dt=  37.0ms  words=91,807,744
[E08   372/1548 G  11207|CLM] train=3.8523  mask=11.0%  norm=0.821  lr=2.22e-05  dt=  37.0ms  words=91,815,936
[E08   373/1548 G  11208|CLM] train=2.0971  mask=10.9%  norm=0.677  lr=2.22e-05  dt=  36.9ms  words=91,824,128
[E08   374/1548 G  11209|CLM] train=4.7811  mask=10.9%  norm=1.257  lr=2.22e-05  dt=  37.1ms  words=91,832,320
[E08   375/1548 G  11210|CLM] train=4.3929  mask=10.9%  norm=0.895  lr=2.22e-05  dt=  37.2ms  words=91,840,512
[E08   376/1548 G  11211|CLM] train=3.8978  mask=10.9%  norm=0.908  lr=2.21e-05  dt=  36.9ms  words=91,848,704
[E08   377/1548 G  11212|CLM] train=2.2781  mask=10.9%  norm=0.775  lr=2.21e-05  dt=  37.3ms  words=91,856,896
[E08   378/1548 G  11213|CLM] train=4.6012  mask=10.9%  norm=0.983  lr=2.21e-05  dt=  37.2ms  words=91,865,088
[E08   379/1548 G  11214|CLM] train=2.3133  mask=10.9%  norm=0.720  lr=2.21e-05  dt=  36.9ms  words=91,873,280
[E08   380/1548 G  11215|CLM] train=3.1678  mask=10.9%  norm=0.846  lr=2.21e-05  dt=  37.0ms  words=91,881,472
[E08   381/1548 G  11216|CLM] train=4.0759  mask=10.9%  norm=0.898  lr=2.21e-05  dt=  36.9ms  words=91,889,664
[E08   382/1548 G  11217|CLM] train=3.8657  mask=10.9%  norm=0.924  lr=2.21e-05  dt=  37.0ms  words=91,897,856
[E08   383/1548 G  11218|CLM] train=4.0193  mask=10.9%  norm=0.846  lr=2.21e-05  dt=  36.8ms  words=91,906,048
[E08   384/1548 G  11219|CLM] train=4.0060  mask=10.9%  norm=0.922  lr=2.21e-05  dt=  36.9ms  words=91,914,240
[E08   385/1548 G  11220|CLM] train=3.9819  mask=10.9%  norm=0.875  lr=2.20e-05  dt=  36.9ms  words=91,922,432
[E08   386/1548 G  11221|CLM] train=3.3220  mask=10.9%  norm=0.782  lr=2.20e-05  dt=  37.0ms  words=91,930,624
[E08   387/1548 G  11222|CLM] train=4.0599  mask=10.9%  norm=0.878  lr=2.20e-05  dt=  36.8ms  words=91,938,816
[E08   388/1548 G  11223|CLM] train=2.3296  mask=10.9%  norm=0.740  lr=2.20e-05  dt=  36.8ms  words=91,947,008
[E08   389/1548 G  11224|CLM] train=1.9622  mask=10.9%  norm=0.704  lr=2.20e-05  dt=  37.0ms  words=91,955,200
[E08   390/1548 G  11225|CLM] train=4.0221  mask=10.9%  norm=0.845  lr=2.20e-05  dt=  37.2ms  words=91,963,392
[E08   391/1548 G  11226|CLM] train=4.3503  mask=10.9%  norm=1.019  lr=2.20e-05  dt=  37.0ms  words=91,971,584
[E08   392/1548 G  11227|CLM] train=3.5483  mask=10.9%  norm=0.879  lr=2.20e-05  dt=  37.1ms  words=91,979,776
[E08   393/1548 G  11228|CLM] train=4.5168  mask=10.9%  norm=0.954  lr=2.19e-05  dt=  37.1ms  words=91,987,968
[E08   394/1548 G  11229|CLM] train=4.1686  mask=10.9%  norm=0.971  lr=2.19e-05  dt=  36.9ms  words=91,996,160
[E08   395/1548 G  11230|CLM] train=3.9452  mask=10.9%  norm=0.993  lr=2.19e-05  dt=  36.9ms  words=92,004,352
[E08   396/1548 G  11231|CLM] train=4.0500  mask=10.9%  norm=0.999  lr=2.19e-05  dt=  37.0ms  words=92,012,544
[E08   397/1548 G  11232|CLM] train=4.0914  mask=10.9%  norm=0.917  lr=2.19e-05  dt=  37.1ms  words=92,020,736
[E08   398/1548 G  11233|CLM] train=2.1582  mask=10.9%  norm=0.841  lr=2.19e-05  dt=  36.9ms  words=92,028,928
[E08   399/1548 G  11234|CLM] train=2.3035  mask=10.9%  norm=0.658  lr=2.19e-05  dt=  36.8ms  words=92,037,120
[E08   400/1548 G  11235|CLM] train=2.0578  mask=10.9%  norm=0.705  lr=2.19e-05  dt=  36.9ms  words=92,045,312
[E08   401/1548 G  11236|CLM] train=1.8621  mask=10.9%  norm=0.836  lr=2.19e-05  dt=  36.9ms  words=92,053,504
[E08   402/1548 G  11237|CLM] train=3.6160  mask=10.9%  norm=1.016  lr=2.18e-05  dt=  37.3ms  words=92,061,696
[E08   403/1548 G  11238|CLM] train=5.2481  mask=10.9%  norm=1.193  lr=2.18e-05  dt=  37.1ms  words=92,069,888
[E08   404/1548 G  11239|CLM] train=3.0168  mask=10.9%  norm=0.764  lr=2.18e-05  dt=  37.1ms  words=92,078,080
[E08   405/1548 G  11240|CLM] train=3.7184  mask=10.9%  norm=0.904  lr=2.18e-05  dt=  37.0ms  words=92,086,272
[E08   406/1548 G  11241|CLM] train=2.2605  mask=10.9%  norm=0.710  lr=2.18e-05  dt=  37.0ms  words=92,094,464
[E08   407/1548 G  11242|CLM] train=3.6745  mask=10.9%  norm=0.831  lr=2.18e-05  dt=  37.0ms  words=92,102,656
[E08   408/1548 G  11243|CLM] train=2.4991  mask=10.9%  norm=0.716  lr=2.18e-05  dt=  37.1ms  words=92,110,848
[E08   409/1548 G  11244|CLM] train=2.1136  mask=10.9%  norm=0.686  lr=2.18e-05  dt=  36.8ms  words=92,119,040
[E08   410/1548 G  11245|CLM] train=3.9493  mask=10.9%  norm=0.861  lr=2.17e-05  dt=  36.9ms  words=92,127,232
[E08   411/1548 G  11246|CLM] train=2.0321  mask=10.9%  norm=0.681  lr=2.17e-05  dt=  37.0ms  words=92,135,424
[E08   412/1548 G  11247|CLM] train=3.8568  mask=10.9%  norm=0.928  lr=2.17e-05  dt=  37.0ms  words=92,143,616
[E08   413/1548 G  11248|CLM] train=2.1024  mask=10.9%  norm=0.770  lr=2.17e-05  dt=  36.8ms  words=92,151,808
[E08   414/1548 G  11249|CLM] train=4.8241  mask=10.9%  norm=1.079  lr=2.17e-05  dt=  36.9ms  words=92,160,000
[E08   415/1548 G  11250|CLM] train=3.6082  mask=10.9%  norm=0.830  lr=2.17e-05  dt=  36.9ms  words=92,168,192
[E08   416/1548 G  11251|CLM] train=4.1275  mask=10.9%  norm=0.955  lr=2.17e-05  dt=  37.3ms  words=92,176,384
[E08   417/1548 G  11252|CLM] train=2.2425  mask=10.9%  norm=0.688  lr=2.17e-05  dt=  37.5ms  words=92,184,576
[E08   418/1548 G  11253|CLM] train=3.5889  mask=10.9%  norm=1.026  lr=2.17e-05  dt=  38.1ms  words=92,192,768
[E08   419/1548 G  11254|CLM] train=3.5130  mask=10.9%  norm=0.764  lr=2.16e-05  dt=  41.1ms  words=92,200,960
[E08   420/1548 G  11255|CLM] train=2.0873  mask=10.9%  norm=0.699  lr=2.16e-05  dt=  37.9ms  words=92,209,152
[E08   421/1548 G  11256|CLM] train=1.9457  mask=10.9%  norm=0.797  lr=2.16e-05  dt=  39.3ms  words=92,217,344
[E08   422/1548 G  11257|CLM] train=4.1044  mask=10.9%  norm=0.977  lr=2.16e-05  dt=  43.0ms  words=92,225,536
[E08   423/1548 G  11258|CLM] train=4.4121  mask=10.9%  norm=0.876  lr=2.16e-05  dt=  39.6ms  words=92,233,728
[E08   424/1548 G  11259|CLM] train=3.5456  mask=10.9%  norm=0.908  lr=2.16e-05  dt=  37.7ms  words=92,241,920
[E08   425/1548 G  11260|CLM] train=2.1189  mask=10.9%  norm=0.770  lr=2.16e-05  dt=  37.8ms  words=92,250,112
[E08   426/1548 G  11261|CLM] train=2.5348  mask=10.9%  norm=0.782  lr=2.16e-05  dt=  37.7ms  words=92,258,304
[E08   427/1548 G  11262|CLM] train=3.9373  mask=10.9%  norm=0.933  lr=2.15e-05  dt=  37.3ms  words=92,266,496
[E08   428/1548 G  11263|CLM] train=4.8269  mask=10.9%  norm=0.960  lr=2.15e-05  dt=  37.2ms  words=92,274,688
[E08   429/1548 G  11264|CLM] train=4.1874  mask=10.9%  norm=0.935  lr=2.15e-05  dt=  37.2ms  words=92,282,880
[E08   430/1548 G  11265|CLM] train=4.3969  mask=10.9%  norm=0.947  lr=2.15e-05  dt=  37.1ms  words=92,291,072
[E08   431/1548 G  11266|CLM] train=2.6425  mask=10.9%  norm=0.772  lr=2.15e-05  dt=  36.9ms  words=92,299,264
[E08   432/1548 G  11267|CLM] train=4.2584  mask=10.9%  norm=1.158  lr=2.15e-05  dt=  37.0ms  words=92,307,456
[E08   433/1548 G  11268|CLM] train=2.2331  mask=10.9%  norm=0.713  lr=2.15e-05  dt=  37.0ms  words=92,315,648
[E08   434/1548 G  11269|CLM] train=3.6782  mask=10.9%  norm=0.822  lr=2.15e-05  dt=  37.5ms  words=92,323,840
[E08   435/1548 G  11270|CLM] train=1.9351  mask=10.9%  norm=0.729  lr=2.15e-05  dt=  37.2ms  words=92,332,032
[E08   436/1548 G  11271|CLM] train=2.6126  mask=10.9%  norm=0.716  lr=2.14e-05  dt=  37.0ms  words=92,340,224
[E08   437/1548 G  11272|CLM] train=3.3671  mask=10.9%  norm=0.792  lr=2.14e-05  dt=  37.3ms  words=92,348,416
[E08   438/1548 G  11273|CLM] train=1.7306  mask=10.9%  norm=0.644  lr=2.14e-05  dt=  37.9ms  words=92,356,608
[E08   439/1548 G  11274|CLM] train=3.9780  mask=10.9%  norm=0.939  lr=2.14e-05  dt=  37.2ms  words=92,364,800
[E08   440/1548 G  11275|CLM] train=4.4789  mask=10.9%  norm=0.930  lr=2.14e-05  dt=  37.1ms  words=92,372,992
[E08   441/1548 G  11276|CLM] train=3.9661  mask=10.9%  norm=0.879  lr=2.14e-05  dt=  37.1ms  words=92,381,184
[E08   442/1548 G  11277|CLM] train=3.3558  mask=10.9%  norm=0.813  lr=2.14e-05  dt=  37.3ms  words=92,389,376
[E08   443/1548 G  11278|CLM] train=2.1574  mask=10.9%  norm=0.722  lr=2.14e-05  dt=  37.7ms  words=92,397,568
[E08   444/1548 G  11279|CLM] train=3.5984  mask=10.9%  norm=0.955  lr=2.14e-05  dt=  37.9ms  words=92,405,760
[E08   445/1548 G  11280|CLM] train=2.3394  mask=10.9%  norm=0.711  lr=2.13e-05  dt=  38.3ms  words=92,413,952
[E08   446/1548 G  11281|CLM] train=3.8306  mask=10.9%  norm=1.006  lr=2.13e-05  dt=  36.9ms  words=92,422,144
[E08   447/1548 G  11282|CLM] train=2.0752  mask=10.9%  norm=0.759  lr=2.13e-05  dt=  39.1ms  words=92,430,336
[E08   448/1548 G  11283|CLM] train=3.7148  mask=10.9%  norm=0.763  lr=2.13e-05  dt=  39.0ms  words=92,438,528
[E08   449/1548 G  11284|CLM] train=3.3514  mask=10.9%  norm=0.817  lr=2.13e-05  dt=  41.8ms  words=92,446,720
[E08   450/1548 G  11285|CLM] train=4.0054  mask=10.9%  norm=0.880  lr=2.13e-05  dt=  38.8ms  words=92,454,912
[E08   451/1548 G  11286|CLM] train=2.2405  mask=10.9%  norm=0.709  lr=2.13e-05  dt=  43.3ms  words=92,463,104
[E08   452/1548 G  11287|CLM] train=3.8293  mask=10.9%  norm=0.910  lr=2.13e-05  dt=  38.7ms  words=92,471,296
[E08   453/1548 G  11288|CLM] train=3.9271  mask=10.9%  norm=0.919  lr=2.12e-05  dt=  36.9ms  words=92,479,488
[E08   454/1548 G  11289|CLM] train=2.2580  mask=10.9%  norm=0.707  lr=2.12e-05  dt=  37.4ms  words=92,487,680
[E08   455/1548 G  11290|CLM] train=4.1124  mask=10.9%  norm=0.900  lr=2.12e-05  dt=  37.4ms  words=92,495,872
[E08   456/1548 G  11291|CLM] train=4.2558  mask=10.9%  norm=1.046  lr=2.12e-05  dt=  37.5ms  words=92,504,064
[E08   457/1548 G  11292|CLM] train=3.9004  mask=10.9%  norm=0.952  lr=2.12e-05  dt=  49.6ms  words=92,512,256
[E08   458/1548 G  11293|CLM] train=1.9952  mask=10.9%  norm=0.687  lr=2.12e-05  dt=  45.7ms  words=92,520,448
[E08   459/1548 G  11294|CLM] train=2.5270  mask=10.9%  norm=0.730  lr=2.12e-05  dt=  42.6ms  words=92,528,640
[E08   460/1548 G  11295|CLM] train=2.1961  mask=10.9%  norm=0.641  lr=2.12e-05  dt=  37.3ms  words=92,536,832
[E08   461/1548 G  11296|CLM] train=3.6677  mask=10.9%  norm=0.791  lr=2.12e-05  dt=  37.5ms  words=92,545,024
[E08   462/1548 G  11297|CLM] train=4.1106  mask=10.9%  norm=0.937  lr=2.11e-05  dt=  37.2ms  words=92,553,216
[E08   463/1548 G  11298|CLM] train=2.2761  mask=10.9%  norm=0.808  lr=2.11e-05  dt=  37.1ms  words=92,561,408
[E08   464/1548 G  11299|CLM] train=2.1864  mask=10.9%  norm=0.719  lr=2.11e-05  dt=  36.9ms  words=92,569,600
[E08   465/1548 G  11300|CLM] train=2.0125  mask=10.9%  norm=0.755  lr=2.11e-05  dt=  37.1ms  words=92,577,792
[E08   466/1548 G  11301|CLM] train=3.9841  mask=10.9%  norm=0.894  lr=2.11e-05  dt=  37.0ms  words=92,585,984
[E08   467/1548 G  11302|CLM] train=4.1821  mask=10.9%  norm=0.975  lr=2.11e-05  dt=  36.9ms  words=92,594,176
[E08   468/1548 G  11303|CLM] train=4.4936  mask=10.9%  norm=0.914  lr=2.11e-05  dt=  37.0ms  words=92,602,368
[E08   469/1548 G  11304|CLM] train=2.1876  mask=10.9%  norm=0.731  lr=2.11e-05  dt=  36.9ms  words=92,610,560
[E08   470/1548 G  11305|CLM] train=4.1202  mask=10.9%  norm=0.978  lr=2.11e-05  dt=  37.1ms  words=92,618,752
[E08   471/1548 G  11306|CLM] train=2.1865  mask=10.9%  norm=0.724  lr=2.10e-05  dt=  36.8ms  words=92,626,944
[E08   472/1548 G  11307|CLM] train=4.0616  mask=10.9%  norm=1.051  lr=2.10e-05  dt=  37.0ms  words=92,635,136
[E08   473/1548 G  11308|CLM] train=4.0607  mask=10.9%  norm=1.060  lr=2.10e-05  dt=  37.0ms  words=92,643,328
[E08   474/1548 G  11309|CLM] train=2.4248  mask=10.9%  norm=0.716  lr=2.10e-05  dt=  36.8ms  words=92,651,520
[E08   475/1548 G  11310|CLM] train=2.3420  mask=10.9%  norm=0.905  lr=2.10e-05  dt=  36.7ms  words=92,659,712
[E08   476/1548 G  11311|CLM] train=2.2796  mask=10.9%  norm=0.768  lr=2.10e-05  dt=  37.1ms  words=92,667,904
[E08   477/1548 G  11312|CLM] train=4.1875  mask=10.9%  norm=0.913  lr=2.10e-05  dt=  36.7ms  words=92,676,096
[E08   478/1548 G  11313|CLM] train=3.9668  mask=10.9%  norm=0.958  lr=2.10e-05  dt=  36.9ms  words=92,684,288
[E08   479/1548 G  11314|CLM] train=3.7851  mask=10.9%  norm=0.932  lr=2.10e-05  dt=  36.8ms  words=92,692,480
[E08   480/1548 G  11315|CLM] train=1.7796  mask=10.9%  norm=0.685  lr=2.09e-05  dt=  36.9ms  words=92,700,672
[E08   481/1548 G  11316|CLM] train=4.1299  mask=10.9%  norm=0.898  lr=2.09e-05  dt=  36.8ms  words=92,708,864
[E08   482/1548 G  11317|CLM] train=1.9591  mask=10.9%  norm=0.822  lr=2.09e-05  dt=  36.9ms  words=92,717,056
[E08   483/1548 G  11318|CLM] train=2.5986  mask=10.9%  norm=0.752  lr=2.09e-05  dt=  36.8ms  words=92,725,248
[E08   484/1548 G  11319|CLM] train=2.6199  mask=10.9%  norm=0.771  lr=2.09e-05  dt=  36.7ms  words=92,733,440
[E08   485/1548 G  11320|CLM] train=2.3660  mask=10.9%  norm=0.699  lr=2.09e-05  dt=  36.8ms  words=92,741,632
[E08   486/1548 G  11321|CLM] train=4.2268  mask=10.9%  norm=1.101  lr=2.09e-05  dt=  36.8ms  words=92,749,824
[E08   487/1548 G  11322|CLM] train=4.3438  mask=10.9%  norm=0.999  lr=2.09e-05  dt=  36.8ms  words=92,758,016
[E08   488/1548 G  11323|CLM] train=2.1318  mask=10.9%  norm=0.646  lr=2.09e-05  dt=  36.9ms  words=92,766,208
[E08   489/1548 G  11324|CLM] train=4.6322  mask=10.9%  norm=0.935  lr=2.08e-05  dt=  36.7ms  words=92,774,400
[E08   490/1548 G  11325|CLM] train=1.9722  mask=10.9%  norm=0.712  lr=2.08e-05  dt=  36.9ms  words=92,782,592
[E08   491/1548 G  11326|CLM] train=2.0460  mask=10.9%  norm=0.759  lr=2.08e-05  dt=  36.8ms  words=92,790,784
[E08   492/1548 G  11327|CLM] train=2.1043  mask=10.9%  norm=0.750  lr=2.08e-05  dt=  36.7ms  words=92,798,976
[E08   493/1548 G  11328|CLM] train=3.6913  mask=10.9%  norm=0.986  lr=2.08e-05  dt=  36.7ms  words=92,807,168
[E08   494/1548 G  11329|CLM] train=3.7258  mask=10.9%  norm=0.797  lr=2.08e-05  dt=  36.8ms  words=92,815,360
[E08   495/1548 G  11330|CLM] train=3.4454  mask=10.9%  norm=0.875  lr=2.08e-05  dt=  37.0ms  words=92,823,552
[E08   496/1548 G  11331|CLM] train=3.8037  mask=10.9%  norm=0.787  lr=2.08e-05  dt=  37.0ms  words=92,831,744
[E08   497/1548 G  11332|CLM] train=2.3851  mask=10.8%  norm=0.868  lr=2.08e-05  dt=  36.8ms  words=92,839,936
[E08   498/1548 G  11333|CLM] train=3.6359  mask=10.8%  norm=0.817  lr=2.07e-05  dt=  36.9ms  words=92,848,128
[E08   499/1548 G  11334|CLM] train=3.6560  mask=10.8%  norm=0.895  lr=2.07e-05  dt=  37.0ms  words=92,856,320
[E08   500/1548 G  11335|CLM] train=4.6213  mask=10.8%  norm=1.162  lr=2.07e-05  dt=  36.8ms  words=92,864,512
[E08   501/1548 G  11336|CLM] train=4.8032  mask=10.8%  norm=0.922  lr=2.07e-05  dt=  36.8ms  words=92,872,704
[E08   502/1548 G  11337|CLM] train=2.3958  mask=10.8%  norm=0.757  lr=2.07e-05  dt=  36.9ms  words=92,880,896
[E08   503/1548 G  11338|CLM] train=3.6405  mask=10.8%  norm=0.797  lr=2.07e-05  dt=  36.9ms  words=92,889,088
[E08   504/1548 G  11339|CLM] train=3.9780  mask=10.8%  norm=1.075  lr=2.07e-05  dt=  37.0ms  words=92,897,280
[E08   505/1548 G  11340|CLM] train=2.3513  mask=10.8%  norm=0.758  lr=2.07e-05  dt=  36.9ms  words=92,905,472
[E08   506/1548 G  11341|CLM] train=3.3556  mask=10.8%  norm=0.785  lr=2.07e-05  dt=  36.9ms  words=92,913,664
[E08   507/1548 G  11342|CLM] train=4.2568  mask=10.8%  norm=1.003  lr=2.07e-05  dt=  37.3ms  words=92,921,856
[E08   508/1548 G  11343|CLM] train=3.7609  mask=10.8%  norm=0.897  lr=2.06e-05  dt=  37.2ms  words=92,930,048
[E08   509/1548 G  11344|CLM] train=3.7623  mask=10.8%  norm=0.848  lr=2.06e-05  dt=  37.1ms  words=92,938,240
[E08   510/1548 G  11345|CLM] train=4.4548  mask=10.8%  norm=0.993  lr=2.06e-05  dt=  36.9ms  words=92,946,432
[E08   511/1548 G  11346|CLM] train=2.2428  mask=10.8%  norm=1.130  lr=2.06e-05  dt=  37.0ms  words=92,954,624
[E08   512/1548 G  11347|CLM] train=4.0999  mask=10.8%  norm=0.859  lr=2.06e-05  dt=  37.0ms  words=92,962,816
[E08   513/1548 G  11348|CLM] train=4.0467  mask=10.8%  norm=0.839  lr=2.06e-05  dt=  36.9ms  words=92,971,008
[E08   514/1548 G  11349|CLM] train=4.1224  mask=10.8%  norm=0.850  lr=2.06e-05  dt=  36.8ms  words=92,979,200
[E08   515/1548 G  11350|CLM] train=2.2628  mask=10.8%  norm=0.708  lr=2.06e-05  dt=  36.9ms  words=92,987,392
[E08   516/1548 G  11351|CLM] train=3.8481  mask=10.8%  norm=0.955  lr=2.06e-05  dt=  36.9ms  words=92,995,584
[E08   517/1548 G  11352|CLM] train=4.5220  mask=10.8%  norm=1.068  lr=2.05e-05  dt=  36.9ms  words=93,003,776
[E08   518/1548 G  11353|CLM] train=3.6430  mask=10.8%  norm=0.913  lr=2.05e-05  dt=  36.9ms  words=93,011,968
[E08   519/1548 G  11354|CLM] train=3.9651  mask=10.8%  norm=0.962  lr=2.05e-05  dt=  37.0ms  words=93,020,160
[E08   520/1548 G  11355|CLM] train=3.6647  mask=10.8%  norm=0.872  lr=2.05e-05  dt=  36.9ms  words=93,028,352
[E08   521/1548 G  11356|CLM] train=4.2003  mask=10.8%  norm=0.865  lr=2.05e-05  dt=  36.7ms  words=93,036,544
[E08   522/1548 G  11357|CLM] train=3.7279  mask=10.8%  norm=0.929  lr=2.05e-05  dt=  36.6ms  words=93,044,736
[E08   523/1548 G  11358|CLM] train=3.4469  mask=10.8%  norm=0.852  lr=2.05e-05  dt=  36.9ms  words=93,052,928
[E08   524/1548 G  11359|CLM] train=1.9775  mask=10.8%  norm=0.804  lr=2.05e-05  dt=  37.0ms  words=93,061,120
[E08   525/1548 G  11360|CLM] train=2.2141  mask=10.8%  norm=0.693  lr=2.05e-05  dt=  36.8ms  words=93,069,312
[E08   526/1548 G  11361|CLM] train=2.1527  mask=10.8%  norm=0.669  lr=2.04e-05  dt=  36.7ms  words=93,077,504
