CR_multichannel.log

Namespace(batch_size=50, data_name='CR', dropout=0.5, epochs=200, gpu=0, log_interval=30, model_mode='multichannel')
Use gpu0
maximum length (in tokens):  105
Done! Tokenizing Time=0.06s, #Sentences=3775
SentimentNet(
  (embedding): Embedding(5343 -> 300, float32)
  (embedding_extend): Embedding(5343 -> 300, float32)
  (encoder): ConvolutionalEncoder(
    (_convs): HybridConcurrent(
      (0): HybridSequential(
        (0): Conv1D(600 -> 100, kernel_size=(3,), stride=(1,))
        (1): HybridLambda(<lambda>)
        (2): Activation(relu)
      )
      (1): HybridSequential(
        (0): Conv1D(600 -> 100, kernel_size=(4,), stride=(1,))
        (1): HybridLambda(<lambda>)
        (2): Activation(relu)
      )
      (2): HybridSequential(
        (0): Conv1D(600 -> 100, kernel_size=(5,), stride=(1,))
        (1): HybridLambda(<lambda>)
        (2): Activation(relu)
      )
    )
  )
  (output): HybridSequential(
    (0): Dropout(p = 0.5, axes=())
    (1): Dense(None -> 2, linear)
  )
)
[Epoch 0 Batch 30/62] avg loss 0.0134723, throughput 0.343674K wps
[Epoch 0 Batch 60/62] avg loss 0.0129089, throughput 3.26262K wps
Begin Testing...
[Epoch 0] train avg loss 0.0133812, dev acc 0.6372, dev avg loss 0.645867, throughput 0.339026K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130102, throughput 3.34238K wps
[Epoch 1 Batch 60/62] avg loss 0.0129448, throughput 3.23616K wps
Begin Testing...
[Epoch 1] train avg loss 0.0131052, dev acc 0.6372, dev avg loss 0.640512, throughput 3.29626K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0126977, throughput 3.33366K wps
[Epoch 2 Batch 60/62] avg loss 0.0127733, throughput 3.25764K wps
Begin Testing...
[Epoch 2] train avg loss 0.0128615, dev acc 0.6372, dev avg loss 0.633058, throughput 3.30186K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0125133, throughput 3.33257K wps
[Epoch 3 Batch 60/62] avg loss 0.0125409, throughput 3.2568K wps
Begin Testing...
[Epoch 3] train avg loss 0.012671, dev acc 0.6372, dev avg loss 0.623487, throughput 3.30107K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0122701, throughput 3.33109K wps
[Epoch 4 Batch 60/62] avg loss 0.0124346, throughput 3.2536K wps
Begin Testing...
[Epoch 4] train avg loss 0.0125311, dev acc 0.6372, dev avg loss 0.61702, throughput 3.29828K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0122674, throughput 3.33839K wps
[Epoch 5 Batch 60/62] avg loss 0.0119561, throughput 3.25442K wps
Begin Testing...
[Epoch 5] train avg loss 0.0123007, dev acc 0.6431, dev avg loss 0.609875, throughput 3.30228K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0119415, throughput 3.33358K wps
[Epoch 6 Batch 60/62] avg loss 0.0119814, throughput 3.23653K wps
Begin Testing...
[Epoch 6] train avg loss 0.0121306, dev acc 0.6401, dev avg loss 0.602441, throughput 3.29088K wps
[Epoch 7 Batch 30/62] avg loss 0.0117209, throughput 3.1797K wps
[Epoch 7 Batch 60/62] avg loss 0.0119209, throughput 3.27397K wps
Begin Testing...
[Epoch 7] train avg loss 0.0119841, dev acc 0.6490, dev avg loss 0.593291, throughput 3.23459K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0115267, throughput 3.30825K wps
[Epoch 8 Batch 60/62] avg loss 0.0114703, throughput 3.23038K wps
Begin Testing...
[Epoch 8] train avg loss 0.0116767, dev acc 0.6608, dev avg loss 0.584986, throughput 3.27405K wps
Observed Improvement.
Begin Testing...
[Epoch 9 Batch 30/62] avg loss 0.0115753, throughput 3.32254K wps
[Epoch 9 Batch 60/62] avg loss 0.0112319, throughput 3.22645K wps
Begin Testing...
[Epoch 9] train avg loss 0.0115095, dev acc 0.6637, dev avg loss 0.576667, throughput 3.28022K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0111671, throughput 3.30046K wps
[Epoch 10 Batch 60/62] avg loss 0.0112022, throughput 3.22593K wps
Begin Testing...
[Epoch 10] train avg loss 0.0113404, dev acc 0.6873, dev avg loss 0.568127, throughput 3.26977K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0109008, throughput 3.30439K wps
[Epoch 11 Batch 60/62] avg loss 0.0109946, throughput 3.2263K wps
Begin Testing...
[Epoch 11] train avg loss 0.0110775, dev acc 0.6637, dev avg loss 0.561266, throughput 3.27122K wps
[Epoch 12 Batch 30/62] avg loss 0.0105575, throughput 3.31961K wps
[Epoch 12 Batch 60/62] avg loss 0.0107065, throughput 3.21559K wps
Begin Testing...
[Epoch 12] train avg loss 0.0108074, dev acc 0.7109, dev avg loss 0.550624, throughput 3.27443K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0107503, throughput 3.32673K wps
[Epoch 13 Batch 60/62] avg loss 0.0103472, throughput 3.2312K wps
Begin Testing...
[Epoch 13] train avg loss 0.0106261, dev acc 0.6873, dev avg loss 0.543977, throughput 3.28388K wps
[Epoch 14 Batch 30/62] avg loss 0.0103625, throughput 3.30368K wps
[Epoch 14 Batch 60/62] avg loss 0.0102037, throughput 3.24421K wps
Begin Testing...
[Epoch 14] train avg loss 0.0104303, dev acc 0.7286, dev avg loss 0.532857, throughput 3.28033K wps
Observed Improvement.
Begin Testing...
[Epoch 15 Batch 30/62] avg loss 0.0102559, throughput 3.34094K wps
[Epoch 15 Batch 60/62] avg loss 0.0100903, throughput 3.22256K wps
Begin Testing...
[Epoch 15] train avg loss 0.010348, dev acc 0.7404, dev avg loss 0.525199, throughput 3.28631K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.00959528, throughput 3.31265K wps
[Epoch 16 Batch 60/62] avg loss 0.0102398, throughput 3.22636K wps
Begin Testing...
[Epoch 16] train avg loss 0.0100203, dev acc 0.7611, dev avg loss 0.517671, throughput 3.27555K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.00966294, throughput 3.31638K wps
[Epoch 17 Batch 60/62] avg loss 0.00970601, throughput 3.24517K wps
Begin Testing...
[Epoch 17] train avg loss 0.00980017, dev acc 0.7463, dev avg loss 0.509622, throughput 3.28731K wps
[Epoch 18 Batch 30/62] avg loss 0.00939605, throughput 3.31666K wps
[Epoch 18 Batch 60/62] avg loss 0.00937983, throughput 3.22201K wps
Begin Testing...
[Epoch 18] train avg loss 0.00957299, dev acc 0.7611, dev avg loss 0.506679, throughput 3.27647K wps
Observed Improvement.
Begin Testing...
[Epoch 19 Batch 30/62] avg loss 0.00941913, throughput 3.31988K wps
[Epoch 19 Batch 60/62] avg loss 0.00922998, throughput 3.22734K wps
Begin Testing...
[Epoch 19] train avg loss 0.00941015, dev acc 0.7640, dev avg loss 0.495414, throughput 3.2798K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.00904799, throughput 3.31764K wps
[Epoch 20 Batch 60/62] avg loss 0.00924885, throughput 3.23532K wps
Begin Testing...
[Epoch 20] train avg loss 0.00929458, dev acc 0.7611, dev avg loss 0.490562, throughput 3.28106K wps
[Epoch 21 Batch 30/62] avg loss 0.00896077, throughput 3.29325K wps
[Epoch 21 Batch 60/62] avg loss 0.00893734, throughput 3.22498K wps
Begin Testing...
[Epoch 21] train avg loss 0.00908357, dev acc 0.7817, dev avg loss 0.483413, throughput 3.26385K wps
Observed Improvement.
Begin Testing...
[Epoch 22 Batch 30/62] avg loss 0.00876101, throughput 3.29305K wps
[Epoch 22 Batch 60/62] avg loss 0.00869727, throughput 3.21492K wps
Begin Testing...
[Epoch 22] train avg loss 0.00886027, dev acc 0.7640, dev avg loss 0.48087, throughput 3.25976K wps
[Epoch 23 Batch 30/62] avg loss 0.00860429, throughput 3.31881K wps
[Epoch 23 Batch 60/62] avg loss 0.00838256, throughput 3.23879K wps
Begin Testing...
[Epoch 23] train avg loss 0.00865908, dev acc 0.7699, dev avg loss 0.474155, throughput 3.28369K wps
[Epoch 24 Batch 30/62] avg loss 0.0086947, throughput 3.2851K wps
[Epoch 24 Batch 60/62] avg loss 0.00827456, throughput 3.23034K wps
Begin Testing...
[Epoch 24] train avg loss 0.00858808, dev acc 0.7758, dev avg loss 0.469919, throughput 3.26461K wps
[Epoch 25 Batch 30/62] avg loss 0.00830087, throughput 3.30858K wps
[Epoch 25 Batch 60/62] avg loss 0.00799783, throughput 3.22975K wps
Begin Testing...
[Epoch 25] train avg loss 0.00827258, dev acc 0.7788, dev avg loss 0.46376, throughput 3.27575K wps
[Epoch 26 Batch 30/62] avg loss 0.00792655, throughput 3.29768K wps
[Epoch 26 Batch 60/62] avg loss 0.00838465, throughput 3.23694K wps
Begin Testing...
[Epoch 26] train avg loss 0.00824073, dev acc 0.7817, dev avg loss 0.459772, throughput 3.27171K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.0081229, throughput 3.32102K wps
[Epoch 27 Batch 60/62] avg loss 0.00793227, throughput 3.23567K wps
Begin Testing...
[Epoch 27] train avg loss 0.00806027, dev acc 0.7817, dev avg loss 0.456041, throughput 3.28356K wps
Observed Improvement.
Begin Testing...
[Epoch 28 Batch 30/62] avg loss 0.00770145, throughput 3.29657K wps
[Epoch 28 Batch 60/62] avg loss 0.00784183, throughput 3.22498K wps
Begin Testing...
[Epoch 28] train avg loss 0.00783569, dev acc 0.7876, dev avg loss 0.451941, throughput 3.26522K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00780541, throughput 3.31888K wps
[Epoch 29 Batch 60/62] avg loss 0.00755988, throughput 3.24892K wps
Begin Testing...
[Epoch 29] train avg loss 0.00775539, dev acc 0.7758, dev avg loss 0.44961, throughput 3.29014K wps
[Epoch 30 Batch 30/62] avg loss 0.00767302, throughput 3.3019K wps
[Epoch 30 Batch 60/62] avg loss 0.00729676, throughput 3.23396K wps
Begin Testing...
[Epoch 30] train avg loss 0.0075499, dev acc 0.7876, dev avg loss 0.445713, throughput 3.27319K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.00729512, throughput 3.30777K wps
[Epoch 31 Batch 60/62] avg loss 0.00731529, throughput 3.23202K wps
Begin Testing...
[Epoch 31] train avg loss 0.00741992, dev acc 0.7788, dev avg loss 0.445104, throughput 3.27476K wps
[Epoch 32 Batch 30/62] avg loss 0.00715808, throughput 3.28979K wps
[Epoch 32 Batch 60/62] avg loss 0.00740053, throughput 3.22262K wps
Begin Testing...
[Epoch 32] train avg loss 0.00739935, dev acc 0.7847, dev avg loss 0.443554, throughput 3.2617K wps
[Epoch 33 Batch 30/62] avg loss 0.0070608, throughput 3.29572K wps
[Epoch 33 Batch 60/62] avg loss 0.00714915, throughput 3.21816K wps
Begin Testing...
[Epoch 33] train avg loss 0.00720835, dev acc 0.7906, dev avg loss 0.437648, throughput 3.26273K wps
Observed Improvement.
Begin Testing...
[Epoch 34 Batch 30/62] avg loss 0.00700767, throughput 3.27862K wps
[Epoch 34 Batch 60/62] avg loss 0.00707173, throughput 3.23245K wps
Begin Testing...
[Epoch 34] train avg loss 0.00705619, dev acc 0.7906, dev avg loss 0.436573, throughput 3.26106K wps
Observed Improvement.
Begin Testing...
[Epoch 35 Batch 30/62] avg loss 0.00676388, throughput 3.29216K wps
[Epoch 35 Batch 60/62] avg loss 0.00698487, throughput 3.23153K wps
Begin Testing...
[Epoch 35] train avg loss 0.00705509, dev acc 0.7876, dev avg loss 0.433251, throughput 3.269K wps
[Epoch 36 Batch 30/62] avg loss 0.00663338, throughput 3.30999K wps
[Epoch 36 Batch 60/62] avg loss 0.00684657, throughput 3.21403K wps
Begin Testing...
[Epoch 36] train avg loss 0.00683581, dev acc 0.7817, dev avg loss 0.438491, throughput 3.26818K wps
[Epoch 37 Batch 30/62] avg loss 0.00666328, throughput 3.33245K wps
[Epoch 37 Batch 60/62] avg loss 0.00666124, throughput 3.23217K wps
Begin Testing...
[Epoch 37] train avg loss 0.00670551, dev acc 0.7788, dev avg loss 0.43255, throughput 3.28855K wps
[Epoch 38 Batch 30/62] avg loss 0.00645705, throughput 3.29445K wps
[Epoch 38 Batch 60/62] avg loss 0.00658762, throughput 3.22781K wps
Begin Testing...
[Epoch 38] train avg loss 0.00662022, dev acc 0.8201, dev avg loss 0.426898, throughput 3.26504K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.00621295, throughput 3.30825K wps
[Epoch 39 Batch 60/62] avg loss 0.00640877, throughput 3.21856K wps
Begin Testing...
[Epoch 39] train avg loss 0.00647128, dev acc 0.8024, dev avg loss 0.423956, throughput 3.26855K wps
[Epoch 40 Batch 30/62] avg loss 0.00630716, throughput 3.31153K wps
[Epoch 40 Batch 60/62] avg loss 0.00626895, throughput 3.20577K wps
Begin Testing...
[Epoch 40] train avg loss 0.00635059, dev acc 0.8142, dev avg loss 0.422436, throughput 3.26418K wps
[Epoch 41 Batch 30/62] avg loss 0.00591307, throughput 3.30095K wps
[Epoch 41 Batch 60/62] avg loss 0.00633876, throughput 3.22163K wps
Begin Testing...
[Epoch 41] train avg loss 0.00615976, dev acc 0.7817, dev avg loss 0.429495, throughput 3.26752K wps
[Epoch 42 Batch 30/62] avg loss 0.00602473, throughput 3.31965K wps
[Epoch 42 Batch 60/62] avg loss 0.00625138, throughput 3.22533K wps
Begin Testing...
[Epoch 42] train avg loss 0.00620687, dev acc 0.8171, dev avg loss 0.419217, throughput 3.27828K wps
[Epoch 43 Batch 30/62] avg loss 0.00601633, throughput 3.29877K wps
[Epoch 43 Batch 60/62] avg loss 0.00602545, throughput 3.22344K wps
Begin Testing...
[Epoch 43] train avg loss 0.00607012, dev acc 0.8053, dev avg loss 0.420083, throughput 3.26671K wps
[Epoch 44 Batch 30/62] avg loss 0.00561471, throughput 3.32077K wps
[Epoch 44 Batch 60/62] avg loss 0.00606478, throughput 3.23325K wps
Begin Testing...
[Epoch 44] train avg loss 0.00587506, dev acc 0.8142, dev avg loss 0.416824, throughput 3.28334K wps
[Epoch 45 Batch 30/62] avg loss 0.00577342, throughput 3.30063K wps
[Epoch 45 Batch 60/62] avg loss 0.00558224, throughput 3.2328K wps
Begin Testing...
[Epoch 45] train avg loss 0.00570039, dev acc 0.8083, dev avg loss 0.415431, throughput 3.27265K wps
[Epoch 46 Batch 30/62] avg loss 0.00538927, throughput 3.29858K wps
[Epoch 46 Batch 60/62] avg loss 0.00571484, throughput 3.23673K wps
Begin Testing...
[Epoch 46] train avg loss 0.00562714, dev acc 0.8171, dev avg loss 0.413723, throughput 3.27451K wps
[Epoch 47 Batch 30/62] avg loss 0.0054065, throughput 3.32832K wps
[Epoch 47 Batch 60/62] avg loss 0.00558721, throughput 3.22322K wps
Begin Testing...
[Epoch 47] train avg loss 0.00553656, dev acc 0.8112, dev avg loss 0.411693, throughput 3.2798K wps
[Epoch 48 Batch 30/62] avg loss 0.00544149, throughput 3.30003K wps
[Epoch 48 Batch 60/62] avg loss 0.00541284, throughput 3.23414K wps
Begin Testing...
[Epoch 48] train avg loss 0.0055122, dev acc 0.8053, dev avg loss 0.414174, throughput 3.27228K wps
[Epoch 49 Batch 30/62] avg loss 0.00565469, throughput 3.29724K wps
[Epoch 49 Batch 60/62] avg loss 0.00513911, throughput 3.20441K wps
Begin Testing...
[Epoch 49] train avg loss 0.00546651, dev acc 0.8201, dev avg loss 0.408184, throughput 3.25307K wps
Observed Improvement.
Begin Testing...
[Epoch 50 Batch 30/62] avg loss 0.00536651, throughput 3.29486K wps
[Epoch 50 Batch 60/62] avg loss 0.00519544, throughput 3.22975K wps
Begin Testing...
[Epoch 50] train avg loss 0.00529447, dev acc 0.8112, dev avg loss 0.413166, throughput 3.26715K wps
[Epoch 51 Batch 30/62] avg loss 0.00519159, throughput 3.28311K wps
[Epoch 51 Batch 60/62] avg loss 0.00512819, throughput 3.21988K wps
Begin Testing...
[Epoch 51] train avg loss 0.00521718, dev acc 0.8201, dev avg loss 0.40608, throughput 3.25741K wps
Observed Improvement.
Begin Testing...
[Epoch 52 Batch 30/62] avg loss 0.00527688, throughput 3.30122K wps
[Epoch 52 Batch 60/62] avg loss 0.00485971, throughput 3.22841K wps
Begin Testing...
[Epoch 52] train avg loss 0.00511752, dev acc 0.8230, dev avg loss 0.405056, throughput 3.27042K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.00514033, throughput 3.3005K wps
[Epoch 53 Batch 60/62] avg loss 0.00480066, throughput 3.23974K wps
Begin Testing...
[Epoch 53] train avg loss 0.00503389, dev acc 0.8112, dev avg loss 0.40768, throughput 3.27547K wps
[Epoch 54 Batch 30/62] avg loss 0.00481823, throughput 3.29592K wps
[Epoch 54 Batch 60/62] avg loss 0.00488368, throughput 3.23277K wps
Begin Testing...
[Epoch 54] train avg loss 0.00488105, dev acc 0.8171, dev avg loss 0.406379, throughput 3.26935K wps
[Epoch 55 Batch 30/62] avg loss 0.00467364, throughput 3.31428K wps
[Epoch 55 Batch 60/62] avg loss 0.0048564, throughput 3.19604K wps
Begin Testing...
[Epoch 55] train avg loss 0.00483617, dev acc 0.8230, dev avg loss 0.402401, throughput 3.2616K wps
Observed Improvement.
Begin Testing...
[Epoch 56 Batch 30/62] avg loss 0.00480682, throughput 3.28673K wps
[Epoch 56 Batch 60/62] avg loss 0.00461925, throughput 3.22143K wps
Begin Testing...
[Epoch 56] train avg loss 0.00479454, dev acc 0.8201, dev avg loss 0.405635, throughput 3.25941K wps
[Epoch 57 Batch 30/62] avg loss 0.00440682, throughput 3.3132K wps
[Epoch 57 Batch 60/62] avg loss 0.00475593, throughput 3.20848K wps
Begin Testing...
[Epoch 57] train avg loss 0.0045979, dev acc 0.8260, dev avg loss 0.401906, throughput 3.26637K wps
Observed Improvement.
Begin Testing...
[Epoch 58 Batch 30/62] avg loss 0.00439177, throughput 3.29761K wps
[Epoch 58 Batch 60/62] avg loss 0.00462431, throughput 3.21642K wps
Begin Testing...
[Epoch 58] train avg loss 0.00455091, dev acc 0.8319, dev avg loss 0.400016, throughput 3.262K wps
Observed Improvement.
Begin Testing...
[Epoch 59 Batch 30/62] avg loss 0.00437344, throughput 3.30008K wps
[Epoch 59 Batch 60/62] avg loss 0.00448443, throughput 3.22982K wps
Begin Testing...
[Epoch 59] train avg loss 0.00447979, dev acc 0.8407, dev avg loss 0.399509, throughput 3.27032K wps
Observed Improvement.
Begin Testing...
[Epoch 60 Batch 30/62] avg loss 0.0042501, throughput 3.31032K wps
[Epoch 60 Batch 60/62] avg loss 0.00455598, throughput 3.23222K wps
Begin Testing...
[Epoch 60] train avg loss 0.00443393, dev acc 0.8348, dev avg loss 0.401052, throughput 3.2708K wps
[Epoch 61 Batch 30/62] avg loss 0.00422981, throughput 3.29831K wps
[Epoch 61 Batch 60/62] avg loss 0.00422732, throughput 3.21102K wps
Begin Testing...
[Epoch 61] train avg loss 0.00425805, dev acc 0.8289, dev avg loss 0.396667, throughput 3.26158K wps
[Epoch 62 Batch 30/62] avg loss 0.00437636, throughput 3.3024K wps
[Epoch 62 Batch 60/62] avg loss 0.00405651, throughput 3.23519K wps
Begin Testing...
[Epoch 62] train avg loss 0.0043168, dev acc 0.8319, dev avg loss 0.396371, throughput 3.2754K wps
[Epoch 63 Batch 30/62] avg loss 0.00411264, throughput 3.29625K wps
[Epoch 63 Batch 60/62] avg loss 0.00404028, throughput 3.21693K wps
Begin Testing...
[Epoch 63] train avg loss 0.00416166, dev acc 0.8437, dev avg loss 0.397971, throughput 3.26325K wps
Observed Improvement.
Begin Testing...
[Epoch 64 Batch 30/62] avg loss 0.00402705, throughput 3.31298K wps
[Epoch 64 Batch 60/62] avg loss 0.00414228, throughput 3.21653K wps
Begin Testing...
[Epoch 64] train avg loss 0.00410033, dev acc 0.8348, dev avg loss 0.395691, throughput 3.27071K wps
[Epoch 65 Batch 30/62] avg loss 0.00397217, throughput 3.3061K wps
[Epoch 65 Batch 60/62] avg loss 0.00396839, throughput 3.22889K wps
Begin Testing...
[Epoch 65] train avg loss 0.00406161, dev acc 0.8260, dev avg loss 0.403318, throughput 3.27189K wps
[Epoch 66 Batch 30/62] avg loss 0.00385111, throughput 3.29607K wps
[Epoch 66 Batch 60/62] avg loss 0.00402661, throughput 3.22201K wps
Begin Testing...
[Epoch 66] train avg loss 0.00399262, dev acc 0.8407, dev avg loss 0.395094, throughput 3.26631K wps
[Epoch 67 Batch 30/62] avg loss 0.00385873, throughput 3.29535K wps
[Epoch 67 Batch 60/62] avg loss 0.00373285, throughput 3.204K wps
Begin Testing...
[Epoch 67] train avg loss 0.0038312, dev acc 0.8496, dev avg loss 0.395513, throughput 3.25459K wps
Observed Improvement.
Begin Testing...
[Epoch 68 Batch 30/62] avg loss 0.00352478, throughput 3.28579K wps
[Epoch 68 Batch 60/62] avg loss 0.00391364, throughput 3.2085K wps
Begin Testing...
[Epoch 68] train avg loss 0.00381432, dev acc 0.8230, dev avg loss 0.392567, throughput 3.25221K wps
[Epoch 69 Batch 30/62] avg loss 0.00372169, throughput 3.2866K wps
[Epoch 69 Batch 60/62] avg loss 0.0036612, throughput 3.21547K wps
Begin Testing...
[Epoch 69] train avg loss 0.00371983, dev acc 0.8319, dev avg loss 0.392922, throughput 3.2561K wps
[Epoch 70 Batch 30/62] avg loss 0.00347704, throughput 3.28018K wps
[Epoch 70 Batch 60/62] avg loss 0.00367201, throughput 3.2143K wps
Begin Testing...
[Epoch 70] train avg loss 0.00359678, dev acc 0.8525, dev avg loss 0.395358, throughput 3.25485K wps
Observed Improvement.
Begin Testing...
[Epoch 71 Batch 30/62] avg loss 0.00344919, throughput 3.29709K wps
[Epoch 71 Batch 60/62] avg loss 0.00355758, throughput 3.21736K wps
Begin Testing...
[Epoch 71] train avg loss 0.00353729, dev acc 0.8319, dev avg loss 0.391801, throughput 3.26274K wps
[Epoch 72 Batch 30/62] avg loss 0.00365617, throughput 3.30477K wps
[Epoch 72 Batch 60/62] avg loss 0.00334467, throughput 3.2184K wps
Begin Testing...
[Epoch 72] train avg loss 0.00355517, dev acc 0.8466, dev avg loss 0.394742, throughput 3.26841K wps
[Epoch 73 Batch 30/62] avg loss 0.00331663, throughput 3.29091K wps
[Epoch 73 Batch 60/62] avg loss 0.00331115, throughput 3.22724K wps
Begin Testing...
[Epoch 73] train avg loss 0.00337466, dev acc 0.8348, dev avg loss 0.390193, throughput 3.26476K wps
[Epoch 74 Batch 30/62] avg loss 0.00329994, throughput 3.29878K wps
[Epoch 74 Batch 60/62] avg loss 0.00337102, throughput 3.22008K wps
Begin Testing...
[Epoch 74] train avg loss 0.00334545, dev acc 0.8348, dev avg loss 0.390526, throughput 3.26467K wps
[Epoch 75 Batch 30/62] avg loss 0.00317221, throughput 3.31775K wps
[Epoch 75 Batch 60/62] avg loss 0.003445, throughput 3.23261K wps
Begin Testing...
[Epoch 75] train avg loss 0.00332648, dev acc 0.8525, dev avg loss 0.391598, throughput 3.28137K wps
Observed Improvement.
Begin Testing...
[Epoch 76 Batch 30/62] avg loss 0.0031992, throughput 3.31361K wps
[Epoch 76 Batch 60/62] avg loss 0.00347003, throughput 3.22705K wps
Begin Testing...
[Epoch 76] train avg loss 0.00335065, dev acc 0.8407, dev avg loss 0.389136, throughput 3.27604K wps
[Epoch 77 Batch 30/62] avg loss 0.00329104, throughput 3.29523K wps
[Epoch 77 Batch 60/62] avg loss 0.00304171, throughput 3.21723K wps
Begin Testing...
[Epoch 77] train avg loss 0.00324275, dev acc 0.8378, dev avg loss 0.388245, throughput 3.26066K wps
[Epoch 78 Batch 30/62] avg loss 0.00303973, throughput 3.28892K wps
[Epoch 78 Batch 60/62] avg loss 0.00313471, throughput 3.22585K wps
Begin Testing...
[Epoch 78] train avg loss 0.00310289, dev acc 0.8437, dev avg loss 0.389966, throughput 3.26276K wps
[Epoch 79 Batch 30/62] avg loss 0.00301366, throughput 3.30693K wps
[Epoch 79 Batch 60/62] avg loss 0.00304934, throughput 3.21177K wps
Begin Testing...
[Epoch 79] train avg loss 0.00305653, dev acc 0.8407, dev avg loss 0.388926, throughput 3.26426K wps
[Epoch 80 Batch 30/62] avg loss 0.00292107, throughput 3.28739K wps
[Epoch 80 Batch 60/62] avg loss 0.0029615, throughput 3.20525K wps
Begin Testing...
[Epoch 80] train avg loss 0.0030004, dev acc 0.8407, dev avg loss 0.389602, throughput 3.25222K wps
[Epoch 81 Batch 30/62] avg loss 0.00300573, throughput 3.29602K wps
[Epoch 81 Batch 60/62] avg loss 0.00289599, throughput 3.21929K wps
Begin Testing...
[Epoch 81] train avg loss 0.00294066, dev acc 0.8525, dev avg loss 0.392829, throughput 3.26372K wps
Observed Improvement.
Begin Testing...
[Epoch 82 Batch 30/62] avg loss 0.00279445, throughput 3.28863K wps
[Epoch 82 Batch 60/62] avg loss 0.00288153, throughput 3.23195K wps
Begin Testing...
[Epoch 82] train avg loss 0.00284179, dev acc 0.8437, dev avg loss 0.388285, throughput 3.26551K wps
[Epoch 83 Batch 30/62] avg loss 0.00293351, throughput 3.29329K wps
[Epoch 83 Batch 60/62] avg loss 0.00277965, throughput 3.23905K wps
Begin Testing...
[Epoch 83] train avg loss 0.00287721, dev acc 0.8437, dev avg loss 0.388527, throughput 3.27501K wps
[Epoch 84 Batch 30/62] avg loss 0.00268538, throughput 3.30941K wps
[Epoch 84 Batch 60/62] avg loss 0.0028424, throughput 3.22296K wps
Begin Testing...
[Epoch 84] train avg loss 0.0027851, dev acc 0.8407, dev avg loss 0.397724, throughput 3.27197K wps
[Epoch 85 Batch 30/62] avg loss 0.00278038, throughput 3.27828K wps
[Epoch 85 Batch 60/62] avg loss 0.0026297, throughput 3.21692K wps
Begin Testing...
[Epoch 85] train avg loss 0.00273534, dev acc 0.8289, dev avg loss 0.389478, throughput 3.25278K wps
[Epoch 86 Batch 30/62] avg loss 0.00276298, throughput 3.28136K wps
[Epoch 86 Batch 60/62] avg loss 0.00273945, throughput 3.21462K wps
Begin Testing...
[Epoch 86] train avg loss 0.00280084, dev acc 0.8348, dev avg loss 0.388193, throughput 3.25468K wps
[Epoch 87 Batch 30/62] avg loss 0.00254576, throughput 3.29895K wps
[Epoch 87 Batch 60/62] avg loss 0.00271004, throughput 3.21273K wps
Begin Testing...
[Epoch 87] train avg loss 0.00267001, dev acc 0.8525, dev avg loss 0.390259, throughput 3.26138K wps
Observed Improvement.
Begin Testing...
[Epoch 88 Batch 30/62] avg loss 0.00272699, throughput 3.28798K wps
[Epoch 88 Batch 60/62] avg loss 0.00248168, throughput 3.18734K wps
Begin Testing...
[Epoch 88] train avg loss 0.00262369, dev acc 0.8437, dev avg loss 0.38882, throughput 3.24523K wps
[Epoch 89 Batch 30/62] avg loss 0.00249105, throughput 3.2749K wps
[Epoch 89 Batch 60/62] avg loss 0.00255826, throughput 3.20457K wps
Begin Testing...
[Epoch 89] train avg loss 0.00258675, dev acc 0.8407, dev avg loss 0.38885, throughput 3.24594K wps
[Epoch 90 Batch 30/62] avg loss 0.0025422, throughput 3.30303K wps
[Epoch 90 Batch 60/62] avg loss 0.00255329, throughput 3.20295K wps
Begin Testing...
[Epoch 90] train avg loss 0.00261719, dev acc 0.8289, dev avg loss 0.390579, throughput 3.25905K wps
[Epoch 91 Batch 30/62] avg loss 0.00236048, throughput 3.31575K wps
[Epoch 91 Batch 60/62] avg loss 0.00257886, throughput 3.20389K wps
Begin Testing...
[Epoch 91] train avg loss 0.00248943, dev acc 0.8289, dev avg loss 0.390438, throughput 3.26667K wps
[Epoch 92 Batch 30/62] avg loss 0.00232691, throughput 3.30306K wps
[Epoch 92 Batch 60/62] avg loss 0.0024305, throughput 3.20762K wps
Begin Testing...
[Epoch 92] train avg loss 0.00242786, dev acc 0.8319, dev avg loss 0.388668, throughput 3.26243K wps
[Epoch 93 Batch 30/62] avg loss 0.00251963, throughput 3.31215K wps
[Epoch 93 Batch 60/62] avg loss 0.00224475, throughput 3.22292K wps
Begin Testing...
[Epoch 93] train avg loss 0.00239372, dev acc 0.8525, dev avg loss 0.390595, throughput 3.27298K wps
Observed Improvement.
Begin Testing...
[Epoch 94 Batch 30/62] avg loss 0.00221825, throughput 3.29441K wps
[Epoch 94 Batch 60/62] avg loss 0.00243126, throughput 3.2292K wps
Begin Testing...
[Epoch 94] train avg loss 0.0023344, dev acc 0.8525, dev avg loss 0.391429, throughput 3.26687K wps
Observed Improvement.
Begin Testing...
[Epoch 95 Batch 30/62] avg loss 0.00241627, throughput 3.29648K wps
[Epoch 95 Batch 60/62] avg loss 0.00222388, throughput 3.21014K wps
Begin Testing...
[Epoch 95] train avg loss 0.00233129, dev acc 0.8378, dev avg loss 0.38917, throughput 3.26002K wps
[Epoch 96 Batch 30/62] avg loss 0.00228826, throughput 3.28843K wps
[Epoch 96 Batch 60/62] avg loss 0.00246106, throughput 3.22754K wps
Begin Testing...
[Epoch 96] train avg loss 0.0023792, dev acc 0.8407, dev avg loss 0.389341, throughput 3.26457K wps
[Epoch 97 Batch 30/62] avg loss 0.00223325, throughput 3.27964K wps
[Epoch 97 Batch 60/62] avg loss 0.00223822, throughput 3.22679K wps
Begin Testing...
[Epoch 97] train avg loss 0.00229143, dev acc 0.8378, dev avg loss 0.389024, throughput 3.25916K wps
[Epoch 98 Batch 30/62] avg loss 0.00221346, throughput 3.27796K wps
[Epoch 98 Batch 60/62] avg loss 0.00227809, throughput 3.23167K wps
Begin Testing...
[Epoch 98] train avg loss 0.00231521, dev acc 0.8289, dev avg loss 0.38874, throughput 3.25917K wps
[Epoch 99 Batch 30/62] avg loss 0.00208261, throughput 3.29972K wps
[Epoch 99 Batch 60/62] avg loss 0.00204515, throughput 3.21821K wps
Begin Testing...
[Epoch 99] train avg loss 0.00210253, dev acc 0.8466, dev avg loss 0.387696, throughput 3.26405K wps
[Epoch 100 Batch 30/62] avg loss 0.0021161, throughput 3.29562K wps
[Epoch 100 Batch 60/62] avg loss 0.00209687, throughput 3.20877K wps
Begin Testing...
[Epoch 100] train avg loss 0.00214338, dev acc 0.8319, dev avg loss 0.388735, throughput 3.25817K wps
[Epoch 101 Batch 30/62] avg loss 0.00216147, throughput 3.27939K wps
[Epoch 101 Batch 60/62] avg loss 0.00205364, throughput 3.21589K wps
Begin Testing...
[Epoch 101] train avg loss 0.00213624, dev acc 0.8289, dev avg loss 0.391255, throughput 3.25327K wps
[Epoch 102 Batch 30/62] avg loss 0.00211164, throughput 3.27082K wps
[Epoch 102 Batch 60/62] avg loss 0.0019952, throughput 3.22466K wps
Begin Testing...
[Epoch 102] train avg loss 0.002083, dev acc 0.8466, dev avg loss 0.39249, throughput 3.25337K wps
[Epoch 103 Batch 30/62] avg loss 0.00200842, throughput 3.29248K wps
[Epoch 103 Batch 60/62] avg loss 0.00205018, throughput 3.22181K wps
Begin Testing...
[Epoch 103] train avg loss 0.00203013, dev acc 0.8437, dev avg loss 0.388835, throughput 3.26247K wps
[Epoch 104 Batch 30/62] avg loss 0.0020067, throughput 3.28145K wps
[Epoch 104 Batch 60/62] avg loss 0.00189851, throughput 3.22149K wps
Begin Testing...
[Epoch 104] train avg loss 0.00197464, dev acc 0.8525, dev avg loss 0.390005, throughput 3.25658K wps
Observed Improvement.
Begin Testing...
[Epoch 105 Batch 30/62] avg loss 0.00199213, throughput 3.2788K wps
[Epoch 105 Batch 60/62] avg loss 0.0020008, throughput 3.1782K wps
Begin Testing...
[Epoch 105] train avg loss 0.00205958, dev acc 0.8437, dev avg loss 0.389645, throughput 3.23448K wps
[Epoch 106 Batch 30/62] avg loss 0.00187829, throughput 3.29454K wps
[Epoch 106 Batch 60/62] avg loss 0.00190597, throughput 3.19596K wps
Begin Testing...
[Epoch 106] train avg loss 0.00190647, dev acc 0.8407, dev avg loss 0.390076, throughput 3.24988K wps
[Epoch 107 Batch 30/62] avg loss 0.00185693, throughput 3.31479K wps
[Epoch 107 Batch 60/62] avg loss 0.00189857, throughput 3.23387K wps
Begin Testing...
[Epoch 107] train avg loss 0.00191293, dev acc 0.8407, dev avg loss 0.390179, throughput 3.28082K wps
[Epoch 108 Batch 30/62] avg loss 0.00174523, throughput 3.309K wps
[Epoch 108 Batch 60/62] avg loss 0.00195723, throughput 3.22334K wps
Begin Testing...
[Epoch 108] train avg loss 0.00187826, dev acc 0.8407, dev avg loss 0.391125, throughput 3.27192K wps
[Epoch 109 Batch 30/62] avg loss 0.00175578, throughput 3.28018K wps
[Epoch 109 Batch 60/62] avg loss 0.0018422, throughput 3.21034K wps
Begin Testing...
[Epoch 109] train avg loss 0.00181805, dev acc 0.8555, dev avg loss 0.393443, throughput 3.25118K wps
Observed Improvement.
Begin Testing...
[Epoch 110 Batch 30/62] avg loss 0.00169076, throughput 3.29496K wps
[Epoch 110 Batch 60/62] avg loss 0.0018451, throughput 3.19842K wps
Begin Testing...
[Epoch 110] train avg loss 0.00181804, dev acc 0.8378, dev avg loss 0.392322, throughput 3.25407K wps
[Epoch 111 Batch 30/62] avg loss 0.00184038, throughput 3.29625K wps
[Epoch 111 Batch 60/62] avg loss 0.00178821, throughput 3.18867K wps
Begin Testing...
[Epoch 111] train avg loss 0.001864, dev acc 0.8437, dev avg loss 0.391509, throughput 3.24997K wps
[Epoch 112 Batch 30/62] avg loss 0.00172273, throughput 3.29424K wps
[Epoch 112 Batch 60/62] avg loss 0.00172912, throughput 3.18377K wps
Begin Testing...
[Epoch 112] train avg loss 0.00175813, dev acc 0.8525, dev avg loss 0.395375, throughput 3.24298K wps
[Epoch 113 Batch 30/62] avg loss 0.00162077, throughput 3.26473K wps
[Epoch 113 Batch 60/62] avg loss 0.00189236, throughput 3.21073K wps
Begin Testing...
[Epoch 113] train avg loss 0.00180109, dev acc 0.8437, dev avg loss 0.393, throughput 3.24343K wps
[Epoch 114 Batch 30/62] avg loss 0.00166752, throughput 3.2699K wps
[Epoch 114 Batch 60/62] avg loss 0.00175969, throughput 3.21173K wps
Begin Testing...
[Epoch 114] train avg loss 0.00172691, dev acc 0.8525, dev avg loss 0.395342, throughput 3.24659K wps
[Epoch 115 Batch 30/62] avg loss 0.00165015, throughput 3.29846K wps
[Epoch 115 Batch 60/62] avg loss 0.00162462, throughput 3.2352K wps
Begin Testing...
[Epoch 115] train avg loss 0.00165205, dev acc 0.8466, dev avg loss 0.393891, throughput 3.27301K wps
[Epoch 116 Batch 30/62] avg loss 0.00156695, throughput 3.29889K wps
[Epoch 116 Batch 60/62] avg loss 0.00171269, throughput 3.23348K wps
Begin Testing...
[Epoch 116] train avg loss 0.00166122, dev acc 0.8437, dev avg loss 0.394668, throughput 3.27234K wps
[Epoch 117 Batch 30/62] avg loss 0.00156918, throughput 3.31637K wps
[Epoch 117 Batch 60/62] avg loss 0.00166263, throughput 3.23099K wps
Begin Testing...
[Epoch 117] train avg loss 0.00162889, dev acc 0.8466, dev avg loss 0.396185, throughput 3.28021K wps
[Epoch 118 Batch 30/62] avg loss 0.00166891, throughput 3.26902K wps
[Epoch 118 Batch 60/62] avg loss 0.00160721, throughput 3.20859K wps
Begin Testing...
[Epoch 118] train avg loss 0.00163918, dev acc 0.8466, dev avg loss 0.398858, throughput 3.24596K wps
[Epoch 119 Batch 30/62] avg loss 0.00157578, throughput 3.26775K wps
[Epoch 119 Batch 60/62] avg loss 0.00150904, throughput 3.15171K wps
Begin Testing...
[Epoch 119] train avg loss 0.00158108, dev acc 0.8466, dev avg loss 0.399138, throughput 3.21564K wps
[Epoch 120 Batch 30/62] avg loss 0.00143529, throughput 3.25264K wps
[Epoch 120 Batch 60/62] avg loss 0.00157817, throughput 3.15017K wps
Begin Testing...
[Epoch 120] train avg loss 0.00151118, dev acc 0.8407, dev avg loss 0.39601, throughput 3.20674K wps
[Epoch 121 Batch 30/62] avg loss 0.00147313, throughput 3.25485K wps
[Epoch 121 Batch 60/62] avg loss 0.00150156, throughput 3.15262K wps
Begin Testing...
[Epoch 121] train avg loss 0.00153048, dev acc 0.8437, dev avg loss 0.400966, throughput 3.20918K wps
[Epoch 122 Batch 30/62] avg loss 0.00145238, throughput 3.24992K wps
[Epoch 122 Batch 60/62] avg loss 0.0015233, throughput 3.15663K wps
Begin Testing...
[Epoch 122] train avg loss 0.00150055, dev acc 0.8496, dev avg loss 0.398548, throughput 3.20964K wps
[Epoch 123 Batch 30/62] avg loss 0.00153649, throughput 3.26206K wps
[Epoch 123 Batch 60/62] avg loss 0.00144486, throughput 3.20947K wps
Begin Testing...
[Epoch 123] train avg loss 0.00152311, dev acc 0.8496, dev avg loss 0.397735, throughput 3.24192K wps
[Epoch 124 Batch 30/62] avg loss 0.00146153, throughput 3.28926K wps
[Epoch 124 Batch 60/62] avg loss 0.00137095, throughput 3.22121K wps
Begin Testing...
[Epoch 124] train avg loss 0.00146532, dev acc 0.8407, dev avg loss 0.396849, throughput 3.26132K wps
[Epoch 125 Batch 30/62] avg loss 0.001439, throughput 3.27489K wps
[Epoch 125 Batch 60/62] avg loss 0.00146776, throughput 3.19366K wps
Begin Testing...
[Epoch 125] train avg loss 0.00147532, dev acc 0.8437, dev avg loss 0.396767, throughput 3.24169K wps
[Epoch 126 Batch 30/62] avg loss 0.00146663, throughput 3.28177K wps
[Epoch 126 Batch 60/62] avg loss 0.00132044, throughput 3.1568K wps
Begin Testing...
[Epoch 126] train avg loss 0.0014118, dev acc 0.8496, dev avg loss 0.399621, throughput 3.22407K wps
[Epoch 127 Batch 30/62] avg loss 0.00137669, throughput 3.23611K wps
[Epoch 127 Batch 60/62] avg loss 0.00138536, throughput 3.15519K wps
Begin Testing...
[Epoch 127] train avg loss 0.00141245, dev acc 0.8496, dev avg loss 0.398625, throughput 3.20103K wps
[Epoch 128 Batch 30/62] avg loss 0.00141957, throughput 3.26182K wps
[Epoch 128 Batch 60/62] avg loss 0.00142737, throughput 3.1661K wps
Begin Testing...
[Epoch 128] train avg loss 0.00148748, dev acc 0.8319, dev avg loss 0.398191, throughput 3.22134K wps
[Epoch 129 Batch 30/62] avg loss 0.00136145, throughput 3.2844K wps
[Epoch 129 Batch 60/62] avg loss 0.00127108, throughput 3.19551K wps
Begin Testing...
[Epoch 129] train avg loss 0.00133248, dev acc 0.8437, dev avg loss 0.398243, throughput 3.24635K wps
[Epoch 130 Batch 30/62] avg loss 0.00131541, throughput 3.25239K wps
[Epoch 130 Batch 60/62] avg loss 0.00128013, throughput 3.16022K wps
Begin Testing...
[Epoch 130] train avg loss 0.0013367, dev acc 0.8407, dev avg loss 0.398031, throughput 3.21253K wps
[Epoch 131 Batch 30/62] avg loss 0.00147907, throughput 3.24936K wps
[Epoch 131 Batch 60/62] avg loss 0.00130702, throughput 3.21129K wps
Begin Testing...
[Epoch 131] train avg loss 0.00142462, dev acc 0.8378, dev avg loss 0.398569, throughput 3.2362K wps
[Epoch 132 Batch 30/62] avg loss 0.00145317, throughput 3.26555K wps
[Epoch 132 Batch 60/62] avg loss 0.00117774, throughput 3.16072K wps
Begin Testing...
[Epoch 132] train avg loss 0.00137631, dev acc 0.8378, dev avg loss 0.41748, throughput 3.21897K wps
[Epoch 133 Batch 30/62] avg loss 0.00127893, throughput 3.23708K wps
[Epoch 133 Batch 60/62] avg loss 0.00141459, throughput 3.15392K wps
Begin Testing...
[Epoch 133] train avg loss 0.0013522, dev acc 0.8437, dev avg loss 0.399488, throughput 3.20165K wps
[Epoch 134 Batch 30/62] avg loss 0.00130058, throughput 3.23931K wps
[Epoch 134 Batch 60/62] avg loss 0.00117367, throughput 3.13912K wps
Begin Testing...
[Epoch 134] train avg loss 0.00123426, dev acc 0.8496, dev avg loss 0.401637, throughput 3.19605K wps
[Epoch 135 Batch 30/62] avg loss 0.001158, throughput 3.2345K wps
[Epoch 135 Batch 60/62] avg loss 0.00123383, throughput 3.16245K wps
Begin Testing...
[Epoch 135] train avg loss 0.00120515, dev acc 0.8496, dev avg loss 0.403589, throughput 3.20434K wps
[Epoch 136 Batch 30/62] avg loss 0.00126212, throughput 3.26366K wps
[Epoch 136 Batch 60/62] avg loss 0.00118602, throughput 3.14379K wps
Begin Testing...
[Epoch 136] train avg loss 0.00131031, dev acc 0.8496, dev avg loss 0.405487, throughput 3.20872K wps
[Epoch 137 Batch 30/62] avg loss 0.00116614, throughput 3.24979K wps
[Epoch 137 Batch 60/62] avg loss 0.00130914, throughput 3.16653K wps
Begin Testing...
[Epoch 137] train avg loss 0.00123935, dev acc 0.8437, dev avg loss 0.400147, throughput 3.21577K wps
[Epoch 138 Batch 30/62] avg loss 0.00114876, throughput 3.24703K wps
[Epoch 138 Batch 60/62] avg loss 0.00122893, throughput 3.19313K wps
Begin Testing...
[Epoch 138] train avg loss 0.00120131, dev acc 0.8437, dev avg loss 0.406947, throughput 3.22604K wps
[Epoch 139 Batch 30/62] avg loss 0.0011528, throughput 3.29324K wps
[Epoch 139 Batch 60/62] avg loss 0.0011626, throughput 3.15172K wps
Begin Testing...
[Epoch 139] train avg loss 0.00117297, dev acc 0.8466, dev avg loss 0.401623, throughput 3.22666K wps
[Epoch 140 Batch 30/62] avg loss 0.00121011, throughput 3.23324K wps
[Epoch 140 Batch 60/62] avg loss 0.00115775, throughput 3.18156K wps
Begin Testing...
[Epoch 140] train avg loss 0.00120417, dev acc 0.8378, dev avg loss 0.401717, throughput 3.21581K wps
[Epoch 141 Batch 30/62] avg loss 0.0011073, throughput 3.2744K wps
[Epoch 141 Batch 60/62] avg loss 0.00117166, throughput 3.18508K wps
Begin Testing...
[Epoch 141] train avg loss 0.00114364, dev acc 0.8437, dev avg loss 0.402345, throughput 3.23459K wps
[Epoch 142 Batch 30/62] avg loss 0.00122524, throughput 3.24093K wps
[Epoch 142 Batch 60/62] avg loss 0.0010482, throughput 3.16989K wps
Begin Testing...
[Epoch 142] train avg loss 0.00114104, dev acc 0.8407, dev avg loss 0.401988, throughput 3.2114K wps
[Epoch 143 Batch 30/62] avg loss 0.00109619, throughput 3.23056K wps
[Epoch 143 Batch 60/62] avg loss 0.00106824, throughput 3.16917K wps
Begin Testing...
[Epoch 143] train avg loss 0.00110914, dev acc 0.8437, dev avg loss 0.402415, throughput 3.20723K wps
[Epoch 144 Batch 30/62] avg loss 0.0011102, throughput 3.25516K wps
[Epoch 144 Batch 60/62] avg loss 0.00107301, throughput 3.18672K wps
Begin Testing...
[Epoch 144] train avg loss 0.00111035, dev acc 0.8466, dev avg loss 0.407574, throughput 3.22758K wps
[Epoch 145 Batch 30/62] avg loss 0.00107743, throughput 3.2741K wps
[Epoch 145 Batch 60/62] avg loss 0.00110053, throughput 3.18113K wps
Begin Testing...
[Epoch 145] train avg loss 0.00110291, dev acc 0.8437, dev avg loss 0.404043, throughput 3.23428K wps
[Epoch 146 Batch 30/62] avg loss 0.0011441, throughput 3.24367K wps
[Epoch 146 Batch 60/62] avg loss 0.00103995, throughput 3.18511K wps
Begin Testing...
[Epoch 146] train avg loss 0.00110344, dev acc 0.8407, dev avg loss 0.404134, throughput 3.21965K wps
[Epoch 147 Batch 30/62] avg loss 0.00098683, throughput 3.26594K wps
[Epoch 147 Batch 60/62] avg loss 0.00108643, throughput 3.15675K wps
Begin Testing...
[Epoch 147] train avg loss 0.00104901, dev acc 0.8466, dev avg loss 0.4055, throughput 3.21648K wps
[Epoch 148 Batch 30/62] avg loss 0.00112259, throughput 3.25421K wps
[Epoch 148 Batch 60/62] avg loss 0.00105626, throughput 3.15004K wps
Begin Testing...
[Epoch 148] train avg loss 0.00110405, dev acc 0.8496, dev avg loss 0.409642, throughput 3.2073K wps
[Epoch 149 Batch 30/62] avg loss 0.000989519, throughput 3.24871K wps
[Epoch 149 Batch 60/62] avg loss 0.00107194, throughput 3.15076K wps
Begin Testing...
[Epoch 149] train avg loss 0.00103309, dev acc 0.8437, dev avg loss 0.409576, throughput 3.20555K wps
[Epoch 150 Batch 30/62] avg loss 0.000917148, throughput 3.2596K wps
[Epoch 150 Batch 60/62] avg loss 0.00104164, throughput 3.16694K wps
Begin Testing...
[Epoch 150] train avg loss 0.000985006, dev acc 0.8407, dev avg loss 0.407092, throughput 3.21986K wps
[Epoch 151 Batch 30/62] avg loss 0.00102093, throughput 3.25806K wps
[Epoch 151 Batch 60/62] avg loss 0.0010371, throughput 3.19089K wps
Begin Testing...
[Epoch 151] train avg loss 0.00105247, dev acc 0.8466, dev avg loss 0.413291, throughput 3.23024K wps
[Epoch 152 Batch 30/62] avg loss 0.00104704, throughput 3.25952K wps
[Epoch 152 Batch 60/62] avg loss 0.000967719, throughput 3.16422K wps
Begin Testing...
[Epoch 152] train avg loss 0.00102265, dev acc 0.8407, dev avg loss 0.406275, throughput 3.21705K wps
[Epoch 153 Batch 30/62] avg loss 0.000955485, throughput 3.24862K wps
[Epoch 153 Batch 60/62] avg loss 0.00103006, throughput 3.13185K wps
Begin Testing...
[Epoch 153] train avg loss 0.00100455, dev acc 0.8378, dev avg loss 0.406671, throughput 3.1951K wps
[Epoch 154 Batch 30/62] avg loss 0.000836776, throughput 3.24998K wps
[Epoch 154 Batch 60/62] avg loss 0.00100767, throughput 3.13571K wps
Begin Testing...
[Epoch 154] train avg loss 0.000935857, dev acc 0.8378, dev avg loss 0.407009, throughput 3.19422K wps
[Epoch 155 Batch 30/62] avg loss 0.000885451, throughput 3.2654K wps
[Epoch 155 Batch 60/62] avg loss 0.000964668, throughput 3.14981K wps
Begin Testing...
[Epoch 155] train avg loss 0.000924592, dev acc 0.8378, dev avg loss 0.408405, throughput 3.21263K wps
[Epoch 156 Batch 30/62] avg loss 0.00087178, throughput 3.24694K wps
[Epoch 156 Batch 60/62] avg loss 0.000953181, throughput 3.15303K wps
Begin Testing...
[Epoch 156] train avg loss 0.000921692, dev acc 0.8378, dev avg loss 0.408626, throughput 3.20456K wps
[Epoch 157 Batch 30/62] avg loss 0.000950652, throughput 3.27553K wps
[Epoch 157 Batch 60/62] avg loss 0.000978885, throughput 3.16088K wps
Begin Testing...
[Epoch 157] train avg loss 0.000988944, dev acc 0.8407, dev avg loss 0.409322, throughput 3.22324K wps
[Epoch 158 Batch 30/62] avg loss 0.000960652, throughput 3.23562K wps
[Epoch 158 Batch 60/62] avg loss 0.000923171, throughput 3.16347K wps
Begin Testing...
[Epoch 158] train avg loss 0.000952645, dev acc 0.8407, dev avg loss 0.409051, throughput 3.2059K wps
[Epoch 159 Batch 30/62] avg loss 0.000875838, throughput 3.25856K wps
[Epoch 159 Batch 60/62] avg loss 0.000920967, throughput 3.18236K wps
Begin Testing...
[Epoch 159] train avg loss 0.000908508, dev acc 0.8378, dev avg loss 0.408372, throughput 3.22629K wps
[Epoch 160 Batch 30/62] avg loss 0.000900512, throughput 3.27347K wps
[Epoch 160 Batch 60/62] avg loss 0.000901154, throughput 3.16393K wps
Begin Testing...
[Epoch 160] train avg loss 0.000914601, dev acc 0.8437, dev avg loss 0.413876, throughput 3.22348K wps
[Epoch 161 Batch 30/62] avg loss 0.00081682, throughput 3.24988K wps
[Epoch 161 Batch 60/62] avg loss 0.000921989, throughput 3.14469K wps
Begin Testing...
[Epoch 161] train avg loss 0.000894754, dev acc 0.8378, dev avg loss 0.410974, throughput 3.20317K wps
[Epoch 162 Batch 30/62] avg loss 0.000941156, throughput 3.24553K wps
[Epoch 162 Batch 60/62] avg loss 0.000802051, throughput 3.14844K wps
Begin Testing...
[Epoch 162] train avg loss 0.000886813, dev acc 0.8378, dev avg loss 0.411818, throughput 3.20274K wps
[Epoch 163 Batch 30/62] avg loss 0.000819615, throughput 3.25889K wps
[Epoch 163 Batch 60/62] avg loss 0.000866993, throughput 3.13349K wps
Begin Testing...
[Epoch 163] train avg loss 0.000886667, dev acc 0.8496, dev avg loss 0.417006, throughput 3.20103K wps
[Epoch 164 Batch 30/62] avg loss 0.000928237, throughput 3.25729K wps
[Epoch 164 Batch 60/62] avg loss 0.000897526, throughput 3.15221K wps
Begin Testing...
[Epoch 164] train avg loss 0.000909757, dev acc 0.8466, dev avg loss 0.413948, throughput 3.21002K wps
[Epoch 165 Batch 30/62] avg loss 0.000867886, throughput 3.24834K wps
[Epoch 165 Batch 60/62] avg loss 0.000871119, throughput 3.16348K wps
Begin Testing...
[Epoch 165] train avg loss 0.000872623, dev acc 0.8378, dev avg loss 0.412925, throughput 3.2114K wps
[Epoch 166 Batch 30/62] avg loss 0.000913893, throughput 3.24569K wps
[Epoch 166 Batch 60/62] avg loss 0.000869908, throughput 3.16556K wps
Begin Testing...
[Epoch 166] train avg loss 0.000896341, dev acc 0.8407, dev avg loss 0.413815, throughput 3.21167K wps
[Epoch 167 Batch 30/62] avg loss 0.000937027, throughput 3.21996K wps
[Epoch 167 Batch 60/62] avg loss 0.00086624, throughput 3.16658K wps
Begin Testing...
[Epoch 167] train avg loss 0.000903147, dev acc 0.8437, dev avg loss 0.415977, throughput 3.19907K wps
[Epoch 168 Batch 30/62] avg loss 0.00081504, throughput 3.2317K wps
[Epoch 168 Batch 60/62] avg loss 0.000825115, throughput 3.15748K wps
Begin Testing...
[Epoch 168] train avg loss 0.000816721, dev acc 0.8437, dev avg loss 0.414828, throughput 3.20054K wps
[Epoch 169 Batch 30/62] avg loss 0.000791054, throughput 3.23152K wps
[Epoch 169 Batch 60/62] avg loss 0.000879886, throughput 3.16558K wps
Begin Testing...
[Epoch 169] train avg loss 0.000838755, dev acc 0.8378, dev avg loss 0.414819, throughput 3.20455K wps
[Epoch 170 Batch 30/62] avg loss 0.000781487, throughput 3.24735K wps
[Epoch 170 Batch 60/62] avg loss 0.000873738, throughput 3.16372K wps
Begin Testing...
[Epoch 170] train avg loss 0.000830254, dev acc 0.8437, dev avg loss 0.415007, throughput 3.21206K wps
[Epoch 171 Batch 30/62] avg loss 0.000802799, throughput 3.22428K wps
[Epoch 171 Batch 60/62] avg loss 0.000815636, throughput 3.14616K wps
Begin Testing...
[Epoch 171] train avg loss 0.000824586, dev acc 0.8437, dev avg loss 0.415976, throughput 3.19095K wps
[Epoch 172 Batch 30/62] avg loss 0.000783063, throughput 3.23417K wps
[Epoch 172 Batch 60/62] avg loss 0.000767788, throughput 3.15906K wps
Begin Testing...
[Epoch 172] train avg loss 0.000786149, dev acc 0.8437, dev avg loss 0.416616, throughput 3.2029K wps
[Epoch 173 Batch 30/62] avg loss 0.000788148, throughput 3.24589K wps
[Epoch 173 Batch 60/62] avg loss 0.0008021, throughput 3.16691K wps
Begin Testing...
[Epoch 173] train avg loss 0.000803167, dev acc 0.8466, dev avg loss 0.423611, throughput 3.21237K wps
[Epoch 174 Batch 30/62] avg loss 0.00074542, throughput 3.22868K wps
[Epoch 174 Batch 60/62] avg loss 0.00078851, throughput 3.15956K wps
Begin Testing...
[Epoch 174] train avg loss 0.00076482, dev acc 0.8466, dev avg loss 0.419527, throughput 3.20162K wps
[Epoch 175 Batch 30/62] avg loss 0.00080713, throughput 3.24349K wps
[Epoch 175 Batch 60/62] avg loss 0.000775451, throughput 3.19714K wps
Begin Testing...
[Epoch 175] train avg loss 0.000794876, dev acc 0.8407, dev avg loss 0.416965, throughput 3.2257K wps
[Epoch 176 Batch 30/62] avg loss 0.000758438, throughput 3.25468K wps
[Epoch 176 Batch 60/62] avg loss 0.000798023, throughput 3.16705K wps
Begin Testing...
[Epoch 176] train avg loss 0.000785955, dev acc 0.8437, dev avg loss 0.42017, throughput 3.21597K wps
[Epoch 177 Batch 30/62] avg loss 0.000696878, throughput 3.25449K wps
[Epoch 177 Batch 60/62] avg loss 0.000789322, throughput 3.16129K wps
Begin Testing...
[Epoch 177] train avg loss 0.000776826, dev acc 0.8466, dev avg loss 0.4172, throughput 3.21371K wps
[Epoch 178 Batch 30/62] avg loss 0.000754291, throughput 3.24968K wps
[Epoch 178 Batch 60/62] avg loss 0.000699679, throughput 3.15357K wps
Begin Testing...
[Epoch 178] train avg loss 0.000727838, dev acc 0.8466, dev avg loss 0.419713, throughput 3.20714K wps
[Epoch 179 Batch 30/62] avg loss 0.000775183, throughput 3.24934K wps
[Epoch 179 Batch 60/62] avg loss 0.000739611, throughput 3.15185K wps
Begin Testing...
[Epoch 179] train avg loss 0.000770162, dev acc 0.8437, dev avg loss 0.419011, throughput 3.20564K wps
[Epoch 180 Batch 30/62] avg loss 0.000819214, throughput 3.23868K wps
[Epoch 180 Batch 60/62] avg loss 0.000665515, throughput 3.1493K wps
Begin Testing...
[Epoch 180] train avg loss 0.000753941, dev acc 0.8407, dev avg loss 0.418744, throughput 3.19894K wps
[Epoch 181 Batch 30/62] avg loss 0.000670374, throughput 3.24977K wps
[Epoch 181 Batch 60/62] avg loss 0.000801806, throughput 3.15296K wps
Begin Testing...
[Epoch 181] train avg loss 0.000738884, dev acc 0.8407, dev avg loss 0.41933, throughput 3.20529K wps
[Epoch 182 Batch 30/62] avg loss 0.000640986, throughput 3.25459K wps
[Epoch 182 Batch 60/62] avg loss 0.00075251, throughput 3.15949K wps
Begin Testing...
[Epoch 182] train avg loss 0.00069369, dev acc 0.8466, dev avg loss 0.421982, throughput 3.21269K wps
[Epoch 183 Batch 30/62] avg loss 0.000817545, throughput 3.25483K wps
[Epoch 183 Batch 60/62] avg loss 0.000731832, throughput 3.16371K wps
Begin Testing...
[Epoch 183] train avg loss 0.000777945, dev acc 0.8407, dev avg loss 0.421007, throughput 3.21695K wps
[Epoch 184 Batch 30/62] avg loss 0.000745812, throughput 3.23429K wps
[Epoch 184 Batch 60/62] avg loss 0.000758532, throughput 3.19677K wps
Begin Testing...
[Epoch 184] train avg loss 0.000754565, dev acc 0.8437, dev avg loss 0.423129, throughput 3.22255K wps
[Epoch 185 Batch 30/62] avg loss 0.000781601, throughput 3.26775K wps
[Epoch 185 Batch 60/62] avg loss 0.000662684, throughput 3.16472K wps
Begin Testing...
[Epoch 185] train avg loss 0.000730471, dev acc 0.8437, dev avg loss 0.422122, throughput 3.22158K wps
[Epoch 186 Batch 30/62] avg loss 0.000764231, throughput 3.25969K wps
[Epoch 186 Batch 60/62] avg loss 0.000725359, throughput 3.17502K wps
Begin Testing...
[Epoch 186] train avg loss 0.000745411, dev acc 0.8466, dev avg loss 0.423248, throughput 3.22482K wps
[Epoch 187 Batch 30/62] avg loss 0.000656999, throughput 3.27893K wps
[Epoch 187 Batch 60/62] avg loss 0.000786882, throughput 3.14309K wps
Begin Testing...
[Epoch 187] train avg loss 0.000723593, dev acc 0.8466, dev avg loss 0.423615, throughput 3.21681K wps
[Epoch 188 Batch 30/62] avg loss 0.000680193, throughput 3.2625K wps
[Epoch 188 Batch 60/62] avg loss 0.000650376, throughput 3.15546K wps
Begin Testing...
[Epoch 188] train avg loss 0.000680365, dev acc 0.8407, dev avg loss 0.422953, throughput 3.21327K wps
[Epoch 189 Batch 30/62] avg loss 0.000678876, throughput 3.26007K wps
[Epoch 189 Batch 60/62] avg loss 0.000693678, throughput 3.1385K wps
Begin Testing...
[Epoch 189] train avg loss 0.000728686, dev acc 0.8407, dev avg loss 0.430882, throughput 3.20432K wps
[Epoch 190 Batch 30/62] avg loss 0.000719715, throughput 3.24675K wps
[Epoch 190 Batch 60/62] avg loss 0.000650824, throughput 3.17041K wps
Begin Testing...
[Epoch 190] train avg loss 0.00068864, dev acc 0.8437, dev avg loss 0.423589, throughput 3.21395K wps
[Epoch 191 Batch 30/62] avg loss 0.000665074, throughput 3.24358K wps
[Epoch 191 Batch 60/62] avg loss 0.000667189, throughput 3.14327K wps
Begin Testing...
[Epoch 191] train avg loss 0.000666489, dev acc 0.8466, dev avg loss 0.425574, throughput 3.19886K wps
[Epoch 192 Batch 30/62] avg loss 0.000607768, throughput 3.23692K wps
[Epoch 192 Batch 60/62] avg loss 0.000663213, throughput 3.167K wps
Begin Testing...
[Epoch 192] train avg loss 0.000640783, dev acc 0.8437, dev avg loss 0.427018, throughput 3.20836K wps
[Epoch 193 Batch 30/62] avg loss 0.000641234, throughput 3.25018K wps
[Epoch 193 Batch 60/62] avg loss 0.000735396, throughput 3.19331K wps
Begin Testing...
[Epoch 193] train avg loss 0.000686551, dev acc 0.8437, dev avg loss 0.425355, throughput 3.22816K wps
[Epoch 194 Batch 30/62] avg loss 0.000602857, throughput 3.27102K wps
[Epoch 194 Batch 60/62] avg loss 0.000681736, throughput 3.15736K wps
Begin Testing...
[Epoch 194] train avg loss 0.000638873, dev acc 0.8466, dev avg loss 0.427264, throughput 3.21752K wps
[Epoch 195 Batch 30/62] avg loss 0.000690048, throughput 3.25811K wps
[Epoch 195 Batch 60/62] avg loss 0.000633498, throughput 3.13181K wps
Begin Testing...
[Epoch 195] train avg loss 0.000668724, dev acc 0.8407, dev avg loss 0.425668, throughput 3.20223K wps
[Epoch 196 Batch 30/62] avg loss 0.000633123, throughput 3.24878K wps
[Epoch 196 Batch 60/62] avg loss 0.000699721, throughput 3.15622K wps
Begin Testing...
[Epoch 196] train avg loss 0.000699741, dev acc 0.8466, dev avg loss 0.427989, throughput 3.20812K wps
[Epoch 197 Batch 30/62] avg loss 0.000622794, throughput 3.25063K wps
[Epoch 197 Batch 60/62] avg loss 0.000614688, throughput 3.15786K wps
Begin Testing...
[Epoch 197] train avg loss 0.000626001, dev acc 0.8466, dev avg loss 0.428052, throughput 3.20909K wps
[Epoch 198 Batch 30/62] avg loss 0.000616123, throughput 3.24976K wps
[Epoch 198 Batch 60/62] avg loss 0.000667874, throughput 3.15063K wps
Begin Testing...
[Epoch 198] train avg loss 0.000654691, dev acc 0.8466, dev avg loss 0.430411, throughput 3.20528K wps
[Epoch 199 Batch 30/62] avg loss 0.000640891, throughput 3.2579K wps
[Epoch 199 Batch 60/62] avg loss 0.00067586, throughput 3.20935K wps
Begin Testing...
[Epoch 199] train avg loss 0.00067198, dev acc 0.8437, dev avg loss 0.429373, throughput 3.24112K wps
Test loss 0.314019, test acc 0.8621
Total time cost 460.29s
[Epoch 0 Batch 30/62] avg loss 0.0135574, throughput 3.07866K wps
[Epoch 0 Batch 60/62] avg loss 0.012979, throughput 3.18491K wps
Begin Testing...
[Epoch 0] train avg loss 0.0133952, dev acc 0.6519, dev avg loss 0.641543, throughput 3.13922K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130709, throughput 3.24171K wps
[Epoch 1 Batch 60/62] avg loss 0.0128744, throughput 3.16558K wps
Begin Testing...
[Epoch 1] train avg loss 0.0131227, dev acc 0.6519, dev avg loss 0.631503, throughput 3.20907K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0128439, throughput 3.27923K wps
[Epoch 2 Batch 60/62] avg loss 0.0128639, throughput 3.13792K wps
Begin Testing...
[Epoch 2] train avg loss 0.0130122, dev acc 0.6519, dev avg loss 0.625119, throughput 3.21116K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0127279, throughput 3.28489K wps
[Epoch 3 Batch 60/62] avg loss 0.0125027, throughput 3.1594K wps
Begin Testing...
[Epoch 3] train avg loss 0.0127523, dev acc 0.6519, dev avg loss 0.616692, throughput 3.22643K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0126343, throughput 3.22785K wps
[Epoch 4 Batch 60/62] avg loss 0.0121908, throughput 3.19766K wps
Begin Testing...
[Epoch 4] train avg loss 0.0126011, dev acc 0.6519, dev avg loss 0.609618, throughput 3.2194K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.012367, throughput 3.28611K wps
[Epoch 5 Batch 60/62] avg loss 0.0121978, throughput 3.17065K wps
Begin Testing...
[Epoch 5] train avg loss 0.0124231, dev acc 0.6519, dev avg loss 0.601991, throughput 3.23314K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0121676, throughput 3.27088K wps
[Epoch 6 Batch 60/62] avg loss 0.01198, throughput 3.16811K wps
Begin Testing...
[Epoch 6] train avg loss 0.0122455, dev acc 0.6519, dev avg loss 0.594572, throughput 3.22396K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0119005, throughput 3.25237K wps
[Epoch 7 Batch 60/62] avg loss 0.0119368, throughput 3.1731K wps
Begin Testing...
[Epoch 7] train avg loss 0.0120854, dev acc 0.6549, dev avg loss 0.587292, throughput 3.21922K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0116713, throughput 3.24862K wps
[Epoch 8 Batch 60/62] avg loss 0.011845, throughput 3.15592K wps
Begin Testing...
[Epoch 8] train avg loss 0.0118977, dev acc 0.6519, dev avg loss 0.578652, throughput 3.20737K wps
[Epoch 9 Batch 30/62] avg loss 0.0115793, throughput 3.23409K wps
[Epoch 9 Batch 60/62] avg loss 0.0116747, throughput 3.15045K wps
Begin Testing...
[Epoch 9] train avg loss 0.0117178, dev acc 0.6667, dev avg loss 0.570167, throughput 3.19645K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0115629, throughput 3.2725K wps
[Epoch 10 Batch 60/62] avg loss 0.0111805, throughput 3.16966K wps
Begin Testing...
[Epoch 10] train avg loss 0.0114645, dev acc 0.6519, dev avg loss 0.564529, throughput 3.22574K wps
[Epoch 11 Batch 30/62] avg loss 0.011223, throughput 3.25131K wps
[Epoch 11 Batch 60/62] avg loss 0.0111048, throughput 3.14373K wps
Begin Testing...
[Epoch 11] train avg loss 0.0112874, dev acc 0.6726, dev avg loss 0.553088, throughput 3.20335K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0113727, throughput 3.25312K wps
[Epoch 12 Batch 60/62] avg loss 0.0106706, throughput 3.17616K wps
Begin Testing...
[Epoch 12] train avg loss 0.0111691, dev acc 0.6962, dev avg loss 0.542883, throughput 3.21861K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0107939, throughput 3.2613K wps
[Epoch 13 Batch 60/62] avg loss 0.0108432, throughput 3.17437K wps
Begin Testing...
[Epoch 13] train avg loss 0.0109506, dev acc 0.7080, dev avg loss 0.533148, throughput 3.22344K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0105937, throughput 3.26849K wps
[Epoch 14 Batch 60/62] avg loss 0.0106055, throughput 3.16112K wps
Begin Testing...
[Epoch 14] train avg loss 0.010696, dev acc 0.7139, dev avg loss 0.523547, throughput 3.21994K wps
Observed Improvement.
Begin Testing...
[Epoch 15 Batch 30/62] avg loss 0.0104243, throughput 3.28289K wps
[Epoch 15 Batch 60/62] avg loss 0.0103302, throughput 3.15614K wps
Begin Testing...
[Epoch 15] train avg loss 0.0105615, dev acc 0.7493, dev avg loss 0.514658, throughput 3.22384K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.0103354, throughput 3.25636K wps
[Epoch 16 Batch 60/62] avg loss 0.0101576, throughput 3.15248K wps
Begin Testing...
[Epoch 16] train avg loss 0.0103702, dev acc 0.7404, dev avg loss 0.504324, throughput 3.20964K wps
[Epoch 17 Batch 30/62] avg loss 0.00986336, throughput 3.25189K wps
[Epoch 17 Batch 60/62] avg loss 0.0100071, throughput 3.14713K wps
Begin Testing...
[Epoch 17] train avg loss 0.0100605, dev acc 0.7463, dev avg loss 0.494493, throughput 3.20533K wps
[Epoch 18 Batch 30/62] avg loss 0.00974508, throughput 3.25095K wps
[Epoch 18 Batch 60/62] avg loss 0.0097594, throughput 3.16575K wps
Begin Testing...
[Epoch 18] train avg loss 0.00989522, dev acc 0.7434, dev avg loss 0.488128, throughput 3.2151K wps
[Epoch 19 Batch 30/62] avg loss 0.00952682, throughput 3.25136K wps
[Epoch 19 Batch 60/62] avg loss 0.00965787, throughput 3.15065K wps
Begin Testing...
[Epoch 19] train avg loss 0.00971442, dev acc 0.7876, dev avg loss 0.476342, throughput 3.20416K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.00941179, throughput 3.24575K wps
[Epoch 20 Batch 60/62] avg loss 0.00924097, throughput 3.15792K wps
Begin Testing...
[Epoch 20] train avg loss 0.00947755, dev acc 0.7434, dev avg loss 0.472154, throughput 3.20742K wps
[Epoch 21 Batch 30/62] avg loss 0.00931306, throughput 3.24868K wps
[Epoch 21 Batch 60/62] avg loss 0.0093113, throughput 3.16769K wps
Begin Testing...
[Epoch 21] train avg loss 0.00947986, dev acc 0.8083, dev avg loss 0.459827, throughput 3.21385K wps
Observed Improvement.
Begin Testing...
[Epoch 22 Batch 30/62] avg loss 0.00892197, throughput 3.25363K wps
[Epoch 22 Batch 60/62] avg loss 0.00903774, throughput 3.17139K wps
Begin Testing...
[Epoch 22] train avg loss 0.0091496, dev acc 0.7758, dev avg loss 0.45287, throughput 3.22023K wps
[Epoch 23 Batch 30/62] avg loss 0.00906015, throughput 3.23046K wps
[Epoch 23 Batch 60/62] avg loss 0.00872183, throughput 3.1978K wps
Begin Testing...
[Epoch 23] train avg loss 0.00903507, dev acc 0.8142, dev avg loss 0.445254, throughput 3.21739K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.00867489, throughput 3.28672K wps
[Epoch 24 Batch 60/62] avg loss 0.00872264, throughput 3.16349K wps
Begin Testing...
[Epoch 24] train avg loss 0.00873972, dev acc 0.7640, dev avg loss 0.442282, throughput 3.22934K wps
[Epoch 25 Batch 30/62] avg loss 0.00868582, throughput 3.27094K wps
[Epoch 25 Batch 60/62] avg loss 0.00827204, throughput 3.16175K wps
Begin Testing...
[Epoch 25] train avg loss 0.00854924, dev acc 0.7965, dev avg loss 0.432367, throughput 3.22135K wps
[Epoch 26 Batch 30/62] avg loss 0.00814497, throughput 3.24028K wps
[Epoch 26 Batch 60/62] avg loss 0.00850115, throughput 3.15265K wps
Begin Testing...
[Epoch 26] train avg loss 0.00844233, dev acc 0.8024, dev avg loss 0.426936, throughput 3.2018K wps
[Epoch 27 Batch 30/62] avg loss 0.00810176, throughput 3.23982K wps
[Epoch 27 Batch 60/62] avg loss 0.00801792, throughput 3.15289K wps
Begin Testing...
[Epoch 27] train avg loss 0.00817964, dev acc 0.8112, dev avg loss 0.421161, throughput 3.20201K wps
[Epoch 28 Batch 30/62] avg loss 0.00807233, throughput 3.24566K wps
[Epoch 28 Batch 60/62] avg loss 0.00796654, throughput 3.15716K wps
Begin Testing...
[Epoch 28] train avg loss 0.00810722, dev acc 0.8260, dev avg loss 0.415569, throughput 3.2085K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00786674, throughput 3.26909K wps
[Epoch 29 Batch 60/62] avg loss 0.00787671, throughput 3.20308K wps
Begin Testing...
[Epoch 29] train avg loss 0.00797557, dev acc 0.8083, dev avg loss 0.411946, throughput 3.24296K wps
[Epoch 30 Batch 30/62] avg loss 0.00796476, throughput 3.27158K wps
[Epoch 30 Batch 60/62] avg loss 0.00756156, throughput 3.16573K wps
Begin Testing...
[Epoch 30] train avg loss 0.00788859, dev acc 0.8142, dev avg loss 0.406946, throughput 3.22383K wps
[Epoch 31 Batch 30/62] avg loss 0.00765778, throughput 3.23778K wps
[Epoch 31 Batch 60/62] avg loss 0.00755673, throughput 3.14496K wps
Begin Testing...
[Epoch 31] train avg loss 0.00768683, dev acc 0.7847, dev avg loss 0.410015, throughput 3.19672K wps
[Epoch 32 Batch 30/62] avg loss 0.00767625, throughput 3.24525K wps
[Epoch 32 Batch 60/62] avg loss 0.00747715, throughput 3.15585K wps
Begin Testing...
[Epoch 32] train avg loss 0.0077104, dev acc 0.8289, dev avg loss 0.398518, throughput 3.20629K wps
Observed Improvement.
Begin Testing...
[Epoch 33 Batch 30/62] avg loss 0.00715346, throughput 3.26697K wps
[Epoch 33 Batch 60/62] avg loss 0.00734539, throughput 3.15733K wps
Begin Testing...
[Epoch 33] train avg loss 0.00747873, dev acc 0.8319, dev avg loss 0.394641, throughput 3.2172K wps
Observed Improvement.
Begin Testing...
[Epoch 34 Batch 30/62] avg loss 0.00706986, throughput 3.27984K wps
[Epoch 34 Batch 60/62] avg loss 0.00709722, throughput 3.16028K wps
Begin Testing...
[Epoch 34] train avg loss 0.00725084, dev acc 0.8260, dev avg loss 0.391031, throughput 3.22478K wps
[Epoch 35 Batch 30/62] avg loss 0.00717212, throughput 3.24901K wps
[Epoch 35 Batch 60/62] avg loss 0.00696186, throughput 3.15867K wps
Begin Testing...
[Epoch 35] train avg loss 0.00716677, dev acc 0.8201, dev avg loss 0.38984, throughput 3.21019K wps
[Epoch 36 Batch 30/62] avg loss 0.00677139, throughput 3.22791K wps
[Epoch 36 Batch 60/62] avg loss 0.00718463, throughput 3.14928K wps
Begin Testing...
[Epoch 36] train avg loss 0.00700991, dev acc 0.8142, dev avg loss 0.388916, throughput 3.19387K wps
[Epoch 37 Batch 30/62] avg loss 0.00670368, throughput 3.26028K wps
[Epoch 37 Batch 60/62] avg loss 0.00688251, throughput 3.13881K wps
Begin Testing...
[Epoch 37] train avg loss 0.00692506, dev acc 0.8171, dev avg loss 0.385076, throughput 3.20645K wps
[Epoch 38 Batch 30/62] avg loss 0.00680024, throughput 3.23948K wps
[Epoch 38 Batch 60/62] avg loss 0.00655596, throughput 3.17035K wps
Begin Testing...
[Epoch 38] train avg loss 0.00677993, dev acc 0.8289, dev avg loss 0.379224, throughput 3.21111K wps
[Epoch 39 Batch 30/62] avg loss 0.00635235, throughput 3.22705K wps
[Epoch 39 Batch 60/62] avg loss 0.00664837, throughput 3.16554K wps
Begin Testing...
[Epoch 39] train avg loss 0.00657837, dev acc 0.8348, dev avg loss 0.376032, throughput 3.2023K wps
Observed Improvement.
Begin Testing...
[Epoch 40 Batch 30/62] avg loss 0.00651779, throughput 3.24429K wps
[Epoch 40 Batch 60/62] avg loss 0.00643835, throughput 3.15378K wps
Begin Testing...
[Epoch 40] train avg loss 0.00658742, dev acc 0.8171, dev avg loss 0.378361, throughput 3.20428K wps
[Epoch 41 Batch 30/62] avg loss 0.00627655, throughput 3.24212K wps
[Epoch 41 Batch 60/62] avg loss 0.00611812, throughput 3.18067K wps
Begin Testing...
[Epoch 41] train avg loss 0.00629779, dev acc 0.8289, dev avg loss 0.370833, throughput 3.21779K wps
[Epoch 42 Batch 30/62] avg loss 0.00623457, throughput 3.26548K wps
[Epoch 42 Batch 60/62] avg loss 0.00636364, throughput 3.20299K wps
Begin Testing...
[Epoch 42] train avg loss 0.00635249, dev acc 0.8319, dev avg loss 0.370998, throughput 3.23948K wps
[Epoch 43 Batch 30/62] avg loss 0.00580316, throughput 3.25637K wps
[Epoch 43 Batch 60/62] avg loss 0.00616958, throughput 3.16592K wps
Begin Testing...
[Epoch 43] train avg loss 0.00603585, dev acc 0.8319, dev avg loss 0.369344, throughput 3.21577K wps
[Epoch 44 Batch 30/62] avg loss 0.00577095, throughput 3.24617K wps
[Epoch 44 Batch 60/62] avg loss 0.00611262, throughput 3.1603K wps
Begin Testing...
[Epoch 44] train avg loss 0.00597394, dev acc 0.8319, dev avg loss 0.364552, throughput 3.2091K wps
[Epoch 45 Batch 30/62] avg loss 0.00591174, throughput 3.23415K wps
[Epoch 45 Batch 60/62] avg loss 0.0058169, throughput 3.1659K wps
Begin Testing...
[Epoch 45] train avg loss 0.00590829, dev acc 0.8171, dev avg loss 0.370522, throughput 3.20709K wps
[Epoch 46 Batch 30/62] avg loss 0.00559361, throughput 3.24783K wps
[Epoch 46 Batch 60/62] avg loss 0.00567178, throughput 3.18862K wps
Begin Testing...
[Epoch 46] train avg loss 0.0057223, dev acc 0.8319, dev avg loss 0.360828, throughput 3.2236K wps
[Epoch 47 Batch 30/62] avg loss 0.0055992, throughput 3.28185K wps
[Epoch 47 Batch 60/62] avg loss 0.00558164, throughput 3.17185K wps
Begin Testing...
[Epoch 47] train avg loss 0.00566658, dev acc 0.8289, dev avg loss 0.362718, throughput 3.23141K wps
[Epoch 48 Batch 30/62] avg loss 0.00574772, throughput 3.24801K wps
[Epoch 48 Batch 60/62] avg loss 0.00538274, throughput 3.15121K wps
Begin Testing...
[Epoch 48] train avg loss 0.00565087, dev acc 0.8260, dev avg loss 0.361251, throughput 3.20646K wps
[Epoch 49 Batch 30/62] avg loss 0.00545892, throughput 3.25633K wps
[Epoch 49 Batch 60/62] avg loss 0.0054308, throughput 3.1968K wps
Begin Testing...
[Epoch 49] train avg loss 0.00553843, dev acc 0.8142, dev avg loss 0.36615, throughput 3.23192K wps
[Epoch 50 Batch 30/62] avg loss 0.00540096, throughput 3.27127K wps
[Epoch 50 Batch 60/62] avg loss 0.00508417, throughput 3.1553K wps
Begin Testing...