[E08   527/1548 G  11362|CLM] train=4.2315  mask=10.8%  norm=0.987  lr=2.04e-05  dt=  37.1ms  words=93,085,696
[E08   528/1548 G  11363|CLM] train=2.1475  mask=10.8%  norm=0.704  lr=2.04e-05  dt=  36.7ms  words=93,093,888
[E08   529/1548 G  11364|CLM] train=3.7973  mask=10.8%  norm=0.879  lr=2.04e-05  dt=  36.9ms  words=93,102,080
[E08   530/1548 G  11365|CLM] train=3.3613  mask=10.8%  norm=1.254  lr=2.04e-05  dt=  37.0ms  words=93,110,272
[E08   531/1548 G  11366|CLM] train=3.9709  mask=10.8%  norm=0.898  lr=2.04e-05  dt=  37.0ms  words=93,118,464
[E08   532/1548 G  11367|CLM] train=4.3766  mask=10.8%  norm=0.897  lr=2.04e-05  dt=  36.8ms  words=93,126,656
[E08   533/1548 G  11368|CLM] train=2.2026  mask=10.8%  norm=0.708  lr=2.04e-05  dt=  37.0ms  words=93,134,848
[E08   534/1548 G  11369|CLM] train=3.6702  mask=10.8%  norm=0.771  lr=2.04e-05  dt=  36.9ms  words=93,143,040
[E08   535/1548 G  11370|CLM] train=4.6384  mask=10.8%  norm=1.019  lr=2.04e-05  dt=  37.5ms  words=93,151,232
[E08   536/1548 G  11371|CLM] train=2.1318  mask=10.8%  norm=0.687  lr=2.03e-05  dt=  37.1ms  words=93,159,424
[E08   537/1548 G  11372|CLM] train=1.9625  mask=10.8%  norm=0.741  lr=2.03e-05  dt=  36.9ms  words=93,167,616
[E08   538/1548 G  11373|CLM] train=3.7955  mask=10.8%  norm=0.911  lr=2.03e-05  dt=  37.2ms  words=93,175,808
[E08   539/1548 G  11374|CLM] train=2.4595  mask=10.8%  norm=0.773  lr=2.03e-05  dt=  36.7ms  words=93,184,000
[E08   540/1548 G  11375|CLM] train=3.4696  mask=10.8%  norm=0.903  lr=2.03e-05  dt=  37.0ms  words=93,192,192
[E08   541/1548 G  11376|CLM] train=4.3282  mask=10.8%  norm=1.018  lr=2.03e-05  dt=  36.9ms  words=93,200,384
[E08   542/1548 G  11377|CLM] train=3.2339  mask=10.8%  norm=0.806  lr=2.03e-05  dt=  36.9ms  words=93,208,576
[E08   543/1548 G  11378|CLM] train=1.8377  mask=10.8%  norm=0.855  lr=2.03e-05  dt=  37.0ms  words=93,216,768
[E08   544/1548 G  11379|CLM] train=4.1999  mask=10.8%  norm=0.901  lr=2.03e-05  dt=  36.7ms  words=93,224,960
[E08   545/1548 G  11380|CLM] train=3.4915  mask=10.8%  norm=0.928  lr=2.02e-05  dt=  36.9ms  words=93,233,152
[E08   546/1548 G  11381|CLM] train=4.2316  mask=10.8%  norm=0.966  lr=2.02e-05  dt=  37.1ms  words=93,241,344
[E08   547/1548 G  11382|CLM] train=4.7399  mask=10.8%  norm=0.890  lr=2.02e-05  dt=  36.8ms  words=93,249,536
[E08   548/1548 G  11383|CLM] train=1.8775  mask=10.8%  norm=0.836  lr=2.02e-05  dt=  37.0ms  words=93,257,728
[E08   549/1548 G  11384|CLM] train=2.4352  mask=10.8%  norm=0.733  lr=2.02e-05  dt=  36.9ms  words=93,265,920
[E08   550/1548 G  11385|CLM] train=4.3433  mask=10.8%  norm=0.933  lr=2.02e-05  dt=  36.8ms  words=93,274,112
[E08   551/1548 G  11386|CLM] train=2.3502  mask=10.8%  norm=0.717  lr=2.02e-05  dt=  37.0ms  words=93,282,304
[E08   552/1548 G  11387|CLM] train=2.2511  mask=10.8%  norm=0.913  lr=2.02e-05  dt=  36.9ms  words=93,290,496
[E08   553/1548 G  11388|CLM] train=3.9603  mask=10.8%  norm=1.032  lr=2.02e-05  dt=  37.0ms  words=93,298,688
[E08   554/1548 G  11389|CLM] train=2.0562  mask=10.8%  norm=0.756  lr=2.02e-05  dt=  37.0ms  words=93,306,880
[E08   555/1548 G  11390|CLM] train=4.1025  mask=10.8%  norm=1.025  lr=2.01e-05  dt=  36.9ms  words=93,315,072
[E08   556/1548 G  11391|CLM] train=3.6142  mask=10.8%  norm=0.894  lr=2.01e-05  dt=  36.8ms  words=93,323,264
[E08   557/1548 G  11392|CLM] train=3.7553  mask=10.8%  norm=0.853  lr=2.01e-05  dt=  36.8ms  words=93,331,456
[E08   558/1548 G  11393|CLM] train=3.2325  mask=10.8%  norm=0.820  lr=2.01e-05  dt=  37.1ms  words=93,339,648
[E08   559/1548 G  11394|CLM] train=2.0772  mask=10.8%  norm=0.778  lr=2.01e-05  dt=  36.8ms  words=93,347,840
[E08   560/1548 G  11395|CLM] train=2.4150  mask=10.8%  norm=0.710  lr=2.01e-05  dt=  37.1ms  words=93,356,032
[E08   561/1548 G  11396|CLM] train=3.9831  mask=10.8%  norm=0.998  lr=2.01e-05  dt=  36.9ms  words=93,364,224
[E08   562/1548 G  11397|CLM] train=3.7439  mask=10.8%  norm=0.867  lr=2.01e-05  dt=  37.0ms  words=93,372,416
[E08   563/1548 G  11398|CLM] train=2.1441  mask=10.8%  norm=0.811  lr=2.01e-05  dt=  37.5ms  words=93,380,608
[E08   564/1548 G  11399|CLM] train=4.0203  mask=10.8%  norm=0.917  lr=2.01e-05  dt=  37.1ms  words=93,388,800
[E08   565/1548 G  11400|CLM] train=1.9841  mask=10.8%  norm=0.656  lr=2.00e-05  dt=  37.2ms  words=93,396,992
[E08   566/1548 G  11401|CLM] train=3.6660  mask=10.8%  norm=0.829  lr=2.00e-05  dt=  37.4ms  words=93,405,184
[E08   567/1548 G  11402|CLM] train=2.5321  mask=10.8%  norm=0.743  lr=2.00e-05  dt=  37.1ms  words=93,413,376
[E08   568/1548 G  11403|CLM] train=3.7218  mask=10.8%  norm=0.904  lr=2.00e-05  dt=  37.1ms  words=93,421,568
[E08   569/1548 G  11404|CLM] train=3.9926  mask=10.8%  norm=0.915  lr=2.00e-05  dt=  37.2ms  words=93,429,760
[E08   570/1548 G  11405|CLM] train=2.2996  mask=10.8%  norm=0.743  lr=2.00e-05  dt=  37.2ms  words=93,437,952
[E08   571/1548 G  11406|CLM] train=2.0942  mask=10.8%  norm=0.755  lr=2.00e-05  dt=  37.2ms  words=93,446,144
[E08   572/1548 G  11407|CLM] train=2.0148  mask=10.8%  norm=0.689  lr=2.00e-05  dt=  37.2ms  words=93,454,336
[E08   573/1548 G  11408|CLM] train=1.9887  mask=10.8%  norm=0.883  lr=2.00e-05  dt=  37.2ms  words=93,462,528
[E08   574/1548 G  11409|CLM] train=3.3880  mask=10.8%  norm=0.805  lr=2.00e-05  dt=  37.2ms  words=93,470,720
[E08   575/1548 G  11410|CLM] train=4.0522  mask=10.8%  norm=0.961  lr=1.99e-05  dt=  37.3ms  words=93,478,912
[E08   576/1548 G  11411|CLM] train=3.4451  mask=10.8%  norm=0.893  lr=1.99e-05  dt=  37.3ms  words=93,487,104
[E08   577/1548 G  11412|CLM] train=2.2154  mask=10.8%  norm=0.756  lr=1.99e-05  dt=  37.3ms  words=93,495,296
[E08   578/1548 G  11413|CLM] train=3.9116  mask=10.8%  norm=0.901  lr=1.99e-05  dt=  37.3ms  words=93,503,488
[E08   579/1548 G  11414|CLM] train=4.3677  mask=10.8%  norm=0.963  lr=1.99e-05  dt=  37.3ms  words=93,511,680
[E08   580/1548 G  11415|CLM] train=3.9067  mask=10.8%  norm=0.812  lr=1.99e-05  dt=  37.2ms  words=93,519,872
[E08   581/1548 G  11416|CLM] train=4.2438  mask=10.8%  norm=1.033  lr=1.99e-05  dt=  37.4ms  words=93,528,064
[E08   582/1548 G  11417|CLM] train=4.5646  mask=10.8%  norm=0.939  lr=1.99e-05  dt=  37.2ms  words=93,536,256
[E08   583/1548 G  11418|CLM] train=1.9182  mask=10.8%  norm=0.730  lr=1.99e-05  dt=  37.1ms  words=93,544,448
[E08   584/1548 G  11419|CLM] train=1.5481  mask=10.8%  norm=0.643  lr=1.99e-05  dt=  37.2ms  words=93,552,640
[E08   585/1548 G  11420|CLM] train=3.9587  mask=10.8%  norm=0.932  lr=1.98e-05  dt=  37.2ms  words=93,560,832
[E08   586/1548 G  11421|CLM] train=4.2057  mask=10.8%  norm=0.916  lr=1.98e-05  dt=  37.2ms  words=93,569,024
[E08   587/1548 G  11422|CLM] train=3.8498  mask=10.8%  norm=0.825  lr=1.98e-05  dt=  37.1ms  words=93,577,216
[E08   588/1548 G  11423|CLM] train=4.8851  mask=10.8%  norm=1.788  lr=1.98e-05  dt=  37.0ms  words=93,585,408
[E08   589/1548 G  11424|CLM] train=3.8547  mask=10.8%  norm=0.834  lr=1.98e-05  dt=  37.1ms  words=93,593,600
[E08   590/1548 G  11425|CLM] train=3.9364  mask=10.8%  norm=0.955  lr=1.98e-05  dt=  37.5ms  words=93,601,792
[E08   591/1548 G  11426|CLM] train=4.5464  mask=10.8%  norm=1.080  lr=1.98e-05  dt=  37.1ms  words=93,609,984
[E08   592/1548 G  11427|CLM] train=3.2833  mask=10.8%  norm=0.788  lr=1.98e-05  dt=  37.1ms  words=93,618,176
[E08   593/1548 G  11428|CLM] train=3.7339  mask=10.8%  norm=0.778  lr=1.98e-05  dt=  37.4ms  words=93,626,368
[E08   594/1548 G  11429|CLM] train=4.1157  mask=10.8%  norm=0.942  lr=1.98e-05  dt=  37.2ms  words=93,634,560
[E08   595/1548 G  11430|CLM] train=3.7841  mask=10.8%  norm=0.886  lr=1.97e-05  dt=  36.9ms  words=93,642,752
[E08   596/1548 G  11431|CLM] train=4.1528  mask=10.8%  norm=0.893  lr=1.97e-05  dt=  37.1ms  words=93,650,944
[E08   597/1548 G  11432|CLM] train=4.4025  mask=10.8%  norm=0.971  lr=1.97e-05  dt=  37.2ms  words=93,659,136
[E08   598/1548 G  11433|CLM] train=4.0534  mask=10.8%  norm=0.874  lr=1.97e-05  dt=  37.1ms  words=93,667,328
[E08   599/1548 G  11434|CLM] train=4.1198  mask=10.8%  norm=0.890  lr=1.97e-05  dt=  37.1ms  words=93,675,520
[E08   600/1548 G  11435|CLM] train=4.3087  mask=10.8%  norm=0.847  lr=1.97e-05  dt=  37.2ms  words=93,683,712
[E08   601/1548 G  11436|CLM] train=3.3534  mask=10.8%  norm=0.846  lr=1.97e-05  dt=  37.2ms  words=93,691,904
[E08   602/1548 G  11437|CLM] train=1.8998  mask=10.8%  norm=0.759  lr=1.97e-05  dt=  37.2ms  words=93,700,096
[E08   603/1548 G  11438|CLM] train=2.2842  mask=10.8%  norm=0.739  lr=1.97e-05  dt=  37.2ms  words=93,708,288
[E08   604/1548 G  11439|CLM] train=4.0184  mask=10.8%  norm=0.853  lr=1.97e-05  dt=  37.7ms  words=93,716,480
[E08   605/1548 G  11440|CLM] train=2.3245  mask=10.8%  norm=0.708  lr=1.96e-05  dt=  37.2ms  words=93,724,672
[E08   606/1548 G  11441|CLM] train=4.0744  mask=10.8%  norm=0.841  lr=1.96e-05  dt=  37.4ms  words=93,732,864
[E08   607/1548 G  11442|CLM] train=3.6559  mask=10.8%  norm=0.896  lr=1.96e-05  dt=  37.2ms  words=93,741,056
[E08   608/1548 G  11443|CLM] train=2.5049  mask=10.8%  norm=0.707  lr=1.96e-05  dt=  37.1ms  words=93,749,248
[E08   609/1548 G  11444|CLM] train=4.0505  mask=10.8%  norm=0.889  lr=1.96e-05  dt=  37.3ms  words=93,757,440
[E08   610/1548 G  11445|CLM] train=1.9216  mask=10.8%  norm=0.758  lr=1.96e-05  dt=  37.1ms  words=93,765,632
[E08   611/1548 G  11446|CLM] train=2.1875  mask=10.8%  norm=0.731  lr=1.96e-05  dt=  37.2ms  words=93,773,824
[E08   612/1548 G  11447|CLM] train=2.0224  mask=10.8%  norm=0.694  lr=1.96e-05  dt=  37.1ms  words=93,782,016
[E08   613/1548 G  11448|CLM] train=3.4578  mask=10.8%  norm=0.835  lr=1.96e-05  dt=  37.2ms  words=93,790,208
[E08   614/1548 G  11449|CLM] train=3.9536  mask=10.8%  norm=0.909  lr=1.96e-05  dt=  37.1ms  words=93,798,400
[E08   615/1548 G  11450|CLM] train=4.6800  mask=10.8%  norm=1.146  lr=1.95e-05  dt=  37.5ms  words=93,806,592
[E08   616/1548 G  11451|CLM] train=2.4162  mask=10.8%  norm=0.744  lr=1.95e-05  dt=  37.3ms  words=93,814,784
[E08   617/1548 G  11452|CLM] train=2.1081  mask=10.8%  norm=0.661  lr=1.95e-05  dt=  38.2ms  words=93,822,976
[E08   618/1548 G  11453|CLM] train=1.9840  mask=10.8%  norm=0.786  lr=1.95e-05  dt=  37.5ms  words=93,831,168
[E08   619/1548 G  11454|CLM] train=4.2111  mask=10.8%  norm=0.970  lr=1.95e-05  dt=  37.5ms  words=93,839,360
[E08   620/1548 G  11455|CLM] train=4.0368  mask=10.8%  norm=0.919  lr=1.95e-05  dt=  37.6ms  words=93,847,552
[E08   621/1548 G  11456|CLM] train=3.7330  mask=10.7%  norm=0.854  lr=1.95e-05  dt=  37.0ms  words=93,855,744
[E08   622/1548 G  11457|CLM] train=4.0950  mask=10.7%  norm=0.912  lr=1.95e-05  dt=  37.1ms  words=93,863,936
[E08   623/1548 G  11458|CLM] train=3.6719  mask=10.7%  norm=0.914  lr=1.95e-05  dt=  37.1ms  words=93,872,128
[E08   624/1548 G  11459|CLM] train=2.2446  mask=10.7%  norm=0.720  lr=1.95e-05  dt=  37.2ms  words=93,880,320
[E08   625/1548 G  11460|CLM] train=4.0045  mask=10.7%  norm=0.865  lr=1.95e-05  dt=  37.3ms  words=93,888,512
[E08   626/1548 G  11461|CLM] train=3.7031  mask=10.7%  norm=0.948  lr=1.94e-05  dt=  37.2ms  words=93,896,704
[E08   627/1548 G  11462|CLM] train=2.2194  mask=10.7%  norm=0.791  lr=1.94e-05  dt=  37.0ms  words=93,904,896
[E08   628/1548 G  11463|CLM] train=2.5928  mask=10.7%  norm=0.741  lr=1.94e-05  dt=  37.2ms  words=93,913,088
[E08   629/1548 G  11464|CLM] train=3.8455  mask=10.7%  norm=1.155  lr=1.94e-05  dt=  37.7ms  words=93,921,280
[E08   630/1548 G  11465|CLM] train=2.2411  mask=10.7%  norm=0.729  lr=1.94e-05  dt=  37.3ms  words=93,929,472
[E08   631/1548 G  11466|CLM] train=1.9962  mask=10.7%  norm=0.742  lr=1.94e-05  dt=  37.1ms  words=93,937,664
[E08   632/1548 G  11467|CLM] train=1.8741  mask=10.7%  norm=0.717  lr=1.94e-05  dt=  37.3ms  words=93,945,856
[E08   633/1548 G  11468|CLM] train=4.5499  mask=10.7%  norm=1.175  lr=1.94e-05  dt=  37.2ms  words=93,954,048
[E08   634/1548 G  11469|CLM] train=3.9091  mask=10.7%  norm=1.002  lr=1.94e-05  dt=  37.2ms  words=93,962,240
[E08   635/1548 G  11470|CLM] train=3.7550  mask=10.7%  norm=0.794  lr=1.94e-05  dt=  37.2ms  words=93,970,432
[E08   636/1548 G  11471|CLM] train=4.5410  mask=10.7%  norm=0.890  lr=1.93e-05  dt=  37.2ms  words=93,978,624
[E08   637/1548 G  11472|CLM] train=2.2850  mask=10.7%  norm=0.866  lr=1.93e-05  dt=  37.2ms  words=93,986,816
[E08   638/1548 G  11473|CLM] train=4.0357  mask=10.7%  norm=0.951  lr=1.93e-05  dt=  37.4ms  words=93,995,008
[E08   639/1548 G  11474|CLM] train=2.2813  mask=10.7%  norm=1.206  lr=1.93e-05  dt=  37.0ms  words=94,003,200
[E08   640/1548 G  11475|CLM] train=4.4061  mask=10.7%  norm=1.038  lr=1.93e-05  dt=  37.3ms  words=94,011,392
[E08   641/1548 G  11476|CLM] train=3.6871  mask=10.7%  norm=0.815  lr=1.93e-05  dt=  37.3ms  words=94,019,584
[E08   642/1548 G  11477|CLM] train=4.0105  mask=10.7%  norm=0.900  lr=1.93e-05  dt=  37.1ms  words=94,027,776
[E08   643/1548 G  11478|CLM] train=4.0184  mask=10.7%  norm=0.903  lr=1.93e-05  dt=  36.9ms  words=94,035,968
[E08   644/1548 G  11479|CLM] train=3.9901  mask=10.7%  norm=1.004  lr=1.93e-05  dt=  37.8ms  words=94,044,160
[E08   645/1548 G  11480|CLM] train=3.9574  mask=10.7%  norm=0.910  lr=1.93e-05  dt=  37.2ms  words=94,052,352
[E08   646/1548 G  11481|CLM] train=3.4588  mask=10.7%  norm=0.783  lr=1.93e-05  dt=  37.2ms  words=94,060,544
[E08   647/1548 G  11482|CLM] train=2.3478  mask=10.7%  norm=0.756  lr=1.92e-05  dt=  37.4ms  words=94,068,736
[E08   648/1548 G  11483|CLM] train=4.0341  mask=10.7%  norm=0.920  lr=1.92e-05  dt=  37.3ms  words=94,076,928
[E08   649/1548 G  11484|CLM] train=2.3757  mask=10.7%  norm=0.658  lr=1.92e-05  dt=  37.1ms  words=94,085,120
[E08   650/1548 G  11485|CLM] train=2.5065  mask=10.7%  norm=0.721  lr=1.92e-05  dt=  37.2ms  words=94,093,312
[E08   651/1548 G  11486|CLM] train=4.6099  mask=10.7%  norm=0.880  lr=1.92e-05  dt=  37.0ms  words=94,101,504
[E08   652/1548 G  11487|CLM] train=3.5066  mask=10.7%  norm=0.899  lr=1.92e-05  dt=  37.3ms  words=94,109,696
[E08   653/1548 G  11488|CLM] train=3.7587  mask=10.7%  norm=0.871  lr=1.92e-05  dt=  37.2ms  words=94,117,888
[E08   654/1548 G  11489|CLM] train=2.1188  mask=10.7%  norm=0.709  lr=1.92e-05  dt=  37.3ms  words=94,126,080
[E08   655/1548 G  11490|CLM] train=1.9768  mask=10.7%  norm=0.684  lr=1.92e-05  dt=  37.4ms  words=94,134,272
[E08   656/1548 G  11491|CLM] train=2.1526  mask=10.7%  norm=0.651  lr=1.92e-05  dt=  38.2ms  words=94,142,464
[E08   657/1548 G  11492|CLM] train=2.0698  mask=10.7%  norm=0.760  lr=1.91e-05  dt=  37.1ms  words=94,150,656
[E08   658/1548 G  11493|CLM] train=2.2756  mask=10.7%  norm=0.688  lr=1.91e-05  dt=  37.6ms  words=94,158,848
[E08   659/1548 G  11494|CLM] train=3.8761  mask=10.7%  norm=0.897  lr=1.91e-05  dt=  37.1ms  words=94,167,040
[E08   660/1548 G  11495|CLM] train=1.9879  mask=10.7%  norm=0.857  lr=1.91e-05  dt=  37.2ms  words=94,175,232
[E08   661/1548 G  11496|CLM] train=3.8873  mask=10.7%  norm=1.292  lr=1.91e-05  dt=  37.3ms  words=94,183,424
[E08   662/1548 G  11497|CLM] train=4.1710  mask=10.7%  norm=0.901  lr=1.91e-05  dt=  37.2ms  words=94,191,616
[E08   663/1548 G  11498|CLM] train=2.2287  mask=10.7%  norm=0.924  lr=1.91e-05  dt=  37.1ms  words=94,199,808
[E08   664/1548 G  11499|CLM] train=4.2595  mask=10.7%  norm=0.970  lr=1.91e-05  dt=  37.5ms  words=94,208,000
[E08   665/1548 G  11500|CLM] train=3.3899  mask=10.7%  norm=0.813  lr=1.91e-05  dt=  37.2ms  words=94,216,192
[E08   666/1548 G  11501|CLM] train=1.9940  mask=10.7%  norm=0.727  lr=1.91e-05  dt=  37.6ms  words=94,224,384
[E08   667/1548 G  11502|CLM] train=3.4540  mask=10.7%  norm=0.833  lr=1.91e-05  dt=  37.3ms  words=94,232,576
[E08   668/1548 G  11503|CLM] train=3.8795  mask=10.7%  norm=0.894  lr=1.90e-05  dt=  37.5ms  words=94,240,768
[E08   669/1548 G  11504|CLM] train=2.6391  mask=10.7%  norm=0.749  lr=1.90e-05  dt=  37.2ms  words=94,248,960
[E08   670/1548 G  11505|CLM] train=4.4802  mask=10.7%  norm=1.006  lr=1.90e-05  dt=  37.3ms  words=94,257,152
[E08   671/1548 G  11506|CLM] train=4.7331  mask=10.7%  norm=0.930  lr=1.90e-05  dt=  37.3ms  words=94,265,344
[E08   672/1548 G  11507|CLM] train=3.9635  mask=10.7%  norm=1.023  lr=1.90e-05  dt=  37.4ms  words=94,273,536
[E08   673/1548 G  11508|CLM] train=4.1581  mask=10.7%  norm=0.953  lr=1.90e-05  dt=  37.2ms  words=94,281,728
[E08   674/1548 G  11509|CLM] train=2.2319  mask=10.7%  norm=0.810  lr=1.90e-05  dt=  37.3ms  words=94,289,920
[E08   675/1548 G  11510|CLM] train=2.5411  mask=10.7%  norm=0.714  lr=1.90e-05  dt=  37.2ms  words=94,298,112
[E08   676/1548 G  11511|CLM] train=4.1449  mask=10.7%  norm=0.948  lr=1.90e-05  dt=  37.2ms  words=94,306,304
[E08   677/1548 G  11512|CLM] train=4.3482  mask=10.7%  norm=1.025  lr=1.90e-05  dt=  37.3ms  words=94,314,496
[E08   678/1548 G  11513|CLM] train=5.1126  mask=10.7%  norm=1.851  lr=1.90e-05  dt=  37.3ms  words=94,322,688
[E08   679/1548 G  11514|CLM] train=4.4780  mask=10.7%  norm=1.130  lr=1.89e-05  dt=  37.2ms  words=94,330,880
[E08   680/1548 G  11515|CLM] train=1.8569  mask=10.7%  norm=0.690  lr=1.89e-05  dt=  37.3ms  words=94,339,072