[Epoch 50] train avg loss 0.00534031, dev acc 0.8230, dev avg loss 0.359594, throughput 3.21664K wps
[Epoch 51 Batch 30/62] avg loss 0.00535777, throughput 3.2509K wps
[Epoch 51 Batch 60/62] avg loss 0.00538751, throughput 3.13842K wps
Begin Testing...
[Epoch 51] train avg loss 0.00542528, dev acc 0.8378, dev avg loss 0.354108, throughput 3.19984K wps
Observed Improvement.
Begin Testing...
[Epoch 52 Batch 30/62] avg loss 0.00521326, throughput 3.27236K wps
[Epoch 52 Batch 60/62] avg loss 0.00526752, throughput 3.16426K wps
Begin Testing...
[Epoch 52] train avg loss 0.00528527, dev acc 0.8407, dev avg loss 0.352234, throughput 3.22253K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.00510656, throughput 3.26709K wps
[Epoch 53 Batch 60/62] avg loss 0.00483918, throughput 3.17188K wps
Begin Testing...
[Epoch 53] train avg loss 0.00505182, dev acc 0.8171, dev avg loss 0.358369, throughput 3.2232K wps
[Epoch 54 Batch 30/62] avg loss 0.00493172, throughput 3.26158K wps
[Epoch 54 Batch 60/62] avg loss 0.00507339, throughput 3.16053K wps
Begin Testing...
[Epoch 54] train avg loss 0.00506992, dev acc 0.8230, dev avg loss 0.352116, throughput 3.21702K wps
[Epoch 55 Batch 30/62] avg loss 0.00461902, throughput 3.25631K wps
[Epoch 55 Batch 60/62] avg loss 0.00498838, throughput 3.21318K wps
Begin Testing...
[Epoch 55] train avg loss 0.00482692, dev acc 0.8201, dev avg loss 0.351037, throughput 3.24043K wps
[Epoch 56 Batch 30/62] avg loss 0.00460913, throughput 3.2674K wps
[Epoch 56 Batch 60/62] avg loss 0.00465399, throughput 3.18831K wps
Begin Testing...
[Epoch 56] train avg loss 0.00468218, dev acc 0.8230, dev avg loss 0.354941, throughput 3.23554K wps
[Epoch 57 Batch 30/62] avg loss 0.00479465, throughput 3.29812K wps
[Epoch 57 Batch 60/62] avg loss 0.00472585, throughput 3.19605K wps
Begin Testing...
[Epoch 57] train avg loss 0.00487994, dev acc 0.8319, dev avg loss 0.349553, throughput 3.25316K wps
[Epoch 58 Batch 30/62] avg loss 0.00461715, throughput 3.27256K wps
[Epoch 58 Batch 60/62] avg loss 0.00458143, throughput 3.17298K wps
Begin Testing...
[Epoch 58] train avg loss 0.00468395, dev acc 0.8437, dev avg loss 0.344143, throughput 3.22729K wps
Observed Improvement.
Begin Testing...
[Epoch 59 Batch 30/62] avg loss 0.00449204, throughput 3.27639K wps
[Epoch 59 Batch 60/62] avg loss 0.00460614, throughput 3.15945K wps
Begin Testing...
[Epoch 59] train avg loss 0.00459681, dev acc 0.8378, dev avg loss 0.345372, throughput 3.22178K wps
[Epoch 60 Batch 30/62] avg loss 0.00449852, throughput 3.25966K wps
[Epoch 60 Batch 60/62] avg loss 0.00432719, throughput 3.13504K wps
Begin Testing...
[Epoch 60] train avg loss 0.00449311, dev acc 0.8437, dev avg loss 0.34313, throughput 3.2017K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00448038, throughput 3.28085K wps
[Epoch 61 Batch 60/62] avg loss 0.00430096, throughput 3.16086K wps
Begin Testing...
[Epoch 61] train avg loss 0.00446496, dev acc 0.8407, dev avg loss 0.342636, throughput 3.2256K wps
[Epoch 62 Batch 30/62] avg loss 0.00431065, throughput 3.25035K wps
[Epoch 62 Batch 60/62] avg loss 0.00429934, throughput 3.16064K wps
Begin Testing...
[Epoch 62] train avg loss 0.00434144, dev acc 0.8201, dev avg loss 0.34909, throughput 3.21122K wps
[Epoch 63 Batch 30/62] avg loss 0.00416075, throughput 3.23566K wps
[Epoch 63 Batch 60/62] avg loss 0.00406999, throughput 3.17501K wps
Begin Testing...
[Epoch 63] train avg loss 0.00414182, dev acc 0.8437, dev avg loss 0.340642, throughput 3.21205K wps
Observed Improvement.
Begin Testing...
[Epoch 64 Batch 30/62] avg loss 0.00418729, throughput 3.2458K wps
[Epoch 64 Batch 60/62] avg loss 0.00383496, throughput 3.20453K wps
Begin Testing...
[Epoch 64] train avg loss 0.00408099, dev acc 0.8496, dev avg loss 0.339674, throughput 3.23329K wps
Observed Improvement.
Begin Testing...
[Epoch 65 Batch 30/62] avg loss 0.00413762, throughput 3.29506K wps
[Epoch 65 Batch 60/62] avg loss 0.00399047, throughput 3.17466K wps
Begin Testing...
[Epoch 65] train avg loss 0.0041188, dev acc 0.8348, dev avg loss 0.341747, throughput 3.23981K wps
[Epoch 66 Batch 30/62] avg loss 0.00369099, throughput 3.23783K wps
[Epoch 66 Batch 60/62] avg loss 0.00409561, throughput 3.14773K wps
Begin Testing...
[Epoch 66] train avg loss 0.00392628, dev acc 0.8407, dev avg loss 0.336997, throughput 3.19899K wps
[Epoch 67 Batch 30/62] avg loss 0.00365632, throughput 3.24741K wps
[Epoch 67 Batch 60/62] avg loss 0.00393873, throughput 3.16828K wps
Begin Testing...
[Epoch 67] train avg loss 0.00381508, dev acc 0.8466, dev avg loss 0.337497, throughput 3.21602K wps
[Epoch 68 Batch 30/62] avg loss 0.0036876, throughput 3.23941K wps
[Epoch 68 Batch 60/62] avg loss 0.00392383, throughput 3.20405K wps
Begin Testing...
[Epoch 68] train avg loss 0.00384256, dev acc 0.8496, dev avg loss 0.336212, throughput 3.22654K wps
Observed Improvement.
Begin Testing...
[Epoch 69 Batch 30/62] avg loss 0.00366884, throughput 3.23924K wps
[Epoch 69 Batch 60/62] avg loss 0.00373269, throughput 3.2121K wps
Begin Testing...
[Epoch 69] train avg loss 0.00379059, dev acc 0.8407, dev avg loss 0.337869, throughput 3.22391K wps
[Epoch 70 Batch 30/62] avg loss 0.00346667, throughput 3.27383K wps
[Epoch 70 Batch 60/62] avg loss 0.003807, throughput 3.18637K wps
Begin Testing...
[Epoch 70] train avg loss 0.00373967, dev acc 0.8348, dev avg loss 0.33963, throughput 3.23817K wps
[Epoch 71 Batch 30/62] avg loss 0.00347218, throughput 3.29084K wps
[Epoch 71 Batch 60/62] avg loss 0.00359777, throughput 3.17764K wps
Begin Testing...
[Epoch 71] train avg loss 0.00359787, dev acc 0.8378, dev avg loss 0.336842, throughput 3.23918K wps
[Epoch 72 Batch 30/62] avg loss 0.00329293, throughput 3.24709K wps
[Epoch 72 Batch 60/62] avg loss 0.00348338, throughput 3.17324K wps
Begin Testing...
[Epoch 72] train avg loss 0.00346843, dev acc 0.8319, dev avg loss 0.341734, throughput 3.21847K wps
[Epoch 73 Batch 30/62] avg loss 0.00333322, throughput 3.25217K wps
[Epoch 73 Batch 60/62] avg loss 0.00339116, throughput 3.21355K wps
Begin Testing...
[Epoch 73] train avg loss 0.00341493, dev acc 0.8437, dev avg loss 0.335365, throughput 3.23776K wps
[Epoch 74 Batch 30/62] avg loss 0.00336357, throughput 3.26212K wps
[Epoch 74 Batch 60/62] avg loss 0.00322253, throughput 3.20374K wps
Begin Testing...
[Epoch 74] train avg loss 0.00329801, dev acc 0.8437, dev avg loss 0.334012, throughput 3.23812K wps
[Epoch 75 Batch 30/62] avg loss 0.00335597, throughput 3.26151K wps
[Epoch 75 Batch 60/62] avg loss 0.00342462, throughput 3.19669K wps
Begin Testing...
[Epoch 75] train avg loss 0.00341396, dev acc 0.8378, dev avg loss 0.335835, throughput 3.23686K wps
[Epoch 76 Batch 30/62] avg loss 0.00312866, throughput 3.25047K wps
[Epoch 76 Batch 60/62] avg loss 0.00318736, throughput 3.19479K wps
Begin Testing...
[Epoch 76] train avg loss 0.00319547, dev acc 0.8230, dev avg loss 0.344446, throughput 3.22848K wps
[Epoch 77 Batch 30/62] avg loss 0.00332871, throughput 3.26542K wps
[Epoch 77 Batch 60/62] avg loss 0.00309796, throughput 3.19186K wps
Begin Testing...
[Epoch 77] train avg loss 0.00328664, dev acc 0.8171, dev avg loss 0.346438, throughput 3.23623K wps
[Epoch 78 Batch 30/62] avg loss 0.00307982, throughput 3.28206K wps
[Epoch 78 Batch 60/62] avg loss 0.00306263, throughput 3.17156K wps
Begin Testing...
[Epoch 78] train avg loss 0.00311299, dev acc 0.8437, dev avg loss 0.332623, throughput 3.23047K wps
[Epoch 79 Batch 30/62] avg loss 0.00310181, throughput 3.25278K wps
[Epoch 79 Batch 60/62] avg loss 0.0029528, throughput 3.15796K wps
Begin Testing...
[Epoch 79] train avg loss 0.00306254, dev acc 0.8407, dev avg loss 0.334645, throughput 3.21258K wps
[Epoch 80 Batch 30/62] avg loss 0.00294142, throughput 3.2724K wps
[Epoch 80 Batch 60/62] avg loss 0.00290534, throughput 3.18644K wps
Begin Testing...
[Epoch 80] train avg loss 0.00307193, dev acc 0.8289, dev avg loss 0.343946, throughput 3.23437K wps
[Epoch 81 Batch 30/62] avg loss 0.00300165, throughput 3.25357K wps
[Epoch 81 Batch 60/62] avg loss 0.00290829, throughput 3.17962K wps
Begin Testing...
[Epoch 81] train avg loss 0.0029807, dev acc 0.8407, dev avg loss 0.335382, throughput 3.22429K wps
[Epoch 82 Batch 30/62] avg loss 0.00292196, throughput 3.25179K wps
[Epoch 82 Batch 60/62] avg loss 0.00280803, throughput 3.19429K wps
Begin Testing...
[Epoch 82] train avg loss 0.00289172, dev acc 0.8378, dev avg loss 0.334094, throughput 3.23034K wps
[Epoch 83 Batch 30/62] avg loss 0.00294166, throughput 3.27051K wps
[Epoch 83 Batch 60/62] avg loss 0.00282727, throughput 3.17797K wps
Begin Testing...
[Epoch 83] train avg loss 0.00289269, dev acc 0.8378, dev avg loss 0.335967, throughput 3.23135K wps
[Epoch 84 Batch 30/62] avg loss 0.00266406, throughput 3.28433K wps
[Epoch 84 Batch 60/62] avg loss 0.00284846, throughput 3.16872K wps
Begin Testing...
[Epoch 84] train avg loss 0.00284142, dev acc 0.8260, dev avg loss 0.343972, throughput 3.23136K wps
[Epoch 85 Batch 30/62] avg loss 0.00258631, throughput 3.26449K wps
[Epoch 85 Batch 60/62] avg loss 0.00282381, throughput 3.19982K wps
Begin Testing...
[Epoch 85] train avg loss 0.00275216, dev acc 0.8289, dev avg loss 0.342097, throughput 3.24066K wps
[Epoch 86 Batch 30/62] avg loss 0.00270572, throughput 3.27561K wps
[Epoch 86 Batch 60/62] avg loss 0.00279859, throughput 3.16871K wps
Begin Testing...
[Epoch 86] train avg loss 0.00275154, dev acc 0.8407, dev avg loss 0.333482, throughput 3.22978K wps
[Epoch 87 Batch 30/62] avg loss 0.0026375, throughput 3.307K wps
[Epoch 87 Batch 60/62] avg loss 0.00252509, throughput 3.16593K wps
Begin Testing...
[Epoch 87] train avg loss 0.0026071, dev acc 0.8378, dev avg loss 0.334414, throughput 3.24081K wps
[Epoch 88 Batch 30/62] avg loss 0.00246377, throughput 3.24443K wps
[Epoch 88 Batch 60/62] avg loss 0.00266045, throughput 3.19616K wps
Begin Testing...
[Epoch 88] train avg loss 0.00261943, dev acc 0.8407, dev avg loss 0.331402, throughput 3.2284K wps
[Epoch 89 Batch 30/62] avg loss 0.00248729, throughput 3.27773K wps
[Epoch 89 Batch 60/62] avg loss 0.00253263, throughput 3.17293K wps
Begin Testing...
[Epoch 89] train avg loss 0.00254793, dev acc 0.8407, dev avg loss 0.331615, throughput 3.23102K wps
[Epoch 90 Batch 30/62] avg loss 0.00241558, throughput 3.23884K wps
[Epoch 90 Batch 60/62] avg loss 0.00256366, throughput 3.1792K wps
Begin Testing...
[Epoch 90] train avg loss 0.0025617, dev acc 0.8348, dev avg loss 0.340105, throughput 3.21699K wps
[Epoch 91 Batch 30/62] avg loss 0.00246904, throughput 3.28799K wps
[Epoch 91 Batch 60/62] avg loss 0.00244432, throughput 3.16104K wps
Begin Testing...
[Epoch 91] train avg loss 0.00248673, dev acc 0.8260, dev avg loss 0.341737, throughput 3.22949K wps
[Epoch 92 Batch 30/62] avg loss 0.00232527, throughput 3.26723K wps
[Epoch 92 Batch 60/62] avg loss 0.00251019, throughput 3.16868K wps
Begin Testing...
[Epoch 92] train avg loss 0.00247087, dev acc 0.8378, dev avg loss 0.338125, throughput 3.22556K wps
[Epoch 93 Batch 30/62] avg loss 0.00230413, throughput 3.26285K wps
[Epoch 93 Batch 60/62] avg loss 0.00231499, throughput 3.19256K wps
Begin Testing...
[Epoch 93] train avg loss 0.00233786, dev acc 0.8437, dev avg loss 0.335256, throughput 3.23333K wps
[Epoch 94 Batch 30/62] avg loss 0.00244875, throughput 3.27296K wps
[Epoch 94 Batch 60/62] avg loss 0.00227085, throughput 3.19848K wps
Begin Testing...
[Epoch 94] train avg loss 0.00239145, dev acc 0.8230, dev avg loss 0.348399, throughput 3.24253K wps
[Epoch 95 Batch 30/62] avg loss 0.00215796, throughput 3.27344K wps
[Epoch 95 Batch 60/62] avg loss 0.00226651, throughput 3.16392K wps
Begin Testing...
[Epoch 95] train avg loss 0.00225415, dev acc 0.8378, dev avg loss 0.339281, throughput 3.22368K wps
[Epoch 96 Batch 30/62] avg loss 0.00220786, throughput 3.27297K wps
[Epoch 96 Batch 60/62] avg loss 0.00219197, throughput 3.21745K wps
Begin Testing...
[Epoch 96] train avg loss 0.00220836, dev acc 0.8407, dev avg loss 0.335764, throughput 3.25121K wps
[Epoch 97 Batch 30/62] avg loss 0.0021009, throughput 3.25738K wps
[Epoch 97 Batch 60/62] avg loss 0.00229194, throughput 3.16831K wps
Begin Testing...
[Epoch 97] train avg loss 0.00225763, dev acc 0.8348, dev avg loss 0.340535, throughput 3.21833K wps
[Epoch 98 Batch 30/62] avg loss 0.00224455, throughput 3.21859K wps
[Epoch 98 Batch 60/62] avg loss 0.00214095, throughput 3.16433K wps
Begin Testing...
[Epoch 98] train avg loss 0.00219527, dev acc 0.8407, dev avg loss 0.337647, throughput 3.19811K wps
[Epoch 99 Batch 30/62] avg loss 0.00205773, throughput 3.25935K wps
[Epoch 99 Batch 60/62] avg loss 0.00218426, throughput 3.22355K wps
Begin Testing...
[Epoch 99] train avg loss 0.00217509, dev acc 0.8437, dev avg loss 0.334212, throughput 3.24709K wps
[Epoch 100 Batch 30/62] avg loss 0.00222236, throughput 3.2565K wps
[Epoch 100 Batch 60/62] avg loss 0.00208779, throughput 3.1779K wps
Begin Testing...
[Epoch 100] train avg loss 0.00216885, dev acc 0.8378, dev avg loss 0.340576, throughput 3.22519K wps
[Epoch 101 Batch 30/62] avg loss 0.00200013, throughput 3.24729K wps
[Epoch 101 Batch 60/62] avg loss 0.00206652, throughput 3.21932K wps
Begin Testing...
[Epoch 101] train avg loss 0.0020458, dev acc 0.8466, dev avg loss 0.335835, throughput 3.2385K wps
[Epoch 102 Batch 30/62] avg loss 0.00201626, throughput 3.25287K wps
[Epoch 102 Batch 60/62] avg loss 0.00201218, throughput 3.18214K wps
Begin Testing...
[Epoch 102] train avg loss 0.0020336, dev acc 0.8407, dev avg loss 0.329873, throughput 3.22539K wps
[Epoch 103 Batch 30/62] avg loss 0.00197718, throughput 3.29008K wps
[Epoch 103 Batch 60/62] avg loss 0.00199412, throughput 3.17178K wps
Begin Testing...
[Epoch 103] train avg loss 0.00202932, dev acc 0.8407, dev avg loss 0.334737, throughput 3.23569K wps
[Epoch 104 Batch 30/62] avg loss 0.00194971, throughput 3.23944K wps
[Epoch 104 Batch 60/62] avg loss 0.00191562, throughput 3.15903K wps
Begin Testing...
[Epoch 104] train avg loss 0.00199383, dev acc 0.8437, dev avg loss 0.330664, throughput 3.20516K wps
[Epoch 105 Batch 30/62] avg loss 0.00203628, throughput 3.24507K wps
[Epoch 105 Batch 60/62] avg loss 0.00192819, throughput 3.15403K wps
Begin Testing...
[Epoch 105] train avg loss 0.00197733, dev acc 0.8437, dev avg loss 0.337417, throughput 3.20445K wps
[Epoch 106 Batch 30/62] avg loss 0.00208789, throughput 3.24632K wps
[Epoch 106 Batch 60/62] avg loss 0.00177032, throughput 3.1795K wps
Begin Testing...
[Epoch 106] train avg loss 0.00192688, dev acc 0.8319, dev avg loss 0.343007, throughput 3.22117K wps
[Epoch 107 Batch 30/62] avg loss 0.00181306, throughput 3.29379K wps
[Epoch 107 Batch 60/62] avg loss 0.00181528, throughput 3.16394K wps
Begin Testing...
[Epoch 107] train avg loss 0.00183095, dev acc 0.8437, dev avg loss 0.330258, throughput 3.23415K wps
[Epoch 108 Batch 30/62] avg loss 0.00176861, throughput 3.27157K wps
[Epoch 108 Batch 60/62] avg loss 0.00181457, throughput 3.21654K wps
Begin Testing...
[Epoch 108] train avg loss 0.00179262, dev acc 0.8407, dev avg loss 0.337033, throughput 3.24919K wps
[Epoch 109 Batch 30/62] avg loss 0.00169636, throughput 3.26788K wps
[Epoch 109 Batch 60/62] avg loss 0.00183696, throughput 3.17074K wps
Begin Testing...
[Epoch 109] train avg loss 0.00178534, dev acc 0.8437, dev avg loss 0.338827, throughput 3.22668K wps
[Epoch 110 Batch 30/62] avg loss 0.00166332, throughput 3.2405K wps
[Epoch 110 Batch 60/62] avg loss 0.00185661, throughput 3.22079K wps
Begin Testing...
[Epoch 110] train avg loss 0.0017643, dev acc 0.8319, dev avg loss 0.343077, throughput 3.23645K wps
[Epoch 111 Batch 30/62] avg loss 0.00162356, throughput 3.2612K wps
[Epoch 111 Batch 60/62] avg loss 0.00179038, throughput 3.21577K wps
Begin Testing...
[Epoch 111] train avg loss 0.0017374, dev acc 0.8437, dev avg loss 0.332604, throughput 3.245K wps
[Epoch 112 Batch 30/62] avg loss 0.00170272, throughput 3.27494K wps
[Epoch 112 Batch 60/62] avg loss 0.00171869, throughput 3.17332K wps
Begin Testing...
[Epoch 112] train avg loss 0.00171709, dev acc 0.8348, dev avg loss 0.342721, throughput 3.22965K wps
[Epoch 113 Batch 30/62] avg loss 0.0017253, throughput 3.2705K wps
[Epoch 113 Batch 60/62] avg loss 0.00160557, throughput 3.20464K wps
Begin Testing...
[Epoch 113] train avg loss 0.00167975, dev acc 0.8407, dev avg loss 0.33623, throughput 3.24357K wps
[Epoch 114 Batch 30/62] avg loss 0.00176034, throughput 3.2666K wps
[Epoch 114 Batch 60/62] avg loss 0.00164217, throughput 3.21337K wps
Begin Testing...
[Epoch 114] train avg loss 0.00175053, dev acc 0.8407, dev avg loss 0.333286, throughput 3.24529K wps
[Epoch 115 Batch 30/62] avg loss 0.00163301, throughput 3.25605K wps
[Epoch 115 Batch 60/62] avg loss 0.00175662, throughput 3.15835K wps
Begin Testing...
[Epoch 115] train avg loss 0.00170449, dev acc 0.8437, dev avg loss 0.339154, throughput 3.21226K wps
[Epoch 116 Batch 30/62] avg loss 0.00158431, throughput 3.24991K wps
[Epoch 116 Batch 60/62] avg loss 0.00170231, throughput 3.17238K wps
Begin Testing...
[Epoch 116] train avg loss 0.0016769, dev acc 0.8407, dev avg loss 0.336739, throughput 3.21869K wps
[Epoch 117 Batch 30/62] avg loss 0.00157317, throughput 3.26526K wps
[Epoch 117 Batch 60/62] avg loss 0.00160248, throughput 3.1935K wps
Begin Testing...
[Epoch 117] train avg loss 0.00162136, dev acc 0.8437, dev avg loss 0.333797, throughput 3.23618K wps
[Epoch 118 Batch 30/62] avg loss 0.00152255, throughput 3.25443K wps
[Epoch 118 Batch 60/62] avg loss 0.00164494, throughput 3.17347K wps
Begin Testing...
[Epoch 118] train avg loss 0.00158516, dev acc 0.8378, dev avg loss 0.342297, throughput 3.21994K wps
[Epoch 119 Batch 30/62] avg loss 0.00162261, throughput 3.24269K wps
[Epoch 119 Batch 60/62] avg loss 0.00149672, throughput 3.20288K wps
Begin Testing...
[Epoch 119] train avg loss 0.00157215, dev acc 0.8407, dev avg loss 0.336706, throughput 3.22871K wps
[Epoch 120 Batch 30/62] avg loss 0.00148782, throughput 3.27847K wps
[Epoch 120 Batch 60/62] avg loss 0.00153393, throughput 3.2021K wps
Begin Testing...
[Epoch 120] train avg loss 0.00155418, dev acc 0.8437, dev avg loss 0.337068, throughput 3.24834K wps
[Epoch 121 Batch 30/62] avg loss 0.00156779, throughput 3.28386K wps
[Epoch 121 Batch 60/62] avg loss 0.00143571, throughput 3.19073K wps
Begin Testing...
[Epoch 121] train avg loss 0.00150509, dev acc 0.8348, dev avg loss 0.341457, throughput 3.24424K wps
[Epoch 122 Batch 30/62] avg loss 0.00143882, throughput 3.27764K wps
[Epoch 122 Batch 60/62] avg loss 0.00145883, throughput 3.17116K wps
Begin Testing...
[Epoch 122] train avg loss 0.00144454, dev acc 0.8466, dev avg loss 0.336226, throughput 3.22916K wps
[Epoch 123 Batch 30/62] avg loss 0.00157338, throughput 3.24978K wps
[Epoch 123 Batch 60/62] avg loss 0.00140881, throughput 3.163K wps
Begin Testing...
[Epoch 123] train avg loss 0.00151275, dev acc 0.8437, dev avg loss 0.334196, throughput 3.21264K wps
[Epoch 124 Batch 30/62] avg loss 0.00144781, throughput 3.24635K wps
[Epoch 124 Batch 60/62] avg loss 0.00145502, throughput 3.17621K wps
Begin Testing...
[Epoch 124] train avg loss 0.00145199, dev acc 0.8319, dev avg loss 0.348058, throughput 3.21918K wps
[Epoch 125 Batch 30/62] avg loss 0.0014865, throughput 3.28061K wps
[Epoch 125 Batch 60/62] avg loss 0.00137697, throughput 3.17949K wps
Begin Testing...
[Epoch 125] train avg loss 0.00142697, dev acc 0.8319, dev avg loss 0.346367, throughput 3.23469K wps
[Epoch 126 Batch 30/62] avg loss 0.00140222, throughput 3.24822K wps
[Epoch 126 Batch 60/62] avg loss 0.00155198, throughput 3.15319K wps
Begin Testing...
[Epoch 126] train avg loss 0.00147629, dev acc 0.8348, dev avg loss 0.344694, throughput 3.2061K wps
[Epoch 127 Batch 30/62] avg loss 0.00135469, throughput 3.24731K wps
[Epoch 127 Batch 60/62] avg loss 0.00134232, throughput 3.19731K wps
Begin Testing...
[Epoch 127] train avg loss 0.00136658, dev acc 0.8348, dev avg loss 0.347752, throughput 3.22982K wps
[Epoch 128 Batch 30/62] avg loss 0.00143818, throughput 3.30727K wps
[Epoch 128 Batch 60/62] avg loss 0.00141247, throughput 3.1619K wps
Begin Testing...
[Epoch 128] train avg loss 0.00145857, dev acc 0.8348, dev avg loss 0.346187, throughput 3.23885K wps
[Epoch 129 Batch 30/62] avg loss 0.00122337, throughput 3.26008K wps
[Epoch 129 Batch 60/62] avg loss 0.00135472, throughput 3.21364K wps
Begin Testing...
[Epoch 129] train avg loss 0.00130349, dev acc 0.8437, dev avg loss 0.337015, throughput 3.24253K wps
[Epoch 130 Batch 30/62] avg loss 0.00124791, throughput 3.26603K wps
[Epoch 130 Batch 60/62] avg loss 0.00135792, throughput 3.19474K wps
Begin Testing...
[Epoch 130] train avg loss 0.00131777, dev acc 0.8437, dev avg loss 0.341875, throughput 3.23844K wps
[Epoch 131 Batch 30/62] avg loss 0.00125031, throughput 3.2796K wps
[Epoch 131 Batch 60/62] avg loss 0.0014063, throughput 3.16123K wps
Begin Testing...
[Epoch 131] train avg loss 0.00136679, dev acc 0.8466, dev avg loss 0.337654, throughput 3.22521K wps
[Epoch 132 Batch 30/62] avg loss 0.00132543, throughput 3.25304K wps
[Epoch 132 Batch 60/62] avg loss 0.00121871, throughput 3.21894K wps
Begin Testing...
[Epoch 132] train avg loss 0.00133596, dev acc 0.8319, dev avg loss 0.364336, throughput 3.24186K wps
[Epoch 133 Batch 30/62] avg loss 0.00124318, throughput 3.27192K wps
[Epoch 133 Batch 60/62] avg loss 0.00124035, throughput 3.16662K wps
Begin Testing...
[Epoch 133] train avg loss 0.00124797, dev acc 0.8319, dev avg loss 0.343185, throughput 3.22507K wps
[Epoch 134 Batch 30/62] avg loss 0.00125222, throughput 3.28326K wps
[Epoch 134 Batch 60/62] avg loss 0.00113669, throughput 3.20099K wps
Begin Testing...
[Epoch 134] train avg loss 0.00120127, dev acc 0.8407, dev avg loss 0.342135, throughput 3.24824K wps
[Epoch 135 Batch 30/62] avg loss 0.00127097, throughput 3.26512K wps
[Epoch 135 Batch 60/62] avg loss 0.00113152, throughput 3.20951K wps
Begin Testing...
[Epoch 135] train avg loss 0.0012262, dev acc 0.8348, dev avg loss 0.348841, throughput 3.24264K wps
[Epoch 136 Batch 30/62] avg loss 0.0012597, throughput 3.26568K wps
[Epoch 136 Batch 60/62] avg loss 0.0011899, throughput 3.17568K wps
Begin Testing...
[Epoch 136] train avg loss 0.0012461, dev acc 0.8378, dev avg loss 0.344235, throughput 3.22735K wps
[Epoch 137 Batch 30/62] avg loss 0.00119556, throughput 3.23427K wps
[Epoch 137 Batch 60/62] avg loss 0.00121821, throughput 3.20222K wps
Begin Testing...
[Epoch 137] train avg loss 0.00122662, dev acc 0.8407, dev avg loss 0.338953, throughput 3.22414K wps
[Epoch 138 Batch 30/62] avg loss 0.00124042, throughput 3.27694K wps
[Epoch 138 Batch 60/62] avg loss 0.00117117, throughput 3.19219K wps
Begin Testing...
[Epoch 138] train avg loss 0.00120274, dev acc 0.8378, dev avg loss 0.345147, throughput 3.24146K wps
[Epoch 139 Batch 30/62] avg loss 0.00114519, throughput 3.30481K wps
[Epoch 139 Batch 60/62] avg loss 0.00113961, throughput 3.17779K wps
Begin Testing...
[Epoch 139] train avg loss 0.00118286, dev acc 0.8466, dev avg loss 0.338523, throughput 3.24786K wps
[Epoch 140 Batch 30/62] avg loss 0.00117526, throughput 3.29276K wps
[Epoch 140 Batch 60/62] avg loss 0.00104273, throughput 3.17681K wps
Begin Testing...
[Epoch 140] train avg loss 0.00112855, dev acc 0.8407, dev avg loss 0.342774, throughput 3.23936K wps
[Epoch 141 Batch 30/62] avg loss 0.00120422, throughput 3.27493K wps
[Epoch 141 Batch 60/62] avg loss 0.00105296, throughput 3.21824K wps
Begin Testing...
[Epoch 141] train avg loss 0.00114446, dev acc 0.8407, dev avg loss 0.346236, throughput 3.25169K wps
[Epoch 142 Batch 30/62] avg loss 0.00112681, throughput 3.28331K wps
[Epoch 142 Batch 60/62] avg loss 0.0011186, throughput 3.21326K wps
Begin Testing...
[Epoch 142] train avg loss 0.0011292, dev acc 0.8378, dev avg loss 0.350427, throughput 3.25344K wps
[Epoch 143 Batch 30/62] avg loss 0.00112756, throughput 3.25941K wps
[Epoch 143 Batch 60/62] avg loss 0.00112317, throughput 3.21861K wps
Begin Testing...
[Epoch 143] train avg loss 0.00113285, dev acc 0.8407, dev avg loss 0.34457, throughput 3.24409K wps
[Epoch 144 Batch 30/62] avg loss 0.00113587, throughput 3.26094K wps
[Epoch 144 Batch 60/62] avg loss 0.00111386, throughput 3.17406K wps
Begin Testing...
[Epoch 144] train avg loss 0.00113701, dev acc 0.8319, dev avg loss 0.359557, throughput 3.22365K wps
[Epoch 145 Batch 30/62] avg loss 0.00112944, throughput 3.25962K wps
[Epoch 145 Batch 60/62] avg loss 0.00115666, throughput 3.20054K wps
Begin Testing...
[Epoch 145] train avg loss 0.00114793, dev acc 0.8407, dev avg loss 0.349371, throughput 3.23612K wps
[Epoch 146 Batch 30/62] avg loss 0.00106856, throughput 3.25776K wps
[Epoch 146 Batch 60/62] avg loss 0.00104232, throughput 3.15083K wps
Begin Testing...
[Epoch 146] train avg loss 0.00110684, dev acc 0.8378, dev avg loss 0.370516, throughput 3.20924K wps
[Epoch 147 Batch 30/62] avg loss 0.0010378, throughput 3.24787K wps
[Epoch 147 Batch 60/62] avg loss 0.000995094, throughput 3.15605K wps
Begin Testing...
[Epoch 147] train avg loss 0.00105761, dev acc 0.8289, dev avg loss 0.360768, throughput 3.2074K wps
[Epoch 148 Batch 30/62] avg loss 0.00101759, throughput 3.25262K wps
[Epoch 148 Batch 60/62] avg loss 0.00101846, throughput 3.15192K wps
Begin Testing...
[Epoch 148] train avg loss 0.00104131, dev acc 0.8407, dev avg loss 0.345502, throughput 3.2081K wps
[Epoch 149 Batch 30/62] avg loss 0.000982734, throughput 3.2333K wps
[Epoch 149 Batch 60/62] avg loss 0.00106564, throughput 3.16507K wps
Begin Testing...
[Epoch 149] train avg loss 0.00104783, dev acc 0.8407, dev avg loss 0.346809, throughput 3.20545K wps
[Epoch 150 Batch 30/62] avg loss 0.00098645, throughput 3.26005K wps
[Epoch 150 Batch 60/62] avg loss 0.000982852, throughput 3.19884K wps
Begin Testing...
[Epoch 150] train avg loss 0.00100095, dev acc 0.8378, dev avg loss 0.347883, throughput 3.23408K wps
[Epoch 151 Batch 30/62] avg loss 0.00107916, throughput 3.2759K wps
[Epoch 151 Batch 60/62] avg loss 0.00100603, throughput 3.16552K wps
Begin Testing...
[Epoch 151] train avg loss 0.00106871, dev acc 0.8378, dev avg loss 0.372396, throughput 3.22515K wps
[Epoch 152 Batch 30/62] avg loss 0.00099751, throughput 3.25897K wps
[Epoch 152 Batch 60/62] avg loss 0.00104212, throughput 3.19233K wps
Begin Testing...
[Epoch 152] train avg loss 0.0010348, dev acc 0.8378, dev avg loss 0.347613, throughput 3.23405K wps
[Epoch 153 Batch 30/62] avg loss 0.000997357, throughput 3.27231K wps
[Epoch 153 Batch 60/62] avg loss 0.000919562, throughput 3.16948K wps
Begin Testing...
[Epoch 153] train avg loss 0.000967942, dev acc 0.8348, dev avg loss 0.350265, throughput 3.22553K wps
[Epoch 154 Batch 30/62] avg loss 0.00102403, throughput 3.28619K wps
[Epoch 154 Batch 60/62] avg loss 0.000975753, throughput 3.19695K wps
Begin Testing...
[Epoch 154] train avg loss 0.00100321, dev acc 0.8407, dev avg loss 0.353692, throughput 3.24622K wps
[Epoch 155 Batch 30/62] avg loss 0.0009009, throughput 3.26379K wps
[Epoch 155 Batch 60/62] avg loss 0.000954053, throughput 3.16295K wps
Begin Testing...
[Epoch 155] train avg loss 0.000931329, dev acc 0.8378, dev avg loss 0.352823, throughput 3.21882K wps
[Epoch 156 Batch 30/62] avg loss 0.000955922, throughput 3.25195K wps
[Epoch 156 Batch 60/62] avg loss 0.000906597, throughput 3.21128K wps
Begin Testing...
[Epoch 156] train avg loss 0.000937203, dev acc 0.8378, dev avg loss 0.350373, throughput 3.23785K wps
[Epoch 157 Batch 30/62] avg loss 0.000917657, throughput 3.25507K wps
[Epoch 157 Batch 60/62] avg loss 0.000939298, throughput 3.17759K wps
Begin Testing...
[Epoch 157] train avg loss 0.000934057, dev acc 0.8407, dev avg loss 0.352004, throughput 3.22427K wps
[Epoch 158 Batch 30/62] avg loss 0.000849709, throughput 3.23144K wps
[Epoch 158 Batch 60/62] avg loss 0.000989962, throughput 3.19549K wps
Begin Testing...
[Epoch 158] train avg loss 0.000928799, dev acc 0.8348, dev avg loss 0.35603, throughput 3.2218K wps
[Epoch 159 Batch 30/62] avg loss 0.000910003, throughput 3.26796K wps
[Epoch 159 Batch 60/62] avg loss 0.00096392, throughput 3.16908K wps
Begin Testing...
[Epoch 159] train avg loss 0.000957697, dev acc 0.8407, dev avg loss 0.349764, throughput 3.22362K wps
[Epoch 160 Batch 30/62] avg loss 0.000878535, throughput 3.27129K wps
[Epoch 160 Batch 60/62] avg loss 0.00091398, throughput 3.20207K wps
Begin Testing...
[Epoch 160] train avg loss 0.000899617, dev acc 0.8378, dev avg loss 0.354335, throughput 3.24241K wps
[Epoch 161 Batch 30/62] avg loss 0.000875912, throughput 3.27372K wps
[Epoch 161 Batch 60/62] avg loss 0.000974, throughput 3.17921K wps
Begin Testing...
[Epoch 161] train avg loss 0.000943255, dev acc 0.8407, dev avg loss 0.349256, throughput 3.23393K wps
[Epoch 162 Batch 30/62] avg loss 0.000886561, throughput 3.29097K wps
[Epoch 162 Batch 60/62] avg loss 0.000900683, throughput 3.16594K wps
Begin Testing...
[Epoch 162] train avg loss 0.000894115, dev acc 0.8378, dev avg loss 0.355361, throughput 3.23299K wps
[Epoch 163 Batch 30/62] avg loss 0.000813898, throughput 3.25933K wps
[Epoch 163 Batch 60/62] avg loss 0.000889921, throughput 3.15094K wps
Begin Testing...
[Epoch 163] train avg loss 0.000872005, dev acc 0.8437, dev avg loss 0.352695, throughput 3.21018K wps
[Epoch 164 Batch 30/62] avg loss 0.000780948, throughput 3.25127K wps
[Epoch 164 Batch 60/62] avg loss 0.000936775, throughput 3.2142K wps
Begin Testing...
[Epoch 164] train avg loss 0.000860532, dev acc 0.8437, dev avg loss 0.354879, throughput 3.23866K wps
[Epoch 165 Batch 30/62] avg loss 0.000852128, throughput 3.27639K wps
[Epoch 165 Batch 60/62] avg loss 0.000864867, throughput 3.21686K wps
Begin Testing...
[Epoch 165] train avg loss 0.000888268, dev acc 0.8378, dev avg loss 0.357916, throughput 3.25224K wps
[Epoch 166 Batch 30/62] avg loss 0.000919558, throughput 3.28178K wps
[Epoch 166 Batch 60/62] avg loss 0.000884139, throughput 3.21287K wps
Begin Testing...
[Epoch 166] train avg loss 0.000916988, dev acc 0.8378, dev avg loss 0.355558, throughput 3.25326K wps
[Epoch 167 Batch 30/62] avg loss 0.000887415, throughput 3.27637K wps
[Epoch 167 Batch 60/62] avg loss 0.000884068, throughput 3.16782K wps
Begin Testing...
[Epoch 167] train avg loss 0.000902859, dev acc 0.8437, dev avg loss 0.352743, throughput 3.22943K wps
[Epoch 168 Batch 30/62] avg loss 0.000808008, throughput 3.27472K wps
[Epoch 168 Batch 60/62] avg loss 0.000808053, throughput 3.19123K wps
Begin Testing...
[Epoch 168] train avg loss 0.000812848, dev acc 0.8348, dev avg loss 0.357499, throughput 3.23916K wps
[Epoch 169 Batch 30/62] avg loss 0.000818256, throughput 3.25652K wps
[Epoch 169 Batch 60/62] avg loss 0.000858767, throughput 3.20338K wps
Begin Testing...
[Epoch 169] train avg loss 0.00085135, dev acc 0.8348, dev avg loss 0.358376, throughput 3.23895K wps
[Epoch 170 Batch 30/62] avg loss 0.000803978, throughput 3.28609K wps
[Epoch 170 Batch 60/62] avg loss 0.000782684, throughput 3.19682K wps
Begin Testing...
[Epoch 170] train avg loss 0.00080556, dev acc 0.8378, dev avg loss 0.35893, throughput 3.24833K wps
[Epoch 171 Batch 30/62] avg loss 0.000808131, throughput 3.28078K wps
[Epoch 171 Batch 60/62] avg loss 0.000761504, throughput 3.16339K wps
Begin Testing...
[Epoch 171] train avg loss 0.000798454, dev acc 0.8378, dev avg loss 0.357932, throughput 3.22615K wps
[Epoch 172 Batch 30/62] avg loss 0.000719278, throughput 3.26043K wps
[Epoch 172 Batch 60/62] avg loss 0.000844641, throughput 3.20574K wps
Begin Testing...
[Epoch 172] train avg loss 0.000791651, dev acc 0.8466, dev avg loss 0.353895, throughput 3.24066K wps
[Epoch 173 Batch 30/62] avg loss 0.000864926, throughput 3.27846K wps
[Epoch 173 Batch 60/62] avg loss 0.000861003, throughput 3.22078K wps
Begin Testing...
[Epoch 173] train avg loss 0.00092173, dev acc 0.8378, dev avg loss 0.378665, throughput 3.25685K wps
[Epoch 174 Batch 30/62] avg loss 0.000792932, throughput 3.28375K wps
[Epoch 174 Batch 60/62] avg loss 0.000796158, throughput 3.21185K wps
Begin Testing...
[Epoch 174] train avg loss 0.000793682, dev acc 0.8378, dev avg loss 0.357258, throughput 3.25332K wps
[Epoch 175 Batch 30/62] avg loss 0.000734204, throughput 3.26217K wps
[Epoch 175 Batch 60/62] avg loss 0.000798817, throughput 3.16164K wps
Begin Testing...
[Epoch 175] train avg loss 0.000777189, dev acc 0.8348, dev avg loss 0.361194, throughput 3.21769K wps
[Epoch 176 Batch 30/62] avg loss 0.000758205, throughput 3.26917K wps
[Epoch 176 Batch 60/62] avg loss 0.000764476, throughput 3.21311K wps
Begin Testing...
[Epoch 176] train avg loss 0.000760957, dev acc 0.8378, dev avg loss 0.366214, throughput 3.24661K wps
[Epoch 177 Batch 30/62] avg loss 0.000798256, throughput 3.26366K wps
[Epoch 177 Batch 60/62] avg loss 0.00066789, throughput 3.21872K wps
Begin Testing...
[Epoch 177] train avg loss 0.000738743, dev acc 0.8378, dev avg loss 0.359243, throughput 3.24754K wps
[Epoch 178 Batch 30/62] avg loss 0.000755463, throughput 3.27682K wps
[Epoch 178 Batch 60/62] avg loss 0.000737056, throughput 3.20558K wps
Begin Testing...
[Epoch 178] train avg loss 0.000755072, dev acc 0.8407, dev avg loss 0.374906, throughput 3.24821K wps
[Epoch 179 Batch 30/62] avg loss 0.000707299, throughput 3.27243K wps
[Epoch 179 Batch 60/62] avg loss 0.000733773, throughput 3.16598K wps
Begin Testing...
[Epoch 179] train avg loss 0.000720844, dev acc 0.8378, dev avg loss 0.356908, throughput 3.22587K wps
[Epoch 180 Batch 30/62] avg loss 0.000704235, throughput 3.31142K wps
[Epoch 180 Batch 60/62] avg loss 0.000694095, throughput 3.17532K wps
Begin Testing...
[Epoch 180] train avg loss 0.00071054, dev acc 0.8378, dev avg loss 0.364451, throughput 3.24745K wps
[Epoch 181 Batch 30/62] avg loss 0.000744089, throughput 3.24601K wps
[Epoch 181 Batch 60/62] avg loss 0.000724887, throughput 3.22276K wps
Begin Testing...
[Epoch 181] train avg loss 0.000742504, dev acc 0.8378, dev avg loss 0.364833, throughput 3.24164K wps
[Epoch 182 Batch 30/62] avg loss 0.000688879, throughput 3.27889K wps
[Epoch 182 Batch 60/62] avg loss 0.000712941, throughput 3.15861K wps
Begin Testing...
[Epoch 182] train avg loss 0.000701157, dev acc 0.8378, dev avg loss 0.365166, throughput 3.22335K wps
[Epoch 183 Batch 30/62] avg loss 0.00071664, throughput 3.24579K wps
[Epoch 183 Batch 60/62] avg loss 0.000696217, throughput 3.21591K wps
Begin Testing...
[Epoch 183] train avg loss 0.000717806, dev acc 0.8407, dev avg loss 0.359145, throughput 3.23638K wps
[Epoch 184 Batch 30/62] avg loss 0.000704926, throughput 3.27174K wps
[Epoch 184 Batch 60/62] avg loss 0.000638717, throughput 3.18548K wps
Begin Testing...
[Epoch 184] train avg loss 0.00068311, dev acc 0.8319, dev avg loss 0.363684, throughput 3.23563K wps
[Epoch 185 Batch 30/62] avg loss 0.000631117, throughput 3.28843K wps
[Epoch 185 Batch 60/62] avg loss 0.000715321, throughput 3.16381K wps
Begin Testing...
[Epoch 185] train avg loss 0.000682957, dev acc 0.8348, dev avg loss 0.36286, throughput 3.23067K wps
[Epoch 186 Batch 30/62] avg loss 0.000633639, throughput 3.26403K wps
[Epoch 186 Batch 60/62] avg loss 0.000637774, throughput 3.22119K wps
Begin Testing...
[Epoch 186] train avg loss 0.000650401, dev acc 0.8348, dev avg loss 0.363577, throughput 3.24995K wps
[Epoch 187 Batch 30/62] avg loss 0.000698302, throughput 3.26816K wps
[Epoch 187 Batch 60/62] avg loss 0.000720624, throughput 3.19788K wps
Begin Testing...
[Epoch 187] train avg loss 0.000718306, dev acc 0.8466, dev avg loss 0.358927, throughput 3.24052K wps
[Epoch 188 Batch 30/62] avg loss 0.000689303, throughput 3.29026K wps
[Epoch 188 Batch 60/62] avg loss 0.000683363, throughput 3.22506K wps
Begin Testing...
[Epoch 188] train avg loss 0.000688879, dev acc 0.8348, dev avg loss 0.364404, throughput 3.26448K wps
[Epoch 189 Batch 30/62] avg loss 0.000637163, throughput 3.27639K wps
[Epoch 189 Batch 60/62] avg loss 0.000636512, throughput 3.22139K wps
Begin Testing...
[Epoch 189] train avg loss 0.00064139, dev acc 0.8348, dev avg loss 0.365731, throughput 3.25514K wps
[Epoch 190 Batch 30/62] avg loss 0.0006143, throughput 3.27308K wps
[Epoch 190 Batch 60/62] avg loss 0.000700271, throughput 3.20988K wps
Begin Testing...
[Epoch 190] train avg loss 0.000669626, dev acc 0.8437, dev avg loss 0.360562, throughput 3.24466K wps
[Epoch 191 Batch 30/62] avg loss 0.000641342, throughput 3.28071K wps
[Epoch 191 Batch 60/62] avg loss 0.000705955, throughput 3.16208K wps
Begin Testing...
[Epoch 191] train avg loss 0.000679573, dev acc 0.8437, dev avg loss 0.362877, throughput 3.22606K wps
[Epoch 192 Batch 30/62] avg loss 0.000663395, throughput 3.23252K wps
[Epoch 192 Batch 60/62] avg loss 0.000673964, throughput 3.16301K wps
Begin Testing...
[Epoch 192] train avg loss 0.000677547, dev acc 0.8348, dev avg loss 0.366021, throughput 3.20447K wps
[Epoch 193 Batch 30/62] avg loss 0.000651265, throughput 3.23073K wps
[Epoch 193 Batch 60/62] avg loss 0.000639048, throughput 3.1578K wps
Begin Testing...
[Epoch 193] train avg loss 0.000647174, dev acc 0.8319, dev avg loss 0.367177, throughput 3.19997K wps
[Epoch 194 Batch 30/62] avg loss 0.000661558, throughput 3.24235K wps
[Epoch 194 Batch 60/62] avg loss 0.000631788, throughput 3.16425K wps
Begin Testing...
[Epoch 194] train avg loss 0.000649456, dev acc 0.8348, dev avg loss 0.373422, throughput 3.21052K wps
[Epoch 195 Batch 30/62] avg loss 0.000619002, throughput 3.24615K wps
[Epoch 195 Batch 60/62] avg loss 0.000653402, throughput 3.2245K wps
Begin Testing...
[Epoch 195] train avg loss 0.000639922, dev acc 0.8466, dev avg loss 0.362087, throughput 3.24179K wps
[Epoch 196 Batch 30/62] avg loss 0.000608062, throughput 3.25513K wps
[Epoch 196 Batch 60/62] avg loss 0.000613679, throughput 3.1928K wps
Begin Testing...
[Epoch 196] train avg loss 0.000621822, dev acc 0.8378, dev avg loss 0.36516, throughput 3.2329K wps
[Epoch 197 Batch 30/62] avg loss 0.000632035, throughput 3.2985K wps
[Epoch 197 Batch 60/62] avg loss 0.000621602, throughput 3.17948K wps
Begin Testing...
[Epoch 197] train avg loss 0.000627045, dev acc 0.8437, dev avg loss 0.368568, throughput 3.24595K wps
[Epoch 198 Batch 30/62] avg loss 0.000621817, throughput 3.29194K wps
[Epoch 198 Batch 60/62] avg loss 0.000638074, throughput 3.18025K wps
Begin Testing...
[Epoch 198] train avg loss 0.000640524, dev acc 0.8378, dev avg loss 0.367559, throughput 3.24069K wps
[Epoch 199 Batch 30/62] avg loss 0.000587076, throughput 3.25889K wps
[Epoch 199 Batch 60/62] avg loss 0.00059152, throughput 3.22122K wps
Begin Testing...
[Epoch 199] train avg loss 0.000605151, dev acc 0.8378, dev avg loss 0.367803, throughput 3.24649K wps
Test loss 0.366191, test acc 0.8408
Total time cost 420.64s
[Epoch 0 Batch 30/62] avg loss 0.0135656, throughput 3.07746K wps
[Epoch 0 Batch 60/62] avg loss 0.0130316, throughput 3.21745K wps
Begin Testing...
[Epoch 0] train avg loss 0.0134389, dev acc 0.6254, dev avg loss 0.661763, throughput 3.15474K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0129868, throughput 3.29257K wps
[Epoch 1 Batch 60/62] avg loss 0.0131181, throughput 3.19908K wps
Begin Testing...
[Epoch 1] train avg loss 0.0132252, dev acc 0.6254, dev avg loss 0.651705, throughput 3.25327K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0129985, throughput 3.2817K wps
[Epoch 2 Batch 60/62] avg loss 0.0128404, throughput 3.17728K wps
Begin Testing...
[Epoch 2] train avg loss 0.0131265, dev acc 0.6254, dev avg loss 0.645815, throughput 3.23495K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0126377, throughput 3.26583K wps
[Epoch 3 Batch 60/62] avg loss 0.0127756, throughput 3.18411K wps
Begin Testing...
[Epoch 3] train avg loss 0.0128507, dev acc 0.6254, dev avg loss 0.638024, throughput 3.2324K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0128437, throughput 3.22684K wps
[Epoch 4 Batch 60/62] avg loss 0.0124598, throughput 3.16697K wps
Begin Testing...
[Epoch 4] train avg loss 0.0128422, dev acc 0.6254, dev avg loss 0.630627, throughput 3.20501K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0126235, throughput 3.22382K wps
[Epoch 5 Batch 60/62] avg loss 0.0121727, throughput 3.15261K wps
Begin Testing...
[Epoch 5] train avg loss 0.0125929, dev acc 0.6254, dev avg loss 0.623087, throughput 3.19495K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0121608, throughput 3.27671K wps
[Epoch 6 Batch 60/62] avg loss 0.0123753, throughput 3.15865K wps
Begin Testing...
[Epoch 6] train avg loss 0.0123945, dev acc 0.6283, dev avg loss 0.61507, throughput 3.22273K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0122362, throughput 3.27112K wps
[Epoch 7 Batch 60/62] avg loss 0.0119997, throughput 3.17058K wps
Begin Testing...
[Epoch 7] train avg loss 0.0122535, dev acc 0.6254, dev avg loss 0.610531, throughput 3.22638K wps
[Epoch 8 Batch 30/62] avg loss 0.0119788, throughput 3.24238K wps
[Epoch 8 Batch 60/62] avg loss 0.0118204, throughput 3.16221K wps
Begin Testing...
[Epoch 8] train avg loss 0.0120773, dev acc 0.6313, dev avg loss 0.599321, throughput 3.20852K wps
Observed Improvement.
Begin Testing...
[Epoch 9 Batch 30/62] avg loss 0.0115975, throughput 3.25888K wps
[Epoch 9 Batch 60/62] avg loss 0.0116716, throughput 3.20234K wps
Begin Testing...
[Epoch 9] train avg loss 0.0117775, dev acc 0.6549, dev avg loss 0.59057, throughput 3.23803K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0114118, throughput 3.27727K wps
[Epoch 10 Batch 60/62] avg loss 0.0116649, throughput 3.19174K wps
Begin Testing...
[Epoch 10] train avg loss 0.0116338, dev acc 0.6608, dev avg loss 0.581879, throughput 3.24037K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0114225, throughput 3.27457K wps
[Epoch 11 Batch 60/62] avg loss 0.0112579, throughput 3.20974K wps
Begin Testing...
[Epoch 11] train avg loss 0.0114282, dev acc 0.6431, dev avg loss 0.575075, throughput 3.24747K wps
[Epoch 12 Batch 30/62] avg loss 0.0111297, throughput 3.27644K wps
[Epoch 12 Batch 60/62] avg loss 0.0111552, throughput 3.17157K wps
Begin Testing...
[Epoch 12] train avg loss 0.0112668, dev acc 0.6726, dev avg loss 0.564623, throughput 3.23189K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0111047, throughput 3.2547K wps
[Epoch 13 Batch 60/62] avg loss 0.01073, throughput 3.20732K wps
Begin Testing...
[Epoch 13] train avg loss 0.011134, dev acc 0.7198, dev avg loss 0.553371, throughput 3.23535K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.010905, throughput 3.27837K wps
[Epoch 14 Batch 60/62] avg loss 0.0105041, throughput 3.16154K wps
Begin Testing...
[Epoch 14] train avg loss 0.0108724, dev acc 0.7021, dev avg loss 0.54483, throughput 3.22402K wps
[Epoch 15 Batch 30/62] avg loss 0.0107377, throughput 3.27404K wps
[Epoch 15 Batch 60/62] avg loss 0.0103211, throughput 3.19055K wps
Begin Testing...
[Epoch 15] train avg loss 0.0106345, dev acc 0.6785, dev avg loss 0.538942, throughput 3.23678K wps
[Epoch 16 Batch 30/62] avg loss 0.0105201, throughput 3.28129K wps
[Epoch 16 Batch 60/62] avg loss 0.0101282, throughput 3.17888K wps
Begin Testing...
[Epoch 16] train avg loss 0.0104693, dev acc 0.7286, dev avg loss 0.525366, throughput 3.23495K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.0101374, throughput 3.27089K wps
[Epoch 17 Batch 60/62] avg loss 0.0100368, throughput 3.20835K wps
Begin Testing...
[Epoch 17] train avg loss 0.0102147, dev acc 0.7198, dev avg loss 0.516552, throughput 3.24548K wps
[Epoch 18 Batch 30/62] avg loss 0.0101034, throughput 3.26954K wps
[Epoch 18 Batch 60/62] avg loss 0.00978012, throughput 3.17412K wps
Begin Testing...
[Epoch 18] train avg loss 0.0101083, dev acc 0.7286, dev avg loss 0.507929, throughput 3.22729K wps
Observed Improvement.
Begin Testing...
[Epoch 19 Batch 30/62] avg loss 0.00974716, throughput 3.26359K wps
[Epoch 19 Batch 60/62] avg loss 0.00965853, throughput 3.18612K wps
Begin Testing...
[Epoch 19] train avg loss 0.00981093, dev acc 0.7316, dev avg loss 0.500293, throughput 3.22961K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.0095542, throughput 3.2484K wps
[Epoch 20 Batch 60/62] avg loss 0.00949891, throughput 3.21298K wps
Begin Testing...
[Epoch 20] train avg loss 0.0096604, dev acc 0.7611, dev avg loss 0.491797, throughput 3.23652K wps
Observed Improvement.
Begin Testing...
[Epoch 21 Batch 30/62] avg loss 0.00951348, throughput 3.27507K wps
[Epoch 21 Batch 60/62] avg loss 0.00902979, throughput 3.17467K wps
Begin Testing...
[Epoch 21] train avg loss 0.00935215, dev acc 0.7611, dev avg loss 0.483657, throughput 3.22997K wps
Observed Improvement.
Begin Testing...
[Epoch 22 Batch 30/62] avg loss 0.0089336, throughput 3.26917K wps
[Epoch 22 Batch 60/62] avg loss 0.00926667, throughput 3.2086K wps
Begin Testing...
[Epoch 22] train avg loss 0.00921105, dev acc 0.7670, dev avg loss 0.476835, throughput 3.24507K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.008747, throughput 3.29013K wps
[Epoch 23 Batch 60/62] avg loss 0.00896048, throughput 3.16877K wps
Begin Testing...
[Epoch 23] train avg loss 0.00896552, dev acc 0.7611, dev avg loss 0.471401, throughput 3.23464K wps
[Epoch 24 Batch 30/62] avg loss 0.00882188, throughput 3.25628K wps
[Epoch 24 Batch 60/62] avg loss 0.00882668, throughput 3.22031K wps
Begin Testing...
[Epoch 24] train avg loss 0.00888717, dev acc 0.7729, dev avg loss 0.4665, throughput 3.2438K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00880593, throughput 3.26357K wps
[Epoch 25 Batch 60/62] avg loss 0.00866787, throughput 3.15413K wps
Begin Testing...
[Epoch 25] train avg loss 0.00881018, dev acc 0.7699, dev avg loss 0.458815, throughput 3.21451K wps
[Epoch 26 Batch 30/62] avg loss 0.00840207, throughput 3.2735K wps
[Epoch 26 Batch 60/62] avg loss 0.0084347, throughput 3.19552K wps
Begin Testing...
[Epoch 26] train avg loss 0.00849735, dev acc 0.7758, dev avg loss 0.457006, throughput 3.24223K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.00831455, throughput 3.27563K wps
[Epoch 27 Batch 60/62] avg loss 0.00812201, throughput 3.17963K wps
Begin Testing...
[Epoch 27] train avg loss 0.00832723, dev acc 0.7788, dev avg loss 0.452492, throughput 3.2323K wps
Observed Improvement.
Begin Testing...
[Epoch 28 Batch 30/62] avg loss 0.0080254, throughput 3.28039K wps
[Epoch 28 Batch 60/62] avg loss 0.008275, throughput 3.16253K wps
Begin Testing...
[Epoch 28] train avg loss 0.00832055, dev acc 0.7876, dev avg loss 0.444193, throughput 3.22689K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00781462, throughput 3.25677K wps
[Epoch 29 Batch 60/62] avg loss 0.00789029, throughput 3.15738K wps
Begin Testing...
[Epoch 29] train avg loss 0.0080549, dev acc 0.7876, dev avg loss 0.440033, throughput 3.21141K wps
Observed Improvement.
Begin Testing...
[Epoch 30 Batch 30/62] avg loss 0.00779917, throughput 3.28889K wps
[Epoch 30 Batch 60/62] avg loss 0.00790414, throughput 3.18569K wps
Begin Testing...
[Epoch 30] train avg loss 0.00800243, dev acc 0.8083, dev avg loss 0.435899, throughput 3.24437K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.007531, throughput 3.24366K wps
[Epoch 31 Batch 60/62] avg loss 0.00788874, throughput 3.19226K wps
Begin Testing...
[Epoch 31] train avg loss 0.00779983, dev acc 0.8201, dev avg loss 0.433034, throughput 3.22694K wps
Observed Improvement.
Begin Testing...
[Epoch 32 Batch 30/62] avg loss 0.00771443, throughput 3.30397K wps
[Epoch 32 Batch 60/62] avg loss 0.00749002, throughput 3.17206K wps
Begin Testing...
[Epoch 32] train avg loss 0.00774633, dev acc 0.8083, dev avg loss 0.428382, throughput 3.24336K wps
[Epoch 33 Batch 30/62] avg loss 0.00753134, throughput 3.29058K wps
[Epoch 33 Batch 60/62] avg loss 0.00731959, throughput 3.20407K wps
Begin Testing...
[Epoch 33] train avg loss 0.00746619, dev acc 0.7788, dev avg loss 0.428725, throughput 3.25207K wps
[Epoch 34 Batch 30/62] avg loss 0.00725792, throughput 3.25494K wps
[Epoch 34 Batch 60/62] avg loss 0.00720736, throughput 3.20725K wps
Begin Testing...
[Epoch 34] train avg loss 0.00729742, dev acc 0.8112, dev avg loss 0.421315, throughput 3.23533K wps
[Epoch 35 Batch 30/62] avg loss 0.00719275, throughput 3.27212K wps
[Epoch 35 Batch 60/62] avg loss 0.00706699, throughput 3.17495K wps
Begin Testing...
[Epoch 35] train avg loss 0.00726917, dev acc 0.8230, dev avg loss 0.419176, throughput 3.23126K wps
Observed Improvement.
Begin Testing...
[Epoch 36 Batch 30/62] avg loss 0.00697106, throughput 3.24024K wps
[Epoch 36 Batch 60/62] avg loss 0.00721562, throughput 3.22041K wps
Begin Testing...
[Epoch 36] train avg loss 0.00720103, dev acc 0.7994, dev avg loss 0.416946, throughput 3.23619K wps
[Epoch 37 Batch 30/62] avg loss 0.00674804, throughput 3.28037K wps
[Epoch 37 Batch 60/62] avg loss 0.00705949, throughput 3.22125K wps
Begin Testing...
[Epoch 37] train avg loss 0.00694462, dev acc 0.8201, dev avg loss 0.412552, throughput 3.25664K wps
[Epoch 38 Batch 30/62] avg loss 0.00686046, throughput 3.25652K wps
[Epoch 38 Batch 60/62] avg loss 0.00667981, throughput 3.16687K wps
Begin Testing...
[Epoch 38] train avg loss 0.00689828, dev acc 0.8201, dev avg loss 0.410027, throughput 3.21878K wps
[Epoch 39 Batch 30/62] avg loss 0.00654078, throughput 3.2355K wps
[Epoch 39 Batch 60/62] avg loss 0.00684954, throughput 3.18187K wps
Begin Testing...
[Epoch 39] train avg loss 0.00680458, dev acc 0.8260, dev avg loss 0.406954, throughput 3.21642K wps
Observed Improvement.
Begin Testing...
[Epoch 40 Batch 30/62] avg loss 0.00646636, throughput 3.23564K wps
[Epoch 40 Batch 60/62] avg loss 0.00670423, throughput 3.21671K wps
Begin Testing...
[Epoch 40] train avg loss 0.00673017, dev acc 0.8319, dev avg loss 0.405029, throughput 3.23294K wps
Observed Improvement.
Begin Testing...
[Epoch 41 Batch 30/62] avg loss 0.00647261, throughput 3.28345K wps
[Epoch 41 Batch 60/62] avg loss 0.00641067, throughput 3.17368K wps
Begin Testing...
[Epoch 41] train avg loss 0.00657214, dev acc 0.8230, dev avg loss 0.403073, throughput 3.2338K wps
[Epoch 42 Batch 30/62] avg loss 0.00639933, throughput 3.26402K wps
[Epoch 42 Batch 60/62] avg loss 0.00612931, throughput 3.20294K wps
Begin Testing...
[Epoch 42] train avg loss 0.00631978, dev acc 0.8260, dev avg loss 0.399914, throughput 3.23925K wps
[Epoch 43 Batch 30/62] avg loss 0.00606641, throughput 3.28288K wps
[Epoch 43 Batch 60/62] avg loss 0.00646453, throughput 3.19082K wps
Begin Testing...
[Epoch 43] train avg loss 0.00635099, dev acc 0.8260, dev avg loss 0.397546, throughput 3.24459K wps
[Epoch 44 Batch 30/62] avg loss 0.00614951, throughput 3.29735K wps
[Epoch 44 Batch 60/62] avg loss 0.00616732, throughput 3.17322K wps
Begin Testing...
[Epoch 44] train avg loss 0.0062273, dev acc 0.8260, dev avg loss 0.394994, throughput 3.2403K wps
[Epoch 45 Batch 30/62] avg loss 0.00595472, throughput 3.28964K wps
[Epoch 45 Batch 60/62] avg loss 0.0057939, throughput 3.20041K wps
Begin Testing...
[Epoch 45] train avg loss 0.00590714, dev acc 0.8289, dev avg loss 0.393012, throughput 3.25056K wps
[Epoch 46 Batch 30/62] avg loss 0.00596047, throughput 3.27861K wps
[Epoch 46 Batch 60/62] avg loss 0.0057876, throughput 3.20294K wps
Begin Testing...
[Epoch 46] train avg loss 0.00594169, dev acc 0.8319, dev avg loss 0.391086, throughput 3.24583K wps
Observed Improvement.
Begin Testing...
[Epoch 47 Batch 30/62] avg loss 0.00576042, throughput 3.30032K wps
[Epoch 47 Batch 60/62] avg loss 0.00582941, throughput 3.20859K wps
Begin Testing...
[Epoch 47] train avg loss 0.00582966, dev acc 0.8289, dev avg loss 0.388658, throughput 3.26044K wps
[Epoch 48 Batch 30/62] avg loss 0.00553726, throughput 3.26493K wps
[Epoch 48 Batch 60/62] avg loss 0.00559528, throughput 3.22007K wps
Begin Testing...
[Epoch 48] train avg loss 0.0056349, dev acc 0.8201, dev avg loss 0.386363, throughput 3.25046K wps
[Epoch 49 Batch 30/62] avg loss 0.00549634, throughput 3.28804K wps
[Epoch 49 Batch 60/62] avg loss 0.00561485, throughput 3.21485K wps
Begin Testing...
[Epoch 49] train avg loss 0.00564531, dev acc 0.8319, dev avg loss 0.385628, throughput 3.25654K wps
Observed Improvement.
Begin Testing...
[Epoch 50 Batch 30/62] avg loss 0.00549216, throughput 3.28724K wps
[Epoch 50 Batch 60/62] avg loss 0.00549077, throughput 3.1933K wps
Begin Testing...
[Epoch 50] train avg loss 0.00553851, dev acc 0.8289, dev avg loss 0.384086, throughput 3.24914K wps
[Epoch 51 Batch 30/62] avg loss 0.00548643, throughput 3.3069K wps
[Epoch 51 Batch 60/62] avg loss 0.00514169, throughput 3.21132K wps
Begin Testing...
[Epoch 51] train avg loss 0.00536238, dev acc 0.8319, dev avg loss 0.381725, throughput 3.26576K wps
Observed Improvement.
Begin Testing...
[Epoch 52 Batch 30/62] avg loss 0.00532645, throughput 3.30668K wps
[Epoch 52 Batch 60/62] avg loss 0.00521547, throughput 3.22851K wps
Begin Testing...
[Epoch 52] train avg loss 0.00534071, dev acc 0.8319, dev avg loss 0.380484, throughput 3.27372K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.00502413, throughput 3.31649K wps
[Epoch 53 Batch 60/62] avg loss 0.00516819, throughput 3.23284K wps
Begin Testing...
[Epoch 53] train avg loss 0.00518399, dev acc 0.8289, dev avg loss 0.378897, throughput 3.28003K wps
[Epoch 54 Batch 30/62] avg loss 0.00519422, throughput 3.27266K wps
[Epoch 54 Batch 60/62] avg loss 0.00491432, throughput 3.2307K wps
Begin Testing...
[Epoch 54] train avg loss 0.00512094, dev acc 0.8289, dev avg loss 0.378035, throughput 3.25708K wps
[Epoch 55 Batch 30/62] avg loss 0.00486624, throughput 3.2852K wps
[Epoch 55 Batch 60/62] avg loss 0.00497387, throughput 3.21236K wps
Begin Testing...
[Epoch 55] train avg loss 0.00496922, dev acc 0.8319, dev avg loss 0.374232, throughput 3.25441K wps
Observed Improvement.
Begin Testing...
[Epoch 56 Batch 30/62] avg loss 0.0050093, throughput 3.30114K wps
[Epoch 56 Batch 60/62] avg loss 0.00493591, throughput 3.23542K wps
Begin Testing...
[Epoch 56] train avg loss 0.00504529, dev acc 0.8378, dev avg loss 0.373273, throughput 3.2744K wps
Observed Improvement.
Begin Testing...
[Epoch 57 Batch 30/62] avg loss 0.00463802, throughput 3.29264K wps
[Epoch 57 Batch 60/62] avg loss 0.00486935, throughput 3.22519K wps
Begin Testing...
[Epoch 57] train avg loss 0.00481345, dev acc 0.8378, dev avg loss 0.3721, throughput 3.26544K wps
Observed Improvement.
Begin Testing...
[Epoch 58 Batch 30/62] avg loss 0.00478151, throughput 3.29509K wps
[Epoch 58 Batch 60/62] avg loss 0.0044133, throughput 3.2282K wps
Begin Testing...
[Epoch 58] train avg loss 0.00464019, dev acc 0.8378, dev avg loss 0.370315, throughput 3.26693K wps
Observed Improvement.
Begin Testing...
[Epoch 59 Batch 30/62] avg loss 0.0046448, throughput 3.31906K wps
[Epoch 59 Batch 60/62] avg loss 0.00472524, throughput 3.23538K wps
Begin Testing...
[Epoch 59] train avg loss 0.00473053, dev acc 0.8348, dev avg loss 0.369211, throughput 3.28299K wps
[Epoch 60 Batch 30/62] avg loss 0.00449333, throughput 3.32065K wps
[Epoch 60 Batch 60/62] avg loss 0.00468013, throughput 3.2409K wps
Begin Testing...
[Epoch 60] train avg loss 0.00462071, dev acc 0.8348, dev avg loss 0.368014, throughput 3.28565K wps
[Epoch 61 Batch 30/62] avg loss 0.00438203, throughput 3.29994K wps
[Epoch 61 Batch 60/62] avg loss 0.0043916, throughput 3.22781K wps
Begin Testing...
[Epoch 61] train avg loss 0.004449, dev acc 0.8407, dev avg loss 0.367537, throughput 3.26902K wps
Observed Improvement.
Begin Testing...
[Epoch 62 Batch 30/62] avg loss 0.00451414, throughput 3.30204K wps
[Epoch 62 Batch 60/62] avg loss 0.00446039, throughput 3.23995K wps
Begin Testing...
[Epoch 62] train avg loss 0.00462361, dev acc 0.8348, dev avg loss 0.36755, throughput 3.2766K wps
[Epoch 63 Batch 30/62] avg loss 0.00443332, throughput 3.32746K wps
[Epoch 63 Batch 60/62] avg loss 0.0043012, throughput 3.22404K wps
Begin Testing...
[Epoch 63] train avg loss 0.00443577, dev acc 0.8348, dev avg loss 0.368383, throughput 3.28262K wps
[Epoch 64 Batch 30/62] avg loss 0.0042954, throughput 3.28362K wps
[Epoch 64 Batch 60/62] avg loss 0.00417853, throughput 3.22577K wps
Begin Testing...
[Epoch 64] train avg loss 0.00426637, dev acc 0.8319, dev avg loss 0.364226, throughput 3.26234K wps
[Epoch 65 Batch 30/62] avg loss 0.00414561, throughput 3.3119K wps
[Epoch 65 Batch 60/62] avg loss 0.00404158, throughput 3.23678K wps
Begin Testing...
[Epoch 65] train avg loss 0.00414307, dev acc 0.8378, dev avg loss 0.363859, throughput 3.28123K wps
[Epoch 66 Batch 30/62] avg loss 0.00399251, throughput 3.31746K wps
[Epoch 66 Batch 60/62] avg loss 0.0040711, throughput 3.2398K wps
Begin Testing...
[Epoch 66] train avg loss 0.00406915, dev acc 0.8289, dev avg loss 0.365156, throughput 3.28342K wps
[Epoch 67 Batch 30/62] avg loss 0.00390114, throughput 3.31254K wps
[Epoch 67 Batch 60/62] avg loss 0.00389539, throughput 3.23688K wps
Begin Testing...
[Epoch 67] train avg loss 0.00393383, dev acc 0.8319, dev avg loss 0.362051, throughput 3.28158K wps
[Epoch 68 Batch 30/62] avg loss 0.00386549, throughput 3.31882K wps
[Epoch 68 Batch 60/62] avg loss 0.00379105, throughput 3.2337K wps
Begin Testing...
[Epoch 68] train avg loss 0.00389068, dev acc 0.8407, dev avg loss 0.359749, throughput 3.28129K wps
Observed Improvement.
Begin Testing...
[Epoch 69 Batch 30/62] avg loss 0.00404623, throughput 3.31601K wps
[Epoch 69 Batch 60/62] avg loss 0.00349173, throughput 3.22755K wps
Begin Testing...
[Epoch 69] train avg loss 0.00386537, dev acc 0.8407, dev avg loss 0.361168, throughput 3.27665K wps
Observed Improvement.
Begin Testing...
[Epoch 70 Batch 30/62] avg loss 0.00371662, throughput 3.30994K wps
[Epoch 70 Batch 60/62] avg loss 0.00392327, throughput 3.22416K wps
Begin Testing...
[Epoch 70] train avg loss 0.00385853, dev acc 0.8319, dev avg loss 0.359754, throughput 3.27267K wps
[Epoch 71 Batch 30/62] avg loss 0.00381831, throughput 3.32864K wps
[Epoch 71 Batch 60/62] avg loss 0.00366284, throughput 3.24541K wps
Begin Testing...
[Epoch 71] train avg loss 0.00383715, dev acc 0.8496, dev avg loss 0.357612, throughput 3.29291K wps
Observed Improvement.
Begin Testing...
[Epoch 72 Batch 30/62] avg loss 0.0037075, throughput 3.32767K wps
[Epoch 72 Batch 60/62] avg loss 0.00357686, throughput 3.229K wps
Begin Testing...
[Epoch 72] train avg loss 0.00367335, dev acc 0.8289, dev avg loss 0.359424, throughput 3.28394K wps
[Epoch 73 Batch 30/62] avg loss 0.00348834, throughput 3.30023K wps
[Epoch 73 Batch 60/62] avg loss 0.00364885, throughput 3.22597K wps
Begin Testing...
[Epoch 73] train avg loss 0.00360728, dev acc 0.8378, dev avg loss 0.359941, throughput 3.26936K wps
[Epoch 74 Batch 30/62] avg loss 0.00360973, throughput 3.31664K wps
[Epoch 74 Batch 60/62] avg loss 0.00342596, throughput 3.23375K wps
Begin Testing...
[Epoch 74] train avg loss 0.00355196, dev acc 0.8466, dev avg loss 0.360765, throughput 3.282K wps
[Epoch 75 Batch 30/62] avg loss 0.00346161, throughput 3.28546K wps
[Epoch 75 Batch 60/62] avg loss 0.00333634, throughput 3.2244K wps
Begin Testing...
[Epoch 75] train avg loss 0.0034633, dev acc 0.8348, dev avg loss 0.358019, throughput 3.26053K wps
[Epoch 76 Batch 30/62] avg loss 0.00313233, throughput 3.32765K wps
[Epoch 76 Batch 60/62] avg loss 0.00353907, throughput 3.23433K wps
Begin Testing...
[Epoch 76] train avg loss 0.00338654, dev acc 0.8466, dev avg loss 0.354043, throughput 3.28804K wps
[Epoch 77 Batch 30/62] avg loss 0.00331752, throughput 3.31023K wps
[Epoch 77 Batch 60/62] avg loss 0.00345796, throughput 3.23472K wps
Begin Testing...
[Epoch 77] train avg loss 0.00345571, dev acc 0.8466, dev avg loss 0.353791, throughput 3.27781K wps
[Epoch 78 Batch 30/62] avg loss 0.00311723, throughput 3.29934K wps
[Epoch 78 Batch 60/62] avg loss 0.00342778, throughput 3.22205K wps
Begin Testing...
[Epoch 78] train avg loss 0.00332533, dev acc 0.8437, dev avg loss 0.352944, throughput 3.26779K wps
[Epoch 79 Batch 30/62] avg loss 0.0032339, throughput 3.31292K wps
[Epoch 79 Batch 60/62] avg loss 0.00299984, throughput 3.24948K wps
Begin Testing...
[Epoch 79] train avg loss 0.00316992, dev acc 0.8466, dev avg loss 0.352628, throughput 3.28703K wps
[Epoch 80 Batch 30/62] avg loss 0.00321009, throughput 3.28874K wps
[Epoch 80 Batch 60/62] avg loss 0.00299868, throughput 3.23374K wps
Begin Testing...
[Epoch 80] train avg loss 0.0031359, dev acc 0.8496, dev avg loss 0.351656, throughput 3.26582K wps
Observed Improvement.
Begin Testing...
[Epoch 81 Batch 30/62] avg loss 0.00307074, throughput 3.29429K wps
[Epoch 81 Batch 60/62] avg loss 0.00294043, throughput 3.22162K wps
Begin Testing...
[Epoch 81] train avg loss 0.00302573, dev acc 0.8496, dev avg loss 0.351456, throughput 3.26408K wps
Observed Improvement.
Begin Testing...
[Epoch 82 Batch 30/62] avg loss 0.00294637, throughput 3.29634K wps
[Epoch 82 Batch 60/62] avg loss 0.00304194, throughput 3.2326K wps
Begin Testing...
[Epoch 82] train avg loss 0.00301765, dev acc 0.8466, dev avg loss 0.353918, throughput 3.26986K wps
[Epoch 83 Batch 30/62] avg loss 0.00303975, throughput 3.30389K wps
[Epoch 83 Batch 60/62] avg loss 0.00292317, throughput 3.217K wps
Begin Testing...
[Epoch 83] train avg loss 0.00304029, dev acc 0.8407, dev avg loss 0.351523, throughput 3.26766K wps
[Epoch 84 Batch 30/62] avg loss 0.00279657, throughput 3.30606K wps
[Epoch 84 Batch 60/62] avg loss 0.00284804, throughput 3.22529K wps
Begin Testing...
[Epoch 84] train avg loss 0.00288766, dev acc 0.8407, dev avg loss 0.351185, throughput 3.27231K wps
[Epoch 85 Batch 30/62] avg loss 0.00281372, throughput 3.29783K wps
[Epoch 85 Batch 60/62] avg loss 0.00300083, throughput 3.22939K wps
Begin Testing...
[Epoch 85] train avg loss 0.00295032, dev acc 0.8466, dev avg loss 0.348654, throughput 3.26889K wps
[Epoch 86 Batch 30/62] avg loss 0.00284831, throughput 3.27907K wps
[Epoch 86 Batch 60/62] avg loss 0.00286974, throughput 3.22702K wps
Begin Testing...
[Epoch 86] train avg loss 0.00290854, dev acc 0.8407, dev avg loss 0.348133, throughput 3.25914K wps
[Epoch 87 Batch 30/62] avg loss 0.0027093, throughput 3.27183K wps
[Epoch 87 Batch 60/62] avg loss 0.00287652, throughput 3.22873K wps
Begin Testing...
[Epoch 87] train avg loss 0.00285864, dev acc 0.8407, dev avg loss 0.348032, throughput 3.25651K wps
[Epoch 88 Batch 30/62] avg loss 0.00268569, throughput 3.31682K wps
[Epoch 88 Batch 60/62] avg loss 0.0026856, throughput 3.22617K wps
Begin Testing...
[Epoch 88] train avg loss 0.00274171, dev acc 0.8466, dev avg loss 0.347359, throughput 3.27826K wps
[Epoch 89 Batch 30/62] avg loss 0.00269036, throughput 3.31089K wps
[Epoch 89 Batch 60/62] avg loss 0.00271591, throughput 3.213K wps
Begin Testing...
[Epoch 89] train avg loss 0.00275124, dev acc 0.8466, dev avg loss 0.347448, throughput 3.26876K wps
[Epoch 90 Batch 30/62] avg loss 0.00246932, throughput 3.30382K wps
[Epoch 90 Batch 60/62] avg loss 0.00271609, throughput 3.24554K wps
Begin Testing...
[Epoch 90] train avg loss 0.00263833, dev acc 0.8496, dev avg loss 0.346758, throughput 3.28035K wps
Observed Improvement.
Begin Testing...
[Epoch 91 Batch 30/62] avg loss 0.00253715, throughput 3.32758K wps
[Epoch 91 Batch 60/62] avg loss 0.00264324, throughput 3.23071K wps
Begin Testing...
[Epoch 91] train avg loss 0.00263435, dev acc 0.8466, dev avg loss 0.346775, throughput 3.28562K wps
[Epoch 92 Batch 30/62] avg loss 0.00255345, throughput 3.32033K wps
[Epoch 92 Batch 60/62] avg loss 0.00248995, throughput 3.23024K wps
Begin Testing...
[Epoch 92] train avg loss 0.00255133, dev acc 0.8466, dev avg loss 0.346073, throughput 3.28011K wps
[Epoch 93 Batch 30/62] avg loss 0.00243459, throughput 3.29284K wps
[Epoch 93 Batch 60/62] avg loss 0.00246514, throughput 3.24639K wps
Begin Testing...
[Epoch 93] train avg loss 0.00252803, dev acc 0.8496, dev avg loss 0.347334, throughput 3.27726K wps
Observed Improvement.
Begin Testing...
[Epoch 94 Batch 30/62] avg loss 0.00248258, throughput 3.31126K wps
[Epoch 94 Batch 60/62] avg loss 0.00234355, throughput 3.21362K wps
Begin Testing...
[Epoch 94] train avg loss 0.00244215, dev acc 0.8466, dev avg loss 0.345822, throughput 3.26814K wps
[Epoch 95 Batch 30/62] avg loss 0.0023408, throughput 3.29349K wps
[Epoch 95 Batch 60/62] avg loss 0.00244367, throughput 3.18644K wps
Begin Testing...
[Epoch 95] train avg loss 0.00242094, dev acc 0.8407, dev avg loss 0.34588, throughput 3.24688K wps
[Epoch 96 Batch 30/62] avg loss 0.00237346, throughput 3.31238K wps
[Epoch 96 Batch 60/62] avg loss 0.00242856, throughput 3.23491K wps
Begin Testing...
[Epoch 96] train avg loss 0.00246857, dev acc 0.8466, dev avg loss 0.345914, throughput 3.2807K wps
[Epoch 97 Batch 30/62] avg loss 0.00232591, throughput 3.3048K wps
[Epoch 97 Batch 60/62] avg loss 0.00235547, throughput 3.22443K wps
Begin Testing...
[Epoch 97] train avg loss 0.00237344, dev acc 0.8466, dev avg loss 0.344521, throughput 3.26943K wps
[Epoch 98 Batch 30/62] avg loss 0.0023309, throughput 3.28377K wps
[Epoch 98 Batch 60/62] avg loss 0.00214544, throughput 3.21489K wps
Begin Testing...
[Epoch 98] train avg loss 0.00227291, dev acc 0.8466, dev avg loss 0.34419, throughput 3.25536K wps
[Epoch 99 Batch 30/62] avg loss 0.00223717, throughput 3.28702K wps
[Epoch 99 Batch 60/62] avg loss 0.0023192, throughput 3.2125K wps
Begin Testing...
[Epoch 99] train avg loss 0.00229702, dev acc 0.8466, dev avg loss 0.343768, throughput 3.25484K wps
[Epoch 100 Batch 30/62] avg loss 0.00219207, throughput 3.27576K wps
[Epoch 100 Batch 60/62] avg loss 0.00211737, throughput 3.21759K wps
Begin Testing...
[Epoch 100] train avg loss 0.00221589, dev acc 0.8496, dev avg loss 0.34293, throughput 3.25282K wps
Observed Improvement.
Begin Testing...
[Epoch 101 Batch 30/62] avg loss 0.00229696, throughput 3.2952K wps
[Epoch 101 Batch 60/62] avg loss 0.00204625, throughput 3.24204K wps
Begin Testing...