[E08   681/1548 G  11516|CLM] train=4.5393  mask=10.7%  norm=0.923  lr=1.89e-05  dt=  37.2ms  words=94,347,264
[E08   682/1548 G  11517|CLM] train=4.2092  mask=10.7%  norm=0.949  lr=1.89e-05  dt=  37.2ms  words=94,355,456
[E08   683/1548 G  11518|CLM] train=2.0527  mask=10.7%  norm=0.673  lr=1.89e-05  dt=  38.0ms  words=94,363,648
[E08   684/1548 G  11519|CLM] train=2.1193  mask=10.7%  norm=0.667  lr=1.89e-05  dt=  37.3ms  words=94,371,840
[E08   685/1548 G  11520|CLM] train=3.8711  mask=10.7%  norm=0.874  lr=1.89e-05  dt=  37.3ms  words=94,380,032
[E08   686/1548 G  11521|CLM] train=2.1825  mask=10.7%  norm=0.680  lr=1.89e-05  dt=  37.1ms  words=94,388,224
[E08   687/1548 G  11522|CLM] train=3.1947  mask=10.7%  norm=0.894  lr=1.89e-05  dt=  37.2ms  words=94,396,416
[E08   688/1548 G  11523|CLM] train=4.2244  mask=10.7%  norm=0.897  lr=1.89e-05  dt=  37.3ms  words=94,404,608
[E08   689/1548 G  11524|CLM] train=2.1228  mask=10.7%  norm=0.688  lr=1.89e-05  dt=  37.3ms  words=94,412,800
[E08   690/1548 G  11525|CLM] train=3.8954  mask=10.7%  norm=0.931  lr=1.88e-05  dt=  37.1ms  words=94,420,992
[E08   691/1548 G  11526|CLM] train=2.3202  mask=10.7%  norm=0.731  lr=1.88e-05  dt=  37.2ms  words=94,429,184
[E08   692/1548 G  11527|CLM] train=3.6539  mask=10.7%  norm=0.902  lr=1.88e-05  dt=  37.2ms  words=94,437,376
[E08   693/1548 G  11528|CLM] train=3.5352  mask=10.7%  norm=0.889  lr=1.88e-05  dt=  37.3ms  words=94,445,568
[E08   694/1548 G  11529|CLM] train=3.8841  mask=10.7%  norm=0.844  lr=1.88e-05  dt=  37.2ms  words=94,453,760
[E08   695/1548 G  11530|CLM] train=1.9806  mask=10.7%  norm=0.655  lr=1.88e-05  dt=  37.2ms  words=94,461,952
[E08   696/1548 G  11531|CLM] train=3.5777  mask=10.7%  norm=0.913  lr=1.88e-05  dt=  37.2ms  words=94,470,144
[E08   697/1548 G  11532|CLM] train=2.6932  mask=10.7%  norm=0.914  lr=1.88e-05  dt=  37.5ms  words=94,478,336
[E08   698/1548 G  11533|CLM] train=3.5338  mask=10.7%  norm=0.888  lr=1.88e-05  dt=  37.1ms  words=94,486,528
[E08   699/1548 G  11534|CLM] train=4.4220  mask=10.7%  norm=1.162  lr=1.88e-05  dt=  37.7ms  words=94,494,720
[E08   700/1548 G  11535|CLM] train=3.8407  mask=10.7%  norm=0.923  lr=1.88e-05  dt=  37.4ms  words=94,502,912
[E08   701/1548 G  11536|CLM] train=3.6795  mask=10.7%  norm=0.880  lr=1.88e-05  dt= 437.3ms  words=94,511,104
[E08   702/1548 G  11537|CLM] train=3.9714  mask=10.7%  norm=0.932  lr=1.87e-05  dt=  39.2ms  words=94,519,296
[E08   703/1548 G  11538|CLM] train=3.5136  mask=10.7%  norm=0.800  lr=1.87e-05  dt=  37.3ms  words=94,527,488
[E08   704/1548 G  11539|CLM] train=3.5715  mask=10.7%  norm=0.754  lr=1.87e-05  dt=  37.4ms  words=94,535,680
[E08   705/1548 G  11540|CLM] train=2.0036  mask=10.7%  norm=0.808  lr=1.87e-05  dt=  37.5ms  words=94,543,872
[E08   706/1548 G  11541|CLM] train=2.1658  mask=10.7%  norm=0.849  lr=1.87e-05  dt=  37.6ms  words=94,552,064
[E08   707/1548 G  11542|CLM] train=3.2634  mask=10.7%  norm=0.882  lr=1.87e-05  dt=  37.2ms  words=94,560,256
[E08   708/1548 G  11543|CLM] train=3.7970  mask=10.7%  norm=0.935  lr=1.87e-05  dt=  37.5ms  words=94,568,448
[E08   709/1548 G  11544|CLM] train=3.4125  mask=10.7%  norm=0.821  lr=1.87e-05  dt=  37.3ms  words=94,576,640
[E08   710/1548 G  11545|CLM] train=1.8400  mask=10.7%  norm=0.804  lr=1.87e-05  dt=  37.4ms  words=94,584,832
[E08   711/1548 G  11546|CLM] train=3.3178  mask=10.7%  norm=1.067  lr=1.87e-05  dt=  37.9ms  words=94,593,024
[E08   712/1548 G  11547|CLM] train=4.1703  mask=10.7%  norm=0.879  lr=1.87e-05  dt=  37.3ms  words=94,601,216
[E08   713/1548 G  11548|CLM] train=3.4019  mask=10.7%  norm=0.795  lr=1.86e-05  dt=  37.5ms  words=94,609,408
[E08   714/1548 G  11549|CLM] train=3.6904  mask=10.7%  norm=0.814  lr=1.86e-05  dt=  37.4ms  words=94,617,600
[E08   715/1548 G  11550|CLM] train=3.9265  mask=10.7%  norm=1.062  lr=1.86e-05  dt=  37.2ms  words=94,625,792
[E08   716/1548 G  11551|CLM] train=2.8819  mask=10.7%  norm=0.784  lr=1.86e-05  dt=  37.6ms  words=94,633,984
[E08   717/1548 G  11552|CLM] train=4.5795  mask=10.7%  norm=0.872  lr=1.86e-05  dt=  37.9ms  words=94,642,176
[E08   718/1548 G  11553|CLM] train=2.1437  mask=10.7%  norm=0.697  lr=1.86e-05  dt=  37.5ms  words=94,650,368
[E08   719/1548 G  11554|CLM] train=2.1215  mask=10.7%  norm=0.721  lr=1.86e-05  dt=  37.6ms  words=94,658,560
[E08   720/1548 G  11555|CLM] train=3.7509  mask=10.7%  norm=0.912  lr=1.86e-05  dt=  37.3ms  words=94,666,752
[E08   721/1548 G  11556|CLM] train=4.1797  mask=10.7%  norm=0.888  lr=1.86e-05  dt=  37.5ms  words=94,674,944
[E08   722/1548 G  11557|CLM] train=2.2572  mask=10.7%  norm=0.694  lr=1.86e-05  dt=  37.3ms  words=94,683,136
[E08   723/1548 G  11558|CLM] train=4.0580  mask=10.7%  norm=0.929  lr=1.86e-05  dt=  37.3ms  words=94,691,328
[E08   724/1548 G  11559|CLM] train=3.5029  mask=10.7%  norm=0.895  lr=1.86e-05  dt=  37.0ms  words=94,699,520
[E08   725/1548 G  11560|CLM] train=4.3063  mask=10.7%  norm=1.214  lr=1.85e-05  dt=  37.5ms  words=94,707,712
[E08   726/1548 G  11561|CLM] train=2.3311  mask=10.7%  norm=0.698  lr=1.85e-05  dt=  37.4ms  words=94,715,904
[E08   727/1548 G  11562|CLM] train=3.3030  mask=10.7%  norm=0.777  lr=1.85e-05  dt=  37.6ms  words=94,724,096
[E08   728/1548 G  11563|CLM] train=1.8742  mask=10.7%  norm=0.882  lr=1.85e-05  dt=  37.1ms  words=94,732,288
[E08   729/1548 G  11564|CLM] train=4.0120  mask=10.7%  norm=0.988  lr=1.85e-05  dt=  37.4ms  words=94,740,480
[E08   730/1548 G  11565|CLM] train=2.4339  mask=10.7%  norm=0.804  lr=1.85e-05  dt=  37.2ms  words=94,748,672
[E08   731/1548 G  11566|CLM] train=4.1346  mask=10.7%  norm=0.849  lr=1.85e-05  dt=  37.3ms  words=94,756,864
[E08   732/1548 G  11567|CLM] train=2.4212  mask=10.7%  norm=0.724  lr=1.85e-05  dt=  37.1ms  words=94,765,056
[E08   733/1548 G  11568|CLM] train=3.3688  mask=10.7%  norm=0.818  lr=1.85e-05  dt=  37.1ms  words=94,773,248
[E08   734/1548 G  11569|CLM] train=3.5585  mask=10.7%  norm=0.806  lr=1.85e-05  dt=  37.1ms  words=94,781,440
[E08   735/1548 G  11570|CLM] train=1.5577  mask=10.7%  norm=0.850  lr=1.85e-05  dt=  37.0ms  words=94,789,632
[E08   736/1548 G  11571|CLM] train=2.3108  mask=10.7%  norm=0.675  lr=1.84e-05  dt=  37.3ms  words=94,797,824
[E08   737/1548 G  11572|CLM] train=3.4348  mask=10.7%  norm=0.773  lr=1.84e-05  dt=  37.1ms  words=94,806,016
[E08   738/1548 G  11573|CLM] train=1.9985  mask=10.7%  norm=0.630  lr=1.84e-05  dt=  37.2ms  words=94,814,208
[E08   739/1548 G  11574|CLM] train=1.9839  mask=10.7%  norm=0.767  lr=1.84e-05  dt=  37.2ms  words=94,822,400
[E08   740/1548 G  11575|CLM] train=3.3933  mask=10.7%  norm=0.988  lr=1.84e-05  dt=  37.4ms  words=94,830,592
[E08   741/1548 G  11576|CLM] train=3.7360  mask=10.7%  norm=1.127  lr=1.84e-05  dt=  37.3ms  words=94,838,784
[E08   742/1548 G  11577|CLM] train=2.5903  mask=10.7%  norm=0.773  lr=1.84e-05  dt=  37.1ms  words=94,846,976
[E08   743/1548 G  11578|CLM] train=3.9160  mask=10.7%  norm=0.900  lr=1.84e-05  dt=  37.3ms  words=94,855,168
[E08   744/1548 G  11579|CLM] train=4.5353  mask=10.7%  norm=1.074  lr=1.84e-05  dt=  36.9ms  words=94,863,360
[E08   745/1548 G  11580|CLM] train=3.5223  mask=10.6%  norm=0.856  lr=1.84e-05  dt=  37.0ms  words=94,871,552
[E08   746/1548 G  11581|CLM] train=3.6468  mask=10.6%  norm=0.953  lr=1.84e-05  dt=  37.3ms  words=94,879,744
[E08   747/1548 G  11582|CLM] train=2.0543  mask=10.6%  norm=0.835  lr=1.84e-05  dt=  37.1ms  words=94,887,936
[E08   748/1548 G  11583|CLM] train=2.4904  mask=10.6%  norm=0.833  lr=1.83e-05  dt=  36.9ms  words=94,896,128
[E08   749/1548 G  11584|CLM] train=3.9301  mask=10.6%  norm=0.864  lr=1.83e-05  dt=  37.2ms  words=94,904,320
[E08   750/1548 G  11585|CLM] train=4.1136  mask=10.6%  norm=0.993  lr=1.83e-05  dt=  37.0ms  words=94,912,512
[E08   751/1548 G  11586|CLM] train=3.6765  mask=10.6%  norm=0.903  lr=1.83e-05  dt=  37.2ms  words=94,920,704
[E08   752/1548 G  11587|CLM] train=1.8127  mask=10.6%  norm=0.764  lr=1.83e-05  dt=  37.3ms  words=94,928,896
[E08   753/1548 G  11588|CLM] train=3.8888  mask=10.6%  norm=0.874  lr=1.83e-05  dt=  37.3ms  words=94,937,088
[E08   754/1548 G  11589|CLM] train=3.6475  mask=10.6%  norm=0.849  lr=1.83e-05  dt=  37.2ms  words=94,945,280
[E08   755/1548 G  11590|CLM] train=4.2055  mask=10.6%  norm=0.908  lr=1.83e-05  dt=  37.1ms  words=94,953,472
[E08   756/1548 G  11591|CLM] train=2.2428  mask=10.6%  norm=0.694  lr=1.83e-05  dt=  37.3ms  words=94,961,664
[E08   757/1548 G  11592|CLM] train=4.0287  mask=10.6%  norm=0.871  lr=1.83e-05  dt=  37.2ms  words=94,969,856
[E08   758/1548 G  11593|CLM] train=4.3599  mask=10.6%  norm=0.968  lr=1.83e-05  dt=  37.3ms  words=94,978,048
[E08   759/1548 G  11594|CLM] train=3.2401  mask=10.6%  norm=0.862  lr=1.83e-05  dt=  37.4ms  words=94,986,240
[E08   760/1548 G  11595|CLM] train=3.6411  mask=10.6%  norm=1.032  lr=1.82e-05  dt=  37.1ms  words=94,994,432
[E08   761/1548 G  11596|CLM] train=3.5910  mask=10.6%  norm=0.845  lr=1.82e-05  dt=  37.4ms  words=95,002,624
[E08   762/1548 G  11597|CLM] train=4.2910  mask=10.6%  norm=1.249  lr=1.82e-05  dt=  37.3ms  words=95,010,816
[E08   763/1548 G  11598|CLM] train=3.9182  mask=10.6%  norm=0.844  lr=1.82e-05  dt=  37.1ms  words=95,019,008
[E08   764/1548 G  11599|CLM] train=4.5498  mask=10.6%  norm=0.880  lr=1.82e-05  dt=  37.2ms  words=95,027,200
[E08   765/1548 G  11600|CLM] train=3.5124  mask=10.6%  norm=0.788  lr=1.82e-05  dt=  37.1ms  words=95,035,392
[E08   766/1548 G  11601|CLM] train=3.7300  mask=10.6%  norm=0.951  lr=1.82e-05  dt=  36.9ms  words=95,043,584
[E08   767/1548 G  11602|CLM] train=3.9611  mask=10.6%  norm=0.908  lr=1.82e-05  dt=  37.3ms  words=95,051,776
[E08   768/1548 G  11603|CLM] train=4.1571  mask=10.6%  norm=0.834  lr=1.82e-05  dt=  37.2ms  words=95,059,968
[E08   769/1548 G  11604|CLM] train=4.1877  mask=10.6%  norm=1.259  lr=1.82e-05  dt=  36.9ms  words=95,068,160
[E08   770/1548 G  11605|CLM] train=4.6988  mask=10.6%  norm=0.900  lr=1.82e-05  dt=  36.9ms  words=95,076,352
[E08   771/1548 G  11606|CLM] train=2.6340  mask=10.6%  norm=0.732  lr=1.82e-05  dt=  37.0ms  words=95,084,544
[E08   772/1548 G  11607|CLM] train=2.2790  mask=10.6%  norm=0.835  lr=1.82e-05  dt=  36.9ms  words=95,092,736
[E08   773/1548 G  11608|CLM] train=3.3700  mask=10.6%  norm=0.780  lr=1.81e-05  dt=  37.0ms  words=95,100,928
[E08   774/1548 G  11609|CLM] train=4.1316  mask=10.6%  norm=0.831  lr=1.81e-05  dt=  37.0ms  words=95,109,120
[E08   775/1548 G  11610|CLM] train=3.9710  mask=10.6%  norm=0.844  lr=1.81e-05  dt=  37.0ms  words=95,117,312
[E08   776/1548 G  11611|CLM] train=2.5531  mask=10.6%  norm=0.916  lr=1.81e-05  dt=  37.0ms  words=95,125,504
[E08   777/1548 G  11612|CLM] train=4.2797  mask=10.6%  norm=0.868  lr=1.81e-05  dt=  36.9ms  words=95,133,696
[E08   778/1548 G  11613|CLM] train=2.3170  mask=10.6%  norm=0.694  lr=1.81e-05  dt=  36.8ms  words=95,141,888
[E08   779/1548 G  11614|CLM] train=3.8397  mask=10.6%  norm=0.877  lr=1.81e-05  dt=  37.2ms  words=95,150,080
[E08   780/1548 G  11615|CLM] train=4.0334  mask=10.6%  norm=1.084  lr=1.81e-05  dt=  37.1ms  words=95,158,272
[E08   781/1548 G  11616|CLM] train=2.4157  mask=10.6%  norm=0.772  lr=1.81e-05  dt=  36.9ms  words=95,166,464
[E08   782/1548 G  11617|CLM] train=4.0345  mask=10.6%  norm=0.836  lr=1.81e-05  dt=  36.8ms  words=95,174,656
[E08   783/1548 G  11618|CLM] train=4.1928  mask=10.6%  norm=1.160  lr=1.81e-05  dt=  36.8ms  words=95,182,848
[E08   784/1548 G  11619|CLM] train=4.4536  mask=10.6%  norm=0.969  lr=1.81e-05  dt=  37.0ms  words=95,191,040
[E08   785/1548 G  11620|CLM] train=4.1964  mask=10.6%  norm=0.940  lr=1.80e-05  dt=  36.8ms  words=95,199,232
[E08   786/1548 G  11621|CLM] train=3.2740  mask=10.6%  norm=0.766  lr=1.80e-05  dt=  36.8ms  words=95,207,424
[E08   787/1548 G  11622|CLM] train=1.8181  mask=10.6%  norm=0.753  lr=1.80e-05  dt=  37.0ms  words=95,215,616
[E08   788/1548 G  11623|CLM] train=4.1063  mask=10.6%  norm=0.902  lr=1.80e-05  dt=  36.9ms  words=95,223,808
[E08   789/1548 G  11624|CLM] train=3.8260  mask=10.6%  norm=0.892  lr=1.80e-05  dt=  36.9ms  words=95,232,000
[E08   790/1548 G  11625|CLM] train=2.1154  mask=10.6%  norm=0.964  lr=1.80e-05  dt=  37.6ms  words=95,240,192
[E08   791/1548 G  11626|CLM] train=4.1203  mask=10.6%  norm=0.833  lr=1.80e-05  dt=  37.0ms  words=95,248,384
[E08   792/1548 G  11627|CLM] train=3.3408  mask=10.6%  norm=0.742  lr=1.80e-05  dt=  37.1ms  words=95,256,576
[E08   793/1548 G  11628|CLM] train=1.7804  mask=10.6%  norm=0.769  lr=1.80e-05  dt=  37.5ms  words=95,264,768
[E08   794/1548 G  11629|CLM] train=4.3819  mask=10.6%  norm=0.977  lr=1.80e-05  dt=  37.8ms  words=95,272,960
[E08   795/1548 G  11630|CLM] train=4.4251  mask=10.6%  norm=0.961  lr=1.80e-05  dt=  37.0ms  words=95,281,152
[E08   796/1548 G  11631|CLM] train=2.4870  mask=10.6%  norm=0.693  lr=1.80e-05  dt=  37.1ms  words=95,289,344
[E08   797/1548 G  11632|CLM] train=3.9805  mask=10.6%  norm=0.851  lr=1.80e-05  dt=  37.0ms  words=95,297,536
[E08   798/1548 G  11633|CLM] train=4.5698  mask=10.6%  norm=1.229  lr=1.79e-05  dt=  36.9ms  words=95,305,728
[E08   799/1548 G  11634|CLM] train=4.1341  mask=10.6%  norm=0.966  lr=1.79e-05  dt=  36.8ms  words=95,313,920
[E08   800/1548 G  11635|CLM] train=2.3222  mask=10.6%  norm=0.679  lr=1.79e-05  dt=  37.1ms  words=95,322,112
[E08   801/1548 G  11636|CLM] train=2.1645  mask=10.6%  norm=0.753  lr=1.79e-05  dt=  37.0ms  words=95,330,304
[E08   802/1548 G  11637|CLM] train=2.0548  mask=10.6%  norm=0.683  lr=1.79e-05  dt=  37.0ms  words=95,338,496
[E08   803/1548 G  11638|CLM] train=2.7450  mask=10.6%  norm=0.776  lr=1.79e-05  dt=  36.9ms  words=95,346,688
[E08   804/1548 G  11639|CLM] train=3.9870  mask=10.6%  norm=0.858  lr=1.79e-05  dt=  36.9ms  words=95,354,880
[E08   805/1548 G  11640|CLM] train=4.2884  mask=10.6%  norm=0.859  lr=1.79e-05  dt=  37.0ms  words=95,363,072
[E08   806/1548 G  11641|CLM] train=2.3605  mask=10.6%  norm=0.801  lr=1.79e-05  dt=  37.3ms  words=95,371,264
[E08   807/1548 G  11642|CLM] train=2.2365  mask=10.6%  norm=0.738  lr=1.79e-05  dt=  36.9ms  words=95,379,456
[E08   808/1548 G  11643|CLM] train=2.2637  mask=10.6%  norm=0.729  lr=1.79e-05  dt=  36.8ms  words=95,387,648
[E08   809/1548 G  11644|CLM] train=3.5895  mask=10.6%  norm=0.882  lr=1.79e-05  dt=  37.1ms  words=95,395,840
[E08   810/1548 G  11645|CLM] train=4.2183  mask=10.6%  norm=0.899  lr=1.79e-05  dt=  36.7ms  words=95,404,032
[E08   811/1548 G  11646|CLM] train=2.6019  mask=10.6%  norm=0.816  lr=1.78e-05  dt=  36.7ms  words=95,412,224
[E08   812/1548 G  11647|CLM] train=4.6009  mask=10.6%  norm=0.894  lr=1.78e-05  dt=  36.9ms  words=95,420,416
[E08   813/1548 G  11648|CLM] train=2.1805  mask=10.6%  norm=0.656  lr=1.78e-05  dt=  37.0ms  words=95,428,608
[E08   814/1548 G  11649|CLM] train=4.4068  mask=10.6%  norm=1.003  lr=1.78e-05  dt=  36.9ms  words=95,436,800
[E08   815/1548 G  11650|CLM] train=2.6272  mask=10.6%  norm=0.785  lr=1.78e-05  dt=  36.8ms  words=95,444,992
[E08   816/1548 G  11651|CLM] train=4.2479  mask=10.6%  norm=1.038  lr=1.78e-05  dt=  36.9ms  words=95,453,184
[E08   817/1548 G  11652|CLM] train=2.2248  mask=10.6%  norm=0.728  lr=1.78e-05  dt=  37.0ms  words=95,461,376
[E08   818/1548 G  11653|CLM] train=3.7075  mask=10.6%  norm=0.885  lr=1.78e-05  dt=  37.0ms  words=95,469,568
[E08   819/1548 G  11654|CLM] train=1.9691  mask=10.6%  norm=0.739  lr=1.78e-05  dt=  36.8ms  words=95,477,760
[E08   820/1548 G  11655|CLM] train=3.7100  mask=10.6%  norm=0.792  lr=1.78e-05  dt=  37.0ms  words=95,485,952
[E08   821/1548 G  11656|CLM] train=4.4943  mask=10.6%  norm=1.457  lr=1.78e-05  dt=  37.1ms  words=95,494,144
[E08   822/1548 G  11657|CLM] train=4.1161  mask=10.6%  norm=0.908  lr=1.78e-05  dt=  36.8ms  words=95,502,336
[E08   823/1548 G  11658|CLM] train=2.2741  mask=10.6%  norm=0.778  lr=1.78e-05  dt=  36.8ms  words=95,510,528
[E08   824/1548 G  11659|CLM] train=3.3011  mask=10.6%  norm=0.775  lr=1.77e-05  dt=  36.9ms  words=95,518,720
[E08   825/1548 G  11660|CLM] train=3.9729  mask=10.6%  norm=0.870  lr=1.77e-05  dt=  37.0ms  words=95,526,912
[E08   826/1548 G  11661|CLM] train=2.3611  mask=10.6%  norm=0.817  lr=1.77e-05  dt=  36.9ms  words=95,535,104
[E08   827/1548 G  11662|CLM] train=4.0373  mask=10.6%  norm=0.941  lr=1.77e-05  dt=  36.7ms  words=95,543,296
[E08   828/1548 G  11663|CLM] train=2.7288  mask=10.6%  norm=0.872  lr=1.77e-05  dt=  36.9ms  words=95,551,488
[E08   829/1548 G  11664|CLM] train=3.8713  mask=10.6%  norm=0.812  lr=1.77e-05  dt=  37.1ms  words=95,559,680
[E08   830/1548 G  11665|CLM] train=3.7552  mask=10.6%  norm=0.875  lr=1.77e-05  dt=  37.0ms  words=95,567,872
[E08   831/1548 G  11666|CLM] train=3.9095  mask=10.6%  norm=0.974  lr=1.77e-05  dt=  36.8ms  words=95,576,064
[E08   832/1548 G  11667|CLM] train=3.4307  mask=10.6%  norm=0.953  lr=1.77e-05  dt=  37.0ms  words=95,584,256
[E08   833/1548 G  11668|CLM] train=2.2591  mask=10.6%  norm=0.701  lr=1.77e-05  dt=  37.4ms  words=95,592,448
[E08   834/1548 G  11669|CLM] train=2.4750  mask=10.6%  norm=0.771  lr=1.77e-05  dt=  37.4ms  words=95,600,640
[E08   835/1548 G  11670|CLM] train=3.7553  mask=10.6%  norm=0.884  lr=1.77e-05  dt=  36.8ms  words=95,608,832
[E08   836/1548 G  11671|CLM] train=3.4793  mask=10.6%  norm=0.859  lr=1.77e-05  dt=  37.1ms  words=95,617,024
[E08   837/1548 G  11672|CLM] train=2.0300  mask=10.6%  norm=0.674  lr=1.76e-05  dt=  36.8ms  words=95,625,216
[E08   838/1548 G  11673|CLM] train=2.2697  mask=10.6%  norm=0.750  lr=1.76e-05  dt=  36.7ms  words=95,633,408
[E08   839/1548 G  11674|CLM] train=2.0725  mask=10.6%  norm=0.830  lr=1.76e-05  dt=  37.0ms  words=95,641,600
[E08   840/1548 G  11675|CLM] train=2.3829  mask=10.6%  norm=0.733  lr=1.76e-05  dt=  37.0ms  words=95,649,792
[E08   841/1548 G  11676|CLM] train=2.0668  mask=10.6%  norm=0.672  lr=1.76e-05  dt=  36.9ms  words=95,657,984
[E08   842/1548 G  11677|CLM] train=2.4206  mask=10.6%  norm=0.721  lr=1.76e-05  dt=  36.9ms  words=95,666,176
[E08   843/1548 G  11678|CLM] train=2.0624  mask=10.6%  norm=0.709  lr=1.76e-05  dt=  36.9ms  words=95,674,368
[E08   844/1548 G  11679|CLM] train=2.2499  mask=10.6%  norm=0.732  lr=1.76e-05  dt=  37.0ms  words=95,682,560
[E08   845/1548 G  11680|CLM] train=1.8395  mask=10.6%  norm=0.754  lr=1.76e-05  dt=  36.8ms  words=95,690,752
[E08   846/1548 G  11681|CLM] train=2.2188  mask=10.6%  norm=0.753  lr=1.76e-05  dt=  36.9ms  words=95,698,944
[E08   847/1548 G  11682|CLM] train=2.3751  mask=10.6%  norm=0.696  lr=1.76e-05  dt=  37.0ms  words=95,707,136
[E08   848/1548 G  11683|CLM] train=3.8656  mask=10.6%  norm=0.872  lr=1.76e-05  dt=  37.0ms  words=95,715,328
[E08   849/1548 G  11684|CLM] train=3.8834  mask=10.6%  norm=0.881  lr=1.76e-05  dt=  36.8ms  words=95,723,520
[E08   850/1548 G  11685|CLM] train=4.3534  mask=10.6%  norm=0.980  lr=1.76e-05  dt=  37.0ms  words=95,731,712
[E08   851/1548 G  11686|CLM] train=3.5771  mask=10.6%  norm=0.901  lr=1.75e-05  dt=  36.9ms  words=95,739,904
[E08   852/1548 G  11687|CLM] train=2.4498  mask=10.6%  norm=0.706  lr=1.75e-05  dt=  36.9ms  words=95,748,096
[E08   853/1548 G  11688|CLM] train=3.5887  mask=10.6%  norm=0.846  lr=1.75e-05  dt=  36.9ms  words=95,756,288
[E08   854/1548 G  11689|CLM] train=4.1381  mask=10.6%  norm=0.828  lr=1.75e-05  dt=  36.9ms  words=95,764,480
[E08   855/1548 G  11690|CLM] train=1.8826  mask=10.6%  norm=0.696  lr=1.75e-05  dt=  36.9ms  words=95,772,672
[E08   856/1548 G  11691|CLM] train=2.2369  mask=10.6%  norm=0.751  lr=1.75e-05  dt=  37.1ms  words=95,780,864
[E08   857/1548 G  11692|CLM] train=1.9537  mask=10.6%  norm=0.717  lr=1.75e-05  dt=  37.2ms  words=95,789,056
[E08   858/1548 G  11693|CLM] train=2.4725  mask=10.6%  norm=1.008  lr=1.75e-05  dt=  36.9ms  words=95,797,248
[E08   859/1548 G  11694|CLM] train=2.1218  mask=10.6%  norm=0.725  lr=1.75e-05  dt=  37.0ms  words=95,805,440
[E08   860/1548 G  11695|CLM] train=2.0140  mask=10.6%  norm=0.760  lr=1.75e-05  dt=  37.2ms  words=95,813,632
[E08   861/1548 G  11696|CLM] train=2.1236  mask=10.6%  norm=0.717  lr=1.75e-05  dt=  37.0ms  words=95,821,824
[E08   862/1548 G  11697|CLM] train=1.7691  mask=10.6%  norm=0.719  lr=1.75e-05  dt=  37.0ms  words=95,830,016
[E08   863/1548 G  11698|CLM] train=2.5211  mask=10.6%  norm=0.839  lr=1.75e-05  dt=  37.0ms  words=95,838,208
[E08   864/1548 G  11699|CLM] train=2.1600  mask=10.6%  norm=0.823  lr=1.75e-05  dt=  36.9ms  words=95,846,400
[E08   865/1548 G  11700|CLM] train=4.7256  mask=10.6%  norm=1.103  lr=1.74e-05  dt=  36.8ms  words=95,854,592
[E08   866/1548 G  11701|CLM] train=4.1337  mask=10.6%  norm=0.930  lr=1.74e-05  dt=  37.3ms  words=95,862,784
[E08   867/1548 G  11702|CLM] train=3.7177  mask=10.6%  norm=0.984  lr=1.74e-05  dt=  36.9ms  words=95,870,976
[E08   868/1548 G  11703|CLM] train=2.1807  mask=10.5%  norm=0.707  lr=1.74e-05  dt=  36.8ms  words=95,879,168
[E08   869/1548 G  11704|CLM] train=1.9312  mask=10.5%  norm=0.749  lr=1.74e-05  dt=  36.8ms  words=95,887,360
[E08   870/1548 G  11705|CLM] train=2.4971  mask=10.5%  norm=0.666  lr=1.74e-05  dt=  36.9ms  words=95,895,552
[E08   871/1548 G  11706|CLM] train=3.4872  mask=10.5%  norm=0.886  lr=1.74e-05  dt=  37.1ms  words=95,903,744
[E08   872/1548 G  11707|CLM] train=2.4462  mask=10.5%  norm=0.799  lr=1.74e-05  dt=  37.1ms  words=95,911,936
[E08   873/1548 G  11708|CLM] train=4.5375  mask=10.5%  norm=0.966  lr=1.74e-05  dt=  37.0ms  words=95,920,128
[E08   874/1548 G  11709|CLM] train=2.0253  mask=10.5%  norm=0.737  lr=1.74e-05  dt=  37.1ms  words=95,928,320
[E08   875/1548 G  11710|CLM] train=3.4221  mask=10.5%  norm=0.785  lr=1.74e-05  dt=  37.1ms  words=95,936,512
[E08   876/1548 G  11711|CLM] train=4.3700  mask=10.5%  norm=1.019  lr=1.74e-05  dt=  36.9ms  words=95,944,704
[E08   877/1548 G  11712|CLM] train=3.7446  mask=10.5%  norm=0.914  lr=1.74e-05  dt=  37.0ms  words=95,952,896
[E08   878/1548 G  11713|CLM] train=3.9103  mask=10.5%  norm=1.097  lr=1.74e-05  dt=  37.1ms  words=95,961,088
[E08   879/1548 G  11714|CLM] train=3.9345  mask=10.5%  norm=0.937  lr=1.73e-05  dt=  36.9ms  words=95,969,280
[E08   880/1548 G  11715|CLM] train=2.0754  mask=10.5%  norm=0.783  lr=1.73e-05  dt=  36.8ms  words=95,977,472
[E08   881/1548 G  11716|CLM] train=2.1108  mask=10.5%  norm=0.983  lr=1.73e-05  dt=  36.9ms  words=95,985,664
[E08   882/1548 G  11717|CLM] train=3.3561  mask=10.5%  norm=0.806  lr=1.73e-05  dt=  37.0ms  words=95,993,856
[E08   883/1548 G  11718|CLM] train=2.0012  mask=10.5%  norm=0.651  lr=1.73e-05  dt=  36.8ms  words=96,002,048
[E08   884/1548 G  11719|CLM] train=4.0980  mask=10.5%  norm=0.925  lr=1.73e-05  dt=  37.0ms  words=96,010,240
[E08   885/1548 G  11720|CLM] train=3.9700  mask=10.5%  norm=1.117  lr=1.73e-05  dt=  36.9ms  words=96,018,432
[E08   886/1548 G  11721|CLM] train=3.7410  mask=10.5%  norm=0.778  lr=1.73e-05  dt=  37.1ms  words=96,026,624
[E08   887/1548 G  11722|CLM] train=1.9828  mask=10.5%  norm=0.856  lr=1.73e-05  dt=  37.3ms  words=96,034,816
[E08   888/1548 G  11723|CLM] train=1.8952  mask=10.5%  norm=0.742  lr=1.73e-05  dt=  37.0ms  words=96,043,008
[E08   889/1548 G  11724|CLM] train=4.1292  mask=10.5%  norm=0.898  lr=1.73e-05  dt=  37.2ms  words=96,051,200
[E08   890/1548 G  11725|CLM] train=3.8015  mask=10.5%  norm=0.882  lr=1.73e-05  dt=  37.0ms  words=96,059,392
[E08   891/1548 G  11726|CLM] train=4.2603  mask=10.5%  norm=0.891  lr=1.73e-05  dt=  37.1ms  words=96,067,584
[E08   892/1548 G  11727|CLM] train=3.8719  mask=10.5%  norm=0.871  lr=1.73e-05  dt=  36.9ms  words=96,075,776
[E08   893/1548 G  11728|CLM] train=4.3006  mask=10.5%  norm=0.915  lr=1.72e-05  dt=  37.0ms  words=96,083,968
[E08   894/1548 G  11729|CLM] train=2.4122  mask=10.5%  norm=0.703  lr=1.72e-05  dt=  36.8ms  words=96,092,160
[E08   895/1548 G  11730|CLM] train=3.3141  mask=10.5%  norm=0.797  lr=1.72e-05  dt=  36.8ms  words=96,100,352
[E08   896/1548 G  11731|CLM] train=2.0743  mask=10.5%  norm=0.842  lr=1.72e-05  dt=  36.9ms  words=96,108,544
[E08   897/1548 G  11732|CLM] train=3.4649  mask=10.5%  norm=0.830  lr=1.72e-05  dt=  37.0ms  words=96,116,736
[E08   898/1548 G  11733|CLM] train=2.1222  mask=10.5%  norm=0.666  lr=1.72e-05  dt=  36.7ms  words=96,124,928
[E08   899/1548 G  11734|CLM] train=2.5572  mask=10.5%  norm=0.757  lr=1.72e-05  dt=  36.9ms  words=96,133,120
[E08   900/1548 G  11735|CLM] train=3.7854  mask=10.5%  norm=0.947  lr=1.72e-05  dt=  37.1ms  words=96,141,312
[E08   901/1548 G  11736|CLM] train=4.0173  mask=10.5%  norm=1.011  lr=1.72e-05  dt=  37.1ms  words=96,149,504
[E08   902/1548 G  11737|CLM] train=2.4803  mask=10.5%  norm=0.760  lr=1.72e-05  dt=  37.4ms  words=96,157,696
[E08   903/1548 G  11738|CLM] train=3.9297  mask=10.5%  norm=0.944  lr=1.72e-05  dt=  37.0ms  words=96,165,888
[E08   904/1548 G  11739|CLM] train=4.1008  mask=10.5%  norm=0.950  lr=1.72e-05  dt=  37.0ms  words=96,174,080
[E08   905/1548 G  11740|CLM] train=1.8553  mask=10.5%  norm=0.680  lr=1.72e-05  dt=  36.9ms  words=96,182,272
[E08   906/1548 G  11741|CLM] train=4.1718  mask=10.5%  norm=0.884  lr=1.72e-05  dt=  36.8ms  words=96,190,464
[E08   907/1548 G  11742|CLM] train=1.9313  mask=10.5%  norm=0.781  lr=1.72e-05  dt=  37.0ms  words=96,198,656
[E08   908/1548 G  11743|CLM] train=3.6555  mask=10.5%  norm=0.870  lr=1.71e-05  dt=  37.1ms  words=96,206,848
[E08   909/1548 G  11744|CLM] train=4.8319  mask=10.5%  norm=1.065  lr=1.71e-05  dt=  36.9ms  words=96,215,040
[E08   910/1548 G  11745|CLM] train=4.5311  mask=10.5%  norm=0.971  lr=1.71e-05  dt=  36.9ms  words=96,223,232
[E08   911/1548 G  11746|CLM] train=4.2842  mask=10.5%  norm=0.944  lr=1.71e-05  dt=  36.9ms  words=96,231,424
[E08   912/1548 G  11747|CLM] train=4.2339  mask=10.5%  norm=0.869  lr=1.71e-05  dt=  37.0ms  words=96,239,616
[E08   913/1548 G  11748|CLM] train=3.5289  mask=10.5%  norm=0.854  lr=1.71e-05  dt=  36.9ms  words=96,247,808
[E08   914/1548 G  11749|CLM] train=2.3435  mask=10.5%  norm=0.735  lr=1.71e-05  dt=  36.9ms  words=96,256,000
[E08   915/1548 G  11750|CLM] train=3.2912  mask=10.5%  norm=0.871  lr=1.71e-05  dt=  37.2ms  words=96,264,192
[E08   916/1548 G  11751|CLM] train=4.4638  mask=10.5%  norm=1.027  lr=1.71e-05  dt=  37.2ms  words=96,272,384
[E08   917/1548 G  11752|CLM] train=4.0590  mask=10.5%  norm=0.851  lr=1.71e-05  dt=  37.1ms  words=96,280,576
[E08   918/1548 G  11753|CLM] train=4.2366  mask=10.5%  norm=1.404  lr=1.71e-05  dt=  37.4ms  words=96,288,768
[E08   919/1548 G  11754|CLM] train=2.0979  mask=10.5%  norm=0.747  lr=1.71e-05  dt=  37.5ms  words=96,296,960
[E08   920/1548 G  11755|CLM] train=3.8513  mask=10.5%  norm=0.857  lr=1.71e-05  dt=  37.1ms  words=96,305,152
[E08   921/1548 G  11756|CLM] train=4.0456  mask=10.5%  norm=0.875  lr=1.71e-05  dt=  37.1ms  words=96,313,344
[E08   922/1548 G  11757|CLM] train=2.4262  mask=10.5%  norm=0.741  lr=1.71e-05  dt=  37.3ms  words=96,321,536
[E08   923/1548 G  11758|CLM] train=2.3335  mask=10.5%  norm=0.845  lr=1.70e-05  dt=  37.0ms  words=96,329,728
[E08   924/1548 G  11759|CLM] train=1.9423  mask=10.5%  norm=0.739  lr=1.70e-05  dt=  37.3ms  words=96,337,920
[E08   925/1548 G  11760|CLM] train=3.7192  mask=10.5%  norm=0.793  lr=1.70e-05  dt=  37.2ms  words=96,346,112
[E08   926/1548 G  11761|CLM] train=3.7535  mask=10.5%  norm=0.929  lr=1.70e-05  dt=  37.0ms  words=96,354,304
[E08   927/1548 G  11762|CLM] train=2.2816  mask=10.5%  norm=0.913  lr=1.70e-05  dt=  37.3ms  words=96,362,496
[E08   928/1548 G  11763|CLM] train=3.6217  mask=10.5%  norm=0.944  lr=1.70e-05  dt=  37.2ms  words=96,370,688
[E08   929/1548 G  11764|CLM] train=3.8448  mask=10.5%  norm=0.972  lr=1.70e-05  dt=  37.2ms  words=96,378,880
[E08   930/1548 G  11765|CLM] train=4.0871  mask=10.5%  norm=0.938  lr=1.70e-05  dt=  37.4ms  words=96,387,072
[E08   931/1548 G  11766|CLM] train=2.3744  mask=10.5%  norm=0.841  lr=1.70e-05  dt=  37.2ms  words=96,395,264
[E08   932/1548 G  11767|CLM] train=4.0222  mask=10.5%  norm=0.880  lr=1.70e-05  dt=  37.1ms  words=96,403,456
[E08   933/1548 G  11768|CLM] train=4.0804  mask=10.5%  norm=0.944  lr=1.70e-05  dt=  37.3ms  words=96,411,648
[E08   934/1548 G  11769|CLM] train=2.1240  mask=10.5%  norm=0.737  lr=1.70e-05  dt=  37.2ms  words=96,419,840
[E08   935/1548 G  11770|CLM] train=2.1019  mask=10.5%  norm=0.687  lr=1.70e-05  dt=  37.1ms  words=96,428,032
[E08   936/1548 G  11771|CLM] train=2.3422  mask=10.5%  norm=0.722  lr=1.70e-05  dt=  37.0ms  words=96,436,224
[E08   937/1548 G  11772|CLM] train=4.6484  mask=10.5%  norm=1.208  lr=1.70e-05  dt=  37.0ms  words=96,444,416
[E08   938/1548 G  11773|CLM] train=3.5675  mask=10.5%  norm=0.872  lr=1.70e-05  dt=  37.1ms  words=96,452,608
[E08   939/1548 G  11774|CLM] train=3.5800  mask=10.5%  norm=0.793  lr=1.69e-05  dt=  37.1ms  words=96,460,800
[E08   940/1548 G  11775|CLM] train=3.5658  mask=10.5%  norm=0.869  lr=1.69e-05  dt=  37.0ms  words=96,468,992
[E08   941/1548 G  11776|CLM] train=2.4236  mask=10.5%  norm=0.749  lr=1.69e-05  dt=  37.2ms  words=96,477,184
[E08   942/1548 G  11777|CLM] train=3.9442  mask=10.5%  norm=0.852  lr=1.69e-05  dt=  37.0ms  words=96,485,376
[E08   943/1548 G  11778|CLM] train=3.4549  mask=10.5%  norm=0.851  lr=1.69e-05  dt=  36.9ms  words=96,493,568
[E08   944/1548 G  11779|CLM] train=4.0420  mask=10.5%  norm=0.856  lr=1.69e-05  dt=  37.0ms  words=96,501,760
[E08   945/1548 G  11780|CLM] train=2.2700  mask=10.5%  norm=0.728  lr=1.69e-05  dt=  37.1ms  words=96,509,952
[E08   946/1548 G  11781|CLM] train=4.0761  mask=10.5%  norm=0.897  lr=1.69e-05  dt=  37.1ms  words=96,518,144
[E08   947/1548 G  11782|CLM] train=4.2172  mask=10.5%  norm=0.945  lr=1.69e-05  dt=  37.1ms  words=96,526,336
[E08   948/1548 G  11783|CLM] train=2.3257  mask=10.5%  norm=0.716  lr=1.69e-05  dt=  37.1ms  words=96,534,528
[E08   949/1548 G  11784|CLM] train=2.2295  mask=10.5%  norm=0.683  lr=1.69e-05  dt=  37.1ms  words=96,542,720
[E08   950/1548 G  11785|CLM] train=2.8036  mask=10.5%  norm=0.869  lr=1.69e-05  dt=  36.8ms  words=96,550,912
[E08   951/1548 G  11786|CLM] train=1.8233  mask=10.5%  norm=0.621  lr=1.69e-05  dt=  37.0ms  words=96,559,104
[E08   952/1548 G  11787|CLM] train=3.8010  mask=10.5%  norm=0.878  lr=1.69e-05  dt=  37.0ms  words=96,567,296
[E08   953/1548 G  11788|CLM] train=2.2971  mask=10.5%  norm=0.753  lr=1.69e-05  dt=  37.3ms  words=96,575,488
[E08   954/1548 G  11789|CLM] train=3.6642  mask=10.5%  norm=0.847  lr=1.69e-05  dt=  37.1ms  words=96,583,680
[E08   955/1548 G  11790|CLM] train=3.1584  mask=10.5%  norm=0.779  lr=1.68e-05  dt=  37.1ms  words=96,591,872
[E08   956/1548 G  11791|CLM] train=4.4395  mask=10.5%  norm=1.114  lr=1.68e-05  dt=  37.3ms  words=96,600,064
[E08   957/1548 G  11792|CLM] train=2.1591  mask=10.5%  norm=0.723  lr=1.68e-05  dt=  37.1ms  words=96,608,256
[E08   958/1548 G  11793|CLM] train=3.9354  mask=10.5%  norm=0.931  lr=1.68e-05  dt=  37.2ms  words=96,616,448
[E08   959/1548 G  11794|CLM] train=1.4949  mask=10.5%  norm=0.662  lr=1.68e-05  dt=  37.1ms  words=96,624,640
[E08   960/1548 G  11795|CLM] train=2.1824  mask=10.5%  norm=0.725  lr=1.68e-05  dt=  37.0ms  words=96,632,832
[E08   961/1548 G  11796|CLM] train=3.9832  mask=10.5%  norm=0.917  lr=1.68e-05  dt=  37.0ms  words=96,641,024
[E08   962/1548 G  11797|CLM] train=1.8807  mask=10.5%  norm=0.733  lr=1.68e-05  dt=  37.1ms  words=96,649,216
[E08   963/1548 G  11798|CLM] train=2.1882  mask=10.5%  norm=0.715  lr=1.68e-05  dt=  37.0ms  words=96,657,408
[E08   964/1548 G  11799|CLM] train=2.1021  mask=10.5%  norm=0.772  lr=1.68e-05  dt=  37.0ms  words=96,665,600
[E08   965/1548 G  11800|CLM] train=3.6979  mask=10.5%  norm=1.006  lr=1.68e-05  dt=  37.2ms  words=96,673,792
[E08   966/1548 G  11801|CLM] train=3.7557  mask=10.5%  norm=0.944  lr=1.68e-05  dt=  37.0ms  words=96,681,984
[E08   967/1548 G  11802|CLM] train=2.2212  mask=10.5%  norm=0.713  lr=1.68e-05  dt=  37.0ms  words=96,690,176
[E08   968/1548 G  11803|CLM] train=4.2103  mask=10.5%  norm=0.896  lr=1.68e-05  dt=  37.1ms  words=96,698,368
[E08   969/1548 G  11804|CLM] train=3.5000  mask=10.5%  norm=0.825  lr=1.68e-05  dt=  37.2ms  words=96,706,560
[E08   970/1548 G  11805|CLM] train=3.3586  mask=10.5%  norm=0.842  lr=1.68e-05  dt=  37.2ms  words=96,714,752
[E08   971/1548 G  11806|CLM] train=3.9933  mask=10.5%  norm=0.923  lr=1.67e-05  dt=  37.1ms  words=96,722,944
[E08   972/1548 G  11807|CLM] train=4.2127  mask=10.5%  norm=0.861  lr=1.67e-05  dt=  37.2ms  words=96,731,136
[E08   973/1548 G  11808|CLM] train=4.0249  mask=10.5%  norm=1.080  lr=1.67e-05  dt=  37.1ms  words=96,739,328
[E08   974/1548 G  11809|CLM] train=4.0609  mask=10.5%  norm=0.945  lr=1.67e-05  dt=  36.9ms  words=96,747,520
[E08   975/1548 G  11810|CLM] train=3.8926  mask=10.5%  norm=1.016  lr=1.67e-05  dt=  36.9ms  words=96,755,712
[E08   976/1548 G  11811|CLM] train=3.8903  mask=10.5%  norm=1.017  lr=1.67e-05  dt=  37.1ms  words=96,763,904
[E08   977/1548 G  11812|CLM] train=4.5375  mask=10.5%  norm=1.045  lr=1.67e-05  dt=  37.2ms  words=96,772,096
[E08   978/1548 G  11813|CLM] train=1.6537  mask=10.5%  norm=0.709  lr=1.67e-05  dt=  37.0ms  words=96,780,288
[E08   979/1548 G  11814|CLM] train=4.5637  mask=10.5%  norm=1.077  lr=1.67e-05  dt=  37.0ms  words=96,788,480
[E08   980/1548 G  11815|CLM] train=2.0760  mask=10.5%  norm=0.779  lr=1.67e-05  dt=  37.0ms  words=96,796,672
[E08   981/1548 G  11816|CLM] train=3.3794  mask=10.5%  norm=0.817  lr=1.67e-05  dt=  37.0ms  words=96,804,864
[E08   982/1548 G  11817|CLM] train=3.9935  mask=10.5%  norm=0.900  lr=1.67e-05  dt=  37.0ms  words=96,813,056
[E08   983/1548 G  11818|CLM] train=2.7435  mask=10.5%  norm=0.778  lr=1.67e-05  dt=  37.1ms  words=96,821,248
[E08   984/1548 G  11819|CLM] train=2.3990  mask=10.5%  norm=0.721  lr=1.67e-05  dt=  36.9ms  words=96,829,440
[E08   985/1548 G  11820|CLM] train=4.0815  mask=10.5%  norm=0.866  lr=1.67e-05  dt=  36.9ms  words=96,837,632
[E08   986/1548 G  11821|CLM] train=3.7459  mask=10.5%  norm=0.937  lr=1.67e-05  dt=  36.9ms  words=96,845,824
[E08   987/1548 G  11822|CLM] train=2.2320  mask=10.5%  norm=0.681  lr=1.67e-05  dt=  37.0ms  words=96,854,016
[E08   988/1548 G  11823|CLM] train=4.5459  mask=10.5%  norm=0.957  lr=1.66e-05  dt=  36.9ms  words=96,862,208
[E08   989/1548 G  11824|CLM] train=2.5926  mask=10.5%  norm=0.746  lr=1.66e-05  dt=  37.2ms  words=96,870,400
[E08   990/1548 G  11825|CLM] train=3.9670  mask=10.5%  norm=0.941  lr=1.66e-05  dt=  37.0ms  words=96,878,592