[Epoch 101] train avg loss 0.00221634, dev acc 0.8496, dev avg loss 0.342664, throughput 3.2745K wps
Observed Improvement.
Begin Testing...
[Epoch 102 Batch 30/62] avg loss 0.00200643, throughput 3.30061K wps
[Epoch 102 Batch 60/62] avg loss 0.00216137, throughput 3.22655K wps
Begin Testing...
[Epoch 102] train avg loss 0.00208087, dev acc 0.8437, dev avg loss 0.344007, throughput 3.26911K wps
[Epoch 103 Batch 30/62] avg loss 0.00207705, throughput 3.29755K wps
[Epoch 103 Batch 60/62] avg loss 0.00221723, throughput 3.24124K wps
Begin Testing...
[Epoch 103] train avg loss 0.00214335, dev acc 0.8466, dev avg loss 0.34329, throughput 3.27708K wps
[Epoch 104 Batch 30/62] avg loss 0.00202585, throughput 3.31731K wps
[Epoch 104 Batch 60/62] avg loss 0.00219003, throughput 3.23735K wps
Begin Testing...
[Epoch 104] train avg loss 0.00211548, dev acc 0.8496, dev avg loss 0.343006, throughput 3.28252K wps
Observed Improvement.
Begin Testing...
[Epoch 105 Batch 30/62] avg loss 0.00204907, throughput 3.27193K wps
[Epoch 105 Batch 60/62] avg loss 0.00196698, throughput 3.21692K wps
Begin Testing...
[Epoch 105] train avg loss 0.00203563, dev acc 0.8466, dev avg loss 0.34509, throughput 3.25127K wps
[Epoch 106 Batch 30/62] avg loss 0.00192504, throughput 3.29099K wps
[Epoch 106 Batch 60/62] avg loss 0.00193131, throughput 3.22612K wps
Begin Testing...
[Epoch 106] train avg loss 0.00198017, dev acc 0.8496, dev avg loss 0.345384, throughput 3.26368K wps
Observed Improvement.
Begin Testing...
[Epoch 107 Batch 30/62] avg loss 0.00207268, throughput 3.31994K wps
[Epoch 107 Batch 60/62] avg loss 0.00191441, throughput 3.23559K wps
Begin Testing...
[Epoch 107] train avg loss 0.00198802, dev acc 0.8496, dev avg loss 0.345244, throughput 3.28231K wps
Observed Improvement.
Begin Testing...
[Epoch 108 Batch 30/62] avg loss 0.00170517, throughput 3.29935K wps
[Epoch 108 Batch 60/62] avg loss 0.00215385, throughput 3.22096K wps
Begin Testing...
[Epoch 108] train avg loss 0.00196, dev acc 0.8496, dev avg loss 0.342056, throughput 3.26574K wps
Observed Improvement.
Begin Testing...
[Epoch 109 Batch 30/62] avg loss 0.00196512, throughput 3.29108K wps
[Epoch 109 Batch 60/62] avg loss 0.00177593, throughput 3.22062K wps
Begin Testing...
[Epoch 109] train avg loss 0.00188373, dev acc 0.8437, dev avg loss 0.342196, throughput 3.26084K wps
[Epoch 110 Batch 30/62] avg loss 0.00186868, throughput 3.27776K wps
[Epoch 110 Batch 60/62] avg loss 0.0018461, throughput 3.22216K wps
Begin Testing...
[Epoch 110] train avg loss 0.00186281, dev acc 0.8437, dev avg loss 0.343106, throughput 3.25524K wps
[Epoch 111 Batch 30/62] avg loss 0.0018439, throughput 3.29655K wps
[Epoch 111 Batch 60/62] avg loss 0.00174038, throughput 3.22732K wps
Begin Testing...
[Epoch 111] train avg loss 0.00179277, dev acc 0.8437, dev avg loss 0.341188, throughput 3.26696K wps
[Epoch 112 Batch 30/62] avg loss 0.00173293, throughput 3.29565K wps
[Epoch 112 Batch 60/62] avg loss 0.00177008, throughput 3.22674K wps
Begin Testing...
[Epoch 112] train avg loss 0.00177239, dev acc 0.8466, dev avg loss 0.342255, throughput 3.26704K wps
[Epoch 113 Batch 30/62] avg loss 0.00182559, throughput 3.31716K wps
[Epoch 113 Batch 60/62] avg loss 0.00173395, throughput 3.22361K wps
Begin Testing...
[Epoch 113] train avg loss 0.00181798, dev acc 0.8437, dev avg loss 0.341068, throughput 3.27554K wps
[Epoch 114 Batch 30/62] avg loss 0.00173138, throughput 3.28974K wps
[Epoch 114 Batch 60/62] avg loss 0.00188174, throughput 3.21779K wps
Begin Testing...
[Epoch 114] train avg loss 0.00180752, dev acc 0.8525, dev avg loss 0.340692, throughput 3.25957K wps
Observed Improvement.
Begin Testing...
[Epoch 115 Batch 30/62] avg loss 0.00170217, throughput 3.2948K wps
[Epoch 115 Batch 60/62] avg loss 0.00186061, throughput 3.20686K wps
Begin Testing...
[Epoch 115] train avg loss 0.00183166, dev acc 0.8496, dev avg loss 0.340832, throughput 3.25744K wps
[Epoch 116 Batch 30/62] avg loss 0.00175122, throughput 3.2952K wps
[Epoch 116 Batch 60/62] avg loss 0.0017778, throughput 3.22226K wps
Begin Testing...
[Epoch 116] train avg loss 0.00176267, dev acc 0.8466, dev avg loss 0.341276, throughput 3.26582K wps
[Epoch 117 Batch 30/62] avg loss 0.00172923, throughput 3.29993K wps
[Epoch 117 Batch 60/62] avg loss 0.00164908, throughput 3.2193K wps
Begin Testing...
[Epoch 117] train avg loss 0.00172604, dev acc 0.8496, dev avg loss 0.340689, throughput 3.26451K wps
[Epoch 118 Batch 30/62] avg loss 0.00167882, throughput 3.27668K wps
[Epoch 118 Batch 60/62] avg loss 0.00171154, throughput 3.22127K wps
Begin Testing...
[Epoch 118] train avg loss 0.00169803, dev acc 0.8525, dev avg loss 0.340356, throughput 3.25544K wps
Observed Improvement.
Begin Testing...
[Epoch 119 Batch 30/62] avg loss 0.00160747, throughput 3.2959K wps
[Epoch 119 Batch 60/62] avg loss 0.00159016, throughput 3.21871K wps
Begin Testing...
[Epoch 119] train avg loss 0.00162367, dev acc 0.8496, dev avg loss 0.340183, throughput 3.26288K wps
[Epoch 120 Batch 30/62] avg loss 0.00153113, throughput 3.28818K wps
[Epoch 120 Batch 60/62] avg loss 0.00161773, throughput 3.20817K wps
Begin Testing...
[Epoch 120] train avg loss 0.00159766, dev acc 0.8466, dev avg loss 0.341118, throughput 3.25454K wps
[Epoch 121 Batch 30/62] avg loss 0.00155221, throughput 3.2937K wps
[Epoch 121 Batch 60/62] avg loss 0.00151937, throughput 3.20737K wps
Begin Testing...
[Epoch 121] train avg loss 0.00154819, dev acc 0.8437, dev avg loss 0.342405, throughput 3.25511K wps
[Epoch 122 Batch 30/62] avg loss 0.00151482, throughput 3.27201K wps
[Epoch 122 Batch 60/62] avg loss 0.00166428, throughput 3.16794K wps
Begin Testing...
[Epoch 122] train avg loss 0.0016167, dev acc 0.8437, dev avg loss 0.339672, throughput 3.22591K wps
[Epoch 123 Batch 30/62] avg loss 0.0014416, throughput 3.27914K wps
[Epoch 123 Batch 60/62] avg loss 0.00157283, throughput 3.19399K wps
Begin Testing...
[Epoch 123] train avg loss 0.00151458, dev acc 0.8466, dev avg loss 0.339799, throughput 3.2419K wps
[Epoch 124 Batch 30/62] avg loss 0.00150594, throughput 3.25741K wps
[Epoch 124 Batch 60/62] avg loss 0.00155604, throughput 3.19249K wps
Begin Testing...
[Epoch 124] train avg loss 0.00154321, dev acc 0.8466, dev avg loss 0.341189, throughput 3.233K wps
[Epoch 125 Batch 30/62] avg loss 0.00154937, throughput 3.28722K wps
[Epoch 125 Batch 60/62] avg loss 0.00148311, throughput 3.15884K wps
Begin Testing...
[Epoch 125] train avg loss 0.00154953, dev acc 0.8466, dev avg loss 0.340952, throughput 3.22992K wps
[Epoch 126 Batch 30/62] avg loss 0.00151633, throughput 3.25946K wps
[Epoch 126 Batch 60/62] avg loss 0.00130884, throughput 3.20562K wps
Begin Testing...
[Epoch 126] train avg loss 0.00144371, dev acc 0.8525, dev avg loss 0.34107, throughput 3.23973K wps
Observed Improvement.
Begin Testing...
[Epoch 127 Batch 30/62] avg loss 0.0014188, throughput 3.29852K wps
[Epoch 127 Batch 60/62] avg loss 0.00143805, throughput 3.16667K wps
Begin Testing...
[Epoch 127] train avg loss 0.00146258, dev acc 0.8496, dev avg loss 0.343938, throughput 3.23677K wps
[Epoch 128 Batch 30/62] avg loss 0.0014333, throughput 3.24278K wps
[Epoch 128 Batch 60/62] avg loss 0.00139733, throughput 3.23391K wps
Begin Testing...
[Epoch 128] train avg loss 0.00142468, dev acc 0.8496, dev avg loss 0.342024, throughput 3.24451K wps
[Epoch 129 Batch 30/62] avg loss 0.00139728, throughput 3.27921K wps
[Epoch 129 Batch 60/62] avg loss 0.0014569, throughput 3.20816K wps
Begin Testing...
[Epoch 129] train avg loss 0.00144908, dev acc 0.8437, dev avg loss 0.341057, throughput 3.2498K wps
[Epoch 130 Batch 30/62] avg loss 0.00146288, throughput 3.24797K wps
[Epoch 130 Batch 60/62] avg loss 0.00142048, throughput 3.16003K wps
Begin Testing...
[Epoch 130] train avg loss 0.00144056, dev acc 0.8437, dev avg loss 0.340409, throughput 3.20995K wps
[Epoch 131 Batch 30/62] avg loss 0.0012328, throughput 3.24788K wps
[Epoch 131 Batch 60/62] avg loss 0.00133832, throughput 3.21566K wps
Begin Testing...
[Epoch 131] train avg loss 0.00134197, dev acc 0.8496, dev avg loss 0.344094, throughput 3.23874K wps
[Epoch 132 Batch 30/62] avg loss 0.0013629, throughput 3.28564K wps
[Epoch 132 Batch 60/62] avg loss 0.00135662, throughput 3.18285K wps
Begin Testing...
[Epoch 132] train avg loss 0.00139703, dev acc 0.8437, dev avg loss 0.339328, throughput 3.24123K wps
[Epoch 133 Batch 30/62] avg loss 0.00133914, throughput 3.28315K wps
[Epoch 133 Batch 60/62] avg loss 0.00131714, throughput 3.16516K wps
Begin Testing...
[Epoch 133] train avg loss 0.00132773, dev acc 0.8496, dev avg loss 0.340419, throughput 3.22922K wps
[Epoch 134 Batch 30/62] avg loss 0.00132585, throughput 3.25528K wps
[Epoch 134 Batch 60/62] avg loss 0.00141869, throughput 3.20355K wps
Begin Testing...
[Epoch 134] train avg loss 0.00137408, dev acc 0.8437, dev avg loss 0.339816, throughput 3.23713K wps
[Epoch 135 Batch 30/62] avg loss 0.0012682, throughput 3.28969K wps
[Epoch 135 Batch 60/62] avg loss 0.00131783, throughput 3.21861K wps
Begin Testing...
[Epoch 135] train avg loss 0.00132304, dev acc 0.8496, dev avg loss 0.343146, throughput 3.26088K wps
[Epoch 136 Batch 30/62] avg loss 0.00124459, throughput 3.27533K wps
[Epoch 136 Batch 60/62] avg loss 0.00125055, throughput 3.19098K wps
Begin Testing...
[Epoch 136] train avg loss 0.00126168, dev acc 0.8437, dev avg loss 0.340531, throughput 3.24103K wps
[Epoch 137 Batch 30/62] avg loss 0.00125167, throughput 3.28519K wps
[Epoch 137 Batch 60/62] avg loss 0.00118954, throughput 3.16683K wps
Begin Testing...
[Epoch 137] train avg loss 0.00126426, dev acc 0.8437, dev avg loss 0.339606, throughput 3.23128K wps
[Epoch 138 Batch 30/62] avg loss 0.00122693, throughput 3.23819K wps
[Epoch 138 Batch 60/62] avg loss 0.00125148, throughput 3.21823K wps
Begin Testing...
[Epoch 138] train avg loss 0.00125968, dev acc 0.8496, dev avg loss 0.339936, throughput 3.23584K wps
[Epoch 139 Batch 30/62] avg loss 0.0011958, throughput 3.27074K wps
[Epoch 139 Batch 60/62] avg loss 0.0011796, throughput 3.14416K wps
Begin Testing...
[Epoch 139] train avg loss 0.00118539, dev acc 0.8437, dev avg loss 0.339801, throughput 3.2115K wps
[Epoch 140 Batch 30/62] avg loss 0.00121735, throughput 3.26247K wps
[Epoch 140 Batch 60/62] avg loss 0.00115298, throughput 3.19158K wps
Begin Testing...
[Epoch 140] train avg loss 0.00121297, dev acc 0.8437, dev avg loss 0.345743, throughput 3.23542K wps
[Epoch 141 Batch 30/62] avg loss 0.00118919, throughput 3.28647K wps
[Epoch 141 Batch 60/62] avg loss 0.00118013, throughput 3.21056K wps
Begin Testing...
[Epoch 141] train avg loss 0.00118345, dev acc 0.8496, dev avg loss 0.340132, throughput 3.25635K wps
[Epoch 142 Batch 30/62] avg loss 0.00122348, throughput 3.2703K wps
[Epoch 142 Batch 60/62] avg loss 0.00116421, throughput 3.16348K wps
Begin Testing...
[Epoch 142] train avg loss 0.00122732, dev acc 0.8496, dev avg loss 0.341952, throughput 3.22222K wps
[Epoch 143 Batch 30/62] avg loss 0.00112318, throughput 3.24672K wps
[Epoch 143 Batch 60/62] avg loss 0.00123521, throughput 3.2206K wps
Begin Testing...
[Epoch 143] train avg loss 0.00118937, dev acc 0.8437, dev avg loss 0.34011, throughput 3.23928K wps
[Epoch 144 Batch 30/62] avg loss 0.00111259, throughput 3.27706K wps
[Epoch 144 Batch 60/62] avg loss 0.00119659, throughput 3.16071K wps
Begin Testing...
[Epoch 144] train avg loss 0.00119549, dev acc 0.8466, dev avg loss 0.340388, throughput 3.22422K wps
[Epoch 145 Batch 30/62] avg loss 0.00110658, throughput 3.26845K wps
[Epoch 145 Batch 60/62] avg loss 0.0011254, throughput 3.21243K wps
Begin Testing...
[Epoch 145] train avg loss 0.00111968, dev acc 0.8466, dev avg loss 0.343084, throughput 3.24613K wps
[Epoch 146 Batch 30/62] avg loss 0.00101754, throughput 3.26999K wps
[Epoch 146 Batch 60/62] avg loss 0.00109438, throughput 3.21496K wps
Begin Testing...
[Epoch 146] train avg loss 0.00106141, dev acc 0.8496, dev avg loss 0.341961, throughput 3.24786K wps
[Epoch 147 Batch 30/62] avg loss 0.00106188, throughput 3.27187K wps
[Epoch 147 Batch 60/62] avg loss 0.00114334, throughput 3.16855K wps
Begin Testing...
[Epoch 147] train avg loss 0.00110893, dev acc 0.8496, dev avg loss 0.342779, throughput 3.22603K wps
[Epoch 148 Batch 30/62] avg loss 0.00111172, throughput 3.29632K wps
[Epoch 148 Batch 60/62] avg loss 0.00111183, throughput 3.16967K wps
Begin Testing...
[Epoch 148] train avg loss 0.00111702, dev acc 0.8555, dev avg loss 0.341739, throughput 3.23686K wps
Observed Improvement.
Begin Testing...
[Epoch 149 Batch 30/62] avg loss 0.00105433, throughput 3.28371K wps
[Epoch 149 Batch 60/62] avg loss 0.00113701, throughput 3.16029K wps
Begin Testing...
[Epoch 149] train avg loss 0.00112407, dev acc 0.8496, dev avg loss 0.341483, throughput 3.2273K wps
[Epoch 150 Batch 30/62] avg loss 0.00120487, throughput 3.27019K wps
[Epoch 150 Batch 60/62] avg loss 0.000971015, throughput 3.21639K wps
Begin Testing...
[Epoch 150] train avg loss 0.0010961, dev acc 0.8496, dev avg loss 0.341314, throughput 3.2487K wps
[Epoch 151 Batch 30/62] avg loss 0.00106268, throughput 3.2823K wps
[Epoch 151 Batch 60/62] avg loss 0.00104255, throughput 3.20805K wps
Begin Testing...
[Epoch 151] train avg loss 0.00106295, dev acc 0.8466, dev avg loss 0.341685, throughput 3.25039K wps
[Epoch 152 Batch 30/62] avg loss 0.000973639, throughput 3.2948K wps
[Epoch 152 Batch 60/62] avg loss 0.000944078, throughput 3.21382K wps
Begin Testing...
[Epoch 152] train avg loss 0.000970312, dev acc 0.8437, dev avg loss 0.343701, throughput 3.25918K wps
[Epoch 153 Batch 30/62] avg loss 0.000934971, throughput 3.2813K wps
[Epoch 153 Batch 60/62] avg loss 0.00106851, throughput 3.22658K wps
Begin Testing...
[Epoch 153] train avg loss 0.0010178, dev acc 0.8496, dev avg loss 0.342568, throughput 3.25872K wps
[Epoch 154 Batch 30/62] avg loss 0.00112719, throughput 3.25682K wps
[Epoch 154 Batch 60/62] avg loss 0.00106178, throughput 3.16287K wps
Begin Testing...
[Epoch 154] train avg loss 0.00110501, dev acc 0.8496, dev avg loss 0.34309, throughput 3.21558K wps
[Epoch 155 Batch 30/62] avg loss 0.00100207, throughput 3.25135K wps
[Epoch 155 Batch 60/62] avg loss 0.00102763, throughput 3.15865K wps
Begin Testing...
[Epoch 155] train avg loss 0.00104573, dev acc 0.8496, dev avg loss 0.342002, throughput 3.2116K wps
[Epoch 156 Batch 30/62] avg loss 0.000896598, throughput 3.24557K wps
[Epoch 156 Batch 60/62] avg loss 0.00106373, throughput 3.2061K wps
Begin Testing...
[Epoch 156] train avg loss 0.000985206, dev acc 0.8496, dev avg loss 0.341746, throughput 3.23281K wps
[Epoch 157 Batch 30/62] avg loss 0.000981454, throughput 3.26289K wps
[Epoch 157 Batch 60/62] avg loss 0.00101228, throughput 3.15976K wps
Begin Testing...
[Epoch 157] train avg loss 0.000993166, dev acc 0.8496, dev avg loss 0.341692, throughput 3.21631K wps
[Epoch 158 Batch 30/62] avg loss 0.00106181, throughput 3.25693K wps
[Epoch 158 Batch 60/62] avg loss 0.000931934, throughput 3.197K wps
Begin Testing...
[Epoch 158] train avg loss 0.0010187, dev acc 0.8496, dev avg loss 0.341877, throughput 3.23534K wps
[Epoch 159 Batch 30/62] avg loss 0.000943678, throughput 3.28211K wps
[Epoch 159 Batch 60/62] avg loss 0.000961083, throughput 3.1521K wps
Begin Testing...
[Epoch 159] train avg loss 0.00097757, dev acc 0.8525, dev avg loss 0.343581, throughput 3.22192K wps
[Epoch 160 Batch 30/62] avg loss 0.00092745, throughput 3.26828K wps
[Epoch 160 Batch 60/62] avg loss 0.000976141, throughput 3.22602K wps
Begin Testing...
[Epoch 160] train avg loss 0.000954505, dev acc 0.8496, dev avg loss 0.342723, throughput 3.25248K wps
[Epoch 161 Batch 30/62] avg loss 0.000851404, throughput 3.2787K wps
[Epoch 161 Batch 60/62] avg loss 0.00104231, throughput 3.21164K wps
Begin Testing...
[Epoch 161] train avg loss 0.000947883, dev acc 0.8555, dev avg loss 0.346472, throughput 3.25017K wps
Observed Improvement.
Begin Testing...
[Epoch 162 Batch 30/62] avg loss 0.000915935, throughput 3.30783K wps
[Epoch 162 Batch 60/62] avg loss 0.000988692, throughput 3.18816K wps
Begin Testing...
[Epoch 162] train avg loss 0.000951952, dev acc 0.8437, dev avg loss 0.34403, throughput 3.25505K wps
[Epoch 163 Batch 30/62] avg loss 0.000933059, throughput 3.30498K wps
[Epoch 163 Batch 60/62] avg loss 0.000927318, throughput 3.16638K wps
Begin Testing...
[Epoch 163] train avg loss 0.000948598, dev acc 0.8525, dev avg loss 0.343077, throughput 3.24067K wps
[Epoch 164 Batch 30/62] avg loss 0.000959348, throughput 3.29521K wps
[Epoch 164 Batch 60/62] avg loss 0.000851596, throughput 3.20678K wps
Begin Testing...
[Epoch 164] train avg loss 0.000901026, dev acc 0.8525, dev avg loss 0.344851, throughput 3.25798K wps
[Epoch 165 Batch 30/62] avg loss 0.000896554, throughput 3.29669K wps
[Epoch 165 Batch 60/62] avg loss 0.00084658, throughput 3.22739K wps
Begin Testing...
[Epoch 165] train avg loss 0.000880318, dev acc 0.8525, dev avg loss 0.343657, throughput 3.27038K wps
[Epoch 166 Batch 30/62] avg loss 0.000903747, throughput 3.30496K wps
[Epoch 166 Batch 60/62] avg loss 0.000792821, throughput 3.22124K wps
Begin Testing...
[Epoch 166] train avg loss 0.00085596, dev acc 0.8525, dev avg loss 0.344388, throughput 3.2701K wps
[Epoch 167 Batch 30/62] avg loss 0.000814398, throughput 3.30349K wps
[Epoch 167 Batch 60/62] avg loss 0.000858468, throughput 3.2345K wps
Begin Testing...
[Epoch 167] train avg loss 0.000832874, dev acc 0.8496, dev avg loss 0.343812, throughput 3.27716K wps
[Epoch 168 Batch 30/62] avg loss 0.000845042, throughput 3.32938K wps
[Epoch 168 Batch 60/62] avg loss 0.000904578, throughput 3.25065K wps
Begin Testing...
[Epoch 168] train avg loss 0.000892341, dev acc 0.8466, dev avg loss 0.345093, throughput 3.29532K wps
[Epoch 169 Batch 30/62] avg loss 0.000883103, throughput 3.30309K wps
[Epoch 169 Batch 60/62] avg loss 0.000822576, throughput 3.22911K wps
Begin Testing...
[Epoch 169] train avg loss 0.000866432, dev acc 0.8466, dev avg loss 0.345515, throughput 3.2742K wps
[Epoch 170 Batch 30/62] avg loss 0.000841103, throughput 3.30294K wps
[Epoch 170 Batch 60/62] avg loss 0.000783954, throughput 3.23194K wps
Begin Testing...
[Epoch 170] train avg loss 0.000823333, dev acc 0.8525, dev avg loss 0.344872, throughput 3.27348K wps
[Epoch 171 Batch 30/62] avg loss 0.000883716, throughput 3.29394K wps
[Epoch 171 Batch 60/62] avg loss 0.000815475, throughput 3.22431K wps
Begin Testing...
[Epoch 171] train avg loss 0.00084755, dev acc 0.8525, dev avg loss 0.34506, throughput 3.26588K wps
[Epoch 172 Batch 30/62] avg loss 0.000866507, throughput 3.29359K wps
[Epoch 172 Batch 60/62] avg loss 0.000851845, throughput 3.21502K wps
Begin Testing...
[Epoch 172] train avg loss 0.000871968, dev acc 0.8525, dev avg loss 0.346183, throughput 3.26022K wps
[Epoch 173 Batch 30/62] avg loss 0.000854901, throughput 3.29194K wps
[Epoch 173 Batch 60/62] avg loss 0.000862846, throughput 3.21001K wps
Begin Testing...
[Epoch 173] train avg loss 0.000858637, dev acc 0.8496, dev avg loss 0.344943, throughput 3.26111K wps
[Epoch 174 Batch 30/62] avg loss 0.000814364, throughput 3.31785K wps
[Epoch 174 Batch 60/62] avg loss 0.000846671, throughput 3.23189K wps
Begin Testing...
[Epoch 174] train avg loss 0.000834033, dev acc 0.8496, dev avg loss 0.344732, throughput 3.28094K wps
[Epoch 175 Batch 30/62] avg loss 0.00084613, throughput 3.29852K wps
[Epoch 175 Batch 60/62] avg loss 0.000844153, throughput 3.23329K wps
Begin Testing...
[Epoch 175] train avg loss 0.000846451, dev acc 0.8584, dev avg loss 0.345891, throughput 3.27168K wps
Observed Improvement.
Begin Testing...
[Epoch 176 Batch 30/62] avg loss 0.000860172, throughput 3.31199K wps
[Epoch 176 Batch 60/62] avg loss 0.00084035, throughput 3.22724K wps
Begin Testing...
[Epoch 176] train avg loss 0.00086672, dev acc 0.8466, dev avg loss 0.345166, throughput 3.27494K wps
[Epoch 177 Batch 30/62] avg loss 0.000722948, throughput 3.28945K wps
[Epoch 177 Batch 60/62] avg loss 0.000836503, throughput 3.21748K wps
Begin Testing...
[Epoch 177] train avg loss 0.000781123, dev acc 0.8466, dev avg loss 0.344365, throughput 3.25874K wps
[Epoch 178 Batch 30/62] avg loss 0.000764542, throughput 3.31346K wps
[Epoch 178 Batch 60/62] avg loss 0.000765563, throughput 3.22329K wps
Begin Testing...
[Epoch 178] train avg loss 0.000763563, dev acc 0.8525, dev avg loss 0.346392, throughput 3.27536K wps
[Epoch 179 Batch 30/62] avg loss 0.000811286, throughput 3.31654K wps
[Epoch 179 Batch 60/62] avg loss 0.000715919, throughput 3.22919K wps
Begin Testing...
[Epoch 179] train avg loss 0.000774862, dev acc 0.8555, dev avg loss 0.348367, throughput 3.2777K wps
[Epoch 180 Batch 30/62] avg loss 0.000696823, throughput 3.3104K wps
[Epoch 180 Batch 60/62] avg loss 0.000803336, throughput 3.2471K wps
Begin Testing...
[Epoch 180] train avg loss 0.000758519, dev acc 0.8496, dev avg loss 0.345944, throughput 3.28581K wps
[Epoch 181 Batch 30/62] avg loss 0.000767837, throughput 3.31031K wps
[Epoch 181 Batch 60/62] avg loss 0.000723816, throughput 3.24106K wps
Begin Testing...
[Epoch 181] train avg loss 0.000746746, dev acc 0.8525, dev avg loss 0.345864, throughput 3.28088K wps
[Epoch 182 Batch 30/62] avg loss 0.000721549, throughput 3.28405K wps
[Epoch 182 Batch 60/62] avg loss 0.000778338, throughput 3.22947K wps
Begin Testing...
[Epoch 182] train avg loss 0.000755079, dev acc 0.8496, dev avg loss 0.345693, throughput 3.26387K wps
[Epoch 183 Batch 30/62] avg loss 0.00072447, throughput 3.30586K wps
[Epoch 183 Batch 60/62] avg loss 0.000743345, throughput 3.18327K wps
Begin Testing...
[Epoch 183] train avg loss 0.000752239, dev acc 0.8555, dev avg loss 0.346102, throughput 3.24944K wps
[Epoch 184 Batch 30/62] avg loss 0.000775247, throughput 3.31481K wps
[Epoch 184 Batch 60/62] avg loss 0.00077893, throughput 3.21825K wps
Begin Testing...
[Epoch 184] train avg loss 0.000774407, dev acc 0.8555, dev avg loss 0.345241, throughput 3.27325K wps
[Epoch 185 Batch 30/62] avg loss 0.0007105, throughput 3.31086K wps
[Epoch 185 Batch 60/62] avg loss 0.000723204, throughput 3.21943K wps
Begin Testing...
[Epoch 185] train avg loss 0.000725065, dev acc 0.8555, dev avg loss 0.346558, throughput 3.27126K wps
[Epoch 186 Batch 30/62] avg loss 0.000661307, throughput 3.30543K wps
[Epoch 186 Batch 60/62] avg loss 0.000745419, throughput 3.23815K wps
Begin Testing...
[Epoch 186] train avg loss 0.00071352, dev acc 0.8466, dev avg loss 0.346294, throughput 3.27741K wps
[Epoch 187 Batch 30/62] avg loss 0.000688969, throughput 3.33158K wps
[Epoch 187 Batch 60/62] avg loss 0.000715608, throughput 3.21057K wps
Begin Testing...
[Epoch 187] train avg loss 0.000713161, dev acc 0.8466, dev avg loss 0.347011, throughput 3.27687K wps
[Epoch 188 Batch 30/62] avg loss 0.000711306, throughput 3.31796K wps
[Epoch 188 Batch 60/62] avg loss 0.000707317, throughput 3.24578K wps
Begin Testing...
[Epoch 188] train avg loss 0.000713817, dev acc 0.8437, dev avg loss 0.347159, throughput 3.28651K wps
[Epoch 189 Batch 30/62] avg loss 0.00070971, throughput 3.33583K wps
[Epoch 189 Batch 60/62] avg loss 0.000667546, throughput 3.2365K wps
Begin Testing...
[Epoch 189] train avg loss 0.000688979, dev acc 0.8496, dev avg loss 0.346572, throughput 3.29079K wps
[Epoch 190 Batch 30/62] avg loss 0.000657231, throughput 3.19446K wps
[Epoch 190 Batch 60/62] avg loss 0.000642676, throughput 3.23662K wps
Begin Testing...
[Epoch 190] train avg loss 0.00065079, dev acc 0.8555, dev avg loss 0.348196, throughput 3.2239K wps
[Epoch 191 Batch 30/62] avg loss 0.000728803, throughput 3.31563K wps
[Epoch 191 Batch 60/62] avg loss 0.000617561, throughput 3.23705K wps
Begin Testing...
[Epoch 191] train avg loss 0.000676455, dev acc 0.8555, dev avg loss 0.347856, throughput 3.28347K wps
[Epoch 192 Batch 30/62] avg loss 0.000632256, throughput 3.31819K wps
[Epoch 192 Batch 60/62] avg loss 0.000629428, throughput 3.24146K wps
Begin Testing...
[Epoch 192] train avg loss 0.000642416, dev acc 0.8466, dev avg loss 0.349594, throughput 3.28657K wps
[Epoch 193 Batch 30/62] avg loss 0.00064813, throughput 3.33302K wps
[Epoch 193 Batch 60/62] avg loss 0.000743202, throughput 3.24246K wps
Begin Testing...
[Epoch 193] train avg loss 0.000702278, dev acc 0.8496, dev avg loss 0.348201, throughput 3.29271K wps
[Epoch 194 Batch 30/62] avg loss 0.000721388, throughput 3.32434K wps
[Epoch 194 Batch 60/62] avg loss 0.000666139, throughput 3.24138K wps
Begin Testing...
[Epoch 194] train avg loss 0.000696048, dev acc 0.8555, dev avg loss 0.34939, throughput 3.28783K wps
[Epoch 195 Batch 30/62] avg loss 0.00060079, throughput 3.27294K wps
[Epoch 195 Batch 60/62] avg loss 0.000631133, throughput 3.23472K wps
Begin Testing...
[Epoch 195] train avg loss 0.000620766, dev acc 0.8555, dev avg loss 0.350398, throughput 3.26021K wps
[Epoch 196 Batch 30/62] avg loss 0.000621068, throughput 3.31609K wps
[Epoch 196 Batch 60/62] avg loss 0.000678999, throughput 3.2309K wps
Begin Testing...
[Epoch 196] train avg loss 0.000660011, dev acc 0.8466, dev avg loss 0.348, throughput 3.28095K wps
[Epoch 197 Batch 30/62] avg loss 0.000633607, throughput 3.32272K wps
[Epoch 197 Batch 60/62] avg loss 0.000634824, throughput 3.24026K wps
Begin Testing...
[Epoch 197] train avg loss 0.00064376, dev acc 0.8466, dev avg loss 0.347967, throughput 3.28649K wps
[Epoch 198 Batch 30/62] avg loss 0.00058103, throughput 3.318K wps
[Epoch 198 Batch 60/62] avg loss 0.000628005, throughput 3.22471K wps
Begin Testing...
[Epoch 198] train avg loss 0.00060593, dev acc 0.8496, dev avg loss 0.348249, throughput 3.27788K wps
[Epoch 199 Batch 30/62] avg loss 0.000645722, throughput 3.3036K wps
[Epoch 199 Batch 60/62] avg loss 0.000632027, throughput 3.21568K wps
Begin Testing...
[Epoch 199] train avg loss 0.000635151, dev acc 0.8496, dev avg loss 0.348341, throughput 3.26589K wps
Test loss 0.348589, test acc 0.8435
Total time cost 419.15s
[Epoch 0 Batch 30/62] avg loss 0.0133872, throughput 3.08643K wps
[Epoch 0 Batch 60/62] avg loss 0.0130518, throughput 3.22455K wps
Begin Testing...
[Epoch 0] train avg loss 0.0134241, dev acc 0.6578, dev avg loss 0.635898, throughput 3.16398K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130752, throughput 3.30218K wps
[Epoch 1 Batch 60/62] avg loss 0.0129574, throughput 3.23011K wps
Begin Testing...
[Epoch 1] train avg loss 0.0131625, dev acc 0.6578, dev avg loss 0.627297, throughput 3.27173K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0130436, throughput 3.30262K wps
[Epoch 2 Batch 60/62] avg loss 0.0126104, throughput 3.2365K wps
Begin Testing...
[Epoch 2] train avg loss 0.0130084, dev acc 0.6578, dev avg loss 0.621891, throughput 3.27541K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0126603, throughput 3.3106K wps
[Epoch 3 Batch 60/62] avg loss 0.0123294, throughput 3.22307K wps
Begin Testing...
[Epoch 3] train avg loss 0.012653, dev acc 0.6578, dev avg loss 0.612855, throughput 3.27177K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0123848, throughput 3.29232K wps
[Epoch 4 Batch 60/62] avg loss 0.0124521, throughput 3.22259K wps
Begin Testing...
[Epoch 4] train avg loss 0.0125916, dev acc 0.6578, dev avg loss 0.607868, throughput 3.26344K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0122161, throughput 3.31535K wps
[Epoch 5 Batch 60/62] avg loss 0.0121326, throughput 3.23208K wps
Begin Testing...
[Epoch 5] train avg loss 0.0123823, dev acc 0.6637, dev avg loss 0.604768, throughput 3.27914K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.012042, throughput 3.26025K wps
[Epoch 6 Batch 60/62] avg loss 0.012105, throughput 3.21346K wps
Begin Testing...
[Epoch 6] train avg loss 0.0122279, dev acc 0.6578, dev avg loss 0.59189, throughput 3.24507K wps
[Epoch 7 Batch 30/62] avg loss 0.0118146, throughput 3.29663K wps
[Epoch 7 Batch 60/62] avg loss 0.0119296, throughput 3.21937K wps
Begin Testing...
[Epoch 7] train avg loss 0.0120425, dev acc 0.6608, dev avg loss 0.584805, throughput 3.26357K wps
[Epoch 8 Batch 30/62] avg loss 0.0116738, throughput 3.30362K wps
[Epoch 8 Batch 60/62] avg loss 0.0117841, throughput 3.24334K wps
Begin Testing...
[Epoch 8] train avg loss 0.0118587, dev acc 0.6578, dev avg loss 0.576268, throughput 3.2811K wps
[Epoch 9 Batch 30/62] avg loss 0.0115351, throughput 3.30467K wps
[Epoch 9 Batch 60/62] avg loss 0.011411, throughput 3.21553K wps
Begin Testing...
[Epoch 9] train avg loss 0.011634, dev acc 0.6696, dev avg loss 0.568223, throughput 3.26638K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0112657, throughput 3.3033K wps
[Epoch 10 Batch 60/62] avg loss 0.0112403, throughput 3.21329K wps
Begin Testing...
[Epoch 10] train avg loss 0.0113868, dev acc 0.6696, dev avg loss 0.559592, throughput 3.26492K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0111209, throughput 3.29065K wps
[Epoch 11 Batch 60/62] avg loss 0.0110126, throughput 3.20681K wps
Begin Testing...
[Epoch 11] train avg loss 0.0112296, dev acc 0.7021, dev avg loss 0.550843, throughput 3.25428K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0110202, throughput 3.28165K wps
[Epoch 12 Batch 60/62] avg loss 0.0106829, throughput 3.22547K wps
Begin Testing...
[Epoch 12] train avg loss 0.0109901, dev acc 0.7198, dev avg loss 0.542508, throughput 3.26035K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.010662, throughput 3.29517K wps
[Epoch 13 Batch 60/62] avg loss 0.0104791, throughput 3.22508K wps
Begin Testing...
[Epoch 13] train avg loss 0.0107074, dev acc 0.7434, dev avg loss 0.534533, throughput 3.26606K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0105088, throughput 3.29455K wps
[Epoch 14 Batch 60/62] avg loss 0.0103709, throughput 3.22473K wps
Begin Testing...
[Epoch 14] train avg loss 0.0105791, dev acc 0.7227, dev avg loss 0.524756, throughput 3.26548K wps
[Epoch 15 Batch 30/62] avg loss 0.0101965, throughput 3.29455K wps
[Epoch 15 Batch 60/62] avg loss 0.0100784, throughput 3.21174K wps
Begin Testing...
[Epoch 15] train avg loss 0.0103146, dev acc 0.7729, dev avg loss 0.517253, throughput 3.25887K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.00991877, throughput 3.29799K wps
[Epoch 16 Batch 60/62] avg loss 0.0101939, throughput 3.23132K wps
Begin Testing...
[Epoch 16] train avg loss 0.0101726, dev acc 0.7404, dev avg loss 0.508453, throughput 3.27013K wps
[Epoch 17 Batch 30/62] avg loss 0.00994279, throughput 3.29238K wps
[Epoch 17 Batch 60/62] avg loss 0.00959039, throughput 3.20876K wps
Begin Testing...
[Epoch 17] train avg loss 0.00993636, dev acc 0.7729, dev avg loss 0.500393, throughput 3.25638K wps
Observed Improvement.
Begin Testing...
[Epoch 18 Batch 30/62] avg loss 0.00952514, throughput 3.28136K wps
[Epoch 18 Batch 60/62] avg loss 0.0095271, throughput 3.21936K wps
Begin Testing...
[Epoch 18] train avg loss 0.00965069, dev acc 0.7847, dev avg loss 0.497622, throughput 3.25618K wps
Observed Improvement.
Begin Testing...
[Epoch 19 Batch 30/62] avg loss 0.00934792, throughput 3.30574K wps
[Epoch 19 Batch 60/62] avg loss 0.00928945, throughput 3.23171K wps
Begin Testing...
[Epoch 19] train avg loss 0.00942503, dev acc 0.7906, dev avg loss 0.48672, throughput 3.27451K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.00898537, throughput 3.31492K wps
[Epoch 20 Batch 60/62] avg loss 0.00925153, throughput 3.21275K wps
Begin Testing...
[Epoch 20] train avg loss 0.00920402, dev acc 0.7906, dev avg loss 0.480389, throughput 3.26811K wps
Observed Improvement.
Begin Testing...
[Epoch 21 Batch 30/62] avg loss 0.00905873, throughput 3.27395K wps
[Epoch 21 Batch 60/62] avg loss 0.00904219, throughput 3.21918K wps
Begin Testing...
[Epoch 21] train avg loss 0.00910034, dev acc 0.7876, dev avg loss 0.473408, throughput 3.25328K wps
[Epoch 22 Batch 30/62] avg loss 0.00857867, throughput 3.27903K wps
[Epoch 22 Batch 60/62] avg loss 0.00858277, throughput 3.21189K wps
Begin Testing...
[Epoch 22] train avg loss 0.00870549, dev acc 0.7906, dev avg loss 0.467127, throughput 3.25072K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00873745, throughput 3.27305K wps
[Epoch 23 Batch 60/62] avg loss 0.0087071, throughput 3.19669K wps
Begin Testing...
[Epoch 23] train avg loss 0.00877512, dev acc 0.7906, dev avg loss 0.464014, throughput 3.24107K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.00846508, throughput 3.27368K wps
[Epoch 24 Batch 60/62] avg loss 0.00846575, throughput 3.2161K wps
Begin Testing...
[Epoch 24] train avg loss 0.00863805, dev acc 0.7994, dev avg loss 0.457813, throughput 3.25127K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00824231, throughput 3.30133K wps
[Epoch 25 Batch 60/62] avg loss 0.00837804, throughput 3.20178K wps
Begin Testing...
[Epoch 25] train avg loss 0.00837449, dev acc 0.7935, dev avg loss 0.45188, throughput 3.25895K wps
[Epoch 26 Batch 30/62] avg loss 0.00807293, throughput 3.28868K wps
[Epoch 26 Batch 60/62] avg loss 0.00819822, throughput 3.21215K wps
Begin Testing...
[Epoch 26] train avg loss 0.00825948, dev acc 0.7965, dev avg loss 0.447406, throughput 3.25598K wps
[Epoch 27 Batch 30/62] avg loss 0.00797055, throughput 3.30059K wps
[Epoch 27 Batch 60/62] avg loss 0.00792719, throughput 3.20996K wps
Begin Testing...
[Epoch 27] train avg loss 0.00806876, dev acc 0.8024, dev avg loss 0.444065, throughput 3.262K wps
Observed Improvement.
Begin Testing...
[Epoch 28 Batch 30/62] avg loss 0.00781206, throughput 3.25803K wps
[Epoch 28 Batch 60/62] avg loss 0.00774386, throughput 3.20489K wps
Begin Testing...
[Epoch 28] train avg loss 0.00797733, dev acc 0.7935, dev avg loss 0.439289, throughput 3.23725K wps
[Epoch 29 Batch 30/62] avg loss 0.00742249, throughput 3.26016K wps
[Epoch 29 Batch 60/62] avg loss 0.00776744, throughput 3.23771K wps
Begin Testing...
[Epoch 29] train avg loss 0.00767545, dev acc 0.8024, dev avg loss 0.435899, throughput 3.25537K wps
Observed Improvement.
Begin Testing...
[Epoch 30 Batch 30/62] avg loss 0.00769107, throughput 3.30071K wps
[Epoch 30 Batch 60/62] avg loss 0.00754736, throughput 3.22762K wps
Begin Testing...
[Epoch 30] train avg loss 0.00768421, dev acc 0.7935, dev avg loss 0.431962, throughput 3.27018K wps
[Epoch 31 Batch 30/62] avg loss 0.0075657, throughput 3.31025K wps
[Epoch 31 Batch 60/62] avg loss 0.00729583, throughput 3.19259K wps
Begin Testing...
[Epoch 31] train avg loss 0.00750881, dev acc 0.8171, dev avg loss 0.430783, throughput 3.25838K wps
Observed Improvement.
Begin Testing...
[Epoch 32 Batch 30/62] avg loss 0.00735187, throughput 3.32007K wps
[Epoch 32 Batch 60/62] avg loss 0.00720714, throughput 3.21171K wps
Begin Testing...
[Epoch 32] train avg loss 0.00738585, dev acc 0.7935, dev avg loss 0.429822, throughput 3.27224K wps
[Epoch 33 Batch 30/62] avg loss 0.00728453, throughput 3.29556K wps
[Epoch 33 Batch 60/62] avg loss 0.00709872, throughput 3.21276K wps
Begin Testing...
[Epoch 33] train avg loss 0.00725406, dev acc 0.8024, dev avg loss 0.422128, throughput 3.2616K wps
[Epoch 34 Batch 30/62] avg loss 0.00687495, throughput 3.29322K wps
[Epoch 34 Batch 60/62] avg loss 0.0070724, throughput 3.22137K wps
Begin Testing...
[Epoch 34] train avg loss 0.00702385, dev acc 0.8053, dev avg loss 0.420128, throughput 3.26341K wps
[Epoch 35 Batch 30/62] avg loss 0.00689106, throughput 3.26144K wps
[Epoch 35 Batch 60/62] avg loss 0.00674045, throughput 3.2151K wps
Begin Testing...
[Epoch 35] train avg loss 0.00699345, dev acc 0.8083, dev avg loss 0.416261, throughput 3.24645K wps
[Epoch 36 Batch 30/62] avg loss 0.00666183, throughput 3.28977K wps
[Epoch 36 Batch 60/62] avg loss 0.00690227, throughput 3.22588K wps
Begin Testing...
[Epoch 36] train avg loss 0.00684089, dev acc 0.8112, dev avg loss 0.413018, throughput 3.26316K wps
[Epoch 37 Batch 30/62] avg loss 0.00687858, throughput 3.27683K wps
[Epoch 37 Batch 60/62] avg loss 0.00628867, throughput 3.21284K wps
Begin Testing...
[Epoch 37] train avg loss 0.00670423, dev acc 0.8260, dev avg loss 0.411552, throughput 3.24957K wps
Observed Improvement.
Begin Testing...
[Epoch 38 Batch 30/62] avg loss 0.00669405, throughput 3.29333K wps
[Epoch 38 Batch 60/62] avg loss 0.00633397, throughput 3.16488K wps
Begin Testing...
[Epoch 38] train avg loss 0.00662436, dev acc 0.8289, dev avg loss 0.408142, throughput 3.23345K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.00635551, throughput 3.27943K wps
[Epoch 39 Batch 60/62] avg loss 0.0065783, throughput 3.16411K wps
Begin Testing...
[Epoch 39] train avg loss 0.00653212, dev acc 0.8201, dev avg loss 0.405189, throughput 3.22488K wps
[Epoch 40 Batch 30/62] avg loss 0.00629287, throughput 3.26219K wps
[Epoch 40 Batch 60/62] avg loss 0.00634437, throughput 3.14724K wps
Begin Testing...
[Epoch 40] train avg loss 0.0063631, dev acc 0.8112, dev avg loss 0.405724, throughput 3.2087K wps
[Epoch 41 Batch 30/62] avg loss 0.00618963, throughput 3.23643K wps
[Epoch 41 Batch 60/62] avg loss 0.00611566, throughput 3.16667K wps
Begin Testing...
[Epoch 41] train avg loss 0.00625739, dev acc 0.8260, dev avg loss 0.400499, throughput 3.20741K wps
[Epoch 42 Batch 30/62] avg loss 0.00602588, throughput 3.25854K wps
[Epoch 42 Batch 60/62] avg loss 0.0060395, throughput 3.16381K wps
Begin Testing...
[Epoch 42] train avg loss 0.00612719, dev acc 0.8230, dev avg loss 0.399078, throughput 3.21661K wps
[Epoch 43 Batch 30/62] avg loss 0.00611972, throughput 3.25751K wps
[Epoch 43 Batch 60/62] avg loss 0.00578485, throughput 3.18379K wps
Begin Testing...
[Epoch 43] train avg loss 0.0060777, dev acc 0.8260, dev avg loss 0.397134, throughput 3.22882K wps
[Epoch 44 Batch 30/62] avg loss 0.00576812, throughput 3.28043K wps
[Epoch 44 Batch 60/62] avg loss 0.00595795, throughput 3.16448K wps
Begin Testing...
[Epoch 44] train avg loss 0.0058914, dev acc 0.8083, dev avg loss 0.401912, throughput 3.22829K wps
[Epoch 45 Batch 30/62] avg loss 0.00575782, throughput 3.23329K wps
[Epoch 45 Batch 60/62] avg loss 0.00569315, throughput 3.17833K wps
Begin Testing...
[Epoch 45] train avg loss 0.00577917, dev acc 0.8230, dev avg loss 0.392463, throughput 3.21235K wps
[Epoch 46 Batch 30/62] avg loss 0.00552282, throughput 3.2617K wps
[Epoch 46 Batch 60/62] avg loss 0.00575031, throughput 3.19563K wps
Begin Testing...
[Epoch 46] train avg loss 0.00566125, dev acc 0.8260, dev avg loss 0.390385, throughput 3.23271K wps
[Epoch 47 Batch 30/62] avg loss 0.00553312, throughput 3.27308K wps
[Epoch 47 Batch 60/62] avg loss 0.0053793, throughput 3.18574K wps
Begin Testing...
[Epoch 47] train avg loss 0.00555353, dev acc 0.8289, dev avg loss 0.388854, throughput 3.23326K wps
Observed Improvement.
Begin Testing...
[Epoch 48 Batch 30/62] avg loss 0.00565766, throughput 3.24189K wps
[Epoch 48 Batch 60/62] avg loss 0.00532331, throughput 3.20462K wps
Begin Testing...
[Epoch 48] train avg loss 0.00551818, dev acc 0.8230, dev avg loss 0.387848, throughput 3.22958K wps
[Epoch 49 Batch 30/62] avg loss 0.00536617, throughput 3.28199K wps
[Epoch 49 Batch 60/62] avg loss 0.00522444, throughput 3.20661K wps
Begin Testing...
[Epoch 49] train avg loss 0.00530992, dev acc 0.8260, dev avg loss 0.385851, throughput 3.2514K wps
[Epoch 50 Batch 30/62] avg loss 0.00543898, throughput 3.29394K wps
[Epoch 50 Batch 60/62] avg loss 0.00516609, throughput 3.21655K wps
Begin Testing...
[Epoch 50] train avg loss 0.00537881, dev acc 0.8289, dev avg loss 0.383818, throughput 3.26054K wps
Observed Improvement.
Begin Testing...
[Epoch 51 Batch 30/62] avg loss 0.00515733, throughput 3.27472K wps
[Epoch 51 Batch 60/62] avg loss 0.00504491, throughput 3.1761K wps
Begin Testing...
[Epoch 51] train avg loss 0.00514159, dev acc 0.8230, dev avg loss 0.382382, throughput 3.23026K wps
[Epoch 52 Batch 30/62] avg loss 0.00494542, throughput 3.24376K wps
[Epoch 52 Batch 60/62] avg loss 0.00507453, throughput 3.16448K wps
Begin Testing...
[Epoch 52] train avg loss 0.00504202, dev acc 0.8230, dev avg loss 0.380914, throughput 3.21153K wps
[Epoch 53 Batch 30/62] avg loss 0.00512199, throughput 3.26659K wps
[Epoch 53 Batch 60/62] avg loss 0.00485396, throughput 3.19631K wps
Begin Testing...
[Epoch 53] train avg loss 0.00501005, dev acc 0.8230, dev avg loss 0.379121, throughput 3.23742K wps
[Epoch 54 Batch 30/62] avg loss 0.00493663, throughput 3.25574K wps
[Epoch 54 Batch 60/62] avg loss 0.00479115, throughput 3.19991K wps
Begin Testing...
[Epoch 54] train avg loss 0.0049475, dev acc 0.8260, dev avg loss 0.379057, throughput 3.23463K wps
[Epoch 55 Batch 30/62] avg loss 0.0047007, throughput 3.27444K wps
[Epoch 55 Batch 60/62] avg loss 0.00470006, throughput 3.17463K wps
Begin Testing...
[Epoch 55] train avg loss 0.00478609, dev acc 0.8260, dev avg loss 0.376825, throughput 3.23074K wps
[Epoch 56 Batch 30/62] avg loss 0.00466942, throughput 3.2257K wps
[Epoch 56 Batch 60/62] avg loss 0.00482936, throughput 3.14563K wps
Begin Testing...
[Epoch 56] train avg loss 0.00482369, dev acc 0.8201, dev avg loss 0.375369, throughput 3.19026K wps
[Epoch 57 Batch 30/62] avg loss 0.00472204, throughput 3.25081K wps
[Epoch 57 Batch 60/62] avg loss 0.00441983, throughput 3.15535K wps
Begin Testing...
[Epoch 57] train avg loss 0.00459871, dev acc 0.8230, dev avg loss 0.374835, throughput 3.20883K wps
[Epoch 58 Batch 30/62] avg loss 0.00444421, throughput 3.26324K wps
[Epoch 58 Batch 60/62] avg loss 0.0045645, throughput 3.19609K wps
Begin Testing...
[Epoch 58] train avg loss 0.00454812, dev acc 0.8201, dev avg loss 0.373517, throughput 3.2371K wps
[Epoch 59 Batch 30/62] avg loss 0.00443324, throughput 3.28029K wps
[Epoch 59 Batch 60/62] avg loss 0.00433557, throughput 3.17455K wps
Begin Testing...
[Epoch 59] train avg loss 0.00440945, dev acc 0.8201, dev avg loss 0.374655, throughput 3.23331K wps
[Epoch 60 Batch 30/62] avg loss 0.00447047, throughput 3.27687K wps
[Epoch 60 Batch 60/62] avg loss 0.00431754, throughput 3.17948K wps
Begin Testing...
[Epoch 60] train avg loss 0.00443918, dev acc 0.8289, dev avg loss 0.371798, throughput 3.23372K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00425252, throughput 3.27809K wps
[Epoch 61 Batch 60/62] avg loss 0.00412592, throughput 3.16743K wps
Begin Testing...
[Epoch 61] train avg loss 0.00422509, dev acc 0.8348, dev avg loss 0.370897, throughput 3.22787K wps
Observed Improvement.
Begin Testing...
[Epoch 62 Batch 30/62] avg loss 0.00409536, throughput 3.2666K wps
[Epoch 62 Batch 60/62] avg loss 0.00420131, throughput 3.19135K wps
Begin Testing...
[Epoch 62] train avg loss 0.00419516, dev acc 0.8289, dev avg loss 0.369508, throughput 3.23631K wps
[Epoch 63 Batch 30/62] avg loss 0.00407032, throughput 3.26723K wps
[Epoch 63 Batch 60/62] avg loss 0.00404456, throughput 3.18404K wps
Begin Testing...
[Epoch 63] train avg loss 0.00410071, dev acc 0.8319, dev avg loss 0.375088, throughput 3.23133K wps
[Epoch 64 Batch 30/62] avg loss 0.00400445, throughput 3.26354K wps
[Epoch 64 Batch 60/62] avg loss 0.00390673, throughput 3.18211K wps
Begin Testing...
[Epoch 64] train avg loss 0.00400526, dev acc 0.8289, dev avg loss 0.371475, throughput 3.23198K wps
[Epoch 65 Batch 30/62] avg loss 0.0039435, throughput 3.29102K wps
[Epoch 65 Batch 60/62] avg loss 0.0040716, throughput 3.1906K wps
Begin Testing...
[Epoch 65] train avg loss 0.00406084, dev acc 0.8260, dev avg loss 0.368071, throughput 3.24833K wps
[Epoch 66 Batch 30/62] avg loss 0.00394968, throughput 3.27868K wps
[Epoch 66 Batch 60/62] avg loss 0.00372068, throughput 3.17602K wps
Begin Testing...
[Epoch 66] train avg loss 0.00384899, dev acc 0.8289, dev avg loss 0.367477, throughput 3.23244K wps
[Epoch 67 Batch 30/62] avg loss 0.00405073, throughput 3.24632K wps
[Epoch 67 Batch 60/62] avg loss 0.00362065, throughput 3.198K wps
Begin Testing...
[Epoch 67] train avg loss 0.00384615, dev acc 0.8289, dev avg loss 0.366162, throughput 3.23K wps
[Epoch 68 Batch 30/62] avg loss 0.00372547, throughput 3.2898K wps
[Epoch 68 Batch 60/62] avg loss 0.00353941, throughput 3.179K wps
Begin Testing...
[Epoch 68] train avg loss 0.00375184, dev acc 0.8260, dev avg loss 0.365346, throughput 3.2407K wps
[Epoch 69 Batch 30/62] avg loss 0.00384722, throughput 3.25291K wps
[Epoch 69 Batch 60/62] avg loss 0.00344841, throughput 3.20194K wps
Begin Testing...
[Epoch 69] train avg loss 0.00369225, dev acc 0.8319, dev avg loss 0.369473, throughput 3.23379K wps
[Epoch 70 Batch 30/62] avg loss 0.00355392, throughput 3.24825K wps
[Epoch 70 Batch 60/62] avg loss 0.00380639, throughput 3.15187K wps
Begin Testing...
[Epoch 70] train avg loss 0.00371327, dev acc 0.8348, dev avg loss 0.367921, throughput 3.20519K wps
Observed Improvement.
Begin Testing...
[Epoch 71 Batch 30/62] avg loss 0.00348498, throughput 3.29937K wps
[Epoch 71 Batch 60/62] avg loss 0.00367283, throughput 3.20548K wps
Begin Testing...
[Epoch 71] train avg loss 0.0036373, dev acc 0.8289, dev avg loss 0.36314, throughput 3.25889K wps
[Epoch 72 Batch 30/62] avg loss 0.00319139, throughput 3.2643K wps
[Epoch 72 Batch 60/62] avg loss 0.00354687, throughput 3.17358K wps
Begin Testing...
[Epoch 72] train avg loss 0.00338537, dev acc 0.8319, dev avg loss 0.362705, throughput 3.22439K wps
[Epoch 73 Batch 30/62] avg loss 0.00345685, throughput 3.23598K wps
[Epoch 73 Batch 60/62] avg loss 0.00332934, throughput 3.1531K wps
Begin Testing...
[Epoch 73] train avg loss 0.00354902, dev acc 0.8260, dev avg loss 0.362061, throughput 3.20052K wps
[Epoch 74 Batch 30/62] avg loss 0.0034063, throughput 3.25031K wps
[Epoch 74 Batch 60/62] avg loss 0.00321087, throughput 3.18116K wps
Begin Testing...
[Epoch 74] train avg loss 0.00335961, dev acc 0.8378, dev avg loss 0.361896, throughput 3.22442K wps
Observed Improvement.
Begin Testing...
[Epoch 75 Batch 30/62] avg loss 0.00320247, throughput 3.29483K wps
[Epoch 75 Batch 60/62] avg loss 0.00336918, throughput 3.17771K wps
Begin Testing...
[Epoch 75] train avg loss 0.00332938, dev acc 0.8319, dev avg loss 0.3615, throughput 3.24162K wps
[Epoch 76 Batch 30/62] avg loss 0.00333652, throughput 3.26602K wps
[Epoch 76 Batch 60/62] avg loss 0.00299697, throughput 3.21006K wps
Begin Testing...
[Epoch 76] train avg loss 0.00320635, dev acc 0.8260, dev avg loss 0.361185, throughput 3.24187K wps
[Epoch 77 Batch 30/62] avg loss 0.00311758, throughput 3.27739K wps
[Epoch 77 Batch 60/62] avg loss 0.00338829, throughput 3.17056K wps
Begin Testing...
[Epoch 77] train avg loss 0.00334677, dev acc 0.8319, dev avg loss 0.365749, throughput 3.22866K wps
[Epoch 78 Batch 30/62] avg loss 0.00308198, throughput 3.25034K wps
[Epoch 78 Batch 60/62] avg loss 0.00303214, throughput 3.19906K wps
Begin Testing...
[Epoch 78] train avg loss 0.00310944, dev acc 0.8348, dev avg loss 0.362884, throughput 3.23014K wps
[Epoch 79 Batch 30/62] avg loss 0.00295494, throughput 3.26789K wps
[Epoch 79 Batch 60/62] avg loss 0.00304744, throughput 3.16947K wps
Begin Testing...
[Epoch 79] train avg loss 0.00306406, dev acc 0.8260, dev avg loss 0.360334, throughput 3.22454K wps
[Epoch 80 Batch 30/62] avg loss 0.00306061, throughput 3.25133K wps
[Epoch 80 Batch 60/62] avg loss 0.00289974, throughput 3.18401K wps
Begin Testing...
[Epoch 80] train avg loss 0.00304028, dev acc 0.8348, dev avg loss 0.362229, throughput 3.22302K wps
[Epoch 81 Batch 30/62] avg loss 0.00295852, throughput 3.27309K wps
[Epoch 81 Batch 60/62] avg loss 0.00282853, throughput 3.16429K wps
Begin Testing...
[Epoch 81] train avg loss 0.00300484, dev acc 0.8348, dev avg loss 0.359915, throughput 3.22378K wps
[Epoch 82 Batch 30/62] avg loss 0.00274497, throughput 3.25516K wps
[Epoch 82 Batch 60/62] avg loss 0.0030022, throughput 3.20869K wps
Begin Testing...
[Epoch 82] train avg loss 0.00292939, dev acc 0.8348, dev avg loss 0.363103, throughput 3.24077K wps
[Epoch 83 Batch 30/62] avg loss 0.00287035, throughput 3.28178K wps
[Epoch 83 Batch 60/62] avg loss 0.00269309, throughput 3.20613K wps
Begin Testing...
[Epoch 83] train avg loss 0.00281004, dev acc 0.8319, dev avg loss 0.361502, throughput 3.24535K wps
[Epoch 84 Batch 30/62] avg loss 0.00274051, throughput 3.27621K wps
[Epoch 84 Batch 60/62] avg loss 0.002895, throughput 3.17059K wps
Begin Testing...
[Epoch 84] train avg loss 0.00281974, dev acc 0.8319, dev avg loss 0.359445, throughput 3.22909K wps
[Epoch 85 Batch 30/62] avg loss 0.00286738, throughput 3.27439K wps
[Epoch 85 Batch 60/62] avg loss 0.00261588, throughput 3.20458K wps
Begin Testing...
[Epoch 85] train avg loss 0.00274917, dev acc 0.8319, dev avg loss 0.359838, throughput 3.24504K wps
[Epoch 86 Batch 30/62] avg loss 0.00269864, throughput 3.2504K wps
[Epoch 86 Batch 60/62] avg loss 0.00264878, throughput 3.17381K wps
Begin Testing...
[Epoch 86] train avg loss 0.00271098, dev acc 0.8319, dev avg loss 0.359749, throughput 3.21904K wps
[Epoch 87 Batch 30/62] avg loss 0.00252631, throughput 3.2297K wps
[Epoch 87 Batch 60/62] avg loss 0.00263471, throughput 3.20879K wps
Begin Testing...
[Epoch 87] train avg loss 0.00261728, dev acc 0.8319, dev avg loss 0.363341, throughput 3.22705K wps
[Epoch 88 Batch 30/62] avg loss 0.00244823, throughput 3.28145K wps
[Epoch 88 Batch 60/62] avg loss 0.00249956, throughput 3.1861K wps
Begin Testing...
[Epoch 88] train avg loss 0.00249439, dev acc 0.8378, dev avg loss 0.361687, throughput 3.24129K wps
Observed Improvement.
Begin Testing...
[Epoch 89 Batch 30/62] avg loss 0.00253092, throughput 3.27825K wps
[Epoch 89 Batch 60/62] avg loss 0.00238407, throughput 3.20683K wps
Begin Testing...
[Epoch 89] train avg loss 0.00250015, dev acc 0.8319, dev avg loss 0.360432, throughput 3.24871K wps
[Epoch 90 Batch 30/62] avg loss 0.0025346, throughput 3.27843K wps
[Epoch 90 Batch 60/62] avg loss 0.00247179, throughput 3.18365K wps
Begin Testing...
[Epoch 90] train avg loss 0.0025148, dev acc 0.8348, dev avg loss 0.361168, throughput 3.23938K wps
[Epoch 91 Batch 30/62] avg loss 0.00249412, throughput 3.24109K wps
[Epoch 91 Batch 60/62] avg loss 0.0023378, throughput 3.17049K wps
Begin Testing...
[Epoch 91] train avg loss 0.00244416, dev acc 0.8348, dev avg loss 0.361901, throughput 3.21295K wps
[Epoch 92 Batch 30/62] avg loss 0.00243472, throughput 3.25364K wps
[Epoch 92 Batch 60/62] avg loss 0.00254423, throughput 3.21311K wps
Begin Testing...
[Epoch 92] train avg loss 0.00250474, dev acc 0.8348, dev avg loss 0.360168, throughput 3.23835K wps
[Epoch 93 Batch 30/62] avg loss 0.00243469, throughput 3.26321K wps
[Epoch 93 Batch 60/62] avg loss 0.00231743, throughput 3.16141K wps
Begin Testing...
[Epoch 93] train avg loss 0.00240666, dev acc 0.8348, dev avg loss 0.360085, throughput 3.21837K wps
[Epoch 94 Batch 30/62] avg loss 0.00223614, throughput 3.2536K wps
[Epoch 94 Batch 60/62] avg loss 0.00236966, throughput 3.17445K wps
Begin Testing...
[Epoch 94] train avg loss 0.00231164, dev acc 0.8378, dev avg loss 0.362197, throughput 3.22193K wps
Observed Improvement.
Begin Testing...
[Epoch 95 Batch 30/62] avg loss 0.0021205, throughput 3.24117K wps
[Epoch 95 Batch 60/62] avg loss 0.00239506, throughput 3.19241K wps
Begin Testing...
[Epoch 95] train avg loss 0.00229588, dev acc 0.8348, dev avg loss 0.360884, throughput 3.22253K wps
[Epoch 96 Batch 30/62] avg loss 0.0022535, throughput 3.27421K wps
[Epoch 96 Batch 60/62] avg loss 0.0021977, throughput 3.18676K wps
Begin Testing...
[Epoch 96] train avg loss 0.00230408, dev acc 0.8407, dev avg loss 0.359243, throughput 3.23597K wps
Observed Improvement.
Begin Testing...
[Epoch 97 Batch 30/62] avg loss 0.00212519, throughput 3.26671K wps
[Epoch 97 Batch 60/62] avg loss 0.00201879, throughput 3.21661K wps
Begin Testing...
[Epoch 97] train avg loss 0.00209947, dev acc 0.8378, dev avg loss 0.361056, throughput 3.24701K wps
[Epoch 98 Batch 30/62] avg loss 0.00217483, throughput 3.249K wps
[Epoch 98 Batch 60/62] avg loss 0.00225991, throughput 3.16696K wps
Begin Testing...
[Epoch 98] train avg loss 0.002239, dev acc 0.8378, dev avg loss 0.360421, throughput 3.21381K wps
[Epoch 99 Batch 30/62] avg loss 0.00222016, throughput 3.24599K wps
[Epoch 99 Batch 60/62] avg loss 0.00201434, throughput 3.15801K wps
Begin Testing...
[Epoch 99] train avg loss 0.00213819, dev acc 0.8378, dev avg loss 0.363279, throughput 3.20886K wps
[Epoch 100 Batch 30/62] avg loss 0.00206842, throughput 3.26877K wps
[Epoch 100 Batch 60/62] avg loss 0.00211289, throughput 3.22163K wps
Begin Testing...
[Epoch 100] train avg loss 0.00210201, dev acc 0.8348, dev avg loss 0.361603, throughput 3.25048K wps
[Epoch 101 Batch 30/62] avg loss 0.00221842, throughput 3.26259K wps
[Epoch 101 Batch 60/62] avg loss 0.00194909, throughput 3.19863K wps
Begin Testing...
[Epoch 101] train avg loss 0.00209462, dev acc 0.8378, dev avg loss 0.362505, throughput 3.23602K wps
[Epoch 102 Batch 30/62] avg loss 0.00201441, throughput 3.27499K wps
[Epoch 102 Batch 60/62] avg loss 0.00201654, throughput 3.1713K wps
Begin Testing...
[Epoch 102] train avg loss 0.00202433, dev acc 0.8348, dev avg loss 0.361244, throughput 3.22802K wps
[Epoch 103 Batch 30/62] avg loss 0.00210826, throughput 3.23619K wps
[Epoch 103 Batch 60/62] avg loss 0.00197868, throughput 3.21386K wps
Begin Testing...
[Epoch 103] train avg loss 0.00207582, dev acc 0.8437, dev avg loss 0.361394, throughput 3.23086K wps
Observed Improvement.
Begin Testing...
[Epoch 104 Batch 30/62] avg loss 0.00187779, throughput 3.29684K wps
[Epoch 104 Batch 60/62] avg loss 0.0019615, throughput 3.19286K wps
Begin Testing...
[Epoch 104] train avg loss 0.00197961, dev acc 0.8407, dev avg loss 0.361917, throughput 3.25247K wps
[Epoch 105 Batch 30/62] avg loss 0.0020734, throughput 3.28586K wps
[Epoch 105 Batch 60/62] avg loss 0.00205472, throughput 3.17726K wps
Begin Testing...
[Epoch 105] train avg loss 0.00207504, dev acc 0.8378, dev avg loss 0.362045, throughput 3.2383K wps
[Epoch 106 Batch 30/62] avg loss 0.00176514, throughput 3.24645K wps
[Epoch 106 Batch 60/62] avg loss 0.00184411, throughput 3.20204K wps
Begin Testing...
[Epoch 106] train avg loss 0.00181596, dev acc 0.8378, dev avg loss 0.362542, throughput 3.23222K wps
[Epoch 107 Batch 30/62] avg loss 0.00191532, throughput 3.27407K wps
[Epoch 107 Batch 60/62] avg loss 0.00168606, throughput 3.15676K wps
Begin Testing...
[Epoch 107] train avg loss 0.00182474, dev acc 0.8466, dev avg loss 0.362299, throughput 3.21928K wps
Observed Improvement.
Begin Testing...
[Epoch 108 Batch 30/62] avg loss 0.00173952, throughput 3.28295K wps
[Epoch 108 Batch 60/62] avg loss 0.00179393, throughput 3.1625K wps
Begin Testing...
[Epoch 108] train avg loss 0.00179724, dev acc 0.8437, dev avg loss 0.362786, throughput 3.22886K wps
[Epoch 109 Batch 30/62] avg loss 0.00186533, throughput 3.25048K wps
[Epoch 109 Batch 60/62] avg loss 0.00180994, throughput 3.16668K wps
Begin Testing...
[Epoch 109] train avg loss 0.00186824, dev acc 0.8348, dev avg loss 0.362917, throughput 3.21547K wps
[Epoch 110 Batch 30/62] avg loss 0.00174997, throughput 3.26138K wps
[Epoch 110 Batch 60/62] avg loss 0.00180282, throughput 3.20279K wps
Begin Testing...
[Epoch 110] train avg loss 0.00179194, dev acc 0.8348, dev avg loss 0.367044, throughput 3.23792K wps
[Epoch 111 Batch 30/62] avg loss 0.00186936, throughput 3.24898K wps
[Epoch 111 Batch 60/62] avg loss 0.00163581, throughput 3.16354K wps
Begin Testing...
[Epoch 111] train avg loss 0.00179187, dev acc 0.8378, dev avg loss 0.363472, throughput 3.21152K wps
[Epoch 112 Batch 30/62] avg loss 0.00179993, throughput 3.25776K wps
[Epoch 112 Batch 60/62] avg loss 0.00164556, throughput 3.20923K wps
Begin Testing...
[Epoch 112] train avg loss 0.00172533, dev acc 0.8407, dev avg loss 0.364234, throughput 3.23896K wps
[Epoch 113 Batch 30/62] avg loss 0.00152962, throughput 3.25928K wps
[Epoch 113 Batch 60/62] avg loss 0.00169794, throughput 3.13963K wps
Begin Testing...
[Epoch 113] train avg loss 0.00161702, dev acc 0.8407, dev avg loss 0.36494, throughput 3.20501K wps
[Epoch 114 Batch 30/62] avg loss 0.00176695, throughput 3.25749K wps
[Epoch 114 Batch 60/62] avg loss 0.00175273, throughput 3.16602K wps
Begin Testing...
[Epoch 114] train avg loss 0.00180888, dev acc 0.8319, dev avg loss 0.365121, throughput 3.21781K wps
[Epoch 115 Batch 30/62] avg loss 0.0016925, throughput 3.24259K wps
[Epoch 115 Batch 60/62] avg loss 0.00164298, throughput 3.1762K wps
Begin Testing...
[Epoch 115] train avg loss 0.00166813, dev acc 0.8407, dev avg loss 0.364746, throughput 3.21678K wps
[Epoch 116 Batch 30/62] avg loss 0.00168057, throughput 3.28557K wps
[Epoch 116 Batch 60/62] avg loss 0.0016871, throughput 3.17783K wps
Begin Testing...
[Epoch 116] train avg loss 0.00174845, dev acc 0.8378, dev avg loss 0.378836, throughput 3.23519K wps
[Epoch 117 Batch 30/62] avg loss 0.00153429, throughput 3.24645K wps
[Epoch 117 Batch 60/62] avg loss 0.00156017, throughput 3.16731K wps
Begin Testing...
[Epoch 117] train avg loss 0.00157764, dev acc 0.8437, dev avg loss 0.365858, throughput 3.21283K wps
[Epoch 118 Batch 30/62] avg loss 0.00152958, throughput 3.23852K wps
[Epoch 118 Batch 60/62] avg loss 0.00155224, throughput 3.16543K wps
Begin Testing...
[Epoch 118] train avg loss 0.00157567, dev acc 0.8348, dev avg loss 0.366869, throughput 3.20785K wps
[Epoch 119 Batch 30/62] avg loss 0.00146014, throughput 3.24634K wps
[Epoch 119 Batch 60/62] avg loss 0.00163058, throughput 3.20316K wps
Begin Testing...
[Epoch 119] train avg loss 0.00155596, dev acc 0.8378, dev avg loss 0.366889, throughput 3.23097K wps
[Epoch 120 Batch 30/62] avg loss 0.00152028, throughput 3.27081K wps
[Epoch 120 Batch 60/62] avg loss 0.00156728, throughput 3.17909K wps
Begin Testing...
[Epoch 120] train avg loss 0.00154411, dev acc 0.8407, dev avg loss 0.367065, throughput 3.2298K wps
[Epoch 121 Batch 30/62] avg loss 0.00152559, throughput 3.23913K wps
[Epoch 121 Batch 60/62] avg loss 0.00142495, throughput 3.16407K wps
Begin Testing...
[Epoch 121] train avg loss 0.00150231, dev acc 0.8437, dev avg loss 0.366289, throughput 3.21053K wps
[Epoch 122 Batch 30/62] avg loss 0.00139608, throughput 3.29715K wps
[Epoch 122 Batch 60/62] avg loss 0.00140801, throughput 3.17065K wps
Begin Testing...
[Epoch 122] train avg loss 0.00142311, dev acc 0.8407, dev avg loss 0.36659, throughput 3.23911K wps
[Epoch 123 Batch 30/62] avg loss 0.00138803, throughput 3.24896K wps
[Epoch 123 Batch 60/62] avg loss 0.00148291, throughput 3.21209K wps
Begin Testing...
[Epoch 123] train avg loss 0.00145575, dev acc 0.8407, dev avg loss 0.366602, throughput 3.23598K wps
[Epoch 124 Batch 30/62] avg loss 0.00144044, throughput 3.28483K wps
[Epoch 124 Batch 60/62] avg loss 0.00147201, throughput 3.21472K wps
Begin Testing...
[Epoch 124] train avg loss 0.00147281, dev acc 0.8378, dev avg loss 0.371841, throughput 3.25701K wps
[Epoch 125 Batch 30/62] avg loss 0.00130165, throughput 3.2854K wps
[Epoch 125 Batch 60/62] avg loss 0.00147396, throughput 3.21586K wps
Begin Testing...
[Epoch 125] train avg loss 0.00141363, dev acc 0.8319, dev avg loss 0.37024, throughput 3.25656K wps
[Epoch 126 Batch 30/62] avg loss 0.00151178, throughput 3.28037K wps
[Epoch 126 Batch 60/62] avg loss 0.00129502, throughput 3.21971K wps
Begin Testing...
[Epoch 126] train avg loss 0.00141326, dev acc 0.8437, dev avg loss 0.366074, throughput 3.25514K wps
[Epoch 127 Batch 30/62] avg loss 0.00141413, throughput 3.28032K wps
[Epoch 127 Batch 60/62] avg loss 0.00144149, throughput 3.21514K wps
Begin Testing...
[Epoch 127] train avg loss 0.00146857, dev acc 0.8407, dev avg loss 0.366589, throughput 3.25254K wps
[Epoch 128 Batch 30/62] avg loss 0.00131687, throughput 3.27597K wps
[Epoch 128 Batch 60/62] avg loss 0.00140626, throughput 3.17213K wps
Begin Testing...
[Epoch 128] train avg loss 0.00138389, dev acc 0.8407, dev avg loss 0.367565, throughput 3.23102K wps
[Epoch 129 Batch 30/62] avg loss 0.00129274, throughput 3.31784K wps
[Epoch 129 Batch 60/62] avg loss 0.00130217, throughput 3.1849K wps
Begin Testing...
[Epoch 129] train avg loss 0.00130613, dev acc 0.8378, dev avg loss 0.369512, throughput 3.25797K wps
[Epoch 130 Batch 30/62] avg loss 0.00126095, throughput 3.32579K wps
[Epoch 130 Batch 60/62] avg loss 0.00148066, throughput 3.23621K wps
Begin Testing...
[Epoch 130] train avg loss 0.00138987, dev acc 0.8378, dev avg loss 0.369557, throughput 3.28557K wps
[Epoch 131 Batch 30/62] avg loss 0.00123771, throughput 3.29022K wps
[Epoch 131 Batch 60/62] avg loss 0.00140488, throughput 3.2247K wps
Begin Testing...
[Epoch 131] train avg loss 0.00134269, dev acc 0.8407, dev avg loss 0.370188, throughput 3.26326K wps
[Epoch 132 Batch 30/62] avg loss 0.00122028, throughput 3.28342K wps
[Epoch 132 Batch 60/62] avg loss 0.00134227, throughput 3.21916K wps
Begin Testing...
[Epoch 132] train avg loss 0.00129661, dev acc 0.8378, dev avg loss 0.369575, throughput 3.25708K wps
[Epoch 133 Batch 30/62] avg loss 0.00116055, throughput 3.27233K wps
[Epoch 133 Batch 60/62] avg loss 0.00124046, throughput 3.21601K wps
Begin Testing...
[Epoch 133] train avg loss 0.00123646, dev acc 0.8407, dev avg loss 0.371238, throughput 3.25018K wps
[Epoch 134 Batch 30/62] avg loss 0.00119029, throughput 3.27822K wps
[Epoch 134 Batch 60/62] avg loss 0.00127908, throughput 3.22721K wps
Begin Testing...
[Epoch 134] train avg loss 0.00124735, dev acc 0.8378, dev avg loss 0.370567, throughput 3.25877K wps
[Epoch 135 Batch 30/62] avg loss 0.00118546, throughput 3.28294K wps
[Epoch 135 Batch 60/62] avg loss 0.00128044, throughput 3.24054K wps
Begin Testing...
[Epoch 135] train avg loss 0.0012489, dev acc 0.8437, dev avg loss 0.370408, throughput 3.26766K wps
[Epoch 136 Batch 30/62] avg loss 0.00122916, throughput 3.33142K wps
[Epoch 136 Batch 60/62] avg loss 0.00125928, throughput 3.23789K wps
Begin Testing...
[Epoch 136] train avg loss 0.001266, dev acc 0.8407, dev avg loss 0.37068, throughput 3.29128K wps
[Epoch 137 Batch 30/62] avg loss 0.00123101, throughput 3.31034K wps
[Epoch 137 Batch 60/62] avg loss 0.00122041, throughput 3.24227K wps
Begin Testing...
[Epoch 137] train avg loss 0.00124918, dev acc 0.8437, dev avg loss 0.371353, throughput 3.28253K wps
[Epoch 138 Batch 30/62] avg loss 0.00115462, throughput 3.3222K wps
[Epoch 138 Batch 60/62] avg loss 0.00117966, throughput 3.23403K wps
Begin Testing...
[Epoch 138] train avg loss 0.00118257, dev acc 0.8378, dev avg loss 0.372547, throughput 3.28433K wps
[Epoch 139 Batch 30/62] avg loss 0.00115512, throughput 3.30454K wps
[Epoch 139 Batch 60/62] avg loss 0.00109367, throughput 3.2339K wps
Begin Testing...
[Epoch 139] train avg loss 0.0011441, dev acc 0.8378, dev avg loss 0.374545, throughput 3.27442K wps
[Epoch 140 Batch 30/62] avg loss 0.00122866, throughput 3.3196K wps
[Epoch 140 Batch 60/62] avg loss 0.00115584, throughput 3.22832K wps
Begin Testing...
[Epoch 140] train avg loss 0.0012239, dev acc 0.8319, dev avg loss 0.378323, throughput 3.2806K wps
[Epoch 141 Batch 30/62] avg loss 0.00106787, throughput 3.30811K wps
[Epoch 141 Batch 60/62] avg loss 0.00119644, throughput 3.24824K wps
Begin Testing...
[Epoch 141] train avg loss 0.00112582, dev acc 0.8407, dev avg loss 0.373728, throughput 3.28399K wps
[Epoch 142 Batch 30/62] avg loss 0.00106524, throughput 3.3182K wps
[Epoch 142 Batch 60/62] avg loss 0.00114566, throughput 3.2464K wps
Begin Testing...
[Epoch 142] train avg loss 0.00113802, dev acc 0.8378, dev avg loss 0.375464, throughput 3.28774K wps
[Epoch 143 Batch 30/62] avg loss 0.00101317, throughput 3.30644K wps
[Epoch 143 Batch 60/62] avg loss 0.00118732, throughput 3.23623K wps
Begin Testing...
[Epoch 143] train avg loss 0.00111882, dev acc 0.8407, dev avg loss 0.37444, throughput 3.27663K wps
[Epoch 144 Batch 30/62] avg loss 0.00115249, throughput 3.30389K wps
[Epoch 144 Batch 60/62] avg loss 0.001014, throughput 3.2327K wps
Begin Testing...
[Epoch 144] train avg loss 0.00108281, dev acc 0.8407, dev avg loss 0.374566, throughput 3.27632K wps
[Epoch 145 Batch 30/62] avg loss 0.00103327, throughput 3.29547K wps
[Epoch 145 Batch 60/62] avg loss 0.00112029, throughput 3.22391K wps
Begin Testing...
[Epoch 145] train avg loss 0.00111585, dev acc 0.8348, dev avg loss 0.376751, throughput 3.26556K wps
[Epoch 146 Batch 30/62] avg loss 0.00105699, throughput 3.29141K wps
[Epoch 146 Batch 60/62] avg loss 0.00106985, throughput 3.21659K wps
Begin Testing...
[Epoch 146] train avg loss 0.00108115, dev acc 0.8437, dev avg loss 0.374855, throughput 3.25953K wps
[Epoch 147 Batch 30/62] avg loss 0.00110737, throughput 3.30036K wps
[Epoch 147 Batch 60/62] avg loss 0.000963251, throughput 3.2398K wps
Begin Testing...
[Epoch 147] train avg loss 0.00104808, dev acc 0.8319, dev avg loss 0.379989, throughput 3.27492K wps
[Epoch 148 Batch 30/62] avg loss 0.00116024, throughput 3.29581K wps
[Epoch 148 Batch 60/62] avg loss 0.00110714, throughput 3.23156K wps
Begin Testing...
[Epoch 148] train avg loss 0.00113611, dev acc 0.8407, dev avg loss 0.376086, throughput 3.27185K wps
[Epoch 149 Batch 30/62] avg loss 0.00102838, throughput 3.31598K wps
[Epoch 149 Batch 60/62] avg loss 0.00105356, throughput 3.2232K wps
Begin Testing...
[Epoch 149] train avg loss 0.00103994, dev acc 0.8348, dev avg loss 0.377664, throughput 3.27534K wps
[Epoch 150 Batch 30/62] avg loss 0.000977162, throughput 3.2974K wps
[Epoch 150 Batch 60/62] avg loss 0.00103163, throughput 3.2198K wps
Begin Testing...
[Epoch 150] train avg loss 0.00102405, dev acc 0.8466, dev avg loss 0.376244, throughput 3.26447K wps
Observed Improvement.
Begin Testing...
[Epoch 151 Batch 30/62] avg loss 0.000976918, throughput 3.30534K wps
[Epoch 151 Batch 60/62] avg loss 0.00102961, throughput 3.23185K wps
Begin Testing...
[Epoch 151] train avg loss 0.00101427, dev acc 0.8378, dev avg loss 0.378075, throughput 3.27501K wps
[Epoch 152 Batch 30/62] avg loss 0.000939013, throughput 3.29989K wps
[Epoch 152 Batch 60/62] avg loss 0.00110095, throughput 3.23949K wps
Begin Testing...
[Epoch 152] train avg loss 0.00102598, dev acc 0.8466, dev avg loss 0.375973, throughput 3.27638K wps
Observed Improvement.
Begin Testing...
[Epoch 153 Batch 30/62] avg loss 0.00097048, throughput 3.32956K wps
[Epoch 153 Batch 60/62] avg loss 0.00100695, throughput 3.25438K wps
Begin Testing...
[Epoch 153] train avg loss 0.00100063, dev acc 0.8348, dev avg loss 0.377543, throughput 3.29817K wps
[Epoch 154 Batch 30/62] avg loss 0.000988961, throughput 3.3102K wps
[Epoch 154 Batch 60/62] avg loss 0.000982844, throughput 3.23481K wps
Begin Testing...
[Epoch 154] train avg loss 0.000995654, dev acc 0.8466, dev avg loss 0.377553, throughput 3.27942K wps
Observed Improvement.
Begin Testing...
[Epoch 155 Batch 30/62] avg loss 0.00091349, throughput 3.33406K wps
[Epoch 155 Batch 60/62] avg loss 0.000895146, throughput 3.2384K wps
Begin Testing...
[Epoch 155] train avg loss 0.000936959, dev acc 0.8466, dev avg loss 0.377592, throughput 3.29141K wps
Observed Improvement.
Begin Testing...
[Epoch 156 Batch 30/62] avg loss 0.000921441, throughput 3.30659K wps
[Epoch 156 Batch 60/62] avg loss 0.000971944, throughput 3.23177K wps
Begin Testing...
[Epoch 156] train avg loss 0.000986172, dev acc 0.8437, dev avg loss 0.378308, throughput 3.27494K wps
[Epoch 157 Batch 30/62] avg loss 0.000952844, throughput 3.32992K wps
[Epoch 157 Batch 60/62] avg loss 0.000985985, throughput 3.21564K wps
Begin Testing...
[Epoch 157] train avg loss 0.000975615, dev acc 0.8407, dev avg loss 0.377514, throughput 3.27919K wps
[Epoch 158 Batch 30/62] avg loss 0.000914234, throughput 3.29804K wps
[Epoch 158 Batch 60/62] avg loss 0.000961194, throughput 3.22884K wps
Begin Testing...
[Epoch 158] train avg loss 0.000928249, dev acc 0.8407, dev avg loss 0.377696, throughput 3.26854K wps
[Epoch 159 Batch 30/62] avg loss 0.000912449, throughput 3.30174K wps
[Epoch 159 Batch 60/62] avg loss 0.000869907, throughput 3.2202K wps
Begin Testing...
[Epoch 159] train avg loss 0.000925986, dev acc 0.8378, dev avg loss 0.379219, throughput 3.2665K wps
[Epoch 160 Batch 30/62] avg loss 0.000876124, throughput 3.28552K wps
[Epoch 160 Batch 60/62] avg loss 0.000925682, throughput 3.22383K wps
Begin Testing...
[Epoch 160] train avg loss 0.000907221, dev acc 0.8437, dev avg loss 0.379053, throughput 3.2606K wps
[Epoch 161 Batch 30/62] avg loss 0.000986955, throughput 3.32979K wps
[Epoch 161 Batch 60/62] avg loss 0.000806778, throughput 3.2238K wps
Begin Testing...
[Epoch 161] train avg loss 0.000909057, dev acc 0.8437, dev avg loss 0.378673, throughput 3.28268K wps
[Epoch 162 Batch 30/62] avg loss 0.000951949, throughput 3.31K wps
[Epoch 162 Batch 60/62] avg loss 0.000906412, throughput 3.22871K wps
Begin Testing...
[Epoch 162] train avg loss 0.000933104, dev acc 0.8378, dev avg loss 0.380132, throughput 3.27479K wps
[Epoch 163 Batch 30/62] avg loss 0.000836694, throughput 3.30279K wps
[Epoch 163 Batch 60/62] avg loss 0.000855998, throughput 3.22534K wps
Begin Testing...
[Epoch 163] train avg loss 0.000849215, dev acc 0.8378, dev avg loss 0.381812, throughput 3.26994K wps
[Epoch 164 Batch 30/62] avg loss 0.000950008, throughput 3.32819K wps
[Epoch 164 Batch 60/62] avg loss 0.000832332, throughput 3.22822K wps
Begin Testing...
[Epoch 164] train avg loss 0.000902662, dev acc 0.8496, dev avg loss 0.379724, throughput 3.28327K wps
Observed Improvement.
Begin Testing...
[Epoch 165 Batch 30/62] avg loss 0.000835204, throughput 3.30331K wps
[Epoch 165 Batch 60/62] avg loss 0.000792747, throughput 3.24341K wps
Begin Testing...
[Epoch 165] train avg loss 0.000824242, dev acc 0.8378, dev avg loss 0.381678, throughput 3.27914K wps
[Epoch 166 Batch 30/62] avg loss 0.000804186, throughput 3.31132K wps
[Epoch 166 Batch 60/62] avg loss 0.000847822, throughput 3.25264K wps
Begin Testing...
[Epoch 166] train avg loss 0.000850273, dev acc 0.8348, dev avg loss 0.384902, throughput 3.28971K wps
[Epoch 167 Batch 30/62] avg loss 0.000835766, throughput 3.31736K wps
[Epoch 167 Batch 60/62] avg loss 0.000832462, throughput 3.25023K wps
Begin Testing...
[Epoch 167] train avg loss 0.000851702, dev acc 0.8378, dev avg loss 0.386021, throughput 3.28985K wps
[Epoch 168 Batch 30/62] avg loss 0.000795884, throughput 3.33526K wps
[Epoch 168 Batch 60/62] avg loss 0.000825457, throughput 3.2383K wps
Begin Testing...
[Epoch 168] train avg loss 0.000822247, dev acc 0.8378, dev avg loss 0.384173, throughput 3.29179K wps
[Epoch 169 Batch 30/62] avg loss 0.000890113, throughput 3.32063K wps
[Epoch 169 Batch 60/62] avg loss 0.000785945, throughput 3.24271K wps
Begin Testing...
[Epoch 169] train avg loss 0.000844904, dev acc 0.8378, dev avg loss 0.386238, throughput 3.28863K wps
[Epoch 170 Batch 30/62] avg loss 0.000803701, throughput 3.30258K wps
[Epoch 170 Batch 60/62] avg loss 0.00074382, throughput 3.2252K wps
Begin Testing...
[Epoch 170] train avg loss 0.000781525, dev acc 0.8407, dev avg loss 0.383302, throughput 3.26872K wps
[Epoch 171 Batch 30/62] avg loss 0.00082295, throughput 3.29873K wps
[Epoch 171 Batch 60/62] avg loss 0.000728233, throughput 3.21364K wps
Begin Testing...
[Epoch 171] train avg loss 0.000804575, dev acc 0.8378, dev avg loss 0.388158, throughput 3.2613K wps
[Epoch 172 Batch 30/62] avg loss 0.000748646, throughput 3.27581K wps
[Epoch 172 Batch 60/62] avg loss 0.000843267, throughput 3.21931K wps
Begin Testing...
[Epoch 172] train avg loss 0.000807198, dev acc 0.8378, dev avg loss 0.385515, throughput 3.25341K wps
[Epoch 173 Batch 30/62] avg loss 0.000737728, throughput 3.29065K wps
[Epoch 173 Batch 60/62] avg loss 0.000739447, throughput 3.23222K wps
Begin Testing...
[Epoch 173] train avg loss 0.000763251, dev acc 0.8437, dev avg loss 0.384101, throughput 3.26769K wps
[Epoch 174 Batch 30/62] avg loss 0.000721051, throughput 3.31456K wps
[Epoch 174 Batch 60/62] avg loss 0.000812396, throughput 3.19502K wps
Begin Testing...
[Epoch 174] train avg loss 0.000800801, dev acc 0.8348, dev avg loss 0.389542, throughput 3.26021K wps
[Epoch 175 Batch 30/62] avg loss 0.000813182, throughput 3.31108K wps
[Epoch 175 Batch 60/62] avg loss 0.000868793, throughput 3.19929K wps
Begin Testing...
[Epoch 175] train avg loss 0.000869112, dev acc 0.8348, dev avg loss 0.387111, throughput 3.26194K wps
[Epoch 176 Batch 30/62] avg loss 0.000740387, throughput 3.31K wps
[Epoch 176 Batch 60/62] avg loss 0.000786874, throughput 3.21912K wps
Begin Testing...
[Epoch 176] train avg loss 0.000762728, dev acc 0.8466, dev avg loss 0.387222, throughput 3.27008K wps
[Epoch 177 Batch 30/62] avg loss 0.000731516, throughput 3.28834K wps
[Epoch 177 Batch 60/62] avg loss 0.000808796, throughput 3.21223K wps
Begin Testing...
[Epoch 177] train avg loss 0.000771487, dev acc 0.8348, dev avg loss 0.389086, throughput 3.25702K wps
[Epoch 178 Batch 30/62] avg loss 0.00077933, throughput 3.29243K wps
[Epoch 178 Batch 60/62] avg loss 0.000736426, throughput 3.21736K wps
Begin Testing...
[Epoch 178] train avg loss 0.000766252, dev acc 0.8437, dev avg loss 0.388747, throughput 3.26004K wps
[Epoch 179 Batch 30/62] avg loss 0.000766446, throughput 3.2904K wps
[Epoch 179 Batch 60/62] avg loss 0.000690782, throughput 3.23859K wps
Begin Testing...
[Epoch 179] train avg loss 0.000734169, dev acc 0.8437, dev avg loss 0.389363, throughput 3.26979K wps
[Epoch 180 Batch 30/62] avg loss 0.000755114, throughput 3.31294K wps
[Epoch 180 Batch 60/62] avg loss 0.000719577, throughput 3.22156K wps
Begin Testing...
[Epoch 180] train avg loss 0.000755694, dev acc 0.8378, dev avg loss 0.389213, throughput 3.2744K wps
[Epoch 181 Batch 30/62] avg loss 0.000688149, throughput 3.31538K wps
[Epoch 181 Batch 60/62] avg loss 0.000733276, throughput 3.23093K wps
Begin Testing...
[Epoch 181] train avg loss 0.000709407, dev acc 0.8378, dev avg loss 0.390059, throughput 3.27773K wps
[Epoch 182 Batch 30/62] avg loss 0.000649793, throughput 3.30145K wps
[Epoch 182 Batch 60/62] avg loss 0.000763974, throughput 3.22364K wps
Begin Testing...
[Epoch 182] train avg loss 0.000712637, dev acc 0.8466, dev avg loss 0.388086, throughput 3.26848K wps
[Epoch 183 Batch 30/62] avg loss 0.000711928, throughput 3.29734K wps
[Epoch 183 Batch 60/62] avg loss 0.00073935, throughput 3.20547K wps
Begin Testing...
[Epoch 183] train avg loss 0.000732014, dev acc 0.8466, dev avg loss 0.388295, throughput 3.25646K wps
[Epoch 184 Batch 30/62] avg loss 0.000720545, throughput 3.30062K wps
[Epoch 184 Batch 60/62] avg loss 0.000702931, throughput 3.20768K wps
Begin Testing...
[Epoch 184] train avg loss 0.000717212, dev acc 0.8437, dev avg loss 0.388946, throughput 3.26001K wps
[Epoch 185 Batch 30/62] avg loss 0.000733611, throughput 3.2908K wps
[Epoch 185 Batch 60/62] avg loss 0.000650179, throughput 3.21334K wps
Begin Testing...
[Epoch 185] train avg loss 0.000705498, dev acc 0.8378, dev avg loss 0.391088, throughput 3.25754K wps
[Epoch 186 Batch 30/62] avg loss 0.00065873, throughput 3.30453K wps
[Epoch 186 Batch 60/62] avg loss 0.000695433, throughput 3.19186K wps
Begin Testing...
[Epoch 186] train avg loss 0.000678781, dev acc 0.8496, dev avg loss 0.389634, throughput 3.25468K wps
Observed Improvement.
Begin Testing...
[Epoch 187 Batch 30/62] avg loss 0.000693402, throughput 3.29674K wps
[Epoch 187 Batch 60/62] avg loss 0.000640661, throughput 3.21766K wps
Begin Testing...
[Epoch 187] train avg loss 0.000668792, dev acc 0.8466, dev avg loss 0.39061, throughput 3.26305K wps
[Epoch 188 Batch 30/62] avg loss 0.0007089, throughput 3.2683K wps
[Epoch 188 Batch 60/62] avg loss 0.000600342, throughput 3.21152K wps
Begin Testing...
[Epoch 188] train avg loss 0.000658994, dev acc 0.8407, dev avg loss 0.393165, throughput 3.24653K wps
[Epoch 189 Batch 30/62] avg loss 0.000809538, throughput 3.27716K wps
[Epoch 189 Batch 60/62] avg loss 0.000663323, throughput 3.21451K wps
Begin Testing...
[Epoch 189] train avg loss 0.000734545, dev acc 0.8496, dev avg loss 0.391213, throughput 3.25198K wps
Observed Improvement.
Begin Testing...
[Epoch 190 Batch 30/62] avg loss 0.000648717, throughput 3.30823K wps
[Epoch 190 Batch 60/62] avg loss 0.000647582, throughput 3.2299K wps
Begin Testing...
[Epoch 190] train avg loss 0.00064918, dev acc 0.8437, dev avg loss 0.392946, throughput 3.27471K wps
[Epoch 191 Batch 30/62] avg loss 0.000717054, throughput 3.30235K wps
[Epoch 191 Batch 60/62] avg loss 0.000703089, throughput 3.22678K wps
Begin Testing...
[Epoch 191] train avg loss 0.00072499, dev acc 0.8378, dev avg loss 0.397242, throughput 3.27036K wps
[Epoch 192 Batch 30/62] avg loss 0.000637519, throughput 3.31082K wps
[Epoch 192 Batch 60/62] avg loss 0.000685752, throughput 3.23456K wps
Begin Testing...
[Epoch 192] train avg loss 0.000675062, dev acc 0.8466, dev avg loss 0.394834, throughput 3.27895K wps
[Epoch 193 Batch 30/62] avg loss 0.00063703, throughput 3.30555K wps
[Epoch 193 Batch 60/62] avg loss 0.000664097, throughput 3.23337K wps
Begin Testing...
[Epoch 193] train avg loss 0.000658611, dev acc 0.8525, dev avg loss 0.394555, throughput 3.27403K wps
Observed Improvement.
Begin Testing...
[Epoch 194 Batch 30/62] avg loss 0.000593853, throughput 3.26946K wps
[Epoch 194 Batch 60/62] avg loss 0.000642569, throughput 3.23306K wps
Begin Testing...
[Epoch 194] train avg loss 0.000626152, dev acc 0.8466, dev avg loss 0.39504, throughput 3.25685K wps
[Epoch 195 Batch 30/62] avg loss 0.000613785, throughput 3.28462K wps
[Epoch 195 Batch 60/62] avg loss 0.00064487, throughput 3.2176K wps
Begin Testing...
[Epoch 195] train avg loss 0.000637381, dev acc 0.8407, dev avg loss 0.396533, throughput 3.25633K wps
[Epoch 196 Batch 30/62] avg loss 0.000585871, throughput 3.279K wps
[Epoch 196 Batch 60/62] avg loss 0.000690515, throughput 3.21412K wps
Begin Testing...
[Epoch 196] train avg loss 0.000662749, dev acc 0.8378, dev avg loss 0.398391, throughput 3.25312K wps
[Epoch 197 Batch 30/62] avg loss 0.000549821, throughput 3.30334K wps
[Epoch 197 Batch 60/62] avg loss 0.000622701, throughput 3.23586K wps
Begin Testing...
[Epoch 197] train avg loss 0.000589513, dev acc 0.8496, dev avg loss 0.396172, throughput 3.27594K wps
[Epoch 198 Batch 30/62] avg loss 0.000682644, throughput 3.29522K wps
[Epoch 198 Batch 60/62] avg loss 0.000575868, throughput 3.22133K wps
Begin Testing...
[Epoch 198] train avg loss 0.000633337, dev acc 0.8466, dev avg loss 0.395932, throughput 3.264K wps
[Epoch 199 Batch 30/62] avg loss 0.000607871, throughput 3.30864K wps
[Epoch 199 Batch 60/62] avg loss 0.000621485, throughput 3.20021K wps
Begin Testing...
[Epoch 199] train avg loss 0.000617583, dev acc 0.8555, dev avg loss 0.395705, throughput 3.2615K wps
Observed Improvement.
Begin Testing...
Test loss 0.473526, test acc 0.8117
Total time cost 418.85s
[Epoch 0 Batch 30/62] avg loss 0.0135575, throughput 3.075K wps
[Epoch 0 Batch 60/62] avg loss 0.0128766, throughput 3.21863K wps
Begin Testing...
[Epoch 0] train avg loss 0.0133604, dev acc 0.6254, dev avg loss 0.655988, throughput 3.15462K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130242, throughput 3.28253K wps
[Epoch 1 Batch 60/62] avg loss 0.0126667, throughput 3.21964K wps
Begin Testing...
[Epoch 1] train avg loss 0.0130236, dev acc 0.6254, dev avg loss 0.647701, throughput 3.25596K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0127615, throughput 3.2935K wps
[Epoch 2 Batch 60/62] avg loss 0.0127018, throughput 3.22855K wps
Begin Testing...
[Epoch 2] train avg loss 0.0128808, dev acc 0.6254, dev avg loss 0.642786, throughput 3.26716K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0126132, throughput 3.29147K wps
[Epoch 3 Batch 60/62] avg loss 0.0124946, throughput 3.22195K wps
Begin Testing...
[Epoch 3] train avg loss 0.0127268, dev acc 0.6254, dev avg loss 0.635783, throughput 3.26299K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0123599, throughput 3.28902K wps
[Epoch 4 Batch 60/62] avg loss 0.012328, throughput 3.20932K wps
Begin Testing...
[Epoch 4] train avg loss 0.0125011, dev acc 0.6254, dev avg loss 0.628178, throughput 3.25665K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0121313, throughput 3.28889K wps
[Epoch 5 Batch 60/62] avg loss 0.0120959, throughput 3.18174K wps
Begin Testing...
[Epoch 5] train avg loss 0.0122803, dev acc 0.6254, dev avg loss 0.621833, throughput 3.23985K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0121585, throughput 3.28309K wps
[Epoch 6 Batch 60/62] avg loss 0.0119709, throughput 3.21063K wps
Begin Testing...
[Epoch 6] train avg loss 0.0121968, dev acc 0.6342, dev avg loss 0.614016, throughput 3.25219K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0118871, throughput 3.28229K wps
[Epoch 7 Batch 60/62] avg loss 0.0116927, throughput 3.19445K wps
Begin Testing...
[Epoch 7] train avg loss 0.0119831, dev acc 0.6401, dev avg loss 0.606915, throughput 3.24495K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0112341, throughput 3.24882K wps
[Epoch 8 Batch 60/62] avg loss 0.0117712, throughput 3.20422K wps
Begin Testing...
[Epoch 8] train avg loss 0.011678, dev acc 0.6342, dev avg loss 0.599642, throughput 3.23311K wps
[Epoch 9 Batch 30/62] avg loss 0.0115649, throughput 3.29063K wps
[Epoch 9 Batch 60/62] avg loss 0.0112047, throughput 3.17423K wps
Begin Testing...
[Epoch 9] train avg loss 0.0115474, dev acc 0.6342, dev avg loss 0.593225, throughput 3.23854K wps
[Epoch 10 Batch 30/62] avg loss 0.0113828, throughput 3.28751K wps
[Epoch 10 Batch 60/62] avg loss 0.0109533, throughput 3.19992K wps
Begin Testing...
[Epoch 10] train avg loss 0.0113836, dev acc 0.6755, dev avg loss 0.584205, throughput 3.24965K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0109493, throughput 3.26441K wps
[Epoch 11 Batch 60/62] avg loss 0.0109784, throughput 3.22538K wps
Begin Testing...
[Epoch 11] train avg loss 0.0110995, dev acc 0.6844, dev avg loss 0.576033, throughput 3.25151K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0107426, throughput 3.27658K wps
[Epoch 12 Batch 60/62] avg loss 0.0108263, throughput 3.20664K wps
Begin Testing...
[Epoch 12] train avg loss 0.0109514, dev acc 0.7080, dev avg loss 0.568256, throughput 3.2468K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0104291, throughput 3.30476K wps
[Epoch 13 Batch 60/62] avg loss 0.0107284, throughput 3.21011K wps
Begin Testing...
[Epoch 13] train avg loss 0.0107044, dev acc 0.7080, dev avg loss 0.560344, throughput 3.26483K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0104209, throughput 3.30407K wps
[Epoch 14 Batch 60/62] avg loss 0.0104812, throughput 3.19139K wps
Begin Testing...
[Epoch 14] train avg loss 0.0105202, dev acc 0.6962, dev avg loss 0.553527, throughput 3.25476K wps
[Epoch 15 Batch 30/62] avg loss 0.0103558, throughput 3.3055K wps
[Epoch 15 Batch 60/62] avg loss 0.010099, throughput 3.22327K wps
Begin Testing...
[Epoch 15] train avg loss 0.0104365, dev acc 0.7345, dev avg loss 0.545163, throughput 3.26943K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.0101204, throughput 3.28312K wps
[Epoch 16 Batch 60/62] avg loss 0.0096943, throughput 3.2011K wps
Begin Testing...
[Epoch 16] train avg loss 0.0100694, dev acc 0.7286, dev avg loss 0.537371, throughput 3.249K wps
[Epoch 17 Batch 30/62] avg loss 0.00977823, throughput 3.28448K wps
[Epoch 17 Batch 60/62] avg loss 0.00979164, throughput 3.22064K wps
Begin Testing...
[Epoch 17] train avg loss 0.00993102, dev acc 0.7434, dev avg loss 0.531023, throughput 3.25904K wps
Observed Improvement.
Begin Testing...
[Epoch 18 Batch 30/62] avg loss 0.00959038, throughput 3.28624K wps
[Epoch 18 Batch 60/62] avg loss 0.00973553, throughput 3.20606K wps
Begin Testing...
[Epoch 18] train avg loss 0.00975855, dev acc 0.7109, dev avg loss 0.526749, throughput 3.25147K wps
[Epoch 19 Batch 30/62] avg loss 0.00955262, throughput 3.30027K wps
[Epoch 19 Batch 60/62] avg loss 0.00932682, throughput 3.18443K wps
Begin Testing...
[Epoch 19] train avg loss 0.0094864, dev acc 0.7316, dev avg loss 0.517628, throughput 3.24807K wps
[Epoch 20 Batch 30/62] avg loss 0.00915216, throughput 3.27642K wps
[Epoch 20 Batch 60/62] avg loss 0.00907251, throughput 3.21118K wps
Begin Testing...
[Epoch 20] train avg loss 0.00925235, dev acc 0.7522, dev avg loss 0.509469, throughput 3.24921K wps
Observed Improvement.
Begin Testing...
[Epoch 21 Batch 30/62] avg loss 0.00940872, throughput 3.29323K wps
[Epoch 21 Batch 60/62] avg loss 0.00876914, throughput 3.21236K wps
Begin Testing...
[Epoch 21] train avg loss 0.00917607, dev acc 0.7345, dev avg loss 0.508112, throughput 3.26003K wps
[Epoch 22 Batch 30/62] avg loss 0.00878293, throughput 3.28724K wps
[Epoch 22 Batch 60/62] avg loss 0.00886032, throughput 3.21788K wps
Begin Testing...
[Epoch 22] train avg loss 0.0089441, dev acc 0.7670, dev avg loss 0.497555, throughput 3.25876K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00871438, throughput 3.29336K wps
[Epoch 23 Batch 60/62] avg loss 0.00856767, throughput 3.21432K wps
Begin Testing...
[Epoch 23] train avg loss 0.008753, dev acc 0.7670, dev avg loss 0.492281, throughput 3.25935K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.0082726, throughput 3.29245K wps
[Epoch 24 Batch 60/62] avg loss 0.00873236, throughput 3.19952K wps
Begin Testing...
[Epoch 24] train avg loss 0.00861481, dev acc 0.7699, dev avg loss 0.48717, throughput 3.25279K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00837873, throughput 3.30448K wps
[Epoch 25 Batch 60/62] avg loss 0.00823681, throughput 3.20494K wps
Begin Testing...
[Epoch 25] train avg loss 0.00842973, dev acc 0.7758, dev avg loss 0.481359, throughput 3.26066K wps
Observed Improvement.
Begin Testing...
[Epoch 26 Batch 30/62] avg loss 0.00826628, throughput 3.28887K wps
[Epoch 26 Batch 60/62] avg loss 0.00810906, throughput 3.22516K wps
Begin Testing...
[Epoch 26] train avg loss 0.00824914, dev acc 0.7847, dev avg loss 0.476799, throughput 3.26408K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.0079684, throughput 3.29835K wps
[Epoch 27 Batch 60/62] avg loss 0.00833762, throughput 3.20918K wps
Begin Testing...
[Epoch 27] train avg loss 0.00823102, dev acc 0.7847, dev avg loss 0.472475, throughput 3.26078K wps
Observed Improvement.
Begin Testing...
[Epoch 28 Batch 30/62] avg loss 0.00793098, throughput 3.26938K wps
[Epoch 28 Batch 60/62] avg loss 0.00796097, throughput 3.20602K wps
Begin Testing...
[Epoch 28] train avg loss 0.0080611, dev acc 0.7906, dev avg loss 0.468812, throughput 3.24253K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00798197, throughput 3.28514K wps
[Epoch 29 Batch 60/62] avg loss 0.00768648, throughput 3.23146K wps
Begin Testing...
[Epoch 29] train avg loss 0.00795508, dev acc 0.7935, dev avg loss 0.464404, throughput 3.26339K wps
Observed Improvement.
Begin Testing...
[Epoch 30 Batch 30/62] avg loss 0.00782747, throughput 3.31024K wps
[Epoch 30 Batch 60/62] avg loss 0.00768879, throughput 3.22135K wps
Begin Testing...
[Epoch 30] train avg loss 0.00779541, dev acc 0.7965, dev avg loss 0.460262, throughput 3.27036K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.00745303, throughput 3.30146K wps
[Epoch 31 Batch 60/62] avg loss 0.00750495, throughput 3.22893K wps
Begin Testing...
[Epoch 31] train avg loss 0.00757427, dev acc 0.7876, dev avg loss 0.458693, throughput 3.27008K wps
[Epoch 32 Batch 30/62] avg loss 0.00745242, throughput 3.27842K wps
[Epoch 32 Batch 60/62] avg loss 0.00723594, throughput 3.2127K wps
Begin Testing...
[Epoch 32] train avg loss 0.00747652, dev acc 0.7935, dev avg loss 0.45509, throughput 3.25116K wps
[Epoch 33 Batch 30/62] avg loss 0.00737253, throughput 3.26815K wps
[Epoch 33 Batch 60/62] avg loss 0.00697756, throughput 3.22786K wps
Begin Testing...
[Epoch 33] train avg loss 0.00726791, dev acc 0.8053, dev avg loss 0.449601, throughput 3.2548K wps
Observed Improvement.
Begin Testing...
[Epoch 34 Batch 30/62] avg loss 0.00675816, throughput 3.28265K wps
[Epoch 34 Batch 60/62] avg loss 0.00720324, throughput 3.20703K wps
Begin Testing...
[Epoch 34] train avg loss 0.00712038, dev acc 0.7935, dev avg loss 0.447035, throughput 3.2515K wps
[Epoch 35 Batch 30/62] avg loss 0.00691508, throughput 3.27384K wps
[Epoch 35 Batch 60/62] avg loss 0.0068313, throughput 3.19134K wps
Begin Testing...
[Epoch 35] train avg loss 0.00711134, dev acc 0.7935, dev avg loss 0.443472, throughput 3.23871K wps
[Epoch 36 Batch 30/62] avg loss 0.00681164, throughput 3.29746K wps
[Epoch 36 Batch 60/62] avg loss 0.00700146, throughput 3.22241K wps
Begin Testing...
[Epoch 36] train avg loss 0.0070838, dev acc 0.8024, dev avg loss 0.440914, throughput 3.2672K wps
[Epoch 37 Batch 30/62] avg loss 0.00654996, throughput 3.30282K wps
[Epoch 37 Batch 60/62] avg loss 0.00696677, throughput 3.22166K wps
Begin Testing...
[Epoch 37] train avg loss 0.00676786, dev acc 0.7965, dev avg loss 0.43939, throughput 3.26902K wps
[Epoch 38 Batch 30/62] avg loss 0.0065368, throughput 3.27631K wps
[Epoch 38 Batch 60/62] avg loss 0.00649923, throughput 3.22009K wps
Begin Testing...
[Epoch 38] train avg loss 0.00662153, dev acc 0.8053, dev avg loss 0.441198, throughput 3.25571K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.00664446, throughput 3.28671K wps
[Epoch 39 Batch 60/62] avg loss 0.00624667, throughput 3.21509K wps
Begin Testing...
[Epoch 39] train avg loss 0.00655144, dev acc 0.8083, dev avg loss 0.434435, throughput 3.25676K wps
Observed Improvement.
Begin Testing...
[Epoch 40 Batch 30/62] avg loss 0.00627207, throughput 3.30986K wps
[Epoch 40 Batch 60/62] avg loss 0.00651045, throughput 3.2107K wps
Begin Testing...
[Epoch 40] train avg loss 0.00647627, dev acc 0.8083, dev avg loss 0.431566, throughput 3.2663K wps
Observed Improvement.
Begin Testing...
[Epoch 41 Batch 30/62] avg loss 0.00603271, throughput 3.31671K wps
[Epoch 41 Batch 60/62] avg loss 0.00631563, throughput 3.23192K wps
Begin Testing...
[Epoch 41] train avg loss 0.00631863, dev acc 0.8024, dev avg loss 0.433478, throughput 3.27843K wps
[Epoch 42 Batch 30/62] avg loss 0.0061102, throughput 3.28132K wps
[Epoch 42 Batch 60/62] avg loss 0.0061217, throughput 3.22136K wps
Begin Testing...
[Epoch 42] train avg loss 0.0061316, dev acc 0.7994, dev avg loss 0.430277, throughput 3.25645K wps
[Epoch 43 Batch 30/62] avg loss 0.00595945, throughput 3.26931K wps
[Epoch 43 Batch 60/62] avg loss 0.00609992, throughput 3.21438K wps
Begin Testing...
[Epoch 43] train avg loss 0.00611292, dev acc 0.8053, dev avg loss 0.430601, throughput 3.24832K wps
[Epoch 44 Batch 30/62] avg loss 0.0057635, throughput 3.27888K wps
[Epoch 44 Batch 60/62] avg loss 0.00616383, throughput 3.2166K wps
Begin Testing...
[Epoch 44] train avg loss 0.00606401, dev acc 0.8083, dev avg loss 0.424362, throughput 3.25462K wps
Observed Improvement.
Begin Testing...
[Epoch 45 Batch 30/62] avg loss 0.00567601, throughput 3.29566K wps
[Epoch 45 Batch 60/62] avg loss 0.00564348, throughput 3.1895K wps
Begin Testing...
[Epoch 45] train avg loss 0.00567183, dev acc 0.8024, dev avg loss 0.422137, throughput 3.24977K wps
[Epoch 46 Batch 30/62] avg loss 0.00564982, throughput 3.29459K wps
[Epoch 46 Batch 60/62] avg loss 0.00595294, throughput 3.23057K wps
Begin Testing...
[Epoch 46] train avg loss 0.00584277, dev acc 0.8053, dev avg loss 0.421021, throughput 3.26913K wps
[Epoch 47 Batch 30/62] avg loss 0.00523094, throughput 3.28526K wps
[Epoch 47 Batch 60/62] avg loss 0.00574498, throughput 3.21267K wps
Begin Testing...
[Epoch 47] train avg loss 0.00553804, dev acc 0.8083, dev avg loss 0.419215, throughput 3.25309K wps
Observed Improvement.
Begin Testing...
[Epoch 48 Batch 30/62] avg loss 0.00543645, throughput 3.27476K wps
[Epoch 48 Batch 60/62] avg loss 0.00547615, throughput 3.19847K wps
Begin Testing...
[Epoch 48] train avg loss 0.00550152, dev acc 0.8053, dev avg loss 0.417092, throughput 3.24269K wps
[Epoch 49 Batch 30/62] avg loss 0.00503884, throughput 3.26049K wps
[Epoch 49 Batch 60/62] avg loss 0.00589173, throughput 3.23039K wps
Begin Testing...
[Epoch 49] train avg loss 0.00552875, dev acc 0.8112, dev avg loss 0.417501, throughput 3.25118K wps
Observed Improvement.
Begin Testing...
[Epoch 50 Batch 30/62] avg loss 0.00525624, throughput 3.29019K wps
[Epoch 50 Batch 60/62] avg loss 0.00529922, throughput 3.21366K wps
Begin Testing...
[Epoch 50] train avg loss 0.00531082, dev acc 0.8053, dev avg loss 0.416997, throughput 3.25853K wps
[Epoch 51 Batch 30/62] avg loss 0.00540844, throughput 3.27478K wps
[Epoch 51 Batch 60/62] avg loss 0.0049593, throughput 3.21226K wps
Begin Testing...
[Epoch 51] train avg loss 0.0052508, dev acc 0.8142, dev avg loss 0.414352, throughput 3.25025K wps
Observed Improvement.
Begin Testing...
[Epoch 52 Batch 30/62] avg loss 0.00506037, throughput 3.29555K wps
[Epoch 52 Batch 60/62] avg loss 0.00512803, throughput 3.2087K wps
Begin Testing...
[Epoch 52] train avg loss 0.00512129, dev acc 0.8142, dev avg loss 0.415211, throughput 3.25792K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.0048475, throughput 3.32009K wps
[Epoch 53 Batch 60/62] avg loss 0.00516737, throughput 3.23602K wps
Begin Testing...
[Epoch 53] train avg loss 0.00504394, dev acc 0.7994, dev avg loss 0.415366, throughput 3.28369K wps
[Epoch 54 Batch 30/62] avg loss 0.00502547, throughput 3.28567K wps
[Epoch 54 Batch 60/62] avg loss 0.0047201, throughput 3.23345K wps
Begin Testing...
[Epoch 54] train avg loss 0.00493105, dev acc 0.8201, dev avg loss 0.413193, throughput 3.26588K wps
Observed Improvement.
Begin Testing...
[Epoch 55 Batch 30/62] avg loss 0.00492683, throughput 3.27463K wps
[Epoch 55 Batch 60/62] avg loss 0.00472868, throughput 3.21569K wps
Begin Testing...
[Epoch 55] train avg loss 0.00485229, dev acc 0.8053, dev avg loss 0.410175, throughput 3.25154K wps
[Epoch 56 Batch 30/62] avg loss 0.00459539, throughput 3.26005K wps
[Epoch 56 Batch 60/62] avg loss 0.00490387, throughput 3.23464K wps
Begin Testing...
[Epoch 56] train avg loss 0.00480302, dev acc 0.8024, dev avg loss 0.420922, throughput 3.25363K wps
[Epoch 57 Batch 30/62] avg loss 0.00455718, throughput 3.28812K wps
[Epoch 57 Batch 60/62] avg loss 0.00480917, throughput 3.20798K wps
Begin Testing...
[Epoch 57] train avg loss 0.00478756, dev acc 0.8171, dev avg loss 0.410371, throughput 3.25393K wps
[Epoch 58 Batch 30/62] avg loss 0.00469718, throughput 3.28465K wps
[Epoch 58 Batch 60/62] avg loss 0.00448331, throughput 3.21536K wps
Begin Testing...
[Epoch 58] train avg loss 0.0045939, dev acc 0.8083, dev avg loss 0.408273, throughput 3.25582K wps
[Epoch 59 Batch 30/62] avg loss 0.00435411, throughput 3.2795K wps
[Epoch 59 Batch 60/62] avg loss 0.00472507, throughput 3.22451K wps
Begin Testing...
[Epoch 59] train avg loss 0.004554, dev acc 0.7994, dev avg loss 0.407346, throughput 3.25905K wps
[Epoch 60 Batch 30/62] avg loss 0.0042932, throughput 3.27966K wps
[Epoch 60 Batch 60/62] avg loss 0.00451616, throughput 3.23335K wps
Begin Testing...
[Epoch 60] train avg loss 0.00440406, dev acc 0.8201, dev avg loss 0.408515, throughput 3.26231K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00428136, throughput 3.29057K wps
[Epoch 61 Batch 60/62] avg loss 0.00443521, throughput 3.22378K wps
Begin Testing...
[Epoch 61] train avg loss 0.0044249, dev acc 0.8053, dev avg loss 0.405408, throughput 3.26201K wps
[Epoch 62 Batch 30/62] avg loss 0.00411746, throughput 3.2801K wps
[Epoch 62 Batch 60/62] avg loss 0.00443391, throughput 3.21275K wps
Begin Testing...
[Epoch 62] train avg loss 0.00431007, dev acc 0.8083, dev avg loss 0.405685, throughput 3.25252K wps
[Epoch 63 Batch 30/62] avg loss 0.00409109, throughput 3.28137K wps
[Epoch 63 Batch 60/62] avg loss 0.00440087, throughput 3.21403K wps
Begin Testing...
[Epoch 63] train avg loss 0.00429371, dev acc 0.8024, dev avg loss 0.404694, throughput 3.2532K wps
[Epoch 64 Batch 30/62] avg loss 0.00388139, throughput 3.28877K wps
[Epoch 64 Batch 60/62] avg loss 0.00420889, throughput 3.22308K wps
Begin Testing...
[Epoch 64] train avg loss 0.00412051, dev acc 0.8053, dev avg loss 0.412468, throughput 3.26202K wps
[Epoch 65 Batch 30/62] avg loss 0.00411764, throughput 3.30365K wps
[Epoch 65 Batch 60/62] avg loss 0.00400834, throughput 3.21296K wps
Begin Testing...
[Epoch 65] train avg loss 0.00410626, dev acc 0.8083, dev avg loss 0.40372, throughput 3.26385K wps
[Epoch 66 Batch 30/62] avg loss 0.00409484, throughput 3.29211K wps
[Epoch 66 Batch 60/62] avg loss 0.00366384, throughput 3.19816K wps
Begin Testing...
[Epoch 66] train avg loss 0.00395917, dev acc 0.8083, dev avg loss 0.404317, throughput 3.25085K wps
[Epoch 67 Batch 30/62] avg loss 0.00365286, throughput 3.27728K wps
[Epoch 67 Batch 60/62] avg loss 0.00387682, throughput 3.21441K wps
Begin Testing...
[Epoch 67] train avg loss 0.00383866, dev acc 0.8053, dev avg loss 0.401277, throughput 3.25095K wps
[Epoch 68 Batch 30/62] avg loss 0.00369575, throughput 3.27657K wps
[Epoch 68 Batch 60/62] avg loss 0.00387665, throughput 3.20463K wps
Begin Testing...
[Epoch 68] train avg loss 0.00384916, dev acc 0.8083, dev avg loss 0.40309, throughput 3.24752K wps
[Epoch 69 Batch 30/62] avg loss 0.00377452, throughput 3.28294K wps
[Epoch 69 Batch 60/62] avg loss 0.00367595, throughput 3.21045K wps
Begin Testing...
[Epoch 69] train avg loss 0.00372189, dev acc 0.8053, dev avg loss 0.401563, throughput 3.25308K wps
[Epoch 70 Batch 30/62] avg loss 0.00362274, throughput 3.2703K wps
[Epoch 70 Batch 60/62] avg loss 0.00346572, throughput 3.2069K wps
Begin Testing...
[Epoch 70] train avg loss 0.00359399, dev acc 0.8053, dev avg loss 0.40027, throughput 3.2454K wps
[Epoch 71 Batch 30/62] avg loss 0.00365003, throughput 3.29064K wps
[Epoch 71 Batch 60/62] avg loss 0.00355986, throughput 3.21817K wps
Begin Testing...
[Epoch 71] train avg loss 0.00367342, dev acc 0.8142, dev avg loss 0.400953, throughput 3.26007K wps
[Epoch 72 Batch 30/62] avg loss 0.00335807, throughput 3.27862K wps
[Epoch 72 Batch 60/62] avg loss 0.00341462, throughput 3.22491K wps
Begin Testing...
[Epoch 72] train avg loss 0.00345726, dev acc 0.8142, dev avg loss 0.403076, throughput 3.25786K wps
[Epoch 73 Batch 30/62] avg loss 0.00327668, throughput 3.28603K wps
[Epoch 73 Batch 60/62] avg loss 0.00347291, throughput 3.22996K wps
Begin Testing...
[Epoch 73] train avg loss 0.00341977, dev acc 0.8053, dev avg loss 0.400538, throughput 3.26427K wps
[Epoch 74 Batch 30/62] avg loss 0.00341166, throughput 3.30399K wps
[Epoch 74 Batch 60/62] avg loss 0.00339612, throughput 3.21797K wps
Begin Testing...
[Epoch 74] train avg loss 0.00343886, dev acc 0.8201, dev avg loss 0.401925, throughput 3.26725K wps
Observed Improvement.
Begin Testing...
[Epoch 75 Batch 30/62] avg loss 0.0032743, throughput 3.30089K wps
[Epoch 75 Batch 60/62] avg loss 0.00316284, throughput 3.216K wps
Begin Testing...
[Epoch 75] train avg loss 0.00328105, dev acc 0.8083, dev avg loss 0.398861, throughput 3.26539K wps
[Epoch 76 Batch 30/62] avg loss 0.00315173, throughput 3.30583K wps
[Epoch 76 Batch 60/62] avg loss 0.00317791, throughput 3.21908K wps
Begin Testing...
[Epoch 76] train avg loss 0.00321054, dev acc 0.8053, dev avg loss 0.398775, throughput 3.26889K wps
[Epoch 77 Batch 30/62] avg loss 0.00302937, throughput 3.29825K wps
[Epoch 77 Batch 60/62] avg loss 0.00324954, throughput 3.23111K wps
Begin Testing...
[Epoch 77] train avg loss 0.00319523, dev acc 0.8083, dev avg loss 0.400734, throughput 3.27021K wps
[Epoch 78 Batch 30/62] avg loss 0.0030397, throughput 3.25014K wps
[Epoch 78 Batch 60/62] avg loss 0.00326679, throughput 3.19696K wps
Begin Testing...
[Epoch 78] train avg loss 0.00318037, dev acc 0.8024, dev avg loss 0.398541, throughput 3.23172K wps
[Epoch 79 Batch 30/62] avg loss 0.00305658, throughput 3.29989K wps
[Epoch 79 Batch 60/62] avg loss 0.00307297, throughput 3.22092K wps
Begin Testing...
[Epoch 79] train avg loss 0.00310116, dev acc 0.8083, dev avg loss 0.399441, throughput 3.2657K wps
[Epoch 80 Batch 30/62] avg loss 0.00286601, throughput 3.28135K wps
[Epoch 80 Batch 60/62] avg loss 0.00310879, throughput 3.20209K wps
Begin Testing...
[Epoch 80] train avg loss 0.00306625, dev acc 0.8083, dev avg loss 0.401721, throughput 3.24733K wps
[Epoch 81 Batch 30/62] avg loss 0.00288468, throughput 3.28493K wps
[Epoch 81 Batch 60/62] avg loss 0.0028979, throughput 3.21116K wps
Begin Testing...
[Epoch 81] train avg loss 0.00291323, dev acc 0.8112, dev avg loss 0.400399, throughput 3.25423K wps
[Epoch 82 Batch 30/62] avg loss 0.00279862, throughput 3.28424K wps
[Epoch 82 Batch 60/62] avg loss 0.00301307, throughput 3.205K wps
Begin Testing...
[Epoch 82] train avg loss 0.00291466, dev acc 0.8112, dev avg loss 0.40083, throughput 3.25248K wps
[Epoch 83 Batch 30/62] avg loss 0.00289027, throughput 3.29528K wps
[Epoch 83 Batch 60/62] avg loss 0.00277412, throughput 3.20705K wps
Begin Testing...
[Epoch 83] train avg loss 0.00285632, dev acc 0.8112, dev avg loss 0.400035, throughput 3.25677K wps
[Epoch 84 Batch 30/62] avg loss 0.00278426, throughput 3.28744K wps
[Epoch 84 Batch 60/62] avg loss 0.00276482, throughput 3.20437K wps
Begin Testing...
[Epoch 84] train avg loss 0.00277536, dev acc 0.8112, dev avg loss 0.400398, throughput 3.25217K wps
[Epoch 85 Batch 30/62] avg loss 0.00282791, throughput 3.29058K wps
[Epoch 85 Batch 60/62] avg loss 0.00265121, throughput 3.21091K wps
Begin Testing...
[Epoch 85] train avg loss 0.00278543, dev acc 0.8112, dev avg loss 0.399659, throughput 3.25683K wps
[Epoch 86 Batch 30/62] avg loss 0.00271217, throughput 3.29081K wps
[Epoch 86 Batch 60/62] avg loss 0.00264704, throughput 3.19168K wps
Begin Testing...
[Epoch 86] train avg loss 0.00272587, dev acc 0.8053, dev avg loss 0.400296, throughput 3.24779K wps
[Epoch 87 Batch 30/62] avg loss 0.00251308, throughput 3.28763K wps
[Epoch 87 Batch 60/62] avg loss 0.00259957, throughput 3.19177K wps
Begin Testing...
[Epoch 87] train avg loss 0.00260111, dev acc 0.8112, dev avg loss 0.401228, throughput 3.24587K wps
[Epoch 88 Batch 30/62] avg loss 0.0026178, throughput 3.29098K wps
[Epoch 88 Batch 60/62] avg loss 0.00248984, throughput 3.20827K wps
Begin Testing...
[Epoch 88] train avg loss 0.00260844, dev acc 0.8112, dev avg loss 0.400051, throughput 3.25684K wps
[Epoch 89 Batch 30/62] avg loss 0.00266529, throughput 3.31522K wps
[Epoch 89 Batch 60/62] avg loss 0.0025655, throughput 3.2336K wps
Begin Testing...
[Epoch 89] train avg loss 0.00265902, dev acc 0.8112, dev avg loss 0.404846, throughput 3.27995K wps
[Epoch 90 Batch 30/62] avg loss 0.00272853, throughput 3.28545K wps
[Epoch 90 Batch 60/62] avg loss 0.00240951, throughput 3.21307K wps
Begin Testing...
[Epoch 90] train avg loss 0.0025909, dev acc 0.8112, dev avg loss 0.400849, throughput 3.25544K wps
[Epoch 91 Batch 30/62] avg loss 0.00259679, throughput 3.28036K wps
[Epoch 91 Batch 60/62] avg loss 0.00240388, throughput 3.21279K wps
Begin Testing...
[Epoch 91] train avg loss 0.00255163, dev acc 0.8053, dev avg loss 0.401817, throughput 3.253K wps
[Epoch 92 Batch 30/62] avg loss 0.00244204, throughput 3.28475K wps
[Epoch 92 Batch 60/62] avg loss 0.00218981, throughput 3.22584K wps
Begin Testing...
[Epoch 92] train avg loss 0.00234124, dev acc 0.8112, dev avg loss 0.402752, throughput 3.26162K wps
[Epoch 93 Batch 30/62] avg loss 0.00240625, throughput 3.27567K wps
[Epoch 93 Batch 60/62] avg loss 0.00232897, throughput 3.2216K wps
Begin Testing...
[Epoch 93] train avg loss 0.0024025, dev acc 0.8112, dev avg loss 0.402523, throughput 3.25445K wps
[Epoch 94 Batch 30/62] avg loss 0.00232013, throughput 3.28184K wps
[Epoch 94 Batch 60/62] avg loss 0.00246157, throughput 3.21327K wps
Begin Testing...
[Epoch 94] train avg loss 0.00240375, dev acc 0.8083, dev avg loss 0.404192, throughput 3.25322K wps
[Epoch 95 Batch 30/62] avg loss 0.00237881, throughput 3.27011K wps
[Epoch 95 Batch 60/62] avg loss 0.00222527, throughput 3.22702K wps
Begin Testing...
[Epoch 95] train avg loss 0.00234363, dev acc 0.8112, dev avg loss 0.403489, throughput 3.25538K wps
[Epoch 96 Batch 30/62] avg loss 0.0022149, throughput 3.27817K wps
[Epoch 96 Batch 60/62] avg loss 0.00208477, throughput 3.21583K wps
Begin Testing...
[Epoch 96] train avg loss 0.00219463, dev acc 0.8083, dev avg loss 0.407771, throughput 3.2538K wps
[Epoch 97 Batch 30/62] avg loss 0.00219812, throughput 3.28266K wps
[Epoch 97 Batch 60/62] avg loss 0.00222729, throughput 3.20792K wps
Begin Testing...
[Epoch 97] train avg loss 0.00224207, dev acc 0.8112, dev avg loss 0.403784, throughput 3.25137K wps
[Epoch 98 Batch 30/62] avg loss 0.00213654, throughput 3.28825K wps
[Epoch 98 Batch 60/62] avg loss 0.00227316, throughput 3.20459K wps
Begin Testing...
[Epoch 98] train avg loss 0.00225564, dev acc 0.8083, dev avg loss 0.406083, throughput 3.25129K wps
[Epoch 99 Batch 30/62] avg loss 0.00204828, throughput 3.28941K wps
[Epoch 99 Batch 60/62] avg loss 0.0023114, throughput 3.21433K wps
Begin Testing...
[Epoch 99] train avg loss 0.0022113, dev acc 0.8053, dev avg loss 0.403894, throughput 3.25733K wps
[Epoch 100 Batch 30/62] avg loss 0.00208192, throughput 3.30329K wps
[Epoch 100 Batch 60/62] avg loss 0.00203693, throughput 3.23238K wps
Begin Testing...
[Epoch 100] train avg loss 0.00213629, dev acc 0.8083, dev avg loss 0.411558, throughput 3.27389K wps
[Epoch 101 Batch 30/62] avg loss 0.00212773, throughput 3.28692K wps
[Epoch 101 Batch 60/62] avg loss 0.00197113, throughput 3.21048K wps
Begin Testing...
[Epoch 101] train avg loss 0.00206857, dev acc 0.8053, dev avg loss 0.405191, throughput 3.25531K wps
[Epoch 102 Batch 30/62] avg loss 0.00198968, throughput 3.3037K wps
[Epoch 102 Batch 60/62] avg loss 0.00209209, throughput 3.21332K wps
Begin Testing...
[Epoch 102] train avg loss 0.00206124, dev acc 0.8053, dev avg loss 0.406529, throughput 3.26557K wps
[Epoch 103 Batch 30/62] avg loss 0.0019113, throughput 3.31851K wps
[Epoch 103 Batch 60/62] avg loss 0.00201679, throughput 3.21453K wps
Begin Testing...
[Epoch 103] train avg loss 0.00203503, dev acc 0.8053, dev avg loss 0.414982, throughput 3.27095K wps
[Epoch 104 Batch 30/62] avg loss 0.00206698, throughput 3.2882K wps
[Epoch 104 Batch 60/62] avg loss 0.00196031, throughput 3.22147K wps
Begin Testing...
[Epoch 104] train avg loss 0.00207722, dev acc 0.8083, dev avg loss 0.407009, throughput 3.2606K wps
[Epoch 105 Batch 30/62] avg loss 0.00199699, throughput 3.27894K wps
[Epoch 105 Batch 60/62] avg loss 0.00197135, throughput 3.21173K wps
Begin Testing...
[Epoch 105] train avg loss 0.00198402, dev acc 0.8142, dev avg loss 0.405231, throughput 3.25108K wps
[Epoch 106 Batch 30/62] avg loss 0.00180912, throughput 3.27158K wps
[Epoch 106 Batch 60/62] avg loss 0.00187169, throughput 3.21562K wps
Begin Testing...
[Epoch 106] train avg loss 0.00185717, dev acc 0.8024, dev avg loss 0.405989, throughput 3.25046K wps
[Epoch 107 Batch 30/62] avg loss 0.00179079, throughput 3.28874K wps
[Epoch 107 Batch 60/62] avg loss 0.00196448, throughput 3.21793K wps
Begin Testing...
[Epoch 107] train avg loss 0.00187182, dev acc 0.8053, dev avg loss 0.406353, throughput 3.25904K wps
[Epoch 108 Batch 30/62] avg loss 0.0018227, throughput 3.2768K wps
[Epoch 108 Batch 60/62] avg loss 0.00190352, throughput 3.20913K wps
Begin Testing...
[Epoch 108] train avg loss 0.00187463, dev acc 0.8083, dev avg loss 0.408382, throughput 3.2497K wps
[Epoch 109 Batch 30/62] avg loss 0.0017166, throughput 3.29451K wps
[Epoch 109 Batch 60/62] avg loss 0.00171986, throughput 3.16546K wps
Begin Testing...
[Epoch 109] train avg loss 0.00172381, dev acc 0.8053, dev avg loss 0.407148, throughput 3.2348K wps
[Epoch 110 Batch 30/62] avg loss 0.00179798, throughput 3.25914K wps
[Epoch 110 Batch 60/62] avg loss 0.00186306, throughput 3.20471K wps
Begin Testing...
[Epoch 110] train avg loss 0.00186181, dev acc 0.8024, dev avg loss 0.407367, throughput 3.23735K wps
[Epoch 111 Batch 30/62] avg loss 0.00175886, throughput 3.29152K wps
[Epoch 111 Batch 60/62] avg loss 0.0018172, throughput 3.20487K wps
Begin Testing...
[Epoch 111] train avg loss 0.00185204, dev acc 0.8112, dev avg loss 0.416082, throughput 3.25442K wps
[Epoch 112 Batch 30/62] avg loss 0.0016887, throughput 3.27382K wps
[Epoch 112 Batch 60/62] avg loss 0.00170453, throughput 3.22255K wps
Begin Testing...
[Epoch 112] train avg loss 0.00171299, dev acc 0.8083, dev avg loss 0.410749, throughput 3.25457K wps
[Epoch 113 Batch 30/62] avg loss 0.00168529, throughput 3.28043K wps
[Epoch 113 Batch 60/62] avg loss 0.00160587, throughput 3.21426K wps
Begin Testing...
[Epoch 113] train avg loss 0.00169229, dev acc 0.8053, dev avg loss 0.409568, throughput 3.25341K wps
[Epoch 114 Batch 30/62] avg loss 0.00175615, throughput 3.2982K wps
[Epoch 114 Batch 60/62] avg loss 0.00168121, throughput 3.22616K wps
Begin Testing...
[Epoch 114] train avg loss 0.00172249, dev acc 0.8083, dev avg loss 0.412942, throughput 3.26706K wps
[Epoch 115 Batch 30/62] avg loss 0.00167608, throughput 3.30796K wps
[Epoch 115 Batch 60/62] avg loss 0.00159934, throughput 3.22454K wps
Begin Testing...
[Epoch 115] train avg loss 0.00165569, dev acc 0.8083, dev avg loss 0.410101, throughput 3.27416K wps
[Epoch 116 Batch 30/62] avg loss 0.00166104, throughput 3.30016K wps
[Epoch 116 Batch 60/62] avg loss 0.0016206, throughput 3.23094K wps
Begin Testing...
[Epoch 116] train avg loss 0.00164175, dev acc 0.8083, dev avg loss 0.411647, throughput 3.27042K wps
[Epoch 117 Batch 30/62] avg loss 0.00157226, throughput 3.26492K wps
[Epoch 117 Batch 60/62] avg loss 0.00157249, throughput 3.2248K wps
Begin Testing...
[Epoch 117] train avg loss 0.00157979, dev acc 0.8083, dev avg loss 0.41193, throughput 3.25098K wps
[Epoch 118 Batch 30/62] avg loss 0.00153265, throughput 3.28762K wps
[Epoch 118 Batch 60/62] avg loss 0.00153549, throughput 3.21968K wps
Begin Testing...
[Epoch 118] train avg loss 0.00155817, dev acc 0.8053, dev avg loss 0.419368, throughput 3.25903K wps
[Epoch 119 Batch 30/62] avg loss 0.00163996, throughput 3.30274K wps
[Epoch 119 Batch 60/62] avg loss 0.00157157, throughput 3.22802K wps
Begin Testing...
[Epoch 119] train avg loss 0.00167011, dev acc 0.8083, dev avg loss 0.412346, throughput 3.27131K wps
[Epoch 120 Batch 30/62] avg loss 0.00155014, throughput 3.30355K wps
[Epoch 120 Batch 60/62] avg loss 0.00148275, throughput 3.20127K wps
Begin Testing...
[Epoch 120] train avg loss 0.00155279, dev acc 0.8053, dev avg loss 0.413085, throughput 3.25868K wps
[Epoch 121 Batch 30/62] avg loss 0.00147823, throughput 3.30841K wps
[Epoch 121 Batch 60/62] avg loss 0.00145393, throughput 3.18863K wps
Begin Testing...
[Epoch 121] train avg loss 0.00148373, dev acc 0.8083, dev avg loss 0.413856, throughput 3.25205K wps
[Epoch 122 Batch 30/62] avg loss 0.00146992, throughput 3.25643K wps
[Epoch 122 Batch 60/62] avg loss 0.00148238, throughput 3.21204K wps
Begin Testing...
[Epoch 122] train avg loss 0.00148708, dev acc 0.8083, dev avg loss 0.415908, throughput 3.23917K wps
[Epoch 123 Batch 30/62] avg loss 0.00144039, throughput 3.26273K wps
[Epoch 123 Batch 60/62] avg loss 0.00153055, throughput 3.19405K wps
Begin Testing...
[Epoch 123] train avg loss 0.00150548, dev acc 0.8083, dev avg loss 0.415981, throughput 3.2352K wps
[Epoch 124 Batch 30/62] avg loss 0.00150645, throughput 3.29057K wps
[Epoch 124 Batch 60/62] avg loss 0.00139357, throughput 3.20028K wps
Begin Testing...
[Epoch 124] train avg loss 0.00146082, dev acc 0.8083, dev avg loss 0.417197, throughput 3.25244K wps
[Epoch 125 Batch 30/62] avg loss 0.0013719, throughput 3.2886K wps
[Epoch 125 Batch 60/62] avg loss 0.00139554, throughput 3.19716K wps
Begin Testing...
[Epoch 125] train avg loss 0.00138753, dev acc 0.8083, dev avg loss 0.417607, throughput 3.24609K wps
[Epoch 126 Batch 30/62] avg loss 0.00139063, throughput 3.28357K wps
[Epoch 126 Batch 60/62] avg loss 0.0014543, throughput 3.19473K wps
Begin Testing...
[Epoch 126] train avg loss 0.00141961, dev acc 0.8083, dev avg loss 0.418647, throughput 3.24598K wps
[Epoch 127 Batch 30/62] avg loss 0.00129439, throughput 3.31628K wps
[Epoch 127 Batch 60/62] avg loss 0.0014351, throughput 3.21352K wps
Begin Testing...
[Epoch 127] train avg loss 0.0013707, dev acc 0.8053, dev avg loss 0.418729, throughput 3.27159K wps
[Epoch 128 Batch 30/62] avg loss 0.0012878, throughput 3.29974K wps
[Epoch 128 Batch 60/62] avg loss 0.00141782, throughput 3.21012K wps
Begin Testing...
[Epoch 128] train avg loss 0.00135426, dev acc 0.8024, dev avg loss 0.419523, throughput 3.26014K wps
[Epoch 129 Batch 30/62] avg loss 0.00140977, throughput 3.28311K wps
[Epoch 129 Batch 60/62] avg loss 0.00126234, throughput 3.20268K wps
Begin Testing...
[Epoch 129] train avg loss 0.00134466, dev acc 0.8024, dev avg loss 0.419285, throughput 3.24996K wps
[Epoch 130 Batch 30/62] avg loss 0.00136508, throughput 3.27708K wps
[Epoch 130 Batch 60/62] avg loss 0.00125024, throughput 3.21268K wps
Begin Testing...
[Epoch 130] train avg loss 0.00134388, dev acc 0.8112, dev avg loss 0.421193, throughput 3.25165K wps
[Epoch 131 Batch 30/62] avg loss 0.00129291, throughput 3.29294K wps
[Epoch 131 Batch 60/62] avg loss 0.00131146, throughput 3.21183K wps
Begin Testing...
[Epoch 131] train avg loss 0.00133067, dev acc 0.8112, dev avg loss 0.421734, throughput 3.25903K wps
[Epoch 132 Batch 30/62] avg loss 0.00132588, throughput 3.30487K wps
[Epoch 132 Batch 60/62] avg loss 0.00131364, throughput 3.22216K wps
Begin Testing...
[Epoch 132] train avg loss 0.00134429, dev acc 0.8083, dev avg loss 0.420871, throughput 3.26957K wps
[Epoch 133 Batch 30/62] avg loss 0.00120808, throughput 3.29451K wps
[Epoch 133 Batch 60/62] avg loss 0.00125427, throughput 3.22007K wps
Begin Testing...
[Epoch 133] train avg loss 0.00125716, dev acc 0.7994, dev avg loss 0.422253, throughput 3.26411K wps
[Epoch 134 Batch 30/62] avg loss 0.00114428, throughput 3.29781K wps
[Epoch 134 Batch 60/62] avg loss 0.00114755, throughput 3.22365K wps
Begin Testing...
[Epoch 134] train avg loss 0.0011797, dev acc 0.7994, dev avg loss 0.423888, throughput 3.26788K wps
[Epoch 135 Batch 30/62] avg loss 0.00119397, throughput 3.31042K wps
[Epoch 135 Batch 60/62] avg loss 0.00130425, throughput 3.22551K wps
Begin Testing...
[Epoch 135] train avg loss 0.00125405, dev acc 0.8024, dev avg loss 0.423582, throughput 3.27482K wps
[Epoch 136 Batch 30/62] avg loss 0.00127063, throughput 3.28209K wps
[Epoch 136 Batch 60/62] avg loss 0.00123524, throughput 3.21349K wps
Begin Testing...
[Epoch 136] train avg loss 0.00127427, dev acc 0.8024, dev avg loss 0.424818, throughput 3.25413K wps
[Epoch 137 Batch 30/62] avg loss 0.00123946, throughput 3.2859K wps
[Epoch 137 Batch 60/62] avg loss 0.00126115, throughput 3.19833K wps
Begin Testing...
[Epoch 137] train avg loss 0.00125114, dev acc 0.8024, dev avg loss 0.42732, throughput 3.24834K wps
[Epoch 138 Batch 30/62] avg loss 0.00116493, throughput 3.28138K wps
[Epoch 138 Batch 60/62] avg loss 0.00123309, throughput 3.18323K wps
Begin Testing...
[Epoch 138] train avg loss 0.00121522, dev acc 0.8024, dev avg loss 0.424727, throughput 3.23864K wps
[Epoch 139 Batch 30/62] avg loss 0.00119553, throughput 3.28402K wps
[Epoch 139 Batch 60/62] avg loss 0.00118083, throughput 3.19594K wps
Begin Testing...
[Epoch 139] train avg loss 0.00119562, dev acc 0.8024, dev avg loss 0.427165, throughput 3.24534K wps
[Epoch 140 Batch 30/62] avg loss 0.00118839, throughput 3.24726K wps
[Epoch 140 Batch 60/62] avg loss 0.00109543, throughput 3.21258K wps
Begin Testing...
[Epoch 140] train avg loss 0.00114764, dev acc 0.8112, dev avg loss 0.425731, throughput 3.23778K wps
[Epoch 141 Batch 30/62] avg loss 0.00108521, throughput 3.29639K wps
[Epoch 141 Batch 60/62] avg loss 0.00116502, throughput 3.23007K wps
Begin Testing...
[Epoch 141] train avg loss 0.00113161, dev acc 0.8024, dev avg loss 0.427241, throughput 3.26939K wps
[Epoch 142 Batch 30/62] avg loss 0.00113308, throughput 3.30289K wps
[Epoch 142 Batch 60/62] avg loss 0.00112269, throughput 3.20214K wps
Begin Testing...
[Epoch 142] train avg loss 0.00114461, dev acc 0.8112, dev avg loss 0.426661, throughput 3.2582K wps
[Epoch 143 Batch 30/62] avg loss 0.00102359, throughput 3.30731K wps
[Epoch 143 Batch 60/62] avg loss 0.00111053, throughput 3.21031K wps
Begin Testing...
[Epoch 143] train avg loss 0.00109235, dev acc 0.8024, dev avg loss 0.427902, throughput 3.2652K wps
[Epoch 144 Batch 30/62] avg loss 0.00107552, throughput 3.32324K wps
[Epoch 144 Batch 60/62] avg loss 0.00110907, throughput 3.23143K wps
Begin Testing...
[Epoch 144] train avg loss 0.00111418, dev acc 0.8112, dev avg loss 0.428023, throughput 3.28227K wps
[Epoch 145 Batch 30/62] avg loss 0.00110352, throughput 3.30163K wps
[Epoch 145 Batch 60/62] avg loss 0.00101376, throughput 3.23469K wps
Begin Testing...
[Epoch 145] train avg loss 0.00106509, dev acc 0.8024, dev avg loss 0.429501, throughput 3.27455K wps
[Epoch 146 Batch 30/62] avg loss 0.00107097, throughput 3.30284K wps
[Epoch 146 Batch 60/62] avg loss 0.00110637, throughput 3.21806K wps
Begin Testing...
[Epoch 146] train avg loss 0.00108276, dev acc 0.8024, dev avg loss 0.429798, throughput 3.26648K wps
[Epoch 147 Batch 30/62] avg loss 0.000982743, throughput 3.30232K wps
[Epoch 147 Batch 60/62] avg loss 0.00110231, throughput 3.22855K wps
Begin Testing...
[Epoch 147] train avg loss 0.00104933, dev acc 0.8083, dev avg loss 0.428892, throughput 3.27168K wps
[Epoch 148 Batch 30/62] avg loss 0.00103623, throughput 3.2861K wps
[Epoch 148 Batch 60/62] avg loss 0.00104467, throughput 3.23047K wps
Begin Testing...
[Epoch 148] train avg loss 0.00107354, dev acc 0.8171, dev avg loss 0.432762, throughput 3.26405K wps
[Epoch 149 Batch 30/62] avg loss 0.0010629, throughput 3.30319K wps
[Epoch 149 Batch 60/62] avg loss 0.000997046, throughput 3.22128K wps
Begin Testing...
[Epoch 149] train avg loss 0.0010493, dev acc 0.8083, dev avg loss 0.430552, throughput 3.26858K wps
[Epoch 150 Batch 30/62] avg loss 0.00101743, throughput 3.30101K wps
[Epoch 150 Batch 60/62] avg loss 0.0010176, throughput 3.2173K wps
Begin Testing...
[Epoch 150] train avg loss 0.00102155, dev acc 0.8053, dev avg loss 0.431754, throughput 3.26591K wps
[Epoch 151 Batch 30/62] avg loss 0.00104112, throughput 3.30172K wps
[Epoch 151 Batch 60/62] avg loss 0.000920192, throughput 3.19036K wps
Begin Testing...
[Epoch 151] train avg loss 0.00100575, dev acc 0.8024, dev avg loss 0.432787, throughput 3.25327K wps
[Epoch 152 Batch 30/62] avg loss 0.000938847, throughput 3.29813K wps
[Epoch 152 Batch 60/62] avg loss 0.00105981, throughput 3.19616K wps
Begin Testing...
[Epoch 152] train avg loss 0.00101479, dev acc 0.8142, dev avg loss 0.431073, throughput 3.25423K wps
[Epoch 153 Batch 30/62] avg loss 0.0010215, throughput 3.28821K wps
[Epoch 153 Batch 60/62] avg loss 0.000929947, throughput 3.21834K wps
Begin Testing...
[Epoch 153] train avg loss 0.000974561, dev acc 0.8053, dev avg loss 0.432823, throughput 3.26069K wps
[Epoch 154 Batch 30/62] avg loss 0.000910489, throughput 3.28902K wps
[Epoch 154 Batch 60/62] avg loss 0.000873463, throughput 3.2095K wps
Begin Testing...
[Epoch 154] train avg loss 0.000909323, dev acc 0.8142, dev avg loss 0.432407, throughput 3.25434K wps
[Epoch 155 Batch 30/62] avg loss 0.00104396, throughput 3.29492K wps
[Epoch 155 Batch 60/62] avg loss 0.000988462, throughput 3.20874K wps
Begin Testing...
[Epoch 155] train avg loss 0.00102111, dev acc 0.8142, dev avg loss 0.432024, throughput 3.25681K wps
[Epoch 156 Batch 30/62] avg loss 0.000938212, throughput 3.28002K wps
[Epoch 156 Batch 60/62] avg loss 0.000978816, throughput 3.21261K wps
Begin Testing...
[Epoch 156] train avg loss 0.00096568, dev acc 0.8083, dev avg loss 0.434159, throughput 3.25424K wps
[Epoch 157 Batch 30/62] avg loss 0.000874145, throughput 3.29723K wps
[Epoch 157 Batch 60/62] avg loss 0.000936177, throughput 3.21217K wps
Begin Testing...
[Epoch 157] train avg loss 0.000910579, dev acc 0.8142, dev avg loss 0.434154, throughput 3.25979K wps
[Epoch 158 Batch 30/62] avg loss 0.000849647, throughput 3.2939K wps
[Epoch 158 Batch 60/62] avg loss 0.000913772, throughput 3.22059K wps
Begin Testing...
[Epoch 158] train avg loss 0.000896088, dev acc 0.8142, dev avg loss 0.43567, throughput 3.26333K wps
[Epoch 159 Batch 30/62] avg loss 0.000956138, throughput 3.29868K wps
[Epoch 159 Batch 60/62] avg loss 0.000874877, throughput 3.24058K wps
Begin Testing...
[Epoch 159] train avg loss 0.000917238, dev acc 0.8053, dev avg loss 0.436814, throughput 3.27582K wps
[Epoch 160 Batch 30/62] avg loss 0.000942736, throughput 3.29764K wps
[Epoch 160 Batch 60/62] avg loss 0.000952566, throughput 3.21729K wps
Begin Testing...
[Epoch 160] train avg loss 0.000949633, dev acc 0.8083, dev avg loss 0.436166, throughput 3.26523K wps
[Epoch 161 Batch 30/62] avg loss 0.000852085, throughput 3.31328K wps
[Epoch 161 Batch 60/62] avg loss 0.000896771, throughput 3.23016K wps
Begin Testing...
[Epoch 161] train avg loss 0.000884128, dev acc 0.8053, dev avg loss 0.437489, throughput 3.27749K wps
[Epoch 162 Batch 30/62] avg loss 0.000859351, throughput 3.3188K wps
[Epoch 162 Batch 60/62] avg loss 0.000851454, throughput 3.23823K wps
Begin Testing...
[Epoch 162] train avg loss 0.000865859, dev acc 0.8142, dev avg loss 0.436714, throughput 3.28554K wps
[Epoch 163 Batch 30/62] avg loss 0.000866957, throughput 3.31265K wps
[Epoch 163 Batch 60/62] avg loss 0.00090765, throughput 3.23131K wps
Begin Testing...
[Epoch 163] train avg loss 0.000895596, dev acc 0.8112, dev avg loss 0.438015, throughput 3.27813K wps
[Epoch 164 Batch 30/62] avg loss 0.000758363, throughput 3.29855K wps
[Epoch 164 Batch 60/62] avg loss 0.000914247, throughput 3.21486K wps
Begin Testing...
[Epoch 164] train avg loss 0.000864131, dev acc 0.8112, dev avg loss 0.438464, throughput 3.26212K wps
[Epoch 165 Batch 30/62] avg loss 0.000854872, throughput 3.29436K wps
[Epoch 165 Batch 60/62] avg loss 0.00088734, throughput 3.19628K wps
Begin Testing...
[Epoch 165] train avg loss 0.000904709, dev acc 0.8142, dev avg loss 0.438551, throughput 3.25189K wps
[Epoch 166 Batch 30/62] avg loss 0.00076653, throughput 3.28864K wps
[Epoch 166 Batch 60/62] avg loss 0.000885691, throughput 3.20704K wps
Begin Testing...
[Epoch 166] train avg loss 0.000833876, dev acc 0.8112, dev avg loss 0.438905, throughput 3.25205K wps
[Epoch 167 Batch 30/62] avg loss 0.000802063, throughput 3.31202K wps
[Epoch 167 Batch 60/62] avg loss 0.000870263, throughput 3.21234K wps
Begin Testing...
[Epoch 167] train avg loss 0.000837432, dev acc 0.8053, dev avg loss 0.441293, throughput 3.2681K wps
[Epoch 168 Batch 30/62] avg loss 0.000931662, throughput 3.31743K wps
[Epoch 168 Batch 60/62] avg loss 0.000877344, throughput 3.21961K wps
Begin Testing...
[Epoch 168] train avg loss 0.000917203, dev acc 0.8112, dev avg loss 0.440879, throughput 3.27523K wps
[Epoch 169 Batch 30/62] avg loss 0.000790857, throughput 3.29181K wps
[Epoch 169 Batch 60/62] avg loss 0.000804211, throughput 3.18574K wps
Begin Testing...
[Epoch 169] train avg loss 0.000804, dev acc 0.8083, dev avg loss 0.442685, throughput 3.24565K wps
[Epoch 170 Batch 30/62] avg loss 0.000808152, throughput 3.30636K wps
[Epoch 170 Batch 60/62] avg loss 0.000786745, throughput 3.23026K wps
Begin Testing...
[Epoch 170] train avg loss 0.000799617, dev acc 0.8024, dev avg loss 0.443753, throughput 3.27442K wps
[Epoch 171 Batch 30/62] avg loss 0.000808372, throughput 3.29602K wps
[Epoch 171 Batch 60/62] avg loss 0.000873922, throughput 3.223K wps
Begin Testing...
[Epoch 171] train avg loss 0.000849987, dev acc 0.8142, dev avg loss 0.442605, throughput 3.26408K wps
[Epoch 172 Batch 30/62] avg loss 0.000759167, throughput 3.27985K wps
[Epoch 172 Batch 60/62] avg loss 0.000815008, throughput 3.22582K wps
Begin Testing...
[Epoch 172] train avg loss 0.000808425, dev acc 0.8142, dev avg loss 0.443819, throughput 3.25947K wps
[Epoch 173 Batch 30/62] avg loss 0.000812014, throughput 3.29842K wps
[Epoch 173 Batch 60/62] avg loss 0.000783948, throughput 3.22434K wps
Begin Testing...
[Epoch 173] train avg loss 0.000822167, dev acc 0.8112, dev avg loss 0.445343, throughput 3.26701K wps
[Epoch 174 Batch 30/62] avg loss 0.000774963, throughput 3.30916K wps
[Epoch 174 Batch 60/62] avg loss 0.000757559, throughput 3.22552K wps
Begin Testing...
[Epoch 174] train avg loss 0.000808263, dev acc 0.8053, dev avg loss 0.446477, throughput 3.27406K wps
[Epoch 175 Batch 30/62] avg loss 0.000811065, throughput 3.30239K wps
[Epoch 175 Batch 60/62] avg loss 0.000786872, throughput 3.23315K wps
Begin Testing...
[Epoch 175] train avg loss 0.000797134, dev acc 0.8112, dev avg loss 0.444777, throughput 3.274K wps
[Epoch 176 Batch 30/62] avg loss 0.000811527, throughput 3.28913K wps
[Epoch 176 Batch 60/62] avg loss 0.000741697, throughput 3.22831K wps
Begin Testing...
[Epoch 176] train avg loss 0.000784432, dev acc 0.8112, dev avg loss 0.44589, throughput 3.2665K wps
[Epoch 177 Batch 30/62] avg loss 0.00081753, throughput 3.31054K wps
[Epoch 177 Batch 60/62] avg loss 0.000740705, throughput 3.22603K wps
Begin Testing...
[Epoch 177] train avg loss 0.000782367, dev acc 0.8112, dev avg loss 0.445594, throughput 3.27297K wps
[Epoch 178 Batch 30/62] avg loss 0.000794743, throughput 3.27617K wps
[Epoch 178 Batch 60/62] avg loss 0.000731103, throughput 3.20555K wps
Begin Testing...
[Epoch 178] train avg loss 0.000775737, dev acc 0.8083, dev avg loss 0.445247, throughput 3.24785K wps
[Epoch 179 Batch 30/62] avg loss 0.000730871, throughput 3.28211K wps
[Epoch 179 Batch 60/62] avg loss 0.000728963, throughput 3.18926K wps
Begin Testing...
[Epoch 179] train avg loss 0.000746377, dev acc 0.8083, dev avg loss 0.445734, throughput 3.24253K wps
[Epoch 180 Batch 30/62] avg loss 0.000691928, throughput 3.27834K wps
[Epoch 180 Batch 60/62] avg loss 0.000796516, throughput 3.19174K wps
Begin Testing...
[Epoch 180] train avg loss 0.000747908, dev acc 0.8142, dev avg loss 0.446283, throughput 3.24106K wps
[Epoch 181 Batch 30/62] avg loss 0.000717587, throughput 3.29082K wps
[Epoch 181 Batch 60/62] avg loss 0.000709216, throughput 3.19997K wps
Begin Testing...
[Epoch 181] train avg loss 0.000723448, dev acc 0.8053, dev avg loss 0.450321, throughput 3.25103K wps
[Epoch 182 Batch 30/62] avg loss 0.000766145, throughput 3.27766K wps
[Epoch 182 Batch 60/62] avg loss 0.000731205, throughput 3.20937K wps
Begin Testing...
[Epoch 182] train avg loss 0.000750696, dev acc 0.8112, dev avg loss 0.449582, throughput 3.24906K wps
[Epoch 183 Batch 30/62] avg loss 0.000672304, throughput 3.26793K wps
[Epoch 183 Batch 60/62] avg loss 0.000745322, throughput 3.21733K wps
Begin Testing...
[Epoch 183] train avg loss 0.000711805, dev acc 0.8083, dev avg loss 0.45109, throughput 3.24852K wps
[Epoch 184 Batch 30/62] avg loss 0.000669218, throughput 3.27679K wps
[Epoch 184 Batch 60/62] avg loss 0.000758009, throughput 3.20777K wps
Begin Testing...
[Epoch 184] train avg loss 0.000718469, dev acc 0.8112, dev avg loss 0.451423, throughput 3.24834K wps
[Epoch 185 Batch 30/62] avg loss 0.000731682, throughput 3.28493K wps
[Epoch 185 Batch 60/62] avg loss 0.000711696, throughput 3.21305K wps
Begin Testing...
[Epoch 185] train avg loss 0.000720788, dev acc 0.8112, dev avg loss 0.452313, throughput 3.25472K wps
[Epoch 186 Batch 30/62] avg loss 0.000666615, throughput 3.30781K wps
[Epoch 186 Batch 60/62] avg loss 0.000745587, throughput 3.22008K wps
Begin Testing...
[Epoch 186] train avg loss 0.000733356, dev acc 0.8112, dev avg loss 0.452285, throughput 3.26907K wps
[Epoch 187 Batch 30/62] avg loss 0.000739457, throughput 3.28183K wps
[Epoch 187 Batch 60/62] avg loss 0.000645238, throughput 3.23213K wps
Begin Testing...
[Epoch 187] train avg loss 0.000688721, dev acc 0.8053, dev avg loss 0.453283, throughput 3.26324K wps
[Epoch 188 Batch 30/62] avg loss 0.000654729, throughput 3.28729K wps
[Epoch 188 Batch 60/62] avg loss 0.000714656, throughput 3.2088K wps
Begin Testing...
[Epoch 188] train avg loss 0.00069909, dev acc 0.8112, dev avg loss 0.45212, throughput 3.25411K wps
[Epoch 189 Batch 30/62] avg loss 0.000683953, throughput 3.27161K wps
[Epoch 189 Batch 60/62] avg loss 0.000718805, throughput 3.22099K wps
Begin Testing...
[Epoch 189] train avg loss 0.000705587, dev acc 0.8053, dev avg loss 0.454082, throughput 3.25264K wps
[Epoch 190 Batch 30/62] avg loss 0.000732736, throughput 3.28468K wps
[Epoch 190 Batch 60/62] avg loss 0.000676039, throughput 3.2216K wps
Begin Testing...
[Epoch 190] train avg loss 0.000704643, dev acc 0.8083, dev avg loss 0.453059, throughput 3.25891K wps
[Epoch 191 Batch 30/62] avg loss 0.000685832, throughput 3.29471K wps
[Epoch 191 Batch 60/62] avg loss 0.000627604, throughput 3.20626K wps
Begin Testing...
[Epoch 191] train avg loss 0.000654061, dev acc 0.8053, dev avg loss 0.456646, throughput 3.25608K wps
[Epoch 192 Batch 30/62] avg loss 0.000677699, throughput 3.30607K wps
[Epoch 192 Batch 60/62] avg loss 0.000632588, throughput 3.22255K wps
Begin Testing...
[Epoch 192] train avg loss 0.000661853, dev acc 0.8112, dev avg loss 0.453936, throughput 3.27066K wps
[Epoch 193 Batch 30/62] avg loss 0.000608638, throughput 3.3249K wps
[Epoch 193 Batch 60/62] avg loss 0.000692281, throughput 3.24009K wps
Begin Testing...
[Epoch 193] train avg loss 0.000672018, dev acc 0.8053, dev avg loss 0.456217, throughput 3.28763K wps
[Epoch 194 Batch 30/62] avg loss 0.000665951, throughput 3.2853K wps
[Epoch 194 Batch 60/62] avg loss 0.000630906, throughput 3.21839K wps
Begin Testing...
[Epoch 194] train avg loss 0.000677855, dev acc 0.8142, dev avg loss 0.454464, throughput 3.25763K wps
[Epoch 195 Batch 30/62] avg loss 0.0006327, throughput 3.26463K wps
[Epoch 195 Batch 60/62] avg loss 0.000637999, throughput 3.20727K wps
Begin Testing...
[Epoch 195] train avg loss 0.000644826, dev acc 0.8142, dev avg loss 0.454488, throughput 3.24211K wps
[Epoch 196 Batch 30/62] avg loss 0.000625495, throughput 3.28948K wps
[Epoch 196 Batch 60/62] avg loss 0.000591452, throughput 3.21414K wps
Begin Testing...
[Epoch 196] train avg loss 0.000616653, dev acc 0.8083, dev avg loss 0.455489, throughput 3.25858K wps
[Epoch 197 Batch 30/62] avg loss 0.00064067, throughput 3.28634K wps
[Epoch 197 Batch 60/62] avg loss 0.000633629, throughput 3.22253K wps
Begin Testing...
[Epoch 197] train avg loss 0.000649507, dev acc 0.8112, dev avg loss 0.456077, throughput 3.25845K wps
[Epoch 198 Batch 30/62] avg loss 0.000601918, throughput 3.28139K wps
[Epoch 198 Batch 60/62] avg loss 0.000643805, throughput 3.23044K wps
Begin Testing...
[Epoch 198] train avg loss 0.000622534, dev acc 0.8083, dev avg loss 0.457317, throughput 3.26094K wps
[Epoch 199 Batch 30/62] avg loss 0.000658879, throughput 3.28992K wps
[Epoch 199 Batch 60/62] avg loss 0.000565965, throughput 3.21015K wps
Begin Testing...
[Epoch 199] train avg loss 0.000642359, dev acc 0.8083, dev avg loss 0.461007, throughput 3.25517K wps
Test loss 0.371589, test acc 0.8408
Total time cost 417.17s
[Epoch 0 Batch 30/62] avg loss 0.0134813, throughput 3.07369K wps
[Epoch 0 Batch 60/62] avg loss 0.0131553, throughput 3.22585K wps
Begin Testing...
[Epoch 0] train avg loss 0.013509, dev acc 0.6224, dev avg loss 0.658453, throughput 3.15679K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130961, throughput 3.30336K wps
[Epoch 1 Batch 60/62] avg loss 0.0131433, throughput 3.21927K wps
Begin Testing...
[Epoch 1] train avg loss 0.0132839, dev acc 0.6224, dev avg loss 0.650297, throughput 3.26687K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0129348, throughput 3.28928K wps
[Epoch 2 Batch 60/62] avg loss 0.0126488, throughput 3.21129K wps
Begin Testing...
[Epoch 2] train avg loss 0.0129521, dev acc 0.6224, dev avg loss 0.645991, throughput 3.25726K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0126561, throughput 3.30445K wps
[Epoch 3 Batch 60/62] avg loss 0.0126068, throughput 3.18915K wps
Begin Testing...
[Epoch 3] train avg loss 0.0127605, dev acc 0.6224, dev avg loss 0.639469, throughput 3.25226K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0126661, throughput 3.26662K wps
[Epoch 4 Batch 60/62] avg loss 0.0123034, throughput 3.22078K wps
Begin Testing...
[Epoch 4] train avg loss 0.0126891, dev acc 0.6224, dev avg loss 0.628904, throughput 3.25017K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0125137, throughput 3.31631K wps
[Epoch 5 Batch 60/62] avg loss 0.0121184, throughput 3.21676K wps
Begin Testing...