[E08   991/1548 G  11826|CLM] train=4.3243  mask=10.5%  norm=1.040  lr=1.66e-05  dt=  37.0ms  words=96,886,784
[E08   992/1548 G  11827|CLM] train=4.0471  mask=10.4%  norm=0.872  lr=1.66e-05  dt=  37.2ms  words=96,894,976
[E08   993/1548 G  11828|CLM] train=3.9207  mask=10.4%  norm=0.944  lr=1.66e-05  dt=  37.0ms  words=96,903,168
[E08   994/1548 G  11829|CLM] train=4.1399  mask=10.4%  norm=0.975  lr=1.66e-05  dt=  37.1ms  words=96,911,360
[E08   995/1548 G  11830|CLM] train=2.4964  mask=10.4%  norm=0.696  lr=1.66e-05  dt=  37.2ms  words=96,919,552
[E08   996/1548 G  11831|CLM] train=2.0479  mask=10.4%  norm=0.683  lr=1.66e-05  dt=  37.4ms  words=96,927,744
[E08   997/1548 G  11832|CLM] train=2.4312  mask=10.4%  norm=0.703  lr=1.66e-05  dt=  37.2ms  words=96,935,936
[E08   998/1548 G  11833|CLM] train=1.8798  mask=10.4%  norm=0.772  lr=1.66e-05  dt=  37.2ms  words=96,944,128
[E08   999/1548 G  11834|CLM] train=1.9900  mask=10.4%  norm=0.705  lr=1.66e-05  dt=  37.1ms  words=96,952,320
[E08  1000/1548 G  11835|CLM] train=4.2015  mask=10.4%  norm=0.858  lr=1.66e-05  dt=  37.0ms  words=96,960,512
[E08  1001/1548 G  11836|CLM] train=3.5051  mask=10.4%  norm=0.864  lr=1.66e-05  dt=  36.9ms  words=96,968,704
[E08  1002/1548 G  11837|CLM] train=2.0598  mask=10.4%  norm=0.710  lr=1.66e-05  dt=  36.8ms  words=96,976,896
[E08  1003/1548 G  11838|CLM] train=3.6182  mask=10.4%  norm=0.928  lr=1.66e-05  dt=  37.0ms  words=96,985,088
[E08  1004/1548 G  11839|CLM] train=4.0461  mask=10.4%  norm=0.951  lr=1.66e-05  dt=  37.1ms  words=96,993,280
[E08  1005/1548 G  11840|CLM] train=3.7259  mask=10.4%  norm=0.925  lr=1.65e-05  dt=  36.9ms  words=97,001,472
[E08  1006/1548 G  11841|CLM] train=2.1130  mask=10.4%  norm=0.746  lr=1.65e-05  dt=  37.0ms  words=97,009,664
[E08  1007/1548 G  11842|CLM] train=2.0519  mask=10.4%  norm=0.671  lr=1.65e-05  dt=  37.0ms  words=97,017,856
[E08  1008/1548 G  11843|CLM] train=3.7160  mask=10.4%  norm=0.885  lr=1.65e-05  dt=  37.0ms  words=97,026,048
[E08  1009/1548 G  11844|CLM] train=2.8197  mask=10.4%  norm=1.504  lr=1.65e-05  dt=  37.3ms  words=97,034,240
[E08  1010/1548 G  11845|CLM] train=3.9362  mask=10.4%  norm=0.908  lr=1.65e-05  dt=  37.2ms  words=97,042,432
[E08  1011/1548 G  11846|CLM] train=3.9259  mask=10.4%  norm=1.106  lr=1.65e-05  dt=  37.0ms  words=97,050,624
[E08  1012/1548 G  11847|CLM] train=2.0883  mask=10.4%  norm=0.743  lr=1.65e-05  dt=  37.1ms  words=97,058,816
[E08  1013/1548 G  11848|CLM] train=4.8757  mask=10.4%  norm=0.968  lr=1.65e-05  dt=  37.0ms  words=97,067,008
[E08  1014/1548 G  11849|CLM] train=3.7663  mask=10.4%  norm=0.842  lr=1.65e-05  dt=  36.9ms  words=97,075,200
[E08  1015/1548 G  11850|CLM] train=2.4687  mask=10.4%  norm=0.756  lr=1.65e-05  dt=  37.1ms  words=97,083,392
[E08  1016/1548 G  11851|CLM] train=3.8668  mask=10.4%  norm=0.932  lr=1.65e-05  dt=  37.0ms  words=97,091,584
[E08  1017/1548 G  11852|CLM] train=2.5348  mask=10.4%  norm=0.744  lr=1.65e-05  dt=  37.1ms  words=97,099,776
[E08  1018/1548 G  11853|CLM] train=3.8087  mask=10.4%  norm=1.109  lr=1.65e-05  dt=  37.2ms  words=97,107,968
[E08  1019/1548 G  11854|CLM] train=3.7792  mask=10.4%  norm=0.944  lr=1.65e-05  dt=  36.9ms  words=97,116,160
[E08  1020/1548 G  11855|CLM] train=4.1507  mask=10.4%  norm=0.890  lr=1.65e-05  dt=  36.7ms  words=97,124,352
[E08  1021/1548 G  11856|CLM] train=4.1723  mask=10.4%  norm=0.910  lr=1.65e-05  dt=  37.0ms  words=97,132,544
[E08  1022/1548 G  11857|CLM] train=3.9821  mask=10.4%  norm=0.908  lr=1.65e-05  dt=  37.2ms  words=97,140,736
[E08  1023/1548 G  11858|CLM] train=4.0433  mask=10.4%  norm=0.813  lr=1.64e-05  dt=  37.3ms  words=97,148,928
[E08  1024/1548 G  11859|CLM] train=3.9489  mask=10.4%  norm=0.986  lr=1.64e-05  dt=  37.1ms  words=97,157,120
[E08  1025/1548 G  11860|CLM] train=4.0903  mask=10.4%  norm=0.809  lr=1.64e-05  dt=  37.1ms  words=97,165,312
[E08  1026/1548 G  11861|CLM] train=2.1326  mask=10.4%  norm=0.707  lr=1.64e-05  dt=  37.0ms  words=97,173,504
[E08  1027/1548 G  11862|CLM] train=2.0493  mask=10.4%  norm=0.688  lr=1.64e-05  dt=  37.0ms  words=97,181,696
[E08  1028/1548 G  11863|CLM] train=3.8456  mask=10.4%  norm=1.118  lr=1.64e-05  dt=  37.0ms  words=97,189,888
[E08  1029/1548 G  11864|CLM] train=2.6244  mask=10.4%  norm=0.778  lr=1.64e-05  dt=  37.0ms  words=97,198,080
[E08  1030/1548 G  11865|CLM] train=4.0796  mask=10.4%  norm=0.904  lr=1.64e-05  dt=  37.0ms  words=97,206,272
[E08  1031/1548 G  11866|CLM] train=1.8614  mask=10.4%  norm=0.744  lr=1.64e-05  dt=  37.2ms  words=97,214,464
[E08  1032/1548 G  11867|CLM] train=4.5564  mask=10.4%  norm=0.883  lr=1.64e-05  dt=  37.1ms  words=97,222,656
[E08  1033/1548 G  11868|CLM] train=3.9396  mask=10.4%  norm=0.878  lr=1.64e-05  dt=  37.0ms  words=97,230,848
[E08  1034/1548 G  11869|CLM] train=4.7648  mask=10.4%  norm=0.975  lr=1.64e-05  dt=  36.9ms  words=97,239,040
[E08  1035/1548 G  11870|CLM] train=2.4370  mask=10.4%  norm=0.716  lr=1.64e-05  dt=  37.0ms  words=97,247,232
[E08  1036/1548 G  11871|CLM] train=3.8806  mask=10.4%  norm=0.857  lr=1.64e-05  dt=  37.0ms  words=97,255,424
[E08  1037/1548 G  11872|CLM] train=4.1527  mask=10.4%  norm=0.960  lr=1.64e-05  dt=  36.9ms  words=97,263,616
[E08  1038/1548 G  11873|CLM] train=2.0104  mask=10.4%  norm=0.876  lr=1.64e-05  dt=  36.9ms  words=97,271,808
[E08  1039/1548 G  11874|CLM] train=2.1564  mask=10.4%  norm=0.773  lr=1.64e-05  dt=  36.9ms  words=97,280,000
[E08  1040/1548 G  11875|CLM] train=4.7175  mask=10.4%  norm=0.997  lr=1.64e-05  dt=  37.0ms  words=97,288,192
[E08  1041/1548 G  11876|CLM] train=3.9681  mask=10.4%  norm=1.046  lr=1.64e-05  dt=  36.9ms  words=97,296,384
[E08  1042/1548 G  11877|CLM] train=2.1824  mask=10.4%  norm=0.677  lr=1.63e-05  dt=  36.8ms  words=97,304,576
[E08  1043/1548 G  11878|CLM] train=4.7910  mask=10.4%  norm=1.175  lr=1.63e-05  dt=  36.9ms  words=97,312,768
[E08  1044/1548 G  11879|CLM] train=3.6064  mask=10.4%  norm=0.820  lr=1.63e-05  dt=  37.1ms  words=97,320,960
[E08  1045/1548 G  11880|CLM] train=3.7996  mask=10.4%  norm=0.882  lr=1.63e-05  dt=  36.9ms  words=97,329,152
[E08  1046/1548 G  11881|CLM] train=2.5133  mask=10.4%  norm=0.909  lr=1.63e-05  dt=  37.0ms  words=97,337,344
[E08  1047/1548 G  11882|CLM] train=4.4115  mask=10.4%  norm=0.969  lr=1.63e-05  dt=  37.0ms  words=97,345,536
[E08  1048/1548 G  11883|CLM] train=4.1198  mask=10.4%  norm=0.845  lr=1.63e-05  dt=  37.3ms  words=97,353,728
[E08  1049/1548 G  11884|CLM] train=3.7312  mask=10.4%  norm=0.822  lr=1.63e-05  dt=  37.8ms  words=97,361,920
[E08  1050/1548 G  11885|CLM] train=4.2163  mask=10.4%  norm=0.935  lr=1.63e-05  dt=  39.4ms  words=97,370,112
[E08  1051/1548 G  11886|CLM] train=5.1947  mask=10.4%  norm=1.280  lr=1.63e-05  dt=  44.4ms  words=97,378,304
[E08  1052/1548 G  11887|CLM] train=3.9402  mask=10.4%  norm=1.007  lr=1.63e-05  dt=  42.3ms  words=97,386,496
[E08  1053/1548 G  11888|CLM] train=4.1469  mask=10.4%  norm=0.997  lr=1.63e-05  dt=  43.8ms  words=97,394,688
[E08  1054/1548 G  11889|CLM] train=1.9892  mask=10.4%  norm=0.794  lr=1.63e-05  dt=  39.3ms  words=97,402,880
[E08  1055/1548 G  11890|CLM] train=3.7443  mask=10.4%  norm=1.059  lr=1.63e-05  dt=  37.9ms  words=97,411,072
[E08  1056/1548 G  11891|CLM] train=2.3715  mask=10.4%  norm=0.717  lr=1.63e-05  dt=  39.3ms  words=97,419,264
[E08  1057/1548 G  11892|CLM] train=5.1847  mask=10.4%  norm=1.335  lr=1.63e-05  dt=  42.4ms  words=97,427,456
[E08  1058/1548 G  11893|CLM] train=4.0052  mask=10.4%  norm=0.929  lr=1.63e-05  dt=  40.3ms  words=97,435,648
[E08  1059/1548 G  11894|CLM] train=3.7205  mask=10.4%  norm=1.061  lr=1.63e-05  dt=  38.5ms  words=97,443,840
[E08  1060/1548 G  11895|CLM] train=2.2409  mask=10.4%  norm=0.769  lr=1.63e-05  dt=  46.9ms  words=97,452,032
[E08  1061/1548 G  11896|CLM] train=4.0755  mask=10.4%  norm=0.932  lr=1.62e-05  dt=  52.3ms  words=97,460,224
[E08  1062/1548 G  11897|CLM] train=3.4974  mask=10.4%  norm=0.929  lr=1.62e-05  dt=  40.4ms  words=97,468,416
[E08  1063/1548 G  11898|CLM] train=4.4593  mask=10.4%  norm=0.939  lr=1.62e-05  dt=  42.9ms  words=97,476,608
[E08  1064/1548 G  11899|CLM] train=4.1645  mask=10.4%  norm=0.891  lr=1.62e-05  dt=  41.1ms  words=97,484,800
[E08  1065/1548 G  11900|CLM] train=1.8743  mask=10.4%  norm=0.756  lr=1.62e-05  dt=  39.3ms  words=97,492,992
[E08  1066/1548 G  11901|CLM] train=1.9501  mask=10.4%  norm=0.685  lr=1.62e-05  dt=  38.4ms  words=97,501,184
[E08  1067/1548 G  11902|CLM] train=2.1960  mask=10.4%  norm=0.654  lr=1.62e-05  dt=  42.9ms  words=97,509,376
[E08  1068/1548 G  11903|CLM] train=4.0179  mask=10.4%  norm=0.866  lr=1.62e-05  dt=  43.9ms  words=97,517,568
[E08  1069/1548 G  11904|CLM] train=4.3532  mask=10.4%  norm=0.981  lr=1.62e-05  dt=  36.8ms  words=97,525,760
[E08  1070/1548 G  11905|CLM] train=2.2178  mask=10.4%  norm=0.721  lr=1.62e-05  dt=  37.5ms  words=97,533,952
[E08  1071/1548 G  11906|CLM] train=4.2930  mask=10.4%  norm=0.937  lr=1.62e-05  dt=  37.3ms  words=97,542,144
[E08  1072/1548 G  11907|CLM] train=2.2033  mask=10.4%  norm=0.737  lr=1.62e-05  dt=  47.2ms  words=97,550,336
[E08  1073/1548 G  11908|CLM] train=4.3885  mask=10.4%  norm=0.956  lr=1.62e-05  dt=  40.5ms  words=97,558,528
[E08  1074/1548 G  11909|CLM] train=2.2995  mask=10.4%  norm=0.647  lr=1.62e-05  dt=  40.2ms  words=97,566,720
[E08  1075/1548 G  11910|CLM] train=3.9641  mask=10.4%  norm=1.116  lr=1.62e-05  dt=  36.9ms  words=97,574,912
[E08  1076/1548 G  11911|CLM] train=4.1931  mask=10.4%  norm=0.851  lr=1.62e-05  dt=  36.9ms  words=97,583,104
[E08  1077/1548 G  11912|CLM] train=3.8312  mask=10.4%  norm=0.898  lr=1.62e-05  dt=  37.2ms  words=97,591,296
[E08  1078/1548 G  11913|CLM] train=3.8212  mask=10.4%  norm=0.916  lr=1.62e-05  dt=  36.8ms  words=97,599,488
[E08  1079/1548 G  11914|CLM] train=3.5213  mask=10.4%  norm=0.873  lr=1.62e-05  dt=  36.7ms  words=97,607,680
[E08  1080/1548 G  11915|CLM] train=3.3097  mask=10.4%  norm=0.868  lr=1.62e-05  dt=  36.9ms  words=97,615,872
[E08  1081/1548 G  11916|CLM] train=1.9583  mask=10.4%  norm=0.699  lr=1.61e-05  dt=  37.0ms  words=97,624,064
[E08  1082/1548 G  11917|CLM] train=4.0142  mask=10.4%  norm=0.849  lr=1.61e-05  dt=  37.0ms  words=97,632,256
[E08  1083/1548 G  11918|CLM] train=2.4272  mask=10.4%  norm=0.710  lr=1.61e-05  dt=  36.8ms  words=97,640,448
[E08  1084/1548 G  11919|CLM] train=4.3359  mask=10.4%  norm=1.003  lr=1.61e-05  dt=  36.9ms  words=97,648,640
[E08  1085/1548 G  11920|CLM] train=1.7564  mask=10.4%  norm=0.694  lr=1.61e-05  dt=  37.0ms  words=97,656,832
[E08  1086/1548 G  11921|CLM] train=3.9183  mask=10.4%  norm=1.042  lr=1.61e-05  dt=  37.0ms  words=97,665,024
[E08  1087/1548 G  11922|CLM] train=3.6105  mask=10.4%  norm=0.867  lr=1.61e-05  dt=  36.9ms  words=97,673,216
[E08  1088/1548 G  11923|CLM] train=2.3597  mask=10.4%  norm=0.864  lr=1.61e-05  dt=  36.8ms  words=97,681,408
[E08  1089/1548 G  11924|CLM] train=4.4405  mask=10.4%  norm=0.989  lr=1.61e-05  dt=  37.0ms  words=97,689,600
[E08  1090/1548 G  11925|CLM] train=3.8249  mask=10.4%  norm=0.773  lr=1.61e-05  dt=  36.9ms  words=97,697,792
[E08  1091/1548 G  11926|CLM] train=3.9657  mask=10.4%  norm=0.927  lr=1.61e-05  dt=  36.8ms  words=97,705,984
[E08  1092/1548 G  11927|CLM] train=2.0661  mask=10.4%  norm=0.817  lr=1.61e-05  dt=  36.9ms  words=97,714,176
[E08  1093/1548 G  11928|CLM] train=3.7136  mask=10.4%  norm=0.974  lr=1.61e-05  dt=  37.0ms  words=97,722,368
[E08  1094/1548 G  11929|CLM] train=2.3645  mask=10.4%  norm=0.710  lr=1.61e-05  dt=  36.9ms  words=97,730,560
[E08  1095/1548 G  11930|CLM] train=2.3100  mask=10.4%  norm=0.836  lr=1.61e-05  dt=  37.8ms  words=97,738,752
[E08  1096/1548 G  11931|CLM] train=3.9536  mask=10.4%  norm=0.998  lr=1.61e-05  dt=  36.8ms  words=97,746,944
[E08  1097/1548 G  11932|CLM] train=2.2188  mask=10.4%  norm=0.719  lr=1.61e-05  dt=  36.9ms  words=97,755,136
[E08  1098/1548 G  11933|CLM] train=2.2850  mask=10.4%  norm=0.690  lr=1.61e-05  dt=  36.8ms  words=97,763,328
[E08  1099/1548 G  11934|CLM] train=2.0570  mask=10.4%  norm=0.748  lr=1.61e-05  dt=  36.7ms  words=97,771,520
[E08  1100/1548 G  11935|CLM] train=3.9133  mask=10.4%  norm=0.841  lr=1.61e-05  dt=  36.8ms  words=97,779,712
[E08  1101/1548 G  11936|CLM] train=4.5050  mask=10.4%  norm=1.018  lr=1.61e-05  dt=  36.9ms  words=97,787,904
[E08  1102/1548 G  11937|CLM] train=4.1559  mask=10.4%  norm=0.866  lr=1.60e-05  dt=  36.9ms  words=97,796,096
[E08  1103/1548 G  11938|CLM] train=2.4517  mask=10.4%  norm=0.718  lr=1.60e-05  dt=  37.1ms  words=97,804,288
[E08  1104/1548 G  11939|CLM] train=4.1436  mask=10.4%  norm=0.883  lr=1.60e-05  dt=  38.0ms  words=97,812,480
[E08  1105/1548 G  11940|CLM] train=4.3654  mask=10.4%  norm=1.010  lr=1.60e-05  dt=  39.0ms  words=97,820,672
[E08  1106/1548 G  11941|CLM] train=3.6385  mask=10.4%  norm=0.910  lr=1.60e-05  dt=  37.0ms  words=97,828,864
[E08  1107/1548 G  11942|CLM] train=2.0762  mask=10.4%  norm=0.787  lr=1.60e-05  dt=  36.8ms  words=97,837,056
[E08  1108/1548 G  11943|CLM] train=2.1594  mask=10.4%  norm=0.712  lr=1.60e-05  dt=  36.7ms  words=97,845,248
[E08  1109/1548 G  11944|CLM] train=3.7388  mask=10.4%  norm=0.784  lr=1.60e-05  dt=  36.7ms  words=97,853,440
[E08  1110/1548 G  11945|CLM] train=4.8230  mask=10.4%  norm=1.072  lr=1.60e-05  dt=  36.8ms  words=97,861,632
[E08  1111/1548 G  11946|CLM] train=4.2368  mask=10.4%  norm=0.908  lr=1.60e-05  dt=  36.9ms  words=97,869,824
[E08  1112/1548 G  11947|CLM] train=2.2377  mask=10.4%  norm=0.693  lr=1.60e-05  dt=  36.8ms  words=97,878,016
[E08  1113/1548 G  11948|CLM] train=3.7367  mask=10.4%  norm=1.035  lr=1.60e-05  dt=  36.9ms  words=97,886,208
[E08  1114/1548 G  11949|CLM] train=3.1988  mask=10.4%  norm=0.773  lr=1.60e-05  dt=  37.0ms  words=97,894,400
[E08  1115/1548 G  11950|CLM] train=2.0245  mask=10.4%  norm=0.637  lr=1.60e-05  dt=  36.9ms  words=97,902,592
[E08  1116/1548 G  11951|CLM] train=4.3200  mask=10.3%  norm=0.923  lr=1.60e-05  dt=  36.8ms  words=97,910,784
[E08  1117/1548 G  11952|CLM] train=3.7391  mask=10.3%  norm=0.855  lr=1.60e-05  dt=  36.9ms  words=97,918,976
[E08  1118/1548 G  11953|CLM] train=3.6716  mask=10.3%  norm=0.899  lr=1.60e-05  dt=  37.0ms  words=97,927,168
[E08  1119/1548 G  11954|CLM] train=2.0670  mask=10.3%  norm=0.829  lr=1.60e-05  dt=  36.9ms  words=97,935,360
[E08  1120/1548 G  11955|CLM] train=1.9933  mask=10.3%  norm=0.678  lr=1.60e-05  dt=  36.8ms  words=97,943,552
[E08  1121/1548 G  11956|CLM] train=2.5715  mask=10.3%  norm=0.863  lr=1.60e-05  dt=  37.0ms  words=97,951,744
[E08  1122/1548 G  11957|CLM] train=3.8142  mask=10.3%  norm=0.915  lr=1.60e-05  dt=  37.0ms  words=97,959,936
[E08  1123/1548 G  11958|CLM] train=3.5473  mask=10.3%  norm=0.909  lr=1.59e-05  dt=  36.9ms  words=97,968,128
[E08  1124/1548 G  11959|CLM] train=4.4741  mask=10.3%  norm=0.991  lr=1.59e-05  dt=  36.8ms  words=97,976,320
[E08  1125/1548 G  11960|CLM] train=3.5676  mask=10.3%  norm=0.908  lr=1.59e-05  dt=  36.9ms  words=97,984,512
[E08  1126/1548 G  11961|CLM] train=2.0834  mask=10.3%  norm=0.673  lr=1.59e-05  dt=  37.0ms  words=97,992,704
[E08  1127/1548 G  11962|CLM] train=4.0671  mask=10.3%  norm=0.970  lr=1.59e-05  dt=  37.0ms  words=98,000,896
[E08  1128/1548 G  11963|CLM] train=3.6463  mask=10.3%  norm=0.864  lr=1.59e-05  dt=  37.0ms  words=98,009,088
[E08  1129/1548 G  11964|CLM] train=1.9818  mask=10.3%  norm=0.696  lr=1.59e-05  dt=  36.8ms  words=98,017,280
[E08  1130/1548 G  11965|CLM] train=3.6815  mask=10.3%  norm=0.810  lr=1.59e-05  dt=  37.0ms  words=98,025,472
[E08  1131/1548 G  11966|CLM] train=1.7169  mask=10.3%  norm=0.885  lr=1.59e-05  dt=  36.8ms  words=98,033,664
[E08  1132/1548 G  11967|CLM] train=3.1884  mask=10.3%  norm=0.802  lr=1.59e-05  dt=  36.9ms  words=98,041,856
[E08  1133/1548 G  11968|CLM] train=3.9961  mask=10.3%  norm=0.921  lr=1.59e-05  dt=  37.0ms  words=98,050,048
[E08  1134/1548 G  11969|CLM] train=2.7142  mask=10.3%  norm=0.849  lr=1.59e-05  dt=  36.9ms  words=98,058,240
[E08  1135/1548 G  11970|CLM] train=4.2482  mask=10.3%  norm=0.914  lr=1.59e-05  dt=  36.7ms  words=98,066,432
[E08  1136/1548 G  11971|CLM] train=3.5873  mask=10.3%  norm=0.898  lr=1.59e-05  dt=  36.9ms  words=98,074,624
[E08  1137/1548 G  11972|CLM] train=1.9471  mask=10.3%  norm=0.735  lr=1.59e-05  dt=  36.9ms  words=98,082,816
[E08  1138/1548 G  11973|CLM] train=2.0830  mask=10.3%  norm=0.719  lr=1.59e-05  dt=  36.9ms  words=98,091,008
[E08  1139/1548 G  11974|CLM] train=2.1698  mask=10.3%  norm=0.711  lr=1.59e-05  dt=  37.9ms  words=98,099,200
[E08  1140/1548 G  11975|CLM] train=2.5289  mask=10.3%  norm=0.696  lr=1.59e-05  dt=  36.9ms  words=98,107,392
[E08  1141/1548 G  11976|CLM] train=3.9795  mask=10.3%  norm=1.045  lr=1.59e-05  dt=  37.0ms  words=98,115,584
[E08  1142/1548 G  11977|CLM] train=4.1494  mask=10.3%  norm=0.968  lr=1.59e-05  dt=  37.0ms  words=98,123,776
[E08  1143/1548 G  11978|CLM] train=2.5760  mask=10.3%  norm=0.778  lr=1.59e-05  dt=  37.1ms  words=98,131,968
[E08  1144/1548 G  11979|CLM] train=3.6559  mask=10.3%  norm=0.819  lr=1.59e-05  dt=  37.0ms  words=98,140,160
[E08  1145/1548 G  11980|CLM] train=4.5653  mask=10.3%  norm=1.237  lr=1.59e-05  dt=  37.2ms  words=98,148,352
[E08  1146/1548 G  11981|CLM] train=3.9755  mask=10.3%  norm=0.909  lr=1.59e-05  dt=  37.0ms  words=98,156,544
[E08  1147/1548 G  11982|CLM] train=3.9794  mask=10.3%  norm=0.927  lr=1.58e-05  dt=  37.1ms  words=98,164,736
[E08  1148/1548 G  11983|CLM] train=2.5067  mask=10.3%  norm=0.760  lr=1.58e-05  dt=  37.0ms  words=98,172,928
[E08  1149/1548 G  11984|CLM] train=2.0816  mask=10.3%  norm=0.686  lr=1.58e-05  dt=  37.2ms  words=98,181,120
[E08  1150/1548 G  11985|CLM] train=4.6141  mask=10.3%  norm=1.052  lr=1.58e-05  dt=  37.1ms  words=98,189,312
[E08  1151/1548 G  11986|CLM] train=2.0337  mask=10.3%  norm=0.741  lr=1.58e-05  dt=  37.0ms  words=98,197,504
[E08  1152/1548 G  11987|CLM] train=1.9879  mask=10.3%  norm=0.791  lr=1.58e-05  dt=  37.1ms  words=98,205,696
[E08  1153/1548 G  11988|CLM] train=1.9954  mask=10.3%  norm=0.762  lr=1.58e-05  dt=  37.0ms  words=98,213,888
[E08  1154/1548 G  11989|CLM] train=1.7125  mask=10.3%  norm=0.650  lr=1.58e-05  dt=  36.9ms  words=98,222,080
[E08  1155/1548 G  11990|CLM] train=3.7635  mask=10.3%  norm=0.845  lr=1.58e-05  dt=  37.0ms  words=98,230,272
[E08  1156/1548 G  11991|CLM] train=3.9329  mask=10.3%  norm=0.826  lr=1.58e-05  dt=  37.0ms  words=98,238,464
[E08  1157/1548 G  11992|CLM] train=3.5049  mask=10.3%  norm=0.911  lr=1.58e-05  dt=  37.0ms  words=98,246,656
[E08  1158/1548 G  11993|CLM] train=3.7338  mask=10.3%  norm=0.812  lr=1.58e-05  dt=  37.0ms  words=98,254,848
[E08  1159/1548 G  11994|CLM] train=4.1633  mask=10.3%  norm=0.949  lr=1.58e-05  dt=  37.0ms  words=98,263,040
[E08  1160/1548 G  11995|CLM] train=4.5576  mask=10.3%  norm=0.983  lr=1.58e-05  dt=  37.1ms  words=98,271,232
[E08  1161/1548 G  11996|CLM] train=3.8199  mask=10.3%  norm=0.867  lr=1.58e-05  dt=  36.8ms  words=98,279,424
[E08  1162/1548 G  11997|CLM] train=2.0738  mask=10.3%  norm=0.775  lr=1.58e-05  dt=  37.1ms  words=98,287,616
[E08  1163/1548 G  11998|CLM] train=2.3023  mask=10.3%  norm=0.779  lr=1.58e-05  dt=  37.2ms  words=98,295,808
[E08  1164/1548 G  11999|CLM] train=4.7530  mask=10.3%  norm=1.688  lr=1.58e-05  dt=  37.1ms  words=98,304,000
[E08  1165/1548 G  12000|CLM] train=2.1488  mask=10.3%  norm=0.717  lr=1.58e-05  dt=  36.9ms  words=98,312,192
[E08  1166/1548 G  12001|CLM] train=4.2088  mask=10.3%  norm=0.911  lr=1.58e-05  dt=  37.0ms  words=98,320,384
[E08  1167/1548 G  12002|CLM] train=4.3493  mask=10.3%  norm=0.924  lr=1.58e-05  dt=  37.0ms  words=98,328,576
[E08  1168/1548 G  12003|CLM] train=4.1247  mask=10.3%  norm=0.944  lr=1.58e-05  dt=  37.1ms  words=98,336,768
[E08  1169/1548 G  12004|CLM] train=2.3446  mask=10.3%  norm=0.726  lr=1.58e-05  dt=  37.1ms  words=98,344,960
[E08  1170/1548 G  12005|CLM] train=2.4485  mask=10.3%  norm=0.723  lr=1.58e-05  dt=  37.1ms  words=98,353,152
[E08  1171/1548 G  12006|CLM] train=3.5760  mask=10.3%  norm=0.898  lr=1.57e-05  dt=  37.0ms  words=98,361,344
[E08  1172/1548 G  12007|CLM] train=2.5685  mask=10.3%  norm=0.907  lr=1.57e-05  dt=  37.0ms  words=98,369,536
[E08  1173/1548 G  12008|CLM] train=3.5062  mask=10.3%  norm=1.028  lr=1.57e-05  dt=  37.0ms  words=98,377,728
[E08  1174/1548 G  12009|CLM] train=1.8327  mask=10.3%  norm=0.780  lr=1.57e-05  dt=  37.0ms  words=98,385,920
[E08  1175/1548 G  12010|CLM] train=2.1307  mask=10.3%  norm=0.693  lr=1.57e-05  dt=  37.0ms  words=98,394,112
[E08  1176/1548 G  12011|CLM] train=4.8734  mask=10.3%  norm=1.074  lr=1.57e-05  dt=  36.9ms  words=98,402,304
[E08  1177/1548 G  12012|CLM] train=3.9588  mask=10.3%  norm=1.078  lr=1.57e-05  dt=  36.9ms  words=98,410,496
[E08  1178/1548 G  12013|CLM] train=2.2475  mask=10.3%  norm=0.708  lr=1.57e-05  dt=  37.0ms  words=98,418,688
[E08  1179/1548 G  12014|CLM] train=2.0706  mask=10.3%  norm=0.656  lr=1.57e-05  dt=  36.9ms  words=98,426,880
[E08  1180/1548 G  12015|CLM] train=1.9672  mask=10.3%  norm=0.731  lr=1.57e-05  dt=  36.9ms  words=98,435,072
[E08  1181/1548 G  12016|CLM] train=4.5364  mask=10.3%  norm=1.236  lr=1.57e-05  dt=  37.0ms  words=98,443,264
[E08  1182/1548 G  12017|CLM] train=3.7399  mask=10.3%  norm=0.945  lr=1.57e-05  dt=  37.0ms  words=98,451,456
[E08  1183/1548 G  12018|CLM] train=2.4989  mask=10.3%  norm=0.921  lr=1.57e-05  dt=  36.9ms  words=98,459,648
[E08  1184/1548 G  12019|CLM] train=4.0421  mask=10.3%  norm=1.327  lr=1.57e-05  dt=  36.9ms  words=98,467,840
[E08  1185/1548 G  12020|CLM] train=4.2441  mask=10.3%  norm=0.980  lr=1.57e-05  dt=  36.9ms  words=98,476,032
[E08  1186/1548 G  12021|CLM] train=2.1941  mask=10.3%  norm=0.741  lr=1.57e-05  dt=  37.1ms  words=98,484,224
[E08  1187/1548 G  12022|CLM] train=4.3472  mask=10.3%  norm=1.001  lr=1.57e-05  dt=  37.0ms  words=98,492,416
[E08  1188/1548 G  12023|CLM] train=3.4895  mask=10.3%  norm=0.815  lr=1.57e-05  dt=  37.2ms  words=98,500,608
[E08  1189/1548 G  12024|CLM] train=2.0173  mask=10.3%  norm=0.740  lr=1.57e-05  dt=  37.2ms  words=98,508,800
[E08  1190/1548 G  12025|CLM] train=2.3310  mask=10.3%  norm=0.790  lr=1.57e-05  dt=  36.9ms  words=98,516,992
[E08  1191/1548 G  12026|CLM] train=4.1857  mask=10.3%  norm=0.906  lr=1.57e-05  dt=  36.9ms  words=98,525,184
[E08  1192/1548 G  12027|CLM] train=4.3054  mask=10.3%  norm=0.922  lr=1.57e-05  dt=  36.9ms  words=98,533,376
[E08  1193/1548 G  12028|CLM] train=4.0368  mask=10.3%  norm=0.924  lr=1.57e-05  dt=  37.0ms  words=98,541,568
[E08  1194/1548 G  12029|CLM] train=2.1069  mask=10.3%  norm=0.647  lr=1.57e-05  dt=  36.9ms  words=98,549,760
[E08  1195/1548 G  12030|CLM] train=4.0420  mask=10.3%  norm=0.975  lr=1.57e-05  dt=  37.1ms  words=98,557,952
[E08  1196/1548 G  12031|CLM] train=2.0825  mask=10.3%  norm=0.720  lr=1.57e-05  dt=  36.8ms  words=98,566,144
[E08  1197/1548 G  12032|CLM] train=4.5339  mask=10.3%  norm=0.929  lr=1.56e-05  dt=  37.0ms  words=98,574,336
[E08  1198/1548 G  12033|CLM] train=4.0162  mask=10.3%  norm=0.903  lr=1.56e-05  dt=  36.9ms  words=98,582,528
[E08  1199/1548 G  12034|CLM] train=3.7310  mask=10.3%  norm=0.814  lr=1.56e-05  dt=  37.0ms  words=98,590,720
[E08  1200/1548 G  12035|CLM] train=2.5596  mask=10.3%  norm=0.707  lr=1.56e-05  dt=  37.0ms  words=98,598,912
[E08  1201/1548 G  12036|CLM] train=3.4288  mask=10.3%  norm=0.828  lr=1.56e-05  dt=  37.0ms  words=98,607,104
[E08  1202/1548 G  12037|CLM] train=2.3560  mask=10.3%  norm=0.724  lr=1.56e-05  dt=  37.0ms  words=98,615,296
[E08  1203/1548 G  12038|CLM] train=3.9504  mask=10.3%  norm=0.881  lr=1.56e-05  dt=  37.0ms  words=98,623,488
[E08  1204/1548 G  12039|CLM] train=1.3294  mask=10.3%  norm=0.618  lr=1.56e-05  dt=  37.1ms  words=98,631,680
[E08  1205/1548 G  12040|CLM] train=4.0673  mask=10.3%  norm=1.066  lr=1.56e-05  dt=  37.0ms  words=98,639,872
[E08  1206/1548 G  12041|CLM] train=4.9230  mask=10.3%  norm=0.977  lr=1.56e-05  dt=  37.0ms  words=98,648,064
[E08  1207/1548 G  12042|CLM] train=1.9854  mask=10.3%  norm=0.811  lr=1.56e-05  dt=  36.9ms  words=98,656,256
[E08  1208/1548 G  12043|CLM] train=3.9429  mask=10.3%  norm=0.915  lr=1.56e-05  dt=  37.1ms  words=98,664,448
[E08  1209/1548 G  12044|CLM] train=2.0233  mask=10.3%  norm=0.648  lr=1.56e-05  dt=  37.1ms  words=98,672,640
[E08  1210/1548 G  12045|CLM] train=4.1437  mask=10.3%  norm=0.929  lr=1.56e-05  dt=  37.2ms  words=98,680,832
[E08  1211/1548 G  12046|CLM] train=3.1047  mask=10.3%  norm=0.877  lr=1.56e-05  dt=  37.0ms  words=98,689,024
[E08  1212/1548 G  12047|CLM] train=4.3133  mask=10.3%  norm=1.110  lr=1.56e-05  dt=  37.0ms  words=98,697,216
[E08  1213/1548 G  12048|CLM] train=1.9919  mask=10.3%  norm=0.654  lr=1.56e-05  dt=  36.9ms  words=98,705,408
[E08  1214/1548 G  12049|CLM] train=3.7222  mask=10.3%  norm=0.873  lr=1.56e-05  dt=  37.0ms  words=98,713,600
[E08  1215/1548 G  12050|CLM] train=2.0700  mask=10.3%  norm=0.795  lr=1.56e-05  dt=  37.1ms  words=98,721,792
[E08  1216/1548 G  12051|CLM] train=1.9027  mask=10.3%  norm=0.703  lr=1.56e-05  dt=  36.9ms  words=98,729,984
[E08  1217/1548 G  12052|CLM] train=4.2431  mask=10.3%  norm=0.898  lr=1.56e-05  dt=  36.8ms  words=98,738,176
[E08  1218/1548 G  12053|CLM] train=3.7902  mask=10.3%  norm=0.975  lr=1.56e-05  dt=  37.0ms  words=98,746,368
[E08  1219/1548 G  12054|CLM] train=3.7570  mask=10.3%  norm=0.855  lr=1.56e-05  dt=  37.1ms  words=98,754,560
[E08  1220/1548 G  12055|CLM] train=4.0862  mask=10.3%  norm=1.054  lr=1.56e-05  dt=  36.9ms  words=98,762,752
[E08  1221/1548 G  12056|CLM] train=3.9600  mask=10.3%  norm=0.824  lr=1.56e-05  dt=  36.8ms  words=98,770,944
[E08  1222/1548 G  12057|CLM] train=5.2499  mask=10.3%  norm=1.921  lr=1.56e-05  dt=  37.2ms  words=98,779,136
[E08  1223/1548 G  12058|CLM] train=3.8188  mask=10.3%  norm=1.083  lr=1.56e-05  dt=  37.1ms  words=98,787,328
[E08  1224/1548 G  12059|CLM] train=2.0352  mask=10.3%  norm=0.655  lr=1.56e-05  dt=  37.1ms  words=98,795,520
[E08  1225/1548 G  12060|CLM] train=3.5613  mask=10.3%  norm=0.899  lr=1.55e-05  dt=  37.0ms  words=98,803,712
[E08  1226/1548 G  12061|CLM] train=2.3769  mask=10.3%  norm=0.726  lr=1.55e-05  dt=  37.3ms  words=98,811,904
[E08  1227/1548 G  12062|CLM] train=1.9533  mask=10.3%  norm=0.781  lr=1.55e-05  dt=  37.0ms  words=98,820,096
[E08  1228/1548 G  12063|CLM] train=4.2737  mask=10.3%  norm=0.937  lr=1.55e-05  dt=  37.3ms  words=98,828,288
[E08  1229/1548 G  12064|CLM] train=2.2232  mask=10.3%  norm=0.777  lr=1.55e-05  dt=  37.5ms  words=98,836,480
[E08  1230/1548 G  12065|CLM] train=5.4348  mask=10.3%  norm=1.468  lr=1.55e-05  dt=  37.3ms  words=98,844,672
[E08  1231/1548 G  12066|CLM] train=1.9535  mask=10.3%  norm=0.733  lr=1.55e-05  dt=  37.1ms  words=98,852,864
[E08  1232/1548 G  12067|CLM] train=2.4381  mask=10.3%  norm=0.691  lr=1.55e-05  dt=  37.1ms  words=98,861,056
[E08  1233/1548 G  12068|CLM] train=2.0875  mask=10.3%  norm=0.817  lr=1.55e-05  dt=  37.0ms  words=98,869,248
[E08  1234/1548 G  12069|CLM] train=2.1467  mask=10.3%  norm=0.715  lr=1.55e-05  dt=  36.9ms  words=98,877,440
[E08  1235/1548 G  12070|CLM] train=2.5216  mask=10.3%  norm=0.771  lr=1.55e-05  dt=  37.0ms  words=98,885,632
[E08  1236/1548 G  12071|CLM] train=4.4313  mask=10.3%  norm=0.904  lr=1.55e-05  dt=  37.0ms  words=98,893,824
[E08  1237/1548 G  12072|CLM] train=3.5572  mask=10.3%  norm=0.886  lr=1.55e-05  dt=  37.0ms  words=98,902,016
[E08  1238/1548 G  12073|CLM] train=3.1340  mask=10.3%  norm=0.753  lr=1.55e-05  dt=  36.9ms  words=98,910,208
[E08  1239/1548 G  12074|CLM] train=4.2728  mask=10.3%  norm=0.993  lr=1.55e-05  dt=  36.9ms  words=98,918,400
[E08  1240/1548 G  12075|CLM] train=4.3490  mask=10.2%  norm=1.280  lr=1.55e-05  dt=  37.1ms  words=98,926,592
[E08  1241/1548 G  12076|CLM] train=2.3455  mask=10.2%  norm=0.729  lr=1.55e-05  dt=  37.0ms  words=98,934,784
[E08  1242/1548 G  12077|CLM] train=2.2064  mask=10.2%  norm=0.699  lr=1.55e-05  dt=  37.0ms  words=98,942,976
[E08  1243/1548 G  12078|CLM] train=4.1749  mask=10.2%  norm=0.932  lr=1.55e-05  dt=  37.1ms  words=98,951,168
[E08  1244/1548 G  12079|CLM] train=2.0074  mask=10.2%  norm=0.783  lr=1.55e-05  dt=  36.9ms  words=98,959,360
[E08  1245/1548 G  12080|CLM] train=2.2408  mask=10.2%  norm=0.829  lr=1.55e-05  dt=  36.9ms  words=98,967,552
[E08  1246/1548 G  12081|CLM] train=3.5051  mask=10.2%  norm=0.915  lr=1.55e-05  dt=  37.0ms  words=98,975,744
[E08  1247/1548 G  12082|CLM] train=3.8438  mask=10.2%  norm=0.890  lr=1.55e-05  dt=  37.2ms  words=98,983,936
[E08  1248/1548 G  12083|CLM] train=4.1471  mask=10.2%  norm=0.930  lr=1.55e-05  dt=  36.8ms  words=98,992,128
[E08  1249/1548 G  12084|CLM] train=2.4008  mask=10.2%  norm=0.711  lr=1.55e-05  dt=  36.8ms  words=99,000,320
[E08  1250/1548 G  12085|CLM] train=4.8126  mask=10.2%  norm=1.082  lr=1.55e-05  dt=  37.2ms  words=99,008,512
[E08  1251/1548 G  12086|CLM] train=3.9345  mask=10.2%  norm=0.999  lr=1.55e-05  dt=  37.0ms  words=99,016,704
[E08  1252/1548 G  12087|CLM] train=3.8655  mask=10.2%  norm=0.929  lr=1.55e-05  dt=  36.8ms  words=99,024,896
[E08  1253/1548 G  12088|CLM] train=4.2086  mask=10.2%  norm=0.845  lr=1.55e-05  dt=  37.0ms  words=99,033,088
[E08  1254/1548 G  12089|CLM] train=3.6866  mask=10.2%  norm=0.860  lr=1.55e-05  dt=  36.9ms  words=99,041,280
[E08  1255/1548 G  12090|CLM] train=1.9192  mask=10.2%  norm=0.786  lr=1.55e-05  dt=  36.9ms  words=99,049,472
[E08  1256/1548 G  12091|CLM] train=4.1282  mask=10.2%  norm=0.871  lr=1.54e-05  dt=  36.8ms  words=99,057,664
[E08  1257/1548 G  12092|CLM] train=3.4683  mask=10.2%  norm=0.856  lr=1.54e-05  dt=  37.0ms  words=99,065,856
[E08  1258/1548 G  12093|CLM] train=2.0135  mask=10.2%  norm=0.800  lr=1.54e-05  dt=  36.8ms  words=99,074,048
[E08  1259/1548 G  12094|CLM] train=4.1295  mask=10.2%  norm=0.909  lr=1.54e-05  dt=  37.0ms  words=99,082,240
[E08  1260/1548 G  12095|CLM] train=1.9284  mask=10.2%  norm=0.723  lr=1.54e-05  dt=  36.8ms  words=99,090,432
[E08  1261/1548 G  12096|CLM] train=2.0370  mask=10.2%  norm=0.669  lr=1.54e-05  dt=  37.0ms  words=99,098,624
[E08  1262/1548 G  12097|CLM] train=3.0981  mask=10.2%  norm=0.778  lr=1.54e-05  dt=  37.1ms  words=99,106,816
[E08  1263/1548 G  12098|CLM] train=2.5362  mask=10.2%  norm=0.735  lr=1.54e-05  dt=  37.2ms  words=99,115,008
[E08  1264/1548 G  12099|CLM] train=3.1537  mask=10.2%  norm=0.902  lr=1.54e-05  dt=  37.1ms  words=99,123,200
[E08  1265/1548 G  12100|CLM] train=3.8517  mask=10.2%  norm=0.900  lr=1.54e-05  dt=  37.0ms  words=99,131,392
[E08  1266/1548 G  12101|CLM] train=2.1780  mask=10.2%  norm=0.762  lr=1.54e-05  dt=  37.0ms  words=99,139,584
[E08  1267/1548 G  12102|CLM] train=2.0740  mask=10.2%  norm=0.680  lr=1.54e-05  dt=  36.9ms  words=99,147,776
[E08  1268/1548 G  12103|CLM] train=2.2916  mask=10.2%  norm=0.671  lr=1.54e-05  dt=  37.0ms  words=99,155,968
[E08  1269/1548 G  12104|CLM] train=4.4304  mask=10.2%  norm=1.041  lr=1.54e-05  dt=  36.9ms  words=99,164,160
[E08  1270/1548 G  12105|CLM] train=2.1375  mask=10.2%  norm=0.739  lr=1.54e-05  dt=  37.0ms  words=99,172,352
[E08  1271/1548 G  12106|CLM] train=3.4397  mask=10.2%  norm=0.846  lr=1.54e-05  dt=  36.8ms  words=99,180,544
[E08  1272/1548 G  12107|CLM] train=4.3325  mask=10.2%  norm=1.138  lr=1.54e-05  dt=  36.9ms  words=99,188,736
[E08  1273/1548 G  12108|CLM] train=4.7331  mask=10.2%  norm=1.175  lr=1.54e-05  dt=  36.9ms  words=99,196,928
[E08  1274/1548 G  12109|CLM] train=2.1718  mask=10.2%  norm=0.750  lr=1.54e-05  dt=  37.0ms  words=99,205,120
[E08  1275/1548 G  12110|CLM] train=4.8442  mask=10.2%  norm=1.054  lr=1.54e-05  dt=  36.9ms  words=99,213,312
[E08  1276/1548 G  12111|CLM] train=1.9423  mask=10.2%  norm=0.728  lr=1.54e-05  dt=  37.6ms  words=99,221,504
[E08  1277/1548 G  12112|CLM] train=2.1914  mask=10.2%  norm=0.718  lr=1.54e-05  dt=  37.2ms  words=99,229,696
[E08  1278/1548 G  12113|CLM] train=4.0633  mask=10.2%  norm=1.075  lr=1.54e-05  dt=  36.9ms  words=99,237,888
[E08  1279/1548 G  12114|CLM] train=2.2813  mask=10.2%  norm=0.713  lr=1.54e-05  dt=  37.0ms  words=99,246,080
[E08  1280/1548 G  12115|CLM] train=4.2660  mask=10.2%  norm=1.030  lr=1.54e-05  dt=  37.0ms  words=99,254,272
[E08  1281/1548 G  12116|CLM] train=4.4407  mask=10.2%  norm=1.034  lr=1.54e-05  dt=  37.1ms  words=99,262,464
[E08  1282/1548 G  12117|CLM] train=4.0325  mask=10.2%  norm=0.909  lr=1.54e-05  dt=  36.8ms  words=99,270,656
[E08  1283/1548 G  12118|CLM] train=3.7340  mask=10.2%  norm=0.854  lr=1.54e-05  dt=  36.7ms  words=99,278,848
[E08  1284/1548 G  12119|CLM] train=2.1198  mask=10.2%  norm=0.805  lr=1.54e-05  dt=  36.9ms  words=99,287,040
[E08  1285/1548 G  12120|CLM] train=3.9491  mask=10.2%  norm=0.866  lr=1.54e-05  dt=  37.1ms  words=99,295,232
[E08  1286/1548 G  12121|CLM] train=2.0919  mask=10.2%  norm=0.708  lr=1.54e-05  dt=  36.8ms  words=99,303,424
[E08  1287/1548 G  12122|CLM] train=2.5593  mask=10.2%  norm=1.574  lr=1.54e-05  dt=  36.8ms  words=99,311,616
[E08  1288/1548 G  12123|CLM] train=3.8134  mask=10.2%  norm=0.824  lr=1.54e-05  dt=  37.1ms  words=99,319,808
[E08  1289/1548 G  12124|CLM] train=3.5170  mask=10.2%  norm=0.865  lr=1.54e-05  dt=  37.0ms  words=99,328,000
[E08  1290/1548 G  12125|CLM] train=4.0213  mask=10.2%  norm=0.915  lr=1.54e-05  dt=  36.8ms  words=99,336,192
[E08  1291/1548 G  12126|CLM] train=4.1739  mask=10.2%  norm=0.868  lr=1.53e-05  dt=  36.8ms  words=99,344,384
[E08  1292/1548 G  12127|CLM] train=2.5476  mask=10.2%  norm=0.766  lr=1.53e-05  dt=  37.2ms  words=99,352,576
[E08  1293/1548 G  12128|CLM] train=2.0595  mask=10.2%  norm=0.841  lr=1.53e-05  dt=  37.1ms  words=99,360,768
[E08  1294/1548 G  12129|CLM] train=2.1311  mask=10.2%  norm=0.718  lr=1.53e-05  dt=  36.9ms  words=99,368,960
[E08  1295/1548 G  12130|CLM] train=2.6484  mask=10.2%  norm=0.829  lr=1.53e-05  dt=  37.0ms  words=99,377,152
[E08  1296/1548 G  12131|CLM] train=4.1091  mask=10.2%  norm=0.843  lr=1.53e-05  dt=  36.9ms  words=99,385,344
[E08  1297/1548 G  12132|CLM] train=1.9052  mask=10.2%  norm=0.799  lr=1.53e-05  dt=  37.1ms  words=99,393,536
[E08  1298/1548 G  12133|CLM] train=3.5156  mask=10.2%  norm=0.871  lr=1.53e-05  dt=  37.0ms  words=99,401,728
[E08  1299/1548 G  12134|CLM] train=4.0529  mask=10.2%  norm=0.980  lr=1.53e-05  dt=  37.0ms  words=99,409,920
[E08  1300/1548 G  12135|CLM] train=2.4658  mask=10.2%  norm=0.723  lr=1.53e-05  dt=  37.0ms  words=99,418,112