[Epoch 5] train avg loss 0.0124589, dev acc 0.6224, dev avg loss 0.621911, throughput 3.27252K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0123632, throughput 3.30946K wps
[Epoch 6 Batch 60/62] avg loss 0.011896, throughput 3.21695K wps
Begin Testing...
[Epoch 6] train avg loss 0.0122679, dev acc 0.6224, dev avg loss 0.618094, throughput 3.26614K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0117871, throughput 3.29962K wps
[Epoch 7 Batch 60/62] avg loss 0.0120491, throughput 3.21811K wps
Begin Testing...
[Epoch 7] train avg loss 0.0120619, dev acc 0.6372, dev avg loss 0.606075, throughput 3.262K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0117213, throughput 3.29776K wps
[Epoch 8 Batch 60/62] avg loss 0.0117937, throughput 3.21721K wps
Begin Testing...
[Epoch 8] train avg loss 0.0118971, dev acc 0.6224, dev avg loss 0.598989, throughput 3.26367K wps
[Epoch 9 Batch 30/62] avg loss 0.0115011, throughput 3.28486K wps
[Epoch 9 Batch 60/62] avg loss 0.0113724, throughput 3.22197K wps
Begin Testing...
[Epoch 9] train avg loss 0.0115286, dev acc 0.6283, dev avg loss 0.591554, throughput 3.25912K wps
[Epoch 10 Batch 30/62] avg loss 0.0114498, throughput 3.28695K wps
[Epoch 10 Batch 60/62] avg loss 0.011103, throughput 3.22472K wps
Begin Testing...
[Epoch 10] train avg loss 0.0113861, dev acc 0.6313, dev avg loss 0.584602, throughput 3.2616K wps
[Epoch 11 Batch 30/62] avg loss 0.0111146, throughput 3.29665K wps
[Epoch 11 Batch 60/62] avg loss 0.0111039, throughput 3.20366K wps
Begin Testing...
[Epoch 11] train avg loss 0.0112518, dev acc 0.6962, dev avg loss 0.571075, throughput 3.25623K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0108391, throughput 3.27213K wps
[Epoch 12 Batch 60/62] avg loss 0.0109424, throughput 3.22912K wps
Begin Testing...
[Epoch 12] train avg loss 0.0109977, dev acc 0.6667, dev avg loss 0.563144, throughput 3.25707K wps
[Epoch 13 Batch 30/62] avg loss 0.0108524, throughput 3.30094K wps
[Epoch 13 Batch 60/62] avg loss 0.0105766, throughput 3.23222K wps
Begin Testing...
[Epoch 13] train avg loss 0.0108478, dev acc 0.6755, dev avg loss 0.554448, throughput 3.2729K wps
[Epoch 14 Batch 30/62] avg loss 0.0104066, throughput 3.27052K wps
[Epoch 14 Batch 60/62] avg loss 0.0106032, throughput 3.21183K wps
Begin Testing...
[Epoch 14] train avg loss 0.0106709, dev acc 0.7227, dev avg loss 0.544076, throughput 3.24737K wps
Observed Improvement.
Begin Testing...
[Epoch 15 Batch 30/62] avg loss 0.0103523, throughput 3.28531K wps
[Epoch 15 Batch 60/62] avg loss 0.00992039, throughput 3.21116K wps
Begin Testing...
[Epoch 15] train avg loss 0.0102657, dev acc 0.7434, dev avg loss 0.534171, throughput 3.2546K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.00998754, throughput 3.29779K wps
[Epoch 16 Batch 60/62] avg loss 0.00992379, throughput 3.21373K wps
Begin Testing...
[Epoch 16] train avg loss 0.0101063, dev acc 0.7493, dev avg loss 0.52443, throughput 3.26122K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.009658, throughput 3.30161K wps
[Epoch 17 Batch 60/62] avg loss 0.00965752, throughput 3.20859K wps
Begin Testing...
[Epoch 17] train avg loss 0.00977711, dev acc 0.7227, dev avg loss 0.520132, throughput 3.26276K wps
[Epoch 18 Batch 30/62] avg loss 0.00975112, throughput 3.31115K wps
[Epoch 18 Batch 60/62] avg loss 0.00928753, throughput 3.23712K wps
Begin Testing...
[Epoch 18] train avg loss 0.00965995, dev acc 0.7404, dev avg loss 0.510745, throughput 3.27922K wps
[Epoch 19 Batch 30/62] avg loss 0.00936324, throughput 3.30035K wps
[Epoch 19 Batch 60/62] avg loss 0.00937653, throughput 3.22794K wps
Begin Testing...
[Epoch 19] train avg loss 0.00947873, dev acc 0.7611, dev avg loss 0.499329, throughput 3.27069K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.00918007, throughput 3.29748K wps
[Epoch 20 Batch 60/62] avg loss 0.00908245, throughput 3.20528K wps
Begin Testing...
[Epoch 20] train avg loss 0.00925166, dev acc 0.7552, dev avg loss 0.493111, throughput 3.25687K wps
[Epoch 21 Batch 30/62] avg loss 0.0091513, throughput 3.28614K wps
[Epoch 21 Batch 60/62] avg loss 0.00883235, throughput 3.21594K wps
Begin Testing...
[Epoch 21] train avg loss 0.0091004, dev acc 0.7729, dev avg loss 0.485114, throughput 3.25826K wps
Observed Improvement.
Begin Testing...
[Epoch 22 Batch 30/62] avg loss 0.00872106, throughput 3.32055K wps
[Epoch 22 Batch 60/62] avg loss 0.00872466, throughput 3.21476K wps
Begin Testing...
[Epoch 22] train avg loss 0.00886434, dev acc 0.7640, dev avg loss 0.480188, throughput 3.27318K wps
[Epoch 23 Batch 30/62] avg loss 0.00862948, throughput 3.31707K wps
[Epoch 23 Batch 60/62] avg loss 0.00873397, throughput 3.22981K wps
Begin Testing...
[Epoch 23] train avg loss 0.00872801, dev acc 0.7611, dev avg loss 0.474659, throughput 3.27883K wps
[Epoch 24 Batch 30/62] avg loss 0.00833408, throughput 3.28988K wps
[Epoch 24 Batch 60/62] avg loss 0.00844943, throughput 3.21732K wps
Begin Testing...
[Epoch 24] train avg loss 0.00847806, dev acc 0.7729, dev avg loss 0.468148, throughput 3.25954K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00827911, throughput 3.29551K wps
[Epoch 25 Batch 60/62] avg loss 0.00817576, throughput 3.22309K wps
Begin Testing...
[Epoch 25] train avg loss 0.00844471, dev acc 0.7906, dev avg loss 0.460034, throughput 3.26603K wps
Observed Improvement.
Begin Testing...
[Epoch 26 Batch 30/62] avg loss 0.00813665, throughput 3.29862K wps
[Epoch 26 Batch 60/62] avg loss 0.00813519, throughput 3.21768K wps
Begin Testing...
[Epoch 26] train avg loss 0.00827583, dev acc 0.7906, dev avg loss 0.455309, throughput 3.26261K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.00770354, throughput 3.30653K wps
[Epoch 27 Batch 60/62] avg loss 0.00826675, throughput 3.22728K wps
Begin Testing...
[Epoch 27] train avg loss 0.00811728, dev acc 0.8024, dev avg loss 0.449322, throughput 3.27353K wps
Observed Improvement.
Begin Testing...
[Epoch 28 Batch 30/62] avg loss 0.00764434, throughput 3.26428K wps
[Epoch 28 Batch 60/62] avg loss 0.00804247, throughput 3.22149K wps
Begin Testing...
[Epoch 28] train avg loss 0.00798038, dev acc 0.7817, dev avg loss 0.450822, throughput 3.24944K wps
[Epoch 29 Batch 30/62] avg loss 0.00778037, throughput 3.28434K wps
[Epoch 29 Batch 60/62] avg loss 0.0075284, throughput 3.22151K wps
Begin Testing...
[Epoch 29] train avg loss 0.00774989, dev acc 0.7788, dev avg loss 0.443312, throughput 3.25911K wps
[Epoch 30 Batch 30/62] avg loss 0.00770954, throughput 3.27981K wps
[Epoch 30 Batch 60/62] avg loss 0.00742155, throughput 3.21948K wps
Begin Testing...
[Epoch 30] train avg loss 0.00768704, dev acc 0.7847, dev avg loss 0.443254, throughput 3.25511K wps
[Epoch 31 Batch 30/62] avg loss 0.0074676, throughput 3.29891K wps
[Epoch 31 Batch 60/62] avg loss 0.0072578, throughput 3.21489K wps
Begin Testing...
[Epoch 31] train avg loss 0.00746636, dev acc 0.7994, dev avg loss 0.434442, throughput 3.26338K wps
[Epoch 32 Batch 30/62] avg loss 0.00740225, throughput 3.30934K wps
[Epoch 32 Batch 60/62] avg loss 0.00723533, throughput 3.2305K wps
Begin Testing...
[Epoch 32] train avg loss 0.007385, dev acc 0.7876, dev avg loss 0.433668, throughput 3.2764K wps
[Epoch 33 Batch 30/62] avg loss 0.00721369, throughput 3.30832K wps
[Epoch 33 Batch 60/62] avg loss 0.00699109, throughput 3.22087K wps
Begin Testing...
[Epoch 33] train avg loss 0.00722904, dev acc 0.8112, dev avg loss 0.425393, throughput 3.27126K wps
Observed Improvement.
Begin Testing...
[Epoch 34 Batch 30/62] avg loss 0.00693231, throughput 3.30052K wps
[Epoch 34 Batch 60/62] avg loss 0.00711278, throughput 3.23036K wps
Begin Testing...
[Epoch 34] train avg loss 0.00711282, dev acc 0.8112, dev avg loss 0.422643, throughput 3.27095K wps
Observed Improvement.
Begin Testing...
[Epoch 35 Batch 30/62] avg loss 0.00668617, throughput 3.28723K wps
[Epoch 35 Batch 60/62] avg loss 0.00688823, throughput 3.22453K wps
Begin Testing...
[Epoch 35] train avg loss 0.00686836, dev acc 0.7994, dev avg loss 0.425039, throughput 3.26045K wps
[Epoch 36 Batch 30/62] avg loss 0.00643294, throughput 3.2746K wps
[Epoch 36 Batch 60/62] avg loss 0.00670674, throughput 3.20061K wps
Begin Testing...
[Epoch 36] train avg loss 0.00661873, dev acc 0.8024, dev avg loss 0.420698, throughput 3.2435K wps
[Epoch 37 Batch 30/62] avg loss 0.00655638, throughput 3.29429K wps
[Epoch 37 Batch 60/62] avg loss 0.00639411, throughput 3.19636K wps
Begin Testing...
[Epoch 37] train avg loss 0.0065537, dev acc 0.8112, dev avg loss 0.412693, throughput 3.25319K wps
Observed Improvement.
Begin Testing...
[Epoch 38 Batch 30/62] avg loss 0.00668499, throughput 3.29716K wps
[Epoch 38 Batch 60/62] avg loss 0.00626806, throughput 3.19471K wps
Begin Testing...
[Epoch 38] train avg loss 0.00654874, dev acc 0.7876, dev avg loss 0.424363, throughput 3.25317K wps
[Epoch 39 Batch 30/62] avg loss 0.00630662, throughput 3.29343K wps
[Epoch 39 Batch 60/62] avg loss 0.00629602, throughput 3.17114K wps
Begin Testing...
[Epoch 39] train avg loss 0.00640495, dev acc 0.8053, dev avg loss 0.409164, throughput 3.23615K wps
[Epoch 40 Batch 30/62] avg loss 0.00626911, throughput 3.25843K wps
[Epoch 40 Batch 60/62] avg loss 0.00606352, throughput 3.21915K wps
Begin Testing...
[Epoch 40] train avg loss 0.00623202, dev acc 0.8083, dev avg loss 0.408633, throughput 3.24552K wps
[Epoch 41 Batch 30/62] avg loss 0.00619162, throughput 3.25212K wps
[Epoch 41 Batch 60/62] avg loss 0.00588085, throughput 3.21706K wps
Begin Testing...
[Epoch 41] train avg loss 0.00611298, dev acc 0.8053, dev avg loss 0.411344, throughput 3.24225K wps
[Epoch 42 Batch 30/62] avg loss 0.005892, throughput 3.28245K wps
[Epoch 42 Batch 60/62] avg loss 0.0060895, throughput 3.20913K wps
Begin Testing...
[Epoch 42] train avg loss 0.00606692, dev acc 0.8112, dev avg loss 0.399971, throughput 3.25204K wps
Observed Improvement.
Begin Testing...
[Epoch 43 Batch 30/62] avg loss 0.00588422, throughput 3.29507K wps
[Epoch 43 Batch 60/62] avg loss 0.00601814, throughput 3.18282K wps
Begin Testing...
[Epoch 43] train avg loss 0.00598522, dev acc 0.8053, dev avg loss 0.399503, throughput 3.24554K wps
[Epoch 44 Batch 30/62] avg loss 0.00570589, throughput 3.3045K wps
[Epoch 44 Batch 60/62] avg loss 0.00567215, throughput 3.19927K wps
Begin Testing...
[Epoch 44] train avg loss 0.00574566, dev acc 0.8083, dev avg loss 0.396289, throughput 3.25956K wps
[Epoch 45 Batch 30/62] avg loss 0.00583454, throughput 3.28313K wps
[Epoch 45 Batch 60/62] avg loss 0.00563916, throughput 3.18731K wps
Begin Testing...
[Epoch 45] train avg loss 0.00581395, dev acc 0.8201, dev avg loss 0.400763, throughput 3.24109K wps
Observed Improvement.
Begin Testing...
[Epoch 46 Batch 30/62] avg loss 0.00564652, throughput 3.29707K wps
[Epoch 46 Batch 60/62] avg loss 0.00547671, throughput 3.17359K wps
Begin Testing...
[Epoch 46] train avg loss 0.00569774, dev acc 0.8053, dev avg loss 0.394537, throughput 3.23949K wps
[Epoch 47 Batch 30/62] avg loss 0.00544775, throughput 3.26237K wps
[Epoch 47 Batch 60/62] avg loss 0.00526667, throughput 3.15494K wps
Begin Testing...
[Epoch 47] train avg loss 0.00541558, dev acc 0.8171, dev avg loss 0.401117, throughput 3.21485K wps
[Epoch 48 Batch 30/62] avg loss 0.00518695, throughput 3.2433K wps
[Epoch 48 Batch 60/62] avg loss 0.00551974, throughput 3.16797K wps
Begin Testing...
[Epoch 48] train avg loss 0.00545239, dev acc 0.8083, dev avg loss 0.391367, throughput 3.21355K wps
[Epoch 49 Batch 30/62] avg loss 0.00522065, throughput 3.22972K wps
[Epoch 49 Batch 60/62] avg loss 0.00519663, throughput 3.21273K wps
Begin Testing...
[Epoch 49] train avg loss 0.00527308, dev acc 0.8171, dev avg loss 0.387817, throughput 3.22682K wps
[Epoch 50 Batch 30/62] avg loss 0.00499706, throughput 3.27684K wps
[Epoch 50 Batch 60/62] avg loss 0.00511131, throughput 3.1748K wps
Begin Testing...
[Epoch 50] train avg loss 0.00511216, dev acc 0.8230, dev avg loss 0.390473, throughput 3.23256K wps
Observed Improvement.
Begin Testing...
[Epoch 51 Batch 30/62] avg loss 0.00505759, throughput 3.27292K wps
[Epoch 51 Batch 60/62] avg loss 0.00493624, throughput 3.21208K wps
Begin Testing...
[Epoch 51] train avg loss 0.00507049, dev acc 0.8112, dev avg loss 0.3854, throughput 3.24867K wps
[Epoch 52 Batch 30/62] avg loss 0.0049538, throughput 3.26054K wps
[Epoch 52 Batch 60/62] avg loss 0.00506329, throughput 3.20401K wps
Begin Testing...
[Epoch 52] train avg loss 0.00506411, dev acc 0.8171, dev avg loss 0.381825, throughput 3.23863K wps
[Epoch 53 Batch 30/62] avg loss 0.00482761, throughput 3.2763K wps
[Epoch 53 Batch 60/62] avg loss 0.00481294, throughput 3.16142K wps
Begin Testing...
[Epoch 53] train avg loss 0.00489946, dev acc 0.8289, dev avg loss 0.379507, throughput 3.22389K wps
Observed Improvement.
Begin Testing...
[Epoch 54 Batch 30/62] avg loss 0.00484531, throughput 3.2683K wps
[Epoch 54 Batch 60/62] avg loss 0.00472495, throughput 3.21588K wps
Begin Testing...
[Epoch 54] train avg loss 0.00481528, dev acc 0.8230, dev avg loss 0.378487, throughput 3.24866K wps
[Epoch 55 Batch 30/62] avg loss 0.00445743, throughput 3.2817K wps
[Epoch 55 Batch 60/62] avg loss 0.00495443, throughput 3.21721K wps
Begin Testing...
[Epoch 55] train avg loss 0.00476023, dev acc 0.8230, dev avg loss 0.385544, throughput 3.25538K wps
[Epoch 56 Batch 30/62] avg loss 0.0043988, throughput 3.30044K wps
[Epoch 56 Batch 60/62] avg loss 0.00470272, throughput 3.21524K wps
Begin Testing...
[Epoch 56] train avg loss 0.00458941, dev acc 0.8201, dev avg loss 0.376981, throughput 3.26276K wps
[Epoch 57 Batch 30/62] avg loss 0.00456364, throughput 3.27929K wps
[Epoch 57 Batch 60/62] avg loss 0.00450766, throughput 3.20436K wps
Begin Testing...
[Epoch 57] train avg loss 0.00462762, dev acc 0.8201, dev avg loss 0.375212, throughput 3.24623K wps
[Epoch 58 Batch 30/62] avg loss 0.00440341, throughput 3.27459K wps
[Epoch 58 Batch 60/62] avg loss 0.00441164, throughput 3.17228K wps
Begin Testing...
[Epoch 58] train avg loss 0.0044632, dev acc 0.8260, dev avg loss 0.374192, throughput 3.23008K wps
[Epoch 59 Batch 30/62] avg loss 0.00420737, throughput 3.26277K wps
[Epoch 59 Batch 60/62] avg loss 0.00446626, throughput 3.19919K wps
Begin Testing...
[Epoch 59] train avg loss 0.00439443, dev acc 0.8289, dev avg loss 0.375624, throughput 3.23722K wps
Observed Improvement.
Begin Testing...
[Epoch 60 Batch 30/62] avg loss 0.00430677, throughput 3.28263K wps
[Epoch 60 Batch 60/62] avg loss 0.00427469, throughput 3.16957K wps
Begin Testing...
[Epoch 60] train avg loss 0.00434861, dev acc 0.8289, dev avg loss 0.370271, throughput 3.23089K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00405922, throughput 3.27157K wps
[Epoch 61 Batch 60/62] avg loss 0.00414354, throughput 3.21461K wps
Begin Testing...
[Epoch 61] train avg loss 0.00417163, dev acc 0.8319, dev avg loss 0.372844, throughput 3.2501K wps
Observed Improvement.
Begin Testing...
[Epoch 62 Batch 30/62] avg loss 0.00404753, throughput 3.28803K wps
[Epoch 62 Batch 60/62] avg loss 0.00415461, throughput 3.17504K wps
Begin Testing...
[Epoch 62] train avg loss 0.0041178, dev acc 0.8319, dev avg loss 0.369785, throughput 3.23663K wps
Observed Improvement.
Begin Testing...
[Epoch 63 Batch 30/62] avg loss 0.00406446, throughput 3.27012K wps
[Epoch 63 Batch 60/62] avg loss 0.0038815, throughput 3.21375K wps
Begin Testing...
[Epoch 63] train avg loss 0.003991, dev acc 0.8319, dev avg loss 0.367913, throughput 3.24693K wps
Observed Improvement.
Begin Testing...
[Epoch 64 Batch 30/62] avg loss 0.00406199, throughput 3.30501K wps
[Epoch 64 Batch 60/62] avg loss 0.00371824, throughput 3.20255K wps
Begin Testing...
[Epoch 64] train avg loss 0.0039639, dev acc 0.8378, dev avg loss 0.3708, throughput 3.26017K wps
Observed Improvement.
Begin Testing...
[Epoch 65 Batch 30/62] avg loss 0.00366903, throughput 3.27799K wps
[Epoch 65 Batch 60/62] avg loss 0.00389, throughput 3.21444K wps
Begin Testing...
[Epoch 65] train avg loss 0.00388017, dev acc 0.8348, dev avg loss 0.365257, throughput 3.25176K wps
[Epoch 66 Batch 30/62] avg loss 0.00390179, throughput 3.30619K wps
[Epoch 66 Batch 60/62] avg loss 0.00375251, throughput 3.20235K wps
Begin Testing...
[Epoch 66] train avg loss 0.00389058, dev acc 0.8348, dev avg loss 0.373239, throughput 3.25907K wps
[Epoch 67 Batch 30/62] avg loss 0.00385815, throughput 3.25257K wps
[Epoch 67 Batch 60/62] avg loss 0.00361928, throughput 3.2222K wps
Begin Testing...
[Epoch 67] train avg loss 0.00375107, dev acc 0.8348, dev avg loss 0.369951, throughput 3.24391K wps
[Epoch 68 Batch 30/62] avg loss 0.00345031, throughput 3.27635K wps
[Epoch 68 Batch 60/62] avg loss 0.00361175, throughput 3.21419K wps
Begin Testing...
[Epoch 68] train avg loss 0.00362572, dev acc 0.8407, dev avg loss 0.368965, throughput 3.25099K wps
Observed Improvement.
Begin Testing...
[Epoch 69 Batch 30/62] avg loss 0.00360179, throughput 3.29761K wps
[Epoch 69 Batch 60/62] avg loss 0.00346871, throughput 3.20913K wps
Begin Testing...
[Epoch 69] train avg loss 0.00362568, dev acc 0.8407, dev avg loss 0.364683, throughput 3.25916K wps
Observed Improvement.
Begin Testing...
[Epoch 70 Batch 30/62] avg loss 0.00361703, throughput 3.29422K wps
[Epoch 70 Batch 60/62] avg loss 0.00345359, throughput 3.21043K wps
Begin Testing...
[Epoch 70] train avg loss 0.00357438, dev acc 0.8378, dev avg loss 0.361649, throughput 3.25758K wps
[Epoch 71 Batch 30/62] avg loss 0.00349648, throughput 3.29164K wps
[Epoch 71 Batch 60/62] avg loss 0.00341266, throughput 3.21314K wps
Begin Testing...
[Epoch 71] train avg loss 0.003501, dev acc 0.8407, dev avg loss 0.367271, throughput 3.25802K wps
Observed Improvement.
Begin Testing...
[Epoch 72 Batch 30/62] avg loss 0.00346832, throughput 3.28363K wps
[Epoch 72 Batch 60/62] avg loss 0.00325943, throughput 3.18809K wps
Begin Testing...
[Epoch 72] train avg loss 0.00346622, dev acc 0.8378, dev avg loss 0.369181, throughput 3.24363K wps
[Epoch 73 Batch 30/62] avg loss 0.00337878, throughput 3.28104K wps
[Epoch 73 Batch 60/62] avg loss 0.00307631, throughput 3.19089K wps
Begin Testing...
[Epoch 73] train avg loss 0.00327632, dev acc 0.8378, dev avg loss 0.363204, throughput 3.24102K wps
[Epoch 74 Batch 30/62] avg loss 0.00316655, throughput 3.26382K wps
[Epoch 74 Batch 60/62] avg loss 0.00323611, throughput 3.21831K wps
Begin Testing...
[Epoch 74] train avg loss 0.00325182, dev acc 0.8407, dev avg loss 0.361504, throughput 3.24664K wps
Observed Improvement.
Begin Testing...
[Epoch 75 Batch 30/62] avg loss 0.00310007, throughput 3.29555K wps
[Epoch 75 Batch 60/62] avg loss 0.00314497, throughput 3.17544K wps
Begin Testing...
[Epoch 75] train avg loss 0.00315734, dev acc 0.8407, dev avg loss 0.361103, throughput 3.24157K wps
Observed Improvement.
Begin Testing...
[Epoch 76 Batch 30/62] avg loss 0.00305129, throughput 3.25999K wps
[Epoch 76 Batch 60/62] avg loss 0.00308123, throughput 3.21322K wps
Begin Testing...
[Epoch 76] train avg loss 0.00310404, dev acc 0.8407, dev avg loss 0.361596, throughput 3.2424K wps
Observed Improvement.
Begin Testing...
[Epoch 77 Batch 30/62] avg loss 0.00310738, throughput 3.29135K wps
[Epoch 77 Batch 60/62] avg loss 0.00301045, throughput 3.16488K wps
Begin Testing...
[Epoch 77] train avg loss 0.00307333, dev acc 0.8466, dev avg loss 0.356829, throughput 3.23155K wps
Observed Improvement.
Begin Testing...
[Epoch 78 Batch 30/62] avg loss 0.00305574, throughput 3.26343K wps
[Epoch 78 Batch 60/62] avg loss 0.00272045, throughput 3.16153K wps
Begin Testing...
[Epoch 78] train avg loss 0.00295068, dev acc 0.8437, dev avg loss 0.358896, throughput 3.21739K wps
[Epoch 79 Batch 30/62] avg loss 0.0028876, throughput 3.26209K wps
[Epoch 79 Batch 60/62] avg loss 0.00287568, throughput 3.19701K wps
Begin Testing...
[Epoch 79] train avg loss 0.00293171, dev acc 0.8407, dev avg loss 0.36043, throughput 3.23656K wps
[Epoch 80 Batch 30/62] avg loss 0.0028542, throughput 3.29264K wps
[Epoch 80 Batch 60/62] avg loss 0.0027793, throughput 3.21742K wps
Begin Testing...
[Epoch 80] train avg loss 0.00286626, dev acc 0.8407, dev avg loss 0.358777, throughput 3.26182K wps
[Epoch 81 Batch 30/62] avg loss 0.00283013, throughput 3.29464K wps
[Epoch 81 Batch 60/62] avg loss 0.0028603, throughput 3.21582K wps
Begin Testing...
[Epoch 81] train avg loss 0.00289667, dev acc 0.8407, dev avg loss 0.359339, throughput 3.26034K wps
[Epoch 82 Batch 30/62] avg loss 0.00283464, throughput 3.27359K wps
[Epoch 82 Batch 60/62] avg loss 0.00259357, throughput 3.22K wps
Begin Testing...
[Epoch 82] train avg loss 0.00271535, dev acc 0.8378, dev avg loss 0.37009, throughput 3.25261K wps
[Epoch 83 Batch 30/62] avg loss 0.00276457, throughput 3.26974K wps
[Epoch 83 Batch 60/62] avg loss 0.00279589, throughput 3.23367K wps
Begin Testing...
[Epoch 83] train avg loss 0.00284041, dev acc 0.8437, dev avg loss 0.357838, throughput 3.25809K wps
[Epoch 84 Batch 30/62] avg loss 0.00273786, throughput 3.26859K wps
[Epoch 84 Batch 60/62] avg loss 0.00252951, throughput 3.21953K wps
Begin Testing...
[Epoch 84] train avg loss 0.00268626, dev acc 0.8437, dev avg loss 0.353187, throughput 3.24907K wps
[Epoch 85 Batch 30/62] avg loss 0.00266857, throughput 3.30866K wps
[Epoch 85 Batch 60/62] avg loss 0.00262511, throughput 3.2122K wps
Begin Testing...
[Epoch 85] train avg loss 0.00269228, dev acc 0.8437, dev avg loss 0.354736, throughput 3.26495K wps
[Epoch 86 Batch 30/62] avg loss 0.00255613, throughput 3.26184K wps
[Epoch 86 Batch 60/62] avg loss 0.00249525, throughput 3.19187K wps
Begin Testing...
[Epoch 86] train avg loss 0.00257074, dev acc 0.8407, dev avg loss 0.352382, throughput 3.23462K wps
[Epoch 87 Batch 30/62] avg loss 0.00234291, throughput 3.28461K wps
[Epoch 87 Batch 60/62] avg loss 0.00264749, throughput 3.17856K wps
Begin Testing...
[Epoch 87] train avg loss 0.00253527, dev acc 0.8348, dev avg loss 0.364308, throughput 3.23862K wps
[Epoch 88 Batch 30/62] avg loss 0.00234617, throughput 3.30603K wps
[Epoch 88 Batch 60/62] avg loss 0.00263216, throughput 3.17737K wps
Begin Testing...
[Epoch 88] train avg loss 0.00250425, dev acc 0.8466, dev avg loss 0.360141, throughput 3.24557K wps
Observed Improvement.
Begin Testing...
[Epoch 89 Batch 30/62] avg loss 0.00239155, throughput 3.26802K wps
[Epoch 89 Batch 60/62] avg loss 0.00240405, throughput 3.18912K wps
Begin Testing...
[Epoch 89] train avg loss 0.00241303, dev acc 0.8437, dev avg loss 0.356835, throughput 3.23631K wps
[Epoch 90 Batch 30/62] avg loss 0.00235679, throughput 3.26126K wps
[Epoch 90 Batch 60/62] avg loss 0.00239073, throughput 3.18888K wps
Begin Testing...
[Epoch 90] train avg loss 0.00245164, dev acc 0.8437, dev avg loss 0.35118, throughput 3.23107K wps
[Epoch 91 Batch 30/62] avg loss 0.00226324, throughput 3.26462K wps
[Epoch 91 Batch 60/62] avg loss 0.00253915, throughput 3.19386K wps
Begin Testing...
[Epoch 91] train avg loss 0.00243049, dev acc 0.8466, dev avg loss 0.351906, throughput 3.23536K wps
Observed Improvement.
Begin Testing...
[Epoch 92 Batch 30/62] avg loss 0.00234251, throughput 3.30701K wps
[Epoch 92 Batch 60/62] avg loss 0.00235849, throughput 3.17627K wps
Begin Testing...
[Epoch 92] train avg loss 0.00236012, dev acc 0.8437, dev avg loss 0.357371, throughput 3.24637K wps
[Epoch 93 Batch 30/62] avg loss 0.00230752, throughput 3.27779K wps
[Epoch 93 Batch 60/62] avg loss 0.00225327, throughput 3.2166K wps
Begin Testing...
[Epoch 93] train avg loss 0.00230657, dev acc 0.8319, dev avg loss 0.364056, throughput 3.2521K wps
[Epoch 94 Batch 30/62] avg loss 0.00210036, throughput 3.26239K wps
[Epoch 94 Batch 60/62] avg loss 0.0023205, throughput 3.21771K wps
Begin Testing...
[Epoch 94] train avg loss 0.00226901, dev acc 0.8466, dev avg loss 0.358665, throughput 3.24612K wps
Observed Improvement.
Begin Testing...
[Epoch 95 Batch 30/62] avg loss 0.00220825, throughput 3.27555K wps
[Epoch 95 Batch 60/62] avg loss 0.00214606, throughput 3.21653K wps
Begin Testing...
[Epoch 95] train avg loss 0.00218415, dev acc 0.8437, dev avg loss 0.358237, throughput 3.25266K wps
[Epoch 96 Batch 30/62] avg loss 0.002001, throughput 3.2898K wps
[Epoch 96 Batch 60/62] avg loss 0.00224353, throughput 3.22154K wps
Begin Testing...
[Epoch 96] train avg loss 0.00212418, dev acc 0.8437, dev avg loss 0.353751, throughput 3.26137K wps
[Epoch 97 Batch 30/62] avg loss 0.00198142, throughput 3.29363K wps
[Epoch 97 Batch 60/62] avg loss 0.00215645, throughput 3.21741K wps
Begin Testing...
[Epoch 97] train avg loss 0.00206291, dev acc 0.8437, dev avg loss 0.357991, throughput 3.26027K wps
[Epoch 98 Batch 30/62] avg loss 0.00188174, throughput 3.28661K wps
[Epoch 98 Batch 60/62] avg loss 0.00220236, throughput 3.2165K wps
Begin Testing...
[Epoch 98] train avg loss 0.00208645, dev acc 0.8466, dev avg loss 0.35102, throughput 3.25692K wps
Observed Improvement.
Begin Testing...
[Epoch 99 Batch 30/62] avg loss 0.00209245, throughput 3.2777K wps
[Epoch 99 Batch 60/62] avg loss 0.00214418, throughput 3.2093K wps
Begin Testing...
[Epoch 99] train avg loss 0.00216268, dev acc 0.8437, dev avg loss 0.350608, throughput 3.25079K wps
[Epoch 100 Batch 30/62] avg loss 0.00213982, throughput 3.28757K wps
[Epoch 100 Batch 60/62] avg loss 0.00198549, throughput 3.20001K wps
Begin Testing...
[Epoch 100] train avg loss 0.00207464, dev acc 0.8407, dev avg loss 0.355701, throughput 3.25061K wps
[Epoch 101 Batch 30/62] avg loss 0.00199524, throughput 3.27113K wps
[Epoch 101 Batch 60/62] avg loss 0.00201576, throughput 3.18488K wps
Begin Testing...
[Epoch 101] train avg loss 0.00202671, dev acc 0.8407, dev avg loss 0.355309, throughput 3.23529K wps
[Epoch 102 Batch 30/62] avg loss 0.00184749, throughput 3.28885K wps
[Epoch 102 Batch 60/62] avg loss 0.00192734, throughput 3.19274K wps
Begin Testing...
[Epoch 102] train avg loss 0.00191229, dev acc 0.8407, dev avg loss 0.356133, throughput 3.24834K wps
[Epoch 103 Batch 30/62] avg loss 0.00185594, throughput 3.30414K wps
[Epoch 103 Batch 60/62] avg loss 0.00194472, throughput 3.18355K wps
Begin Testing...
[Epoch 103] train avg loss 0.00191296, dev acc 0.8407, dev avg loss 0.362208, throughput 3.25034K wps
[Epoch 104 Batch 30/62] avg loss 0.00196698, throughput 3.29456K wps
[Epoch 104 Batch 60/62] avg loss 0.00178434, throughput 3.18286K wps
Begin Testing...
[Epoch 104] train avg loss 0.00188398, dev acc 0.8407, dev avg loss 0.354596, throughput 3.24417K wps
[Epoch 105 Batch 30/62] avg loss 0.0018124, throughput 3.25427K wps
[Epoch 105 Batch 60/62] avg loss 0.00179255, throughput 3.1827K wps
Begin Testing...
[Epoch 105] train avg loss 0.00182783, dev acc 0.8378, dev avg loss 0.357256, throughput 3.22553K wps
[Epoch 106 Batch 30/62] avg loss 0.00177654, throughput 3.28201K wps
[Epoch 106 Batch 60/62] avg loss 0.00186249, throughput 3.16969K wps
Begin Testing...
[Epoch 106] train avg loss 0.00186758, dev acc 0.8437, dev avg loss 0.359541, throughput 3.23054K wps
[Epoch 107 Batch 30/62] avg loss 0.00165994, throughput 3.26312K wps
[Epoch 107 Batch 60/62] avg loss 0.00202468, throughput 3.19683K wps
Begin Testing...
[Epoch 107] train avg loss 0.00185977, dev acc 0.8407, dev avg loss 0.355781, throughput 3.23694K wps
[Epoch 108 Batch 30/62] avg loss 0.00173164, throughput 3.27638K wps
[Epoch 108 Batch 60/62] avg loss 0.00177318, throughput 3.17888K wps
Begin Testing...
[Epoch 108] train avg loss 0.0017613, dev acc 0.8407, dev avg loss 0.356819, throughput 3.23174K wps
[Epoch 109 Batch 30/62] avg loss 0.00164186, throughput 3.25671K wps
[Epoch 109 Batch 60/62] avg loss 0.00180685, throughput 3.20775K wps
Begin Testing...
[Epoch 109] train avg loss 0.00174347, dev acc 0.8466, dev avg loss 0.351111, throughput 3.23901K wps
Observed Improvement.
Begin Testing...
[Epoch 110 Batch 30/62] avg loss 0.00169786, throughput 3.27658K wps
[Epoch 110 Batch 60/62] avg loss 0.00171557, throughput 3.21414K wps
Begin Testing...
[Epoch 110] train avg loss 0.00172312, dev acc 0.8407, dev avg loss 0.355066, throughput 3.25265K wps
[Epoch 111 Batch 30/62] avg loss 0.00180154, throughput 3.29065K wps
[Epoch 111 Batch 60/62] avg loss 0.00163848, throughput 3.22347K wps
Begin Testing...
[Epoch 111] train avg loss 0.00175722, dev acc 0.8407, dev avg loss 0.356409, throughput 3.2628K wps
[Epoch 112 Batch 30/62] avg loss 0.0016569, throughput 3.27118K wps
[Epoch 112 Batch 60/62] avg loss 0.00159154, throughput 3.22805K wps
Begin Testing...
[Epoch 112] train avg loss 0.00163016, dev acc 0.8378, dev avg loss 0.359389, throughput 3.25613K wps
[Epoch 113 Batch 30/62] avg loss 0.00158873, throughput 3.2865K wps
[Epoch 113 Batch 60/62] avg loss 0.00162313, throughput 3.22243K wps
Begin Testing...
[Epoch 113] train avg loss 0.0016734, dev acc 0.8407, dev avg loss 0.357591, throughput 3.25995K wps
[Epoch 114 Batch 30/62] avg loss 0.00153236, throughput 3.27182K wps
[Epoch 114 Batch 60/62] avg loss 0.00157624, throughput 3.21152K wps
Begin Testing...
[Epoch 114] train avg loss 0.00158301, dev acc 0.8407, dev avg loss 0.357197, throughput 3.2464K wps
[Epoch 115 Batch 30/62] avg loss 0.00154669, throughput 3.27019K wps
[Epoch 115 Batch 60/62] avg loss 0.001678, throughput 3.2066K wps
Begin Testing...
[Epoch 115] train avg loss 0.00162113, dev acc 0.8407, dev avg loss 0.357794, throughput 3.2436K wps
[Epoch 116 Batch 30/62] avg loss 0.00158665, throughput 3.27963K wps
[Epoch 116 Batch 60/62] avg loss 0.00147763, throughput 3.17776K wps
Begin Testing...
[Epoch 116] train avg loss 0.00154624, dev acc 0.8378, dev avg loss 0.361667, throughput 3.23574K wps
[Epoch 117 Batch 30/62] avg loss 0.00157534, throughput 3.30586K wps
[Epoch 117 Batch 60/62] avg loss 0.00154561, throughput 3.19029K wps
Begin Testing...
[Epoch 117] train avg loss 0.00158044, dev acc 0.8407, dev avg loss 0.352765, throughput 3.25391K wps
[Epoch 118 Batch 30/62] avg loss 0.00139721, throughput 3.25804K wps
[Epoch 118 Batch 60/62] avg loss 0.00162116, throughput 3.20547K wps
Begin Testing...
[Epoch 118] train avg loss 0.00151299, dev acc 0.8348, dev avg loss 0.360717, throughput 3.23699K wps
[Epoch 119 Batch 30/62] avg loss 0.00150883, throughput 3.27219K wps
[Epoch 119 Batch 60/62] avg loss 0.00148184, throughput 3.18967K wps
Begin Testing...
[Epoch 119] train avg loss 0.00149485, dev acc 0.8378, dev avg loss 0.359005, throughput 3.23862K wps
[Epoch 120 Batch 30/62] avg loss 0.00159837, throughput 3.29525K wps
[Epoch 120 Batch 60/62] avg loss 0.00147568, throughput 3.16745K wps
Begin Testing...
[Epoch 120] train avg loss 0.00155037, dev acc 0.8378, dev avg loss 0.355495, throughput 3.23528K wps
[Epoch 121 Batch 30/62] avg loss 0.00153336, throughput 3.24803K wps
[Epoch 121 Batch 60/62] avg loss 0.00144029, throughput 3.18312K wps
Begin Testing...
[Epoch 121] train avg loss 0.00150177, dev acc 0.8348, dev avg loss 0.3628, throughput 3.22306K wps
[Epoch 122 Batch 30/62] avg loss 0.00138942, throughput 3.29065K wps
[Epoch 122 Batch 60/62] avg loss 0.0014407, throughput 3.16306K wps
Begin Testing...
[Epoch 122] train avg loss 0.00143969, dev acc 0.8348, dev avg loss 0.375994, throughput 3.2317K wps
[Epoch 123 Batch 30/62] avg loss 0.00136091, throughput 3.26202K wps
[Epoch 123 Batch 60/62] avg loss 0.00141093, throughput 3.19517K wps
Begin Testing...
[Epoch 123] train avg loss 0.00138067, dev acc 0.8348, dev avg loss 0.361784, throughput 3.23577K wps
[Epoch 124 Batch 30/62] avg loss 0.00135676, throughput 3.29676K wps
[Epoch 124 Batch 60/62] avg loss 0.00134874, throughput 3.19359K wps
Begin Testing...
[Epoch 124] train avg loss 0.00134645, dev acc 0.8437, dev avg loss 0.357154, throughput 3.25263K wps
[Epoch 125 Batch 30/62] avg loss 0.00137077, throughput 3.29639K wps
[Epoch 125 Batch 60/62] avg loss 0.00135611, throughput 3.20125K wps
Begin Testing...
[Epoch 125] train avg loss 0.00137448, dev acc 0.8407, dev avg loss 0.365509, throughput 3.25463K wps
[Epoch 126 Batch 30/62] avg loss 0.00141236, throughput 3.30041K wps
[Epoch 126 Batch 60/62] avg loss 0.0012716, throughput 3.2092K wps
Begin Testing...
[Epoch 126] train avg loss 0.00134632, dev acc 0.8437, dev avg loss 0.367011, throughput 3.26015K wps
[Epoch 127 Batch 30/62] avg loss 0.00125708, throughput 3.28577K wps
[Epoch 127 Batch 60/62] avg loss 0.00128238, throughput 3.2252K wps
Begin Testing...
[Epoch 127] train avg loss 0.00129109, dev acc 0.8437, dev avg loss 0.367164, throughput 3.26161K wps
[Epoch 128 Batch 30/62] avg loss 0.00132779, throughput 3.28016K wps
[Epoch 128 Batch 60/62] avg loss 0.00131649, throughput 3.21647K wps
Begin Testing...
[Epoch 128] train avg loss 0.00133369, dev acc 0.8407, dev avg loss 0.359992, throughput 3.25398K wps
[Epoch 129 Batch 30/62] avg loss 0.00124418, throughput 3.25963K wps
[Epoch 129 Batch 60/62] avg loss 0.00131146, throughput 3.18957K wps
Begin Testing...
[Epoch 129] train avg loss 0.00130245, dev acc 0.8407, dev avg loss 0.358141, throughput 3.23198K wps
[Epoch 130 Batch 30/62] avg loss 0.00124364, throughput 3.2946K wps
[Epoch 130 Batch 60/62] avg loss 0.0012815, throughput 3.18738K wps
Begin Testing...
[Epoch 130] train avg loss 0.00127168, dev acc 0.8407, dev avg loss 0.359372, throughput 3.24618K wps
[Epoch 131 Batch 30/62] avg loss 0.00121318, throughput 3.30377K wps
[Epoch 131 Batch 60/62] avg loss 0.00116154, throughput 3.19114K wps
Begin Testing...
[Epoch 131] train avg loss 0.00120322, dev acc 0.8378, dev avg loss 0.363967, throughput 3.25156K wps
[Epoch 132 Batch 30/62] avg loss 0.0012771, throughput 3.2911K wps
[Epoch 132 Batch 60/62] avg loss 0.00113933, throughput 3.17692K wps
Begin Testing...
[Epoch 132] train avg loss 0.00121613, dev acc 0.8407, dev avg loss 0.360977, throughput 3.23911K wps
[Epoch 133 Batch 30/62] avg loss 0.00117319, throughput 3.25304K wps
[Epoch 133 Batch 60/62] avg loss 0.00121054, throughput 3.1693K wps
Begin Testing...
[Epoch 133] train avg loss 0.00121432, dev acc 0.8378, dev avg loss 0.36299, throughput 3.21671K wps
[Epoch 134 Batch 30/62] avg loss 0.00121614, throughput 3.25059K wps
[Epoch 134 Batch 60/62] avg loss 0.00118946, throughput 3.21433K wps
Begin Testing...
[Epoch 134] train avg loss 0.00120087, dev acc 0.8407, dev avg loss 0.367607, throughput 3.23775K wps
[Epoch 135 Batch 30/62] avg loss 0.00115523, throughput 3.27168K wps
[Epoch 135 Batch 60/62] avg loss 0.00118448, throughput 3.19251K wps
Begin Testing...
[Epoch 135] train avg loss 0.00116545, dev acc 0.8348, dev avg loss 0.360618, throughput 3.24098K wps
[Epoch 136 Batch 30/62] avg loss 0.00132467, throughput 3.30419K wps
[Epoch 136 Batch 60/62] avg loss 0.00114591, throughput 3.21559K wps
Begin Testing...
[Epoch 136] train avg loss 0.00123673, dev acc 0.8348, dev avg loss 0.358406, throughput 3.26513K wps
[Epoch 137 Batch 30/62] avg loss 0.00109798, throughput 3.27489K wps
[Epoch 137 Batch 60/62] avg loss 0.00114825, throughput 3.21244K wps
Begin Testing...
[Epoch 137] train avg loss 0.00113801, dev acc 0.8378, dev avg loss 0.357907, throughput 3.24916K wps
[Epoch 138 Batch 30/62] avg loss 0.00110574, throughput 3.27252K wps
[Epoch 138 Batch 60/62] avg loss 0.00113507, throughput 3.19848K wps
Begin Testing...
[Epoch 138] train avg loss 0.0011349, dev acc 0.8378, dev avg loss 0.359797, throughput 3.2443K wps
[Epoch 139 Batch 30/62] avg loss 0.00116585, throughput 3.29097K wps
[Epoch 139 Batch 60/62] avg loss 0.00103348, throughput 3.21775K wps
Begin Testing...
[Epoch 139] train avg loss 0.00112095, dev acc 0.8407, dev avg loss 0.371669, throughput 3.26099K wps
[Epoch 140 Batch 30/62] avg loss 0.00110233, throughput 3.28353K wps
[Epoch 140 Batch 60/62] avg loss 0.00104506, throughput 3.22104K wps
Begin Testing...
[Epoch 140] train avg loss 0.00109285, dev acc 0.8407, dev avg loss 0.368848, throughput 3.25951K wps
[Epoch 141 Batch 30/62] avg loss 0.00116118, throughput 3.27544K wps
[Epoch 141 Batch 60/62] avg loss 0.0010034, throughput 3.21171K wps
Begin Testing...
[Epoch 141] train avg loss 0.00109201, dev acc 0.8378, dev avg loss 0.35714, throughput 3.24893K wps
[Epoch 142 Batch 30/62] avg loss 0.00105058, throughput 3.27678K wps
[Epoch 142 Batch 60/62] avg loss 0.00112271, throughput 3.19323K wps
Begin Testing...
[Epoch 142] train avg loss 0.00110954, dev acc 0.8348, dev avg loss 0.363861, throughput 3.24142K wps
[Epoch 143 Batch 30/62] avg loss 0.00106065, throughput 3.28765K wps
[Epoch 143 Batch 60/62] avg loss 0.00113119, throughput 3.17444K wps
Begin Testing...
[Epoch 143] train avg loss 0.00111761, dev acc 0.8348, dev avg loss 0.359664, throughput 3.23616K wps
[Epoch 144 Batch 30/62] avg loss 0.00111546, throughput 3.26063K wps
[Epoch 144 Batch 60/62] avg loss 0.000978124, throughput 3.21219K wps
Begin Testing...
[Epoch 144] train avg loss 0.0010494, dev acc 0.8378, dev avg loss 0.362435, throughput 3.24141K wps
[Epoch 145 Batch 30/62] avg loss 0.00103372, throughput 3.27069K wps
[Epoch 145 Batch 60/62] avg loss 0.00103301, throughput 3.22977K wps
Begin Testing...
[Epoch 145] train avg loss 0.00104573, dev acc 0.8407, dev avg loss 0.371556, throughput 3.25569K wps
[Epoch 146 Batch 30/62] avg loss 0.00107151, throughput 3.27897K wps
[Epoch 146 Batch 60/62] avg loss 0.000937449, throughput 3.20806K wps
Begin Testing...
[Epoch 146] train avg loss 0.0010135, dev acc 0.8407, dev avg loss 0.357167, throughput 3.24894K wps
[Epoch 147 Batch 30/62] avg loss 0.000937385, throughput 3.26873K wps
[Epoch 147 Batch 60/62] avg loss 0.00102182, throughput 3.21552K wps
Begin Testing...
[Epoch 147] train avg loss 0.000980389, dev acc 0.8378, dev avg loss 0.367585, throughput 3.24789K wps
[Epoch 148 Batch 30/62] avg loss 0.000958023, throughput 3.28003K wps
[Epoch 148 Batch 60/62] avg loss 0.00100502, throughput 3.16741K wps
Begin Testing...
[Epoch 148] train avg loss 0.000985305, dev acc 0.8378, dev avg loss 0.368414, throughput 3.22878K wps
[Epoch 149 Batch 30/62] avg loss 0.000942727, throughput 3.25243K wps
[Epoch 149 Batch 60/62] avg loss 0.00103241, throughput 3.21069K wps
Begin Testing...
[Epoch 149] train avg loss 0.0010163, dev acc 0.8407, dev avg loss 0.357527, throughput 3.237K wps
[Epoch 150 Batch 30/62] avg loss 0.00101596, throughput 3.28223K wps
[Epoch 150 Batch 60/62] avg loss 0.00102374, throughput 3.20862K wps
Begin Testing...
[Epoch 150] train avg loss 0.00101754, dev acc 0.8348, dev avg loss 0.362247, throughput 3.25172K wps
[Epoch 151 Batch 30/62] avg loss 0.000996875, throughput 3.27902K wps
[Epoch 151 Batch 60/62] avg loss 0.000963236, throughput 3.22319K wps
Begin Testing...
[Epoch 151] train avg loss 0.00101034, dev acc 0.8407, dev avg loss 0.380382, throughput 3.25685K wps
[Epoch 152 Batch 30/62] avg loss 0.000975853, throughput 3.2903K wps
[Epoch 152 Batch 60/62] avg loss 0.000929804, throughput 3.21098K wps
Begin Testing...
[Epoch 152] train avg loss 0.000962516, dev acc 0.8348, dev avg loss 0.367438, throughput 3.25595K wps
[Epoch 153 Batch 30/62] avg loss 0.000958223, throughput 3.27474K wps
[Epoch 153 Batch 60/62] avg loss 0.00095961, throughput 3.17863K wps
Begin Testing...
[Epoch 153] train avg loss 0.000992777, dev acc 0.8378, dev avg loss 0.367361, throughput 3.23507K wps
[Epoch 154 Batch 30/62] avg loss 0.000834017, throughput 3.29963K wps
[Epoch 154 Batch 60/62] avg loss 0.000987705, throughput 3.17444K wps
Begin Testing...
[Epoch 154] train avg loss 0.000928642, dev acc 0.8348, dev avg loss 0.362757, throughput 3.24329K wps
[Epoch 155 Batch 30/62] avg loss 0.000863946, throughput 3.29465K wps
[Epoch 155 Batch 60/62] avg loss 0.000963994, throughput 3.18176K wps
Begin Testing...
[Epoch 155] train avg loss 0.000925544, dev acc 0.8378, dev avg loss 0.366348, throughput 3.244K wps
[Epoch 156 Batch 30/62] avg loss 0.000815058, throughput 3.29276K wps
[Epoch 156 Batch 60/62] avg loss 0.00095363, throughput 3.17606K wps
Begin Testing...
[Epoch 156] train avg loss 0.000899706, dev acc 0.8407, dev avg loss 0.380881, throughput 3.23752K wps
[Epoch 157 Batch 30/62] avg loss 0.000848905, throughput 3.27174K wps
[Epoch 157 Batch 60/62] avg loss 0.000890436, throughput 3.18996K wps
Begin Testing...
[Epoch 157] train avg loss 0.000887494, dev acc 0.8378, dev avg loss 0.367031, throughput 3.2385K wps
[Epoch 158 Batch 30/62] avg loss 0.000911107, throughput 3.29146K wps
[Epoch 158 Batch 60/62] avg loss 0.000940254, throughput 3.18107K wps
Begin Testing...
[Epoch 158] train avg loss 0.000929504, dev acc 0.8378, dev avg loss 0.367833, throughput 3.24103K wps
[Epoch 159 Batch 30/62] avg loss 0.000842972, throughput 3.28072K wps
[Epoch 159 Batch 60/62] avg loss 0.000827926, throughput 3.20078K wps
Begin Testing...
[Epoch 159] train avg loss 0.000858104, dev acc 0.8378, dev avg loss 0.372131, throughput 3.2455K wps
[Epoch 160 Batch 30/62] avg loss 0.000911047, throughput 3.25529K wps
[Epoch 160 Batch 60/62] avg loss 0.000821974, throughput 3.17771K wps
Begin Testing...
[Epoch 160] train avg loss 0.000876996, dev acc 0.8378, dev avg loss 0.367385, throughput 3.22363K wps
[Epoch 161 Batch 30/62] avg loss 0.000889614, throughput 3.30194K wps
[Epoch 161 Batch 60/62] avg loss 0.000819413, throughput 3.19659K wps
Begin Testing...
[Epoch 161] train avg loss 0.000885062, dev acc 0.8407, dev avg loss 0.375109, throughput 3.25664K wps
[Epoch 162 Batch 30/62] avg loss 0.000782905, throughput 3.30086K wps
[Epoch 162 Batch 60/62] avg loss 0.000863467, throughput 3.17833K wps
Begin Testing...
[Epoch 162] train avg loss 0.000833695, dev acc 0.8319, dev avg loss 0.364556, throughput 3.24576K wps
[Epoch 163 Batch 30/62] avg loss 0.000789817, throughput 3.2715K wps
[Epoch 163 Batch 60/62] avg loss 0.000825813, throughput 3.19841K wps
Begin Testing...
[Epoch 163] train avg loss 0.00081139, dev acc 0.8348, dev avg loss 0.365564, throughput 3.2394K wps
[Epoch 164 Batch 30/62] avg loss 0.000908308, throughput 3.27557K wps
[Epoch 164 Batch 60/62] avg loss 0.000832743, throughput 3.21241K wps
Begin Testing...
[Epoch 164] train avg loss 0.000873637, dev acc 0.8348, dev avg loss 0.366486, throughput 3.25029K wps
[Epoch 165 Batch 30/62] avg loss 0.000751402, throughput 3.27662K wps
[Epoch 165 Batch 60/62] avg loss 0.000831091, throughput 3.21346K wps
Begin Testing...
[Epoch 165] train avg loss 0.000819939, dev acc 0.8319, dev avg loss 0.362444, throughput 3.25091K wps
[Epoch 166 Batch 30/62] avg loss 0.000744577, throughput 3.29459K wps
[Epoch 166 Batch 60/62] avg loss 0.000836014, throughput 3.15803K wps
Begin Testing...
[Epoch 166] train avg loss 0.000794102, dev acc 0.8348, dev avg loss 0.371377, throughput 3.23356K wps
[Epoch 167 Batch 30/62] avg loss 0.00078959, throughput 3.3016K wps
[Epoch 167 Batch 60/62] avg loss 0.000806224, throughput 3.19075K wps
Begin Testing...
[Epoch 167] train avg loss 0.000799856, dev acc 0.8319, dev avg loss 0.368492, throughput 3.25234K wps
[Epoch 168 Batch 30/62] avg loss 0.000759852, throughput 3.29096K wps
[Epoch 168 Batch 60/62] avg loss 0.000736719, throughput 3.18165K wps
Begin Testing...
[Epoch 168] train avg loss 0.000746144, dev acc 0.8348, dev avg loss 0.3703, throughput 3.24099K wps
[Epoch 169 Batch 30/62] avg loss 0.000730131, throughput 3.24523K wps
[Epoch 169 Batch 60/62] avg loss 0.000805791, throughput 3.16813K wps
Begin Testing...
[Epoch 169] train avg loss 0.000772457, dev acc 0.8378, dev avg loss 0.374893, throughput 3.21454K wps
[Epoch 170 Batch 30/62] avg loss 0.00079159, throughput 3.26139K wps
[Epoch 170 Batch 60/62] avg loss 0.000753976, throughput 3.20127K wps
Begin Testing...
[Epoch 170] train avg loss 0.000777555, dev acc 0.8319, dev avg loss 0.370963, throughput 3.23705K wps
[Epoch 171 Batch 30/62] avg loss 0.000802691, throughput 3.26284K wps
[Epoch 171 Batch 60/62] avg loss 0.000694021, throughput 3.18907K wps
Begin Testing...
[Epoch 171] train avg loss 0.000746523, dev acc 0.8289, dev avg loss 0.369632, throughput 3.23517K wps
[Epoch 172 Batch 30/62] avg loss 0.000732253, throughput 3.28352K wps
[Epoch 172 Batch 60/62] avg loss 0.000772034, throughput 3.19403K wps
Begin Testing...
[Epoch 172] train avg loss 0.000758835, dev acc 0.8319, dev avg loss 0.368034, throughput 3.24553K wps
[Epoch 173 Batch 30/62] avg loss 0.000767986, throughput 3.3015K wps
[Epoch 173 Batch 60/62] avg loss 0.000745226, throughput 3.17786K wps
Begin Testing...
[Epoch 173] train avg loss 0.000762458, dev acc 0.8378, dev avg loss 0.375274, throughput 3.24681K wps
[Epoch 174 Batch 30/62] avg loss 0.000735189, throughput 3.30148K wps
[Epoch 174 Batch 60/62] avg loss 0.000770924, throughput 3.19117K wps
Begin Testing...
[Epoch 174] train avg loss 0.000764253, dev acc 0.8260, dev avg loss 0.371556, throughput 3.25381K wps
[Epoch 175 Batch 30/62] avg loss 0.000715061, throughput 3.28246K wps
[Epoch 175 Batch 60/62] avg loss 0.000740247, throughput 3.17127K wps
Begin Testing...
[Epoch 175] train avg loss 0.000727585, dev acc 0.8289, dev avg loss 0.367881, throughput 3.23129K wps
[Epoch 176 Batch 30/62] avg loss 0.000720873, throughput 3.26101K wps
[Epoch 176 Batch 60/62] avg loss 0.000789448, throughput 3.2309K wps
Begin Testing...
[Epoch 176] train avg loss 0.000760686, dev acc 0.8260, dev avg loss 0.371099, throughput 3.25172K wps
[Epoch 177 Batch 30/62] avg loss 0.00078627, throughput 3.26827K wps
[Epoch 177 Batch 60/62] avg loss 0.000660123, throughput 3.21106K wps
Begin Testing...
[Epoch 177] train avg loss 0.000728309, dev acc 0.8289, dev avg loss 0.368349, throughput 3.24681K wps
[Epoch 178 Batch 30/62] avg loss 0.000757175, throughput 3.28683K wps
[Epoch 178 Batch 60/62] avg loss 0.000676432, throughput 3.20766K wps
Begin Testing...
[Epoch 178] train avg loss 0.000732942, dev acc 0.8407, dev avg loss 0.380663, throughput 3.25272K wps
[Epoch 179 Batch 30/62] avg loss 0.000743697, throughput 3.29284K wps
[Epoch 179 Batch 60/62] avg loss 0.000670995, throughput 3.20646K wps
Begin Testing...
[Epoch 179] train avg loss 0.000712885, dev acc 0.8407, dev avg loss 0.381185, throughput 3.25474K wps
[Epoch 180 Batch 30/62] avg loss 0.000718095, throughput 3.28044K wps
[Epoch 180 Batch 60/62] avg loss 0.000745981, throughput 3.21744K wps
Begin Testing...
[Epoch 180] train avg loss 0.000731757, dev acc 0.8289, dev avg loss 0.374633, throughput 3.25624K wps
[Epoch 181 Batch 30/62] avg loss 0.000626684, throughput 3.28304K wps
[Epoch 181 Batch 60/62] avg loss 0.000719398, throughput 3.21285K wps
Begin Testing...
[Epoch 181] train avg loss 0.000678236, dev acc 0.8289, dev avg loss 0.369976, throughput 3.25356K wps
[Epoch 182 Batch 30/62] avg loss 0.000656489, throughput 3.27327K wps
[Epoch 182 Batch 60/62] avg loss 0.000677589, throughput 3.18023K wps
Begin Testing...
[Epoch 182] train avg loss 0.000693718, dev acc 0.8407, dev avg loss 0.392833, throughput 3.23291K wps
[Epoch 183 Batch 30/62] avg loss 0.00065765, throughput 3.2639K wps
[Epoch 183 Batch 60/62] avg loss 0.000738727, throughput 3.20275K wps
Begin Testing...
[Epoch 183] train avg loss 0.000698408, dev acc 0.8319, dev avg loss 0.374975, throughput 3.23981K wps
[Epoch 184 Batch 30/62] avg loss 0.000669154, throughput 3.27981K wps
[Epoch 184 Batch 60/62] avg loss 0.000649265, throughput 3.20648K wps
Begin Testing...
[Epoch 184] train avg loss 0.000668772, dev acc 0.8289, dev avg loss 0.372025, throughput 3.2481K wps
[Epoch 185 Batch 30/62] avg loss 0.00070901, throughput 3.24914K wps
[Epoch 185 Batch 60/62] avg loss 0.000621253, throughput 3.17784K wps
Begin Testing...
[Epoch 185] train avg loss 0.000674874, dev acc 0.8289, dev avg loss 0.372502, throughput 3.22173K wps
[Epoch 186 Batch 30/62] avg loss 0.000654205, throughput 3.29061K wps
[Epoch 186 Batch 60/62] avg loss 0.000663266, throughput 3.19354K wps
Begin Testing...
[Epoch 186] train avg loss 0.00068326, dev acc 0.8378, dev avg loss 0.368832, throughput 3.24692K wps
[Epoch 187 Batch 30/62] avg loss 0.000661272, throughput 3.30328K wps
[Epoch 187 Batch 60/62] avg loss 0.000605259, throughput 3.18636K wps
Begin Testing...
[Epoch 187] train avg loss 0.000638065, dev acc 0.8319, dev avg loss 0.369238, throughput 3.24993K wps
[Epoch 188 Batch 30/62] avg loss 0.000689209, throughput 3.2654K wps
[Epoch 188 Batch 60/62] avg loss 0.000631731, throughput 3.2134K wps
Begin Testing...
[Epoch 188] train avg loss 0.000661428, dev acc 0.8348, dev avg loss 0.378611, throughput 3.24525K wps
[Epoch 189 Batch 30/62] avg loss 0.000631743, throughput 3.25084K wps
[Epoch 189 Batch 60/62] avg loss 0.000653525, throughput 3.21407K wps
Begin Testing...
[Epoch 189] train avg loss 0.000653927, dev acc 0.8348, dev avg loss 0.378171, throughput 3.23759K wps
[Epoch 190 Batch 30/62] avg loss 0.000586755, throughput 3.26115K wps
[Epoch 190 Batch 60/62] avg loss 0.000663671, throughput 3.17842K wps
Begin Testing...
[Epoch 190] train avg loss 0.000631412, dev acc 0.8289, dev avg loss 0.377224, throughput 3.22637K wps
[Epoch 191 Batch 30/62] avg loss 0.000581811, throughput 3.26837K wps
[Epoch 191 Batch 60/62] avg loss 0.000618533, throughput 3.22254K wps
Begin Testing...
[Epoch 191] train avg loss 0.000597678, dev acc 0.8289, dev avg loss 0.372493, throughput 3.25172K wps
[Epoch 192 Batch 30/62] avg loss 0.000599149, throughput 3.27404K wps
[Epoch 192 Batch 60/62] avg loss 0.000602213, throughput 3.20742K wps
Begin Testing...
[Epoch 192] train avg loss 0.000616813, dev acc 0.8289, dev avg loss 0.377616, throughput 3.24569K wps
[Epoch 193 Batch 30/62] avg loss 0.000592635, throughput 3.26457K wps
[Epoch 193 Batch 60/62] avg loss 0.000673795, throughput 3.20041K wps
Begin Testing...
[Epoch 193] train avg loss 0.000644336, dev acc 0.8289, dev avg loss 0.375532, throughput 3.24061K wps
[Epoch 194 Batch 30/62] avg loss 0.000598357, throughput 3.29863K wps
[Epoch 194 Batch 60/62] avg loss 0.000639597, throughput 3.21926K wps
Begin Testing...
[Epoch 194] train avg loss 0.000619099, dev acc 0.8289, dev avg loss 0.377668, throughput 3.26317K wps
[Epoch 195 Batch 30/62] avg loss 0.000562178, throughput 3.26787K wps
[Epoch 195 Batch 60/62] avg loss 0.000629869, throughput 3.19188K wps
Begin Testing...
[Epoch 195] train avg loss 0.000602524, dev acc 0.8319, dev avg loss 0.380947, throughput 3.23755K wps
[Epoch 196 Batch 30/62] avg loss 0.000552511, throughput 3.288K wps
[Epoch 196 Batch 60/62] avg loss 0.000544043, throughput 3.18085K wps
Begin Testing...
[Epoch 196] train avg loss 0.000555254, dev acc 0.8348, dev avg loss 0.380569, throughput 3.2409K wps
[Epoch 197 Batch 30/62] avg loss 0.000619933, throughput 3.28066K wps
[Epoch 197 Batch 60/62] avg loss 0.000631119, throughput 3.18059K wps
Begin Testing...
[Epoch 197] train avg loss 0.000627421, dev acc 0.8319, dev avg loss 0.379489, throughput 3.2369K wps
[Epoch 198 Batch 30/62] avg loss 0.000582143, throughput 3.25659K wps
[Epoch 198 Batch 60/62] avg loss 0.000581697, throughput 3.22316K wps
Begin Testing...
[Epoch 198] train avg loss 0.000580109, dev acc 0.8348, dev avg loss 0.376297, throughput 3.24556K wps
[Epoch 199 Batch 30/62] avg loss 0.000545574, throughput 3.27177K wps
[Epoch 199 Batch 60/62] avg loss 0.000596361, throughput 3.20536K wps
Begin Testing...
[Epoch 199] train avg loss 0.000580485, dev acc 0.8319, dev avg loss 0.37917, throughput 3.24551K wps
Test loss 0.46364, test acc 0.7984
Total time cost 418.98s
[Epoch 0 Batch 30/62] avg loss 0.0135988, throughput 3.07612K wps
[Epoch 0 Batch 60/62] avg loss 0.0132434, throughput 3.17548K wps
Begin Testing...
[Epoch 0] train avg loss 0.0136172, dev acc 0.6519, dev avg loss 0.647467, throughput 3.13337K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0131196, throughput 3.27821K wps
[Epoch 1 Batch 60/62] avg loss 0.0129127, throughput 3.18706K wps
Begin Testing...
[Epoch 1] train avg loss 0.0131801, dev acc 0.6519, dev avg loss 0.63404, throughput 3.23944K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.012847, throughput 3.25127K wps
[Epoch 2 Batch 60/62] avg loss 0.0127617, throughput 3.21302K wps
Begin Testing...
[Epoch 2] train avg loss 0.0129818, dev acc 0.6519, dev avg loss 0.626937, throughput 3.2393K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0128267, throughput 3.28836K wps
[Epoch 3 Batch 60/62] avg loss 0.0126126, throughput 3.21942K wps
Begin Testing...
[Epoch 3] train avg loss 0.0128398, dev acc 0.6519, dev avg loss 0.622171, throughput 3.25979K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0125171, throughput 3.29741K wps
[Epoch 4 Batch 60/62] avg loss 0.0125024, throughput 3.20623K wps
Begin Testing...
[Epoch 4] train avg loss 0.012738, dev acc 0.6608, dev avg loss 0.625115, throughput 3.25802K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0123477, throughput 3.30344K wps
[Epoch 5 Batch 60/62] avg loss 0.0123694, throughput 3.19102K wps
Begin Testing...
[Epoch 5] train avg loss 0.0125793, dev acc 0.6519, dev avg loss 0.608399, throughput 3.25428K wps
[Epoch 6 Batch 30/62] avg loss 0.0121657, throughput 3.29403K wps
[Epoch 6 Batch 60/62] avg loss 0.0122083, throughput 3.15754K wps
Begin Testing...
[Epoch 6] train avg loss 0.0123517, dev acc 0.6519, dev avg loss 0.599666, throughput 3.2295K wps
[Epoch 7 Batch 30/62] avg loss 0.012159, throughput 3.25564K wps
[Epoch 7 Batch 60/62] avg loss 0.01196, throughput 3.20075K wps
Begin Testing...
[Epoch 7] train avg loss 0.012199, dev acc 0.6608, dev avg loss 0.592432, throughput 3.23544K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0118962, throughput 3.30423K wps
[Epoch 8 Batch 60/62] avg loss 0.0117092, throughput 3.14876K wps
Begin Testing...
[Epoch 8] train avg loss 0.0119001, dev acc 0.6519, dev avg loss 0.583778, throughput 3.2317K wps
[Epoch 9 Batch 30/62] avg loss 0.0116636, throughput 3.25181K wps
[Epoch 9 Batch 60/62] avg loss 0.011496, throughput 3.15583K wps
Begin Testing...
[Epoch 9] train avg loss 0.011735, dev acc 0.6637, dev avg loss 0.575374, throughput 3.2082K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0112497, throughput 3.26693K wps
[Epoch 10 Batch 60/62] avg loss 0.0115087, throughput 3.1657K wps
Begin Testing...
[Epoch 10] train avg loss 0.0115498, dev acc 0.6637, dev avg loss 0.566716, throughput 3.22078K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0111908, throughput 3.27385K wps
[Epoch 11 Batch 60/62] avg loss 0.0109861, throughput 3.16364K wps
Begin Testing...
[Epoch 11] train avg loss 0.0112357, dev acc 0.6844, dev avg loss 0.558158, throughput 3.22435K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0108407, throughput 3.26695K wps
[Epoch 12 Batch 60/62] avg loss 0.010912, throughput 3.16432K wps
Begin Testing...
[Epoch 12] train avg loss 0.0110181, dev acc 0.6903, dev avg loss 0.549551, throughput 3.22072K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0110078, throughput 3.28758K wps
[Epoch 13 Batch 60/62] avg loss 0.01057, throughput 3.1753K wps
Begin Testing...
[Epoch 13] train avg loss 0.0109355, dev acc 0.6873, dev avg loss 0.541828, throughput 3.23881K wps
[Epoch 14 Batch 30/62] avg loss 0.0105836, throughput 3.28976K wps
[Epoch 14 Batch 60/62] avg loss 0.0105359, throughput 3.15741K wps
Begin Testing...
[Epoch 14] train avg loss 0.0106786, dev acc 0.7139, dev avg loss 0.532701, throughput 3.22835K wps
Observed Improvement.
Begin Testing...
[Epoch 15 Batch 30/62] avg loss 0.0102543, throughput 3.27261K wps
[Epoch 15 Batch 60/62] avg loss 0.0103391, throughput 3.18197K wps
Begin Testing...
[Epoch 15] train avg loss 0.0104676, dev acc 0.7257, dev avg loss 0.524834, throughput 3.2346K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.010137, throughput 3.26745K wps
[Epoch 16 Batch 60/62] avg loss 0.00991986, throughput 3.21705K wps
Begin Testing...
[Epoch 16] train avg loss 0.0102242, dev acc 0.7493, dev avg loss 0.518476, throughput 3.24752K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.00975755, throughput 3.28716K wps
[Epoch 17 Batch 60/62] avg loss 0.00991787, throughput 3.22419K wps
Begin Testing...
[Epoch 17] train avg loss 0.00998808, dev acc 0.7670, dev avg loss 0.512133, throughput 3.26093K wps
Observed Improvement.
Begin Testing...
[Epoch 18 Batch 30/62] avg loss 0.00987758, throughput 3.28905K wps
[Epoch 18 Batch 60/62] avg loss 0.00943221, throughput 3.22303K wps
Begin Testing...
[Epoch 18] train avg loss 0.00980649, dev acc 0.7552, dev avg loss 0.500904, throughput 3.26221K wps
[Epoch 19 Batch 30/62] avg loss 0.00930043, throughput 3.28597K wps
[Epoch 19 Batch 60/62] avg loss 0.00957792, throughput 3.21649K wps
Begin Testing...
[Epoch 19] train avg loss 0.00962763, dev acc 0.7581, dev avg loss 0.495123, throughput 3.25692K wps
[Epoch 20 Batch 30/62] avg loss 0.0090317, throughput 3.28606K wps
[Epoch 20 Batch 60/62] avg loss 0.00933591, throughput 3.21468K wps
Begin Testing...
[Epoch 20] train avg loss 0.0093422, dev acc 0.7581, dev avg loss 0.487922, throughput 3.25583K wps
[Epoch 21 Batch 30/62] avg loss 0.00890054, throughput 3.26489K wps
[Epoch 21 Batch 60/62] avg loss 0.00941401, throughput 3.18541K wps
Begin Testing...
[Epoch 21] train avg loss 0.00928898, dev acc 0.7581, dev avg loss 0.482541, throughput 3.23293K wps
[Epoch 22 Batch 30/62] avg loss 0.00882174, throughput 3.29708K wps
[Epoch 22 Batch 60/62] avg loss 0.00896749, throughput 3.1543K wps
Begin Testing...
[Epoch 22] train avg loss 0.00905789, dev acc 0.7699, dev avg loss 0.477979, throughput 3.22954K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00889996, throughput 3.27502K wps
[Epoch 23 Batch 60/62] avg loss 0.00858731, throughput 3.15731K wps
Begin Testing...
[Epoch 23] train avg loss 0.00884522, dev acc 0.7699, dev avg loss 0.471361, throughput 3.22152K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.00835701, throughput 3.27672K wps
[Epoch 24 Batch 60/62] avg loss 0.00858499, throughput 3.17218K wps
Begin Testing...
[Epoch 24] train avg loss 0.0086254, dev acc 0.7699, dev avg loss 0.46809, throughput 3.22969K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00829707, throughput 3.26993K wps
[Epoch 25 Batch 60/62] avg loss 0.00848787, throughput 3.19144K wps
Begin Testing...
[Epoch 25] train avg loss 0.00844234, dev acc 0.7847, dev avg loss 0.461773, throughput 3.23855K wps
Observed Improvement.
Begin Testing...
[Epoch 26 Batch 30/62] avg loss 0.0083039, throughput 3.23527K wps
[Epoch 26 Batch 60/62] avg loss 0.00829696, throughput 3.2062K wps
Begin Testing...
[Epoch 26] train avg loss 0.00838336, dev acc 0.7699, dev avg loss 0.460659, throughput 3.22898K wps
[Epoch 27 Batch 30/62] avg loss 0.0079182, throughput 3.28198K wps
[Epoch 27 Batch 60/62] avg loss 0.00830019, throughput 3.19252K wps
Begin Testing...
[Epoch 27] train avg loss 0.00822666, dev acc 0.7699, dev avg loss 0.458351, throughput 3.24501K wps
[Epoch 28 Batch 30/62] avg loss 0.00801627, throughput 3.29508K wps
[Epoch 28 Batch 60/62] avg loss 0.00787325, throughput 3.19669K wps
Begin Testing...
[Epoch 28] train avg loss 0.00803164, dev acc 0.7906, dev avg loss 0.449456, throughput 3.25376K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00784389, throughput 3.30748K wps
[Epoch 29 Batch 60/62] avg loss 0.00792542, throughput 3.20476K wps
Begin Testing...
[Epoch 29] train avg loss 0.00797006, dev acc 0.7817, dev avg loss 0.446818, throughput 3.2638K wps
[Epoch 30 Batch 30/62] avg loss 0.00759588, throughput 3.28568K wps
[Epoch 30 Batch 60/62] avg loss 0.007786, throughput 3.18828K wps
Begin Testing...
[Epoch 30] train avg loss 0.00782183, dev acc 0.7758, dev avg loss 0.444959, throughput 3.24472K wps
[Epoch 31 Batch 30/62] avg loss 0.00758795, throughput 3.30678K wps
[Epoch 31 Batch 60/62] avg loss 0.00726941, throughput 3.22677K wps
Begin Testing...
[Epoch 31] train avg loss 0.00760351, dev acc 0.7729, dev avg loss 0.444847, throughput 3.27329K wps
[Epoch 32 Batch 30/62] avg loss 0.00750058, throughput 3.28135K wps
[Epoch 32 Batch 60/62] avg loss 0.00744035, throughput 3.22462K wps
Begin Testing...
[Epoch 32] train avg loss 0.00757447, dev acc 0.7817, dev avg loss 0.437787, throughput 3.25921K wps
[Epoch 33 Batch 30/62] avg loss 0.00744395, throughput 3.25508K wps
[Epoch 33 Batch 60/62] avg loss 0.00718094, throughput 3.17301K wps
Begin Testing...
[Epoch 33] train avg loss 0.00744627, dev acc 0.7670, dev avg loss 0.435091, throughput 3.22144K wps
[Epoch 34 Batch 30/62] avg loss 0.00685772, throughput 3.27061K wps
[Epoch 34 Batch 60/62] avg loss 0.00711602, throughput 3.19284K wps
Begin Testing...
[Epoch 34] train avg loss 0.00706256, dev acc 0.7729, dev avg loss 0.435481, throughput 3.23697K wps
[Epoch 35 Batch 30/62] avg loss 0.00699583, throughput 3.27322K wps
[Epoch 35 Batch 60/62] avg loss 0.00689417, throughput 3.20641K wps
Begin Testing...
[Epoch 35] train avg loss 0.00713527, dev acc 0.7788, dev avg loss 0.428701, throughput 3.24775K wps
[Epoch 36 Batch 30/62] avg loss 0.00682426, throughput 3.27414K wps
[Epoch 36 Batch 60/62] avg loss 0.00674794, throughput 3.21012K wps
Begin Testing...
[Epoch 36] train avg loss 0.00691981, dev acc 0.7670, dev avg loss 0.428823, throughput 3.24709K wps
[Epoch 37 Batch 30/62] avg loss 0.00674785, throughput 3.27772K wps
[Epoch 37 Batch 60/62] avg loss 0.00681875, throughput 3.1676K wps
Begin Testing...
[Epoch 37] train avg loss 0.00689934, dev acc 0.7699, dev avg loss 0.424804, throughput 3.2274K wps
[Epoch 38 Batch 30/62] avg loss 0.00690042, throughput 3.23612K wps
[Epoch 38 Batch 60/62] avg loss 0.00647066, throughput 3.15973K wps
Begin Testing...
[Epoch 38] train avg loss 0.00677602, dev acc 0.7906, dev avg loss 0.422237, throughput 3.2035K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.0063824, throughput 3.274K wps
[Epoch 39 Batch 60/62] avg loss 0.00641894, throughput 3.15888K wps
Begin Testing...
[Epoch 39] train avg loss 0.00651738, dev acc 0.7729, dev avg loss 0.41946, throughput 3.22197K wps
[Epoch 40 Batch 30/62] avg loss 0.00621482, throughput 3.26766K wps
[Epoch 40 Batch 60/62] avg loss 0.00653204, throughput 3.21208K wps
Begin Testing...
[Epoch 40] train avg loss 0.0064339, dev acc 0.8024, dev avg loss 0.417913, throughput 3.24492K wps
Observed Improvement.
Begin Testing...
[Epoch 41 Batch 30/62] avg loss 0.00637926, throughput 3.27939K wps
[Epoch 41 Batch 60/62] avg loss 0.00623838, throughput 3.20944K wps
Begin Testing...
[Epoch 41] train avg loss 0.00631374, dev acc 0.7935, dev avg loss 0.414448, throughput 3.25341K wps
[Epoch 42 Batch 30/62] avg loss 0.00620401, throughput 3.30478K wps
[Epoch 42 Batch 60/62] avg loss 0.00624421, throughput 3.19615K wps
Begin Testing...
[Epoch 42] train avg loss 0.00628098, dev acc 0.7935, dev avg loss 0.412902, throughput 3.25799K wps
[Epoch 43 Batch 30/62] avg loss 0.00600348, throughput 3.29622K wps
[Epoch 43 Batch 60/62] avg loss 0.00609059, throughput 3.18126K wps
Begin Testing...
[Epoch 43] train avg loss 0.00606519, dev acc 0.8053, dev avg loss 0.411595, throughput 3.24491K wps
Observed Improvement.
Begin Testing...
[Epoch 44 Batch 30/62] avg loss 0.00586722, throughput 3.25279K wps
[Epoch 44 Batch 60/62] avg loss 0.00602506, throughput 3.19687K wps
Begin Testing...
[Epoch 44] train avg loss 0.00596877, dev acc 0.7994, dev avg loss 0.411734, throughput 3.2312K wps
[Epoch 45 Batch 30/62] avg loss 0.00582187, throughput 3.28004K wps
[Epoch 45 Batch 60/62] avg loss 0.00567386, throughput 3.20341K wps
Begin Testing...
[Epoch 45] train avg loss 0.00580712, dev acc 0.7965, dev avg loss 0.40767, throughput 3.2498K wps
[Epoch 46 Batch 30/62] avg loss 0.00569979, throughput 3.27548K wps
[Epoch 46 Batch 60/62] avg loss 0.00572071, throughput 3.18314K wps
Begin Testing...
[Epoch 46] train avg loss 0.00577221, dev acc 0.7906, dev avg loss 0.406084, throughput 3.23555K wps
[Epoch 47 Batch 30/62] avg loss 0.00579018, throughput 3.24689K wps
[Epoch 47 Batch 60/62] avg loss 0.00558671, throughput 3.22579K wps
Begin Testing...
[Epoch 47] train avg loss 0.00572095, dev acc 0.7906, dev avg loss 0.404976, throughput 3.24292K wps
[Epoch 48 Batch 30/62] avg loss 0.00557248, throughput 3.26847K wps
[Epoch 48 Batch 60/62] avg loss 0.0055189, throughput 3.20996K wps
Begin Testing...
[Epoch 48] train avg loss 0.00560293, dev acc 0.7965, dev avg loss 0.404667, throughput 3.24615K wps
[Epoch 49 Batch 30/62] avg loss 0.00531935, throughput 3.27314K wps
[Epoch 49 Batch 60/62] avg loss 0.00547086, throughput 3.2022K wps
Begin Testing...
[Epoch 49] train avg loss 0.00542781, dev acc 0.8024, dev avg loss 0.404921, throughput 3.24544K wps
[Epoch 50 Batch 30/62] avg loss 0.00530507, throughput 3.29485K wps
[Epoch 50 Batch 60/62] avg loss 0.00531167, throughput 3.22959K wps
Begin Testing...
[Epoch 50] train avg loss 0.00535771, dev acc 0.7994, dev avg loss 0.401989, throughput 3.268K wps
[Epoch 51 Batch 30/62] avg loss 0.00508944, throughput 3.30255K wps
[Epoch 51 Batch 60/62] avg loss 0.00527456, throughput 3.23103K wps
Begin Testing...
[Epoch 51] train avg loss 0.00523141, dev acc 0.7965, dev avg loss 0.401328, throughput 3.27237K wps
[Epoch 52 Batch 30/62] avg loss 0.00511404, throughput 3.30445K wps
[Epoch 52 Batch 60/62] avg loss 0.00523911, throughput 3.23479K wps
Begin Testing...
[Epoch 52] train avg loss 0.00518645, dev acc 0.7994, dev avg loss 0.400044, throughput 3.27696K wps
[Epoch 53 Batch 30/62] avg loss 0.00476582, throughput 3.32296K wps
[Epoch 53 Batch 60/62] avg loss 0.00503626, throughput 3.23234K wps
Begin Testing...
[Epoch 53] train avg loss 0.00502856, dev acc 0.7994, dev avg loss 0.400336, throughput 3.28349K wps
[Epoch 54 Batch 30/62] avg loss 0.00480154, throughput 3.32208K wps
[Epoch 54 Batch 60/62] avg loss 0.00504102, throughput 3.20844K wps
Begin Testing...
[Epoch 54] train avg loss 0.00497418, dev acc 0.7847, dev avg loss 0.396772, throughput 3.27078K wps
[Epoch 55 Batch 30/62] avg loss 0.00497097, throughput 3.29221K wps
[Epoch 55 Batch 60/62] avg loss 0.00484619, throughput 3.23247K wps
Begin Testing...
[Epoch 55] train avg loss 0.00498467, dev acc 0.7876, dev avg loss 0.395954, throughput 3.27007K wps
[Epoch 56 Batch 30/62] avg loss 0.0047616, throughput 3.30315K wps
[Epoch 56 Batch 60/62] avg loss 0.00480701, throughput 3.2348K wps
Begin Testing...
[Epoch 56] train avg loss 0.0048062, dev acc 0.7994, dev avg loss 0.396443, throughput 3.275K wps
[Epoch 57 Batch 30/62] avg loss 0.00447137, throughput 3.31008K wps
[Epoch 57 Batch 60/62] avg loss 0.00485845, throughput 3.23851K wps
Begin Testing...