[E08  1301/1548 G  12136|CLM] train=3.4980  mask=10.2%  norm=0.899  lr=1.53e-05  dt=  36.9ms  words=99,426,304
[E08  1302/1548 G  12137|CLM] train=2.6998  mask=10.2%  norm=0.752  lr=1.53e-05  dt=  37.2ms  words=99,434,496
[E08  1303/1548 G  12138|CLM] train=4.4132  mask=10.2%  norm=0.920  lr=1.53e-05  dt=  37.3ms  words=99,442,688
[E08  1304/1548 G  12139|CLM] train=3.7797  mask=10.2%  norm=0.868  lr=1.53e-05  dt=  37.5ms  words=99,450,880
[E08  1305/1548 G  12140|CLM] train=2.0872  mask=10.2%  norm=0.705  lr=1.53e-05  dt=  36.8ms  words=99,459,072
[E08  1306/1548 G  12141|CLM] train=4.0359  mask=10.2%  norm=0.883  lr=1.53e-05  dt=  36.9ms  words=99,467,264
[E08  1307/1548 G  12142|CLM] train=2.1988  mask=10.2%  norm=0.720  lr=1.53e-05  dt=  37.0ms  words=99,475,456
[E08  1308/1548 G  12143|CLM] train=2.1558  mask=10.2%  norm=0.719  lr=1.53e-05  dt=  36.9ms  words=99,483,648
[E08  1309/1548 G  12144|CLM] train=2.1559  mask=10.2%  norm=0.698  lr=1.53e-05  dt=  36.9ms  words=99,491,840
[E08  1310/1548 G  12145|CLM] train=3.3046  mask=10.2%  norm=0.825  lr=1.53e-05  dt=  36.9ms  words=99,500,032
[E08  1311/1548 G  12146|CLM] train=2.0599  mask=10.2%  norm=0.713  lr=1.53e-05  dt=  37.0ms  words=99,508,224
[E08  1312/1548 G  12147|CLM] train=2.1750  mask=10.2%  norm=0.718  lr=1.53e-05  dt=  36.9ms  words=99,516,416
[E08  1313/1548 G  12148|CLM] train=4.1330  mask=10.2%  norm=0.972  lr=1.53e-05  dt=  36.9ms  words=99,524,608
[E08  1314/1548 G  12149|CLM] train=2.2424  mask=10.2%  norm=0.747  lr=1.53e-05  dt=  36.9ms  words=99,532,800
[E08  1315/1548 G  12150|CLM] train=2.1795  mask=10.2%  norm=0.753  lr=1.53e-05  dt=  37.1ms  words=99,540,992
[E08  1316/1548 G  12151|CLM] train=3.4890  mask=10.2%  norm=0.958  lr=1.53e-05  dt=  38.2ms  words=99,549,184
[E08  1317/1548 G  12152|CLM] train=3.9860  mask=10.2%  norm=0.856  lr=1.53e-05  dt=  40.2ms  words=99,557,376
[E08  1318/1548 G  12153|CLM] train=3.6369  mask=10.2%  norm=0.936  lr=1.53e-05  dt=  37.1ms  words=99,565,568
[E08  1319/1548 G  12154|CLM] train=3.6684  mask=10.2%  norm=0.918  lr=1.53e-05  dt=  37.0ms  words=99,573,760
[E08  1320/1548 G  12155|CLM] train=3.9104  mask=10.2%  norm=0.868  lr=1.53e-05  dt=  36.9ms  words=99,581,952
[E08  1321/1548 G  12156|CLM] train=3.8347  mask=10.2%  norm=0.936  lr=1.53e-05  dt=  36.9ms  words=99,590,144
[E08  1322/1548 G  12157|CLM] train=2.3159  mask=10.2%  norm=0.718  lr=1.53e-05  dt=  37.1ms  words=99,598,336
[E08  1323/1548 G  12158|CLM] train=1.7395  mask=10.2%  norm=0.713  lr=1.53e-05  dt=  36.8ms  words=99,606,528
[E08  1324/1548 G  12159|CLM] train=3.5055  mask=10.2%  norm=0.867  lr=1.53e-05  dt=  37.0ms  words=99,614,720
[E08  1325/1548 G  12160|CLM] train=2.4420  mask=10.2%  norm=0.792  lr=1.53e-05  dt=  37.0ms  words=99,622,912
[E08  1326/1548 G  12161|CLM] train=2.1750  mask=10.2%  norm=0.677  lr=1.53e-05  dt=  37.2ms  words=99,631,104
[E08  1327/1548 G  12162|CLM] train=4.1685  mask=10.2%  norm=0.905  lr=1.53e-05  dt=  36.8ms  words=99,639,296
[E08  1328/1548 G  12163|CLM] train=4.2059  mask=10.2%  norm=0.890  lr=1.53e-05  dt=  36.7ms  words=99,647,488
[E08  1329/1548 G  12164|CLM] train=3.8662  mask=10.2%  norm=0.876  lr=1.53e-05  dt=  36.9ms  words=99,655,680
[E08  1330/1548 G  12165|CLM] train=4.3171  mask=10.2%  norm=0.906  lr=1.53e-05  dt=  37.2ms  words=99,663,872
[E08  1331/1548 G  12166|CLM] train=3.8366  mask=10.2%  norm=0.831  lr=1.52e-05  dt=  37.1ms  words=99,672,064
[E08  1332/1548 G  12167|CLM] train=3.6750  mask=10.2%  norm=0.925  lr=1.52e-05  dt=  37.0ms  words=99,680,256
[E08  1333/1548 G  12168|CLM] train=2.0117  mask=10.2%  norm=0.735  lr=1.52e-05  dt=  37.0ms  words=99,688,448
[E08  1334/1548 G  12169|CLM] train=2.2714  mask=10.2%  norm=0.688  lr=1.52e-05  dt=  37.0ms  words=99,696,640
[E08  1335/1548 G  12170|CLM] train=1.8095  mask=10.2%  norm=0.684  lr=1.52e-05  dt=  36.9ms  words=99,704,832
[E08  1336/1548 G  12171|CLM] train=3.8039  mask=10.2%  norm=0.858  lr=1.52e-05  dt=  37.0ms  words=99,713,024
[E08  1337/1548 G  12172|CLM] train=3.9766  mask=10.2%  norm=0.894  lr=1.52e-05  dt=  37.0ms  words=99,721,216
[E08  1338/1548 G  12173|CLM] train=4.2776  mask=10.2%  norm=1.022  lr=1.52e-05  dt=  36.9ms  words=99,729,408
[E08  1339/1548 G  12174|CLM] train=5.2676  mask=10.2%  norm=1.158  lr=1.52e-05  dt=  36.8ms  words=99,737,600
[E08  1340/1548 G  12175|CLM] train=4.1056  mask=10.2%  norm=0.994  lr=1.52e-05  dt=  37.0ms  words=99,745,792
[E08  1341/1548 G  12176|CLM] train=3.9165  mask=10.2%  norm=0.836  lr=1.52e-05  dt=  37.1ms  words=99,753,984
[E08  1342/1548 G  12177|CLM] train=1.9410  mask=10.2%  norm=0.741  lr=1.52e-05  dt=  36.9ms  words=99,762,176
[E08  1343/1548 G  12178|CLM] train=4.1591  mask=10.2%  norm=0.890  lr=1.52e-05  dt=  36.8ms  words=99,770,368
[E08  1344/1548 G  12179|CLM] train=3.9119  mask=10.2%  norm=0.808  lr=1.52e-05  dt=  36.9ms  words=99,778,560
[E08  1345/1548 G  12180|CLM] train=1.6306  mask=10.2%  norm=0.665  lr=1.52e-05  dt=  37.0ms  words=99,786,752
[E08  1346/1548 G  12181|CLM] train=1.9900  mask=10.2%  norm=0.678  lr=1.52e-05  dt=  36.9ms  words=99,794,944
[E08  1347/1548 G  12182|CLM] train=4.1170  mask=10.2%  norm=0.970  lr=1.52e-05  dt=  36.8ms  words=99,803,136
[E08  1348/1548 G  12183|CLM] train=2.2211  mask=10.2%  norm=0.690  lr=1.52e-05  dt=  36.9ms  words=99,811,328
[E08  1349/1548 G  12184|CLM] train=2.3518  mask=10.2%  norm=0.764  lr=1.52e-05  dt=  36.9ms  words=99,819,520
[E08  1350/1548 G  12185|CLM] train=2.3161  mask=10.2%  norm=0.824  lr=1.52e-05  dt=  37.0ms  words=99,827,712
[E08  1351/1548 G  12186|CLM] train=3.8007  mask=10.2%  norm=0.963  lr=1.52e-05  dt=  36.8ms  words=99,835,904
[E08  1352/1548 G  12187|CLM] train=3.9365  mask=10.2%  norm=0.834  lr=1.52e-05  dt=  37.0ms  words=99,844,096
[E08  1353/1548 G  12188|CLM] train=1.4099  mask=10.2%  norm=0.633  lr=1.52e-05  dt=  37.0ms  words=99,852,288
[E08  1354/1548 G  12189|CLM] train=2.0588  mask=10.2%  norm=0.666  lr=1.52e-05  dt=  36.9ms  words=99,860,480
[E08  1355/1548 G  12190|CLM] train=4.5903  mask=10.2%  norm=0.946  lr=1.52e-05  dt=  38.0ms  words=99,868,672
[E08  1356/1548 G  12191|CLM] train=3.7242  mask=10.2%  norm=0.952  lr=1.52e-05  dt=  37.1ms  words=99,876,864
[E08  1357/1548 G  12192|CLM] train=3.3924  mask=10.2%  norm=0.819  lr=1.52e-05  dt=  36.9ms  words=99,885,056
[E08  1358/1548 G  12193|CLM] train=2.0666  mask=10.2%  norm=0.678  lr=1.52e-05  dt=  36.9ms  words=99,893,248
[E08  1359/1548 G  12194|CLM] train=4.0511  mask=10.2%  norm=0.914  lr=1.52e-05  dt=  36.8ms  words=99,901,440
[E08  1360/1548 G  12195|CLM] train=4.2960  mask=10.2%  norm=0.863  lr=1.52e-05  dt=  37.1ms  words=99,909,632
[E08  1361/1548 G  12196|CLM] train=1.9158  mask=10.2%  norm=0.715  lr=1.52e-05  dt=  36.9ms  words=99,917,824
[E08  1362/1548 G  12197|CLM] train=2.1640  mask=10.2%  norm=0.720  lr=1.52e-05  dt=  36.8ms  words=99,926,016
[E08  1363/1548 G  12198|CLM] train=4.1256  mask=10.2%  norm=0.845  lr=1.52e-05  dt=  37.0ms  words=99,934,208
[E08  1364/1548 G  12199|CLM] train=4.0034  mask=10.1%  norm=1.029  lr=1.52e-05  dt=  37.0ms  words=99,942,400
[E08  1365/1548 G  12200|CLM] train=4.3244  mask=10.1%  norm=1.051  lr=1.52e-05  dt=  36.8ms  words=99,950,592
[E08  1366/1548 G  12201|CLM] train=1.7421  mask=10.1%  norm=0.712  lr=1.52e-05  dt=  36.8ms  words=99,958,784
[E08  1367/1548 G  12202|CLM] train=3.9683  mask=10.1%  norm=0.989  lr=1.52e-05  dt=  36.9ms  words=99,966,976
[E08  1368/1548 G  12203|CLM] train=4.7953  mask=10.1%  norm=1.113  lr=1.52e-05  dt=  37.1ms  words=99,975,168
[E08  1369/1548 G  12204|CLM] train=3.5668  mask=10.1%  norm=0.903  lr=1.52e-05  dt=  36.9ms  words=99,983,360
[E08  1370/1548 G  12205|CLM] train=2.3219  mask=10.1%  norm=0.769  lr=1.52e-05  dt=  36.8ms  words=99,991,552
[E08  1371/1548 G  12206|CLM] train=3.9900  mask=10.1%  norm=0.887  lr=1.52e-05  dt=  36.9ms  words=99,999,744
[E08  1372/1548 G  12207|CLM] train=1.6179  mask=10.1%  norm=0.676  lr=1.52e-05  dt=  37.0ms  words=100,007,936

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/chck_100M'...
[Checkpoint] Checkpoint 'chck_100M' successfully saved.
[E08  1373/1548 G  12208|CLM] train=2.1782  mask=10.1%  norm=0.747  lr=1.52e-05  dt=  37.7ms  words=100,016,128
[E08  1374/1548 G  12209|CLM] train=4.0268  mask=10.1%  norm=0.901  lr=1.52e-05  dt=  37.1ms  words=100,024,320
[E08  1375/1548 G  12210|CLM] train=2.1478  mask=10.1%  norm=0.699  lr=1.52e-05  dt=  37.1ms  words=100,032,512
[E08  1376/1548 G  12211|CLM] train=4.4083  mask=10.1%  norm=1.135  lr=1.52e-05  dt=  37.1ms  words=100,040,704
[E08  1377/1548 G  12212|CLM] train=2.0141  mask=10.1%  norm=0.843  lr=1.52e-05  dt=  36.9ms  words=100,048,896
[E08  1378/1548 G  12213|CLM] train=2.0979  mask=10.1%  norm=0.658  lr=1.52e-05  dt=  37.2ms  words=100,057,088
[E08  1379/1548 G  12214|CLM] train=5.0845  mask=10.1%  norm=1.014  lr=1.52e-05  dt=  36.9ms  words=100,065,280
[E08  1380/1548 G  12215|CLM] train=3.9904  mask=10.1%  norm=0.907  lr=1.51e-05  dt=  37.0ms  words=100,073,472
[E08  1381/1548 G  12216|CLM] train=4.3828  mask=10.1%  norm=0.934  lr=1.51e-05  dt=  37.1ms  words=100,081,664
[E08  1382/1548 G  12217|CLM] train=1.8882  mask=10.1%  norm=0.737  lr=1.51e-05  dt=  37.1ms  words=100,089,856
[E08  1383/1548 G  12218|CLM] train=2.1693  mask=10.1%  norm=0.710  lr=1.51e-05  dt=  37.3ms  words=100,098,048
[E08  1384/1548 G  12219|CLM] train=4.3816  mask=10.1%  norm=0.922  lr=1.51e-05  dt=  37.0ms  words=100,106,240
[E08  1385/1548 G  12220|CLM] train=4.2413  mask=10.1%  norm=0.885  lr=1.51e-05  dt=  36.8ms  words=100,114,432
[E08  1386/1548 G  12221|CLM] train=4.0524  mask=10.1%  norm=0.963  lr=1.51e-05  dt=  36.9ms  words=100,122,624
[E08  1387/1548 G  12222|CLM] train=2.0270  mask=10.1%  norm=0.702  lr=1.51e-05  dt=  37.0ms  words=100,130,816
[E08  1388/1548 G  12223|CLM] train=2.3491  mask=10.1%  norm=0.710  lr=1.51e-05  dt=  36.8ms  words=100,139,008
[E08  1389/1548 G  12224|CLM] train=2.0353  mask=10.1%  norm=0.703  lr=1.51e-05  dt=  37.0ms  words=100,147,200
[E08  1390/1548 G  12225|CLM] train=1.9437  mask=10.1%  norm=0.711  lr=1.51e-05  dt=  36.9ms  words=100,155,392
[E08  1391/1548 G  12226|CLM] train=4.5096  mask=10.1%  norm=1.119  lr=1.51e-05  dt=  37.0ms  words=100,163,584
[E08  1392/1548 G  12227|CLM] train=4.2473  mask=10.1%  norm=0.947  lr=1.51e-05  dt=  36.9ms  words=100,171,776
[E08  1393/1548 G  12228|CLM] train=4.1913  mask=10.1%  norm=0.988  lr=1.51e-05  dt=  37.0ms  words=100,179,968
[E08  1394/1548 G  12229|CLM] train=4.2396  mask=10.1%  norm=0.947  lr=1.51e-05  dt=  36.9ms  words=100,188,160
[E08  1395/1548 G  12230|CLM] train=2.1585  mask=10.1%  norm=0.676  lr=1.51e-05  dt=  36.9ms  words=100,196,352
[E08  1396/1548 G  12231|CLM] train=3.5789  mask=10.1%  norm=0.904  lr=1.51e-05  dt=  36.9ms  words=100,204,544
[E08  1397/1548 G  12232|CLM] train=1.9829  mask=10.1%  norm=0.807  lr=1.51e-05  dt=  37.2ms  words=100,212,736
[E08  1398/1548 G  12233|CLM] train=2.7238  mask=10.1%  norm=1.272  lr=1.51e-05  dt=  37.1ms  words=100,220,928
[E08  1399/1548 G  12234|CLM] train=4.4857  mask=10.1%  norm=1.096  lr=1.51e-05  dt=  37.1ms  words=100,229,120
[E08  1400/1548 G  12235|CLM] train=2.3813  mask=10.1%  norm=0.734  lr=1.51e-05  dt=  36.9ms  words=100,237,312
[E08  1401/1548 G  12236|CLM] train=2.4462  mask=10.1%  norm=0.866  lr=1.51e-05  dt=  37.1ms  words=100,245,504
[E08  1402/1548 G  12237|CLM] train=4.6153  mask=10.1%  norm=0.926  lr=1.51e-05  dt=  37.1ms  words=100,253,696
[E08  1403/1548 G  12238|CLM] train=4.6193  mask=10.1%  norm=1.125  lr=1.51e-05  dt=  36.8ms  words=100,261,888
[E08  1404/1548 G  12239|CLM] train=2.4435  mask=10.1%  norm=0.813  lr=1.51e-05  dt=  36.9ms  words=100,270,080
[E08  1405/1548 G  12240|CLM] train=4.7015  mask=10.1%  norm=1.233  lr=1.51e-05  dt=  36.9ms  words=100,278,272
[E08  1406/1548 G  12241|CLM] train=3.9672  mask=10.1%  norm=1.235  lr=1.51e-05  dt=  37.1ms  words=100,286,464
[E08  1407/1548 G  12242|CLM] train=2.4717  mask=10.1%  norm=0.707  lr=1.51e-05  dt=  36.9ms  words=100,294,656
[E08  1408/1548 G  12243|CLM] train=3.8990  mask=10.1%  norm=0.825  lr=1.51e-05  dt=  37.2ms  words=100,302,848
[E08  1409/1548 G  12244|CLM] train=4.9695  mask=10.1%  norm=1.115  lr=1.51e-05  dt=  37.1ms  words=100,311,040
[E08  1410/1548 G  12245|CLM] train=3.7607  mask=10.1%  norm=1.117  lr=1.51e-05  dt=  37.0ms  words=100,319,232
[E08  1411/1548 G  12246|CLM] train=3.9181  mask=10.1%  norm=0.867  lr=1.51e-05  dt=  37.0ms  words=100,327,424
[E08  1412/1548 G  12247|CLM] train=3.9502  mask=10.1%  norm=0.944  lr=1.51e-05  dt=  36.9ms  words=100,335,616
[E08  1413/1548 G  12248|CLM] train=4.8508  mask=10.1%  norm=1.114  lr=1.51e-05  dt=  37.1ms  words=100,343,808
[E08  1414/1548 G  12249|CLM] train=4.8947  mask=10.1%  norm=1.096  lr=1.51e-05  dt=  36.9ms  words=100,352,000
[E08  1415/1548 G  12250|CLM] train=3.3424  mask=10.1%  norm=0.830  lr=1.51e-05  dt=  36.9ms  words=100,360,192
[E08  1416/1548 G  12251|CLM] train=2.1943  mask=10.1%  norm=0.696  lr=1.51e-05  dt=  36.9ms  words=100,368,384
[E08  1417/1548 G  12252|CLM] train=3.3658  mask=10.1%  norm=0.828  lr=1.51e-05  dt=  37.6ms  words=100,376,576
[E08  1418/1548 G  12253|CLM] train=2.4800  mask=10.1%  norm=0.743  lr=1.51e-05  dt=  37.1ms  words=100,384,768
[E08  1419/1548 G  12254|CLM] train=3.9527  mask=10.1%  norm=0.944  lr=1.51e-05  dt=  36.9ms  words=100,392,960
[E08  1420/1548 G  12255|CLM] train=4.0960  mask=10.1%  norm=0.921  lr=1.51e-05  dt=  37.1ms  words=100,401,152
[E08  1421/1548 G  12256|CLM] train=2.2401  mask=10.1%  norm=0.797  lr=1.51e-05  dt=  37.2ms  words=100,409,344
[E08  1422/1548 G  12257|CLM] train=3.5575  mask=10.1%  norm=0.922  lr=1.51e-05  dt=  36.8ms  words=100,417,536
[E08  1423/1548 G  12258|CLM] train=4.2499  mask=10.1%  norm=0.994  lr=1.51e-05  dt=  36.9ms  words=100,425,728
[E08  1424/1548 G  12259|CLM] train=3.2013  mask=10.1%  norm=0.912  lr=1.51e-05  dt=  37.0ms  words=100,433,920
[E08  1425/1548 G  12260|CLM] train=2.2611  mask=10.1%  norm=0.709  lr=1.51e-05  dt=  36.9ms  words=100,442,112
[E08  1426/1548 G  12261|CLM] train=3.9067  mask=10.1%  norm=0.885  lr=1.51e-05  dt=  36.8ms  words=100,450,304
[E08  1427/1548 G  12262|CLM] train=1.9927  mask=10.1%  norm=0.736  lr=1.51e-05  dt=  36.8ms  words=100,458,496
[E08  1428/1548 G  12263|CLM] train=3.7447  mask=10.1%  norm=0.857  lr=1.51e-05  dt=  37.0ms  words=100,466,688
[E08  1429/1548 G  12264|CLM] train=2.0384  mask=10.1%  norm=0.662  lr=1.51e-05  dt=  36.8ms  words=100,474,880
[E08  1430/1548 G  12265|CLM] train=2.1633  mask=10.1%  norm=0.770  lr=1.51e-05  dt=  36.9ms  words=100,483,072
[E08  1431/1548 G  12266|CLM] train=2.1465  mask=10.1%  norm=0.730  lr=1.51e-05  dt=  37.0ms  words=100,491,264
[E08  1432/1548 G  12267|CLM] train=4.3713  mask=10.1%  norm=1.025  lr=1.51e-05  dt=  37.1ms  words=100,499,456
[E08  1433/1548 G  12268|CLM] train=4.0013  mask=10.1%  norm=0.911  lr=1.51e-05  dt=  36.8ms  words=100,507,648
[E08  1434/1548 G  12269|CLM] train=3.6694  mask=10.1%  norm=0.833  lr=1.51e-05  dt=  36.7ms  words=100,515,840
[E08  1435/1548 G  12270|CLM] train=3.5358  mask=10.1%  norm=0.960  lr=1.51e-05  dt=  37.0ms  words=100,524,032
[E08  1436/1548 G  12271|CLM] train=4.6343  mask=10.1%  norm=1.128  lr=1.51e-05  dt=  37.0ms  words=100,532,224
[E08  1437/1548 G  12272|CLM] train=3.9760  mask=10.1%  norm=0.925  lr=1.51e-05  dt=  36.9ms  words=100,540,416
[E08  1438/1548 G  12273|CLM] train=2.2545  mask=10.1%  norm=0.786  lr=1.51e-05  dt=  37.0ms  words=100,548,608
[E08  1439/1548 G  12274|CLM] train=4.0387  mask=10.1%  norm=0.820  lr=1.51e-05  dt=  36.9ms  words=100,556,800
[E08  1440/1548 G  12275|CLM] train=2.5599  mask=10.1%  norm=0.738  lr=1.51e-05  dt=  37.1ms  words=100,564,992
[E08  1441/1548 G  12276|CLM] train=4.1457  mask=10.1%  norm=0.919  lr=1.51e-05  dt=  36.9ms  words=100,573,184
[E08  1442/1548 G  12277|CLM] train=4.0012  mask=10.1%  norm=0.884  lr=1.51e-05  dt=  36.7ms  words=100,581,376
[E08  1443/1548 G  12278|CLM] train=3.8342  mask=10.1%  norm=0.885  lr=1.51e-05  dt=  37.0ms  words=100,589,568
[E08  1444/1548 G  12279|CLM] train=2.1786  mask=10.1%  norm=0.672  lr=1.51e-05  dt=  37.0ms  words=100,597,760
[E08  1445/1548 G  12280|CLM] train=1.8383  mask=10.1%  norm=0.623  lr=1.51e-05  dt=  36.9ms  words=100,605,952
[E08  1446/1548 G  12281|CLM] train=4.1186  mask=10.1%  norm=1.028  lr=1.51e-05  dt=  36.7ms  words=100,614,144
[E08  1447/1548 G  12282|CLM] train=2.3058  mask=10.1%  norm=0.882  lr=1.51e-05  dt=  36.9ms  words=100,622,336
[E08  1448/1548 G  12283|CLM] train=2.6334  mask=10.1%  norm=0.774  lr=1.51e-05  dt=  37.1ms  words=100,630,528
[E08  1449/1548 G  12284|CLM] train=3.7479  mask=10.1%  norm=1.169  lr=1.51e-05  dt=  36.9ms  words=100,638,720
[E08  1450/1548 G  12285|CLM] train=3.8548  mask=10.1%  norm=1.028  lr=1.51e-05  dt=  36.7ms  words=100,646,912
[E08  1451/1548 G  12286|CLM] train=3.6279  mask=10.1%  norm=0.802  lr=1.51e-05  dt=  36.9ms  words=100,655,104
[E08  1452/1548 G  12287|CLM] train=2.5206  mask=10.1%  norm=0.709  lr=1.50e-05  dt=  37.1ms  words=100,663,296