[Epoch 57] train avg loss 0.00481495, dev acc 0.7994, dev avg loss 0.404368, throughput 3.28077K wps
[Epoch 58 Batch 30/62] avg loss 0.0045991, throughput 3.30467K wps
[Epoch 58 Batch 60/62] avg loss 0.00442338, throughput 3.23571K wps
Begin Testing...
[Epoch 58] train avg loss 0.00454603, dev acc 0.7935, dev avg loss 0.394301, throughput 3.27563K wps
[Epoch 59 Batch 30/62] avg loss 0.00445463, throughput 3.28243K wps
[Epoch 59 Batch 60/62] avg loss 0.00457926, throughput 3.23287K wps
Begin Testing...
[Epoch 59] train avg loss 0.00452777, dev acc 0.7906, dev avg loss 0.392518, throughput 3.26376K wps
[Epoch 60 Batch 30/62] avg loss 0.00433362, throughput 3.30278K wps
[Epoch 60 Batch 60/62] avg loss 0.00451223, throughput 3.22734K wps
Begin Testing...
[Epoch 60] train avg loss 0.00457571, dev acc 0.7935, dev avg loss 0.392382, throughput 3.27233K wps
[Epoch 61 Batch 30/62] avg loss 0.00442705, throughput 3.3151K wps
[Epoch 61 Batch 60/62] avg loss 0.00430613, throughput 3.21729K wps
Begin Testing...
[Epoch 61] train avg loss 0.00445825, dev acc 0.7906, dev avg loss 0.39326, throughput 3.27267K wps
[Epoch 62 Batch 30/62] avg loss 0.00433605, throughput 3.30482K wps
[Epoch 62 Batch 60/62] avg loss 0.00421098, throughput 3.23514K wps
Begin Testing...
[Epoch 62] train avg loss 0.00431096, dev acc 0.7876, dev avg loss 0.390675, throughput 3.27489K wps
[Epoch 63 Batch 30/62] avg loss 0.00398901, throughput 3.3155K wps
[Epoch 63 Batch 60/62] avg loss 0.0042724, throughput 3.22398K wps
Begin Testing...
[Epoch 63] train avg loss 0.00418294, dev acc 0.7906, dev avg loss 0.390385, throughput 3.27799K wps
[Epoch 64 Batch 30/62] avg loss 0.00420414, throughput 3.33918K wps
[Epoch 64 Batch 60/62] avg loss 0.00402513, throughput 3.24637K wps
Begin Testing...
[Epoch 64] train avg loss 0.00421979, dev acc 0.7935, dev avg loss 0.393808, throughput 3.29943K wps
[Epoch 65 Batch 30/62] avg loss 0.00406493, throughput 3.3396K wps
[Epoch 65 Batch 60/62] avg loss 0.00385504, throughput 3.24932K wps
Begin Testing...
[Epoch 65] train avg loss 0.00401604, dev acc 0.7935, dev avg loss 0.39036, throughput 3.30001K wps
[Epoch 66 Batch 30/62] avg loss 0.00394069, throughput 3.33809K wps
[Epoch 66 Batch 60/62] avg loss 0.00382116, throughput 3.2512K wps
Begin Testing...
[Epoch 66] train avg loss 0.00392616, dev acc 0.7935, dev avg loss 0.38714, throughput 3.29895K wps
[Epoch 67 Batch 30/62] avg loss 0.00375044, throughput 3.32197K wps
[Epoch 67 Batch 60/62] avg loss 0.00380135, throughput 3.24597K wps
Begin Testing...
[Epoch 67] train avg loss 0.00387912, dev acc 0.7876, dev avg loss 0.387948, throughput 3.29091K wps
[Epoch 68 Batch 30/62] avg loss 0.00376601, throughput 3.30317K wps
[Epoch 68 Batch 60/62] avg loss 0.00379733, throughput 3.22063K wps
Begin Testing...
[Epoch 68] train avg loss 0.00380448, dev acc 0.7935, dev avg loss 0.392111, throughput 3.26674K wps
[Epoch 69 Batch 30/62] avg loss 0.00363533, throughput 3.28768K wps
[Epoch 69 Batch 60/62] avg loss 0.0037506, throughput 3.2455K wps
Begin Testing...
[Epoch 69] train avg loss 0.00378193, dev acc 0.7965, dev avg loss 0.388561, throughput 3.2728K wps
[Epoch 70 Batch 30/62] avg loss 0.00349258, throughput 3.33149K wps
[Epoch 70 Batch 60/62] avg loss 0.00369474, throughput 3.24836K wps
Begin Testing...
[Epoch 70] train avg loss 0.00362986, dev acc 0.7906, dev avg loss 0.385605, throughput 3.29413K wps
[Epoch 71 Batch 30/62] avg loss 0.00356163, throughput 3.31746K wps
[Epoch 71 Batch 60/62] avg loss 0.00349409, throughput 3.22635K wps
Begin Testing...
[Epoch 71] train avg loss 0.00356146, dev acc 0.7935, dev avg loss 0.384185, throughput 3.27876K wps
[Epoch 72 Batch 30/62] avg loss 0.00357206, throughput 3.30512K wps
[Epoch 72 Batch 60/62] avg loss 0.00336446, throughput 3.20713K wps
Begin Testing...
[Epoch 72] train avg loss 0.00351785, dev acc 0.7994, dev avg loss 0.387739, throughput 3.26328K wps
[Epoch 73 Batch 30/62] avg loss 0.00341728, throughput 3.30796K wps
[Epoch 73 Batch 60/62] avg loss 0.00349126, throughput 3.22739K wps
Begin Testing...
[Epoch 73] train avg loss 0.00350029, dev acc 0.7994, dev avg loss 0.385615, throughput 3.27438K wps
[Epoch 74 Batch 30/62] avg loss 0.00324248, throughput 3.29484K wps
[Epoch 74 Batch 60/62] avg loss 0.00334779, throughput 3.23222K wps
Begin Testing...
[Epoch 74] train avg loss 0.00331891, dev acc 0.7994, dev avg loss 0.383615, throughput 3.2703K wps
[Epoch 75 Batch 30/62] avg loss 0.00333996, throughput 3.30692K wps
[Epoch 75 Batch 60/62] avg loss 0.00332596, throughput 3.23249K wps
Begin Testing...
[Epoch 75] train avg loss 0.00335631, dev acc 0.8024, dev avg loss 0.383377, throughput 3.27775K wps
[Epoch 76 Batch 30/62] avg loss 0.00317654, throughput 3.32092K wps
[Epoch 76 Batch 60/62] avg loss 0.00324409, throughput 3.24483K wps
Begin Testing...
[Epoch 76] train avg loss 0.00326909, dev acc 0.8053, dev avg loss 0.382882, throughput 3.28848K wps
Observed Improvement.
Begin Testing...
[Epoch 77 Batch 30/62] avg loss 0.00312548, throughput 3.32677K wps
[Epoch 77 Batch 60/62] avg loss 0.00329309, throughput 3.24876K wps
Begin Testing...
[Epoch 77] train avg loss 0.00328051, dev acc 0.7965, dev avg loss 0.386262, throughput 3.29582K wps
[Epoch 78 Batch 30/62] avg loss 0.0031292, throughput 3.30969K wps
[Epoch 78 Batch 60/62] avg loss 0.00320146, throughput 3.21445K wps
Begin Testing...
[Epoch 78] train avg loss 0.00317395, dev acc 0.8053, dev avg loss 0.382331, throughput 3.267K wps
Observed Improvement.
Begin Testing...
[Epoch 79 Batch 30/62] avg loss 0.0031924, throughput 3.29857K wps
[Epoch 79 Batch 60/62] avg loss 0.00302059, throughput 3.23888K wps
Begin Testing...
[Epoch 79] train avg loss 0.00312917, dev acc 0.7935, dev avg loss 0.38318, throughput 3.27436K wps
[Epoch 80 Batch 30/62] avg loss 0.00284961, throughput 3.31833K wps
[Epoch 80 Batch 60/62] avg loss 0.00293324, throughput 3.23568K wps
Begin Testing...
[Epoch 80] train avg loss 0.00298412, dev acc 0.8053, dev avg loss 0.382179, throughput 3.28347K wps
Observed Improvement.
Begin Testing...
[Epoch 81 Batch 30/62] avg loss 0.00287039, throughput 3.31279K wps
[Epoch 81 Batch 60/62] avg loss 0.00303209, throughput 3.2304K wps
Begin Testing...
[Epoch 81] train avg loss 0.00295769, dev acc 0.7994, dev avg loss 0.382367, throughput 3.27702K wps
[Epoch 82 Batch 30/62] avg loss 0.00284495, throughput 3.29257K wps
[Epoch 82 Batch 60/62] avg loss 0.00282676, throughput 3.21787K wps
Begin Testing...
[Epoch 82] train avg loss 0.00291978, dev acc 0.7935, dev avg loss 0.383603, throughput 3.26231K wps
[Epoch 83 Batch 30/62] avg loss 0.00291484, throughput 3.29793K wps
[Epoch 83 Batch 60/62] avg loss 0.00277705, throughput 3.24138K wps
Begin Testing...
[Epoch 83] train avg loss 0.00288477, dev acc 0.7994, dev avg loss 0.38163, throughput 3.2768K wps
[Epoch 84 Batch 30/62] avg loss 0.0027381, throughput 3.32285K wps
[Epoch 84 Batch 60/62] avg loss 0.00286838, throughput 3.24509K wps
Begin Testing...
[Epoch 84] train avg loss 0.0029084, dev acc 0.8024, dev avg loss 0.38673, throughput 3.29035K wps
[Epoch 85 Batch 30/62] avg loss 0.00282353, throughput 3.31114K wps
[Epoch 85 Batch 60/62] avg loss 0.0025997, throughput 3.23458K wps
Begin Testing...
[Epoch 85] train avg loss 0.00275074, dev acc 0.8083, dev avg loss 0.381772, throughput 3.2802K wps
Observed Improvement.
Begin Testing...
[Epoch 86 Batch 30/62] avg loss 0.00279264, throughput 3.32951K wps
[Epoch 86 Batch 60/62] avg loss 0.00271767, throughput 3.24829K wps
Begin Testing...
[Epoch 86] train avg loss 0.0028152, dev acc 0.8083, dev avg loss 0.382337, throughput 3.29426K wps
Observed Improvement.
Begin Testing...
[Epoch 87 Batch 30/62] avg loss 0.00250812, throughput 3.29879K wps
[Epoch 87 Batch 60/62] avg loss 0.00275172, throughput 3.21182K wps
Begin Testing...
[Epoch 87] train avg loss 0.00266365, dev acc 0.7994, dev avg loss 0.38431, throughput 3.26156K wps
[Epoch 88 Batch 30/62] avg loss 0.0025686, throughput 3.30334K wps
[Epoch 88 Batch 60/62] avg loss 0.00260794, throughput 3.22318K wps
Begin Testing...
[Epoch 88] train avg loss 0.00263388, dev acc 0.8024, dev avg loss 0.381817, throughput 3.27022K wps
[Epoch 89 Batch 30/62] avg loss 0.00244104, throughput 3.32097K wps
[Epoch 89 Batch 60/62] avg loss 0.0025614, throughput 3.22965K wps
Begin Testing...
[Epoch 89] train avg loss 0.00254178, dev acc 0.8024, dev avg loss 0.382341, throughput 3.28001K wps
[Epoch 90 Batch 30/62] avg loss 0.00266673, throughput 3.29024K wps
[Epoch 90 Batch 60/62] avg loss 0.00247815, throughput 3.23111K wps
Begin Testing...
[Epoch 90] train avg loss 0.00261409, dev acc 0.8083, dev avg loss 0.381409, throughput 3.26741K wps
Observed Improvement.
Begin Testing...
[Epoch 91 Batch 30/62] avg loss 0.00242768, throughput 3.31362K wps
[Epoch 91 Batch 60/62] avg loss 0.00248375, throughput 3.2448K wps
Begin Testing...
[Epoch 91] train avg loss 0.00247008, dev acc 0.8053, dev avg loss 0.385898, throughput 3.28594K wps
[Epoch 92 Batch 30/62] avg loss 0.00228893, throughput 3.32619K wps
[Epoch 92 Batch 60/62] avg loss 0.00252234, throughput 3.23203K wps
Begin Testing...
[Epoch 92] train avg loss 0.002427, dev acc 0.7994, dev avg loss 0.381018, throughput 3.28385K wps
[Epoch 93 Batch 30/62] avg loss 0.00243465, throughput 3.30228K wps
[Epoch 93 Batch 60/62] avg loss 0.00243746, throughput 3.2231K wps
Begin Testing...
[Epoch 93] train avg loss 0.00243689, dev acc 0.8142, dev avg loss 0.379259, throughput 3.27016K wps
Observed Improvement.
Begin Testing...
[Epoch 94 Batch 30/62] avg loss 0.00236065, throughput 3.32092K wps
[Epoch 94 Batch 60/62] avg loss 0.00223222, throughput 3.23351K wps
Begin Testing...
[Epoch 94] train avg loss 0.00229123, dev acc 0.8053, dev avg loss 0.38031, throughput 3.2835K wps
[Epoch 95 Batch 30/62] avg loss 0.0023006, throughput 3.3087K wps
[Epoch 95 Batch 60/62] avg loss 0.00228586, throughput 3.2428K wps
Begin Testing...
[Epoch 95] train avg loss 0.00234319, dev acc 0.8053, dev avg loss 0.380378, throughput 3.28191K wps
[Epoch 96 Batch 30/62] avg loss 0.00223831, throughput 3.27731K wps
[Epoch 96 Batch 60/62] avg loss 0.00231299, throughput 3.20181K wps
Begin Testing...
[Epoch 96] train avg loss 0.00229393, dev acc 0.8024, dev avg loss 0.385012, throughput 3.2453K wps
[Epoch 97 Batch 30/62] avg loss 0.00230245, throughput 3.27946K wps
[Epoch 97 Batch 60/62] avg loss 0.00233963, throughput 3.24674K wps
Begin Testing...
[Epoch 97] train avg loss 0.00233775, dev acc 0.7994, dev avg loss 0.380446, throughput 3.2694K wps
[Epoch 98 Batch 30/62] avg loss 0.00224949, throughput 3.32182K wps
[Epoch 98 Batch 60/62] avg loss 0.00224681, throughput 3.24342K wps
Begin Testing...
[Epoch 98] train avg loss 0.00226833, dev acc 0.8024, dev avg loss 0.380052, throughput 3.2867K wps
[Epoch 99 Batch 30/62] avg loss 0.00212472, throughput 3.31316K wps
[Epoch 99 Batch 60/62] avg loss 0.00211474, throughput 3.22014K wps
Begin Testing...
[Epoch 99] train avg loss 0.002138, dev acc 0.8053, dev avg loss 0.381985, throughput 3.27208K wps
[Epoch 100 Batch 30/62] avg loss 0.00225252, throughput 3.30488K wps
[Epoch 100 Batch 60/62] avg loss 0.00214094, throughput 3.20603K wps
Begin Testing...
[Epoch 100] train avg loss 0.00223265, dev acc 0.8053, dev avg loss 0.381473, throughput 3.26195K wps
[Epoch 101 Batch 30/62] avg loss 0.00213981, throughput 3.31834K wps
[Epoch 101 Batch 60/62] avg loss 0.002069, throughput 3.23605K wps
Begin Testing...
[Epoch 101] train avg loss 0.00217867, dev acc 0.8112, dev avg loss 0.385086, throughput 3.28289K wps
[Epoch 102 Batch 30/62] avg loss 0.00193348, throughput 3.28788K wps
[Epoch 102 Batch 60/62] avg loss 0.00196293, throughput 3.23055K wps
Begin Testing...
[Epoch 102] train avg loss 0.00199635, dev acc 0.8112, dev avg loss 0.380103, throughput 3.2654K wps
[Epoch 103 Batch 30/62] avg loss 0.0019887, throughput 3.28781K wps
[Epoch 103 Batch 60/62] avg loss 0.00208069, throughput 3.21605K wps
Begin Testing...
[Epoch 103] train avg loss 0.00203685, dev acc 0.8024, dev avg loss 0.380582, throughput 3.25778K wps
[Epoch 104 Batch 30/62] avg loss 0.00196065, throughput 3.28292K wps
[Epoch 104 Batch 60/62] avg loss 0.001926, throughput 3.20288K wps
Begin Testing...
[Epoch 104] train avg loss 0.00197209, dev acc 0.8053, dev avg loss 0.381127, throughput 3.24876K wps
[Epoch 105 Batch 30/62] avg loss 0.00182143, throughput 3.26658K wps
[Epoch 105 Batch 60/62] avg loss 0.00204248, throughput 3.21269K wps
Begin Testing...
[Epoch 105] train avg loss 0.00197826, dev acc 0.8142, dev avg loss 0.382184, throughput 3.24541K wps
Observed Improvement.
Begin Testing...
[Epoch 106 Batch 30/62] avg loss 0.00193123, throughput 3.29787K wps
[Epoch 106 Batch 60/62] avg loss 0.00193805, throughput 3.18729K wps
Begin Testing...
[Epoch 106] train avg loss 0.00195168, dev acc 0.8053, dev avg loss 0.381398, throughput 3.24962K wps
[Epoch 107 Batch 30/62] avg loss 0.00187844, throughput 3.2899K wps
[Epoch 107 Batch 60/62] avg loss 0.00185349, throughput 3.21177K wps
Begin Testing...
[Epoch 107] train avg loss 0.0018765, dev acc 0.8024, dev avg loss 0.382628, throughput 3.25741K wps
[Epoch 108 Batch 30/62] avg loss 0.00180527, throughput 3.29508K wps
[Epoch 108 Batch 60/62] avg loss 0.00192684, throughput 3.20478K wps
Begin Testing...
[Epoch 108] train avg loss 0.00189756, dev acc 0.8053, dev avg loss 0.38118, throughput 3.25601K wps
[Epoch 109 Batch 30/62] avg loss 0.0017725, throughput 3.29587K wps
[Epoch 109 Batch 60/62] avg loss 0.00189361, throughput 3.19185K wps
Begin Testing...
[Epoch 109] train avg loss 0.00187689, dev acc 0.8053, dev avg loss 0.381817, throughput 3.25033K wps
[Epoch 110 Batch 30/62] avg loss 0.00179402, throughput 3.31068K wps
[Epoch 110 Batch 60/62] avg loss 0.00175464, throughput 3.21836K wps
Begin Testing...
[Epoch 110] train avg loss 0.00179209, dev acc 0.8083, dev avg loss 0.384022, throughput 3.27128K wps
[Epoch 111 Batch 30/62] avg loss 0.0016992, throughput 3.29207K wps
[Epoch 111 Batch 60/62] avg loss 0.00177921, throughput 3.22343K wps
Begin Testing...
[Epoch 111] train avg loss 0.00179916, dev acc 0.8083, dev avg loss 0.381028, throughput 3.26344K wps
[Epoch 112 Batch 30/62] avg loss 0.00176845, throughput 3.30293K wps
[Epoch 112 Batch 60/62] avg loss 0.00166733, throughput 3.22656K wps
Begin Testing...
[Epoch 112] train avg loss 0.00173134, dev acc 0.8112, dev avg loss 0.38211, throughput 3.26924K wps
[Epoch 113 Batch 30/62] avg loss 0.00175679, throughput 3.28115K wps
[Epoch 113 Batch 60/62] avg loss 0.00153667, throughput 3.23847K wps
Begin Testing...
[Epoch 113] train avg loss 0.00165293, dev acc 0.8083, dev avg loss 0.38363, throughput 3.26638K wps
[Epoch 114 Batch 30/62] avg loss 0.00155803, throughput 3.32121K wps
[Epoch 114 Batch 60/62] avg loss 0.00170846, throughput 3.22214K wps
Begin Testing...
[Epoch 114] train avg loss 0.00167354, dev acc 0.8142, dev avg loss 0.382509, throughput 3.27884K wps
Observed Improvement.
Begin Testing...
[Epoch 115 Batch 30/62] avg loss 0.00162521, throughput 3.31532K wps
[Epoch 115 Batch 60/62] avg loss 0.00168617, throughput 3.23303K wps
Begin Testing...
[Epoch 115] train avg loss 0.00168838, dev acc 0.8053, dev avg loss 0.383391, throughput 3.27768K wps
[Epoch 116 Batch 30/62] avg loss 0.00154102, throughput 3.30895K wps
[Epoch 116 Batch 60/62] avg loss 0.00167962, throughput 3.22858K wps
Begin Testing...
[Epoch 116] train avg loss 0.00161237, dev acc 0.8083, dev avg loss 0.382135, throughput 3.27553K wps
[Epoch 117 Batch 30/62] avg loss 0.00164724, throughput 3.31433K wps
[Epoch 117 Batch 60/62] avg loss 0.0016433, throughput 3.23787K wps
Begin Testing...
[Epoch 117] train avg loss 0.00166623, dev acc 0.8142, dev avg loss 0.382431, throughput 3.28281K wps
Observed Improvement.
Begin Testing...
[Epoch 118 Batch 30/62] avg loss 0.0016947, throughput 3.29745K wps
[Epoch 118 Batch 60/62] avg loss 0.00146005, throughput 3.24169K wps
Begin Testing...
[Epoch 118] train avg loss 0.00159406, dev acc 0.8112, dev avg loss 0.385664, throughput 3.27609K wps
[Epoch 119 Batch 30/62] avg loss 0.00162184, throughput 3.32362K wps
[Epoch 119 Batch 60/62] avg loss 0.00163782, throughput 3.23134K wps
Begin Testing...
[Epoch 119] train avg loss 0.001619, dev acc 0.8142, dev avg loss 0.381967, throughput 3.28447K wps
Observed Improvement.
Begin Testing...
[Epoch 120 Batch 30/62] avg loss 0.00149326, throughput 3.31034K wps
[Epoch 120 Batch 60/62] avg loss 0.00148425, throughput 3.24261K wps
Begin Testing...
[Epoch 120] train avg loss 0.00152629, dev acc 0.8171, dev avg loss 0.389264, throughput 3.2831K wps
Observed Improvement.
Begin Testing...
[Epoch 121 Batch 30/62] avg loss 0.00168316, throughput 3.26877K wps
[Epoch 121 Batch 60/62] avg loss 0.0014045, throughput 3.21263K wps
Begin Testing...
[Epoch 121] train avg loss 0.00154243, dev acc 0.8171, dev avg loss 0.383403, throughput 3.24708K wps
Observed Improvement.
Begin Testing...
[Epoch 122 Batch 30/62] avg loss 0.00143709, throughput 3.29586K wps
[Epoch 122 Batch 60/62] avg loss 0.00153638, throughput 3.2072K wps
Begin Testing...
[Epoch 122] train avg loss 0.00148686, dev acc 0.8083, dev avg loss 0.383339, throughput 3.25844K wps
[Epoch 123 Batch 30/62] avg loss 0.0014209, throughput 3.29725K wps
[Epoch 123 Batch 60/62] avg loss 0.00159122, throughput 3.20785K wps
Begin Testing...
[Epoch 123] train avg loss 0.00151442, dev acc 0.8083, dev avg loss 0.384544, throughput 3.25943K wps
[Epoch 124 Batch 30/62] avg loss 0.00140059, throughput 3.28446K wps
[Epoch 124 Batch 60/62] avg loss 0.00140829, throughput 3.218K wps
Begin Testing...
[Epoch 124] train avg loss 0.0013971, dev acc 0.8083, dev avg loss 0.384566, throughput 3.25722K wps
[Epoch 125 Batch 30/62] avg loss 0.00137496, throughput 3.30542K wps
[Epoch 125 Batch 60/62] avg loss 0.00135842, throughput 3.21853K wps
Begin Testing...
[Epoch 125] train avg loss 0.00138232, dev acc 0.8112, dev avg loss 0.385801, throughput 3.26687K wps
[Epoch 126 Batch 30/62] avg loss 0.00135959, throughput 3.28848K wps
[Epoch 126 Batch 60/62] avg loss 0.0014701, throughput 3.21994K wps
Begin Testing...
[Epoch 126] train avg loss 0.00141641, dev acc 0.8112, dev avg loss 0.387256, throughput 3.26064K wps
[Epoch 127 Batch 30/62] avg loss 0.00140562, throughput 3.28483K wps
[Epoch 127 Batch 60/62] avg loss 0.00133124, throughput 3.2254K wps
Begin Testing...
[Epoch 127] train avg loss 0.00139531, dev acc 0.8112, dev avg loss 0.384884, throughput 3.26066K wps
[Epoch 128 Batch 30/62] avg loss 0.00133434, throughput 3.28064K wps
[Epoch 128 Batch 60/62] avg loss 0.00133897, throughput 3.22216K wps
Begin Testing...
[Epoch 128] train avg loss 0.00134686, dev acc 0.8112, dev avg loss 0.385394, throughput 3.25692K wps
[Epoch 129 Batch 30/62] avg loss 0.00136155, throughput 3.2481K wps
[Epoch 129 Batch 60/62] avg loss 0.00144949, throughput 3.20536K wps
Begin Testing...
[Epoch 129] train avg loss 0.00141546, dev acc 0.8024, dev avg loss 0.385297, throughput 3.23448K wps
[Epoch 130 Batch 30/62] avg loss 0.00128107, throughput 3.29138K wps
[Epoch 130 Batch 60/62] avg loss 0.00137752, throughput 3.1865K wps
Begin Testing...
[Epoch 130] train avg loss 0.00132914, dev acc 0.8053, dev avg loss 0.385975, throughput 3.24537K wps
[Epoch 131 Batch 30/62] avg loss 0.00141162, throughput 3.29951K wps
[Epoch 131 Batch 60/62] avg loss 0.00129745, throughput 3.23736K wps
Begin Testing...
[Epoch 131] train avg loss 0.00136034, dev acc 0.8142, dev avg loss 0.385471, throughput 3.27523K wps
[Epoch 132 Batch 30/62] avg loss 0.00139147, throughput 3.28668K wps
[Epoch 132 Batch 60/62] avg loss 0.00127105, throughput 3.22912K wps
Begin Testing...
[Epoch 132] train avg loss 0.00136073, dev acc 0.8083, dev avg loss 0.387841, throughput 3.26341K wps
[Epoch 133 Batch 30/62] avg loss 0.00119889, throughput 3.27951K wps
[Epoch 133 Batch 60/62] avg loss 0.00133301, throughput 3.22711K wps
Begin Testing...
[Epoch 133] train avg loss 0.00128539, dev acc 0.8083, dev avg loss 0.387593, throughput 3.25829K wps
[Epoch 134 Batch 30/62] avg loss 0.00129508, throughput 3.28741K wps
[Epoch 134 Batch 60/62] avg loss 0.00126991, throughput 3.21644K wps
Begin Testing...
[Epoch 134] train avg loss 0.00129433, dev acc 0.8171, dev avg loss 0.386628, throughput 3.25731K wps
Observed Improvement.
Begin Testing...
[Epoch 135 Batch 30/62] avg loss 0.00124384, throughput 3.29092K wps
[Epoch 135 Batch 60/62] avg loss 0.001292, throughput 3.21192K wps
Begin Testing...
[Epoch 135] train avg loss 0.00129035, dev acc 0.8171, dev avg loss 0.391713, throughput 3.2578K wps
Observed Improvement.
Begin Testing...
[Epoch 136 Batch 30/62] avg loss 0.00115454, throughput 3.29972K wps
[Epoch 136 Batch 60/62] avg loss 0.00132219, throughput 3.2306K wps
Begin Testing...
[Epoch 136] train avg loss 0.00124785, dev acc 0.8171, dev avg loss 0.38678, throughput 3.2704K wps
Observed Improvement.
Begin Testing...
[Epoch 137 Batch 30/62] avg loss 0.00120551, throughput 3.30262K wps
[Epoch 137 Batch 60/62] avg loss 0.00117476, throughput 3.22728K wps
Begin Testing...
[Epoch 137] train avg loss 0.00121173, dev acc 0.8053, dev avg loss 0.389403, throughput 3.27013K wps
[Epoch 138 Batch 30/62] avg loss 0.00117585, throughput 3.31862K wps
[Epoch 138 Batch 60/62] avg loss 0.00127009, throughput 3.22465K wps
Begin Testing...
[Epoch 138] train avg loss 0.00123303, dev acc 0.8142, dev avg loss 0.388563, throughput 3.27788K wps
[Epoch 139 Batch 30/62] avg loss 0.00115787, throughput 3.31008K wps
[Epoch 139 Batch 60/62] avg loss 0.00115612, throughput 3.23179K wps
Begin Testing...
[Epoch 139] train avg loss 0.00117459, dev acc 0.8083, dev avg loss 0.389685, throughput 3.2765K wps
[Epoch 140 Batch 30/62] avg loss 0.00114747, throughput 3.27984K wps
[Epoch 140 Batch 60/62] avg loss 0.00114476, throughput 3.21227K wps
Begin Testing...
[Epoch 140] train avg loss 0.00118095, dev acc 0.8171, dev avg loss 0.389299, throughput 3.25194K wps
Observed Improvement.
Begin Testing...
[Epoch 141 Batch 30/62] avg loss 0.00118888, throughput 3.307K wps
[Epoch 141 Batch 60/62] avg loss 0.001121, throughput 3.22563K wps
Begin Testing...
[Epoch 141] train avg loss 0.00115593, dev acc 0.8083, dev avg loss 0.389813, throughput 3.27169K wps
[Epoch 142 Batch 30/62] avg loss 0.00116105, throughput 3.29982K wps
[Epoch 142 Batch 60/62] avg loss 0.00104636, throughput 3.22977K wps
Begin Testing...
[Epoch 142] train avg loss 0.0011427, dev acc 0.8171, dev avg loss 0.401265, throughput 3.2714K wps
Observed Improvement.
Begin Testing...
[Epoch 143 Batch 30/62] avg loss 0.00113277, throughput 3.30848K wps
[Epoch 143 Batch 60/62] avg loss 0.00110534, throughput 3.25712K wps
Begin Testing...
[Epoch 143] train avg loss 0.00112063, dev acc 0.8112, dev avg loss 0.390165, throughput 3.29086K wps
[Epoch 144 Batch 30/62] avg loss 0.00102966, throughput 3.29522K wps
[Epoch 144 Batch 60/62] avg loss 0.00112324, throughput 3.21987K wps
Begin Testing...
[Epoch 144] train avg loss 0.00107994, dev acc 0.8201, dev avg loss 0.389967, throughput 3.26218K wps
Observed Improvement.
Begin Testing...
[Epoch 145 Batch 30/62] avg loss 0.00110587, throughput 3.31989K wps
[Epoch 145 Batch 60/62] avg loss 0.00111219, throughput 3.24069K wps
Begin Testing...
[Epoch 145] train avg loss 0.00112313, dev acc 0.8083, dev avg loss 0.393252, throughput 3.28549K wps
[Epoch 146 Batch 30/62] avg loss 0.00114851, throughput 3.28779K wps
[Epoch 146 Batch 60/62] avg loss 0.00103923, throughput 3.22002K wps
Begin Testing...
[Epoch 146] train avg loss 0.00112337, dev acc 0.8112, dev avg loss 0.39096, throughput 3.26016K wps
[Epoch 147 Batch 30/62] avg loss 0.00110218, throughput 3.279K wps
[Epoch 147 Batch 60/62] avg loss 0.00112426, throughput 3.22048K wps
Begin Testing...
[Epoch 147] train avg loss 0.00111665, dev acc 0.8142, dev avg loss 0.39613, throughput 3.25621K wps
[Epoch 148 Batch 30/62] avg loss 0.00101849, throughput 3.29988K wps
[Epoch 148 Batch 60/62] avg loss 0.00103405, throughput 3.21325K wps
Begin Testing...
[Epoch 148] train avg loss 0.00104372, dev acc 0.8201, dev avg loss 0.390558, throughput 3.26194K wps
Observed Improvement.
Begin Testing...
[Epoch 149 Batch 30/62] avg loss 0.00101308, throughput 3.29384K wps
[Epoch 149 Batch 60/62] avg loss 0.00108425, throughput 3.22728K wps
Begin Testing...
[Epoch 149] train avg loss 0.00105582, dev acc 0.8112, dev avg loss 0.391512, throughput 3.26604K wps
[Epoch 150 Batch 30/62] avg loss 0.000973895, throughput 3.28963K wps
[Epoch 150 Batch 60/62] avg loss 0.0010638, throughput 3.22535K wps
Begin Testing...
[Epoch 150] train avg loss 0.00102643, dev acc 0.8142, dev avg loss 0.392062, throughput 3.26352K wps
[Epoch 151 Batch 30/62] avg loss 0.000974868, throughput 3.33271K wps
[Epoch 151 Batch 60/62] avg loss 0.00106399, throughput 3.24049K wps
Begin Testing...
[Epoch 151] train avg loss 0.00102826, dev acc 0.8112, dev avg loss 0.394044, throughput 3.29192K wps
[Epoch 152 Batch 30/62] avg loss 0.000956031, throughput 3.29213K wps
[Epoch 152 Batch 60/62] avg loss 0.000945349, throughput 3.22251K wps
Begin Testing...
[Epoch 152] train avg loss 0.000957541, dev acc 0.8142, dev avg loss 0.392438, throughput 3.2633K wps
[Epoch 153 Batch 30/62] avg loss 0.00103113, throughput 3.28622K wps
[Epoch 153 Batch 60/62] avg loss 0.00101662, throughput 3.24161K wps
Begin Testing...
[Epoch 153] train avg loss 0.00103848, dev acc 0.8142, dev avg loss 0.394991, throughput 3.27061K wps
[Epoch 154 Batch 30/62] avg loss 0.000918346, throughput 3.29605K wps
[Epoch 154 Batch 60/62] avg loss 0.000992765, throughput 3.21011K wps
Begin Testing...
[Epoch 154] train avg loss 0.000964944, dev acc 0.8142, dev avg loss 0.400106, throughput 3.25952K wps
[Epoch 155 Batch 30/62] avg loss 0.000961282, throughput 3.29941K wps
[Epoch 155 Batch 60/62] avg loss 0.00097178, throughput 3.22218K wps
Begin Testing...
[Epoch 155] train avg loss 0.000976199, dev acc 0.8142, dev avg loss 0.394763, throughput 3.26645K wps
[Epoch 156 Batch 30/62] avg loss 0.000921832, throughput 3.28766K wps
[Epoch 156 Batch 60/62] avg loss 0.0010137, throughput 3.2433K wps
Begin Testing...
[Epoch 156] train avg loss 0.000972121, dev acc 0.8112, dev avg loss 0.393983, throughput 3.27117K wps
[Epoch 157 Batch 30/62] avg loss 0.000983162, throughput 3.31595K wps
[Epoch 157 Batch 60/62] avg loss 0.000918444, throughput 3.23131K wps
Begin Testing...
[Epoch 157] train avg loss 0.00095443, dev acc 0.8083, dev avg loss 0.395641, throughput 3.28039K wps
[Epoch 158 Batch 30/62] avg loss 0.000850759, throughput 3.29757K wps
[Epoch 158 Batch 60/62] avg loss 0.000944118, throughput 3.21935K wps
Begin Testing...
[Epoch 158] train avg loss 0.000901555, dev acc 0.8142, dev avg loss 0.397549, throughput 3.26534K wps
[Epoch 159 Batch 30/62] avg loss 0.000879728, throughput 3.30157K wps
[Epoch 159 Batch 60/62] avg loss 0.000974191, throughput 3.24234K wps
Begin Testing...
[Epoch 159] train avg loss 0.000935294, dev acc 0.8142, dev avg loss 0.398594, throughput 3.27825K wps
[Epoch 160 Batch 30/62] avg loss 0.000844358, throughput 3.33042K wps
[Epoch 160 Batch 60/62] avg loss 0.000965255, throughput 3.15697K wps
Begin Testing...
[Epoch 160] train avg loss 0.00091197, dev acc 0.8112, dev avg loss 0.397956, throughput 3.24673K wps
[Epoch 161 Batch 30/62] avg loss 0.000896408, throughput 3.33028K wps
[Epoch 161 Batch 60/62] avg loss 0.000874703, throughput 3.25108K wps
Begin Testing...
[Epoch 161] train avg loss 0.000892942, dev acc 0.8083, dev avg loss 0.396151, throughput 3.29602K wps
[Epoch 162 Batch 30/62] avg loss 0.000832683, throughput 3.30627K wps
[Epoch 162 Batch 60/62] avg loss 0.000819585, throughput 3.22677K wps
Begin Testing...
[Epoch 162] train avg loss 0.000846552, dev acc 0.8112, dev avg loss 0.396426, throughput 3.27261K wps
[Epoch 163 Batch 30/62] avg loss 0.000802446, throughput 3.3072K wps
[Epoch 163 Batch 60/62] avg loss 0.000910486, throughput 3.21932K wps
Begin Testing...
[Epoch 163] train avg loss 0.00087463, dev acc 0.8083, dev avg loss 0.397029, throughput 3.27062K wps
[Epoch 164 Batch 30/62] avg loss 0.00087489, throughput 3.31333K wps
[Epoch 164 Batch 60/62] avg loss 0.000849714, throughput 3.2417K wps
Begin Testing...
[Epoch 164] train avg loss 0.000862918, dev acc 0.8112, dev avg loss 0.398137, throughput 3.28313K wps
[Epoch 165 Batch 30/62] avg loss 0.00087139, throughput 3.28826K wps
[Epoch 165 Batch 60/62] avg loss 0.000860023, throughput 3.2227K wps
Begin Testing...
[Epoch 165] train avg loss 0.000877862, dev acc 0.8083, dev avg loss 0.398469, throughput 3.26165K wps
[Epoch 166 Batch 30/62] avg loss 0.000866691, throughput 3.32764K wps
[Epoch 166 Batch 60/62] avg loss 0.000856602, throughput 3.20448K wps
Begin Testing...
[Epoch 166] train avg loss 0.000861604, dev acc 0.8112, dev avg loss 0.396809, throughput 3.27216K wps
[Epoch 167 Batch 30/62] avg loss 0.000815544, throughput 3.30071K wps
[Epoch 167 Batch 60/62] avg loss 0.000842172, throughput 3.21055K wps
Begin Testing...
[Epoch 167] train avg loss 0.000863552, dev acc 0.8112, dev avg loss 0.397284, throughput 3.26205K wps
[Epoch 168 Batch 30/62] avg loss 0.000844534, throughput 3.30599K wps
[Epoch 168 Batch 60/62] avg loss 0.000809775, throughput 3.21774K wps
Begin Testing...
[Epoch 168] train avg loss 0.000830367, dev acc 0.8083, dev avg loss 0.400063, throughput 3.2674K wps
[Epoch 169 Batch 30/62] avg loss 0.000773476, throughput 3.30268K wps
[Epoch 169 Batch 60/62] avg loss 0.000863428, throughput 3.2193K wps
Begin Testing...
[Epoch 169] train avg loss 0.000848378, dev acc 0.8142, dev avg loss 0.399673, throughput 3.2673K wps
[Epoch 170 Batch 30/62] avg loss 0.000870823, throughput 3.29769K wps
[Epoch 170 Batch 60/62] avg loss 0.000862288, throughput 3.2206K wps
Begin Testing...
[Epoch 170] train avg loss 0.000887487, dev acc 0.8112, dev avg loss 0.405449, throughput 3.26436K wps
[Epoch 171 Batch 30/62] avg loss 0.000754576, throughput 3.29895K wps
[Epoch 171 Batch 60/62] avg loss 0.00086621, throughput 3.21788K wps
Begin Testing...
[Epoch 171] train avg loss 0.000850767, dev acc 0.8112, dev avg loss 0.400379, throughput 3.26579K wps
[Epoch 172 Batch 30/62] avg loss 0.000780099, throughput 3.31207K wps
[Epoch 172 Batch 60/62] avg loss 0.000790105, throughput 3.17689K wps
Begin Testing...
[Epoch 172] train avg loss 0.000789645, dev acc 0.8142, dev avg loss 0.405099, throughput 3.25067K wps
[Epoch 173 Batch 30/62] avg loss 0.000739949, throughput 3.30931K wps
[Epoch 173 Batch 60/62] avg loss 0.000766247, throughput 3.21851K wps
Begin Testing...
[Epoch 173] train avg loss 0.000780521, dev acc 0.8142, dev avg loss 0.401573, throughput 3.26955K wps
[Epoch 174 Batch 30/62] avg loss 0.000786265, throughput 3.29295K wps
[Epoch 174 Batch 60/62] avg loss 0.000846886, throughput 3.22146K wps
Begin Testing...
[Epoch 174] train avg loss 0.0008153, dev acc 0.8142, dev avg loss 0.401109, throughput 3.26295K wps
[Epoch 175 Batch 30/62] avg loss 0.000736652, throughput 3.28729K wps
[Epoch 175 Batch 60/62] avg loss 0.000850209, throughput 3.22557K wps
Begin Testing...
[Epoch 175] train avg loss 0.000807174, dev acc 0.8112, dev avg loss 0.406681, throughput 3.2614K wps
[Epoch 176 Batch 30/62] avg loss 0.000693152, throughput 3.29096K wps
[Epoch 176 Batch 60/62] avg loss 0.000820092, throughput 3.22125K wps
Begin Testing...
[Epoch 176] train avg loss 0.000762388, dev acc 0.8142, dev avg loss 0.402988, throughput 3.26199K wps
[Epoch 177 Batch 30/62] avg loss 0.000790961, throughput 3.31438K wps
[Epoch 177 Batch 60/62] avg loss 0.000743948, throughput 3.20509K wps
Begin Testing...
[Epoch 177] train avg loss 0.000770826, dev acc 0.8171, dev avg loss 0.401902, throughput 3.26447K wps
[Epoch 178 Batch 30/62] avg loss 0.000741742, throughput 3.29312K wps
[Epoch 178 Batch 60/62] avg loss 0.000771802, throughput 3.22045K wps
Begin Testing...
[Epoch 178] train avg loss 0.000769787, dev acc 0.8142, dev avg loss 0.402579, throughput 3.26366K wps
[Epoch 179 Batch 30/62] avg loss 0.000773182, throughput 3.30857K wps
[Epoch 179 Batch 60/62] avg loss 0.000801788, throughput 3.20807K wps
Begin Testing...
[Epoch 179] train avg loss 0.000786365, dev acc 0.8142, dev avg loss 0.402214, throughput 3.26493K wps
[Epoch 180 Batch 30/62] avg loss 0.000680305, throughput 3.30222K wps
[Epoch 180 Batch 60/62] avg loss 0.000736694, throughput 3.20198K wps
Begin Testing...
[Epoch 180] train avg loss 0.000724243, dev acc 0.8142, dev avg loss 0.401366, throughput 3.25914K wps
[Epoch 181 Batch 30/62] avg loss 0.000748112, throughput 3.30536K wps
[Epoch 181 Batch 60/62] avg loss 0.000788542, throughput 3.21449K wps
Begin Testing...
[Epoch 181] train avg loss 0.000787466, dev acc 0.8142, dev avg loss 0.403527, throughput 3.2668K wps
[Epoch 182 Batch 30/62] avg loss 0.000727417, throughput 3.28787K wps
[Epoch 182 Batch 60/62] avg loss 0.000771127, throughput 3.21992K wps
Begin Testing...
[Epoch 182] train avg loss 0.000748043, dev acc 0.8171, dev avg loss 0.406114, throughput 3.25894K wps
[Epoch 183 Batch 30/62] avg loss 0.000657211, throughput 3.29176K wps
[Epoch 183 Batch 60/62] avg loss 0.000726753, throughput 3.2103K wps
Begin Testing...
[Epoch 183] train avg loss 0.000712052, dev acc 0.8171, dev avg loss 0.404667, throughput 3.25671K wps
[Epoch 184 Batch 30/62] avg loss 0.000758342, throughput 3.28341K wps
[Epoch 184 Batch 60/62] avg loss 0.000708175, throughput 3.22875K wps
Begin Testing...
[Epoch 184] train avg loss 0.000730288, dev acc 0.8171, dev avg loss 0.404543, throughput 3.26191K wps
[Epoch 185 Batch 30/62] avg loss 0.000629707, throughput 3.28513K wps
[Epoch 185 Batch 60/62] avg loss 0.000751368, throughput 3.22951K wps
Begin Testing...
[Epoch 185] train avg loss 0.000694128, dev acc 0.8142, dev avg loss 0.404777, throughput 3.26317K wps
[Epoch 186 Batch 30/62] avg loss 0.000660155, throughput 3.31135K wps
[Epoch 186 Batch 60/62] avg loss 0.000714187, throughput 3.21286K wps
Begin Testing...
[Epoch 186] train avg loss 0.000700747, dev acc 0.8112, dev avg loss 0.405595, throughput 3.26853K wps
[Epoch 187 Batch 30/62] avg loss 0.000724211, throughput 3.31571K wps
[Epoch 187 Batch 60/62] avg loss 0.00072805, throughput 3.22266K wps
Begin Testing...
[Epoch 187] train avg loss 0.000754231, dev acc 0.8112, dev avg loss 0.403652, throughput 3.27383K wps
[Epoch 188 Batch 30/62] avg loss 0.000649827, throughput 3.28895K wps
[Epoch 188 Batch 60/62] avg loss 0.000699435, throughput 3.22711K wps
Begin Testing...
[Epoch 188] train avg loss 0.000675699, dev acc 0.8171, dev avg loss 0.409869, throughput 3.26451K wps
[Epoch 189 Batch 30/62] avg loss 0.000699651, throughput 3.29542K wps
[Epoch 189 Batch 60/62] avg loss 0.000662096, throughput 3.2206K wps
Begin Testing...
[Epoch 189] train avg loss 0.000682599, dev acc 0.8142, dev avg loss 0.407673, throughput 3.26401K wps
[Epoch 190 Batch 30/62] avg loss 0.000682575, throughput 3.28174K wps
[Epoch 190 Batch 60/62] avg loss 0.000652633, throughput 3.21845K wps
Begin Testing...
[Epoch 190] train avg loss 0.000666547, dev acc 0.8142, dev avg loss 0.406816, throughput 3.25665K wps
[Epoch 191 Batch 30/62] avg loss 0.000741694, throughput 3.27949K wps
[Epoch 191 Batch 60/62] avg loss 0.000646438, throughput 3.22931K wps
Begin Testing...
[Epoch 191] train avg loss 0.000692287, dev acc 0.8142, dev avg loss 0.405202, throughput 3.25948K wps
[Epoch 192 Batch 30/62] avg loss 0.000658628, throughput 3.28051K wps
[Epoch 192 Batch 60/62] avg loss 0.000651952, throughput 3.21953K wps
Begin Testing...
[Epoch 192] train avg loss 0.000652102, dev acc 0.8112, dev avg loss 0.406659, throughput 3.25402K wps
[Epoch 193 Batch 30/62] avg loss 0.000613014, throughput 3.27968K wps
[Epoch 193 Batch 60/62] avg loss 0.000626002, throughput 3.21918K wps
Begin Testing...
[Epoch 193] train avg loss 0.00063577, dev acc 0.8112, dev avg loss 0.405327, throughput 3.2558K wps
[Epoch 194 Batch 30/62] avg loss 0.000689652, throughput 3.28904K wps
[Epoch 194 Batch 60/62] avg loss 0.000659898, throughput 3.21561K wps
Begin Testing...
[Epoch 194] train avg loss 0.000692997, dev acc 0.8171, dev avg loss 0.410904, throughput 3.25729K wps
[Epoch 195 Batch 30/62] avg loss 0.000651761, throughput 3.27792K wps
[Epoch 195 Batch 60/62] avg loss 0.000657616, throughput 3.22462K wps
Begin Testing...
[Epoch 195] train avg loss 0.000715477, dev acc 0.8171, dev avg loss 0.405538, throughput 3.25831K wps
[Epoch 196 Batch 30/62] avg loss 0.0006692, throughput 3.2868K wps
[Epoch 196 Batch 60/62] avg loss 0.000637555, throughput 3.19991K wps
Begin Testing...
[Epoch 196] train avg loss 0.000674022, dev acc 0.8112, dev avg loss 0.405845, throughput 3.24858K wps
[Epoch 197 Batch 30/62] avg loss 0.000640027, throughput 3.29256K wps
[Epoch 197 Batch 60/62] avg loss 0.000613396, throughput 3.21805K wps
Begin Testing...
[Epoch 197] train avg loss 0.000625576, dev acc 0.8142, dev avg loss 0.408422, throughput 3.26182K wps
[Epoch 198 Batch 30/62] avg loss 0.000605952, throughput 3.26331K wps
[Epoch 198 Batch 60/62] avg loss 0.000603957, throughput 3.22377K wps
Begin Testing...
[Epoch 198] train avg loss 0.000607622, dev acc 0.8142, dev avg loss 0.406372, throughput 3.24994K wps
[Epoch 199 Batch 30/62] avg loss 0.000586052, throughput 3.28478K wps
[Epoch 199 Batch 60/62] avg loss 0.000605655, throughput 3.21634K wps
Begin Testing...
[Epoch 199] train avg loss 0.00059968, dev acc 0.8142, dev avg loss 0.411325, throughput 3.25658K wps
Test loss 0.370007, test acc 0.8382
Total time cost 417.23s
[Epoch 0 Batch 30/62] avg loss 0.0135338, throughput 3.07502K wps
[Epoch 0 Batch 60/62] avg loss 0.0130983, throughput 3.20798K wps
Begin Testing...
[Epoch 0] train avg loss 0.0135182, dev acc 0.6431, dev avg loss 0.640452, throughput 3.1499K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0132253, throughput 3.27928K wps
[Epoch 1 Batch 60/62] avg loss 0.0129665, throughput 3.20021K wps
Begin Testing...
[Epoch 1] train avg loss 0.0132951, dev acc 0.6431, dev avg loss 0.633845, throughput 3.24555K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0127718, throughput 3.28352K wps
[Epoch 2 Batch 60/62] avg loss 0.0128139, throughput 3.20685K wps
Begin Testing...
[Epoch 2] train avg loss 0.012965, dev acc 0.6431, dev avg loss 0.625658, throughput 3.25117K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0126107, throughput 3.30538K wps
[Epoch 3 Batch 60/62] avg loss 0.0126092, throughput 3.20593K wps
Begin Testing...
[Epoch 3] train avg loss 0.0127427, dev acc 0.6431, dev avg loss 0.616302, throughput 3.26219K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.0125014, throughput 3.28417K wps
[Epoch 4 Batch 60/62] avg loss 0.0123934, throughput 3.19229K wps
Begin Testing...
[Epoch 4] train avg loss 0.0126139, dev acc 0.6696, dev avg loss 0.614851, throughput 3.24371K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0124326, throughput 3.28222K wps
[Epoch 5 Batch 60/62] avg loss 0.0121699, throughput 3.2096K wps
Begin Testing...
[Epoch 5] train avg loss 0.0124753, dev acc 0.6431, dev avg loss 0.601433, throughput 3.2522K wps
[Epoch 6 Batch 30/62] avg loss 0.0119918, throughput 3.24949K wps
[Epoch 6 Batch 60/62] avg loss 0.0122099, throughput 3.19257K wps
Begin Testing...
[Epoch 6] train avg loss 0.0122766, dev acc 0.6696, dev avg loss 0.593973, throughput 3.22906K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0117754, throughput 3.26936K wps
[Epoch 7 Batch 60/62] avg loss 0.0118468, throughput 3.19488K wps
Begin Testing...
[Epoch 7] train avg loss 0.0119591, dev acc 0.6490, dev avg loss 0.584045, throughput 3.23864K wps
[Epoch 8 Batch 30/62] avg loss 0.0119549, throughput 3.28858K wps
[Epoch 8 Batch 60/62] avg loss 0.0113915, throughput 3.21915K wps
Begin Testing...
[Epoch 8] train avg loss 0.0119017, dev acc 0.6844, dev avg loss 0.576774, throughput 3.25869K wps
Observed Improvement.
Begin Testing...
[Epoch 9 Batch 30/62] avg loss 0.0113523, throughput 3.29975K wps
[Epoch 9 Batch 60/62] avg loss 0.0115441, throughput 3.21374K wps
Begin Testing...
[Epoch 9] train avg loss 0.011598, dev acc 0.6696, dev avg loss 0.566084, throughput 3.26371K wps
[Epoch 10 Batch 30/62] avg loss 0.0113822, throughput 3.27961K wps
[Epoch 10 Batch 60/62] avg loss 0.011244, throughput 3.22439K wps
Begin Testing...
[Epoch 10] train avg loss 0.0114187, dev acc 0.6726, dev avg loss 0.557795, throughput 3.25923K wps
[Epoch 11 Batch 30/62] avg loss 0.0111517, throughput 3.2689K wps
[Epoch 11 Batch 60/62] avg loss 0.0108624, throughput 3.20164K wps
Begin Testing...
[Epoch 11] train avg loss 0.011122, dev acc 0.7257, dev avg loss 0.548222, throughput 3.24076K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0110088, throughput 3.29519K wps
[Epoch 12 Batch 60/62] avg loss 0.0106535, throughput 3.18105K wps
Begin Testing...
[Epoch 12] train avg loss 0.010981, dev acc 0.7080, dev avg loss 0.538697, throughput 3.24185K wps
[Epoch 13 Batch 30/62] avg loss 0.0107513, throughput 3.27756K wps
[Epoch 13 Batch 60/62] avg loss 0.0105054, throughput 3.21013K wps
Begin Testing...
[Epoch 13] train avg loss 0.0107649, dev acc 0.7316, dev avg loss 0.529706, throughput 3.24983K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0104187, throughput 3.28935K wps
[Epoch 14 Batch 60/62] avg loss 0.0103652, throughput 3.22178K wps
Begin Testing...
[Epoch 14] train avg loss 0.0105286, dev acc 0.7316, dev avg loss 0.520848, throughput 3.26142K wps
Observed Improvement.
Begin Testing...
[Epoch 15 Batch 30/62] avg loss 0.0101206, throughput 3.28536K wps
[Epoch 15 Batch 60/62] avg loss 0.0100803, throughput 3.22023K wps
Begin Testing...
[Epoch 15] train avg loss 0.0102618, dev acc 0.7286, dev avg loss 0.513596, throughput 3.25922K wps
[Epoch 16 Batch 30/62] avg loss 0.0100846, throughput 3.28255K wps
[Epoch 16 Batch 60/62] avg loss 0.00983461, throughput 3.20941K wps
Begin Testing...
[Epoch 16] train avg loss 0.0100419, dev acc 0.7463, dev avg loss 0.504874, throughput 3.25101K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.00954055, throughput 3.29656K wps
[Epoch 17 Batch 60/62] avg loss 0.00990141, throughput 3.20366K wps
Begin Testing...
[Epoch 17] train avg loss 0.00984493, dev acc 0.7522, dev avg loss 0.497377, throughput 3.25629K wps
Observed Improvement.
Begin Testing...
[Epoch 18 Batch 30/62] avg loss 0.00951516, throughput 3.25385K wps
[Epoch 18 Batch 60/62] avg loss 0.00961923, throughput 3.22189K wps
Begin Testing...
[Epoch 18] train avg loss 0.00968511, dev acc 0.7729, dev avg loss 0.489823, throughput 3.24414K wps
Observed Improvement.
Begin Testing...
[Epoch 19 Batch 30/62] avg loss 0.00929757, throughput 3.30008K wps
[Epoch 19 Batch 60/62] avg loss 0.00932258, throughput 3.20742K wps
Begin Testing...
[Epoch 19] train avg loss 0.00940538, dev acc 0.7581, dev avg loss 0.484398, throughput 3.25897K wps
[Epoch 20 Batch 30/62] avg loss 0.00926272, throughput 3.27906K wps
[Epoch 20 Batch 60/62] avg loss 0.00915807, throughput 3.21628K wps
Begin Testing...
[Epoch 20] train avg loss 0.00925127, dev acc 0.7699, dev avg loss 0.478028, throughput 3.25371K wps
[Epoch 21 Batch 30/62] avg loss 0.00921355, throughput 3.28236K wps
[Epoch 21 Batch 60/62] avg loss 0.00887253, throughput 3.19717K wps
Begin Testing...
[Epoch 21] train avg loss 0.00913563, dev acc 0.7876, dev avg loss 0.471595, throughput 3.2466K wps
Observed Improvement.
Begin Testing...
[Epoch 22 Batch 30/62] avg loss 0.00898902, throughput 3.28949K wps
[Epoch 22 Batch 60/62] avg loss 0.00882666, throughput 3.20109K wps
Begin Testing...
[Epoch 22] train avg loss 0.00902601, dev acc 0.7906, dev avg loss 0.466633, throughput 3.2512K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00856457, throughput 3.27695K wps
[Epoch 23 Batch 60/62] avg loss 0.00879341, throughput 3.21859K wps
Begin Testing...
[Epoch 23] train avg loss 0.0088051, dev acc 0.7965, dev avg loss 0.461883, throughput 3.25334K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.00853078, throughput 3.28489K wps
[Epoch 24 Batch 60/62] avg loss 0.0084144, throughput 3.21253K wps
Begin Testing...
[Epoch 24] train avg loss 0.00854795, dev acc 0.7935, dev avg loss 0.460555, throughput 3.25576K wps
[Epoch 25 Batch 30/62] avg loss 0.00827107, throughput 3.28627K wps
[Epoch 25 Batch 60/62] avg loss 0.00842414, throughput 3.20945K wps
Begin Testing...
[Epoch 25] train avg loss 0.00845681, dev acc 0.8024, dev avg loss 0.452949, throughput 3.25405K wps
Observed Improvement.
Begin Testing...
[Epoch 26 Batch 30/62] avg loss 0.00825977, throughput 3.29524K wps
[Epoch 26 Batch 60/62] avg loss 0.00809842, throughput 3.19371K wps
Begin Testing...
[Epoch 26] train avg loss 0.0082652, dev acc 0.8112, dev avg loss 0.448851, throughput 3.24994K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.0079361, throughput 3.28754K wps
[Epoch 27 Batch 60/62] avg loss 0.00788342, throughput 3.18358K wps
Begin Testing...
[Epoch 27] train avg loss 0.00802647, dev acc 0.8024, dev avg loss 0.445071, throughput 3.24055K wps
[Epoch 28 Batch 30/62] avg loss 0.00771056, throughput 3.28671K wps
[Epoch 28 Batch 60/62] avg loss 0.00799471, throughput 3.21388K wps
Begin Testing...
[Epoch 28] train avg loss 0.00801368, dev acc 0.8083, dev avg loss 0.443412, throughput 3.25581K wps
[Epoch 29 Batch 30/62] avg loss 0.00784909, throughput 3.28138K wps
[Epoch 29 Batch 60/62] avg loss 0.00758326, throughput 3.20239K wps
Begin Testing...
[Epoch 29] train avg loss 0.00786056, dev acc 0.8112, dev avg loss 0.438738, throughput 3.24894K wps
Observed Improvement.
Begin Testing...
[Epoch 30 Batch 30/62] avg loss 0.00787317, throughput 3.28916K wps
[Epoch 30 Batch 60/62] avg loss 0.00736667, throughput 3.20718K wps
Begin Testing...
[Epoch 30] train avg loss 0.00770291, dev acc 0.8201, dev avg loss 0.43544, throughput 3.25325K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.00755771, throughput 3.27767K wps
[Epoch 31 Batch 60/62] avg loss 0.00744378, throughput 3.21293K wps
Begin Testing...
[Epoch 31] train avg loss 0.00756783, dev acc 0.8289, dev avg loss 0.432768, throughput 3.25114K wps
Observed Improvement.
Begin Testing...
[Epoch 32 Batch 30/62] avg loss 0.00746223, throughput 3.29083K wps
[Epoch 32 Batch 60/62] avg loss 0.00744054, throughput 3.21451K wps
Begin Testing...
[Epoch 32] train avg loss 0.00747913, dev acc 0.8201, dev avg loss 0.431228, throughput 3.25843K wps
[Epoch 33 Batch 30/62] avg loss 0.00736267, throughput 3.29245K wps
[Epoch 33 Batch 60/62] avg loss 0.00712075, throughput 3.22083K wps
Begin Testing...
[Epoch 33] train avg loss 0.00730322, dev acc 0.8171, dev avg loss 0.429532, throughput 3.26199K wps
[Epoch 34 Batch 30/62] avg loss 0.00715355, throughput 3.28257K wps
[Epoch 34 Batch 60/62] avg loss 0.00692048, throughput 3.20299K wps
Begin Testing...
[Epoch 34] train avg loss 0.00716026, dev acc 0.8053, dev avg loss 0.429522, throughput 3.24823K wps
[Epoch 35 Batch 30/62] avg loss 0.00720111, throughput 3.28879K wps
[Epoch 35 Batch 60/62] avg loss 0.00676693, throughput 3.21495K wps
Begin Testing...
[Epoch 35] train avg loss 0.0070798, dev acc 0.8260, dev avg loss 0.423417, throughput 3.2573K wps
[Epoch 36 Batch 30/62] avg loss 0.00682806, throughput 3.26946K wps
[Epoch 36 Batch 60/62] avg loss 0.00672782, throughput 3.20035K wps
Begin Testing...
[Epoch 36] train avg loss 0.0069029, dev acc 0.8260, dev avg loss 0.421572, throughput 3.24252K wps
[Epoch 37 Batch 30/62] avg loss 0.0068883, throughput 3.28951K wps
[Epoch 37 Batch 60/62] avg loss 0.00648205, throughput 3.2023K wps
Begin Testing...
[Epoch 37] train avg loss 0.00679046, dev acc 0.8230, dev avg loss 0.420145, throughput 3.25245K wps
[Epoch 38 Batch 30/62] avg loss 0.00662394, throughput 3.29967K wps
[Epoch 38 Batch 60/62] avg loss 0.00652516, throughput 3.15431K wps
Begin Testing...
[Epoch 38] train avg loss 0.00669993, dev acc 0.8319, dev avg loss 0.417615, throughput 3.23239K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.00644078, throughput 3.29677K wps
[Epoch 39 Batch 60/62] avg loss 0.00646486, throughput 3.23058K wps
Begin Testing...
[Epoch 39] train avg loss 0.00656479, dev acc 0.8378, dev avg loss 0.414154, throughput 3.26937K wps
Observed Improvement.
Begin Testing...
[Epoch 40 Batch 30/62] avg loss 0.006269, throughput 3.28872K wps
[Epoch 40 Batch 60/62] avg loss 0.00643694, throughput 3.22681K wps
Begin Testing...
[Epoch 40] train avg loss 0.00645309, dev acc 0.8319, dev avg loss 0.413539, throughput 3.26351K wps
[Epoch 41 Batch 30/62] avg loss 0.00618066, throughput 3.288K wps
[Epoch 41 Batch 60/62] avg loss 0.00627478, throughput 3.2239K wps
Begin Testing...
[Epoch 41] train avg loss 0.00628729, dev acc 0.8348, dev avg loss 0.417351, throughput 3.26128K wps
[Epoch 42 Batch 30/62] avg loss 0.00608563, throughput 3.26619K wps
[Epoch 42 Batch 60/62] avg loss 0.00611878, throughput 3.1988K wps
Begin Testing...
[Epoch 42] train avg loss 0.00628822, dev acc 0.8437, dev avg loss 0.410391, throughput 3.23794K wps
Observed Improvement.
Begin Testing...
[Epoch 43 Batch 30/62] avg loss 0.00633089, throughput 3.29269K wps
[Epoch 43 Batch 60/62] avg loss 0.00605646, throughput 3.17425K wps
Begin Testing...
[Epoch 43] train avg loss 0.00620954, dev acc 0.8407, dev avg loss 0.406543, throughput 3.23836K wps
[Epoch 44 Batch 30/62] avg loss 0.00601632, throughput 3.26978K wps
[Epoch 44 Batch 60/62] avg loss 0.00616703, throughput 3.21417K wps
Begin Testing...
[Epoch 44] train avg loss 0.00613436, dev acc 0.8407, dev avg loss 0.404639, throughput 3.24767K wps
[Epoch 45 Batch 30/62] avg loss 0.00594801, throughput 3.27335K wps
[Epoch 45 Batch 60/62] avg loss 0.00567657, throughput 3.19166K wps
Begin Testing...
[Epoch 45] train avg loss 0.00584877, dev acc 0.8437, dev avg loss 0.402757, throughput 3.23801K wps
Observed Improvement.
Begin Testing...
[Epoch 46 Batch 30/62] avg loss 0.00576025, throughput 3.27967K wps
[Epoch 46 Batch 60/62] avg loss 0.00573664, throughput 3.19758K wps
Begin Testing...
[Epoch 46] train avg loss 0.00582574, dev acc 0.8378, dev avg loss 0.402294, throughput 3.24455K wps
[Epoch 47 Batch 30/62] avg loss 0.0057566, throughput 3.27988K wps
[Epoch 47 Batch 60/62] avg loss 0.00541102, throughput 3.22313K wps
Begin Testing...
[Epoch 47] train avg loss 0.00568022, dev acc 0.8378, dev avg loss 0.401359, throughput 3.25717K wps
[Epoch 48 Batch 30/62] avg loss 0.00559114, throughput 3.28508K wps
[Epoch 48 Batch 60/62] avg loss 0.00542888, throughput 3.21675K wps
Begin Testing...
[Epoch 48] train avg loss 0.00563951, dev acc 0.8466, dev avg loss 0.398091, throughput 3.25713K wps
Observed Improvement.
Begin Testing...
[Epoch 49 Batch 30/62] avg loss 0.00545627, throughput 3.28318K wps
[Epoch 49 Batch 60/62] avg loss 0.00547582, throughput 3.21212K wps
Begin Testing...
[Epoch 49] train avg loss 0.00552178, dev acc 0.8496, dev avg loss 0.397886, throughput 3.25322K wps
Observed Improvement.
Begin Testing...
[Epoch 50 Batch 30/62] avg loss 0.00523795, throughput 3.30076K wps
[Epoch 50 Batch 60/62] avg loss 0.00527745, throughput 3.20865K wps
Begin Testing...
[Epoch 50] train avg loss 0.00535869, dev acc 0.8466, dev avg loss 0.395346, throughput 3.26085K wps
[Epoch 51 Batch 30/62] avg loss 0.00501881, throughput 3.29773K wps
[Epoch 51 Batch 60/62] avg loss 0.00537078, throughput 3.21118K wps
Begin Testing...
[Epoch 51] train avg loss 0.00526403, dev acc 0.8437, dev avg loss 0.39521, throughput 3.26078K wps
[Epoch 52 Batch 30/62] avg loss 0.00506332, throughput 3.28125K wps
[Epoch 52 Batch 60/62] avg loss 0.00522433, throughput 3.18658K wps
Begin Testing...
[Epoch 52] train avg loss 0.00522858, dev acc 0.8525, dev avg loss 0.393695, throughput 3.24081K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.00511182, throughput 3.23422K wps
[Epoch 53 Batch 60/62] avg loss 0.00512876, throughput 3.20777K wps
Begin Testing...
[Epoch 53] train avg loss 0.0051547, dev acc 0.8496, dev avg loss 0.391669, throughput 3.22778K wps
[Epoch 54 Batch 30/62] avg loss 0.00495415, throughput 3.30089K wps
[Epoch 54 Batch 60/62] avg loss 0.00493616, throughput 3.21493K wps
Begin Testing...
[Epoch 54] train avg loss 0.00505379, dev acc 0.8496, dev avg loss 0.391102, throughput 3.26312K wps
[Epoch 55 Batch 30/62] avg loss 0.00486215, throughput 3.28062K wps
[Epoch 55 Batch 60/62] avg loss 0.00489428, throughput 3.21474K wps
Begin Testing...
[Epoch 55] train avg loss 0.00496356, dev acc 0.8496, dev avg loss 0.390028, throughput 3.25455K wps
[Epoch 56 Batch 30/62] avg loss 0.00475153, throughput 3.2874K wps
[Epoch 56 Batch 60/62] avg loss 0.00487625, throughput 3.22618K wps
Begin Testing...
[Epoch 56] train avg loss 0.00481, dev acc 0.8584, dev avg loss 0.386887, throughput 3.26222K wps
Observed Improvement.
Begin Testing...
[Epoch 57 Batch 30/62] avg loss 0.00461463, throughput 3.29229K wps
[Epoch 57 Batch 60/62] avg loss 0.00475844, throughput 3.19482K wps
Begin Testing...
[Epoch 57] train avg loss 0.00478163, dev acc 0.8525, dev avg loss 0.387187, throughput 3.25074K wps
[Epoch 58 Batch 30/62] avg loss 0.00477517, throughput 3.28401K wps
[Epoch 58 Batch 60/62] avg loss 0.00455892, throughput 3.19737K wps
Begin Testing...
[Epoch 58] train avg loss 0.00475784, dev acc 0.8555, dev avg loss 0.385141, throughput 3.24691K wps
[Epoch 59 Batch 30/62] avg loss 0.00452081, throughput 3.29485K wps
[Epoch 59 Batch 60/62] avg loss 0.0045146, throughput 3.20637K wps
Begin Testing...
[Epoch 59] train avg loss 0.00457597, dev acc 0.8555, dev avg loss 0.383842, throughput 3.25737K wps
[Epoch 60 Batch 30/62] avg loss 0.00454056, throughput 3.29866K wps
[Epoch 60 Batch 60/62] avg loss 0.0043852, throughput 3.19559K wps
Begin Testing...
[Epoch 60] train avg loss 0.00450736, dev acc 0.8437, dev avg loss 0.384553, throughput 3.25272K wps
[Epoch 61 Batch 30/62] avg loss 0.00410702, throughput 3.29777K wps
[Epoch 61 Batch 60/62] avg loss 0.0044814, throughput 3.18466K wps
Begin Testing...
[Epoch 61] train avg loss 0.0043688, dev acc 0.8466, dev avg loss 0.383737, throughput 3.24584K wps
[Epoch 62 Batch 30/62] avg loss 0.00419522, throughput 3.26251K wps
[Epoch 62 Batch 60/62] avg loss 0.00437406, throughput 3.20422K wps
Begin Testing...
[Epoch 62] train avg loss 0.00432747, dev acc 0.8584, dev avg loss 0.380373, throughput 3.23906K wps
Observed Improvement.
Begin Testing...
[Epoch 63 Batch 30/62] avg loss 0.00407714, throughput 3.30158K wps
[Epoch 63 Batch 60/62] avg loss 0.00411834, throughput 3.2161K wps
Begin Testing...
[Epoch 63] train avg loss 0.00410773, dev acc 0.8584, dev avg loss 0.379346, throughput 3.26446K wps
Observed Improvement.
Begin Testing...
[Epoch 64 Batch 30/62] avg loss 0.00401969, throughput 3.30423K wps
[Epoch 64 Batch 60/62] avg loss 0.00413161, throughput 3.21654K wps
Begin Testing...
[Epoch 64] train avg loss 0.00413184, dev acc 0.8525, dev avg loss 0.382421, throughput 3.2656K wps
[Epoch 65 Batch 30/62] avg loss 0.00419302, throughput 3.30032K wps
[Epoch 65 Batch 60/62] avg loss 0.00398776, throughput 3.20855K wps
Begin Testing...
[Epoch 65] train avg loss 0.00412218, dev acc 0.8584, dev avg loss 0.377966, throughput 3.25992K wps
Observed Improvement.
Begin Testing...
[Epoch 66 Batch 30/62] avg loss 0.00410583, throughput 3.28205K wps
[Epoch 66 Batch 60/62] avg loss 0.0039137, throughput 3.19812K wps
Begin Testing...
[Epoch 66] train avg loss 0.0040628, dev acc 0.8525, dev avg loss 0.376769, throughput 3.24672K wps
[Epoch 67 Batch 30/62] avg loss 0.00385017, throughput 3.2898K wps
[Epoch 67 Batch 60/62] avg loss 0.00386832, throughput 3.19581K wps
Begin Testing...
[Epoch 67] train avg loss 0.00390026, dev acc 0.8525, dev avg loss 0.376512, throughput 3.248K wps
[Epoch 68 Batch 30/62] avg loss 0.00360363, throughput 3.27308K wps
[Epoch 68 Batch 60/62] avg loss 0.0040245, throughput 3.20448K wps
Begin Testing...
[Epoch 68] train avg loss 0.00389399, dev acc 0.8584, dev avg loss 0.375304, throughput 3.24455K wps
Observed Improvement.
Begin Testing...
[Epoch 69 Batch 30/62] avg loss 0.00369778, throughput 3.28377K wps
[Epoch 69 Batch 60/62] avg loss 0.00375637, throughput 3.20481K wps
Begin Testing...
[Epoch 69] train avg loss 0.00375584, dev acc 0.8555, dev avg loss 0.374063, throughput 3.25079K wps
[Epoch 70 Batch 30/62] avg loss 0.00376998, throughput 3.30356K wps
[Epoch 70 Batch 60/62] avg loss 0.00365905, throughput 3.19986K wps
Begin Testing...
[Epoch 70] train avg loss 0.00375759, dev acc 0.8496, dev avg loss 0.37425, throughput 3.25408K wps
[Epoch 71 Batch 30/62] avg loss 0.00361018, throughput 3.29701K wps
[Epoch 71 Batch 60/62] avg loss 0.0038209, throughput 3.20456K wps
Begin Testing...
[Epoch 71] train avg loss 0.00378114, dev acc 0.8555, dev avg loss 0.373344, throughput 3.25804K wps
[Epoch 72 Batch 30/62] avg loss 0.00364971, throughput 3.28281K wps
[Epoch 72 Batch 60/62] avg loss 0.00352686, throughput 3.20486K wps
Begin Testing...
[Epoch 72] train avg loss 0.00366988, dev acc 0.8525, dev avg loss 0.374595, throughput 3.25213K wps
[Epoch 73 Batch 30/62] avg loss 0.00320652, throughput 3.29344K wps
[Epoch 73 Batch 60/62] avg loss 0.00370516, throughput 3.21437K wps
Begin Testing...
[Epoch 73] train avg loss 0.00349602, dev acc 0.8525, dev avg loss 0.373117, throughput 3.26017K wps
[Epoch 74 Batch 30/62] avg loss 0.00334703, throughput 3.2818K wps
[Epoch 74 Batch 60/62] avg loss 0.00351496, throughput 3.20508K wps
Begin Testing...
[Epoch 74] train avg loss 0.00345905, dev acc 0.8525, dev avg loss 0.372888, throughput 3.24974K wps
[Epoch 75 Batch 30/62] avg loss 0.00320545, throughput 3.28979K wps
[Epoch 75 Batch 60/62] avg loss 0.00347545, throughput 3.20321K wps
Begin Testing...
[Epoch 75] train avg loss 0.00337038, dev acc 0.8525, dev avg loss 0.373053, throughput 3.25302K wps
[Epoch 76 Batch 30/62] avg loss 0.00330856, throughput 3.30198K wps
[Epoch 76 Batch 60/62] avg loss 0.00337072, throughput 3.23128K wps
Begin Testing...
[Epoch 76] train avg loss 0.00342807, dev acc 0.8584, dev avg loss 0.373171, throughput 3.2733K wps
Observed Improvement.
Begin Testing...
[Epoch 77 Batch 30/62] avg loss 0.00326736, throughput 3.30266K wps
[Epoch 77 Batch 60/62] avg loss 0.00332317, throughput 3.22467K wps
Begin Testing...
[Epoch 77] train avg loss 0.00335713, dev acc 0.8584, dev avg loss 0.373212, throughput 3.26861K wps
Observed Improvement.
Begin Testing...
[Epoch 78 Batch 30/62] avg loss 0.00322451, throughput 3.29326K wps
[Epoch 78 Batch 60/62] avg loss 0.00311293, throughput 3.20836K wps
Begin Testing...
[Epoch 78] train avg loss 0.00317741, dev acc 0.8555, dev avg loss 0.371199, throughput 3.25678K wps
[Epoch 79 Batch 30/62] avg loss 0.0029953, throughput 3.27736K wps
[Epoch 79 Batch 60/62] avg loss 0.00306595, throughput 3.20469K wps
Begin Testing...
[Epoch 79] train avg loss 0.00309627, dev acc 0.8525, dev avg loss 0.369629, throughput 3.24828K wps
[Epoch 80 Batch 30/62] avg loss 0.00327232, throughput 3.2998K wps
[Epoch 80 Batch 60/62] avg loss 0.00294874, throughput 3.21843K wps
Begin Testing...
[Epoch 80] train avg loss 0.00313723, dev acc 0.8584, dev avg loss 0.368709, throughput 3.26528K wps
Observed Improvement.
Begin Testing...
[Epoch 81 Batch 30/62] avg loss 0.00302327, throughput 3.30513K wps
[Epoch 81 Batch 60/62] avg loss 0.00303731, throughput 3.21444K wps
Begin Testing...
[Epoch 81] train avg loss 0.00306489, dev acc 0.8614, dev avg loss 0.368487, throughput 3.26611K wps
Observed Improvement.
Begin Testing...
[Epoch 82 Batch 30/62] avg loss 0.00311353, throughput 3.30706K wps
[Epoch 82 Batch 60/62] avg loss 0.00285204, throughput 3.19099K wps
Begin Testing...
[Epoch 82] train avg loss 0.00301522, dev acc 0.8525, dev avg loss 0.369542, throughput 3.25422K wps
[Epoch 83 Batch 30/62] avg loss 0.0028892, throughput 3.28052K wps
[Epoch 83 Batch 60/62] avg loss 0.00286933, throughput 3.20177K wps
Begin Testing...
[Epoch 83] train avg loss 0.00292491, dev acc 0.8584, dev avg loss 0.367586, throughput 3.24704K wps
[Epoch 84 Batch 30/62] avg loss 0.00281276, throughput 3.25715K wps
[Epoch 84 Batch 60/62] avg loss 0.00278473, throughput 3.22664K wps
Begin Testing...
[Epoch 84] train avg loss 0.00283189, dev acc 0.8496, dev avg loss 0.367427, throughput 3.24868K wps
[Epoch 85 Batch 30/62] avg loss 0.00266317, throughput 3.27901K wps
[Epoch 85 Batch 60/62] avg loss 0.00277987, throughput 3.21285K wps
Begin Testing...
[Epoch 85] train avg loss 0.00274355, dev acc 0.8525, dev avg loss 0.368001, throughput 3.25199K wps
[Epoch 86 Batch 30/62] avg loss 0.00276399, throughput 3.27619K wps
[Epoch 86 Batch 60/62] avg loss 0.00277995, throughput 3.20661K wps
Begin Testing...
[Epoch 86] train avg loss 0.00279632, dev acc 0.8584, dev avg loss 0.372429, throughput 3.2481K wps
[Epoch 87 Batch 30/62] avg loss 0.00276953, throughput 3.29314K wps
[Epoch 87 Batch 60/62] avg loss 0.00276403, throughput 3.19898K wps
Begin Testing...
[Epoch 87] train avg loss 0.00277532, dev acc 0.8584, dev avg loss 0.36634, throughput 3.25229K wps
[Epoch 88 Batch 30/62] avg loss 0.00272341, throughput 3.28826K wps
[Epoch 88 Batch 60/62] avg loss 0.00259103, throughput 3.18622K wps
Begin Testing...
[Epoch 88] train avg loss 0.00273688, dev acc 0.8525, dev avg loss 0.366653, throughput 3.24223K wps
[Epoch 89 Batch 30/62] avg loss 0.00262559, throughput 3.27552K wps
[Epoch 89 Batch 60/62] avg loss 0.00263009, throughput 3.2013K wps
Begin Testing...
[Epoch 89] train avg loss 0.0026276, dev acc 0.8525, dev avg loss 0.366414, throughput 3.24406K wps
[Epoch 90 Batch 30/62] avg loss 0.00248097, throughput 3.27696K wps
[Epoch 90 Batch 60/62] avg loss 0.00255751, throughput 3.21091K wps
Begin Testing...
[Epoch 90] train avg loss 0.00256093, dev acc 0.8555, dev avg loss 0.368672, throughput 3.25054K wps
[Epoch 91 Batch 30/62] avg loss 0.00240733, throughput 3.28149K wps
[Epoch 91 Batch 60/62] avg loss 0.00256801, throughput 3.21395K wps
Begin Testing...
[Epoch 91] train avg loss 0.00250482, dev acc 0.8584, dev avg loss 0.365233, throughput 3.25352K wps
[Epoch 92 Batch 30/62] avg loss 0.00240913, throughput 3.27968K wps
[Epoch 92 Batch 60/62] avg loss 0.00248969, throughput 3.21315K wps
Begin Testing...
[Epoch 92] train avg loss 0.00247305, dev acc 0.8525, dev avg loss 0.367553, throughput 3.25222K wps
[Epoch 93 Batch 30/62] avg loss 0.00243132, throughput 3.28146K wps
[Epoch 93 Batch 60/62] avg loss 0.00249823, throughput 3.20543K wps
Begin Testing...
[Epoch 93] train avg loss 0.00254293, dev acc 0.8496, dev avg loss 0.379251, throughput 3.24896K wps
[Epoch 94 Batch 30/62] avg loss 0.0024378, throughput 3.293K wps
[Epoch 94 Batch 60/62] avg loss 0.00239998, throughput 3.19164K wps
Begin Testing...
[Epoch 94] train avg loss 0.00246477, dev acc 0.8584, dev avg loss 0.366177, throughput 3.2469K wps
[Epoch 95 Batch 30/62] avg loss 0.00227371, throughput 3.30344K wps
[Epoch 95 Batch 60/62] avg loss 0.00227674, throughput 3.18404K wps
Begin Testing...
[Epoch 95] train avg loss 0.00227754, dev acc 0.8555, dev avg loss 0.365248, throughput 3.2491K wps
[Epoch 96 Batch 30/62] avg loss 0.00232007, throughput 3.24806K wps
[Epoch 96 Batch 60/62] avg loss 0.00218271, throughput 3.2145K wps
Begin Testing...
[Epoch 96] train avg loss 0.00230459, dev acc 0.8614, dev avg loss 0.36428, throughput 3.23756K wps
Observed Improvement.
Begin Testing...
[Epoch 97 Batch 30/62] avg loss 0.00225529, throughput 3.30098K wps
[Epoch 97 Batch 60/62] avg loss 0.00223228, throughput 3.20414K wps
Begin Testing...
[Epoch 97] train avg loss 0.00232769, dev acc 0.8555, dev avg loss 0.366315, throughput 3.26013K wps
[Epoch 98 Batch 30/62] avg loss 0.00224736, throughput 3.28878K wps
[Epoch 98 Batch 60/62] avg loss 0.00215672, throughput 3.20876K wps
Begin Testing...
[Epoch 98] train avg loss 0.00221799, dev acc 0.8584, dev avg loss 0.364125, throughput 3.25526K wps
[Epoch 99 Batch 30/62] avg loss 0.00218745, throughput 3.28555K wps
[Epoch 99 Batch 60/62] avg loss 0.00223463, throughput 3.21642K wps
Begin Testing...
[Epoch 99] train avg loss 0.0022391, dev acc 0.8525, dev avg loss 0.364526, throughput 3.25625K wps
[Epoch 100 Batch 30/62] avg loss 0.00206785, throughput 3.29483K wps
[Epoch 100 Batch 60/62] avg loss 0.00205972, throughput 3.20876K wps
Begin Testing...
[Epoch 100] train avg loss 0.00208533, dev acc 0.8555, dev avg loss 0.364314, throughput 3.2583K wps
[Epoch 101 Batch 30/62] avg loss 0.00213796, throughput 3.29151K wps
[Epoch 101 Batch 60/62] avg loss 0.00216935, throughput 3.21359K wps
Begin Testing...
[Epoch 101] train avg loss 0.00222081, dev acc 0.8614, dev avg loss 0.364383, throughput 3.2577K wps
Observed Improvement.
Begin Testing...
[Epoch 102 Batch 30/62] avg loss 0.00200224, throughput 3.29731K wps
[Epoch 102 Batch 60/62] avg loss 0.00210463, throughput 3.19654K wps
Begin Testing...
[Epoch 102] train avg loss 0.0020628, dev acc 0.8555, dev avg loss 0.364376, throughput 3.25332K wps
[Epoch 103 Batch 30/62] avg loss 0.0020568, throughput 3.30885K wps
[Epoch 103 Batch 60/62] avg loss 0.00213695, throughput 3.19267K wps
Begin Testing...
[Epoch 103] train avg loss 0.00209301, dev acc 0.8643, dev avg loss 0.36446, throughput 3.2573K wps
Observed Improvement.
Begin Testing...
[Epoch 104 Batch 30/62] avg loss 0.00187924, throughput 3.2445K wps
[Epoch 104 Batch 60/62] avg loss 0.00200861, throughput 3.21236K wps
Begin Testing...
[Epoch 104] train avg loss 0.00194199, dev acc 0.8555, dev avg loss 0.365199, throughput 3.23459K wps
[Epoch 105 Batch 30/62] avg loss 0.00187002, throughput 3.26632K wps
[Epoch 105 Batch 60/62] avg loss 0.00207143, throughput 3.20207K wps
Begin Testing...
[Epoch 105] train avg loss 0.00198891, dev acc 0.8555, dev avg loss 0.364602, throughput 3.24168K wps
[Epoch 106 Batch 30/62] avg loss 0.00196804, throughput 3.29409K wps
[Epoch 106 Batch 60/62] avg loss 0.00196484, throughput 3.21048K wps
Begin Testing...
[Epoch 106] train avg loss 0.00195723, dev acc 0.8555, dev avg loss 0.366714, throughput 3.25873K wps
[Epoch 107 Batch 30/62] avg loss 0.00198081, throughput 3.28299K wps
[Epoch 107 Batch 60/62] avg loss 0.00195164, throughput 3.21466K wps
Begin Testing...
[Epoch 107] train avg loss 0.00198036, dev acc 0.8584, dev avg loss 0.364456, throughput 3.25571K wps
[Epoch 108 Batch 30/62] avg loss 0.00184704, throughput 3.29403K wps
[Epoch 108 Batch 60/62] avg loss 0.00194309, throughput 3.21952K wps
Begin Testing...
[Epoch 108] train avg loss 0.0019111, dev acc 0.8555, dev avg loss 0.365598, throughput 3.26185K wps
[Epoch 109 Batch 30/62] avg loss 0.00180241, throughput 3.28845K wps
[Epoch 109 Batch 60/62] avg loss 0.00191124, throughput 3.21354K wps
Begin Testing...
[Epoch 109] train avg loss 0.00187278, dev acc 0.8496, dev avg loss 0.370632, throughput 3.25676K wps
[Epoch 110 Batch 30/62] avg loss 0.00178788, throughput 3.27254K wps
[Epoch 110 Batch 60/62] avg loss 0.00187819, throughput 3.187K wps
Begin Testing...
[Epoch 110] train avg loss 0.00187642, dev acc 0.8555, dev avg loss 0.365043, throughput 3.23679K wps
[Epoch 111 Batch 30/62] avg loss 0.00176685, throughput 3.30332K wps
[Epoch 111 Batch 60/62] avg loss 0.00175755, throughput 3.20052K wps
Begin Testing...
[Epoch 111] train avg loss 0.00176715, dev acc 0.8555, dev avg loss 0.365038, throughput 3.25792K wps
[Epoch 112 Batch 30/62] avg loss 0.00168496, throughput 3.302K wps
[Epoch 112 Batch 60/62] avg loss 0.00183479, throughput 3.20322K wps
Begin Testing...
[Epoch 112] train avg loss 0.00176973, dev acc 0.8555, dev avg loss 0.365994, throughput 3.25988K wps
[Epoch 113 Batch 30/62] avg loss 0.00175258, throughput 3.29522K wps
[Epoch 113 Batch 60/62] avg loss 0.00158924, throughput 3.20026K wps
Begin Testing...
[Epoch 113] train avg loss 0.001688, dev acc 0.8525, dev avg loss 0.3737, throughput 3.25448K wps
[Epoch 114 Batch 30/62] avg loss 0.00163972, throughput 3.29369K wps
[Epoch 114 Batch 60/62] avg loss 0.00171251, throughput 3.21116K wps
Begin Testing...
[Epoch 114] train avg loss 0.00169409, dev acc 0.8584, dev avg loss 0.365743, throughput 3.26037K wps
[Epoch 115 Batch 30/62] avg loss 0.00173603, throughput 3.29197K wps
[Epoch 115 Batch 60/62] avg loss 0.00173142, throughput 3.16965K wps
Begin Testing...
[Epoch 115] train avg loss 0.00173526, dev acc 0.8555, dev avg loss 0.365798, throughput 3.23844K wps
[Epoch 116 Batch 30/62] avg loss 0.00158099, throughput 3.29108K wps
[Epoch 116 Batch 60/62] avg loss 0.0016909, throughput 3.19277K wps
Begin Testing...
[Epoch 116] train avg loss 0.00164676, dev acc 0.8584, dev avg loss 0.36466, throughput 3.24823K wps
[Epoch 117 Batch 30/62] avg loss 0.00156258, throughput 3.26821K wps
[Epoch 117 Batch 60/62] avg loss 0.00161541, throughput 3.21789K wps
Begin Testing...
[Epoch 117] train avg loss 0.00159239, dev acc 0.8555, dev avg loss 0.366133, throughput 3.24893K wps
[Epoch 118 Batch 30/62] avg loss 0.0015319, throughput 3.28127K wps
[Epoch 118 Batch 60/62] avg loss 0.00160097, throughput 3.22438K wps
Begin Testing...
[Epoch 118] train avg loss 0.00158305, dev acc 0.8525, dev avg loss 0.367429, throughput 3.25878K wps
[Epoch 119 Batch 30/62] avg loss 0.00157873, throughput 3.28631K wps
[Epoch 119 Batch 60/62] avg loss 0.00161901, throughput 3.21722K wps
Begin Testing...
[Epoch 119] train avg loss 0.00163983, dev acc 0.8496, dev avg loss 0.364519, throughput 3.25757K wps
[Epoch 120 Batch 30/62] avg loss 0.00161978, throughput 3.28874K wps
[Epoch 120 Batch 60/62] avg loss 0.00152486, throughput 3.21754K wps
Begin Testing...
[Epoch 120] train avg loss 0.00158444, dev acc 0.8525, dev avg loss 0.364824, throughput 3.25869K wps
[Epoch 121 Batch 30/62] avg loss 0.00152075, throughput 3.29546K wps
[Epoch 121 Batch 60/62] avg loss 0.0014443, throughput 3.19739K wps
Begin Testing...
[Epoch 121] train avg loss 0.00149456, dev acc 0.8555, dev avg loss 0.366556, throughput 3.25131K wps
[Epoch 122 Batch 30/62] avg loss 0.00150652, throughput 3.27856K wps
[Epoch 122 Batch 60/62] avg loss 0.00147929, throughput 3.21676K wps
Begin Testing...
[Epoch 122] train avg loss 0.00150117, dev acc 0.8555, dev avg loss 0.36599, throughput 3.2526K wps
[Epoch 123 Batch 30/62] avg loss 0.00143549, throughput 3.2807K wps
[Epoch 123 Batch 60/62] avg loss 0.00147467, throughput 3.21933K wps
Begin Testing...
[Epoch 123] train avg loss 0.00146681, dev acc 0.8525, dev avg loss 0.365881, throughput 3.25576K wps
[Epoch 124 Batch 30/62] avg loss 0.00145744, throughput 3.2743K wps
[Epoch 124 Batch 60/62] avg loss 0.00146937, throughput 3.21077K wps
Begin Testing...
[Epoch 124] train avg loss 0.00147614, dev acc 0.8555, dev avg loss 0.365703, throughput 3.24799K wps
[Epoch 125 Batch 30/62] avg loss 0.0015323, throughput 3.27742K wps
[Epoch 125 Batch 60/62] avg loss 0.00139922, throughput 3.20748K wps
Begin Testing...
[Epoch 125] train avg loss 0.00152967, dev acc 0.8496, dev avg loss 0.372171, throughput 3.24599K wps
[Epoch 126 Batch 30/62] avg loss 0.0014259, throughput 3.27796K wps
[Epoch 126 Batch 60/62] avg loss 0.00156306, throughput 3.2172K wps
Begin Testing...
[Epoch 126] train avg loss 0.00150878, dev acc 0.8496, dev avg loss 0.368812, throughput 3.25521K wps
[Epoch 127 Batch 30/62] avg loss 0.00144166, throughput 3.29203K wps
[Epoch 127 Batch 60/62] avg loss 0.00145053, throughput 3.22531K wps
Begin Testing...
[Epoch 127] train avg loss 0.0014721, dev acc 0.8584, dev avg loss 0.36732, throughput 3.26394K wps
[Epoch 128 Batch 30/62] avg loss 0.00136985, throughput 3.29486K wps
[Epoch 128 Batch 60/62] avg loss 0.0013289, throughput 3.21115K wps
Begin Testing...
[Epoch 128] train avg loss 0.00136806, dev acc 0.8496, dev avg loss 0.371846, throughput 3.25868K wps
[Epoch 129 Batch 30/62] avg loss 0.0013821, throughput 3.31805K wps
[Epoch 129 Batch 60/62] avg loss 0.00139517, throughput 3.2136K wps
Begin Testing...
[Epoch 129] train avg loss 0.00139346, dev acc 0.8555, dev avg loss 0.369086, throughput 3.27156K wps
[Epoch 130 Batch 30/62] avg loss 0.0013536, throughput 3.29688K wps
[Epoch 130 Batch 60/62] avg loss 0.00128958, throughput 3.19349K wps
Begin Testing...
[Epoch 130] train avg loss 0.00134434, dev acc 0.8525, dev avg loss 0.368496, throughput 3.25161K wps
[Epoch 131 Batch 30/62] avg loss 0.00131184, throughput 3.2578K wps
[Epoch 131 Batch 60/62] avg loss 0.00131604, throughput 3.21028K wps
Begin Testing...
[Epoch 131] train avg loss 0.00131661, dev acc 0.8525, dev avg loss 0.367592, throughput 3.24169K wps
[Epoch 132 Batch 30/62] avg loss 0.00139727, throughput 3.27217K wps
[Epoch 132 Batch 60/62] avg loss 0.00127223, throughput 3.21493K wps
Begin Testing...
[Epoch 132] train avg loss 0.00133895, dev acc 0.8525, dev avg loss 0.368574, throughput 3.24888K wps
[Epoch 133 Batch 30/62] avg loss 0.00134312, throughput 3.2639K wps
[Epoch 133 Batch 60/62] avg loss 0.00132147, throughput 3.19766K wps
Begin Testing...
[Epoch 133] train avg loss 0.00136482, dev acc 0.8496, dev avg loss 0.368562, throughput 3.23814K wps
[Epoch 134 Batch 30/62] avg loss 0.0012737, throughput 3.29262K wps
[Epoch 134 Batch 60/62] avg loss 0.00121839, throughput 3.19642K wps
Begin Testing...
[Epoch 134] train avg loss 0.00128707, dev acc 0.8496, dev avg loss 0.367548, throughput 3.24961K wps
[Epoch 135 Batch 30/62] avg loss 0.00128015, throughput 3.26346K wps
[Epoch 135 Batch 60/62] avg loss 0.00131058, throughput 3.20838K wps
Begin Testing...
[Epoch 135] train avg loss 0.00131968, dev acc 0.8525, dev avg loss 0.367978, throughput 3.24175K wps
[Epoch 136 Batch 30/62] avg loss 0.00125901, throughput 3.28168K wps
[Epoch 136 Batch 60/62] avg loss 0.001353, throughput 3.22051K wps
Begin Testing...
[Epoch 136] train avg loss 0.00132266, dev acc 0.8496, dev avg loss 0.369202, throughput 3.25707K wps
[Epoch 137 Batch 30/62] avg loss 0.00124558, throughput 3.29075K wps
[Epoch 137 Batch 60/62] avg loss 0.00113385, throughput 3.21908K wps
Begin Testing...
[Epoch 137] train avg loss 0.00120131, dev acc 0.8466, dev avg loss 0.369259, throughput 3.26036K wps
[Epoch 138 Batch 30/62] avg loss 0.00120627, throughput 3.30146K wps
[Epoch 138 Batch 60/62] avg loss 0.00120463, throughput 3.22591K wps
Begin Testing...
[Epoch 138] train avg loss 0.00121954, dev acc 0.8466, dev avg loss 0.370723, throughput 3.26937K wps
[Epoch 139 Batch 30/62] avg loss 0.00133722, throughput 3.31596K wps
[Epoch 139 Batch 60/62] avg loss 0.00114421, throughput 3.24074K wps
Begin Testing...
[Epoch 139] train avg loss 0.00126007, dev acc 0.8496, dev avg loss 0.370389, throughput 3.28303K wps
[Epoch 140 Batch 30/62] avg loss 0.0010956, throughput 3.27717K wps
[Epoch 140 Batch 60/62] avg loss 0.00117119, throughput 3.20973K wps
Begin Testing...
[Epoch 140] train avg loss 0.00117128, dev acc 0.8466, dev avg loss 0.372232, throughput 3.24906K wps
[Epoch 141 Batch 30/62] avg loss 0.0011951, throughput 3.28316K wps
[Epoch 141 Batch 60/62] avg loss 0.00121272, throughput 3.20473K wps
Begin Testing...
[Epoch 141] train avg loss 0.00122205, dev acc 0.8437, dev avg loss 0.384088, throughput 3.25128K wps
[Epoch 142 Batch 30/62] avg loss 0.00112176, throughput 3.29191K wps
[Epoch 142 Batch 60/62] avg loss 0.00109783, throughput 3.2153K wps
Begin Testing...
[Epoch 142] train avg loss 0.00116474, dev acc 0.8555, dev avg loss 0.370725, throughput 3.25961K wps
[Epoch 143 Batch 30/62] avg loss 0.00110053, throughput 3.29312K wps
[Epoch 143 Batch 60/62] avg loss 0.00110655, throughput 3.21469K wps
Begin Testing...
[Epoch 143] train avg loss 0.00111039, dev acc 0.8525, dev avg loss 0.371312, throughput 3.25963K wps
[Epoch 144 Batch 30/62] avg loss 0.00107454, throughput 3.28934K wps
[Epoch 144 Batch 60/62] avg loss 0.00117364, throughput 3.21945K wps
Begin Testing...
[Epoch 144] train avg loss 0.00116364, dev acc 0.8496, dev avg loss 0.372013, throughput 3.26005K wps
[Epoch 145 Batch 30/62] avg loss 0.00109571, throughput 3.27344K wps
[Epoch 145 Batch 60/62] avg loss 0.0010856, throughput 3.20322K wps
Begin Testing...
[Epoch 145] train avg loss 0.00110399, dev acc 0.8496, dev avg loss 0.37802, throughput 3.24485K wps
[Epoch 146 Batch 30/62] avg loss 0.00104988, throughput 3.29623K wps
[Epoch 146 Batch 60/62] avg loss 0.00116397, throughput 3.20969K wps
Begin Testing...
[Epoch 146] train avg loss 0.00112736, dev acc 0.8496, dev avg loss 0.372064, throughput 3.26027K wps
[Epoch 147 Batch 30/62] avg loss 0.00111341, throughput 3.29429K wps
[Epoch 147 Batch 60/62] avg loss 0.00108536, throughput 3.21532K wps
Begin Testing...
[Epoch 147] train avg loss 0.00110039, dev acc 0.8466, dev avg loss 0.37485, throughput 3.26089K wps
[Epoch 148 Batch 30/62] avg loss 0.00107183, throughput 3.28967K wps
[Epoch 148 Batch 60/62] avg loss 0.00110682, throughput 3.21984K wps
Begin Testing...
[Epoch 148] train avg loss 0.00109373, dev acc 0.8466, dev avg loss 0.374885, throughput 3.26044K wps
[Epoch 149 Batch 30/62] avg loss 0.00101506, throughput 3.28458K wps
[Epoch 149 Batch 60/62] avg loss 0.00104148, throughput 3.22469K wps
Begin Testing...
[Epoch 149] train avg loss 0.00104567, dev acc 0.8525, dev avg loss 0.371827, throughput 3.26043K wps
[Epoch 150 Batch 30/62] avg loss 0.00102654, throughput 3.28528K wps
[Epoch 150 Batch 60/62] avg loss 0.000998435, throughput 3.22241K wps
Begin Testing...
[Epoch 150] train avg loss 0.0010261, dev acc 0.8525, dev avg loss 0.371364, throughput 3.25893K wps
[Epoch 151 Batch 30/62] avg loss 0.000985997, throughput 3.27879K wps
[Epoch 151 Batch 60/62] avg loss 0.00101642, throughput 3.22233K wps
Begin Testing...
[Epoch 151] train avg loss 0.00100666, dev acc 0.8496, dev avg loss 0.376663, throughput 3.25521K wps
[Epoch 152 Batch 30/62] avg loss 0.00101168, throughput 3.27153K wps
[Epoch 152 Batch 60/62] avg loss 0.00101171, throughput 3.21785K wps
Begin Testing...
[Epoch 152] train avg loss 0.00102473, dev acc 0.8466, dev avg loss 0.375178, throughput 3.25036K wps
[Epoch 153 Batch 30/62] avg loss 0.00110823, throughput 3.28608K wps
[Epoch 153 Batch 60/62] avg loss 0.000949908, throughput 3.21008K wps
Begin Testing...
[Epoch 153] train avg loss 0.00104609, dev acc 0.8466, dev avg loss 0.376804, throughput 3.25461K wps
[Epoch 154 Batch 30/62] avg loss 0.00104793, throughput 3.29134K wps
[Epoch 154 Batch 60/62] avg loss 0.00100985, throughput 3.21294K wps
Begin Testing...
[Epoch 154] train avg loss 0.00103013, dev acc 0.8525, dev avg loss 0.374622, throughput 3.25749K wps
[Epoch 155 Batch 30/62] avg loss 0.000999687, throughput 3.28629K wps
[Epoch 155 Batch 60/62] avg loss 0.000994688, throughput 3.2007K wps
Begin Testing...
[Epoch 155] train avg loss 0.00101511, dev acc 0.8496, dev avg loss 0.374217, throughput 3.24997K wps
[Epoch 156 Batch 30/62] avg loss 0.00095133, throughput 3.29181K wps
[Epoch 156 Batch 60/62] avg loss 0.000950011, throughput 3.20645K wps
Begin Testing...
[Epoch 156] train avg loss 0.000960891, dev acc 0.8525, dev avg loss 0.375143, throughput 3.25555K wps
[Epoch 157 Batch 30/62] avg loss 0.00101524, throughput 3.29672K wps
[Epoch 157 Batch 60/62] avg loss 0.000889577, throughput 3.23563K wps
Begin Testing...
[Epoch 157] train avg loss 0.000950281, dev acc 0.8525, dev avg loss 0.375857, throughput 3.27133K wps
[Epoch 158 Batch 30/62] avg loss 0.000914818, throughput 3.2949K wps
[Epoch 158 Batch 60/62] avg loss 0.00100693, throughput 3.21582K wps
Begin Testing...
[Epoch 158] train avg loss 0.000973039, dev acc 0.8466, dev avg loss 0.377133, throughput 3.26024K wps
[Epoch 159 Batch 30/62] avg loss 0.000985964, throughput 3.27729K wps
[Epoch 159 Batch 60/62] avg loss 0.000950745, throughput 3.20579K wps
Begin Testing...
[Epoch 159] train avg loss 0.000996631, dev acc 0.8525, dev avg loss 0.374614, throughput 3.24785K wps
[Epoch 160 Batch 30/62] avg loss 0.000903038, throughput 3.29022K wps
[Epoch 160 Batch 60/62] avg loss 0.000981396, throughput 3.20961K wps
Begin Testing...
[Epoch 160] train avg loss 0.000957649, dev acc 0.8555, dev avg loss 0.37403, throughput 3.25843K wps
[Epoch 161 Batch 30/62] avg loss 0.000936487, throughput 3.28228K wps
[Epoch 161 Batch 60/62] avg loss 0.000931473, throughput 3.21005K wps
Begin Testing...
[Epoch 161] train avg loss 0.000935447, dev acc 0.8466, dev avg loss 0.375159, throughput 3.25261K wps
[Epoch 162 Batch 30/62] avg loss 0.000903088, throughput 3.30293K wps
[Epoch 162 Batch 60/62] avg loss 0.000831458, throughput 3.22183K wps
Begin Testing...
[Epoch 162] train avg loss 0.000878911, dev acc 0.8466, dev avg loss 0.37689, throughput 3.26763K wps
[Epoch 163 Batch 30/62] avg loss 0.000886491, throughput 3.27658K wps
[Epoch 163 Batch 60/62] avg loss 0.000905296, throughput 3.22862K wps
Begin Testing...
[Epoch 163] train avg loss 0.000898404, dev acc 0.8466, dev avg loss 0.376093, throughput 3.25753K wps
[Epoch 164 Batch 30/62] avg loss 0.000848844, throughput 3.26825K wps
[Epoch 164 Batch 60/62] avg loss 0.000927229, throughput 3.20827K wps
Begin Testing...
[Epoch 164] train avg loss 0.000897372, dev acc 0.8466, dev avg loss 0.376088, throughput 3.24564K wps
[Epoch 165 Batch 30/62] avg loss 0.000873833, throughput 3.28933K wps
[Epoch 165 Batch 60/62] avg loss 0.000833361, throughput 3.2101K wps
Begin Testing...
[Epoch 165] train avg loss 0.000859219, dev acc 0.8525, dev avg loss 0.376409, throughput 3.25645K wps
[Epoch 166 Batch 30/62] avg loss 0.000924789, throughput 3.29164K wps
[Epoch 166 Batch 60/62] avg loss 0.000808876, throughput 3.22702K wps
Begin Testing...
[Epoch 166] train avg loss 0.000873812, dev acc 0.8525, dev avg loss 0.378113, throughput 3.2657K wps
[Epoch 167 Batch 30/62] avg loss 0.000824417, throughput 3.26999K wps
[Epoch 167 Batch 60/62] avg loss 0.000785194, throughput 3.23147K wps
Begin Testing...
[Epoch 167] train avg loss 0.000813555, dev acc 0.8466, dev avg loss 0.379668, throughput 3.25677K wps
[Epoch 168 Batch 30/62] avg loss 0.000828165, throughput 3.28809K wps
[Epoch 168 Batch 60/62] avg loss 0.000781142, throughput 3.21513K wps
Begin Testing...
[Epoch 168] train avg loss 0.000857971, dev acc 0.8466, dev avg loss 0.37882, throughput 3.25716K wps
[Epoch 169 Batch 30/62] avg loss 0.000855686, throughput 3.27099K wps
[Epoch 169 Batch 60/62] avg loss 0.000833252, throughput 3.22662K wps
Begin Testing...
[Epoch 169] train avg loss 0.00084402, dev acc 0.8466, dev avg loss 0.381809, throughput 3.25485K wps
[Epoch 170 Batch 30/62] avg loss 0.000811151, throughput 3.27943K wps
[Epoch 170 Batch 60/62] avg loss 0.000813026, throughput 3.21751K wps
Begin Testing...
[Epoch 170] train avg loss 0.00081173, dev acc 0.8466, dev avg loss 0.380015, throughput 3.25449K wps
[Epoch 171 Batch 30/62] avg loss 0.000767272, throughput 3.27385K wps
[Epoch 171 Batch 60/62] avg loss 0.000746931, throughput 3.21187K wps
Begin Testing...
[Epoch 171] train avg loss 0.000784016, dev acc 0.8614, dev avg loss 0.378949, throughput 3.24868K wps
[Epoch 172 Batch 30/62] avg loss 0.000844578, throughput 3.27625K wps
[Epoch 172 Batch 60/62] avg loss 0.000806651, throughput 3.21645K wps
Begin Testing...
[Epoch 172] train avg loss 0.000839782, dev acc 0.8496, dev avg loss 0.383145, throughput 3.25301K wps
[Epoch 173 Batch 30/62] avg loss 0.000835561, throughput 3.2884K wps
[Epoch 173 Batch 60/62] avg loss 0.000779555, throughput 3.21413K wps
Begin Testing...
[Epoch 173] train avg loss 0.000814479, dev acc 0.8466, dev avg loss 0.379758, throughput 3.25593K wps
[Epoch 174 Batch 30/62] avg loss 0.000741419, throughput 3.2925K wps
[Epoch 174 Batch 60/62] avg loss 0.000840856, throughput 3.22981K wps
Begin Testing...
[Epoch 174] train avg loss 0.000816081, dev acc 0.8466, dev avg loss 0.378659, throughput 3.26704K wps
[Epoch 175 Batch 30/62] avg loss 0.000730533, throughput 3.26917K wps
[Epoch 175 Batch 60/62] avg loss 0.000817584, throughput 3.21827K wps
Begin Testing...
[Epoch 175] train avg loss 0.00079049, dev acc 0.8466, dev avg loss 0.384571, throughput 3.25117K wps
[Epoch 176 Batch 30/62] avg loss 0.00084928, throughput 3.2849K wps
[Epoch 176 Batch 60/62] avg loss 0.000840933, throughput 3.2113K wps
Begin Testing...
[Epoch 176] train avg loss 0.000862082, dev acc 0.8466, dev avg loss 0.38266, throughput 3.25413K wps
[Epoch 177 Batch 30/62] avg loss 0.000833658, throughput 3.27925K wps
[Epoch 177 Batch 60/62] avg loss 0.000783762, throughput 3.19901K wps
Begin Testing...
[Epoch 177] train avg loss 0.000821322, dev acc 0.8466, dev avg loss 0.381922, throughput 3.24428K wps
[Epoch 178 Batch 30/62] avg loss 0.000756882, throughput 3.29331K wps
[Epoch 178 Batch 60/62] avg loss 0.00071922, throughput 3.21364K wps
Begin Testing...
[Epoch 178] train avg loss 0.000759601, dev acc 0.8466, dev avg loss 0.382728, throughput 3.25982K wps
[Epoch 179 Batch 30/62] avg loss 0.000808407, throughput 3.29347K wps
[Epoch 179 Batch 60/62] avg loss 0.000781836, throughput 3.2225K wps
Begin Testing...
[Epoch 179] train avg loss 0.000798695, dev acc 0.8496, dev avg loss 0.380396, throughput 3.26322K wps
[Epoch 180 Batch 30/62] avg loss 0.000759115, throughput 3.28388K wps
[Epoch 180 Batch 60/62] avg loss 0.000726675, throughput 3.21733K wps
Begin Testing...
[Epoch 180] train avg loss 0.000745121, dev acc 0.8466, dev avg loss 0.37961, throughput 3.25638K wps
[Epoch 181 Batch 30/62] avg loss 0.000678367, throughput 3.27131K wps
[Epoch 181 Batch 60/62] avg loss 0.000776152, throughput 3.22177K wps
Begin Testing...
[Epoch 181] train avg loss 0.000734015, dev acc 0.8466, dev avg loss 0.381074, throughput 3.25282K wps
[Epoch 182 Batch 30/62] avg loss 0.000736181, throughput 3.27285K wps
[Epoch 182 Batch 60/62] avg loss 0.000760839, throughput 3.21773K wps
Begin Testing...
[Epoch 182] train avg loss 0.000766294, dev acc 0.8525, dev avg loss 0.378927, throughput 3.25054K wps
[Epoch 183 Batch 30/62] avg loss 0.000727317, throughput 3.28869K wps
[Epoch 183 Batch 60/62] avg loss 0.000674948, throughput 3.2175K wps
Begin Testing...
[Epoch 183] train avg loss 0.000724064, dev acc 0.8466, dev avg loss 0.380532, throughput 3.25846K wps
[Epoch 184 Batch 30/62] avg loss 0.000748804, throughput 3.28727K wps
[Epoch 184 Batch 60/62] avg loss 0.000736394, throughput 3.21523K wps
Begin Testing...
[Epoch 184] train avg loss 0.000752211, dev acc 0.8496, dev avg loss 0.382508, throughput 3.25666K wps
[Epoch 185 Batch 30/62] avg loss 0.000702008, throughput 3.28542K wps
[Epoch 185 Batch 60/62] avg loss 0.000657161, throughput 3.20144K wps
Begin Testing...
[Epoch 185] train avg loss 0.000690785, dev acc 0.8466, dev avg loss 0.381517, throughput 3.24957K wps
[Epoch 186 Batch 30/62] avg loss 0.0006827, throughput 3.29302K wps
[Epoch 186 Batch 60/62] avg loss 0.000691809, throughput 3.21057K wps
Begin Testing...
[Epoch 186] train avg loss 0.000703831, dev acc 0.8496, dev avg loss 0.381795, throughput 3.25777K wps
[Epoch 187 Batch 30/62] avg loss 0.000708259, throughput 3.28894K wps
[Epoch 187 Batch 60/62] avg loss 0.000703306, throughput 3.201K wps
Begin Testing...
[Epoch 187] train avg loss 0.000705404, dev acc 0.8496, dev avg loss 0.38267, throughput 3.25114K wps
[Epoch 188 Batch 30/62] avg loss 0.000654966, throughput 3.28763K wps
[Epoch 188 Batch 60/62] avg loss 0.000766153, throughput 3.18914K wps
Begin Testing...
[Epoch 188] train avg loss 0.000726501, dev acc 0.8496, dev avg loss 0.3857, throughput 3.2412K wps
[Epoch 189 Batch 30/62] avg loss 0.000625154, throughput 3.26995K wps
[Epoch 189 Batch 60/62] avg loss 0.000679812, throughput 3.21796K wps
Begin Testing...
[Epoch 189] train avg loss 0.000652239, dev acc 0.8466, dev avg loss 0.383644, throughput 3.2494K wps
[Epoch 190 Batch 30/62] avg loss 0.000725918, throughput 3.26563K wps
[Epoch 190 Batch 60/62] avg loss 0.000640315, throughput 3.2137K wps
Begin Testing...
[Epoch 190] train avg loss 0.0006907, dev acc 0.8496, dev avg loss 0.386067, throughput 3.2455K wps
[Epoch 191 Batch 30/62] avg loss 0.000625111, throughput 3.29117K wps
[Epoch 191 Batch 60/62] avg loss 0.000642097, throughput 3.22346K wps
Begin Testing...
[Epoch 191] train avg loss 0.000640314, dev acc 0.8466, dev avg loss 0.384836, throughput 3.26299K wps
[Epoch 192 Batch 30/62] avg loss 0.000743479, throughput 3.2868K wps
[Epoch 192 Batch 60/62] avg loss 0.000661114, throughput 3.21043K wps
Begin Testing...
[Epoch 192] train avg loss 0.000705383, dev acc 0.8496, dev avg loss 0.38442, throughput 3.25414K wps
[Epoch 193 Batch 30/62] avg loss 0.000697146, throughput 3.26784K wps
[Epoch 193 Batch 60/62] avg loss 0.000663381, throughput 3.22556K wps
Begin Testing...
[Epoch 193] train avg loss 0.000687203, dev acc 0.8466, dev avg loss 0.384533, throughput 3.25246K wps
[Epoch 194 Batch 30/62] avg loss 0.000605136, throughput 3.27493K wps
[Epoch 194 Batch 60/62] avg loss 0.00059896, throughput 3.20793K wps
Begin Testing...
[Epoch 194] train avg loss 0.000603851, dev acc 0.8466, dev avg loss 0.385158, throughput 3.24864K wps
[Epoch 195 Batch 30/62] avg loss 0.000602018, throughput 3.28434K wps
[Epoch 195 Batch 60/62] avg loss 0.000644683, throughput 3.20188K wps
Begin Testing...
[Epoch 195] train avg loss 0.000626835, dev acc 0.8437, dev avg loss 0.385064, throughput 3.25045K wps
[Epoch 196 Batch 30/62] avg loss 0.000634627, throughput 3.28819K wps
[Epoch 196 Batch 60/62] avg loss 0.00069646, throughput 3.21201K wps
Begin Testing...
[Epoch 196] train avg loss 0.000671338, dev acc 0.8496, dev avg loss 0.386983, throughput 3.25713K wps
[Epoch 197 Batch 30/62] avg loss 0.000620879, throughput 3.28758K wps
[Epoch 197 Batch 60/62] avg loss 0.000677202, throughput 3.20876K wps
Begin Testing...
[Epoch 197] train avg loss 0.000646868, dev acc 0.8466, dev avg loss 0.385017, throughput 3.25289K wps
[Epoch 198 Batch 30/62] avg loss 0.000639692, throughput 3.27533K wps
[Epoch 198 Batch 60/62] avg loss 0.00060886, throughput 3.18723K wps
Begin Testing...
[Epoch 198] train avg loss 0.000625828, dev acc 0.8496, dev avg loss 0.38584, throughput 3.23677K wps
[Epoch 199 Batch 30/62] avg loss 0.000620507, throughput 3.2705K wps
[Epoch 199 Batch 60/62] avg loss 0.000651206, throughput 3.21063K wps
Begin Testing...
[Epoch 199] train avg loss 0.000636861, dev acc 0.8466, dev avg loss 0.38597, throughput 3.24676K wps
Test loss 0.359136, test acc 0.8302
Total time cost 418.26s
[Epoch 0 Batch 30/62] avg loss 0.0133194, throughput 3.09651K wps
[Epoch 0 Batch 60/62] avg loss 0.0132243, throughput 3.21286K wps
Begin Testing...
[Epoch 0] train avg loss 0.0133858, dev acc 0.6077, dev avg loss 0.667537, throughput 3.16234K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130396, throughput 3.29921K wps
[Epoch 1 Batch 60/62] avg loss 0.0129912, throughput 3.20574K wps
Begin Testing...
[Epoch 1] train avg loss 0.0131865, dev acc 0.6077, dev avg loss 0.657183, throughput 3.2592K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0128743, throughput 3.30231K wps
[Epoch 2 Batch 60/62] avg loss 0.0127642, throughput 3.18752K wps
Begin Testing...
[Epoch 2] train avg loss 0.0129857, dev acc 0.6077, dev avg loss 0.654114, throughput 3.25069K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0127782, throughput 3.24165K wps
[Epoch 3 Batch 60/62] avg loss 0.0125122, throughput 3.20475K wps
Begin Testing...
[Epoch 3] train avg loss 0.012804, dev acc 0.6077, dev avg loss 0.645783, throughput 3.23112K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.012495, throughput 3.28673K wps
[Epoch 4 Batch 60/62] avg loss 0.012359, throughput 3.19424K wps
Begin Testing...
[Epoch 4] train avg loss 0.0126347, dev acc 0.6077, dev avg loss 0.637065, throughput 3.24572K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0122847, throughput 3.272K wps
[Epoch 5 Batch 60/62] avg loss 0.0122507, throughput 3.20549K wps
Begin Testing...
[Epoch 5] train avg loss 0.0124187, dev acc 0.6077, dev avg loss 0.63275, throughput 3.24565K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0122767, throughput 3.28718K wps
[Epoch 6 Batch 60/62] avg loss 0.0119282, throughput 3.18547K wps
Begin Testing...
[Epoch 6] train avg loss 0.0122175, dev acc 0.6077, dev avg loss 0.62937, throughput 3.24394K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0116946, throughput 3.25303K wps
[Epoch 7 Batch 60/62] avg loss 0.0121172, throughput 3.21745K wps
Begin Testing...
[Epoch 7] train avg loss 0.012062, dev acc 0.6195, dev avg loss 0.617059, throughput 3.2418K wps
Observed Improvement.
Begin Testing...
[Epoch 8 Batch 30/62] avg loss 0.0117611, throughput 3.28897K wps
[Epoch 8 Batch 60/62] avg loss 0.0116303, throughput 3.2082K wps
Begin Testing...
[Epoch 8] train avg loss 0.0118458, dev acc 0.6254, dev avg loss 0.610228, throughput 3.25441K wps
Observed Improvement.
Begin Testing...
[Epoch 9 Batch 30/62] avg loss 0.0114879, throughput 3.28457K wps
[Epoch 9 Batch 60/62] avg loss 0.0114626, throughput 3.19953K wps
Begin Testing...
[Epoch 9] train avg loss 0.0116256, dev acc 0.6283, dev avg loss 0.603276, throughput 3.24898K wps
Observed Improvement.
Begin Testing...
[Epoch 10 Batch 30/62] avg loss 0.0113433, throughput 3.28149K wps
[Epoch 10 Batch 60/62] avg loss 0.0110761, throughput 3.19548K wps
Begin Testing...
[Epoch 10] train avg loss 0.0113361, dev acc 0.6224, dev avg loss 0.598597, throughput 3.24431K wps
[Epoch 11 Batch 30/62] avg loss 0.0109872, throughput 3.28741K wps
[Epoch 11 Batch 60/62] avg loss 0.0110199, throughput 3.20413K wps
Begin Testing...
[Epoch 11] train avg loss 0.0111282, dev acc 0.6401, dev avg loss 0.588713, throughput 3.25084K wps
Observed Improvement.
Begin Testing...
[Epoch 12 Batch 30/62] avg loss 0.0108117, throughput 3.29213K wps
[Epoch 12 Batch 60/62] avg loss 0.0107145, throughput 3.19497K wps
Begin Testing...
[Epoch 12] train avg loss 0.0109102, dev acc 0.6667, dev avg loss 0.578912, throughput 3.25088K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0106723, throughput 3.26673K wps
[Epoch 13 Batch 60/62] avg loss 0.0106927, throughput 3.21878K wps
Begin Testing...
[Epoch 13] train avg loss 0.010841, dev acc 0.7198, dev avg loss 0.570102, throughput 3.24902K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0104143, throughput 3.28016K wps
[Epoch 14 Batch 60/62] avg loss 0.0104262, throughput 3.21487K wps
Begin Testing...
[Epoch 14] train avg loss 0.0105147, dev acc 0.6637, dev avg loss 0.570085, throughput 3.25458K wps
[Epoch 15 Batch 30/62] avg loss 0.0102797, throughput 3.2771K wps
[Epoch 15 Batch 60/62] avg loss 0.0101839, throughput 3.21601K wps
Begin Testing...
[Epoch 15] train avg loss 0.0103146, dev acc 0.6755, dev avg loss 0.557188, throughput 3.2536K wps
[Epoch 16 Batch 30/62] avg loss 0.00997964, throughput 3.27378K wps
[Epoch 16 Batch 60/62] avg loss 0.00996116, throughput 3.19432K wps
Begin Testing...
[Epoch 16] train avg loss 0.0101116, dev acc 0.6873, dev avg loss 0.550807, throughput 3.24042K wps
[Epoch 17 Batch 30/62] avg loss 0.00997167, throughput 3.28482K wps
[Epoch 17 Batch 60/62] avg loss 0.00961641, throughput 3.17665K wps
Begin Testing...
[Epoch 17] train avg loss 0.00992665, dev acc 0.6903, dev avg loss 0.544092, throughput 3.23549K wps
[Epoch 18 Batch 30/62] avg loss 0.0096946, throughput 3.2405K wps
[Epoch 18 Batch 60/62] avg loss 0.0093813, throughput 3.21587K wps
Begin Testing...
[Epoch 18] train avg loss 0.00965741, dev acc 0.7316, dev avg loss 0.534644, throughput 3.23582K wps
Observed Improvement.
Begin Testing...
[Epoch 19 Batch 30/62] avg loss 0.00938919, throughput 3.27915K wps
[Epoch 19 Batch 60/62] avg loss 0.00916936, throughput 3.18638K wps
Begin Testing...
[Epoch 19] train avg loss 0.0093815, dev acc 0.7227, dev avg loss 0.52995, throughput 3.23887K wps
[Epoch 20 Batch 30/62] avg loss 0.00906625, throughput 3.26579K wps
[Epoch 20 Batch 60/62] avg loss 0.0088845, throughput 3.21165K wps
Begin Testing...
[Epoch 20] train avg loss 0.00911705, dev acc 0.7080, dev avg loss 0.526409, throughput 3.24399K wps
[Epoch 21 Batch 30/62] avg loss 0.0088882, throughput 3.29644K wps
[Epoch 21 Batch 60/62] avg loss 0.0089227, throughput 3.21354K wps
Begin Testing...
[Epoch 21] train avg loss 0.0090319, dev acc 0.7109, dev avg loss 0.523253, throughput 3.26067K wps
[Epoch 22 Batch 30/62] avg loss 0.00879924, throughput 3.27501K wps
[Epoch 22 Batch 60/62] avg loss 0.00871447, throughput 3.1959K wps
Begin Testing...
[Epoch 22] train avg loss 0.00887688, dev acc 0.7493, dev avg loss 0.513041, throughput 3.24279K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00871817, throughput 3.26192K wps
[Epoch 23 Batch 60/62] avg loss 0.00839548, throughput 3.20833K wps
Begin Testing...
[Epoch 23] train avg loss 0.00863972, dev acc 0.7552, dev avg loss 0.50819, throughput 3.24095K wps
Observed Improvement.
Begin Testing...
[Epoch 24 Batch 30/62] avg loss 0.00839052, throughput 3.28008K wps
[Epoch 24 Batch 60/62] avg loss 0.00842196, throughput 3.18032K wps
Begin Testing...
[Epoch 24] train avg loss 0.00851821, dev acc 0.7640, dev avg loss 0.502348, throughput 3.23624K wps
Observed Improvement.
Begin Testing...
[Epoch 25 Batch 30/62] avg loss 0.00834442, throughput 3.27594K wps
[Epoch 25 Batch 60/62] avg loss 0.00808259, throughput 3.19845K wps
Begin Testing...
[Epoch 25] train avg loss 0.0083129, dev acc 0.7611, dev avg loss 0.499053, throughput 3.24454K wps
[Epoch 26 Batch 30/62] avg loss 0.00795754, throughput 3.27687K wps
[Epoch 26 Batch 60/62] avg loss 0.00807001, throughput 3.2025K wps
Begin Testing...
[Epoch 26] train avg loss 0.00813977, dev acc 0.7434, dev avg loss 0.502516, throughput 3.24702K wps
[Epoch 27 Batch 30/62] avg loss 0.008101, throughput 3.29112K wps
[Epoch 27 Batch 60/62] avg loss 0.00774589, throughput 3.1999K wps
Begin Testing...
[Epoch 27] train avg loss 0.008099, dev acc 0.7611, dev avg loss 0.492292, throughput 3.25159K wps
[Epoch 28 Batch 30/62] avg loss 0.00789794, throughput 3.30248K wps
[Epoch 28 Batch 60/62] avg loss 0.00760923, throughput 3.19541K wps
Begin Testing...
[Epoch 28] train avg loss 0.00783654, dev acc 0.7463, dev avg loss 0.49221, throughput 3.25598K wps
[Epoch 29 Batch 30/62] avg loss 0.00767543, throughput 3.2996K wps
[Epoch 29 Batch 60/62] avg loss 0.00753967, throughput 3.21123K wps
Begin Testing...
[Epoch 29] train avg loss 0.00764264, dev acc 0.7581, dev avg loss 0.488076, throughput 3.26124K wps
[Epoch 30 Batch 30/62] avg loss 0.00751063, throughput 3.28692K wps
[Epoch 30 Batch 60/62] avg loss 0.00750815, throughput 3.20329K wps
Begin Testing...
[Epoch 30] train avg loss 0.00765803, dev acc 0.7699, dev avg loss 0.483666, throughput 3.25057K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.00706203, throughput 3.27811K wps
[Epoch 31 Batch 60/62] avg loss 0.00741253, throughput 3.19767K wps
Begin Testing...
[Epoch 31] train avg loss 0.00734312, dev acc 0.7817, dev avg loss 0.479485, throughput 3.24267K wps
Observed Improvement.
Begin Testing...
[Epoch 32 Batch 30/62] avg loss 0.00726706, throughput 3.27512K wps
[Epoch 32 Batch 60/62] avg loss 0.00720219, throughput 3.17814K wps
Begin Testing...
[Epoch 32] train avg loss 0.00732295, dev acc 0.7729, dev avg loss 0.478173, throughput 3.2318K wps
[Epoch 33 Batch 30/62] avg loss 0.00752682, throughput 3.26459K wps
[Epoch 33 Batch 60/62] avg loss 0.00670238, throughput 3.20762K wps
Begin Testing...
[Epoch 33] train avg loss 0.00723979, dev acc 0.7522, dev avg loss 0.481818, throughput 3.24207K wps
[Epoch 34 Batch 30/62] avg loss 0.00685401, throughput 3.28195K wps
[Epoch 34 Batch 60/62] avg loss 0.00690254, throughput 3.20126K wps
Begin Testing...
[Epoch 34] train avg loss 0.00693654, dev acc 0.7729, dev avg loss 0.471327, throughput 3.24753K wps
[Epoch 35 Batch 30/62] avg loss 0.00669079, throughput 3.29793K wps
[Epoch 35 Batch 60/62] avg loss 0.00691435, throughput 3.20488K wps
Begin Testing...
[Epoch 35] train avg loss 0.00685218, dev acc 0.7699, dev avg loss 0.471285, throughput 3.25586K wps
[Epoch 36 Batch 30/62] avg loss 0.00678148, throughput 3.28449K wps
[Epoch 36 Batch 60/62] avg loss 0.00661551, throughput 3.1909K wps
Begin Testing...
[Epoch 36] train avg loss 0.00685943, dev acc 0.7758, dev avg loss 0.469068, throughput 3.24375K wps
[Epoch 37 Batch 30/62] avg loss 0.00631808, throughput 3.26665K wps
[Epoch 37 Batch 60/62] avg loss 0.00663341, throughput 3.21082K wps
Begin Testing...
[Epoch 37] train avg loss 0.00660926, dev acc 0.7758, dev avg loss 0.466253, throughput 3.24466K wps
[Epoch 38 Batch 30/62] avg loss 0.00654631, throughput 3.23808K wps
[Epoch 38 Batch 60/62] avg loss 0.00626609, throughput 3.1886K wps
Begin Testing...
[Epoch 38] train avg loss 0.00646429, dev acc 0.7847, dev avg loss 0.462827, throughput 3.22154K wps
Observed Improvement.
Begin Testing...
[Epoch 39 Batch 30/62] avg loss 0.00643294, throughput 3.28926K wps
[Epoch 39 Batch 60/62] avg loss 0.00630142, throughput 3.21061K wps
Begin Testing...
[Epoch 39] train avg loss 0.00643975, dev acc 0.7817, dev avg loss 0.46113, throughput 3.25581K wps
[Epoch 40 Batch 30/62] avg loss 0.00617786, throughput 3.28194K wps
[Epoch 40 Batch 60/62] avg loss 0.00609164, throughput 3.19792K wps
Begin Testing...
[Epoch 40] train avg loss 0.00623895, dev acc 0.7817, dev avg loss 0.459361, throughput 3.24333K wps
[Epoch 41 Batch 30/62] avg loss 0.00603994, throughput 3.27762K wps
[Epoch 41 Batch 60/62] avg loss 0.00598225, throughput 3.22327K wps
Begin Testing...
[Epoch 41] train avg loss 0.00616745, dev acc 0.7699, dev avg loss 0.460251, throughput 3.2562K wps
[Epoch 42 Batch 30/62] avg loss 0.00597547, throughput 3.26668K wps
[Epoch 42 Batch 60/62] avg loss 0.00585781, throughput 3.21447K wps
Begin Testing...
[Epoch 42] train avg loss 0.00606753, dev acc 0.7788, dev avg loss 0.455813, throughput 3.2465K wps
[Epoch 43 Batch 30/62] avg loss 0.00566956, throughput 3.27521K wps
[Epoch 43 Batch 60/62] avg loss 0.00601832, throughput 3.19921K wps
Begin Testing...
[Epoch 43] train avg loss 0.00592897, dev acc 0.7847, dev avg loss 0.455745, throughput 3.24525K wps
Observed Improvement.
Begin Testing...
[Epoch 44 Batch 30/62] avg loss 0.00589822, throughput 3.25158K wps
[Epoch 44 Batch 60/62] avg loss 0.00562691, throughput 3.2075K wps
Begin Testing...
[Epoch 44] train avg loss 0.0058474, dev acc 0.7699, dev avg loss 0.456726, throughput 3.23569K wps
[Epoch 45 Batch 30/62] avg loss 0.00573247, throughput 3.27964K wps
[Epoch 45 Batch 60/62] avg loss 0.00552494, throughput 3.19225K wps
Begin Testing...
[Epoch 45] train avg loss 0.0057267, dev acc 0.7817, dev avg loss 0.451855, throughput 3.24145K wps
[Epoch 46 Batch 30/62] avg loss 0.00551242, throughput 3.28451K wps
[Epoch 46 Batch 60/62] avg loss 0.00541175, throughput 3.19187K wps
Begin Testing...
[Epoch 46] train avg loss 0.00560405, dev acc 0.7817, dev avg loss 0.448526, throughput 3.24414K wps
[Epoch 47 Batch 30/62] avg loss 0.00551037, throughput 3.26465K wps
[Epoch 47 Batch 60/62] avg loss 0.00547403, throughput 3.19683K wps
Begin Testing...
[Epoch 47] train avg loss 0.00553386, dev acc 0.7847, dev avg loss 0.447076, throughput 3.23709K wps
Observed Improvement.
Begin Testing...
[Epoch 48 Batch 30/62] avg loss 0.00534908, throughput 3.28285K wps
[Epoch 48 Batch 60/62] avg loss 0.00534103, throughput 3.2114K wps
Begin Testing...
[Epoch 48] train avg loss 0.00540254, dev acc 0.7729, dev avg loss 0.446603, throughput 3.25319K wps
[Epoch 49 Batch 30/62] avg loss 0.00525469, throughput 3.29761K wps
[Epoch 49 Batch 60/62] avg loss 0.00517441, throughput 3.21621K wps
Begin Testing...
[Epoch 49] train avg loss 0.00525673, dev acc 0.7729, dev avg loss 0.448155, throughput 3.26191K wps
[Epoch 50 Batch 30/62] avg loss 0.00499775, throughput 3.28826K wps
[Epoch 50 Batch 60/62] avg loss 0.00539901, throughput 3.21224K wps
Begin Testing...
[Epoch 50] train avg loss 0.005229, dev acc 0.7817, dev avg loss 0.447571, throughput 3.2565K wps
[Epoch 51 Batch 30/62] avg loss 0.00519015, throughput 3.27913K wps
[Epoch 51 Batch 60/62] avg loss 0.00489643, throughput 3.21662K wps
Begin Testing...
[Epoch 51] train avg loss 0.00512389, dev acc 0.7788, dev avg loss 0.4436, throughput 3.25302K wps
[Epoch 52 Batch 30/62] avg loss 0.00496725, throughput 3.28778K wps
[Epoch 52 Batch 60/62] avg loss 0.00490715, throughput 3.21004K wps
Begin Testing...
[Epoch 52] train avg loss 0.00500343, dev acc 0.7847, dev avg loss 0.445749, throughput 3.25523K wps
Observed Improvement.
Begin Testing...
[Epoch 53 Batch 30/62] avg loss 0.00492418, throughput 3.28121K wps
[Epoch 53 Batch 60/62] avg loss 0.00478953, throughput 3.19102K wps
Begin Testing...
[Epoch 53] train avg loss 0.00489023, dev acc 0.7788, dev avg loss 0.441379, throughput 3.24143K wps
[Epoch 54 Batch 30/62] avg loss 0.00484208, throughput 3.25751K wps
[Epoch 54 Batch 60/62] avg loss 0.00497547, throughput 3.19773K wps
Begin Testing...
[Epoch 54] train avg loss 0.00495055, dev acc 0.7758, dev avg loss 0.439318, throughput 3.23407K wps
[Epoch 55 Batch 30/62] avg loss 0.00487606, throughput 3.26139K wps
[Epoch 55 Batch 60/62] avg loss 0.00452817, throughput 3.18081K wps
Begin Testing...
[Epoch 55] train avg loss 0.00475408, dev acc 0.7699, dev avg loss 0.452021, throughput 3.22642K wps
[Epoch 56 Batch 30/62] avg loss 0.00453311, throughput 3.24326K wps
[Epoch 56 Batch 60/62] avg loss 0.00458486, throughput 3.2145K wps
Begin Testing...
[Epoch 56] train avg loss 0.00461491, dev acc 0.7847, dev avg loss 0.439914, throughput 3.23673K wps
Observed Improvement.
Begin Testing...
[Epoch 57 Batch 30/62] avg loss 0.00435515, throughput 3.29414K wps
[Epoch 57 Batch 60/62] avg loss 0.00439926, throughput 3.22035K wps
Begin Testing...
[Epoch 57] train avg loss 0.00452216, dev acc 0.7817, dev avg loss 0.439753, throughput 3.26327K wps
[Epoch 58 Batch 30/62] avg loss 0.00452566, throughput 3.28204K wps
[Epoch 58 Batch 60/62] avg loss 0.00421179, throughput 3.18746K wps
Begin Testing...
[Epoch 58] train avg loss 0.0043817, dev acc 0.7817, dev avg loss 0.438759, throughput 3.24146K wps
[Epoch 59 Batch 30/62] avg loss 0.00466518, throughput 3.27186K wps
[Epoch 59 Batch 60/62] avg loss 0.0041486, throughput 3.20292K wps
Begin Testing...
[Epoch 59] train avg loss 0.00445373, dev acc 0.7758, dev avg loss 0.433862, throughput 3.24343K wps
[Epoch 60 Batch 30/62] avg loss 0.00401443, throughput 3.31351K wps
[Epoch 60 Batch 60/62] avg loss 0.00427385, throughput 3.20224K wps
Begin Testing...
[Epoch 60] train avg loss 0.00430397, dev acc 0.7847, dev avg loss 0.445079, throughput 3.26252K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00420674, throughput 3.27537K wps
[Epoch 61 Batch 60/62] avg loss 0.00423294, throughput 3.21001K wps
Begin Testing...
[Epoch 61] train avg loss 0.00423725, dev acc 0.7788, dev avg loss 0.43329, throughput 3.249K wps
[Epoch 62 Batch 30/62] avg loss 0.00404384, throughput 3.27181K wps
[Epoch 62 Batch 60/62] avg loss 0.00414188, throughput 3.20336K wps
Begin Testing...
[Epoch 62] train avg loss 0.00416785, dev acc 0.7788, dev avg loss 0.433018, throughput 3.2449K wps
[Epoch 63 Batch 30/62] avg loss 0.00408781, throughput 3.28704K wps
[Epoch 63 Batch 60/62] avg loss 0.00388581, throughput 3.18763K wps
Begin Testing...
[Epoch 63] train avg loss 0.00405616, dev acc 0.7788, dev avg loss 0.440816, throughput 3.24391K wps
[Epoch 64 Batch 30/62] avg loss 0.0040555, throughput 3.29584K wps
[Epoch 64 Batch 60/62] avg loss 0.00367281, throughput 3.20618K wps
Begin Testing...
[Epoch 64] train avg loss 0.00389749, dev acc 0.7788, dev avg loss 0.431396, throughput 3.2577K wps
[Epoch 65 Batch 30/62] avg loss 0.00393207, throughput 3.29005K wps
[Epoch 65 Batch 60/62] avg loss 0.00391718, throughput 3.19837K wps
Begin Testing...
[Epoch 65] train avg loss 0.00398416, dev acc 0.7788, dev avg loss 0.440297, throughput 3.25098K wps
[Epoch 66 Batch 30/62] avg loss 0.00370876, throughput 3.28611K wps
[Epoch 66 Batch 60/62] avg loss 0.00389023, throughput 3.19854K wps
Begin Testing...
[Epoch 66] train avg loss 0.00380307, dev acc 0.7817, dev avg loss 0.434748, throughput 3.24862K wps
[Epoch 67 Batch 30/62] avg loss 0.00370527, throughput 3.28631K wps
[Epoch 67 Batch 60/62] avg loss 0.00374019, throughput 3.18631K wps
Begin Testing...
[Epoch 67] train avg loss 0.00377324, dev acc 0.7788, dev avg loss 0.430617, throughput 3.2414K wps
[Epoch 68 Batch 30/62] avg loss 0.00352027, throughput 3.2705K wps
[Epoch 68 Batch 60/62] avg loss 0.00363559, throughput 3.21426K wps
Begin Testing...
[Epoch 68] train avg loss 0.00369393, dev acc 0.7758, dev avg loss 0.437666, throughput 3.24831K wps
[Epoch 69 Batch 30/62] avg loss 0.0035457, throughput 3.27588K wps
[Epoch 69 Batch 60/62] avg loss 0.00351993, throughput 3.20688K wps
Begin Testing...
[Epoch 69] train avg loss 0.00358974, dev acc 0.7788, dev avg loss 0.432116, throughput 3.24787K wps
[Epoch 70 Batch 30/62] avg loss 0.00354601, throughput 3.27953K wps
[Epoch 70 Batch 60/62] avg loss 0.00336171, throughput 3.18738K wps
Begin Testing...
[Epoch 70] train avg loss 0.00346886, dev acc 0.7817, dev avg loss 0.428482, throughput 3.2394K wps
[Epoch 71 Batch 30/62] avg loss 0.00333546, throughput 3.28345K wps
[Epoch 71 Batch 60/62] avg loss 0.00341807, throughput 3.20418K wps
Begin Testing...
[Epoch 71] train avg loss 0.00344935, dev acc 0.7817, dev avg loss 0.430377, throughput 3.24922K wps
[Epoch 72 Batch 30/62] avg loss 0.00341808, throughput 3.26472K wps
[Epoch 72 Batch 60/62] avg loss 0.00340279, throughput 3.2256K wps
Begin Testing...
[Epoch 72] train avg loss 0.00342914, dev acc 0.7788, dev avg loss 0.430946, throughput 3.25193K wps
[Epoch 73 Batch 30/62] avg loss 0.00342962, throughput 3.27956K wps
[Epoch 73 Batch 60/62] avg loss 0.00325516, throughput 3.22558K wps
Begin Testing...
[Epoch 73] train avg loss 0.00337555, dev acc 0.7788, dev avg loss 0.436347, throughput 3.25894K wps
[Epoch 74 Batch 30/62] avg loss 0.00324526, throughput 3.3091K wps
[Epoch 74 Batch 60/62] avg loss 0.00310212, throughput 3.19516K wps
Begin Testing...
[Epoch 74] train avg loss 0.00325205, dev acc 0.7758, dev avg loss 0.425694, throughput 3.25655K wps
[Epoch 75 Batch 30/62] avg loss 0.00319681, throughput 3.25932K wps
[Epoch 75 Batch 60/62] avg loss 0.00317256, throughput 3.21255K wps
Begin Testing...
[Epoch 75] train avg loss 0.00319491, dev acc 0.7817, dev avg loss 0.436172, throughput 3.24195K wps
[Epoch 76 Batch 30/62] avg loss 0.00300659, throughput 3.2639K wps
[Epoch 76 Batch 60/62] avg loss 0.00322301, throughput 3.19582K wps
Begin Testing...
[Epoch 76] train avg loss 0.00314218, dev acc 0.7817, dev avg loss 0.427409, throughput 3.23731K wps
[Epoch 77 Batch 30/62] avg loss 0.00306184, throughput 3.26834K wps
[Epoch 77 Batch 60/62] avg loss 0.00304086, throughput 3.18477K wps
Begin Testing...
[Epoch 77] train avg loss 0.00310017, dev acc 0.7817, dev avg loss 0.426904, throughput 3.23296K wps
[Epoch 78 Batch 30/62] avg loss 0.00307619, throughput 3.25313K wps
[Epoch 78 Batch 60/62] avg loss 0.0030705, throughput 3.20782K wps
Begin Testing...
[Epoch 78] train avg loss 0.0030968, dev acc 0.7817, dev avg loss 0.427505, throughput 3.23717K wps
[Epoch 79 Batch 30/62] avg loss 0.00316133, throughput 3.28495K wps
[Epoch 79 Batch 60/62] avg loss 0.00297896, throughput 3.20378K wps
Begin Testing...
[Epoch 79] train avg loss 0.00309041, dev acc 0.7817, dev avg loss 0.424889, throughput 3.25125K wps
[Epoch 80 Batch 30/62] avg loss 0.00293202, throughput 3.27702K wps
[Epoch 80 Batch 60/62] avg loss 0.0029264, throughput 3.19681K wps
Begin Testing...
[Epoch 80] train avg loss 0.00298665, dev acc 0.7817, dev avg loss 0.431376, throughput 3.24458K wps
[Epoch 81 Batch 30/62] avg loss 0.00308039, throughput 3.30632K wps
[Epoch 81 Batch 60/62] avg loss 0.00287769, throughput 3.22592K wps
Begin Testing...
[Epoch 81] train avg loss 0.00297856, dev acc 0.7817, dev avg loss 0.429051, throughput 3.27152K wps
[Epoch 82 Batch 30/62] avg loss 0.00288558, throughput 3.27825K wps
[Epoch 82 Batch 60/62] avg loss 0.0026751, throughput 3.21457K wps
Begin Testing...
[Epoch 82] train avg loss 0.00281298, dev acc 0.7847, dev avg loss 0.430902, throughput 3.25304K wps
Observed Improvement.
Begin Testing...
[Epoch 83 Batch 30/62] avg loss 0.00281443, throughput 3.28621K wps
[Epoch 83 Batch 60/62] avg loss 0.0025506, throughput 3.18672K wps
Begin Testing...
[Epoch 83] train avg loss 0.00273322, dev acc 0.7847, dev avg loss 0.429454, throughput 3.24304K wps
Observed Improvement.
Begin Testing...
[Epoch 84 Batch 30/62] avg loss 0.00278545, throughput 3.25669K wps
[Epoch 84 Batch 60/62] avg loss 0.00266953, throughput 3.19589K wps
Begin Testing...
[Epoch 84] train avg loss 0.00276908, dev acc 0.7817, dev avg loss 0.422378, throughput 3.23153K wps
[Epoch 85 Batch 30/62] avg loss 0.00257074, throughput 3.28137K wps
[Epoch 85 Batch 60/62] avg loss 0.00292101, throughput 3.19396K wps
Begin Testing...
[Epoch 85] train avg loss 0.00280844, dev acc 0.7847, dev avg loss 0.421432, throughput 3.24477K wps
Observed Improvement.
Begin Testing...
[Epoch 86 Batch 30/62] avg loss 0.00246626, throughput 3.28417K wps
[Epoch 86 Batch 60/62] avg loss 0.00286901, throughput 3.20407K wps
Begin Testing...
[Epoch 86] train avg loss 0.00272291, dev acc 0.7817, dev avg loss 0.42463, throughput 3.25004K wps
[Epoch 87 Batch 30/62] avg loss 0.00257678, throughput 3.28608K wps
[Epoch 87 Batch 60/62] avg loss 0.00262336, throughput 3.20387K wps
Begin Testing...
[Epoch 87] train avg loss 0.00261332, dev acc 0.7876, dev avg loss 0.426212, throughput 3.25107K wps
Observed Improvement.
Begin Testing...
[Epoch 88 Batch 30/62] avg loss 0.00237053, throughput 3.2878K wps
[Epoch 88 Batch 60/62] avg loss 0.00260641, throughput 3.20854K wps
Begin Testing...
[Epoch 88] train avg loss 0.00249905, dev acc 0.7876, dev avg loss 0.422447, throughput 3.25335K wps
Observed Improvement.
Begin Testing...
[Epoch 89 Batch 30/62] avg loss 0.00249884, throughput 3.27897K wps
[Epoch 89 Batch 60/62] avg loss 0.00239835, throughput 3.20157K wps
Begin Testing...
[Epoch 89] train avg loss 0.00252896, dev acc 0.7847, dev avg loss 0.439087, throughput 3.24816K wps
[Epoch 90 Batch 30/62] avg loss 0.00250677, throughput 3.3001K wps
[Epoch 90 Batch 60/62] avg loss 0.00238169, throughput 3.18657K wps
Begin Testing...
[Epoch 90] train avg loss 0.00247591, dev acc 0.7876, dev avg loss 0.422757, throughput 3.25024K wps
Observed Improvement.
Begin Testing...
[Epoch 91 Batch 30/62] avg loss 0.00233544, throughput 3.28922K wps
[Epoch 91 Batch 60/62] avg loss 0.00238496, throughput 3.20353K wps
Begin Testing...
[Epoch 91] train avg loss 0.00239742, dev acc 0.7788, dev avg loss 0.430696, throughput 3.2518K wps
[Epoch 92 Batch 30/62] avg loss 0.00243613, throughput 3.26927K wps
[Epoch 92 Batch 60/62] avg loss 0.00243391, throughput 3.21858K wps
Begin Testing...
[Epoch 92] train avg loss 0.00243771, dev acc 0.7876, dev avg loss 0.425309, throughput 3.24941K wps
Observed Improvement.
Begin Testing...
[Epoch 93 Batch 30/62] avg loss 0.00229014, throughput 3.29101K wps
[Epoch 93 Batch 60/62] avg loss 0.00231172, throughput 3.19871K wps
Begin Testing...
[Epoch 93] train avg loss 0.00233362, dev acc 0.7876, dev avg loss 0.423183, throughput 3.25154K wps
Observed Improvement.
Begin Testing...
[Epoch 94 Batch 30/62] avg loss 0.00214796, throughput 3.26692K wps
[Epoch 94 Batch 60/62] avg loss 0.00248253, throughput 3.20281K wps
Begin Testing...
[Epoch 94] train avg loss 0.00232918, dev acc 0.7817, dev avg loss 0.425112, throughput 3.24073K wps
[Epoch 95 Batch 30/62] avg loss 0.00214649, throughput 3.26228K wps
[Epoch 95 Batch 60/62] avg loss 0.00222015, throughput 3.20914K wps
Begin Testing...
[Epoch 95] train avg loss 0.00224599, dev acc 0.7906, dev avg loss 0.421678, throughput 3.24136K wps
Observed Improvement.
Begin Testing...
[Epoch 96 Batch 30/62] avg loss 0.00212278, throughput 3.29211K wps
[Epoch 96 Batch 60/62] avg loss 0.00220698, throughput 3.17587K wps
Begin Testing...
[Epoch 96] train avg loss 0.00217751, dev acc 0.7906, dev avg loss 0.426554, throughput 3.23617K wps
Observed Improvement.
Begin Testing...
[Epoch 97 Batch 30/62] avg loss 0.00209706, throughput 3.28081K wps
[Epoch 97 Batch 60/62] avg loss 0.0023012, throughput 3.20704K wps
Begin Testing...
[Epoch 97] train avg loss 0.00225025, dev acc 0.7847, dev avg loss 0.430401, throughput 3.25058K wps
[Epoch 98 Batch 30/62] avg loss 0.00220755, throughput 3.28162K wps
[Epoch 98 Batch 60/62] avg loss 0.00210444, throughput 3.21096K wps
Begin Testing...
[Epoch 98] train avg loss 0.00216858, dev acc 0.7876, dev avg loss 0.428493, throughput 3.25333K wps
[Epoch 99 Batch 30/62] avg loss 0.00196072, throughput 3.29518K wps
[Epoch 99 Batch 60/62] avg loss 0.00219997, throughput 3.20875K wps
Begin Testing...
[Epoch 99] train avg loss 0.002203, dev acc 0.7876, dev avg loss 0.423609, throughput 3.25735K wps
[Epoch 100 Batch 30/62] avg loss 0.00218617, throughput 3.28567K wps
[Epoch 100 Batch 60/62] avg loss 0.00199987, throughput 3.20017K wps
Begin Testing...
[Epoch 100] train avg loss 0.00211157, dev acc 0.7847, dev avg loss 0.423078, throughput 3.24849K wps
[Epoch 101 Batch 30/62] avg loss 0.00192377, throughput 3.30007K wps
[Epoch 101 Batch 60/62] avg loss 0.00194253, throughput 3.21937K wps
Begin Testing...
[Epoch 101] train avg loss 0.00195181, dev acc 0.7847, dev avg loss 0.427307, throughput 3.26482K wps
[Epoch 102 Batch 30/62] avg loss 0.00186716, throughput 3.27653K wps
[Epoch 102 Batch 60/62] avg loss 0.00213472, throughput 3.21414K wps
Begin Testing...
[Epoch 102] train avg loss 0.00203915, dev acc 0.7847, dev avg loss 0.423582, throughput 3.25068K wps
[Epoch 103 Batch 30/62] avg loss 0.00207231, throughput 3.28387K wps
[Epoch 103 Batch 60/62] avg loss 0.00192478, throughput 3.18879K wps
Begin Testing...
[Epoch 103] train avg loss 0.00204701, dev acc 0.7847, dev avg loss 0.435772, throughput 3.24345K wps
[Epoch 104 Batch 30/62] avg loss 0.0019093, throughput 3.29124K wps
[Epoch 104 Batch 60/62] avg loss 0.00189783, throughput 3.19011K wps
Begin Testing...
[Epoch 104] train avg loss 0.00193465, dev acc 0.7876, dev avg loss 0.429444, throughput 3.24659K wps
[Epoch 105 Batch 30/62] avg loss 0.0019229, throughput 3.28369K wps
[Epoch 105 Batch 60/62] avg loss 0.00195008, throughput 3.20376K wps
Begin Testing...
[Epoch 105] train avg loss 0.00194497, dev acc 0.7876, dev avg loss 0.425183, throughput 3.25013K wps
[Epoch 106 Batch 30/62] avg loss 0.00182792, throughput 3.27935K wps
[Epoch 106 Batch 60/62] avg loss 0.00175337, throughput 3.21214K wps
Begin Testing...
[Epoch 106] train avg loss 0.00181181, dev acc 0.7906, dev avg loss 0.428686, throughput 3.25161K wps
Observed Improvement.
Begin Testing...
[Epoch 107 Batch 30/62] avg loss 0.00189079, throughput 3.28138K wps
[Epoch 107 Batch 60/62] avg loss 0.00167544, throughput 3.22391K wps
Begin Testing...
[Epoch 107] train avg loss 0.0018407, dev acc 0.7817, dev avg loss 0.428071, throughput 3.25858K wps
[Epoch 108 Batch 30/62] avg loss 0.00177433, throughput 3.27778K wps
[Epoch 108 Batch 60/62] avg loss 0.00189214, throughput 3.21577K wps
Begin Testing...
[Epoch 108] train avg loss 0.00185624, dev acc 0.7847, dev avg loss 0.428317, throughput 3.25253K wps
[Epoch 109 Batch 30/62] avg loss 0.00175573, throughput 3.27559K wps
[Epoch 109 Batch 60/62] avg loss 0.00173048, throughput 3.20733K wps
Begin Testing...
[Epoch 109] train avg loss 0.00179035, dev acc 0.7847, dev avg loss 0.442339, throughput 3.24701K wps
[Epoch 110 Batch 30/62] avg loss 0.00176077, throughput 3.2704K wps
[Epoch 110 Batch 60/62] avg loss 0.0016808, throughput 3.19599K wps
Begin Testing...
[Epoch 110] train avg loss 0.00173063, dev acc 0.7847, dev avg loss 0.436496, throughput 3.23897K wps
[Epoch 111 Batch 30/62] avg loss 0.00177331, throughput 3.29817K wps
[Epoch 111 Batch 60/62] avg loss 0.00177097, throughput 3.19948K wps
Begin Testing...
[Epoch 111] train avg loss 0.0017943, dev acc 0.7876, dev avg loss 0.426815, throughput 3.25563K wps
[Epoch 112 Batch 30/62] avg loss 0.0016983, throughput 3.28229K wps
[Epoch 112 Batch 60/62] avg loss 0.00176357, throughput 3.1911K wps
Begin Testing...
[Epoch 112] train avg loss 0.00176532, dev acc 0.7847, dev avg loss 0.426835, throughput 3.23983K wps
[Epoch 113 Batch 30/62] avg loss 0.00166293, throughput 3.27049K wps
[Epoch 113 Batch 60/62] avg loss 0.00165746, throughput 3.21008K wps
Begin Testing...
[Epoch 113] train avg loss 0.00167321, dev acc 0.7935, dev avg loss 0.43704, throughput 3.24578K wps
Observed Improvement.
Begin Testing...
[Epoch 114 Batch 30/62] avg loss 0.00164583, throughput 3.28161K wps
[Epoch 114 Batch 60/62] avg loss 0.00172788, throughput 3.19734K wps
Begin Testing...
[Epoch 114] train avg loss 0.00174589, dev acc 0.7906, dev avg loss 0.426556, throughput 3.24566K wps
[Epoch 115 Batch 30/62] avg loss 0.00157784, throughput 3.29349K wps
[Epoch 115 Batch 60/62] avg loss 0.00163118, throughput 3.20133K wps
Begin Testing...
[Epoch 115] train avg loss 0.00161132, dev acc 0.7906, dev avg loss 0.428518, throughput 3.25435K wps
[Epoch 116 Batch 30/62] avg loss 0.00161408, throughput 3.29237K wps
[Epoch 116 Batch 60/62] avg loss 0.00166034, throughput 3.20707K wps
Begin Testing...
[Epoch 116] train avg loss 0.00166944, dev acc 0.7876, dev avg loss 0.440339, throughput 3.25682K wps
[Epoch 117 Batch 30/62] avg loss 0.00157745, throughput 3.28946K wps
[Epoch 117 Batch 60/62] avg loss 0.00155072, throughput 3.19368K wps
Begin Testing...
[Epoch 117] train avg loss 0.00159054, dev acc 0.7906, dev avg loss 0.429913, throughput 3.24952K wps
[Epoch 118 Batch 30/62] avg loss 0.00163912, throughput 3.29489K wps
[Epoch 118 Batch 60/62] avg loss 0.00148762, throughput 3.21243K wps
Begin Testing...
[Epoch 118] train avg loss 0.00158995, dev acc 0.7876, dev avg loss 0.433822, throughput 3.26049K wps
[Epoch 119 Batch 30/62] avg loss 0.00156166, throughput 3.28541K wps
[Epoch 119 Batch 60/62] avg loss 0.00136102, throughput 3.20464K wps
Begin Testing...
[Epoch 119] train avg loss 0.00149917, dev acc 0.7906, dev avg loss 0.433577, throughput 3.25158K wps
[Epoch 120 Batch 30/62] avg loss 0.0015432, throughput 3.28473K wps
[Epoch 120 Batch 60/62] avg loss 0.00151581, throughput 3.19955K wps
Begin Testing...
[Epoch 120] train avg loss 0.00155717, dev acc 0.7817, dev avg loss 0.44248, throughput 3.24909K wps
[Epoch 121 Batch 30/62] avg loss 0.00150696, throughput 3.28528K wps
[Epoch 121 Batch 60/62] avg loss 0.00147627, throughput 3.19072K wps
Begin Testing...
[Epoch 121] train avg loss 0.00149826, dev acc 0.7847, dev avg loss 0.439521, throughput 3.24439K wps
[Epoch 122 Batch 30/62] avg loss 0.00149274, throughput 3.30179K wps
[Epoch 122 Batch 60/62] avg loss 0.00139652, throughput 3.193K wps
Begin Testing...
[Epoch 122] train avg loss 0.00146998, dev acc 0.7906, dev avg loss 0.436651, throughput 3.25354K wps
[Epoch 123 Batch 30/62] avg loss 0.00148707, throughput 3.27554K wps
[Epoch 123 Batch 60/62] avg loss 0.00145333, throughput 3.19642K wps
Begin Testing...
[Epoch 123] train avg loss 0.0014774, dev acc 0.7935, dev avg loss 0.434728, throughput 3.24141K wps
Observed Improvement.
Begin Testing...
[Epoch 124 Batch 30/62] avg loss 0.00136519, throughput 3.27153K wps
[Epoch 124 Batch 60/62] avg loss 0.00137654, throughput 3.19583K wps
Begin Testing...
[Epoch 124] train avg loss 0.00140265, dev acc 0.7876, dev avg loss 0.431708, throughput 3.23965K wps
[Epoch 125 Batch 30/62] avg loss 0.00141168, throughput 3.30274K wps
[Epoch 125 Batch 60/62] avg loss 0.00147748, throughput 3.2156K wps
Begin Testing...
[Epoch 125] train avg loss 0.00149749, dev acc 0.7906, dev avg loss 0.437247, throughput 3.26517K wps
[Epoch 126 Batch 30/62] avg loss 0.00140516, throughput 3.29633K wps
[Epoch 126 Batch 60/62] avg loss 0.00142302, throughput 3.20471K wps
Begin Testing...
[Epoch 126] train avg loss 0.00142274, dev acc 0.7906, dev avg loss 0.432586, throughput 3.25588K wps
[Epoch 127 Batch 30/62] avg loss 0.00137749, throughput 3.2814K wps
[Epoch 127 Batch 60/62] avg loss 0.00131165, throughput 3.19759K wps
Begin Testing...
[Epoch 127] train avg loss 0.00139296, dev acc 0.7876, dev avg loss 0.435404, throughput 3.24621K wps
[Epoch 128 Batch 30/62] avg loss 0.00137811, throughput 3.30257K wps
[Epoch 128 Batch 60/62] avg loss 0.0013228, throughput 3.18475K wps
Begin Testing...
[Epoch 128] train avg loss 0.00137479, dev acc 0.7876, dev avg loss 0.43372, throughput 3.25053K wps
[Epoch 129 Batch 30/62] avg loss 0.00132756, throughput 3.30685K wps
[Epoch 129 Batch 60/62] avg loss 0.00132388, throughput 3.19953K wps
Begin Testing...
[Epoch 129] train avg loss 0.0013545, dev acc 0.7847, dev avg loss 0.434336, throughput 3.25876K wps
[Epoch 130 Batch 30/62] avg loss 0.00136456, throughput 3.29133K wps
[Epoch 130 Batch 60/62] avg loss 0.00133117, throughput 3.18824K wps
Begin Testing...
[Epoch 130] train avg loss 0.00136141, dev acc 0.7876, dev avg loss 0.435944, throughput 3.24652K wps
[Epoch 131 Batch 30/62] avg loss 0.00137786, throughput 3.29396K wps
[Epoch 131 Batch 60/62] avg loss 0.00119547, throughput 3.19515K wps
Begin Testing...
[Epoch 131] train avg loss 0.00129863, dev acc 0.7906, dev avg loss 0.436973, throughput 3.25014K wps
[Epoch 132 Batch 30/62] avg loss 0.00131113, throughput 3.27225K wps
[Epoch 132 Batch 60/62] avg loss 0.00122943, throughput 3.20814K wps
Begin Testing...
[Epoch 132] train avg loss 0.00127919, dev acc 0.7906, dev avg loss 0.438264, throughput 3.24617K wps
[Epoch 133 Batch 30/62] avg loss 0.00128921, throughput 3.26951K wps
[Epoch 133 Batch 60/62] avg loss 0.00121225, throughput 3.21132K wps
Begin Testing...
[Epoch 133] train avg loss 0.00126271, dev acc 0.7876, dev avg loss 0.437977, throughput 3.24662K wps
[Epoch 134 Batch 30/62] avg loss 0.00130385, throughput 3.26344K wps
[Epoch 134 Batch 60/62] avg loss 0.00120704, throughput 3.20858K wps
Begin Testing...
[Epoch 134] train avg loss 0.00126475, dev acc 0.7906, dev avg loss 0.442867, throughput 3.24208K wps
[Epoch 135 Batch 30/62] avg loss 0.00110431, throughput 3.2857K wps
[Epoch 135 Batch 60/62] avg loss 0.00124849, throughput 3.18005K wps
Begin Testing...
[Epoch 135] train avg loss 0.00119873, dev acc 0.7935, dev avg loss 0.442229, throughput 3.23909K wps
Observed Improvement.
Begin Testing...
[Epoch 136 Batch 30/62] avg loss 0.00129926, throughput 3.26952K wps
[Epoch 136 Batch 60/62] avg loss 0.00117088, throughput 3.20878K wps
Begin Testing...
[Epoch 136] train avg loss 0.00124473, dev acc 0.7935, dev avg loss 0.441042, throughput 3.24611K wps
Observed Improvement.
Begin Testing...
[Epoch 137 Batch 30/62] avg loss 0.00115269, throughput 3.30834K wps
[Epoch 137 Batch 60/62] avg loss 0.00115209, throughput 3.20929K wps
Begin Testing...
[Epoch 137] train avg loss 0.00118703, dev acc 0.7876, dev avg loss 0.439542, throughput 3.26533K wps
[Epoch 138 Batch 30/62] avg loss 0.00119598, throughput 3.28682K wps
[Epoch 138 Batch 60/62] avg loss 0.00120038, throughput 3.20561K wps
Begin Testing...
[Epoch 138] train avg loss 0.00120237, dev acc 0.7876, dev avg loss 0.439436, throughput 3.25309K wps
[Epoch 139 Batch 30/62] avg loss 0.0010088, throughput 3.2971K wps
[Epoch 139 Batch 60/62] avg loss 0.00117892, throughput 3.21695K wps
Begin Testing...
[Epoch 139] train avg loss 0.0011136, dev acc 0.7935, dev avg loss 0.444214, throughput 3.26242K wps
Observed Improvement.
Begin Testing...
[Epoch 140 Batch 30/62] avg loss 0.00106029, throughput 3.28926K wps
[Epoch 140 Batch 60/62] avg loss 0.00121233, throughput 3.20177K wps
Begin Testing...
[Epoch 140] train avg loss 0.00115741, dev acc 0.7906, dev avg loss 0.444223, throughput 3.2523K wps
[Epoch 141 Batch 30/62] avg loss 0.00114682, throughput 3.28364K wps
[Epoch 141 Batch 60/62] avg loss 0.00106764, throughput 3.19336K wps
Begin Testing...
[Epoch 141] train avg loss 0.00111945, dev acc 0.7906, dev avg loss 0.441361, throughput 3.24397K wps
[Epoch 142 Batch 30/62] avg loss 0.00112862, throughput 3.17467K wps
[Epoch 142 Batch 60/62] avg loss 0.0011773, throughput 3.20696K wps
Begin Testing...
[Epoch 142] train avg loss 0.00118051, dev acc 0.7876, dev avg loss 0.443128, throughput 3.1984K wps
[Epoch 143 Batch 30/62] avg loss 0.00108009, throughput 3.26707K wps
[Epoch 143 Batch 60/62] avg loss 0.00117104, throughput 3.21372K wps
Begin Testing...
[Epoch 143] train avg loss 0.00112184, dev acc 0.7876, dev avg loss 0.446103, throughput 3.24615K wps
[Epoch 144 Batch 30/62] avg loss 0.00115938, throughput 3.27851K wps
[Epoch 144 Batch 60/62] avg loss 0.00107154, throughput 3.20393K wps
Begin Testing...
[Epoch 144] train avg loss 0.0011139, dev acc 0.7876, dev avg loss 0.45123, throughput 3.24737K wps
[Epoch 145 Batch 30/62] avg loss 0.00109093, throughput 3.27727K wps
[Epoch 145 Batch 60/62] avg loss 0.001045, throughput 3.19644K wps
Begin Testing...
[Epoch 145] train avg loss 0.00108567, dev acc 0.7906, dev avg loss 0.449678, throughput 3.24425K wps
[Epoch 146 Batch 30/62] avg loss 0.00110531, throughput 3.27077K wps
[Epoch 146 Batch 60/62] avg loss 0.0010387, throughput 3.18753K wps
Begin Testing...
[Epoch 146] train avg loss 0.00108312, dev acc 0.7876, dev avg loss 0.447593, throughput 3.23562K wps
[Epoch 147 Batch 30/62] avg loss 0.000982169, throughput 3.28654K wps
[Epoch 147 Batch 60/62] avg loss 0.00108036, throughput 3.20445K wps
Begin Testing...
[Epoch 147] train avg loss 0.00106578, dev acc 0.7906, dev avg loss 0.45532, throughput 3.25096K wps
[Epoch 148 Batch 30/62] avg loss 0.00102137, throughput 3.26841K wps
[Epoch 148 Batch 60/62] avg loss 0.00109757, throughput 3.19875K wps
Begin Testing...
[Epoch 148] train avg loss 0.00105946, dev acc 0.7906, dev avg loss 0.445635, throughput 3.2399K wps
[Epoch 149 Batch 30/62] avg loss 0.00101215, throughput 3.28219K wps
[Epoch 149 Batch 60/62] avg loss 0.000990739, throughput 3.21143K wps
Begin Testing...
[Epoch 149] train avg loss 0.00102746, dev acc 0.7906, dev avg loss 0.447993, throughput 3.25256K wps
[Epoch 150 Batch 30/62] avg loss 0.000917273, throughput 3.28371K wps
[Epoch 150 Batch 60/62] avg loss 0.00101195, throughput 3.20856K wps
Begin Testing...
[Epoch 150] train avg loss 0.000979693, dev acc 0.7876, dev avg loss 0.449406, throughput 3.25139K wps
[Epoch 151 Batch 30/62] avg loss 0.000992658, throughput 3.28086K wps
[Epoch 151 Batch 60/62] avg loss 0.00104594, throughput 3.19142K wps
Begin Testing...
[Epoch 151] train avg loss 0.00102695, dev acc 0.7906, dev avg loss 0.451834, throughput 3.24237K wps
[Epoch 152 Batch 30/62] avg loss 0.00104549, throughput 3.29875K wps
[Epoch 152 Batch 60/62] avg loss 0.000967364, throughput 3.18718K wps
Begin Testing...
[Epoch 152] train avg loss 0.00101964, dev acc 0.7906, dev avg loss 0.452851, throughput 3.2476K wps
[Epoch 153 Batch 30/62] avg loss 0.000884714, throughput 3.25898K wps
[Epoch 153 Batch 60/62] avg loss 0.000963246, throughput 3.21404K wps
Begin Testing...
[Epoch 153] train avg loss 0.000924402, dev acc 0.7876, dev avg loss 0.44965, throughput 3.24197K wps
[Epoch 154 Batch 30/62] avg loss 0.00090695, throughput 3.26209K wps
[Epoch 154 Batch 60/62] avg loss 0.00103113, throughput 3.19591K wps
Begin Testing...
[Epoch 154] train avg loss 0.000976923, dev acc 0.7876, dev avg loss 0.450887, throughput 3.23779K wps
[Epoch 155 Batch 30/62] avg loss 0.000941109, throughput 3.28139K wps
[Epoch 155 Batch 60/62] avg loss 0.000962403, throughput 3.19309K wps
Begin Testing...
[Epoch 155] train avg loss 0.000977226, dev acc 0.7906, dev avg loss 0.452562, throughput 3.24436K wps
[Epoch 156 Batch 30/62] avg loss 0.000949457, throughput 3.2787K wps
[Epoch 156 Batch 60/62] avg loss 0.00097231, throughput 3.20233K wps
Begin Testing...
[Epoch 156] train avg loss 0.000975613, dev acc 0.7906, dev avg loss 0.448743, throughput 3.24743K wps
[Epoch 157 Batch 30/62] avg loss 0.000913447, throughput 3.28957K wps
[Epoch 157 Batch 60/62] avg loss 0.000902743, throughput 3.20918K wps
Begin Testing...
[Epoch 157] train avg loss 0.000924217, dev acc 0.7906, dev avg loss 0.450235, throughput 3.255K wps
[Epoch 158 Batch 30/62] avg loss 0.000916683, throughput 3.2855K wps
[Epoch 158 Batch 60/62] avg loss 0.000913719, throughput 3.20177K wps
Begin Testing...
[Epoch 158] train avg loss 0.000920178, dev acc 0.7935, dev avg loss 0.456291, throughput 3.24867K wps
Observed Improvement.
Begin Testing...
[Epoch 159 Batch 30/62] avg loss 0.000923415, throughput 3.26258K wps
[Epoch 159 Batch 60/62] avg loss 0.000932662, throughput 3.21348K wps
Begin Testing...
[Epoch 159] train avg loss 0.000929033, dev acc 0.7935, dev avg loss 0.457224, throughput 3.24568K wps
Observed Improvement.
Begin Testing...
[Epoch 160 Batch 30/62] avg loss 0.000870738, throughput 3.27987K wps
[Epoch 160 Batch 60/62] avg loss 0.000928466, throughput 3.19187K wps
Begin Testing...
[Epoch 160] train avg loss 0.00093916, dev acc 0.7906, dev avg loss 0.449059, throughput 3.2411K wps
[Epoch 161 Batch 30/62] avg loss 0.000929422, throughput 3.24784K wps
[Epoch 161 Batch 60/62] avg loss 0.000912962, throughput 3.16616K wps
Begin Testing...
[Epoch 161] train avg loss 0.000924937, dev acc 0.7906, dev avg loss 0.452788, throughput 3.21397K wps
[Epoch 162 Batch 30/62] avg loss 0.000901857, throughput 3.27491K wps
[Epoch 162 Batch 60/62] avg loss 0.000823912, throughput 3.21162K wps
Begin Testing...
[Epoch 162] train avg loss 0.000870887, dev acc 0.7906, dev avg loss 0.452815, throughput 3.24914K wps
[Epoch 163 Batch 30/62] avg loss 0.000833108, throughput 3.2749K wps
[Epoch 163 Batch 60/62] avg loss 0.000893228, throughput 3.20585K wps
Begin Testing...
[Epoch 163] train avg loss 0.000863277, dev acc 0.7935, dev avg loss 0.460098, throughput 3.24543K wps
Observed Improvement.
Begin Testing...
[Epoch 164 Batch 30/62] avg loss 0.000807818, throughput 3.30847K wps
[Epoch 164 Batch 60/62] avg loss 0.000862164, throughput 3.22141K wps
Begin Testing...
[Epoch 164] train avg loss 0.000850381, dev acc 0.7906, dev avg loss 0.465363, throughput 3.26865K wps
[Epoch 165 Batch 30/62] avg loss 0.000789744, throughput 3.30189K wps
[Epoch 165 Batch 60/62] avg loss 0.000824241, throughput 3.224K wps
Begin Testing...
[Epoch 165] train avg loss 0.000833424, dev acc 0.7906, dev avg loss 0.451675, throughput 3.26802K wps
[Epoch 166 Batch 30/62] avg loss 0.00092859, throughput 3.2746K wps
[Epoch 166 Batch 60/62] avg loss 0.000829232, throughput 3.21127K wps
Begin Testing...
[Epoch 166] train avg loss 0.000886407, dev acc 0.7935, dev avg loss 0.456142, throughput 3.24887K wps
Observed Improvement.
Begin Testing...
[Epoch 167 Batch 30/62] avg loss 0.000815206, throughput 3.28183K wps
[Epoch 167 Batch 60/62] avg loss 0.000803655, throughput 3.18997K wps
Begin Testing...
[Epoch 167] train avg loss 0.000809754, dev acc 0.7906, dev avg loss 0.458613, throughput 3.24274K wps
[Epoch 168 Batch 30/62] avg loss 0.00084164, throughput 3.27687K wps
[Epoch 168 Batch 60/62] avg loss 0.000827971, throughput 3.19526K wps
Begin Testing...
[Epoch 168] train avg loss 0.000847964, dev acc 0.7906, dev avg loss 0.45772, throughput 3.24164K wps
[Epoch 169 Batch 30/62] avg loss 0.000785984, throughput 3.28115K wps
[Epoch 169 Batch 60/62] avg loss 0.000863724, throughput 3.2145K wps
Begin Testing...
[Epoch 169] train avg loss 0.000831645, dev acc 0.7906, dev avg loss 0.457658, throughput 3.25377K wps
[Epoch 170 Batch 30/62] avg loss 0.000806693, throughput 3.25842K wps
[Epoch 170 Batch 60/62] avg loss 0.00076488, throughput 3.19591K wps
Begin Testing...
[Epoch 170] train avg loss 0.000781331, dev acc 0.7876, dev avg loss 0.458357, throughput 3.23569K wps
[Epoch 171 Batch 30/62] avg loss 0.000788777, throughput 3.29038K wps
[Epoch 171 Batch 60/62] avg loss 0.000746521, throughput 3.22302K wps
Begin Testing...
[Epoch 171] train avg loss 0.00077844, dev acc 0.7876, dev avg loss 0.456884, throughput 3.26465K wps
[Epoch 172 Batch 30/62] avg loss 0.000822784, throughput 3.3051K wps
[Epoch 172 Batch 60/62] avg loss 0.000781729, throughput 3.23101K wps
Begin Testing...
[Epoch 172] train avg loss 0.00081861, dev acc 0.7906, dev avg loss 0.4589, throughput 3.27289K wps
[Epoch 173 Batch 30/62] avg loss 0.00077151, throughput 3.30217K wps
[Epoch 173 Batch 60/62] avg loss 0.000698508, throughput 3.21772K wps
Begin Testing...
[Epoch 173] train avg loss 0.000739657, dev acc 0.7906, dev avg loss 0.458048, throughput 3.26556K wps
[Epoch 174 Batch 30/62] avg loss 0.000743963, throughput 3.29332K wps
[Epoch 174 Batch 60/62] avg loss 0.000806403, throughput 3.20187K wps
Begin Testing...
[Epoch 174] train avg loss 0.000770611, dev acc 0.7906, dev avg loss 0.458757, throughput 3.25355K wps
[Epoch 175 Batch 30/62] avg loss 0.000716356, throughput 3.27976K wps
[Epoch 175 Batch 60/62] avg loss 0.000757468, throughput 3.20032K wps
Begin Testing...
[Epoch 175] train avg loss 0.000744757, dev acc 0.7876, dev avg loss 0.458528, throughput 3.24535K wps
[Epoch 176 Batch 30/62] avg loss 0.000772811, throughput 3.26676K wps
[Epoch 176 Batch 60/62] avg loss 0.00080521, throughput 3.19753K wps
Begin Testing...
[Epoch 176] train avg loss 0.00079582, dev acc 0.7906, dev avg loss 0.459539, throughput 3.23915K wps
[Epoch 177 Batch 30/62] avg loss 0.000736433, throughput 3.29213K wps
[Epoch 177 Batch 60/62] avg loss 0.000774239, throughput 3.21026K wps
Begin Testing...
[Epoch 177] train avg loss 0.000761722, dev acc 0.7876, dev avg loss 0.459231, throughput 3.25842K wps
[Epoch 178 Batch 30/62] avg loss 0.000763684, throughput 3.29851K wps
[Epoch 178 Batch 60/62] avg loss 0.000764599, throughput 3.21176K wps
Begin Testing...
[Epoch 178] train avg loss 0.00076084, dev acc 0.7935, dev avg loss 0.463677, throughput 3.26072K wps
Observed Improvement.
Begin Testing...
[Epoch 179 Batch 30/62] avg loss 0.000764335, throughput 3.29307K wps
[Epoch 179 Batch 60/62] avg loss 0.000706498, throughput 3.2087K wps
Begin Testing...
[Epoch 179] train avg loss 0.000740656, dev acc 0.7906, dev avg loss 0.461598, throughput 3.25784K wps
[Epoch 180 Batch 30/62] avg loss 0.000732806, throughput 3.29512K wps
[Epoch 180 Batch 60/62] avg loss 0.000733659, throughput 3.21545K wps
Begin Testing...
[Epoch 180] train avg loss 0.000747969, dev acc 0.7876, dev avg loss 0.458816, throughput 3.26019K wps
[Epoch 181 Batch 30/62] avg loss 0.000739552, throughput 3.29081K wps
[Epoch 181 Batch 60/62] avg loss 0.000754362, throughput 3.21193K wps
Begin Testing...
[Epoch 181] train avg loss 0.000758475, dev acc 0.7876, dev avg loss 0.459797, throughput 3.2578K wps
[Epoch 182 Batch 30/62] avg loss 0.000694908, throughput 3.27543K wps
[Epoch 182 Batch 60/62] avg loss 0.000682119, throughput 3.19612K wps
Begin Testing...
[Epoch 182] train avg loss 0.000749186, dev acc 0.7965, dev avg loss 0.45426, throughput 3.24269K wps
Observed Improvement.
Begin Testing...
[Epoch 183 Batch 30/62] avg loss 0.000689693, throughput 3.30331K wps
[Epoch 183 Batch 60/62] avg loss 0.000730125, throughput 3.1884K wps
Begin Testing...
[Epoch 183] train avg loss 0.000725683, dev acc 0.7876, dev avg loss 0.457878, throughput 3.25174K wps
[Epoch 184 Batch 30/62] avg loss 0.000751259, throughput 3.28075K wps
[Epoch 184 Batch 60/62] avg loss 0.000626824, throughput 3.18816K wps
Begin Testing...
[Epoch 184] train avg loss 0.000729995, dev acc 0.7876, dev avg loss 0.461286, throughput 3.23971K wps
[Epoch 185 Batch 30/62] avg loss 0.00071337, throughput 3.28864K wps
[Epoch 185 Batch 60/62] avg loss 0.000744187, throughput 3.20305K wps
Begin Testing...
[Epoch 185] train avg loss 0.000759551, dev acc 0.7965, dev avg loss 0.468984, throughput 3.25102K wps
Observed Improvement.
Begin Testing...
[Epoch 186 Batch 30/62] avg loss 0.000739203, throughput 3.30369K wps
[Epoch 186 Batch 60/62] avg loss 0.000739989, throughput 3.21867K wps
Begin Testing...
[Epoch 186] train avg loss 0.000772072, dev acc 0.7935, dev avg loss 0.455553, throughput 3.26756K wps
[Epoch 187 Batch 30/62] avg loss 0.000656119, throughput 3.27607K wps
[Epoch 187 Batch 60/62] avg loss 0.00070275, throughput 3.21532K wps
Begin Testing...
[Epoch 187] train avg loss 0.000685968, dev acc 0.7876, dev avg loss 0.461556, throughput 3.24806K wps
[Epoch 188 Batch 30/62] avg loss 0.000712194, throughput 3.28095K wps
[Epoch 188 Batch 60/62] avg loss 0.000643793, throughput 3.18773K wps
Begin Testing...
[Epoch 188] train avg loss 0.000687809, dev acc 0.7876, dev avg loss 0.464525, throughput 3.24099K wps
[Epoch 189 Batch 30/62] avg loss 0.000602283, throughput 3.29457K wps
[Epoch 189 Batch 60/62] avg loss 0.000637507, throughput 3.18501K wps
Begin Testing...
[Epoch 189] train avg loss 0.000654507, dev acc 0.7994, dev avg loss 0.466799, throughput 3.24454K wps
Observed Improvement.
Begin Testing...
[Epoch 190 Batch 30/62] avg loss 0.000696209, throughput 3.29639K wps
[Epoch 190 Batch 60/62] avg loss 0.000601691, throughput 3.20871K wps
Begin Testing...
[Epoch 190] train avg loss 0.000667249, dev acc 0.7935, dev avg loss 0.466967, throughput 3.25724K wps
[Epoch 191 Batch 30/62] avg loss 0.00065671, throughput 3.27216K wps
[Epoch 191 Batch 60/62] avg loss 0.00063095, throughput 3.22015K wps
Begin Testing...
[Epoch 191] train avg loss 0.000654238, dev acc 0.7906, dev avg loss 0.467208, throughput 3.25057K wps
[Epoch 192 Batch 30/62] avg loss 0.000674346, throughput 3.27226K wps
[Epoch 192 Batch 60/62] avg loss 0.00059573, throughput 3.20143K wps
Begin Testing...
[Epoch 192] train avg loss 0.000635763, dev acc 0.7876, dev avg loss 0.465232, throughput 3.24356K wps
[Epoch 193 Batch 30/62] avg loss 0.000691653, throughput 3.29773K wps
[Epoch 193 Batch 60/62] avg loss 0.000616741, throughput 3.22323K wps
Begin Testing...
[Epoch 193] train avg loss 0.00065617, dev acc 0.8024, dev avg loss 0.472101, throughput 3.26609K wps
Observed Improvement.
Begin Testing...
[Epoch 194 Batch 30/62] avg loss 0.000645254, throughput 3.2929K wps
[Epoch 194 Batch 60/62] avg loss 0.000717506, throughput 3.20582K wps
Begin Testing...
[Epoch 194] train avg loss 0.000691043, dev acc 0.7876, dev avg loss 0.467275, throughput 3.25588K wps
[Epoch 195 Batch 30/62] avg loss 0.000672238, throughput 3.29524K wps
[Epoch 195 Batch 60/62] avg loss 0.000669993, throughput 3.19791K wps
Begin Testing...
[Epoch 195] train avg loss 0.00067227, dev acc 0.7876, dev avg loss 0.465794, throughput 3.25455K wps
[Epoch 196 Batch 30/62] avg loss 0.00066767, throughput 3.29483K wps
[Epoch 196 Batch 60/62] avg loss 0.000597493, throughput 3.2156K wps
Begin Testing...
[Epoch 196] train avg loss 0.000631884, dev acc 0.7994, dev avg loss 0.471363, throughput 3.26131K wps
[Epoch 197 Batch 30/62] avg loss 0.000574387, throughput 3.27336K wps
[Epoch 197 Batch 60/62] avg loss 0.000633927, throughput 3.18296K wps
Begin Testing...
[Epoch 197] train avg loss 0.000608584, dev acc 0.7906, dev avg loss 0.469113, throughput 3.23521K wps
[Epoch 198 Batch 30/62] avg loss 0.000587301, throughput 3.29599K wps
[Epoch 198 Batch 60/62] avg loss 0.00059537, throughput 3.1946K wps
Begin Testing...
[Epoch 198] train avg loss 0.000600655, dev acc 0.7876, dev avg loss 0.468171, throughput 3.25023K wps
[Epoch 199 Batch 30/62] avg loss 0.000656186, throughput 3.26616K wps
[Epoch 199 Batch 60/62] avg loss 0.000606889, throughput 3.22631K wps
Begin Testing...
[Epoch 199] train avg loss 0.000634434, dev acc 0.7906, dev avg loss 0.469991, throughput 3.2521K wps
Test loss 0.407642, test acc 0.8382
Total time cost 419.64s
[Epoch 0 Batch 30/62] avg loss 0.0139818, throughput 3.04688K wps
[Epoch 0 Batch 60/62] avg loss 0.0131103, throughput 3.18723K wps
Begin Testing...
[Epoch 0] train avg loss 0.0137728, dev acc 0.6519, dev avg loss 0.642638, throughput 3.12577K wps
Observed Improvement.
Begin Testing...
[Epoch 1 Batch 30/62] avg loss 0.0130823, throughput 3.26232K wps
[Epoch 1 Batch 60/62] avg loss 0.0129907, throughput 3.20316K wps
Begin Testing...
[Epoch 1] train avg loss 0.0132504, dev acc 0.6519, dev avg loss 0.633943, throughput 3.24078K wps
Observed Improvement.
Begin Testing...
[Epoch 2 Batch 30/62] avg loss 0.0130183, throughput 3.30154K wps
[Epoch 2 Batch 60/62] avg loss 0.0127645, throughput 3.19673K wps
Begin Testing...
[Epoch 2] train avg loss 0.0130394, dev acc 0.6519, dev avg loss 0.624388, throughput 3.25547K wps
Observed Improvement.
Begin Testing...
[Epoch 3 Batch 30/62] avg loss 0.0125127, throughput 3.28281K wps
[Epoch 3 Batch 60/62] avg loss 0.01287, throughput 3.21143K wps
Begin Testing...
[Epoch 3] train avg loss 0.0128406, dev acc 0.6519, dev avg loss 0.616, throughput 3.25317K wps
Observed Improvement.
Begin Testing...
[Epoch 4 Batch 30/62] avg loss 0.012809, throughput 3.26698K wps
[Epoch 4 Batch 60/62] avg loss 0.0123179, throughput 3.20143K wps
Begin Testing...
[Epoch 4] train avg loss 0.0127197, dev acc 0.6519, dev avg loss 0.609318, throughput 3.24101K wps
Observed Improvement.
Begin Testing...
[Epoch 5 Batch 30/62] avg loss 0.0123196, throughput 3.29023K wps
[Epoch 5 Batch 60/62] avg loss 0.0122359, throughput 3.19805K wps
Begin Testing...
[Epoch 5] train avg loss 0.0124297, dev acc 0.6519, dev avg loss 0.601679, throughput 3.25088K wps
Observed Improvement.
Begin Testing...
[Epoch 6 Batch 30/62] avg loss 0.0122054, throughput 3.27274K wps
[Epoch 6 Batch 60/62] avg loss 0.0120893, throughput 3.21428K wps
Begin Testing...
[Epoch 6] train avg loss 0.012299, dev acc 0.6549, dev avg loss 0.593802, throughput 3.24931K wps
Observed Improvement.
Begin Testing...
[Epoch 7 Batch 30/62] avg loss 0.0118362, throughput 3.28098K wps
[Epoch 7 Batch 60/62] avg loss 0.0120839, throughput 3.17741K wps
Begin Testing...
[Epoch 7] train avg loss 0.0120724, dev acc 0.6519, dev avg loss 0.587576, throughput 3.2352K wps
[Epoch 8 Batch 30/62] avg loss 0.0117208, throughput 3.26588K wps
[Epoch 8 Batch 60/62] avg loss 0.0116999, throughput 3.20386K wps
Begin Testing...
[Epoch 8] train avg loss 0.0119362, dev acc 0.6755, dev avg loss 0.580268, throughput 3.24142K wps
Observed Improvement.
Begin Testing...
[Epoch 9 Batch 30/62] avg loss 0.0116715, throughput 3.28147K wps
[Epoch 9 Batch 60/62] avg loss 0.0115819, throughput 3.18535K wps
Begin Testing...
[Epoch 9] train avg loss 0.0117583, dev acc 0.6696, dev avg loss 0.570069, throughput 3.23997K wps
[Epoch 10 Batch 30/62] avg loss 0.0114706, throughput 3.24865K wps
[Epoch 10 Batch 60/62] avg loss 0.0114015, throughput 3.19605K wps
Begin Testing...
[Epoch 10] train avg loss 0.0115573, dev acc 0.6844, dev avg loss 0.561734, throughput 3.22839K wps
Observed Improvement.
Begin Testing...
[Epoch 11 Batch 30/62] avg loss 0.0111558, throughput 3.30182K wps
[Epoch 11 Batch 60/62] avg loss 0.0113638, throughput 3.21003K wps
Begin Testing...
[Epoch 11] train avg loss 0.0114238, dev acc 0.6755, dev avg loss 0.553235, throughput 3.26252K wps
[Epoch 12 Batch 30/62] avg loss 0.0111217, throughput 3.29426K wps
[Epoch 12 Batch 60/62] avg loss 0.0109551, throughput 3.18651K wps
Begin Testing...
[Epoch 12] train avg loss 0.0111516, dev acc 0.6903, dev avg loss 0.544315, throughput 3.24717K wps
Observed Improvement.
Begin Testing...
[Epoch 13 Batch 30/62] avg loss 0.0108943, throughput 3.24812K wps
[Epoch 13 Batch 60/62] avg loss 0.0105959, throughput 3.21186K wps
Begin Testing...
[Epoch 13] train avg loss 0.0109321, dev acc 0.7286, dev avg loss 0.535386, throughput 3.23698K wps
Observed Improvement.
Begin Testing...
[Epoch 14 Batch 30/62] avg loss 0.0105909, throughput 3.27964K wps
[Epoch 14 Batch 60/62] avg loss 0.0107101, throughput 3.20062K wps
Begin Testing...
[Epoch 14] train avg loss 0.0107575, dev acc 0.7257, dev avg loss 0.526567, throughput 3.24611K wps
[Epoch 15 Batch 30/62] avg loss 0.0104032, throughput 3.29486K wps
[Epoch 15 Batch 60/62] avg loss 0.0103789, throughput 3.203K wps
Begin Testing...
[Epoch 15] train avg loss 0.0105662, dev acc 0.7404, dev avg loss 0.51766, throughput 3.2548K wps
Observed Improvement.
Begin Testing...
[Epoch 16 Batch 30/62] avg loss 0.0100794, throughput 3.26634K wps
[Epoch 16 Batch 60/62] avg loss 0.010115, throughput 3.21026K wps
Begin Testing...
[Epoch 16] train avg loss 0.0101827, dev acc 0.7404, dev avg loss 0.509105, throughput 3.24416K wps
Observed Improvement.
Begin Testing...
[Epoch 17 Batch 30/62] avg loss 0.00997394, throughput 3.26613K wps
[Epoch 17 Batch 60/62] avg loss 0.00991951, throughput 3.18049K wps
Begin Testing...
[Epoch 17] train avg loss 0.0100909, dev acc 0.7906, dev avg loss 0.50088, throughput 3.23K wps
Observed Improvement.
Begin Testing...
[Epoch 18 Batch 30/62] avg loss 0.00979157, throughput 3.27036K wps
[Epoch 18 Batch 60/62] avg loss 0.00967749, throughput 3.21368K wps
Begin Testing...
[Epoch 18] train avg loss 0.00988412, dev acc 0.7758, dev avg loss 0.493071, throughput 3.24829K wps
[Epoch 19 Batch 30/62] avg loss 0.00969842, throughput 3.28115K wps
[Epoch 19 Batch 60/62] avg loss 0.00937259, throughput 3.20599K wps
Begin Testing...
[Epoch 19] train avg loss 0.0096818, dev acc 0.7994, dev avg loss 0.485442, throughput 3.24947K wps
Observed Improvement.
Begin Testing...
[Epoch 20 Batch 30/62] avg loss 0.00924469, throughput 3.29887K wps
[Epoch 20 Batch 60/62] avg loss 0.00950673, throughput 3.2054K wps
Begin Testing...
[Epoch 20] train avg loss 0.00951225, dev acc 0.7817, dev avg loss 0.478863, throughput 3.25839K wps
[Epoch 21 Batch 30/62] avg loss 0.00925382, throughput 3.295K wps
[Epoch 21 Batch 60/62] avg loss 0.009186, throughput 3.20943K wps
Begin Testing...
[Epoch 21] train avg loss 0.00932936, dev acc 0.7906, dev avg loss 0.471571, throughput 3.2604K wps
[Epoch 22 Batch 30/62] avg loss 0.00901391, throughput 3.2999K wps
[Epoch 22 Batch 60/62] avg loss 0.00882754, throughput 3.21082K wps
Begin Testing...
[Epoch 22] train avg loss 0.00902551, dev acc 0.8112, dev avg loss 0.465034, throughput 3.26133K wps
Observed Improvement.
Begin Testing...
[Epoch 23 Batch 30/62] avg loss 0.00893986, throughput 3.29589K wps
[Epoch 23 Batch 60/62] avg loss 0.00866379, throughput 3.21088K wps
Begin Testing...
[Epoch 23] train avg loss 0.00890436, dev acc 0.8083, dev avg loss 0.458848, throughput 3.26047K wps
[Epoch 24 Batch 30/62] avg loss 0.00855203, throughput 3.29192K wps
[Epoch 24 Batch 60/62] avg loss 0.00866363, throughput 3.19936K wps
Begin Testing...
[Epoch 24] train avg loss 0.00870398, dev acc 0.7876, dev avg loss 0.458073, throughput 3.25279K wps
[Epoch 25 Batch 30/62] avg loss 0.00847076, throughput 3.29129K wps
[Epoch 25 Batch 60/62] avg loss 0.00826396, throughput 3.19447K wps
Begin Testing...
[Epoch 25] train avg loss 0.00846184, dev acc 0.7994, dev avg loss 0.450453, throughput 3.25089K wps
[Epoch 26 Batch 30/62] avg loss 0.00842346, throughput 3.29043K wps
[Epoch 26 Batch 60/62] avg loss 0.00810821, throughput 3.19155K wps
Begin Testing...
[Epoch 26] train avg loss 0.00838919, dev acc 0.8112, dev avg loss 0.443516, throughput 3.24739K wps
Observed Improvement.
Begin Testing...
[Epoch 27 Batch 30/62] avg loss 0.00805858, throughput 3.2383K wps
[Epoch 27 Batch 60/62] avg loss 0.00818687, throughput 3.20895K wps
Begin Testing...
[Epoch 27] train avg loss 0.00822202, dev acc 0.8083, dev avg loss 0.440382, throughput 3.2306K wps
[Epoch 28 Batch 30/62] avg loss 0.00803567, throughput 3.28048K wps
[Epoch 28 Batch 60/62] avg loss 0.00788283, throughput 3.18652K wps
Begin Testing...
[Epoch 28] train avg loss 0.00813735, dev acc 0.8142, dev avg loss 0.434799, throughput 3.23987K wps
Observed Improvement.
Begin Testing...
[Epoch 29 Batch 30/62] avg loss 0.00780291, throughput 3.2443K wps
[Epoch 29 Batch 60/62] avg loss 0.00797057, throughput 3.21566K wps
Begin Testing...
[Epoch 29] train avg loss 0.0079523, dev acc 0.8053, dev avg loss 0.431605, throughput 3.23612K wps
[Epoch 30 Batch 30/62] avg loss 0.0077525, throughput 3.27561K wps
[Epoch 30 Batch 60/62] avg loss 0.00768926, throughput 3.19492K wps
Begin Testing...
[Epoch 30] train avg loss 0.00779015, dev acc 0.8201, dev avg loss 0.427415, throughput 3.24194K wps
Observed Improvement.
Begin Testing...
[Epoch 31 Batch 30/62] avg loss 0.00759505, throughput 3.27169K wps
[Epoch 31 Batch 60/62] avg loss 0.00776, throughput 3.21073K wps
Begin Testing...
[Epoch 31] train avg loss 0.00776738, dev acc 0.8112, dev avg loss 0.423454, throughput 3.24741K wps
[Epoch 32 Batch 30/62] avg loss 0.00738991, throughput 3.2745K wps
[Epoch 32 Batch 60/62] avg loss 0.007613, throughput 3.21334K wps
Begin Testing...
[Epoch 32] train avg loss 0.00771906, dev acc 0.7729, dev avg loss 0.431595, throughput 3.24986K wps
[Epoch 33 Batch 30/62] avg loss 0.00721824, throughput 3.27683K wps
[Epoch 33 Batch 60/62] avg loss 0.00733307, throughput 3.21363K wps
Begin Testing...
[Epoch 33] train avg loss 0.00732164, dev acc 0.8142, dev avg loss 0.417452, throughput 3.25099K wps
[Epoch 34 Batch 30/62] avg loss 0.00701439, throughput 3.28162K wps
[Epoch 34 Batch 60/62] avg loss 0.00731169, throughput 3.20861K wps
Begin Testing...
[Epoch 34] train avg loss 0.00722147, dev acc 0.8171, dev avg loss 0.413853, throughput 3.25161K wps
[Epoch 35 Batch 30/62] avg loss 0.00714654, throughput 3.29409K wps
[Epoch 35 Batch 60/62] avg loss 0.00691443, throughput 3.20551K wps
Begin Testing...
[Epoch 35] train avg loss 0.00718058, dev acc 0.8171, dev avg loss 0.411192, throughput 3.25588K wps
[Epoch 36 Batch 30/62] avg loss 0.00686285, throughput 3.28143K wps
[Epoch 36 Batch 60/62] avg loss 0.00706305, throughput 3.18698K wps
Begin Testing...
[Epoch 36] train avg loss 0.00706418, dev acc 0.8083, dev avg loss 0.410885, throughput 3.24123K wps
[Epoch 37 Batch 30/62] avg loss 0.00679313, throughput 3.2733K wps
[Epoch 37 Batch 60/62] avg loss 0.00700908, throughput 3.19884K wps
Begin Testing...
[Epoch 37] train avg loss 0.0069656, dev acc 0.8171, dev avg loss 0.405885, throughput 3.24173K wps
[Epoch 38 Batch 30/62] avg loss 0.00668107, throughput 3.2884K wps
[Epoch 38 Batch 60/62] avg loss 0.00656995, throughput 3.21738K wps
Begin Testing...
[Epoch 38] train avg loss 0.00666259, dev acc 0.8171, dev avg loss 0.405503, throughput 3.25974K wps
[Epoch 39 Batch 30/62] avg loss 0.00661579, throughput 3.27553K wps
[Epoch 39 Batch 60/62] avg loss 0.00640166, throughput 3.21626K wps
Begin Testing...
[Epoch 39] train avg loss 0.00657926, dev acc 0.8142, dev avg loss 0.400542, throughput 3.25094K wps
[Epoch 40 Batch 30/62] avg loss 0.00652928, throughput 3.28148K wps
[Epoch 40 Batch 60/62] avg loss 0.00626453, throughput 3.21054K wps
Begin Testing...
[Epoch 40] train avg loss 0.00654123, dev acc 0.8230, dev avg loss 0.397793, throughput 3.25102K wps
Observed Improvement.
Begin Testing...
[Epoch 41 Batch 30/62] avg loss 0.00644023, throughput 3.29823K wps
[Epoch 41 Batch 60/62] avg loss 0.00631888, throughput 3.21091K wps
Begin Testing...
[Epoch 41] train avg loss 0.00649213, dev acc 0.8171, dev avg loss 0.409456, throughput 3.25944K wps
[Epoch 42 Batch 30/62] avg loss 0.00652424, throughput 3.29225K wps
[Epoch 42 Batch 60/62] avg loss 0.00607082, throughput 3.19857K wps
Begin Testing...
[Epoch 42] train avg loss 0.00634043, dev acc 0.8201, dev avg loss 0.393707, throughput 3.2502K wps
[Epoch 43 Batch 30/62] avg loss 0.00606072, throughput 3.28373K wps
[Epoch 43 Batch 60/62] avg loss 0.00608776, throughput 3.19215K wps
Begin Testing...
[Epoch 43] train avg loss 0.00613574, dev acc 0.8201, dev avg loss 0.391644, throughput 3.24471K wps
[Epoch 44 Batch 30/62] avg loss 0.00607152, throughput 3.26015K wps
[Epoch 44 Batch 60/62] avg loss 0.00598713, throughput 3.21381K wps
Begin Testing...
[Epoch 44] train avg loss 0.0061636, dev acc 0.8201, dev avg loss 0.389787, throughput 3.24368K wps
[Epoch 45 Batch 30/62] avg loss 0.00570666, throughput 3.27772K wps
[Epoch 45 Batch 60/62] avg loss 0.00599967, throughput 3.20993K wps
Begin Testing...
[Epoch 45] train avg loss 0.00592328, dev acc 0.8112, dev avg loss 0.390509, throughput 3.24949K wps
[Epoch 46 Batch 30/62] avg loss 0.00561421, throughput 3.2805K wps
[Epoch 46 Batch 60/62] avg loss 0.0057929, throughput 3.22056K wps
Begin Testing...
[Epoch 46] train avg loss 0.00575597, dev acc 0.8171, dev avg loss 0.38631, throughput 3.25579K wps
[Epoch 47 Batch 30/62] avg loss 0.00581878, throughput 3.27726K wps
[Epoch 47 Batch 60/62] avg loss 0.00560732, throughput 3.22084K wps
Begin Testing...
[Epoch 47] train avg loss 0.00575408, dev acc 0.8142, dev avg loss 0.384589, throughput 3.25552K wps
[Epoch 48 Batch 30/62] avg loss 0.00571124, throughput 3.28165K wps
[Epoch 48 Batch 60/62] avg loss 0.00554127, throughput 3.21654K wps
Begin Testing...
[Epoch 48] train avg loss 0.00564217, dev acc 0.8260, dev avg loss 0.382177, throughput 3.25493K wps
Observed Improvement.
Begin Testing...
[Epoch 49 Batch 30/62] avg loss 0.0055734, throughput 3.29175K wps
[Epoch 49 Batch 60/62] avg loss 0.00534647, throughput 3.21089K wps
Begin Testing...
[Epoch 49] train avg loss 0.005531, dev acc 0.8230, dev avg loss 0.380039, throughput 3.25794K wps
[Epoch 50 Batch 30/62] avg loss 0.00529, throughput 3.28992K wps
[Epoch 50 Batch 60/62] avg loss 0.00546407, throughput 3.21409K wps
Begin Testing...
[Epoch 50] train avg loss 0.00539418, dev acc 0.8260, dev avg loss 0.378714, throughput 3.25802K wps
Observed Improvement.
Begin Testing...
[Epoch 51 Batch 30/62] avg loss 0.00532601, throughput 3.28728K wps
[Epoch 51 Batch 60/62] avg loss 0.00514749, throughput 3.19164K wps
Begin Testing...
[Epoch 51] train avg loss 0.00537133, dev acc 0.8171, dev avg loss 0.379727, throughput 3.24517K wps
[Epoch 52 Batch 30/62] avg loss 0.00506399, throughput 3.267K wps
[Epoch 52 Batch 60/62] avg loss 0.00526731, throughput 3.20078K wps
Begin Testing...
[Epoch 52] train avg loss 0.00520068, dev acc 0.8230, dev avg loss 0.375245, throughput 3.24007K wps
[Epoch 53 Batch 30/62] avg loss 0.00515488, throughput 3.25962K wps
[Epoch 53 Batch 60/62] avg loss 0.00511001, throughput 3.21525K wps
Begin Testing...
[Epoch 53] train avg loss 0.00518782, dev acc 0.8230, dev avg loss 0.374147, throughput 3.24387K wps
[Epoch 54 Batch 30/62] avg loss 0.00512623, throughput 3.29025K wps
[Epoch 54 Batch 60/62] avg loss 0.00499894, throughput 3.22619K wps
Begin Testing...
[Epoch 54] train avg loss 0.00517357, dev acc 0.8230, dev avg loss 0.372594, throughput 3.26453K wps
[Epoch 55 Batch 30/62] avg loss 0.00488417, throughput 3.27265K wps
[Epoch 55 Batch 60/62] avg loss 0.00473695, throughput 3.22412K wps
Begin Testing...
[Epoch 55] train avg loss 0.00488265, dev acc 0.8230, dev avg loss 0.371378, throughput 3.25429K wps
[Epoch 56 Batch 30/62] avg loss 0.00481751, throughput 3.28312K wps
[Epoch 56 Batch 60/62] avg loss 0.00473611, throughput 3.19792K wps
Begin Testing...
[Epoch 56] train avg loss 0.00482238, dev acc 0.8201, dev avg loss 0.374037, throughput 3.24597K wps
[Epoch 57 Batch 30/62] avg loss 0.00500852, throughput 3.2835K wps
[Epoch 57 Batch 60/62] avg loss 0.00457221, throughput 3.21353K wps
Begin Testing...
[Epoch 57] train avg loss 0.00485125, dev acc 0.8348, dev avg loss 0.369672, throughput 3.25453K wps
Observed Improvement.
Begin Testing...
[Epoch 58 Batch 30/62] avg loss 0.00450184, throughput 3.30055K wps
[Epoch 58 Batch 60/62] avg loss 0.00459831, throughput 3.2K wps
Begin Testing...
[Epoch 58] train avg loss 0.00467739, dev acc 0.8230, dev avg loss 0.369463, throughput 3.25666K wps
[Epoch 59 Batch 30/62] avg loss 0.00495184, throughput 3.27815K wps
[Epoch 59 Batch 60/62] avg loss 0.00449279, throughput 3.18295K wps
Begin Testing...
[Epoch 59] train avg loss 0.0047392, dev acc 0.8289, dev avg loss 0.366647, throughput 3.23665K wps
[Epoch 60 Batch 30/62] avg loss 0.00445955, throughput 3.27371K wps
[Epoch 60 Batch 60/62] avg loss 0.00456382, throughput 3.21621K wps
Begin Testing...
[Epoch 60] train avg loss 0.0045865, dev acc 0.8378, dev avg loss 0.366609, throughput 3.25122K wps
Observed Improvement.
Begin Testing...
[Epoch 61 Batch 30/62] avg loss 0.00439992, throughput 3.27244K wps
[Epoch 61 Batch 60/62] avg loss 0.0043902, throughput 3.20224K wps
Begin Testing...
[Epoch 61] train avg loss 0.0044431, dev acc 0.8260, dev avg loss 0.365291, throughput 3.24567K wps
[Epoch 62 Batch 30/62] avg loss 0.00421691, throughput 3.28022K wps
[Epoch 62 Batch 60/62] avg loss 0.00459729, throughput 3.21928K wps
Begin Testing...
[Epoch 62] train avg loss 0.00441866, dev acc 0.8348, dev avg loss 0.364561, throughput 3.25734K wps
[Epoch 63 Batch 30/62] avg loss 0.00420465, throughput 3.30604K wps
[Epoch 63 Batch 60/62] avg loss 0.00430718, throughput 3.21958K wps
Begin Testing...
[Epoch 63] train avg loss 0.00431335, dev acc 0.8378, dev avg loss 0.367134, throughput 3.26799K wps
Observed Improvement.
Begin Testing...
[Epoch 64 Batch 30/62] avg loss 0.00407476, throughput 3.28922K wps
[Epoch 64 Batch 60/62] avg loss 0.00414284, throughput 3.20053K wps
Begin Testing...
[Epoch 64] train avg loss 0.00421034, dev acc 0.8319, dev avg loss 0.362292, throughput 3.25031K wps
[Epoch 65 Batch 30/62] avg loss 0.00408709, throughput 3.28758K wps
[Epoch 65 Batch 60/62] avg loss 0.00403468, throughput 3.19988K wps
Begin Testing...
[Epoch 65] train avg loss 0.00410962, dev acc 0.8348, dev avg loss 0.362666, throughput 3.2512K wps
[Epoch 66 Batch 30/62] avg loss 0.00389947, throughput 3.28467K wps
[Epoch 66 Batch 60/62] avg loss 0.00413256, throughput 3.16772K wps
Begin Testing...
[Epoch 66] train avg loss 0.00402066, dev acc 0.8378, dev avg loss 0.361953, throughput 3.23074K wps
Observed Improvement.
Begin Testing...
[Epoch 67 Batch 30/62] avg loss 0.00387877, throughput 3.27285K wps
[Epoch 67 Batch 60/62] avg loss 0.00387963, throughput 3.17138K wps
Begin Testing...
[Epoch 67] train avg loss 0.00392592, dev acc 0.8319, dev avg loss 0.359599, throughput 3.22747K wps
[Epoch 68 Batch 30/62] avg loss 0.00376583, throughput 3.24707K wps
[Epoch 68 Batch 60/62] avg loss 0.00382645, throughput 3.19342K wps
Begin Testing...
[Epoch 68] train avg loss 0.00389236, dev acc 0.8407, dev avg loss 0.359381, throughput 3.22837K wps
Observed Improvement.
Begin Testing...
[Epoch 69 Batch 30/62] avg loss 0.00392201, throughput 3.29023K wps
[Epoch 69 Batch 60/62] avg loss 0.00365505, throughput 3.16612K wps
Begin Testing...
[Epoch 69] train avg loss 0.00384521, dev acc 0.8348, dev avg loss 0.35907, throughput 3.23255K wps
[Epoch 70 Batch 30/62] avg loss 0.00391006, throughput 3.26576K wps
[Epoch 70 Batch 60/62] avg loss 0.00385765, throughput 3.16501K wps
Begin Testing...
[Epoch 70] train avg loss 0.00403633, dev acc 0.8348, dev avg loss 0.358394, throughput 3.22316K wps
[Epoch 71 Batch 30/62] avg loss 0.0035523, throughput 3.24252K wps
[Epoch 71 Batch 60/62] avg loss 0.00372435, throughput 3.19409K wps
Begin Testing...
[Epoch 71] train avg loss 0.00369333, dev acc 0.8348, dev avg loss 0.358205, throughput 3.223K wps
[Epoch 72 Batch 30/62] avg loss 0.00368396, throughput 3.28405K wps
[Epoch 72 Batch 60/62] avg loss 0.00346308, throughput 3.16845K wps
Begin Testing...
[Epoch 72] train avg loss 0.00362157, dev acc 0.8378, dev avg loss 0.357876, throughput 3.23112K wps
[Epoch 73 Batch 30/62] avg loss 0.00353265, throughput 3.24185K wps
[Epoch 73 Batch 60/62] avg loss 0.00343063, throughput 3.19221K wps
Begin Testing...
[Epoch 73] train avg loss 0.00353837, dev acc 0.8437, dev avg loss 0.355908, throughput 3.21943K wps
Observed Improvement.
Begin Testing...
[Epoch 74 Batch 30/62] avg loss 0.00337518, throughput 3.2469K wps
[Epoch 74 Batch 60/62] avg loss 0.00340815, throughput 3.16021K wps
Begin Testing...
[Epoch 74] train avg loss 0.003425, dev acc 0.8437, dev avg loss 0.356701, throughput 3.20901K wps
Observed Improvement.
Begin Testing...
[Epoch 75 Batch 30/62] avg loss 0.00336642, throughput 3.25289K wps
[Epoch 75 Batch 60/62] avg loss 0.00332573, throughput 3.15706K wps
Begin Testing...
[Epoch 75] train avg loss 0.00338667, dev acc 0.8437, dev avg loss 0.3545, throughput 3.21019K wps
Observed Improvement.
Begin Testing...
[Epoch 76 Batch 30/62] avg loss 0.00324352, throughput 3.26345K wps
[Epoch 76 Batch 60/62] avg loss 0.00331015, throughput 3.16305K wps
Begin Testing...
[Epoch 76] train avg loss 0.0033317, dev acc 0.8437, dev avg loss 0.354041, throughput 3.21827K wps
Observed Improvement.
Begin Testing...
[Epoch 77 Batch 30/62] avg loss 0.00317137, throughput 3.27741K wps
[Epoch 77 Batch 60/62] avg loss 0.00338147, throughput 3.16522K wps
Begin Testing...
[Epoch 77] train avg loss 0.00328643, dev acc 0.8437, dev avg loss 0.354076, throughput 3.22637K wps
Observed Improvement.
Begin Testing...
[Epoch 78 Batch 30/62] avg loss 0.00316104, throughput 3.27537K wps
[Epoch 78 Batch 60/62] avg loss 0.00322916, throughput 3.20099K wps
Begin Testing...
[Epoch 78] train avg loss 0.00320629, dev acc 0.8437, dev avg loss 0.352596, throughput 3.24478K wps
Observed Improvement.
Begin Testing...
[Epoch 79 Batch 30/62] avg loss 0.0031262, throughput 3.27038K wps
[Epoch 79 Batch 60/62] avg loss 0.00325227, throughput 3.1789K wps
Begin Testing...
[Epoch 79] train avg loss 0.00320536, dev acc 0.8437, dev avg loss 0.352449, throughput 3.22944K wps
Observed Improvement.
Begin Testing...
[Epoch 80 Batch 30/62] avg loss 0.00310927, throughput 3.28433K wps
[Epoch 80 Batch 60/62] avg loss 0.00299911, throughput 3.16332K wps
Begin Testing...
[Epoch 80] train avg loss 0.00310046, dev acc 0.8437, dev avg loss 0.351945, throughput 3.22576K wps
Observed Improvement.
Begin Testing...
[Epoch 81 Batch 30/62] avg loss 0.00306412, throughput 3.26356K wps
[Epoch 81 Batch 60/62] avg loss 0.00287275, throughput 3.1622K wps
Begin Testing...
[Epoch 81] train avg loss 0.00300561, dev acc 0.8466, dev avg loss 0.352074, throughput 3.21809K wps
Observed Improvement.
Begin Testing...
[Epoch 82 Batch 30/62] avg loss 0.0029544, throughput 3.26345K wps
[Epoch 82 Batch 60/62] avg loss 0.00293543, throughput 3.1671K wps
Begin Testing...
[Epoch 82] train avg loss 0.0029924, dev acc 0.8437, dev avg loss 0.351935, throughput 3.22079K wps
[Epoch 83 Batch 30/62] avg loss 0.00273807, throughput 3.26541K wps
[Epoch 83 Batch 60/62] avg loss 0.00290632, throughput 3.21193K wps
Begin Testing...
[Epoch 83] train avg loss 0.00285968, dev acc 0.8466, dev avg loss 0.351623, throughput 3.24394K wps
Observed Improvement.
Begin Testing...
[Epoch 84 Batch 30/62] avg loss 0.00273807, throughput 3.28297K wps
[Epoch 84 Batch 60/62] avg loss 0.00301379, throughput 3.15184K wps
Begin Testing...
[Epoch 84] train avg loss 0.00289002, dev acc 0.8437, dev avg loss 0.351321, throughput 3.22198K wps
[Epoch 85 Batch 30/62] avg loss 0.00285959, throughput 3.25135K wps
[Epoch 85 Batch 60/62] avg loss 0.00287076, throughput 3.19879K wps
Begin Testing...
[Epoch 85] train avg loss 0.0029568, dev acc 0.8466, dev avg loss 0.35086, throughput 3.23294K wps
Observed Improvement.
Begin Testing...
[Epoch 86 Batch 30/62] avg loss 0.00275655, throughput 3.27052K wps
[Epoch 86 Batch 60/62] avg loss 0.00270224, throughput 3.17607K wps
Begin Testing...
[Epoch 86] train avg loss 0.00278417, dev acc 0.8466, dev avg loss 0.351746, throughput 3.22824K wps
Observed Improvement.
Begin Testing...
[Epoch 87 Batch 30/62] avg loss 0.00276093, throughput 3.29178K wps
[Epoch 87 Batch 60/62] avg loss 0.00276185, throughput 3.16162K wps
Begin Testing...
[Epoch 87] train avg loss 0.00282106, dev acc 0.8555, dev avg loss 0.350083, throughput 3.23082K wps
Observed Improvement.
Begin Testing...
[Epoch 88 Batch 30/62] avg loss 0.0025732, throughput 3.28785K wps
[Epoch 88 Batch 60/62] avg loss 0.00264369, throughput 3.20551K wps
Begin Testing...
[Epoch 88] train avg loss 0.00262314, dev acc 0.8466, dev avg loss 0.351153, throughput 3.25388K wps
[Epoch 89 Batch 30/62] avg loss 0.00249947, throughput 3.28762K wps
[Epoch 89 Batch 60/62] avg loss 0.0027226, throughput 3.19905K wps
Begin Testing...
[Epoch 89] train avg loss 0.00264509, dev acc 0.8437, dev avg loss 0.349758, throughput 3.24966K wps
[Epoch 90 Batch 30/62] avg loss 0.002498, throughput 3.28808K wps
[Epoch 90 Batch 60/62] avg loss 0.00250497, throughput 3.16755K wps
Begin Testing...
[Epoch 90] train avg loss 0.00254839, dev acc 0.8437, dev avg loss 0.34941, throughput 3.23446K wps
[Epoch 91 Batch 30/62] avg loss 0.00249391, throughput 3.28518K wps
[Epoch 91 Batch 60/62] avg loss 0.00246565, throughput 3.19391K wps
Begin Testing...
[Epoch 91] train avg loss 0.00256028, dev acc 0.8525, dev avg loss 0.349247, throughput 3.24439K wps
[Epoch 92 Batch 30/62] avg loss 0.00256953, throughput 3.25212K wps
[Epoch 92 Batch 60/62] avg loss 0.00255021, throughput 3.17661K wps
Begin Testing...
[Epoch 92] train avg loss 0.00257193, dev acc 0.8466, dev avg loss 0.351287, throughput 3.22291K wps
[Epoch 93 Batch 30/62] avg loss 0.00249626, throughput 3.27458K wps
[Epoch 93 Batch 60/62] avg loss 0.0025085, throughput 3.17458K wps
Begin Testing...
[Epoch 93] train avg loss 0.00252811, dev acc 0.8466, dev avg loss 0.348136, throughput 3.22978K wps
[Epoch 94 Batch 30/62] avg loss 0.00232201, throughput 3.24548K wps
[Epoch 94 Batch 60/62] avg loss 0.00238496, throughput 3.16795K wps
Begin Testing...
[Epoch 94] train avg loss 0.00242045, dev acc 0.8466, dev avg loss 0.348908, throughput 3.21492K wps
[Epoch 95 Batch 30/62] avg loss 0.00229566, throughput 3.30744K wps
[Epoch 95 Batch 60/62] avg loss 0.00245753, throughput 3.16944K wps
Begin Testing...
[Epoch 95] train avg loss 0.00241265, dev acc 0.8496, dev avg loss 0.351271, throughput 3.24217K wps
[Epoch 96 Batch 30/62] avg loss 0.00246453, throughput 3.25142K wps
[Epoch 96 Batch 60/62] avg loss 0.00222414, throughput 3.18386K wps
Begin Testing...
[Epoch 96] train avg loss 0.00240905, dev acc 0.8437, dev avg loss 0.351283, throughput 3.22453K wps
[Epoch 97 Batch 30/62] avg loss 0.00229535, throughput 3.2824K wps
[Epoch 97 Batch 60/62] avg loss 0.0021661, throughput 3.1696K wps
Begin Testing...
[Epoch 97] train avg loss 0.00224744, dev acc 0.8525, dev avg loss 0.347531, throughput 3.23126K wps
[Epoch 98 Batch 30/62] avg loss 0.00225221, throughput 3.24643K wps
[Epoch 98 Batch 60/62] avg loss 0.00221022, throughput 3.15245K wps
Begin Testing...
[Epoch 98] train avg loss 0.00226635, dev acc 0.8466, dev avg loss 0.348884, throughput 3.20667K wps
[Epoch 99 Batch 30/62] avg loss 0.00216037, throughput 3.25777K wps
[Epoch 99 Batch 60/62] avg loss 0.00215052, throughput 3.13891K wps
Begin Testing...
[Epoch 99] train avg loss 0.00222363, dev acc 0.8466, dev avg loss 0.350097, throughput 3.20324K wps
[Epoch 100 Batch 30/62] avg loss 0.0022852, throughput 3.26157K wps
[Epoch 100 Batch 60/62] avg loss 0.00218278, throughput 3.17463K wps
Begin Testing...
[Epoch 100] train avg loss 0.00227776, dev acc 0.8407, dev avg loss 0.353543, throughput 3.2254K wps
[Epoch 101 Batch 30/62] avg loss 0.0021116, throughput 3.24625K wps
[Epoch 101 Batch 60/62] avg loss 0.00215956, throughput 3.21172K wps
Begin Testing...
[Epoch 101] train avg loss 0.00215471, dev acc 0.8466, dev avg loss 0.350384, throughput 3.23481K wps
[Epoch 102 Batch 30/62] avg loss 0.00202399, throughput 3.25362K wps
[Epoch 102 Batch 60/62] avg loss 0.00216872, throughput 3.17351K wps
Begin Testing...
[Epoch 102] train avg loss 0.00213372, dev acc 0.8496, dev avg loss 0.34791, throughput 3.22131K wps
[Epoch 103 Batch 30/62] avg loss 0.00208299, throughput 3.26251K wps
[Epoch 103 Batch 60/62] avg loss 0.00193657, throughput 3.19263K wps
Begin Testing...
[Epoch 103] train avg loss 0.00205699, dev acc 0.8496, dev avg loss 0.347923, throughput 3.23318K wps
[Epoch 104 Batch 30/62] avg loss 0.00215661, throughput 3.26175K wps
[Epoch 104 Batch 60/62] avg loss 0.00185283, throughput 3.19364K wps
Begin Testing...
[Epoch 104] train avg loss 0.00201526, dev acc 0.8525, dev avg loss 0.348842, throughput 3.23537K wps
[Epoch 105 Batch 30/62] avg loss 0.0020447, throughput 3.28145K wps
[Epoch 105 Batch 60/62] avg loss 0.00188642, throughput 3.17352K wps
Begin Testing...
[Epoch 105] train avg loss 0.00199875, dev acc 0.8525, dev avg loss 0.348308, throughput 3.23368K wps
[Epoch 106 Batch 30/62] avg loss 0.00196254, throughput 3.24877K wps
[Epoch 106 Batch 60/62] avg loss 0.00193635, throughput 3.19316K wps
Begin Testing...
[Epoch 106] train avg loss 0.00196356, dev acc 0.8496, dev avg loss 0.35253, throughput 3.22811K wps
[Epoch 107 Batch 30/62] avg loss 0.00182314, throughput 3.29769K wps
[Epoch 107 Batch 60/62] avg loss 0.00190293, throughput 3.15182K wps
Begin Testing...
[Epoch 107] train avg loss 0.00189353, dev acc 0.8496, dev avg loss 0.348663, throughput 3.2286K wps
[Epoch 108 Batch 30/62] avg loss 0.00184598, throughput 3.24906K wps
[Epoch 108 Batch 60/62] avg loss 0.0019564, throughput 3.21293K wps
Begin Testing...
[Epoch 108] train avg loss 0.00190741, dev acc 0.8555, dev avg loss 0.349473, throughput 3.23605K wps
Observed Improvement.
Begin Testing...
[Epoch 109 Batch 30/62] avg loss 0.00179577, throughput 3.29747K wps
[Epoch 109 Batch 60/62] avg loss 0.00182876, throughput 3.16334K wps
Begin Testing...
[Epoch 109] train avg loss 0.00184506, dev acc 0.8496, dev avg loss 0.35052, throughput 3.23441K wps
[Epoch 110 Batch 30/62] avg loss 0.00190231, throughput 3.26984K wps
[Epoch 110 Batch 60/62] avg loss 0.00176065, throughput 3.20153K wps
Begin Testing...
[Epoch 110] train avg loss 0.00186912, dev acc 0.8525, dev avg loss 0.348434, throughput 3.24353K wps
[Epoch 111 Batch 30/62] avg loss 0.00180962, throughput 3.27578K wps
[Epoch 111 Batch 60/62] avg loss 0.00186462, throughput 3.16899K wps
Begin Testing...
[Epoch 111] train avg loss 0.00186335, dev acc 0.8584, dev avg loss 0.349804, throughput 3.22861K wps
Observed Improvement.
Begin Testing...
[Epoch 112 Batch 30/62] avg loss 0.0017359, throughput 3.25209K wps
[Epoch 112 Batch 60/62] avg loss 0.00174883, throughput 3.15231K wps
Begin Testing...
[Epoch 112] train avg loss 0.00175563, dev acc 0.8525, dev avg loss 0.350624, throughput 3.20774K wps
[Epoch 113 Batch 30/62] avg loss 0.00175811, throughput 3.2404K wps
[Epoch 113 Batch 60/62] avg loss 0.00165245, throughput 3.16414K wps
Begin Testing...
[Epoch 113] train avg loss 0.00174617, dev acc 0.8437, dev avg loss 0.347956, throughput 3.20925K wps
[Epoch 114 Batch 30/62] avg loss 0.00168466, throughput 3.23276K wps
[Epoch 114 Batch 60/62] avg loss 0.00173621, throughput 3.19394K wps
Begin Testing...
[Epoch 114] train avg loss 0.00170885, dev acc 0.8496, dev avg loss 0.348077, throughput 3.22159K wps
[Epoch 115 Batch 30/62] avg loss 0.00166832, throughput 3.29163K wps
[Epoch 115 Batch 60/62] avg loss 0.00176716, throughput 3.15981K wps
Begin Testing...
[Epoch 115] train avg loss 0.00174397, dev acc 0.8496, dev avg loss 0.35089, throughput 3.23013K wps
[Epoch 116 Batch 30/62] avg loss 0.00156176, throughput 3.23391K wps
[Epoch 116 Batch 60/62] avg loss 0.00172058, throughput 3.18373K wps
Begin Testing...
[Epoch 116] train avg loss 0.00164416, dev acc 0.8555, dev avg loss 0.349361, throughput 3.21698K wps
[Epoch 117 Batch 30/62] avg loss 0.00167254, throughput 3.26468K wps
[Epoch 117 Batch 60/62] avg loss 0.00152197, throughput 3.16671K wps
Begin Testing...
[Epoch 117] train avg loss 0.00162222, dev acc 0.8555, dev avg loss 0.350767, throughput 3.22077K wps
[Epoch 118 Batch 30/62] avg loss 0.00157497, throughput 3.27233K wps
[Epoch 118 Batch 60/62] avg loss 0.00156066, throughput 3.18297K wps
Begin Testing...
[Epoch 118] train avg loss 0.00158489, dev acc 0.8525, dev avg loss 0.35043, throughput 3.23499K wps
[Epoch 119 Batch 30/62] avg loss 0.00154739, throughput 3.26743K wps
[Epoch 119 Batch 60/62] avg loss 0.00155353, throughput 3.18864K wps
Begin Testing...
[Epoch 119] train avg loss 0.00158055, dev acc 0.8496, dev avg loss 0.3502, throughput 3.2358K wps
[Epoch 120 Batch 30/62] avg loss 0.00150081, throughput 3.25519K wps
[Epoch 120 Batch 60/62] avg loss 0.00151942, throughput 3.17817K wps
Begin Testing...
[Epoch 120] train avg loss 0.00154066, dev acc 0.8496, dev avg loss 0.350794, throughput 3.2244K wps
[Epoch 121 Batch 30/62] avg loss 0.00161795, throughput 3.29324K wps
[Epoch 121 Batch 60/62] avg loss 0.00158842, throughput 3.16347K wps
Begin Testing...
[Epoch 121] train avg loss 0.00161835, dev acc 0.8525, dev avg loss 0.351394, throughput 3.23271K wps
[Epoch 122 Batch 30/62] avg loss 0.00149558, throughput 3.26876K wps
[Epoch 122 Batch 60/62] avg loss 0.00142057, throughput 3.19202K wps
Begin Testing...
[Epoch 122] train avg loss 0.00147918, dev acc 0.8466, dev avg loss 0.350766, throughput 3.23795K wps
[Epoch 123 Batch 30/62] avg loss 0.00149795, throughput 3.28504K wps
[Epoch 123 Batch 60/62] avg loss 0.00144521, throughput 3.18009K wps
Begin Testing...
[Epoch 123] train avg loss 0.001498, dev acc 0.8496, dev avg loss 0.356921, throughput 3.23872K wps
[Epoch 124 Batch 30/62] avg loss 0.00149877, throughput 3.24172K wps
[Epoch 124 Batch 60/62] avg loss 0.00148616, throughput 3.19217K wps
Begin Testing...
[Epoch 124] train avg loss 0.00150308, dev acc 0.8496, dev avg loss 0.351149, throughput 3.22395K wps
[Epoch 125 Batch 30/62] avg loss 0.00153976, throughput 3.28581K wps
[Epoch 125 Batch 60/62] avg loss 0.00139716, throughput 3.17187K wps
Begin Testing...
[Epoch 125] train avg loss 0.00150363, dev acc 0.8525, dev avg loss 0.351053, throughput 3.23558K wps
[Epoch 126 Batch 30/62] avg loss 0.00133691, throughput 3.23414K wps
[Epoch 126 Batch 60/62] avg loss 0.00149186, throughput 3.17555K wps
Begin Testing...
[Epoch 126] train avg loss 0.00142282, dev acc 0.8496, dev avg loss 0.351596, throughput 3.21208K wps
[Epoch 127 Batch 30/62] avg loss 0.00146452, throughput 3.24545K wps
[Epoch 127 Batch 60/62] avg loss 0.00134111, throughput 3.19488K wps
Begin Testing...
[Epoch 127] train avg loss 0.0014064, dev acc 0.8555, dev avg loss 0.355862, throughput 3.2259K wps
[Epoch 128 Batch 30/62] avg loss 0.00141723, throughput 3.25466K wps
[Epoch 128 Batch 60/62] avg loss 0.00135625, throughput 3.16232K wps
Begin Testing...
[Epoch 128] train avg loss 0.00143279, dev acc 0.8555, dev avg loss 0.352121, throughput 3.21432K wps
[Epoch 129 Batch 30/62] avg loss 0.00147063, throughput 3.24617K wps
[Epoch 129 Batch 60/62] avg loss 0.00132458, throughput 3.20102K wps
Begin Testing...
[Epoch 129] train avg loss 0.00142554, dev acc 0.8496, dev avg loss 0.35805, throughput 3.23114K wps
[Epoch 130 Batch 30/62] avg loss 0.00124935, throughput 3.27634K wps
[Epoch 130 Batch 60/62] avg loss 0.00147421, throughput 3.15761K wps
Begin Testing...
[Epoch 130] train avg loss 0.00139734, dev acc 0.8496, dev avg loss 0.351879, throughput 3.22174K wps
[Epoch 131 Batch 30/62] avg loss 0.00138233, throughput 3.24316K wps
[Epoch 131 Batch 60/62] avg loss 0.00123953, throughput 3.15126K wps
Begin Testing...
[Epoch 131] train avg loss 0.0013301, dev acc 0.8525, dev avg loss 0.354729, throughput 3.20308K wps
[Epoch 132 Batch 30/62] avg loss 0.00138991, throughput 3.27627K wps
[Epoch 132 Batch 60/62] avg loss 0.00132778, throughput 3.15751K wps
Begin Testing...
[Epoch 132] train avg loss 0.00135998, dev acc 0.8584, dev avg loss 0.355254, throughput 3.22371K wps
Observed Improvement.
Begin Testing...
[Epoch 133 Batch 30/62] avg loss 0.0012287, throughput 3.25073K wps
[Epoch 133 Batch 60/62] avg loss 0.00120444, throughput 3.18288K wps
Begin Testing...
[Epoch 133] train avg loss 0.00122928, dev acc 0.8555, dev avg loss 0.354403, throughput 3.22441K wps
[Epoch 134 Batch 30/62] avg loss 0.001324, throughput 3.27783K wps
[Epoch 134 Batch 60/62] avg loss 0.00120554, throughput 3.18967K wps
Begin Testing...
[Epoch 134] train avg loss 0.00127804, dev acc 0.8555, dev avg loss 0.355374, throughput 3.23839K wps
[Epoch 135 Batch 30/62] avg loss 0.00127207, throughput 3.22717K wps
[Epoch 135 Batch 60/62] avg loss 0.00120028, throughput 3.1864K wps
Begin Testing...
[Epoch 135] train avg loss 0.00124093, dev acc 0.8555, dev avg loss 0.354912, throughput 3.21375K wps
[Epoch 136 Batch 30/62] avg loss 0.00123982, throughput 3.29982K wps
[Epoch 136 Batch 60/62] avg loss 0.00126867, throughput 3.17932K wps
Begin Testing...
[Epoch 136] train avg loss 0.00127953, dev acc 0.8496, dev avg loss 0.354509, throughput 3.24367K wps
[Epoch 137 Batch 30/62] avg loss 0.0012261, throughput 3.25235K wps
[Epoch 137 Batch 60/62] avg loss 0.00120682, throughput 3.18953K wps
Begin Testing...
[Epoch 137] train avg loss 0.00123314, dev acc 0.8525, dev avg loss 0.355702, throughput 3.22898K wps
[Epoch 138 Batch 30/62] avg loss 0.00117396, throughput 3.29324K wps
[Epoch 138 Batch 60/62] avg loss 0.00117873, throughput 3.17367K wps
Begin Testing...
[Epoch 138] train avg loss 0.00117478, dev acc 0.8496, dev avg loss 0.356284, throughput 3.23719K wps
[Epoch 139 Batch 30/62] avg loss 0.00129419, throughput 3.25752K wps
[Epoch 139 Batch 60/62] avg loss 0.00124785, throughput 3.20316K wps
Begin Testing...
[Epoch 139] train avg loss 0.00127821, dev acc 0.8466, dev avg loss 0.353095, throughput 3.23603K wps
[Epoch 140 Batch 30/62] avg loss 0.00112799, throughput 3.28209K wps
[Epoch 140 Batch 60/62] avg loss 0.00118854, throughput 3.16686K wps
Begin Testing...
[Epoch 140] train avg loss 0.00118087, dev acc 0.8496, dev avg loss 0.354105, throughput 3.22975K wps
[Epoch 141 Batch 30/62] avg loss 0.00109162, throughput 3.25672K wps
[Epoch 141 Batch 60/62] avg loss 0.0011449, throughput 3.19044K wps
Begin Testing...
[Epoch 141] train avg loss 0.00112145, dev acc 0.8555, dev avg loss 0.357253, throughput 3.22973K wps
[Epoch 142 Batch 30/62] avg loss 0.00109059, throughput 3.27875K wps
[Epoch 142 Batch 60/62] avg loss 0.00113115, throughput 3.21681K wps
Begin Testing...
[Epoch 142] train avg loss 0.00112554, dev acc 0.8466, dev avg loss 0.35484, throughput 3.2545K wps
[Epoch 143 Batch 30/62] avg loss 0.00111451, throughput 3.26799K wps
[Epoch 143 Batch 60/62] avg loss 0.00108729, throughput 3.16231K wps
Begin Testing...
[Epoch 143] train avg loss 0.00111506, dev acc 0.8584, dev avg loss 0.357796, throughput 3.21986K wps
Observed Improvement.
Begin Testing...
[Epoch 144 Batch 30/62] avg loss 0.00108393, throughput 3.26908K wps
[Epoch 144 Batch 60/62] avg loss 0.00112635, throughput 3.15806K wps
Begin Testing...
[Epoch 144] train avg loss 0.00110599, dev acc 0.8496, dev avg loss 0.355254, throughput 3.21939K wps
[Epoch 145 Batch 30/62] avg loss 0.00110838, throughput 3.25154K wps
[Epoch 145 Batch 60/62] avg loss 0.00119779, throughput 3.17828K wps
Begin Testing...
[Epoch 145] train avg loss 0.00115089, dev acc 0.8525, dev avg loss 0.356433, throughput 3.22193K wps
[Epoch 146 Batch 30/62] avg loss 0.00105397, throughput 3.28763K wps
[Epoch 146 Batch 60/62] avg loss 0.00104508, throughput 3.15513K wps
Begin Testing...
[Epoch 146] train avg loss 0.00108979, dev acc 0.8525, dev avg loss 0.358973, throughput 3.22489K wps
[Epoch 147 Batch 30/62] avg loss 0.00113329, throughput 3.27363K wps
[Epoch 147 Batch 60/62] avg loss 0.00106434, throughput 3.15725K wps
Begin Testing...
[Epoch 147] train avg loss 0.00109743, dev acc 0.8584, dev avg loss 0.358393, throughput 3.22019K wps
Observed Improvement.
Begin Testing...
[Epoch 148 Batch 30/62] avg loss 0.001019, throughput 3.27448K wps
[Epoch 148 Batch 60/62] avg loss 0.00108855, throughput 3.16828K wps
Begin Testing...
[Epoch 148] train avg loss 0.00106744, dev acc 0.8555, dev avg loss 0.362252, throughput 3.22617K wps
[Epoch 149 Batch 30/62] avg loss 0.00109072, throughput 3.26815K wps
[Epoch 149 Batch 60/62] avg loss 0.00104692, throughput 3.19469K wps
Begin Testing...
[Epoch 149] train avg loss 0.00113098, dev acc 0.8525, dev avg loss 0.360673, throughput 3.23894K wps
[Epoch 150 Batch 30/62] avg loss 0.000994475, throughput 3.27173K wps
[Epoch 150 Batch 60/62] avg loss 0.0010561, throughput 3.18225K wps
Begin Testing...
[Epoch 150] train avg loss 0.00103528, dev acc 0.8555, dev avg loss 0.35836, throughput 3.23309K wps
[Epoch 151 Batch 30/62] avg loss 0.00101208, throughput 3.30259K wps
[Epoch 151 Batch 60/62] avg loss 0.00101491, throughput 3.16408K wps
Begin Testing...
[Epoch 151] train avg loss 0.00101275, dev acc 0.8555, dev avg loss 0.360587, throughput 3.23755K wps
[Epoch 152 Batch 30/62] avg loss 0.000995044, throughput 3.2683K wps
[Epoch 152 Batch 60/62] avg loss 0.000948347, throughput 3.22989K wps
Begin Testing...
[Epoch 152] train avg loss 0.000985498, dev acc 0.8555, dev avg loss 0.360421, throughput 3.25402K wps
[Epoch 153 Batch 30/62] avg loss 0.00089057, throughput 3.27845K wps
[Epoch 153 Batch 60/62] avg loss 0.000996086, throughput 3.21949K wps
Begin Testing...
[Epoch 153] train avg loss 0.000955109, dev acc 0.8525, dev avg loss 0.359456, throughput 3.25311K wps
[Epoch 154 Batch 30/62] avg loss 0.000952514, throughput 3.26902K wps
[Epoch 154 Batch 60/62] avg loss 0.00102705, throughput 3.21875K wps
Begin Testing...
[Epoch 154] train avg loss 0.00100262, dev acc 0.8555, dev avg loss 0.36633, throughput 3.24822K wps
[Epoch 155 Batch 30/62] avg loss 0.000981542, throughput 3.2907K wps
[Epoch 155 Batch 60/62] avg loss 0.00113953, throughput 3.15913K wps
Begin Testing...
[Epoch 155] train avg loss 0.00106482, dev acc 0.8525, dev avg loss 0.360801, throughput 3.23042K wps
[Epoch 156 Batch 30/62] avg loss 0.00103634, throughput 3.25159K wps
[Epoch 156 Batch 60/62] avg loss 0.0010343, throughput 3.21099K wps
Begin Testing...
[Epoch 156] train avg loss 0.00104944, dev acc 0.8466, dev avg loss 0.360433, throughput 3.23928K wps
[Epoch 157 Batch 30/62] avg loss 0.00100207, throughput 3.27043K wps
[Epoch 157 Batch 60/62] avg loss 0.000951341, throughput 3.15174K wps
Begin Testing...
[Epoch 157] train avg loss 0.00099689, dev acc 0.8614, dev avg loss 0.363015, throughput 3.21604K wps
Observed Improvement.
Begin Testing...
[Epoch 158 Batch 30/62] avg loss 0.00102814, throughput 3.28128K wps
[Epoch 158 Batch 60/62] avg loss 0.000842584, throughput 3.15824K wps
Begin Testing...
[Epoch 158] train avg loss 0.000955742, dev acc 0.8525, dev avg loss 0.36095, throughput 3.22431K wps
[Epoch 159 Batch 30/62] avg loss 0.00090452, throughput 3.23314K wps
[Epoch 159 Batch 60/62] avg loss 0.000859247, throughput 3.20514K wps
Begin Testing...
[Epoch 159] train avg loss 0.000899378, dev acc 0.8525, dev avg loss 0.3617, throughput 3.22757K wps
[Epoch 160 Batch 30/62] avg loss 0.00089693, throughput 3.30305K wps
[Epoch 160 Batch 60/62] avg loss 0.00090561, throughput 3.19574K wps
Begin Testing...
[Epoch 160] train avg loss 0.000907402, dev acc 0.8555, dev avg loss 0.36282, throughput 3.25628K wps
[Epoch 161 Batch 30/62] avg loss 0.00101119, throughput 3.29945K wps
[Epoch 161 Batch 60/62] avg loss 0.000930871, throughput 3.20997K wps
Begin Testing...
[Epoch 161] train avg loss 0.000974411, dev acc 0.8525, dev avg loss 0.36351, throughput 3.25991K wps
[Epoch 162 Batch 30/62] avg loss 0.000816294, throughput 3.28855K wps
[Epoch 162 Batch 60/62] avg loss 0.000964245, throughput 3.18481K wps
Begin Testing...
[Epoch 162] train avg loss 0.000899184, dev acc 0.8525, dev avg loss 0.362274, throughput 3.24308K wps
[Epoch 163 Batch 30/62] avg loss 0.000811651, throughput 3.31237K wps
[Epoch 163 Batch 60/62] avg loss 0.00101192, throughput 3.1687K wps
Begin Testing...
[Epoch 163] train avg loss 0.000908293, dev acc 0.8525, dev avg loss 0.364497, throughput 3.24518K wps
[Epoch 164 Batch 30/62] avg loss 0.000926236, throughput 3.2469K wps
[Epoch 164 Batch 60/62] avg loss 0.000841495, throughput 3.19902K wps
Begin Testing...
[Epoch 164] train avg loss 0.000884298, dev acc 0.8525, dev avg loss 0.363178, throughput 3.22941K wps
[Epoch 165 Batch 30/62] avg loss 0.000828212, throughput 3.28482K wps
[Epoch 165 Batch 60/62] avg loss 0.000887246, throughput 3.15949K wps
Begin Testing...
[Epoch 165] train avg loss 0.000867025, dev acc 0.8525, dev avg loss 0.364419, throughput 3.22727K wps
[Epoch 166 Batch 30/62] avg loss 0.000858765, throughput 3.24634K wps
[Epoch 166 Batch 60/62] avg loss 0.000853655, throughput 3.16338K wps
Begin Testing...
[Epoch 166] train avg loss 0.000872078, dev acc 0.8614, dev avg loss 0.366178, throughput 3.21105K wps
Observed Improvement.
Begin Testing...
[Epoch 167 Batch 30/62] avg loss 0.000893265, throughput 3.25842K wps
[Epoch 167 Batch 60/62] avg loss 0.000841033, throughput 3.16699K wps
Begin Testing...
[Epoch 167] train avg loss 0.00089001, dev acc 0.8496, dev avg loss 0.362757, throughput 3.21923K wps
[Epoch 168 Batch 30/62] avg loss 0.000893526, throughput 3.22937K wps
[Epoch 168 Batch 60/62] avg loss 0.000811727, throughput 3.17043K wps
Begin Testing...
[Epoch 168] train avg loss 0.000866096, dev acc 0.8525, dev avg loss 0.364662, throughput 3.2077K wps
[Epoch 169 Batch 30/62] avg loss 0.000762972, throughput 3.23643K wps
[Epoch 169 Batch 60/62] avg loss 0.000840177, throughput 3.20624K wps
Begin Testing...
[Epoch 169] train avg loss 0.000809548, dev acc 0.8555, dev avg loss 0.367179, throughput 3.22615K wps
[Epoch 170 Batch 30/62] avg loss 0.000848745, throughput 3.27075K wps
[Epoch 170 Batch 60/62] avg loss 0.000872331, throughput 3.15776K wps
Begin Testing...
[Epoch 170] train avg loss 0.000871088, dev acc 0.8496, dev avg loss 0.363509, throughput 3.2177K wps
[Epoch 171 Batch 30/62] avg loss 0.000924095, throughput 3.26182K wps
[Epoch 171 Batch 60/62] avg loss 0.000827016, throughput 3.22065K wps
Begin Testing...
[Epoch 171] train avg loss 0.000876043, dev acc 0.8496, dev avg loss 0.366665, throughput 3.24402K wps
[Epoch 172 Batch 30/62] avg loss 0.000762054, throughput 3.30346K wps
[Epoch 172 Batch 60/62] avg loss 0.000826597, throughput 3.20139K wps
Begin Testing...
[Epoch 172] train avg loss 0.000819491, dev acc 0.8555, dev avg loss 0.368751, throughput 3.25646K wps
[Epoch 173 Batch 30/62] avg loss 0.000780855, throughput 3.28425K wps
[Epoch 173 Batch 60/62] avg loss 0.000804358, throughput 3.2332K wps
Begin Testing...
[Epoch 173] train avg loss 0.000801935, dev acc 0.8496, dev avg loss 0.36613, throughput 3.26429K wps
[Epoch 174 Batch 30/62] avg loss 0.000772477, throughput 3.27901K wps
[Epoch 174 Batch 60/62] avg loss 0.000822016, throughput 3.2044K wps
Begin Testing...
[Epoch 174] train avg loss 0.000801927, dev acc 0.8496, dev avg loss 0.365231, throughput 3.24624K wps
[Epoch 175 Batch 30/62] avg loss 0.000782912, throughput 3.29465K wps
[Epoch 175 Batch 60/62] avg loss 0.000802249, throughput 3.17179K wps
Begin Testing...
[Epoch 175] train avg loss 0.000796684, dev acc 0.8525, dev avg loss 0.369778, throughput 3.23977K wps
[Epoch 176 Batch 30/62] avg loss 0.000730004, throughput 3.28859K wps
[Epoch 176 Batch 60/62] avg loss 0.000792819, throughput 3.15615K wps
Begin Testing...
[Epoch 176] train avg loss 0.000768224, dev acc 0.8496, dev avg loss 0.367212, throughput 3.22784K wps
[Epoch 177 Batch 30/62] avg loss 0.000704691, throughput 3.2587K wps
[Epoch 177 Batch 60/62] avg loss 0.000720614, throughput 3.14745K wps
Begin Testing...
[Epoch 177] train avg loss 0.000726958, dev acc 0.8496, dev avg loss 0.366812, throughput 3.20669K wps
[Epoch 178 Batch 30/62] avg loss 0.000752738, throughput 3.25078K wps
[Epoch 178 Batch 60/62] avg loss 0.000730851, throughput 3.16215K wps
Begin Testing...
[Epoch 178] train avg loss 0.000740893, dev acc 0.8496, dev avg loss 0.366603, throughput 3.21234K wps
[Epoch 179 Batch 30/62] avg loss 0.000805195, throughput 3.24581K wps
[Epoch 179 Batch 60/62] avg loss 0.000691005, throughput 3.18533K wps
Begin Testing...
[Epoch 179] train avg loss 0.000753781, dev acc 0.8466, dev avg loss 0.368301, throughput 3.2225K wps
[Epoch 180 Batch 30/62] avg loss 0.000707271, throughput 3.29628K wps
[Epoch 180 Batch 60/62] avg loss 0.000716589, throughput 3.17556K wps
Begin Testing...
[Epoch 180] train avg loss 0.000741804, dev acc 0.8466, dev avg loss 0.366026, throughput 3.24302K wps
[Epoch 181 Batch 30/62] avg loss 0.000760514, throughput 3.30422K wps
[Epoch 181 Batch 60/62] avg loss 0.000709762, throughput 3.16393K wps
Begin Testing...
[Epoch 181] train avg loss 0.000740446, dev acc 0.8496, dev avg loss 0.369916, throughput 3.23842K wps
[Epoch 182 Batch 30/62] avg loss 0.00067126, throughput 3.28963K wps
[Epoch 182 Batch 60/62] avg loss 0.000753842, throughput 3.21156K wps
Begin Testing...
[Epoch 182] train avg loss 0.00071693, dev acc 0.8525, dev avg loss 0.371235, throughput 3.25534K wps
[Epoch 183 Batch 30/62] avg loss 0.000744355, throughput 3.25474K wps
[Epoch 183 Batch 60/62] avg loss 0.000684918, throughput 3.19684K wps
Begin Testing...
[Epoch 183] train avg loss 0.000753494, dev acc 0.8496, dev avg loss 0.368382, throughput 3.23348K wps
[Epoch 184 Batch 30/62] avg loss 0.000664942, throughput 3.2752K wps
[Epoch 184 Batch 60/62] avg loss 0.000746042, throughput 3.2014K wps
Begin Testing...
[Epoch 184] train avg loss 0.000729022, dev acc 0.8466, dev avg loss 0.370134, throughput 3.24406K wps
[Epoch 185 Batch 30/62] avg loss 0.00074896, throughput 3.23302K wps
[Epoch 185 Batch 60/62] avg loss 0.000630405, throughput 3.20019K wps
Begin Testing...
[Epoch 185] train avg loss 0.000689942, dev acc 0.8466, dev avg loss 0.368589, throughput 3.22493K wps
[Epoch 186 Batch 30/62] avg loss 0.000770287, throughput 3.26222K wps
[Epoch 186 Batch 60/62] avg loss 0.000700508, throughput 3.15734K wps
Begin Testing...
[Epoch 186] train avg loss 0.000754963, dev acc 0.8643, dev avg loss 0.372772, throughput 3.21487K wps
Observed Improvement.
Begin Testing...
[Epoch 187 Batch 30/62] avg loss 0.000684554, throughput 3.28075K wps
[Epoch 187 Batch 60/62] avg loss 0.000656111, throughput 3.15261K wps
Begin Testing...
[Epoch 187] train avg loss 0.000680338, dev acc 0.8496, dev avg loss 0.371034, throughput 3.22162K wps
[Epoch 188 Batch 30/62] avg loss 0.000696778, throughput 3.2445K wps
[Epoch 188 Batch 60/62] avg loss 0.000724919, throughput 3.14662K wps
Begin Testing...
[Epoch 188] train avg loss 0.000710975, dev acc 0.8466, dev avg loss 0.369949, throughput 3.19925K wps
[Epoch 189 Batch 30/62] avg loss 0.000676856, throughput 3.25865K wps
[Epoch 189 Batch 60/62] avg loss 0.000719322, throughput 3.15667K wps
Begin Testing...
[Epoch 189] train avg loss 0.000712093, dev acc 0.8555, dev avg loss 0.373868, throughput 3.21588K wps
[Epoch 190 Batch 30/62] avg loss 0.000654035, throughput 3.24994K wps
[Epoch 190 Batch 60/62] avg loss 0.000680048, throughput 3.19231K wps
Begin Testing...
[Epoch 190] train avg loss 0.000669674, dev acc 0.8525, dev avg loss 0.371677, throughput 3.2296K wps
[Epoch 191 Batch 30/62] avg loss 0.000660261, throughput 3.29259K wps
[Epoch 191 Batch 60/62] avg loss 0.000681169, throughput 3.17343K wps
Begin Testing...
[Epoch 191] train avg loss 0.000685732, dev acc 0.8496, dev avg loss 0.37145, throughput 3.23856K wps
[Epoch 192 Batch 30/62] avg loss 0.000621512, throughput 3.27386K wps
[Epoch 192 Batch 60/62] avg loss 0.000653816, throughput 3.20124K wps
Begin Testing...
[Epoch 192] train avg loss 0.00065318, dev acc 0.8496, dev avg loss 0.369903, throughput 3.24358K wps
[Epoch 193 Batch 30/62] avg loss 0.00060587, throughput 3.25918K wps
[Epoch 193 Batch 60/62] avg loss 0.000696927, throughput 3.21826K wps
Begin Testing...
[Epoch 193] train avg loss 0.000659364, dev acc 0.8555, dev avg loss 0.374112, throughput 3.24553K wps
[Epoch 194 Batch 30/62] avg loss 0.000601445, throughput 3.2646K wps
[Epoch 194 Batch 60/62] avg loss 0.000643684, throughput 3.17982K wps
Begin Testing...
[Epoch 194] train avg loss 0.000635861, dev acc 0.8466, dev avg loss 0.371188, throughput 3.22993K wps
[Epoch 195 Batch 30/62] avg loss 0.000651123, throughput 3.26188K wps
[Epoch 195 Batch 60/62] avg loss 0.000701397, throughput 3.18107K wps
Begin Testing...
[Epoch 195] train avg loss 0.000680714, dev acc 0.8466, dev avg loss 0.372137, throughput 3.2273K wps
[Epoch 196 Batch 30/62] avg loss 0.000655309, throughput 3.26972K wps
[Epoch 196 Batch 60/62] avg loss 0.000648536, throughput 3.17868K wps
Begin Testing...
[Epoch 196] train avg loss 0.000652246, dev acc 0.8437, dev avg loss 0.371401, throughput 3.23111K wps
[Epoch 197 Batch 30/62] avg loss 0.000725082, throughput 3.29917K wps
[Epoch 197 Batch 60/62] avg loss 0.000610456, throughput 3.16136K wps
Begin Testing...
[Epoch 197] train avg loss 0.000675281, dev acc 0.8555, dev avg loss 0.375873, throughput 3.23395K wps
[Epoch 198 Batch 30/62] avg loss 0.000674839, throughput 3.27279K wps
[Epoch 198 Batch 60/62] avg loss 0.000630405, throughput 3.19936K wps
Begin Testing...
[Epoch 198] train avg loss 0.00067006, dev acc 0.8496, dev avg loss 0.371975, throughput 3.2423K wps
[Epoch 199 Batch 30/62] avg loss 0.000664242, throughput 3.26787K wps
[Epoch 199 Batch 60/62] avg loss 0.000599452, throughput 3.15763K wps
Begin Testing...
[Epoch 199] train avg loss 0.000639649, dev acc 0.8437, dev avg loss 0.373857, throughput 3.21819K wps
Test loss 0.416966, test acc 0.8276
Total time cost 421.09s
K-fold cross valid avg acc 0.8331564986737401