[E08  1453/1548 G  12288|CLM] train=3.8965  mask=10.1%  norm=1.050  lr=1.50e-05  dt=  36.9ms  words=100,671,488
[E08  1454/1548 G  12289|CLM] train=2.1481  mask=10.1%  norm=0.846  lr=1.50e-05  dt=  36.9ms  words=100,679,680
[E08  1455/1548 G  12290|CLM] train=4.2891  mask=10.1%  norm=0.982  lr=1.50e-05  dt=  36.9ms  words=100,687,872
[E08  1456/1548 G  12291|CLM] train=4.2142  mask=10.1%  norm=1.167  lr=1.50e-05  dt=  37.0ms  words=100,696,064
[E08  1457/1548 G  12292|CLM] train=2.1746  mask=10.1%  norm=0.702  lr=1.50e-05  dt=  36.9ms  words=100,704,256
[E08  1458/1548 G  12293|CLM] train=4.7376  mask=10.1%  norm=1.062  lr=1.50e-05  dt=  36.7ms  words=100,712,448
[E08  1459/1548 G  12294|CLM] train=2.1213  mask=10.1%  norm=0.679  lr=1.50e-05  dt=  37.3ms  words=100,720,640
[E08  1460/1548 G  12295|CLM] train=1.9776  mask=10.1%  norm=0.695  lr=1.50e-05  dt=  37.0ms  words=100,728,832
[E08  1461/1548 G  12296|CLM] train=2.0334  mask=10.1%  norm=0.686  lr=1.50e-05  dt=  37.0ms  words=100,737,024
[E08  1462/1548 G  12297|CLM] train=2.1952  mask=10.1%  norm=0.695  lr=1.50e-05  dt=  37.3ms  words=100,745,216
[E08  1463/1548 G  12298|CLM] train=3.6893  mask=10.1%  norm=0.881  lr=1.50e-05  dt=  37.0ms  words=100,753,408
[E08  1464/1548 G  12299|CLM] train=4.9093  mask=10.1%  norm=1.066  lr=1.50e-05  dt=  37.0ms  words=100,761,600
[E08  1465/1548 G  12300|CLM] train=3.8525  mask=10.1%  norm=0.834  lr=1.50e-05  dt=  37.0ms  words=100,769,792
[E08  1466/1548 G  12301|CLM] train=3.8042  mask=10.1%  norm=0.900  lr=1.50e-05  dt=  36.9ms  words=100,777,984
[E08  1467/1548 G  12302|CLM] train=4.1625  mask=10.1%  norm=0.921  lr=1.50e-05  dt=  37.2ms  words=100,786,176
[E08  1468/1548 G  12303|CLM] train=4.3597  mask=10.1%  norm=0.886  lr=1.50e-05  dt=  36.9ms  words=100,794,368
[E08  1469/1548 G  12304|CLM] train=1.9347  mask=10.1%  norm=0.720  lr=1.50e-05  dt=  36.9ms  words=100,802,560
[E08  1470/1548 G  12305|CLM] train=3.7026  mask=10.1%  norm=0.917  lr=1.50e-05  dt=  36.9ms  words=100,810,752
[E08  1471/1548 G  12306|CLM] train=4.1423  mask=10.1%  norm=0.929  lr=1.50e-05  dt=  37.0ms  words=100,818,944
[E08  1472/1548 G  12307|CLM] train=4.7927  mask=10.1%  norm=1.132  lr=1.50e-05  dt=  36.8ms  words=100,827,136
[E08  1473/1548 G  12308|CLM] train=3.9433  mask=10.1%  norm=0.900  lr=1.50e-05  dt=  36.9ms  words=100,835,328
[E08  1474/1548 G  12309|CLM] train=4.0714  mask=10.1%  norm=1.092  lr=1.50e-05  dt=  36.9ms  words=100,843,520
[E08  1475/1548 G  12310|CLM] train=4.1074  mask=10.1%  norm=1.053  lr=1.50e-05  dt=  37.0ms  words=100,851,712
[E08  1476/1548 G  12311|CLM] train=4.0974  mask=10.1%  norm=0.984  lr=1.50e-05  dt=  37.1ms  words=100,859,904
[E08  1477/1548 G  12312|CLM] train=1.9448  mask=10.1%  norm=0.724  lr=1.50e-05  dt=  36.8ms  words=100,868,096
[E08  1478/1548 G  12313|CLM] train=4.0749  mask=10.1%  norm=0.916  lr=1.50e-05  dt=  36.8ms  words=100,876,288
[E08  1479/1548 G  12314|CLM] train=4.0693  mask=10.1%  norm=0.988  lr=1.50e-05  dt=  37.1ms  words=100,884,480
[E08  1480/1548 G  12315|CLM] train=3.9919  mask=10.1%  norm=1.016  lr=1.50e-05  dt=  36.8ms  words=100,892,672
[E08  1481/1548 G  12316|CLM] train=2.3348  mask=10.1%  norm=0.785  lr=1.50e-05  dt=  36.9ms  words=100,900,864
[E08  1482/1548 G  12317|CLM] train=1.9289  mask=10.1%  norm=0.659  lr=1.50e-05  dt=  36.9ms  words=100,909,056
[E08  1483/1548 G  12318|CLM] train=2.1681  mask=10.1%  norm=0.712  lr=1.50e-05  dt=  37.0ms  words=100,917,248
[E08  1484/1548 G  12319|CLM] train=2.0430  mask=10.1%  norm=0.676  lr=1.50e-05  dt=  36.8ms  words=100,925,440
[E08  1485/1548 G  12320|CLM] train=3.9371  mask=10.1%  norm=0.928  lr=1.50e-05  dt=  36.8ms  words=100,933,632
[E08  1486/1548 G  12321|CLM] train=3.9513  mask=10.1%  norm=0.905  lr=1.50e-05  dt=  37.0ms  words=100,941,824
[E08  1487/1548 G  12322|CLM] train=3.9633  mask=10.1%  norm=0.920  lr=1.50e-05  dt=  37.0ms  words=100,950,016
[E08  1488/1548 G  12323|CLM] train=1.7461  mask=10.0%  norm=0.750  lr=1.50e-05  dt=  36.9ms  words=100,958,208
[E08  1489/1548 G  12324|CLM] train=3.9829  mask=10.0%  norm=0.958  lr=1.50e-05  dt=  36.9ms  words=100,966,400
[E08  1490/1548 G  12325|CLM] train=3.6568  mask=10.0%  norm=0.892  lr=1.50e-05  dt=  36.9ms  words=100,974,592
[E08  1491/1548 G  12326|CLM] train=3.4016  mask=10.0%  norm=1.017  lr=1.50e-05  dt=  36.9ms  words=100,982,784
[E08  1492/1548 G  12327|CLM] train=3.8610  mask=10.0%  norm=0.844  lr=1.50e-05  dt=  36.9ms  words=100,990,976
[E08  1493/1548 G  12328|CLM] train=3.2648  mask=10.0%  norm=0.818  lr=1.50e-05  dt=  36.9ms  words=100,999,168
[E08  1494/1548 G  12329|CLM] train=3.6934  mask=10.0%  norm=0.868  lr=1.50e-05  dt=  37.0ms  words=101,007,360
[E08  1495/1548 G  12330|CLM] train=4.0661  mask=10.0%  norm=0.970  lr=1.50e-05  dt=  37.0ms  words=101,015,552
[E08  1496/1548 G  12331|CLM] train=2.3842  mask=10.0%  norm=0.729  lr=1.50e-05  dt=  36.8ms  words=101,023,744
[E08  1497/1548 G  12332|CLM] train=3.5989  mask=10.0%  norm=0.986  lr=1.50e-05  dt=  36.8ms  words=101,031,936
[E08  1498/1548 G  12333|CLM] train=4.5609  mask=10.0%  norm=0.861  lr=1.50e-05  dt=  37.0ms  words=101,040,128
[E08  1499/1548 G  12334|CLM] train=1.8410  mask=10.0%  norm=0.737  lr=1.50e-05  dt=  37.0ms  words=101,048,320
[E08  1500/1548 G  12335|CLM] train=3.6886  mask=10.0%  norm=0.978  lr=1.50e-05  dt=  36.9ms  words=101,056,512
[E08  1501/1548 G  12336|CLM] train=4.0233  mask=10.0%  norm=0.924  lr=1.50e-05  dt=  36.9ms  words=101,064,704
[E08  1502/1548 G  12337|CLM] train=2.2045  mask=10.0%  norm=0.695  lr=1.50e-05  dt=  36.9ms  words=101,072,896
[E08  1503/1548 G  12338|CLM] train=3.6332  mask=10.0%  norm=0.993  lr=1.50e-05  dt=  37.1ms  words=101,081,088
[E08  1504/1548 G  12339|CLM] train=4.1978  mask=10.0%  norm=1.311  lr=1.50e-05  dt=  37.0ms  words=101,089,280
[E08  1505/1548 G  12340|CLM] train=2.4074  mask=10.0%  norm=0.675  lr=1.50e-05  dt=  36.9ms  words=101,097,472
[E08  1506/1548 G  12341|CLM] train=3.9610  mask=10.0%  norm=0.883  lr=1.50e-05  dt=  36.8ms  words=101,105,664
[E08  1507/1548 G  12342|CLM] train=4.4305  mask=10.0%  norm=1.029  lr=1.50e-05  dt=  37.0ms  words=101,113,856
[E08  1508/1548 G  12343|CLM] train=3.7991  mask=10.0%  norm=0.806  lr=1.50e-05  dt=  36.9ms  words=101,122,048
[E08  1509/1548 G  12344|CLM] train=4.6725  mask=10.0%  norm=1.101  lr=1.50e-05  dt=  36.9ms  words=101,130,240
[E08  1510/1548 G  12345|CLM] train=3.8189  mask=10.0%  norm=1.068  lr=1.50e-05  dt=  37.0ms  words=101,138,432
[E08  1511/1548 G  12346|CLM] train=4.1542  mask=10.0%  norm=0.825  lr=1.50e-05  dt=  37.0ms  words=101,146,624
[E08  1512/1548 G  12347|CLM] train=3.9467  mask=10.0%  norm=0.945  lr=1.50e-05  dt=  36.9ms  words=101,154,816
[E08  1513/1548 G  12348|CLM] train=3.5747  mask=10.0%  norm=0.867  lr=1.50e-05  dt=  37.4ms  words=101,163,008
[E08  1514/1548 G  12349|CLM] train=2.0183  mask=10.0%  norm=0.685  lr=1.50e-05  dt=  37.0ms  words=101,171,200
[E08  1515/1548 G  12350|CLM] train=4.4276  mask=10.0%  norm=0.996  lr=1.50e-05  dt=  36.9ms  words=101,179,392
[E08  1516/1548 G  12351|CLM] train=2.1864  mask=10.0%  norm=0.724  lr=1.50e-05  dt=  36.9ms  words=101,187,584
[E08  1517/1548 G  12352|CLM] train=2.1293  mask=10.0%  norm=0.701  lr=1.50e-05  dt=  37.0ms  words=101,195,776
[E08  1518/1548 G  12353|CLM] train=4.5976  mask=10.0%  norm=1.260  lr=1.50e-05  dt=  37.1ms  words=101,203,968
[E08  1519/1548 G  12354|CLM] train=4.0253  mask=10.0%  norm=0.947  lr=1.50e-05  dt=  36.9ms  words=101,212,160
[E08  1520/1548 G  12355|CLM] train=2.0424  mask=10.0%  norm=0.694  lr=1.50e-05  dt=  36.9ms  words=101,220,352
[E08  1521/1548 G  12356|CLM] train=3.9853  mask=10.0%  norm=1.003  lr=1.50e-05  dt=  36.9ms  words=101,228,544
[E08  1522/1548 G  12357|CLM] train=2.0667  mask=10.0%  norm=0.703  lr=1.50e-05  dt=  37.1ms  words=101,236,736
[E08  1523/1548 G  12358|CLM] train=1.9706  mask=10.0%  norm=0.753  lr=1.50e-05  dt=  36.8ms  words=101,244,928
[E08  1524/1548 G  12359|CLM] train=2.3210  mask=10.0%  norm=0.755  lr=1.50e-05  dt=  36.9ms  words=101,253,120
[E08  1525/1548 G  12360|CLM] train=3.8157  mask=10.0%  norm=0.913  lr=1.50e-05  dt=  37.0ms  words=101,261,312
[E08  1526/1548 G  12361|CLM] train=4.0685  mask=10.0%  norm=0.935  lr=1.50e-05  dt=  38.0ms  words=101,269,504
[E08  1527/1548 G  12362|CLM] train=2.5355  mask=10.0%  norm=0.717  lr=1.50e-05  dt=  39.6ms  words=101,277,696
[E08  1528/1548 G  12363|CLM] train=4.3177  mask=10.0%  norm=0.909  lr=1.50e-05  dt=  39.0ms  words=101,285,888
[E08  1529/1548 G  12364|CLM] train=1.9568  mask=10.0%  norm=0.673  lr=1.50e-05  dt=  37.0ms  words=101,294,080
[E08  1530/1548 G  12365|CLM] train=4.2059  mask=10.0%  norm=0.959  lr=1.50e-05  dt=  36.9ms  words=101,302,272
[E08  1531/1548 G  12366|CLM] train=4.1447  mask=10.0%  norm=0.867  lr=1.50e-05  dt=  36.9ms  words=101,310,464
[E08  1532/1548 G  12367|CLM] train=3.7340  mask=10.0%  norm=0.944  lr=1.50e-05  dt=  37.1ms  words=101,318,656
[E08  1533/1548 G  12368|CLM] train=3.9175  mask=10.0%  norm=0.896  lr=1.50e-05  dt=  36.9ms  words=101,326,848
[E08  1534/1548 G  12369|CLM] train=3.8904  mask=10.0%  norm=0.936  lr=1.50e-05  dt=  36.9ms  words=101,335,040
[E08  1535/1548 G  12370|CLM] train=4.5892  mask=10.0%  norm=1.020  lr=1.50e-05  dt=  36.9ms  words=101,343,232
[E08  1536/1548 G  12371|CLM] train=3.8466  mask=10.0%  norm=0.778  lr=1.50e-05  dt=  37.2ms  words=101,351,424
[E08  1537/1548 G  12372|CLM] train=3.7787  mask=10.0%  norm=0.839  lr=1.50e-05  dt=  37.2ms  words=101,359,616
[E08  1538/1548 G  12373|CLM] train=3.8996  mask=10.0%  norm=0.884  lr=1.50e-05  dt=  37.2ms  words=101,367,808
[E08  1539/1548 G  12374|CLM] train=3.6002  mask=10.0%  norm=0.827  lr=1.50e-05  dt=  37.2ms  words=101,376,000
[E08  1540/1548 G  12375|CLM] train=3.9103  mask=10.0%  norm=0.879  lr=1.50e-05  dt=  37.0ms  words=101,384,192
[E08  1541/1548 G  12376|CLM] train=2.3301  mask=10.0%  norm=0.911  lr=1.50e-05  dt=  37.3ms  words=101,392,384
[E08  1542/1548 G  12377|CLM] train=2.1357  mask=10.0%  norm=0.668  lr=1.50e-05  dt=  37.1ms  words=101,400,576
[E08  1543/1548 G  12378|CLM] train=3.6713  mask=10.0%  norm=0.839  lr=1.50e-05  dt=  37.0ms  words=101,408,768
[E08  1544/1548 G  12379|CLM] train=3.7925  mask=10.0%  norm=0.921  lr=1.50e-05  dt=  36.8ms  words=101,416,960
[E08  1545/1548 G  12380|CLM] train=2.3150  mask=10.0%  norm=0.686  lr=1.50e-05  dt=  36.9ms  words=101,425,152
[E08  1546/1548 G  12381|CLM] train=2.5611  mask=10.0%  norm=0.705  lr=1.50e-05  dt=  37.1ms  words=101,433,344
[E08  1547/1548 G  12382|CLM] train=3.6079  mask=10.0%  norm=0.873  lr=1.50e-05  dt=  36.8ms  words=101,441,536
[E08  1548/1548 G  12383|CLM] train=4.0721  mask=10.0%  norm=0.925  lr=1.50e-05  dt=  36.8ms  words=101,449,728

[Checkpoint] Saving Hugging Face format checkpoint to '/teamspace/studios/this_studio/Normal_c1/checkpoints/xpertgpt_fresh/main'...
[Checkpoint] Checkpoint 'main' successfully saved.

[Training] Training phase complete!
[Eval] Cloned repository does not contain global_piqa tasks.
[Eval] Deleting and cloning official main branch...
[Eval] Using strict directory: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict
[GlobalPIQA] Patching local checkpoint loader in /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/evaluation_pipeline/sentence_zero_shot/run.py...
[GlobalPIQA] Successfully patched run.py
[Eval] Stripping Windows-specific packages from requirements.txt...
[Eval] Verifying and installing evaluation dependencies programmatically...
[Eval] Downloading NLTK tokenizer resources...
[nltk_data] Downloading package punkt to
[nltk_data]     /teamspace/studios/this_studio/Normal_c1/nltk_data...
[nltk_data]   Unzipping tokenizers/punkt.zip.
[nltk_data] Downloading package punkt_tab to
[nltk_data]     /teamspace/studios/this_studio/Normal_c1/nltk_data...
[nltk_data]   Unzipping tokenizers/punkt_tab.zip.
[Eval] Standard zero-shot datasets not found. Downloading...
[Eval] Unzipping EWoK fast data...
[Eval] Downloading and filtering full EWoK dataset...
[Eval] GlobalPIQA dataset not found. Downloading...
[Eval] Making evaluation shell scripts executable...
[Eval] Running full zero-shot evaluation on main...
[Eval] Running task 'blimp' (blimp_filtered) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/blimp/blimp_filtered to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/blimp/blimp_filtered...
[Eval] Verifying main blimp (blimp_filtered) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/blimp/blimp_filtered...
[Eval] Success! Verified main blimp (blimp_filtered) results are stored correctly.
[Eval] Running task 'blimp' (supplement_filtered) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/blimp/supplement_filtered to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/blimp/supplement_filtered...
[Eval] Verifying main blimp (supplement_filtered) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/blimp/supplement_filtered...
[Eval] Success! Verified main blimp (supplement_filtered) results are stored correctly.
[Eval] Running task 'ewok' (ewok_filtered) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/ewok/ewok_filtered to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/ewok/ewok_filtered...
[Eval] Verifying main ewok (ewok_filtered) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/ewok/ewok_filtered...
[Eval] Success! Verified main ewok (ewok_filtered) results are stored correctly.
[Eval] Running task 'entity_tracking' (entity_tracking) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/entity_tracking/entity_tracking to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/entity_tracking/entity_tracking...
[Eval] Verifying main entity_tracking (entity_tracking) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/entity_tracking/entity_tracking...
[Eval] Success! Verified main entity_tracking (entity_tracking) results are stored correctly.
[Eval] Running task 'comps' (comps) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/comps/comps to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/comps/comps...
[Eval] Verifying main comps (comps) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/comps/comps...
[Eval] Success! Verified main comps (comps) results are stored correctly.
[Eval] Running task 'reading' (reading) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/reading to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/reading...
[Eval] Verifying main reading (reading) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/reading...
[Eval] Success! Verified main reading (reading) results are stored correctly.
[Eval] Running task 'global_piqa_parallel' (global_piqa_parallel) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/global_piqa_parallel/global_piqa_parallel to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/global_piqa_parallel/global_piqa_parallel...
[Eval] Verifying main global_piqa_parallel (global_piqa_parallel) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/global_piqa_parallel/global_piqa_parallel...
[Eval] Success! Verified main global_piqa_parallel (global_piqa_parallel) results are stored correctly.
[Eval] Running task 'global_piqa_nonparallel' (global_piqa_nonparallel) for checkpoint 'main'...
[Eval] Relocating results from /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/main/main/zero_shot/causal/global_piqa_nonparallel/global_piqa_nonparallel to /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/global_piqa_nonparallel/global_piqa_nonparallel...
[Eval] Verifying main global_piqa_nonparallel (global_piqa_nonparallel) path: /teamspace/studios/this_studio/Normal_c1/babylm_eval_repo/strict/results/xpertgpt_fresh/main/zero_shot/causal/global_piqa_nonparallel/global_piqa_nonparallel...
[Eval] Success! Verified main global_piqa_nonparallel (global_piqa_nonparallel) results are stored correctly.
[Eval] Running GLUE fine-tuning evaluations on main task-by-task...
[Eval] Running GLUE task 'boolq'...
Traceback (most recent call last):
  File "/teamspace/studios/this_studio/Normal_c1/train.py", line 1429, in <module>
    run_pipeline(args.model_name, epochs=args.epochs, skip_eval=args.skip_eval, skip_aoa=args.skip_aoa, skip_glue=args.skip_glue)
  File "/teamspace/studios/this_studio/Normal_c1/train.py", line 906, in run_pipeline
    run_finetune_task_with_cache(task_name, cmd)
  File "/teamspace/studios/this_studio/Normal_c1/train.py", line 737, in run_finetune_task_with_cache
    subprocess.run(cmd, cwd=strict_dir, check=True)
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/subprocess.py", line 550, in run
    stdout, stderr = process.communicate(input, timeout=timeout)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/subprocess.py", line 1201, in communicate
    self.wait()
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/subprocess.py", line 1264, in wait
    return self._wait(timeout=timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/subprocess.py", line 2053, in _wait
    (pid, sts) = self._try_wait(0)
                 ^^^^^^^^^^^^^^^^^
  File "/home/zeus/miniconda3/envs/cloudspace/lib/python3.12/subprocess.py", line 2011, in _try_wait
    (pid, sts) = os.waitpid(self.pid, wait_flags)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyboardInterrupt