{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 824, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00486470051687443, "grad_norm": 7.871616740292343, "learning_rate": 0.0, "loss": 1.098, "step": 1 }, { "epoch": 0.00972940103374886, "grad_norm": 7.799603527969922, "learning_rate": 1.204819277108434e-07, "loss": 1.0752, "step": 2 }, { "epoch": 0.01459410155062329, "grad_norm": 7.423748979018268, "learning_rate": 2.409638554216868e-07, "loss": 1.0455, "step": 3 }, { "epoch": 0.01945880206749772, "grad_norm": 7.564632174548383, "learning_rate": 3.614457831325301e-07, "loss": 1.0596, "step": 4 }, { "epoch": 0.024323502584372148, "grad_norm": 7.9915263324758445, "learning_rate": 4.819277108433736e-07, "loss": 1.0663, "step": 5 }, { "epoch": 0.02918820310124658, "grad_norm": 7.454492919123446, "learning_rate": 6.024096385542169e-07, "loss": 1.0698, "step": 6 }, { "epoch": 0.03405290361812101, "grad_norm": 7.6426494930377675, "learning_rate": 7.228915662650602e-07, "loss": 1.0578, "step": 7 }, { "epoch": 0.03891760413499544, "grad_norm": 7.218028919786697, "learning_rate": 8.433734939759036e-07, "loss": 1.0742, "step": 8 }, { "epoch": 0.04378230465186987, "grad_norm": 6.916645064217657, "learning_rate": 9.638554216867472e-07, "loss": 1.0415, "step": 9 }, { "epoch": 0.048647005168744296, "grad_norm": 6.533862037369981, "learning_rate": 1.0843373493975905e-06, "loss": 1.081, "step": 10 }, { "epoch": 0.05351170568561873, "grad_norm": 5.907831319110147, "learning_rate": 1.2048192771084338e-06, "loss": 1.0091, "step": 11 }, { "epoch": 0.05837640620249316, "grad_norm": 5.910899760943595, "learning_rate": 1.3253012048192773e-06, "loss": 1.0196, "step": 12 }, { "epoch": 0.06324110671936758, "grad_norm": 3.9072512975667073, "learning_rate": 1.4457831325301204e-06, "loss": 0.9819, "step": 13 }, { "epoch": 0.06810580723624202, "grad_norm": 3.6210194450936655, "learning_rate": 1.566265060240964e-06, "loss": 0.9871, "step": 14 }, { "epoch": 0.07297050775311645, "grad_norm": 3.385650180354361, "learning_rate": 1.6867469879518073e-06, "loss": 0.9592, "step": 15 }, { "epoch": 0.07783520826999088, "grad_norm": 3.087496999583691, "learning_rate": 1.8072289156626508e-06, "loss": 0.95, "step": 16 }, { "epoch": 0.08269990878686531, "grad_norm": 2.762465012422017, "learning_rate": 1.9277108433734943e-06, "loss": 0.9221, "step": 17 }, { "epoch": 0.08756460930373974, "grad_norm": 2.168579083802785, "learning_rate": 2.0481927710843377e-06, "loss": 0.8951, "step": 18 }, { "epoch": 0.09242930982061417, "grad_norm": 2.3188100119997603, "learning_rate": 2.168674698795181e-06, "loss": 0.9424, "step": 19 }, { "epoch": 0.09729401033748859, "grad_norm": 1.9097827418782145, "learning_rate": 2.2891566265060243e-06, "loss": 0.8866, "step": 20 }, { "epoch": 0.10215871085436302, "grad_norm": 1.8810911464259783, "learning_rate": 2.4096385542168676e-06, "loss": 0.9143, "step": 21 }, { "epoch": 0.10702341137123746, "grad_norm": 1.7690971431658378, "learning_rate": 2.530120481927711e-06, "loss": 0.9122, "step": 22 }, { "epoch": 0.11188811188811189, "grad_norm": 1.4875309096817997, "learning_rate": 2.6506024096385547e-06, "loss": 0.8947, "step": 23 }, { "epoch": 0.11675281240498632, "grad_norm": 1.2588461642135405, "learning_rate": 2.771084337349398e-06, "loss": 0.8806, "step": 24 }, { "epoch": 0.12161751292186075, "grad_norm": 1.2718827356211329, "learning_rate": 2.891566265060241e-06, "loss": 0.8649, "step": 25 }, { "epoch": 0.12648221343873517, "grad_norm": 1.3111246689174925, "learning_rate": 3.012048192771085e-06, "loss": 0.8469, "step": 26 }, { "epoch": 0.1313469139556096, "grad_norm": 1.23713732205432, "learning_rate": 3.132530120481928e-06, "loss": 0.8466, "step": 27 }, { "epoch": 0.13621161447248403, "grad_norm": 1.0896143312290152, "learning_rate": 3.2530120481927713e-06, "loss": 0.8125, "step": 28 }, { "epoch": 0.14107631498935846, "grad_norm": 0.984807252420441, "learning_rate": 3.3734939759036146e-06, "loss": 0.8017, "step": 29 }, { "epoch": 0.1459410155062329, "grad_norm": 0.808677185338004, "learning_rate": 3.4939759036144583e-06, "loss": 0.8006, "step": 30 }, { "epoch": 0.15080571602310733, "grad_norm": 0.7511476567807504, "learning_rate": 3.6144578313253016e-06, "loss": 0.8126, "step": 31 }, { "epoch": 0.15567041653998176, "grad_norm": 0.6784023795349318, "learning_rate": 3.7349397590361445e-06, "loss": 0.8152, "step": 32 }, { "epoch": 0.1605351170568562, "grad_norm": 0.687290952692141, "learning_rate": 3.855421686746989e-06, "loss": 0.7862, "step": 33 }, { "epoch": 0.16539981757373062, "grad_norm": 0.7497785629029042, "learning_rate": 3.975903614457832e-06, "loss": 0.7801, "step": 34 }, { "epoch": 0.17026451809060505, "grad_norm": 0.7300038686169489, "learning_rate": 4.096385542168675e-06, "loss": 0.817, "step": 35 }, { "epoch": 0.1751292186074795, "grad_norm": 0.6609922528040404, "learning_rate": 4.216867469879519e-06, "loss": 0.7617, "step": 36 }, { "epoch": 0.17999391912435392, "grad_norm": 0.614697070133524, "learning_rate": 4.337349397590362e-06, "loss": 0.7619, "step": 37 }, { "epoch": 0.18485861964122835, "grad_norm": 0.6077536528599503, "learning_rate": 4.457831325301205e-06, "loss": 0.7479, "step": 38 }, { "epoch": 0.18972332015810275, "grad_norm": 0.5860762533393374, "learning_rate": 4.578313253012049e-06, "loss": 0.7454, "step": 39 }, { "epoch": 0.19458802067497719, "grad_norm": 0.5773793355854958, "learning_rate": 4.698795180722892e-06, "loss": 0.7523, "step": 40 }, { "epoch": 0.19945272119185162, "grad_norm": 0.5542277512570439, "learning_rate": 4.819277108433735e-06, "loss": 0.7409, "step": 41 }, { "epoch": 0.20431742170872605, "grad_norm": 0.5237956233348399, "learning_rate": 4.939759036144578e-06, "loss": 0.7243, "step": 42 }, { "epoch": 0.20918212222560048, "grad_norm": 0.4787904640164728, "learning_rate": 5.060240963855422e-06, "loss": 0.7402, "step": 43 }, { "epoch": 0.2140468227424749, "grad_norm": 0.45408220171968083, "learning_rate": 5.180722891566266e-06, "loss": 0.7396, "step": 44 }, { "epoch": 0.21891152325934934, "grad_norm": 0.40479505304377766, "learning_rate": 5.301204819277109e-06, "loss": 0.7238, "step": 45 }, { "epoch": 0.22377622377622378, "grad_norm": 0.41220220446447914, "learning_rate": 5.421686746987952e-06, "loss": 0.7244, "step": 46 }, { "epoch": 0.2286409242930982, "grad_norm": 0.4604658158205623, "learning_rate": 5.542168674698796e-06, "loss": 0.7147, "step": 47 }, { "epoch": 0.23350562480997264, "grad_norm": 0.4115568367425201, "learning_rate": 5.66265060240964e-06, "loss": 0.7047, "step": 48 }, { "epoch": 0.23837032532684707, "grad_norm": 0.42372985871674096, "learning_rate": 5.783132530120482e-06, "loss": 0.7156, "step": 49 }, { "epoch": 0.2432350258437215, "grad_norm": 0.38489101084563504, "learning_rate": 5.9036144578313255e-06, "loss": 0.6983, "step": 50 }, { "epoch": 0.24809972636059593, "grad_norm": 0.3780162411545877, "learning_rate": 6.02409638554217e-06, "loss": 0.6989, "step": 51 }, { "epoch": 0.25296442687747034, "grad_norm": 0.3709017650876072, "learning_rate": 6.144578313253012e-06, "loss": 0.7309, "step": 52 }, { "epoch": 0.25782912739434477, "grad_norm": 0.3623310095010558, "learning_rate": 6.265060240963856e-06, "loss": 0.6957, "step": 53 }, { "epoch": 0.2626938279112192, "grad_norm": 0.38444067769427515, "learning_rate": 6.385542168674699e-06, "loss": 0.7156, "step": 54 }, { "epoch": 0.26755852842809363, "grad_norm": 0.37118023126197947, "learning_rate": 6.5060240963855425e-06, "loss": 0.7272, "step": 55 }, { "epoch": 0.27242322894496807, "grad_norm": 0.37104279152511443, "learning_rate": 6.626506024096386e-06, "loss": 0.6986, "step": 56 }, { "epoch": 0.2772879294618425, "grad_norm": 0.3428943633484335, "learning_rate": 6.746987951807229e-06, "loss": 0.6925, "step": 57 }, { "epoch": 0.28215262997871693, "grad_norm": 0.33413814452617036, "learning_rate": 6.867469879518073e-06, "loss": 0.6746, "step": 58 }, { "epoch": 0.28701733049559136, "grad_norm": 0.3908432972867295, "learning_rate": 6.987951807228917e-06, "loss": 0.6751, "step": 59 }, { "epoch": 0.2918820310124658, "grad_norm": 0.37944860090816573, "learning_rate": 7.1084337349397595e-06, "loss": 0.6925, "step": 60 }, { "epoch": 0.2967467315293402, "grad_norm": 0.32522149657437316, "learning_rate": 7.228915662650603e-06, "loss": 0.6892, "step": 61 }, { "epoch": 0.30161143204621466, "grad_norm": 0.3340974817250857, "learning_rate": 7.349397590361447e-06, "loss": 0.6879, "step": 62 }, { "epoch": 0.3064761325630891, "grad_norm": 0.3413822984437306, "learning_rate": 7.469879518072289e-06, "loss": 0.6598, "step": 63 }, { "epoch": 0.3113408330799635, "grad_norm": 0.3002390480902653, "learning_rate": 7.590361445783133e-06, "loss": 0.6695, "step": 64 }, { "epoch": 0.31620553359683795, "grad_norm": 0.28980952917352437, "learning_rate": 7.710843373493977e-06, "loss": 0.6839, "step": 65 }, { "epoch": 0.3210702341137124, "grad_norm": 0.3260429942196874, "learning_rate": 7.83132530120482e-06, "loss": 0.6669, "step": 66 }, { "epoch": 0.3259349346305868, "grad_norm": 0.30808718354811904, "learning_rate": 7.951807228915663e-06, "loss": 0.6666, "step": 67 }, { "epoch": 0.33079963514746125, "grad_norm": 0.33148289433783834, "learning_rate": 8.072289156626508e-06, "loss": 0.7033, "step": 68 }, { "epoch": 0.3356643356643357, "grad_norm": 0.3189299211341105, "learning_rate": 8.19277108433735e-06, "loss": 0.7107, "step": 69 }, { "epoch": 0.3405290361812101, "grad_norm": 0.2962290263438809, "learning_rate": 8.313253012048194e-06, "loss": 0.6713, "step": 70 }, { "epoch": 0.34539373669808454, "grad_norm": 0.3021392117861154, "learning_rate": 8.433734939759038e-06, "loss": 0.6544, "step": 71 }, { "epoch": 0.350258437214959, "grad_norm": 0.323233089263355, "learning_rate": 8.55421686746988e-06, "loss": 0.6748, "step": 72 }, { "epoch": 0.3551231377318334, "grad_norm": 0.33117087054539995, "learning_rate": 8.674698795180724e-06, "loss": 0.6637, "step": 73 }, { "epoch": 0.35998783824870784, "grad_norm": 0.3134253526382447, "learning_rate": 8.795180722891567e-06, "loss": 0.6717, "step": 74 }, { "epoch": 0.36485253876558227, "grad_norm": 0.30226586352586127, "learning_rate": 8.91566265060241e-06, "loss": 0.6592, "step": 75 }, { "epoch": 0.3697172392824567, "grad_norm": 0.3328065720875336, "learning_rate": 9.036144578313254e-06, "loss": 0.6478, "step": 76 }, { "epoch": 0.3745819397993311, "grad_norm": 0.2847681287612717, "learning_rate": 9.156626506024097e-06, "loss": 0.6695, "step": 77 }, { "epoch": 0.3794466403162055, "grad_norm": 0.3397213424189545, "learning_rate": 9.27710843373494e-06, "loss": 0.694, "step": 78 }, { "epoch": 0.38431134083307994, "grad_norm": 0.33375278029082783, "learning_rate": 9.397590361445785e-06, "loss": 0.6842, "step": 79 }, { "epoch": 0.38917604134995437, "grad_norm": 0.2853578407471598, "learning_rate": 9.518072289156628e-06, "loss": 0.6735, "step": 80 }, { "epoch": 0.3940407418668288, "grad_norm": 0.3074938971217896, "learning_rate": 9.63855421686747e-06, "loss": 0.7076, "step": 81 }, { "epoch": 0.39890544238370323, "grad_norm": 0.31873594402724836, "learning_rate": 9.759036144578315e-06, "loss": 0.6481, "step": 82 }, { "epoch": 0.40377014290057767, "grad_norm": 0.28397571344041816, "learning_rate": 9.879518072289156e-06, "loss": 0.6628, "step": 83 }, { "epoch": 0.4086348434174521, "grad_norm": 0.3231744717226557, "learning_rate": 1e-05, "loss": 0.662, "step": 84 }, { "epoch": 0.41349954393432653, "grad_norm": 0.3064500442482252, "learning_rate": 9.99995506314361e-06, "loss": 0.6602, "step": 85 }, { "epoch": 0.41836424445120096, "grad_norm": 0.3230100691154973, "learning_rate": 9.99982025338217e-06, "loss": 0.6882, "step": 86 }, { "epoch": 0.4232289449680754, "grad_norm": 0.2800126589618668, "learning_rate": 9.999595573138845e-06, "loss": 0.6329, "step": 87 }, { "epoch": 0.4280936454849498, "grad_norm": 0.31430268544090867, "learning_rate": 9.99928102645221e-06, "loss": 0.6571, "step": 88 }, { "epoch": 0.43295834600182426, "grad_norm": 0.3036046109153711, "learning_rate": 9.99887661897616e-06, "loss": 0.6385, "step": 89 }, { "epoch": 0.4378230465186987, "grad_norm": 0.32487136299918457, "learning_rate": 9.99838235797981e-06, "loss": 0.6674, "step": 90 }, { "epoch": 0.4426877470355731, "grad_norm": 0.3031998931969764, "learning_rate": 9.997798252347382e-06, "loss": 0.6045, "step": 91 }, { "epoch": 0.44755244755244755, "grad_norm": 0.3038369920366118, "learning_rate": 9.99712431257802e-06, "loss": 0.6292, "step": 92 }, { "epoch": 0.452417148069322, "grad_norm": 0.3329356283073232, "learning_rate": 9.996360550785619e-06, "loss": 0.6754, "step": 93 }, { "epoch": 0.4572818485861964, "grad_norm": 0.31567669911748764, "learning_rate": 9.9955069806986e-06, "loss": 0.6515, "step": 94 }, { "epoch": 0.46214654910307085, "grad_norm": 0.32833013838410197, "learning_rate": 9.994563617659665e-06, "loss": 0.6487, "step": 95 }, { "epoch": 0.4670112496199453, "grad_norm": 0.2940284322979485, "learning_rate": 9.993530478625524e-06, "loss": 0.6463, "step": 96 }, { "epoch": 0.4718759501368197, "grad_norm": 0.2893495605450668, "learning_rate": 9.992407582166582e-06, "loss": 0.6144, "step": 97 }, { "epoch": 0.47674065065369414, "grad_norm": 0.35388954247988424, "learning_rate": 9.991194948466615e-06, "loss": 0.6583, "step": 98 }, { "epoch": 0.4816053511705686, "grad_norm": 0.3255958183582087, "learning_rate": 9.989892599322404e-06, "loss": 0.6366, "step": 99 }, { "epoch": 0.486470051687443, "grad_norm": 0.3451092306603101, "learning_rate": 9.988500558143337e-06, "loss": 0.6683, "step": 100 }, { "epoch": 0.49133475220431744, "grad_norm": 0.30173242350276314, "learning_rate": 9.987018849950996e-06, "loss": 0.6542, "step": 101 }, { "epoch": 0.49619945272119187, "grad_norm": 0.31734024915060194, "learning_rate": 9.985447501378706e-06, "loss": 0.6464, "step": 102 }, { "epoch": 0.5010641532380663, "grad_norm": 0.3340204530720514, "learning_rate": 9.983786540671052e-06, "loss": 0.6409, "step": 103 }, { "epoch": 0.5059288537549407, "grad_norm": 0.35953177534893943, "learning_rate": 9.982035997683372e-06, "loss": 0.6399, "step": 104 }, { "epoch": 0.5107935542718152, "grad_norm": 0.28766789678290994, "learning_rate": 9.980195903881231e-06, "loss": 0.6419, "step": 105 }, { "epoch": 0.5156582547886895, "grad_norm": 0.3316301588623575, "learning_rate": 9.978266292339838e-06, "loss": 0.6561, "step": 106 }, { "epoch": 0.520522955305564, "grad_norm": 0.28194758329871084, "learning_rate": 9.976247197743465e-06, "loss": 0.6362, "step": 107 }, { "epoch": 0.5253876558224384, "grad_norm": 0.3131499006180912, "learning_rate": 9.974138656384815e-06, "loss": 0.6346, "step": 108 }, { "epoch": 0.5302523563393129, "grad_norm": 0.30900576616616077, "learning_rate": 9.97194070616438e-06, "loss": 0.6398, "step": 109 }, { "epoch": 0.5351170568561873, "grad_norm": 0.30165318020075954, "learning_rate": 9.969653386589749e-06, "loss": 0.6455, "step": 110 }, { "epoch": 0.5399817573730618, "grad_norm": 0.29148738560695625, "learning_rate": 9.967276738774897e-06, "loss": 0.6372, "step": 111 }, { "epoch": 0.5448464578899361, "grad_norm": 0.29937833276487447, "learning_rate": 9.964810805439464e-06, "loss": 0.6495, "step": 112 }, { "epoch": 0.5497111584068106, "grad_norm": 0.3215648587156084, "learning_rate": 9.962255630907964e-06, "loss": 0.6604, "step": 113 }, { "epoch": 0.554575858923685, "grad_norm": 0.3016549120115337, "learning_rate": 9.959611261108999e-06, "loss": 0.6268, "step": 114 }, { "epoch": 0.5594405594405595, "grad_norm": 0.32418813186220485, "learning_rate": 9.956877743574437e-06, "loss": 0.657, "step": 115 }, { "epoch": 0.5643052599574339, "grad_norm": 0.2773971918035161, "learning_rate": 9.954055127438554e-06, "loss": 0.6326, "step": 116 }, { "epoch": 0.5691699604743083, "grad_norm": 0.30671381432141426, "learning_rate": 9.951143463437145e-06, "loss": 0.6171, "step": 117 }, { "epoch": 0.5740346609911827, "grad_norm": 0.294221207297223, "learning_rate": 9.948142803906623e-06, "loss": 0.6416, "step": 118 }, { "epoch": 0.5788993615080572, "grad_norm": 0.3309169613334198, "learning_rate": 9.94505320278307e-06, "loss": 0.6509, "step": 119 }, { "epoch": 0.5837640620249316, "grad_norm": 0.31330113566177165, "learning_rate": 9.94187471560127e-06, "loss": 0.6386, "step": 120 }, { "epoch": 0.5886287625418061, "grad_norm": 0.32126509470942055, "learning_rate": 9.938607399493714e-06, "loss": 0.6398, "step": 121 }, { "epoch": 0.5934934630586804, "grad_norm": 0.31134400279374636, "learning_rate": 9.935251313189564e-06, "loss": 0.6712, "step": 122 }, { "epoch": 0.5983581635755548, "grad_norm": 0.3248486723103563, "learning_rate": 9.931806517013612e-06, "loss": 0.6457, "step": 123 }, { "epoch": 0.6032228640924293, "grad_norm": 0.3139884948675962, "learning_rate": 9.92827307288518e-06, "loss": 0.6619, "step": 124 }, { "epoch": 0.6080875646093037, "grad_norm": 0.3072037010173652, "learning_rate": 9.924651044317017e-06, "loss": 0.6303, "step": 125 }, { "epoch": 0.6129522651261782, "grad_norm": 0.313420051996835, "learning_rate": 9.920940496414153e-06, "loss": 0.6276, "step": 126 }, { "epoch": 0.6178169656430526, "grad_norm": 0.33102586835036, "learning_rate": 9.917141495872733e-06, "loss": 0.6373, "step": 127 }, { "epoch": 0.622681666159927, "grad_norm": 0.3293019683736833, "learning_rate": 9.913254110978812e-06, "loss": 0.6494, "step": 128 }, { "epoch": 0.6275463666768014, "grad_norm": 0.3201254836551897, "learning_rate": 9.909278411607134e-06, "loss": 0.6393, "step": 129 }, { "epoch": 0.6324110671936759, "grad_norm": 0.3029967295356934, "learning_rate": 9.90521446921987e-06, "loss": 0.609, "step": 130 }, { "epoch": 0.6372757677105503, "grad_norm": 0.2938531531316102, "learning_rate": 9.90106235686534e-06, "loss": 0.6486, "step": 131 }, { "epoch": 0.6421404682274248, "grad_norm": 0.3305524191163304, "learning_rate": 9.896822149176695e-06, "loss": 0.6556, "step": 132 }, { "epoch": 0.6470051687442991, "grad_norm": 0.31564384472194085, "learning_rate": 9.892493922370575e-06, "loss": 0.6393, "step": 133 }, { "epoch": 0.6518698692611736, "grad_norm": 0.34096226592518836, "learning_rate": 9.888077754245741e-06, "loss": 0.647, "step": 134 }, { "epoch": 0.656734569778048, "grad_norm": 0.3292830699158915, "learning_rate": 9.883573724181683e-06, "loss": 0.6641, "step": 135 }, { "epoch": 0.6615992702949225, "grad_norm": 0.3179497250191383, "learning_rate": 9.878981913137178e-06, "loss": 0.6357, "step": 136 }, { "epoch": 0.6664639708117969, "grad_norm": 0.29352043038957887, "learning_rate": 9.87430240364885e-06, "loss": 0.6414, "step": 137 }, { "epoch": 0.6713286713286714, "grad_norm": 0.3195944873583672, "learning_rate": 9.869535279829674e-06, "loss": 0.6373, "step": 138 }, { "epoch": 0.6761933718455457, "grad_norm": 0.31585842341884124, "learning_rate": 9.864680627367476e-06, "loss": 0.6444, "step": 139 }, { "epoch": 0.6810580723624202, "grad_norm": 0.3122950909270544, "learning_rate": 9.859738533523384e-06, "loss": 0.6342, "step": 140 }, { "epoch": 0.6859227728792946, "grad_norm": 0.3066082108786697, "learning_rate": 9.854709087130261e-06, "loss": 0.6343, "step": 141 }, { "epoch": 0.6907874733961691, "grad_norm": 0.31549766123110123, "learning_rate": 9.849592378591113e-06, "loss": 0.6535, "step": 142 }, { "epoch": 0.6956521739130435, "grad_norm": 0.2904073187209748, "learning_rate": 9.844388499877457e-06, "loss": 0.6356, "step": 143 }, { "epoch": 0.700516874429918, "grad_norm": 0.29647098758166235, "learning_rate": 9.839097544527674e-06, "loss": 0.6205, "step": 144 }, { "epoch": 0.7053815749467923, "grad_norm": 0.31575637182121563, "learning_rate": 9.833719607645325e-06, "loss": 0.6192, "step": 145 }, { "epoch": 0.7102462754636668, "grad_norm": 0.333422147334672, "learning_rate": 9.82825478589744e-06, "loss": 0.637, "step": 146 }, { "epoch": 0.7151109759805412, "grad_norm": 0.28378992515332846, "learning_rate": 9.822703177512783e-06, "loss": 0.6507, "step": 147 }, { "epoch": 0.7199756764974157, "grad_norm": 0.3248811786859313, "learning_rate": 9.817064882280085e-06, "loss": 0.6221, "step": 148 }, { "epoch": 0.72484037701429, "grad_norm": 0.31059374589112126, "learning_rate": 9.811340001546252e-06, "loss": 0.6237, "step": 149 }, { "epoch": 0.7297050775311645, "grad_norm": 0.2831511442896517, "learning_rate": 9.805528638214543e-06, "loss": 0.6327, "step": 150 }, { "epoch": 0.7345697780480389, "grad_norm": 0.31145307371556186, "learning_rate": 9.799630896742716e-06, "loss": 0.6284, "step": 151 }, { "epoch": 0.7394344785649134, "grad_norm": 0.3026563219956784, "learning_rate": 9.793646883141155e-06, "loss": 0.6154, "step": 152 }, { "epoch": 0.7442991790817878, "grad_norm": 0.2941879445857105, "learning_rate": 9.787576704970965e-06, "loss": 0.6227, "step": 153 }, { "epoch": 0.7491638795986622, "grad_norm": 0.2783423864355946, "learning_rate": 9.781420471342035e-06, "loss": 0.6314, "step": 154 }, { "epoch": 0.7540285801155366, "grad_norm": 0.32618411754942406, "learning_rate": 9.77517829291108e-06, "loss": 0.6318, "step": 155 }, { "epoch": 0.758893280632411, "grad_norm": 0.3202205598622637, "learning_rate": 9.768850281879651e-06, "loss": 0.6448, "step": 156 }, { "epoch": 0.7637579811492855, "grad_norm": 0.3067835918016461, "learning_rate": 9.762436551992117e-06, "loss": 0.6343, "step": 157 }, { "epoch": 0.7686226816661599, "grad_norm": 0.28662018300175146, "learning_rate": 9.755937218533622e-06, "loss": 0.628, "step": 158 }, { "epoch": 0.7734873821830344, "grad_norm": 0.2959364635896564, "learning_rate": 9.74935239832801e-06, "loss": 0.6215, "step": 159 }, { "epoch": 0.7783520826999087, "grad_norm": 0.33661418227611106, "learning_rate": 9.742682209735727e-06, "loss": 0.6373, "step": 160 }, { "epoch": 0.7832167832167832, "grad_norm": 0.31025228760207435, "learning_rate": 9.735926772651703e-06, "loss": 0.6311, "step": 161 }, { "epoch": 0.7880814837336576, "grad_norm": 0.29469085430130315, "learning_rate": 9.729086208503174e-06, "loss": 0.6424, "step": 162 }, { "epoch": 0.7929461842505321, "grad_norm": 0.2903443690677671, "learning_rate": 9.722160640247523e-06, "loss": 0.5911, "step": 163 }, { "epoch": 0.7978108847674065, "grad_norm": 0.3415565105091893, "learning_rate": 9.715150192370054e-06, "loss": 0.6413, "step": 164 }, { "epoch": 0.802675585284281, "grad_norm": 0.2747763530864899, "learning_rate": 9.708054990881763e-06, "loss": 0.6179, "step": 165 }, { "epoch": 0.8075402858011553, "grad_norm": 0.27732863370117194, "learning_rate": 9.700875163317072e-06, "loss": 0.6237, "step": 166 }, { "epoch": 0.8124049863180298, "grad_norm": 0.2783090216099878, "learning_rate": 9.693610838731532e-06, "loss": 0.6079, "step": 167 }, { "epoch": 0.8172696868349042, "grad_norm": 0.30137662776658314, "learning_rate": 9.686262147699507e-06, "loss": 0.6257, "step": 168 }, { "epoch": 0.8221343873517787, "grad_norm": 0.2938092491968976, "learning_rate": 9.678829222311827e-06, "loss": 0.6209, "step": 169 }, { "epoch": 0.8269990878686531, "grad_norm": 0.30850109121695873, "learning_rate": 9.671312196173413e-06, "loss": 0.6409, "step": 170 }, { "epoch": 0.8318637883855275, "grad_norm": 0.31488336546549756, "learning_rate": 9.663711204400872e-06, "loss": 0.6232, "step": 171 }, { "epoch": 0.8367284889024019, "grad_norm": 0.33193878673588145, "learning_rate": 9.656026383620076e-06, "loss": 0.6353, "step": 172 }, { "epoch": 0.8415931894192764, "grad_norm": 0.3172330136868242, "learning_rate": 9.6482578719637e-06, "loss": 0.6433, "step": 173 }, { "epoch": 0.8464578899361508, "grad_norm": 0.30901889717151554, "learning_rate": 9.640405809068743e-06, "loss": 0.6336, "step": 174 }, { "epoch": 0.8513225904530253, "grad_norm": 0.30817037607544295, "learning_rate": 9.632470336074009e-06, "loss": 0.6284, "step": 175 }, { "epoch": 0.8561872909698997, "grad_norm": 0.31855238974367667, "learning_rate": 9.624451595617588e-06, "loss": 0.6222, "step": 176 }, { "epoch": 0.8610519914867741, "grad_norm": 0.3262552248783998, "learning_rate": 9.616349731834271e-06, "loss": 0.636, "step": 177 }, { "epoch": 0.8659166920036485, "grad_norm": 0.3143462631647167, "learning_rate": 9.608164890352977e-06, "loss": 0.6511, "step": 178 }, { "epoch": 0.870781392520523, "grad_norm": 0.30787306966695105, "learning_rate": 9.599897218294122e-06, "loss": 0.611, "step": 179 }, { "epoch": 0.8756460930373974, "grad_norm": 0.3222949877422363, "learning_rate": 9.591546864266983e-06, "loss": 0.6015, "step": 180 }, { "epoch": 0.8805107935542719, "grad_norm": 0.6468852925640117, "learning_rate": 9.583113978367026e-06, "loss": 0.6248, "step": 181 }, { "epoch": 0.8853754940711462, "grad_norm": 0.31834615934154936, "learning_rate": 9.574598712173202e-06, "loss": 0.6362, "step": 182 }, { "epoch": 0.8902401945880207, "grad_norm": 0.3353766921729296, "learning_rate": 9.56600121874523e-06, "loss": 0.627, "step": 183 }, { "epoch": 0.8951048951048951, "grad_norm": 0.3441156972393706, "learning_rate": 9.557321652620839e-06, "loss": 0.6395, "step": 184 }, { "epoch": 0.8999695956217695, "grad_norm": 0.31474912726146764, "learning_rate": 9.548560169812997e-06, "loss": 0.6329, "step": 185 }, { "epoch": 0.904834296138644, "grad_norm": 0.3073487937876131, "learning_rate": 9.539716927807102e-06, "loss": 0.6296, "step": 186 }, { "epoch": 0.9096989966555183, "grad_norm": 0.33226958000665824, "learning_rate": 9.530792085558151e-06, "loss": 0.6189, "step": 187 }, { "epoch": 0.9145636971723928, "grad_norm": 0.3380666322235001, "learning_rate": 9.521785803487888e-06, "loss": 0.6324, "step": 188 }, { "epoch": 0.9194283976892672, "grad_norm": 0.33075937757491486, "learning_rate": 9.512698243481914e-06, "loss": 0.6453, "step": 189 }, { "epoch": 0.9242930982061417, "grad_norm": 0.3034706255741723, "learning_rate": 9.50352956888678e-06, "loss": 0.6252, "step": 190 }, { "epoch": 0.9291577987230161, "grad_norm": 0.2934371993664979, "learning_rate": 9.49427994450705e-06, "loss": 0.6031, "step": 191 }, { "epoch": 0.9340224992398906, "grad_norm": 0.28402396567132315, "learning_rate": 9.484949536602343e-06, "loss": 0.6392, "step": 192 }, { "epoch": 0.9388871997567649, "grad_norm": 0.3257493963036653, "learning_rate": 9.47553851288434e-06, "loss": 0.6248, "step": 193 }, { "epoch": 0.9437519002736394, "grad_norm": 0.36609807315254334, "learning_rate": 9.466047042513767e-06, "loss": 0.6364, "step": 194 }, { "epoch": 0.9486166007905138, "grad_norm": 0.3135930799311896, "learning_rate": 9.45647529609736e-06, "loss": 0.6357, "step": 195 }, { "epoch": 0.9534813013073883, "grad_norm": 0.282534058839446, "learning_rate": 9.4468234456848e-06, "loss": 0.6447, "step": 196 }, { "epoch": 0.9583460018242627, "grad_norm": 0.30039550961649686, "learning_rate": 9.437091664765611e-06, "loss": 0.5999, "step": 197 }, { "epoch": 0.9632107023411371, "grad_norm": 0.2983505184946651, "learning_rate": 9.427280128266049e-06, "loss": 0.6239, "step": 198 }, { "epoch": 0.9680754028580115, "grad_norm": 0.32267636708049524, "learning_rate": 9.41738901254596e-06, "loss": 0.6371, "step": 199 }, { "epoch": 0.972940103374886, "grad_norm": 0.3161637479255845, "learning_rate": 9.4074184953956e-06, "loss": 0.6136, "step": 200 }, { "epoch": 0.9778048038917604, "grad_norm": 0.28216722909182457, "learning_rate": 9.397368756032445e-06, "loss": 0.6263, "step": 201 }, { "epoch": 0.9826695044086349, "grad_norm": 0.29543173068975137, "learning_rate": 9.38723997509798e-06, "loss": 0.6209, "step": 202 }, { "epoch": 0.9875342049255093, "grad_norm": 0.3148459636663263, "learning_rate": 9.37703233465443e-06, "loss": 0.6302, "step": 203 }, { "epoch": 0.9923989054423837, "grad_norm": 0.2985230574806046, "learning_rate": 9.366746018181503e-06, "loss": 0.6341, "step": 204 }, { "epoch": 0.9972636059592581, "grad_norm": 0.2887080510422836, "learning_rate": 9.356381210573092e-06, "loss": 0.6035, "step": 205 }, { "epoch": 1.0, "grad_norm": 0.39122078027568374, "learning_rate": 9.345938098133946e-06, "loss": 0.6018, "step": 206 }, { "epoch": 1.0048647005168745, "grad_norm": 0.313252516190162, "learning_rate": 9.33541686857632e-06, "loss": 0.5895, "step": 207 }, { "epoch": 1.0097294010337488, "grad_norm": 0.3874020915060344, "learning_rate": 9.324817711016609e-06, "loss": 0.5999, "step": 208 }, { "epoch": 1.0145941015506232, "grad_norm": 0.294346619405537, "learning_rate": 9.31414081597194e-06, "loss": 0.5972, "step": 209 }, { "epoch": 1.0194588020674977, "grad_norm": 0.3224735476280501, "learning_rate": 9.303386375356752e-06, "loss": 0.5842, "step": 210 }, { "epoch": 1.0243235025843722, "grad_norm": 0.3274928088607993, "learning_rate": 9.292554582479349e-06, "loss": 0.5986, "step": 211 }, { "epoch": 1.0291882031012465, "grad_norm": 0.33949920305788156, "learning_rate": 9.281645632038417e-06, "loss": 0.6205, "step": 212 }, { "epoch": 1.034052903618121, "grad_norm": 0.29249693190899456, "learning_rate": 9.270659720119533e-06, "loss": 0.596, "step": 213 }, { "epoch": 1.0389176041349955, "grad_norm": 0.33036073695433377, "learning_rate": 9.259597044191635e-06, "loss": 0.5965, "step": 214 }, { "epoch": 1.04378230465187, "grad_norm": 0.31787930137308906, "learning_rate": 9.248457803103476e-06, "loss": 0.5566, "step": 215 }, { "epoch": 1.0486470051687442, "grad_norm": 0.3683668799990001, "learning_rate": 9.237242197080045e-06, "loss": 0.595, "step": 216 }, { "epoch": 1.0535117056856187, "grad_norm": 0.3199128394432867, "learning_rate": 9.225950427718974e-06, "loss": 0.614, "step": 217 }, { "epoch": 1.0583764062024932, "grad_norm": 0.32832344590376233, "learning_rate": 9.21458269798691e-06, "loss": 0.6024, "step": 218 }, { "epoch": 1.0632411067193677, "grad_norm": 0.3591732882030981, "learning_rate": 9.203139212215868e-06, "loss": 0.6353, "step": 219 }, { "epoch": 1.068105807236242, "grad_norm": 0.3158693119429108, "learning_rate": 9.191620176099559e-06, "loss": 0.6171, "step": 220 }, { "epoch": 1.0729705077531164, "grad_norm": 0.30321725130957683, "learning_rate": 9.180025796689692e-06, "loss": 0.6016, "step": 221 }, { "epoch": 1.077835208269991, "grad_norm": 0.3275829577047881, "learning_rate": 9.168356282392253e-06, "loss": 0.5951, "step": 222 }, { "epoch": 1.0826999087868654, "grad_norm": 0.29954315226185724, "learning_rate": 9.156611842963753e-06, "loss": 0.5952, "step": 223 }, { "epoch": 1.0875646093037397, "grad_norm": 0.3303361969254419, "learning_rate": 9.144792689507471e-06, "loss": 0.5851, "step": 224 }, { "epoch": 1.0924293098206141, "grad_norm": 0.3369206227134472, "learning_rate": 9.132899034469648e-06, "loss": 0.595, "step": 225 }, { "epoch": 1.0972940103374886, "grad_norm": 0.3388807630519231, "learning_rate": 9.120931091635669e-06, "loss": 0.6279, "step": 226 }, { "epoch": 1.1021587108543631, "grad_norm": 0.31124074690970155, "learning_rate": 9.108889076126226e-06, "loss": 0.5947, "step": 227 }, { "epoch": 1.1070234113712374, "grad_norm": 0.29762923723371265, "learning_rate": 9.09677320439345e-06, "loss": 0.6089, "step": 228 }, { "epoch": 1.1118881118881119, "grad_norm": 0.3253100815232674, "learning_rate": 9.084583694217012e-06, "loss": 0.5728, "step": 229 }, { "epoch": 1.1167528124049864, "grad_norm": 0.30985871932631076, "learning_rate": 9.072320764700223e-06, "loss": 0.5935, "step": 230 }, { "epoch": 1.1216175129218608, "grad_norm": 0.28239053433013905, "learning_rate": 9.059984636266082e-06, "loss": 0.5833, "step": 231 }, { "epoch": 1.1264822134387351, "grad_norm": 0.3449624841528913, "learning_rate": 9.047575530653324e-06, "loss": 0.6124, "step": 232 }, { "epoch": 1.1313469139556096, "grad_norm": 0.2837693517809675, "learning_rate": 9.035093670912424e-06, "loss": 0.5916, "step": 233 }, { "epoch": 1.136211614472484, "grad_norm": 0.3029715666609081, "learning_rate": 9.022539281401601e-06, "loss": 0.6039, "step": 234 }, { "epoch": 1.1410763149893586, "grad_norm": 0.34740133048150384, "learning_rate": 9.009912587782772e-06, "loss": 0.6029, "step": 235 }, { "epoch": 1.1459410155062328, "grad_norm": 0.3055584136420432, "learning_rate": 8.997213817017508e-06, "loss": 0.6168, "step": 236 }, { "epoch": 1.1508057160231073, "grad_norm": 0.2711721375963674, "learning_rate": 8.984443197362938e-06, "loss": 0.5731, "step": 237 }, { "epoch": 1.1556704165399818, "grad_norm": 0.30976644973447115, "learning_rate": 8.971600958367668e-06, "loss": 0.5871, "step": 238 }, { "epoch": 1.160535117056856, "grad_norm": 0.3267548031055678, "learning_rate": 8.958687330867634e-06, "loss": 0.5925, "step": 239 }, { "epoch": 1.1653998175737306, "grad_norm": 0.2733756189235018, "learning_rate": 8.94570254698197e-06, "loss": 0.587, "step": 240 }, { "epoch": 1.170264518090605, "grad_norm": 0.30574356144752574, "learning_rate": 8.932646840108818e-06, "loss": 0.6001, "step": 241 }, { "epoch": 1.1751292186074795, "grad_norm": 0.3302940776687681, "learning_rate": 8.919520444921153e-06, "loss": 0.6059, "step": 242 }, { "epoch": 1.179993919124354, "grad_norm": 0.28222859873408973, "learning_rate": 8.906323597362547e-06, "loss": 0.5751, "step": 243 }, { "epoch": 1.1848586196412283, "grad_norm": 0.28378012128958036, "learning_rate": 8.893056534642938e-06, "loss": 0.5532, "step": 244 }, { "epoch": 1.1897233201581028, "grad_norm": 0.31176227272835405, "learning_rate": 8.879719495234363e-06, "loss": 0.6032, "step": 245 }, { "epoch": 1.1945880206749773, "grad_norm": 0.310028083968784, "learning_rate": 8.866312718866669e-06, "loss": 0.5915, "step": 246 }, { "epoch": 1.1994527211918515, "grad_norm": 0.3057911975783169, "learning_rate": 8.852836446523213e-06, "loss": 0.5814, "step": 247 }, { "epoch": 1.204317421708726, "grad_norm": 0.30204737374831203, "learning_rate": 8.83929092043652e-06, "loss": 0.5888, "step": 248 }, { "epoch": 1.2091821222256005, "grad_norm": 0.2890354780093531, "learning_rate": 8.825676384083936e-06, "loss": 0.5794, "step": 249 }, { "epoch": 1.214046822742475, "grad_norm": 0.31315769970721063, "learning_rate": 8.811993082183243e-06, "loss": 0.5727, "step": 250 }, { "epoch": 1.2189115232593493, "grad_norm": 0.34491961450386777, "learning_rate": 8.798241260688273e-06, "loss": 0.6089, "step": 251 }, { "epoch": 1.2237762237762237, "grad_norm": 0.3111676557647456, "learning_rate": 8.784421166784476e-06, "loss": 0.6078, "step": 252 }, { "epoch": 1.2286409242930982, "grad_norm": 0.30085106375809656, "learning_rate": 8.770533048884483e-06, "loss": 0.59, "step": 253 }, { "epoch": 1.2335056248099727, "grad_norm": 0.30120737176372964, "learning_rate": 8.756577156623636e-06, "loss": 0.6053, "step": 254 }, { "epoch": 1.238370325326847, "grad_norm": 0.29312180826659123, "learning_rate": 8.742553740855507e-06, "loss": 0.5773, "step": 255 }, { "epoch": 1.2432350258437215, "grad_norm": 0.29242274272108004, "learning_rate": 8.728463053647382e-06, "loss": 0.5917, "step": 256 }, { "epoch": 1.248099726360596, "grad_norm": 0.2974398288336428, "learning_rate": 8.71430534827574e-06, "loss": 0.6053, "step": 257 }, { "epoch": 1.2529644268774702, "grad_norm": 0.29759000625673626, "learning_rate": 8.700080879221689e-06, "loss": 0.5904, "step": 258 }, { "epoch": 1.2578291273943447, "grad_norm": 0.31774153711940456, "learning_rate": 8.685789902166395e-06, "loss": 0.6148, "step": 259 }, { "epoch": 1.2626938279112192, "grad_norm": 0.35616216338767925, "learning_rate": 8.671432673986493e-06, "loss": 0.5877, "step": 260 }, { "epoch": 1.2675585284280937, "grad_norm": 0.2955010266710203, "learning_rate": 8.657009452749466e-06, "loss": 0.6011, "step": 261 }, { "epoch": 1.2724232289449682, "grad_norm": 0.28250541025994863, "learning_rate": 8.642520497709001e-06, "loss": 0.5907, "step": 262 }, { "epoch": 1.2772879294618424, "grad_norm": 0.3125872432334312, "learning_rate": 8.627966069300332e-06, "loss": 0.6089, "step": 263 }, { "epoch": 1.282152629978717, "grad_norm": 0.29603469731216636, "learning_rate": 8.613346429135567e-06, "loss": 0.5901, "step": 264 }, { "epoch": 1.2870173304955914, "grad_norm": 0.2742211482636206, "learning_rate": 8.598661839998972e-06, "loss": 0.5828, "step": 265 }, { "epoch": 1.2918820310124657, "grad_norm": 0.3228096079625964, "learning_rate": 8.583912565842258e-06, "loss": 0.6162, "step": 266 }, { "epoch": 1.2967467315293402, "grad_norm": 0.28649229212132593, "learning_rate": 8.569098871779828e-06, "loss": 0.5783, "step": 267 }, { "epoch": 1.3016114320462147, "grad_norm": 0.2967355907396642, "learning_rate": 8.554221024084019e-06, "loss": 0.579, "step": 268 }, { "epoch": 1.3064761325630891, "grad_norm": 0.31386189421282373, "learning_rate": 8.539279290180315e-06, "loss": 0.6079, "step": 269 }, { "epoch": 1.3113408330799636, "grad_norm": 0.2819760471699943, "learning_rate": 8.524273938642539e-06, "loss": 0.5949, "step": 270 }, { "epoch": 1.316205533596838, "grad_norm": 0.29105246936191187, "learning_rate": 8.509205239188017e-06, "loss": 0.6032, "step": 271 }, { "epoch": 1.3210702341137124, "grad_norm": 0.3062939730360163, "learning_rate": 8.494073462672743e-06, "loss": 0.602, "step": 272 }, { "epoch": 1.3259349346305869, "grad_norm": 0.2958974353727754, "learning_rate": 8.478878881086505e-06, "loss": 0.6153, "step": 273 }, { "epoch": 1.3307996351474611, "grad_norm": 0.30921513735866024, "learning_rate": 8.463621767547998e-06, "loss": 0.6063, "step": 274 }, { "epoch": 1.3356643356643356, "grad_norm": 0.28434960423872424, "learning_rate": 8.448302396299906e-06, "loss": 0.6033, "step": 275 }, { "epoch": 1.34052903618121, "grad_norm": 0.2987655238064537, "learning_rate": 8.432921042703985e-06, "loss": 0.5792, "step": 276 }, { "epoch": 1.3453937366980846, "grad_norm": 0.292260213537656, "learning_rate": 8.417477983236107e-06, "loss": 0.5993, "step": 277 }, { "epoch": 1.350258437214959, "grad_norm": 0.29375985725617115, "learning_rate": 8.401973495481289e-06, "loss": 0.6305, "step": 278 }, { "epoch": 1.3551231377318333, "grad_norm": 0.29771224443210076, "learning_rate": 8.386407858128707e-06, "loss": 0.6061, "step": 279 }, { "epoch": 1.3599878382487078, "grad_norm": 0.2906539347742839, "learning_rate": 8.370781350966683e-06, "loss": 0.5759, "step": 280 }, { "epoch": 1.3648525387655823, "grad_norm": 0.31334076925159593, "learning_rate": 8.355094254877665e-06, "loss": 0.595, "step": 281 }, { "epoch": 1.3697172392824566, "grad_norm": 0.29597782060020583, "learning_rate": 8.339346851833163e-06, "loss": 0.6118, "step": 282 }, { "epoch": 1.374581939799331, "grad_norm": 0.2987450884439521, "learning_rate": 8.323539424888695e-06, "loss": 0.6, "step": 283 }, { "epoch": 1.3794466403162056, "grad_norm": 0.3413110664151245, "learning_rate": 8.30767225817869e-06, "loss": 0.6154, "step": 284 }, { "epoch": 1.3843113408330798, "grad_norm": 0.3021764475833527, "learning_rate": 8.291745636911382e-06, "loss": 0.6138, "step": 285 }, { "epoch": 1.3891760413499543, "grad_norm": 0.3023527885625636, "learning_rate": 8.27575984736369e-06, "loss": 0.59, "step": 286 }, { "epoch": 1.3940407418668288, "grad_norm": 0.29959412122471446, "learning_rate": 8.259715176876069e-06, "loss": 0.5971, "step": 287 }, { "epoch": 1.3989054423837033, "grad_norm": 0.2959828198265794, "learning_rate": 8.243611913847337e-06, "loss": 0.5955, "step": 288 }, { "epoch": 1.4037701429005778, "grad_norm": 0.29187106473551455, "learning_rate": 8.2274503477295e-06, "loss": 0.5683, "step": 289 }, { "epoch": 1.408634843417452, "grad_norm": 0.28073411311513313, "learning_rate": 8.211230769022552e-06, "loss": 0.5849, "step": 290 }, { "epoch": 1.4134995439343265, "grad_norm": 0.31051745767426425, "learning_rate": 8.19495346926924e-06, "loss": 0.6184, "step": 291 }, { "epoch": 1.418364244451201, "grad_norm": 0.3266728172465444, "learning_rate": 8.178618741049841e-06, "loss": 0.6052, "step": 292 }, { "epoch": 1.4232289449680753, "grad_norm": 0.2544904842914839, "learning_rate": 8.162226877976886e-06, "loss": 0.5618, "step": 293 }, { "epoch": 1.4280936454849498, "grad_norm": 0.31084184131857023, "learning_rate": 8.145778174689897e-06, "loss": 0.6088, "step": 294 }, { "epoch": 1.4329583460018243, "grad_norm": 0.3043254560299071, "learning_rate": 8.129272926850079e-06, "loss": 0.5889, "step": 295 }, { "epoch": 1.4378230465186987, "grad_norm": 0.3134623339910932, "learning_rate": 8.112711431135014e-06, "loss": 0.611, "step": 296 }, { "epoch": 1.4426877470355732, "grad_norm": 0.3127520079235682, "learning_rate": 8.096093985233323e-06, "loss": 0.5923, "step": 297 }, { "epoch": 1.4475524475524475, "grad_norm": 0.3050563928349181, "learning_rate": 8.079420887839316e-06, "loss": 0.5786, "step": 298 }, { "epoch": 1.452417148069322, "grad_norm": 0.33431482821996417, "learning_rate": 8.062692438647628e-06, "loss": 0.6102, "step": 299 }, { "epoch": 1.4572818485861965, "grad_norm": 0.31461488130638626, "learning_rate": 8.045908938347828e-06, "loss": 0.5595, "step": 300 }, { "epoch": 1.4621465491030707, "grad_norm": 0.27751977816230294, "learning_rate": 8.029070688619013e-06, "loss": 0.5619, "step": 301 }, { "epoch": 1.4670112496199452, "grad_norm": 0.3308135306826131, "learning_rate": 8.012177992124385e-06, "loss": 0.5821, "step": 302 }, { "epoch": 1.4718759501368197, "grad_norm": 0.2870457263862016, "learning_rate": 7.995231152505815e-06, "loss": 0.5945, "step": 303 }, { "epoch": 1.4767406506536942, "grad_norm": 0.3080156040824572, "learning_rate": 7.978230474378383e-06, "loss": 0.5928, "step": 304 }, { "epoch": 1.4816053511705687, "grad_norm": 0.3132312440715278, "learning_rate": 7.961176263324902e-06, "loss": 0.621, "step": 305 }, { "epoch": 1.486470051687443, "grad_norm": 0.3438780778651031, "learning_rate": 7.944068825890424e-06, "loss": 0.6374, "step": 306 }, { "epoch": 1.4913347522043174, "grad_norm": 0.3283100616288732, "learning_rate": 7.92690846957673e-06, "loss": 0.5977, "step": 307 }, { "epoch": 1.496199452721192, "grad_norm": 0.3000731561157294, "learning_rate": 7.909695502836814e-06, "loss": 0.6022, "step": 308 }, { "epoch": 1.5010641532380662, "grad_norm": 0.27814460303213917, "learning_rate": 7.892430235069317e-06, "loss": 0.5955, "step": 309 }, { "epoch": 1.5059288537549407, "grad_norm": 0.3400755187140113, "learning_rate": 7.875112976612984e-06, "loss": 0.6092, "step": 310 }, { "epoch": 1.5107935542718152, "grad_norm": 0.2869741781455487, "learning_rate": 7.857744038741076e-06, "loss": 0.5984, "step": 311 }, { "epoch": 1.5156582547886894, "grad_norm": 0.31353583623274073, "learning_rate": 7.84032373365578e-06, "loss": 0.6159, "step": 312 }, { "epoch": 1.5205229553055641, "grad_norm": 0.27461294588206386, "learning_rate": 7.822852374482597e-06, "loss": 0.5836, "step": 313 }, { "epoch": 1.5253876558224384, "grad_norm": 0.3037901039714085, "learning_rate": 7.805330275264707e-06, "loss": 0.6095, "step": 314 }, { "epoch": 1.530252356339313, "grad_norm": 0.27393558315372263, "learning_rate": 7.787757750957335e-06, "loss": 0.5763, "step": 315 }, { "epoch": 1.5351170568561874, "grad_norm": 0.29933276907338924, "learning_rate": 7.77013511742208e-06, "loss": 0.5898, "step": 316 }, { "epoch": 1.5399817573730616, "grad_norm": 0.29241067989328, "learning_rate": 7.752462691421245e-06, "loss": 0.6032, "step": 317 }, { "epoch": 1.5448464578899361, "grad_norm": 0.3174998551974883, "learning_rate": 7.734740790612137e-06, "loss": 0.5906, "step": 318 }, { "epoch": 1.5497111584068106, "grad_norm": 0.2976404981783012, "learning_rate": 7.716969733541357e-06, "loss": 0.6044, "step": 319 }, { "epoch": 1.5545758589236849, "grad_norm": 0.3119585167475296, "learning_rate": 7.699149839639086e-06, "loss": 0.5968, "step": 320 }, { "epoch": 1.5594405594405596, "grad_norm": 0.3379481572529628, "learning_rate": 7.681281429213328e-06, "loss": 0.5949, "step": 321 }, { "epoch": 1.5643052599574339, "grad_norm": 0.2796045388485364, "learning_rate": 7.663364823444157e-06, "loss": 0.5771, "step": 322 }, { "epoch": 1.5691699604743083, "grad_norm": 0.3176843226345013, "learning_rate": 7.645400344377953e-06, "loss": 0.5982, "step": 323 }, { "epoch": 1.5740346609911828, "grad_norm": 0.2932753733259599, "learning_rate": 7.627388314921602e-06, "loss": 0.599, "step": 324 }, { "epoch": 1.578899361508057, "grad_norm": 0.33768156115276027, "learning_rate": 7.609329058836694e-06, "loss": 0.6208, "step": 325 }, { "epoch": 1.5837640620249316, "grad_norm": 0.29272761455414553, "learning_rate": 7.59122290073371e-06, "loss": 0.5809, "step": 326 }, { "epoch": 1.588628762541806, "grad_norm": 0.2968614098732931, "learning_rate": 7.5730701660661795e-06, "loss": 0.579, "step": 327 }, { "epoch": 1.5934934630586803, "grad_norm": 0.3139335379685541, "learning_rate": 7.554871181124836e-06, "loss": 0.5597, "step": 328 }, { "epoch": 1.5983581635755548, "grad_norm": 0.29259703899124107, "learning_rate": 7.536626273031747e-06, "loss": 0.6057, "step": 329 }, { "epoch": 1.6032228640924293, "grad_norm": 0.28146664372412034, "learning_rate": 7.5183357697344395e-06, "loss": 0.5954, "step": 330 }, { "epoch": 1.6080875646093036, "grad_norm": 0.29047328773925213, "learning_rate": 7.500000000000001e-06, "loss": 0.6068, "step": 331 }, { "epoch": 1.6129522651261783, "grad_norm": 0.340158510763134, "learning_rate": 7.481619293409173e-06, "loss": 0.5929, "step": 332 }, { "epoch": 1.6178169656430526, "grad_norm": 0.28938526257467434, "learning_rate": 7.4631939803504215e-06, "loss": 0.5564, "step": 333 }, { "epoch": 1.622681666159927, "grad_norm": 0.31277538066312616, "learning_rate": 7.44472439201401e-06, "loss": 0.595, "step": 334 }, { "epoch": 1.6275463666768015, "grad_norm": 0.3276150531415197, "learning_rate": 7.426210860386032e-06, "loss": 0.5914, "step": 335 }, { "epoch": 1.6324110671936758, "grad_norm": 0.2925867639303719, "learning_rate": 7.407653718242449e-06, "loss": 0.5451, "step": 336 }, { "epoch": 1.6372757677105503, "grad_norm": 0.3001946275767832, "learning_rate": 7.3890532991431174e-06, "loss": 0.5884, "step": 337 }, { "epoch": 1.6421404682274248, "grad_norm": 0.30280396777422025, "learning_rate": 7.370409937425781e-06, "loss": 0.5687, "step": 338 }, { "epoch": 1.647005168744299, "grad_norm": 0.3076228032122007, "learning_rate": 7.3517239682000675e-06, "loss": 0.5816, "step": 339 }, { "epoch": 1.6518698692611737, "grad_norm": 0.30238937043171743, "learning_rate": 7.332995727341462e-06, "loss": 0.6102, "step": 340 }, { "epoch": 1.656734569778048, "grad_norm": 0.3007096629113998, "learning_rate": 7.314225551485273e-06, "loss": 0.5942, "step": 341 }, { "epoch": 1.6615992702949225, "grad_norm": 0.29099350720282346, "learning_rate": 7.295413778020579e-06, "loss": 0.5703, "step": 342 }, { "epoch": 1.666463970811797, "grad_norm": 0.3326376639559874, "learning_rate": 7.276560745084167e-06, "loss": 0.6009, "step": 343 }, { "epoch": 1.6713286713286712, "grad_norm": 0.33694675905264737, "learning_rate": 7.257666791554448e-06, "loss": 0.6022, "step": 344 }, { "epoch": 1.6761933718455457, "grad_norm": 0.2907904110831913, "learning_rate": 7.2387322570453724e-06, "loss": 0.5749, "step": 345 }, { "epoch": 1.6810580723624202, "grad_norm": 0.28014026469209535, "learning_rate": 7.219757481900325e-06, "loss": 0.5779, "step": 346 }, { "epoch": 1.6859227728792945, "grad_norm": 0.3069328743549373, "learning_rate": 7.2007428071860045e-06, "loss": 0.5961, "step": 347 }, { "epoch": 1.6907874733961692, "grad_norm": 0.36348696542968195, "learning_rate": 7.181688574686292e-06, "loss": 0.566, "step": 348 }, { "epoch": 1.6956521739130435, "grad_norm": 0.33233144390603875, "learning_rate": 7.162595126896111e-06, "loss": 0.602, "step": 349 }, { "epoch": 1.700516874429918, "grad_norm": 0.3190135467102481, "learning_rate": 7.143462807015271e-06, "loss": 0.6029, "step": 350 }, { "epoch": 1.7053815749467924, "grad_norm": 0.33984585319051935, "learning_rate": 7.1242919589422974e-06, "loss": 0.595, "step": 351 }, { "epoch": 1.7102462754636667, "grad_norm": 0.2945015499348542, "learning_rate": 7.105082927268247e-06, "loss": 0.5894, "step": 352 }, { "epoch": 1.7151109759805412, "grad_norm": 0.3203826323223575, "learning_rate": 7.085836057270521e-06, "loss": 0.5914, "step": 353 }, { "epoch": 1.7199756764974157, "grad_norm": 0.3135140462483351, "learning_rate": 7.066551694906651e-06, "loss": 0.5838, "step": 354 }, { "epoch": 1.72484037701429, "grad_norm": 0.3053471485898868, "learning_rate": 7.047230186808085e-06, "loss": 0.5988, "step": 355 }, { "epoch": 1.7297050775311646, "grad_norm": 0.30633204813295156, "learning_rate": 7.027871880273959e-06, "loss": 0.5878, "step": 356 }, { "epoch": 1.734569778048039, "grad_norm": 0.30041327488698116, "learning_rate": 7.008477123264849e-06, "loss": 0.59, "step": 357 }, { "epoch": 1.7394344785649134, "grad_norm": 0.2860703978901428, "learning_rate": 6.989046264396516e-06, "loss": 0.5888, "step": 358 }, { "epoch": 1.7442991790817879, "grad_norm": 0.29872158354355416, "learning_rate": 6.96957965293365e-06, "loss": 0.588, "step": 359 }, { "epoch": 1.7491638795986622, "grad_norm": 0.29182552006591084, "learning_rate": 6.9500776387835785e-06, "loss": 0.5589, "step": 360 }, { "epoch": 1.7540285801155366, "grad_norm": 0.2971579947817233, "learning_rate": 6.9305405724899876e-06, "loss": 0.5954, "step": 361 }, { "epoch": 1.7588932806324111, "grad_norm": 0.2982643112427319, "learning_rate": 6.91096880522661e-06, "loss": 0.6186, "step": 362 }, { "epoch": 1.7637579811492854, "grad_norm": 0.2956880150323247, "learning_rate": 6.891362688790925e-06, "loss": 0.5976, "step": 363 }, { "epoch": 1.7686226816661599, "grad_norm": 0.30217580035851954, "learning_rate": 6.871722575597829e-06, "loss": 0.568, "step": 364 }, { "epoch": 1.7734873821830344, "grad_norm": 0.2563510928284065, "learning_rate": 6.8520488186733e-06, "loss": 0.573, "step": 365 }, { "epoch": 1.7783520826999086, "grad_norm": 0.3042684540410719, "learning_rate": 6.832341771648057e-06, "loss": 0.6199, "step": 366 }, { "epoch": 1.7832167832167833, "grad_norm": 0.2768777792919464, "learning_rate": 6.812601788751192e-06, "loss": 0.5921, "step": 367 }, { "epoch": 1.7880814837336576, "grad_norm": 0.2647032273275463, "learning_rate": 6.792829224803816e-06, "loss": 0.5853, "step": 368 }, { "epoch": 1.792946184250532, "grad_norm": 0.26864810498814923, "learning_rate": 6.773024435212678e-06, "loss": 0.5921, "step": 369 }, { "epoch": 1.7978108847674066, "grad_norm": 0.30314336868055797, "learning_rate": 6.753187775963773e-06, "loss": 0.609, "step": 370 }, { "epoch": 1.8026755852842808, "grad_norm": 0.2772858655679343, "learning_rate": 6.733319603615941e-06, "loss": 0.5656, "step": 371 }, { "epoch": 1.8075402858011553, "grad_norm": 0.28150765101780584, "learning_rate": 6.713420275294467e-06, "loss": 0.6155, "step": 372 }, { "epoch": 1.8124049863180298, "grad_norm": 0.30218141892668393, "learning_rate": 6.693490148684654e-06, "loss": 0.5779, "step": 373 }, { "epoch": 1.817269686834904, "grad_norm": 0.28275067077284505, "learning_rate": 6.673529582025398e-06, "loss": 0.5761, "step": 374 }, { "epoch": 1.8221343873517788, "grad_norm": 0.2853379921512944, "learning_rate": 6.653538934102743e-06, "loss": 0.621, "step": 375 }, { "epoch": 1.826999087868653, "grad_norm": 0.275390771186356, "learning_rate": 6.633518564243442e-06, "loss": 0.6025, "step": 376 }, { "epoch": 1.8318637883855275, "grad_norm": 0.27878895559962946, "learning_rate": 6.6134688323084884e-06, "loss": 0.5947, "step": 377 }, { "epoch": 1.836728488902402, "grad_norm": 0.31401487153561664, "learning_rate": 6.593390098686653e-06, "loss": 0.6175, "step": 378 }, { "epoch": 1.8415931894192763, "grad_norm": 0.2890642735721841, "learning_rate": 6.573282724288001e-06, "loss": 0.603, "step": 379 }, { "epoch": 1.8464578899361508, "grad_norm": 0.2756016967533866, "learning_rate": 6.553147070537413e-06, "loss": 0.6132, "step": 380 }, { "epoch": 1.8513225904530253, "grad_norm": 0.2841199314491842, "learning_rate": 6.532983499368078e-06, "loss": 0.5886, "step": 381 }, { "epoch": 1.8561872909698995, "grad_norm": 0.2974906694510715, "learning_rate": 6.512792373215e-06, "loss": 0.5769, "step": 382 }, { "epoch": 1.8610519914867742, "grad_norm": 0.2605920119052759, "learning_rate": 6.492574055008474e-06, "loss": 0.5856, "step": 383 }, { "epoch": 1.8659166920036485, "grad_norm": 0.29930024327749283, "learning_rate": 6.472328908167562e-06, "loss": 0.5994, "step": 384 }, { "epoch": 1.870781392520523, "grad_norm": 0.2836877704119603, "learning_rate": 6.452057296593568e-06, "loss": 0.5939, "step": 385 }, { "epoch": 1.8756460930373975, "grad_norm": 0.2620981184675462, "learning_rate": 6.431759584663492e-06, "loss": 0.5901, "step": 386 }, { "epoch": 1.8805107935542718, "grad_norm": 0.2660169524668314, "learning_rate": 6.411436137223479e-06, "loss": 0.5561, "step": 387 }, { "epoch": 1.8853754940711462, "grad_norm": 0.2863064725801307, "learning_rate": 6.391087319582264e-06, "loss": 0.5734, "step": 388 }, { "epoch": 1.8902401945880207, "grad_norm": 0.2873616080767967, "learning_rate": 6.370713497504607e-06, "loss": 0.5863, "step": 389 }, { "epoch": 1.895104895104895, "grad_norm": 0.2756108475803721, "learning_rate": 6.350315037204714e-06, "loss": 0.5863, "step": 390 }, { "epoch": 1.8999695956217695, "grad_norm": 0.2840921414869869, "learning_rate": 6.329892305339659e-06, "loss": 0.5922, "step": 391 }, { "epoch": 1.904834296138644, "grad_norm": 0.2703518461208396, "learning_rate": 6.309445669002787e-06, "loss": 0.5764, "step": 392 }, { "epoch": 1.9096989966555182, "grad_norm": 0.3179366615818676, "learning_rate": 6.288975495717124e-06, "loss": 0.5918, "step": 393 }, { "epoch": 1.914563697172393, "grad_norm": 0.2836363650856831, "learning_rate": 6.268482153428763e-06, "loss": 0.5982, "step": 394 }, { "epoch": 1.9194283976892672, "grad_norm": 0.29578539666674475, "learning_rate": 6.247966010500258e-06, "loss": 0.6103, "step": 395 }, { "epoch": 1.9242930982061417, "grad_norm": 0.2974645756111545, "learning_rate": 6.227427435703997e-06, "loss": 0.601, "step": 396 }, { "epoch": 1.9291577987230162, "grad_norm": 0.3107388663737716, "learning_rate": 6.206866798215571e-06, "loss": 0.587, "step": 397 }, { "epoch": 1.9340224992398904, "grad_norm": 0.29959172321227634, "learning_rate": 6.186284467607149e-06, "loss": 0.6045, "step": 398 }, { "epoch": 1.938887199756765, "grad_norm": 0.29068983272896337, "learning_rate": 6.165680813840822e-06, "loss": 0.5864, "step": 399 }, { "epoch": 1.9437519002736394, "grad_norm": 0.3054960426974372, "learning_rate": 6.1450562072619635e-06, "loss": 0.6067, "step": 400 }, { "epoch": 1.9486166007905137, "grad_norm": 0.2773181702959524, "learning_rate": 6.124411018592568e-06, "loss": 0.5984, "step": 401 }, { "epoch": 1.9534813013073884, "grad_norm": 0.285293740086508, "learning_rate": 6.103745618924587e-06, "loss": 0.5812, "step": 402 }, { "epoch": 1.9583460018242627, "grad_norm": 0.30191299157402707, "learning_rate": 6.0830603797132574e-06, "loss": 0.592, "step": 403 }, { "epoch": 1.9632107023411371, "grad_norm": 0.29440871707780525, "learning_rate": 6.0623556727704306e-06, "loss": 0.5956, "step": 404 }, { "epoch": 1.9680754028580116, "grad_norm": 0.2864730353254991, "learning_rate": 6.041631870257882e-06, "loss": 0.5988, "step": 405 }, { "epoch": 1.972940103374886, "grad_norm": 0.28390240434279995, "learning_rate": 6.020889344680627e-06, "loss": 0.595, "step": 406 }, { "epoch": 1.9778048038917604, "grad_norm": 0.28669443245202686, "learning_rate": 6.000128468880223e-06, "loss": 0.606, "step": 407 }, { "epoch": 1.9826695044086349, "grad_norm": 0.3066867340447252, "learning_rate": 5.979349616028067e-06, "loss": 0.5884, "step": 408 }, { "epoch": 1.9875342049255091, "grad_norm": 0.28977772843987104, "learning_rate": 5.958553159618693e-06, "loss": 0.5991, "step": 409 }, { "epoch": 1.9923989054423838, "grad_norm": 0.28410752030212394, "learning_rate": 5.937739473463047e-06, "loss": 0.6118, "step": 410 }, { "epoch": 1.9972636059592581, "grad_norm": 0.2965319797611234, "learning_rate": 5.916908931681781e-06, "loss": 0.5832, "step": 411 }, { "epoch": 2.0, "grad_norm": 0.36267863006296397, "learning_rate": 5.896061908698521e-06, "loss": 0.5858, "step": 412 }, { "epoch": 2.0048647005168743, "grad_norm": 0.356790463227785, "learning_rate": 5.8751987792331365e-06, "loss": 0.5532, "step": 413 }, { "epoch": 2.009729401033749, "grad_norm": 0.31044181275769156, "learning_rate": 5.854319918295012e-06, "loss": 0.563, "step": 414 }, { "epoch": 2.0145941015506232, "grad_norm": 0.3174358316750536, "learning_rate": 5.833425701176294e-06, "loss": 0.5803, "step": 415 }, { "epoch": 2.0194588020674975, "grad_norm": 0.3451873559978031, "learning_rate": 5.812516503445158e-06, "loss": 0.5798, "step": 416 }, { "epoch": 2.024323502584372, "grad_norm": 0.3208914624167093, "learning_rate": 5.79159270093905e-06, "loss": 0.5839, "step": 417 }, { "epoch": 2.0291882031012465, "grad_norm": 0.2835072658503529, "learning_rate": 5.770654669757935e-06, "loss": 0.5578, "step": 418 }, { "epoch": 2.034052903618121, "grad_norm": 0.29746142707499595, "learning_rate": 5.749702786257529e-06, "loss": 0.5412, "step": 419 }, { "epoch": 2.0389176041349955, "grad_norm": 0.2741212450118802, "learning_rate": 5.7287374270425475e-06, "loss": 0.5418, "step": 420 }, { "epoch": 2.0437823046518697, "grad_norm": 0.3540271516597851, "learning_rate": 5.707758968959923e-06, "loss": 0.5512, "step": 421 }, { "epoch": 2.0486470051687444, "grad_norm": 0.2811743634816071, "learning_rate": 5.686767789092041e-06, "loss": 0.5621, "step": 422 }, { "epoch": 2.0535117056856187, "grad_norm": 0.2986834344933115, "learning_rate": 5.6657642647499545e-06, "loss": 0.5835, "step": 423 }, { "epoch": 2.058376406202493, "grad_norm": 0.27817990450996455, "learning_rate": 5.644748773466606e-06, "loss": 0.5352, "step": 424 }, { "epoch": 2.0632411067193677, "grad_norm": 0.2842480307740508, "learning_rate": 5.62372169299004e-06, "loss": 0.5605, "step": 425 }, { "epoch": 2.068105807236242, "grad_norm": 0.30427607542668367, "learning_rate": 5.6026834012766155e-06, "loss": 0.5511, "step": 426 }, { "epoch": 2.0729705077531166, "grad_norm": 0.30901440315170514, "learning_rate": 5.581634276484211e-06, "loss": 0.5729, "step": 427 }, { "epoch": 2.077835208269991, "grad_norm": 1.06688341898057, "learning_rate": 5.560574696965425e-06, "loss": 0.5872, "step": 428 }, { "epoch": 2.082699908786865, "grad_norm": 0.29316931511059174, "learning_rate": 5.539505041260779e-06, "loss": 0.551, "step": 429 }, { "epoch": 2.08756460930374, "grad_norm": 0.30159252468162273, "learning_rate": 5.518425688091906e-06, "loss": 0.5675, "step": 430 }, { "epoch": 2.092429309820614, "grad_norm": 0.3184503591788103, "learning_rate": 5.497337016354757e-06, "loss": 0.569, "step": 431 }, { "epoch": 2.0972940103374884, "grad_norm": 0.2944898037583308, "learning_rate": 5.476239405112775e-06, "loss": 0.5516, "step": 432 }, { "epoch": 2.102158710854363, "grad_norm": 0.26888261720258333, "learning_rate": 5.45513323359009e-06, "loss": 0.5602, "step": 433 }, { "epoch": 2.1070234113712374, "grad_norm": 0.271054360419919, "learning_rate": 5.434018881164702e-06, "loss": 0.5505, "step": 434 }, { "epoch": 2.111888111888112, "grad_norm": 0.2922062293101122, "learning_rate": 5.412896727361663e-06, "loss": 0.5352, "step": 435 }, { "epoch": 2.1167528124049864, "grad_norm": 0.2827651832311034, "learning_rate": 5.391767151846247e-06, "loss": 0.5254, "step": 436 }, { "epoch": 2.1216175129218606, "grad_norm": 0.26964188438969894, "learning_rate": 5.370630534417133e-06, "loss": 0.5519, "step": 437 }, { "epoch": 2.1264822134387353, "grad_norm": 0.2820757532319473, "learning_rate": 5.349487254999579e-06, "loss": 0.572, "step": 438 }, { "epoch": 2.1313469139556096, "grad_norm": 0.29298880154114176, "learning_rate": 5.328337693638591e-06, "loss": 0.5561, "step": 439 }, { "epoch": 2.136211614472484, "grad_norm": 0.32237144129821205, "learning_rate": 5.307182230492089e-06, "loss": 0.5736, "step": 440 }, { "epoch": 2.1410763149893586, "grad_norm": 0.28875601718513016, "learning_rate": 5.286021245824075e-06, "loss": 0.5558, "step": 441 }, { "epoch": 2.145941015506233, "grad_norm": 0.2857212658938584, "learning_rate": 5.264855119997803e-06, "loss": 0.5625, "step": 442 }, { "epoch": 2.1508057160231075, "grad_norm": 0.300716440607665, "learning_rate": 5.243684233468933e-06, "loss": 0.5593, "step": 443 }, { "epoch": 2.155670416539982, "grad_norm": 0.2752037982062981, "learning_rate": 5.222508966778702e-06, "loss": 0.5709, "step": 444 }, { "epoch": 2.160535117056856, "grad_norm": 0.29386936674665565, "learning_rate": 5.201329700547077e-06, "loss": 0.5681, "step": 445 }, { "epoch": 2.165399817573731, "grad_norm": 0.30257828802584974, "learning_rate": 5.180146815465915e-06, "loss": 0.5547, "step": 446 }, { "epoch": 2.170264518090605, "grad_norm": 0.2807700176970982, "learning_rate": 5.158960692292122e-06, "loss": 0.5553, "step": 447 }, { "epoch": 2.1751292186074793, "grad_norm": 0.260893015316446, "learning_rate": 5.137771711840811e-06, "loss": 0.5603, "step": 448 }, { "epoch": 2.179993919124354, "grad_norm": 0.3064453944331366, "learning_rate": 5.116580254978447e-06, "loss": 0.5541, "step": 449 }, { "epoch": 2.1848586196412283, "grad_norm": 0.2956353605373719, "learning_rate": 5.095386702616012e-06, "loss": 0.5653, "step": 450 }, { "epoch": 2.1897233201581026, "grad_norm": 0.30148473158624955, "learning_rate": 5.074191435702155e-06, "loss": 0.562, "step": 451 }, { "epoch": 2.1945880206749773, "grad_norm": 0.29361676721145913, "learning_rate": 5.05299483521634e-06, "loss": 0.5757, "step": 452 }, { "epoch": 2.1994527211918515, "grad_norm": 0.2759979946022341, "learning_rate": 5.031797282162007e-06, "loss": 0.5678, "step": 453 }, { "epoch": 2.2043174217087262, "grad_norm": 0.2922497783252449, "learning_rate": 5.010599157559713e-06, "loss": 0.5492, "step": 454 }, { "epoch": 2.2091821222256005, "grad_norm": 0.26741770943762144, "learning_rate": 4.98940084244029e-06, "loss": 0.5588, "step": 455 }, { "epoch": 2.2140468227424748, "grad_norm": 0.2765225837872397, "learning_rate": 4.968202717837996e-06, "loss": 0.551, "step": 456 }, { "epoch": 2.2189115232593495, "grad_norm": 0.2872768531738294, "learning_rate": 4.947005164783661e-06, "loss": 0.5414, "step": 457 }, { "epoch": 2.2237762237762237, "grad_norm": 0.29669008488361037, "learning_rate": 4.925808564297847e-06, "loss": 0.5584, "step": 458 }, { "epoch": 2.228640924293098, "grad_norm": 0.27195801647882323, "learning_rate": 4.9046132973839895e-06, "loss": 0.5558, "step": 459 }, { "epoch": 2.2335056248099727, "grad_norm": 0.2941575466914715, "learning_rate": 4.883419745021554e-06, "loss": 0.5568, "step": 460 }, { "epoch": 2.238370325326847, "grad_norm": 0.27127633010721547, "learning_rate": 4.862228288159191e-06, "loss": 0.5493, "step": 461 }, { "epoch": 2.2432350258437217, "grad_norm": 0.29790760329389465, "learning_rate": 4.841039307707878e-06, "loss": 0.5555, "step": 462 }, { "epoch": 2.248099726360596, "grad_norm": 0.28178969119006886, "learning_rate": 4.819853184534085e-06, "loss": 0.5489, "step": 463 }, { "epoch": 2.2529644268774702, "grad_norm": 0.28665825131237604, "learning_rate": 4.798670299452926e-06, "loss": 0.5367, "step": 464 }, { "epoch": 2.257829127394345, "grad_norm": 0.2935937293566066, "learning_rate": 4.7774910332213005e-06, "loss": 0.5389, "step": 465 }, { "epoch": 2.262693827911219, "grad_norm": 0.3136938141716208, "learning_rate": 4.756315766531069e-06, "loss": 0.6028, "step": 466 }, { "epoch": 2.2675585284280935, "grad_norm": 0.28593161525850275, "learning_rate": 4.735144880002199e-06, "loss": 0.5531, "step": 467 }, { "epoch": 2.272423228944968, "grad_norm": 0.2584739193021387, "learning_rate": 4.713978754175926e-06, "loss": 0.5356, "step": 468 }, { "epoch": 2.2772879294618424, "grad_norm": 0.2886853828654475, "learning_rate": 4.692817769507912e-06, "loss": 0.5722, "step": 469 }, { "epoch": 2.282152629978717, "grad_norm": 0.2773111425837377, "learning_rate": 4.671662306361409e-06, "loss": 0.5686, "step": 470 }, { "epoch": 2.2870173304955914, "grad_norm": 0.28283661445618624, "learning_rate": 4.6505127450004216e-06, "loss": 0.5776, "step": 471 }, { "epoch": 2.2918820310124657, "grad_norm": 0.2846289879526706, "learning_rate": 4.62936946558287e-06, "loss": 0.5533, "step": 472 }, { "epoch": 2.2967467315293404, "grad_norm": 0.2756039705083194, "learning_rate": 4.608232848153757e-06, "loss": 0.5747, "step": 473 }, { "epoch": 2.3016114320462147, "grad_norm": 0.3041913373340015, "learning_rate": 4.587103272638339e-06, "loss": 0.5548, "step": 474 }, { "epoch": 2.306476132563089, "grad_norm": 0.27928043703610245, "learning_rate": 4.565981118835299e-06, "loss": 0.5839, "step": 475 }, { "epoch": 2.3113408330799636, "grad_norm": 0.26672258260338855, "learning_rate": 4.5448667664099125e-06, "loss": 0.5564, "step": 476 }, { "epoch": 2.316205533596838, "grad_norm": 0.28664804760674745, "learning_rate": 4.523760594887228e-06, "loss": 0.5758, "step": 477 }, { "epoch": 2.321070234113712, "grad_norm": 0.2819918846210883, "learning_rate": 4.5026629836452445e-06, "loss": 0.5615, "step": 478 }, { "epoch": 2.325934934630587, "grad_norm": 0.30134456578571694, "learning_rate": 4.481574311908096e-06, "loss": 0.5479, "step": 479 }, { "epoch": 2.330799635147461, "grad_norm": 0.26346632654449464, "learning_rate": 4.460494958739223e-06, "loss": 0.5519, "step": 480 }, { "epoch": 2.335664335664336, "grad_norm": 0.27203806055889157, "learning_rate": 4.439425303034576e-06, "loss": 0.5591, "step": 481 }, { "epoch": 2.34052903618121, "grad_norm": 0.29967914488350744, "learning_rate": 4.418365723515791e-06, "loss": 0.5709, "step": 482 }, { "epoch": 2.3453937366980844, "grad_norm": 0.27259291077879916, "learning_rate": 4.397316598723385e-06, "loss": 0.5755, "step": 483 }, { "epoch": 2.350258437214959, "grad_norm": 0.3072483238099613, "learning_rate": 4.376278307009962e-06, "loss": 0.5783, "step": 484 }, { "epoch": 2.3551231377318333, "grad_norm": 0.287167100211482, "learning_rate": 4.355251226533396e-06, "loss": 0.5682, "step": 485 }, { "epoch": 2.359987838248708, "grad_norm": 0.2862588361920942, "learning_rate": 4.334235735250047e-06, "loss": 0.549, "step": 486 }, { "epoch": 2.3648525387655823, "grad_norm": 0.28696247683014703, "learning_rate": 4.313232210907959e-06, "loss": 0.555, "step": 487 }, { "epoch": 2.3697172392824566, "grad_norm": 0.3153334685758682, "learning_rate": 4.292241031040077e-06, "loss": 0.5504, "step": 488 }, { "epoch": 2.374581939799331, "grad_norm": 0.28504667487142915, "learning_rate": 4.271262572957453e-06, "loss": 0.5518, "step": 489 }, { "epoch": 2.3794466403162056, "grad_norm": 0.27770695323001815, "learning_rate": 4.250297213742473e-06, "loss": 0.5608, "step": 490 }, { "epoch": 2.38431134083308, "grad_norm": 0.30172889237393113, "learning_rate": 4.229345330242067e-06, "loss": 0.5504, "step": 491 }, { "epoch": 2.3891760413499545, "grad_norm": 0.30192183823039137, "learning_rate": 4.2084072990609505e-06, "loss": 0.5874, "step": 492 }, { "epoch": 2.394040741866829, "grad_norm": 0.2889245223125804, "learning_rate": 4.187483496554844e-06, "loss": 0.557, "step": 493 }, { "epoch": 2.398905442383703, "grad_norm": 0.29264660042424073, "learning_rate": 4.166574298823707e-06, "loss": 0.5661, "step": 494 }, { "epoch": 2.4037701429005778, "grad_norm": 0.29990302043506745, "learning_rate": 4.145680081704989e-06, "loss": 0.5794, "step": 495 }, { "epoch": 2.408634843417452, "grad_norm": 0.2964130087441388, "learning_rate": 4.1248012207668635e-06, "loss": 0.5696, "step": 496 }, { "epoch": 2.4134995439343268, "grad_norm": 0.26620295707728103, "learning_rate": 4.103938091301479e-06, "loss": 0.5458, "step": 497 }, { "epoch": 2.418364244451201, "grad_norm": 0.32380498570218474, "learning_rate": 4.08309106831822e-06, "loss": 0.5755, "step": 498 }, { "epoch": 2.4232289449680753, "grad_norm": 0.3123446432786783, "learning_rate": 4.062260526536955e-06, "loss": 0.5558, "step": 499 }, { "epoch": 2.42809364548495, "grad_norm": 0.27281931300647566, "learning_rate": 4.041446840381309e-06, "loss": 0.5664, "step": 500 }, { "epoch": 2.4329583460018243, "grad_norm": 0.26549881730269004, "learning_rate": 4.0206503839719335e-06, "loss": 0.532, "step": 501 }, { "epoch": 2.4378230465186985, "grad_norm": 0.2862521923091063, "learning_rate": 3.999871531119779e-06, "loss": 0.5732, "step": 502 }, { "epoch": 2.4426877470355732, "grad_norm": 0.29835350483128603, "learning_rate": 3.9791106553193746e-06, "loss": 0.541, "step": 503 }, { "epoch": 2.4475524475524475, "grad_norm": 0.32010831116550664, "learning_rate": 3.9583681297421194e-06, "loss": 0.5831, "step": 504 }, { "epoch": 2.4524171480693218, "grad_norm": 0.2986325160109337, "learning_rate": 3.937644327229572e-06, "loss": 0.5491, "step": 505 }, { "epoch": 2.4572818485861965, "grad_norm": 0.28436781389409954, "learning_rate": 3.916939620286743e-06, "loss": 0.5842, "step": 506 }, { "epoch": 2.4621465491030707, "grad_norm": 0.27550162480930007, "learning_rate": 3.896254381075416e-06, "loss": 0.5729, "step": 507 }, { "epoch": 2.4670112496199454, "grad_norm": 0.28583680637352304, "learning_rate": 3.875588981407433e-06, "loss": 0.5431, "step": 508 }, { "epoch": 2.4718759501368197, "grad_norm": 0.42714406383063547, "learning_rate": 3.854943792738037e-06, "loss": 0.5558, "step": 509 }, { "epoch": 2.476740650653694, "grad_norm": 0.3171813500702169, "learning_rate": 3.834319186159179e-06, "loss": 0.5703, "step": 510 }, { "epoch": 2.4816053511705687, "grad_norm": 0.3241718603153869, "learning_rate": 3.8137155323928526e-06, "loss": 0.5682, "step": 511 }, { "epoch": 2.486470051687443, "grad_norm": 0.283409128437201, "learning_rate": 3.7931332017844302e-06, "loss": 0.5735, "step": 512 }, { "epoch": 2.4913347522043177, "grad_norm": 0.2666723728998163, "learning_rate": 3.7725725642960047e-06, "loss": 0.5609, "step": 513 }, { "epoch": 2.496199452721192, "grad_norm": 0.2915908817333503, "learning_rate": 3.752033989499742e-06, "loss": 0.5521, "step": 514 }, { "epoch": 2.501064153238066, "grad_norm": 0.2821280771972244, "learning_rate": 3.7315178465712364e-06, "loss": 0.5538, "step": 515 }, { "epoch": 2.5059288537549405, "grad_norm": 0.26527362534481613, "learning_rate": 3.7110245042828786e-06, "loss": 0.5747, "step": 516 }, { "epoch": 2.510793554271815, "grad_norm": 0.3161918959301386, "learning_rate": 3.690554330997215e-06, "loss": 0.5523, "step": 517 }, { "epoch": 2.5156582547886894, "grad_norm": 0.27704126728191486, "learning_rate": 3.670107694660343e-06, "loss": 0.5654, "step": 518 }, { "epoch": 2.520522955305564, "grad_norm": 0.2661985993377897, "learning_rate": 3.6496849627952875e-06, "loss": 0.5535, "step": 519 }, { "epoch": 2.5253876558224384, "grad_norm": 0.2910913978941874, "learning_rate": 3.6292865024953945e-06, "loss": 0.5906, "step": 520 }, { "epoch": 2.5302523563393127, "grad_norm": 0.2797826067282238, "learning_rate": 3.6089126804177373e-06, "loss": 0.5596, "step": 521 }, { "epoch": 2.5351170568561874, "grad_norm": 0.27913707760157175, "learning_rate": 3.5885638627765228e-06, "loss": 0.5659, "step": 522 }, { "epoch": 2.5399817573730616, "grad_norm": 0.2571836165098686, "learning_rate": 3.568240415336509e-06, "loss": 0.5594, "step": 523 }, { "epoch": 2.5448464578899364, "grad_norm": 0.2829619981605505, "learning_rate": 3.547942703406433e-06, "loss": 0.5617, "step": 524 }, { "epoch": 2.5497111584068106, "grad_norm": 0.255637225666014, "learning_rate": 3.52767109183244e-06, "loss": 0.5333, "step": 525 }, { "epoch": 2.554575858923685, "grad_norm": 0.28042606370570583, "learning_rate": 3.507425944991529e-06, "loss": 0.5545, "step": 526 }, { "epoch": 2.5594405594405596, "grad_norm": 0.27788574463666416, "learning_rate": 3.4872076267850015e-06, "loss": 0.5315, "step": 527 }, { "epoch": 2.564305259957434, "grad_norm": 0.28081543524721414, "learning_rate": 3.4670165006319236e-06, "loss": 0.5512, "step": 528 }, { "epoch": 2.5691699604743086, "grad_norm": 0.28595134835716307, "learning_rate": 3.4468529294625895e-06, "loss": 0.5575, "step": 529 }, { "epoch": 2.574034660991183, "grad_norm": 0.26816319265835026, "learning_rate": 3.4267172757120005e-06, "loss": 0.5745, "step": 530 }, { "epoch": 2.578899361508057, "grad_norm": 0.3155283513191719, "learning_rate": 3.406609901313349e-06, "loss": 0.5611, "step": 531 }, { "epoch": 2.5837640620249314, "grad_norm": 0.30475121501867114, "learning_rate": 3.386531167691512e-06, "loss": 0.5619, "step": 532 }, { "epoch": 2.588628762541806, "grad_norm": 0.296459382173757, "learning_rate": 3.36648143575656e-06, "loss": 0.5613, "step": 533 }, { "epoch": 2.5934934630586803, "grad_norm": 0.2938538757516733, "learning_rate": 3.3464610658972584e-06, "loss": 0.5555, "step": 534 }, { "epoch": 2.598358163575555, "grad_norm": 0.2792214422778138, "learning_rate": 3.326470417974604e-06, "loss": 0.5465, "step": 535 }, { "epoch": 2.6032228640924293, "grad_norm": 0.28362467918000106, "learning_rate": 3.3065098513153473e-06, "loss": 0.5297, "step": 536 }, { "epoch": 2.6080875646093036, "grad_norm": 0.27879108969817884, "learning_rate": 3.2865797247055354e-06, "loss": 0.5835, "step": 537 }, { "epoch": 2.6129522651261783, "grad_norm": 0.28728538245271634, "learning_rate": 3.266680396384061e-06, "loss": 0.5511, "step": 538 }, { "epoch": 2.6178169656430526, "grad_norm": 0.27113518802362235, "learning_rate": 3.2468122240362287e-06, "loss": 0.568, "step": 539 }, { "epoch": 2.6226816661599273, "grad_norm": 0.2561298925923076, "learning_rate": 3.226975564787322e-06, "loss": 0.5626, "step": 540 }, { "epoch": 2.6275463666768015, "grad_norm": 0.2634434844335726, "learning_rate": 3.2071707751961838e-06, "loss": 0.5599, "step": 541 }, { "epoch": 2.632411067193676, "grad_norm": 0.2818666459537398, "learning_rate": 3.187398211248811e-06, "loss": 0.5537, "step": 542 }, { "epoch": 2.63727576771055, "grad_norm": 0.2513509252992497, "learning_rate": 3.1676582283519454e-06, "loss": 0.5544, "step": 543 }, { "epoch": 2.6421404682274248, "grad_norm": 0.272026918761039, "learning_rate": 3.1479511813267006e-06, "loss": 0.5518, "step": 544 }, { "epoch": 2.647005168744299, "grad_norm": 0.26916779611998876, "learning_rate": 3.1282774244021717e-06, "loss": 0.5401, "step": 545 }, { "epoch": 2.6518698692611737, "grad_norm": 0.2700796072752056, "learning_rate": 3.1086373112090762e-06, "loss": 0.5746, "step": 546 }, { "epoch": 2.656734569778048, "grad_norm": 0.26802456742744996, "learning_rate": 3.089031194773392e-06, "loss": 0.571, "step": 547 }, { "epoch": 2.6615992702949223, "grad_norm": 0.2814167501997253, "learning_rate": 3.069459427510014e-06, "loss": 0.5723, "step": 548 }, { "epoch": 2.666463970811797, "grad_norm": 0.3104275824013885, "learning_rate": 3.049922361216422e-06, "loss": 0.5581, "step": 549 }, { "epoch": 2.6713286713286712, "grad_norm": 0.2788082453065843, "learning_rate": 3.0304203470663507e-06, "loss": 0.5519, "step": 550 }, { "epoch": 2.676193371845546, "grad_norm": 0.26139488585239185, "learning_rate": 3.0109537356034856e-06, "loss": 0.5557, "step": 551 }, { "epoch": 2.68105807236242, "grad_norm": 0.2894908984023114, "learning_rate": 2.991522876735154e-06, "loss": 0.5454, "step": 552 }, { "epoch": 2.6859227728792945, "grad_norm": 0.276894662927451, "learning_rate": 2.9721281197260427e-06, "loss": 0.5729, "step": 553 }, { "epoch": 2.690787473396169, "grad_norm": 0.2959577260752574, "learning_rate": 2.9527698131919156e-06, "loss": 0.5698, "step": 554 }, { "epoch": 2.6956521739130435, "grad_norm": 0.28739897280327087, "learning_rate": 2.9334483050933506e-06, "loss": 0.5509, "step": 555 }, { "epoch": 2.700516874429918, "grad_norm": 0.2818512070327422, "learning_rate": 2.91416394272948e-06, "loss": 0.5638, "step": 556 }, { "epoch": 2.7053815749467924, "grad_norm": 0.2806476774239191, "learning_rate": 2.894917072731753e-06, "loss": 0.5502, "step": 557 }, { "epoch": 2.7102462754636667, "grad_norm": 0.2854039845839264, "learning_rate": 2.8757080410577042e-06, "loss": 0.5758, "step": 558 }, { "epoch": 2.715110975980541, "grad_norm": 0.3005839729890748, "learning_rate": 2.8565371929847286e-06, "loss": 0.5355, "step": 559 }, { "epoch": 2.7199756764974157, "grad_norm": 0.2852454554240035, "learning_rate": 2.83740487310389e-06, "loss": 0.5461, "step": 560 }, { "epoch": 2.72484037701429, "grad_norm": 0.2805043903962514, "learning_rate": 2.81831142531371e-06, "loss": 0.5533, "step": 561 }, { "epoch": 2.7297050775311646, "grad_norm": 0.278284787936014, "learning_rate": 2.7992571928139984e-06, "loss": 0.5843, "step": 562 }, { "epoch": 2.734569778048039, "grad_norm": 0.28004315319531786, "learning_rate": 2.780242518099675e-06, "loss": 0.5806, "step": 563 }, { "epoch": 2.739434478564913, "grad_norm": 0.2692332754546377, "learning_rate": 2.761267742954629e-06, "loss": 0.5482, "step": 564 }, { "epoch": 2.744299179081788, "grad_norm": 0.26093840862288964, "learning_rate": 2.7423332084455543e-06, "loss": 0.5705, "step": 565 }, { "epoch": 2.749163879598662, "grad_norm": 0.28110457374939907, "learning_rate": 2.723439254915834e-06, "loss": 0.5781, "step": 566 }, { "epoch": 2.754028580115537, "grad_norm": 0.27225004942475917, "learning_rate": 2.704586221979422e-06, "loss": 0.5762, "step": 567 }, { "epoch": 2.758893280632411, "grad_norm": 0.34678887132265535, "learning_rate": 2.6857744485147286e-06, "loss": 0.5433, "step": 568 }, { "epoch": 2.7637579811492854, "grad_norm": 0.27210550805207784, "learning_rate": 2.667004272658541e-06, "loss": 0.5507, "step": 569 }, { "epoch": 2.7686226816661597, "grad_norm": 0.2786452611437435, "learning_rate": 2.6482760317999338e-06, "loss": 0.5736, "step": 570 }, { "epoch": 2.7734873821830344, "grad_norm": 0.27389150632515263, "learning_rate": 2.629590062574221e-06, "loss": 0.5679, "step": 571 }, { "epoch": 2.7783520826999086, "grad_norm": 0.29467305273327854, "learning_rate": 2.610946700856885e-06, "loss": 0.5735, "step": 572 }, { "epoch": 2.7832167832167833, "grad_norm": 0.2515051525383281, "learning_rate": 2.592346281757552e-06, "loss": 0.5689, "step": 573 }, { "epoch": 2.7880814837336576, "grad_norm": 0.2552830435147318, "learning_rate": 2.5737891396139713e-06, "loss": 0.5469, "step": 574 }, { "epoch": 2.792946184250532, "grad_norm": 0.26885759554382604, "learning_rate": 2.5552756079859904e-06, "loss": 0.5526, "step": 575 }, { "epoch": 2.7978108847674066, "grad_norm": 0.2834321504380753, "learning_rate": 2.5368060196495785e-06, "loss": 0.5429, "step": 576 }, { "epoch": 2.802675585284281, "grad_norm": 0.28864858545572697, "learning_rate": 2.5183807065908296e-06, "loss": 0.5678, "step": 577 }, { "epoch": 2.8075402858011556, "grad_norm": 0.2940404870152954, "learning_rate": 2.5000000000000015e-06, "loss": 0.553, "step": 578 }, { "epoch": 2.81240498631803, "grad_norm": 0.26621780717075505, "learning_rate": 2.4816642302655634e-06, "loss": 0.5387, "step": 579 }, { "epoch": 2.817269686834904, "grad_norm": 0.40137657004542887, "learning_rate": 2.4633737269682546e-06, "loss": 0.5761, "step": 580 }, { "epoch": 2.822134387351779, "grad_norm": 0.26349536926537026, "learning_rate": 2.445128818875166e-06, "loss": 0.5608, "step": 581 }, { "epoch": 2.826999087868653, "grad_norm": 0.33678105941528547, "learning_rate": 2.4269298339338205e-06, "loss": 0.5634, "step": 582 }, { "epoch": 2.8318637883855278, "grad_norm": 0.4567255623818097, "learning_rate": 2.408777099266291e-06, "loss": 0.5453, "step": 583 }, { "epoch": 2.836728488902402, "grad_norm": 0.28926382766763636, "learning_rate": 2.3906709411633073e-06, "loss": 0.5556, "step": 584 }, { "epoch": 2.8415931894192763, "grad_norm": 0.28979181326791686, "learning_rate": 2.3726116850783987e-06, "loss": 0.5429, "step": 585 }, { "epoch": 2.8464578899361506, "grad_norm": 0.2578275780326417, "learning_rate": 2.354599655622049e-06, "loss": 0.578, "step": 586 }, { "epoch": 2.8513225904530253, "grad_norm": 0.2832433370240154, "learning_rate": 2.3366351765558437e-06, "loss": 0.5467, "step": 587 }, { "epoch": 2.8561872909698995, "grad_norm": 0.25907604040265186, "learning_rate": 2.318718570786675e-06, "loss": 0.5328, "step": 588 }, { "epoch": 2.8610519914867742, "grad_norm": 0.3355257499996, "learning_rate": 2.3008501603609147e-06, "loss": 0.5502, "step": 589 }, { "epoch": 2.8659166920036485, "grad_norm": 0.2791830270131117, "learning_rate": 2.283030266458644e-06, "loss": 0.5141, "step": 590 }, { "epoch": 2.870781392520523, "grad_norm": 0.260781169536477, "learning_rate": 2.265259209387867e-06, "loss": 0.5685, "step": 591 }, { "epoch": 2.8756460930373975, "grad_norm": 0.2655154581142735, "learning_rate": 2.2475373085787568e-06, "loss": 0.5532, "step": 592 }, { "epoch": 2.8805107935542718, "grad_norm": 0.271525316668963, "learning_rate": 2.229864882577921e-06, "loss": 0.5756, "step": 593 }, { "epoch": 2.8853754940711465, "grad_norm": 0.23653376983647245, "learning_rate": 2.2122422490426676e-06, "loss": 0.5544, "step": 594 }, { "epoch": 2.8902401945880207, "grad_norm": 0.266883606760571, "learning_rate": 2.194669724735296e-06, "loss": 0.5608, "step": 595 }, { "epoch": 2.895104895104895, "grad_norm": 0.2705642503429929, "learning_rate": 2.1771476255174056e-06, "loss": 0.5445, "step": 596 }, { "epoch": 2.8999695956217693, "grad_norm": 0.2842509880427732, "learning_rate": 2.159676266344222e-06, "loss": 0.5429, "step": 597 }, { "epoch": 2.904834296138644, "grad_norm": 0.29749824871155994, "learning_rate": 2.1422559612589266e-06, "loss": 0.5599, "step": 598 }, { "epoch": 2.9096989966555182, "grad_norm": 0.29624640077501896, "learning_rate": 2.124887023387017e-06, "loss": 0.571, "step": 599 }, { "epoch": 2.914563697172393, "grad_norm": 0.28018917318528175, "learning_rate": 2.1075697649306838e-06, "loss": 0.5515, "step": 600 }, { "epoch": 2.919428397689267, "grad_norm": 0.27398058489328575, "learning_rate": 2.0903044971631854e-06, "loss": 0.5651, "step": 601 }, { "epoch": 2.9242930982061415, "grad_norm": 0.2909278442303323, "learning_rate": 2.0730915304232692e-06, "loss": 0.5526, "step": 602 }, { "epoch": 2.929157798723016, "grad_norm": 0.469240393716124, "learning_rate": 2.055931174109579e-06, "loss": 0.5354, "step": 603 }, { "epoch": 2.9340224992398904, "grad_norm": 0.2826999345119178, "learning_rate": 2.0388237366751005e-06, "loss": 0.5461, "step": 604 }, { "epoch": 2.938887199756765, "grad_norm": 0.3163005970075211, "learning_rate": 2.02176952562162e-06, "loss": 0.5461, "step": 605 }, { "epoch": 2.9437519002736394, "grad_norm": 0.26437346964057357, "learning_rate": 2.004768847494186e-06, "loss": 0.553, "step": 606 }, { "epoch": 2.9486166007905137, "grad_norm": 0.2797324594113432, "learning_rate": 1.987822007875617e-06, "loss": 0.5698, "step": 607 }, { "epoch": 2.9534813013073884, "grad_norm": 0.2761094052806844, "learning_rate": 1.9709293113809876e-06, "loss": 0.5698, "step": 608 }, { "epoch": 2.9583460018242627, "grad_norm": 0.2702451870211346, "learning_rate": 1.954091061652172e-06, "loss": 0.5707, "step": 609 }, { "epoch": 2.9632107023411374, "grad_norm": 0.28430070425140097, "learning_rate": 1.9373075613523728e-06, "loss": 0.567, "step": 610 }, { "epoch": 2.9680754028580116, "grad_norm": 0.27985449046566496, "learning_rate": 1.920579112160685e-06, "loss": 0.5602, "step": 611 }, { "epoch": 2.972940103374886, "grad_norm": 0.2548926215077567, "learning_rate": 1.903906014766681e-06, "loss": 0.5562, "step": 612 }, { "epoch": 2.97780480389176, "grad_norm": 0.2814290936624728, "learning_rate": 1.8872885688649879e-06, "loss": 0.5471, "step": 613 }, { "epoch": 2.982669504408635, "grad_norm": 0.2733316331032585, "learning_rate": 1.8707270731499223e-06, "loss": 0.5574, "step": 614 }, { "epoch": 2.987534204925509, "grad_norm": 0.2543167272997479, "learning_rate": 1.854221825310103e-06, "loss": 0.559, "step": 615 }, { "epoch": 2.992398905442384, "grad_norm": 0.25182984990195645, "learning_rate": 1.8377731220231144e-06, "loss": 0.559, "step": 616 }, { "epoch": 2.997263605959258, "grad_norm": 0.2639861524020335, "learning_rate": 1.8213812589501611e-06, "loss": 0.5663, "step": 617 }, { "epoch": 3.0, "grad_norm": 0.3763708992245366, "learning_rate": 1.8050465307307602e-06, "loss": 0.5628, "step": 618 }, { "epoch": 3.0048647005168743, "grad_norm": 0.31757089401419397, "learning_rate": 1.78876923097745e-06, "loss": 0.5318, "step": 619 }, { "epoch": 3.009729401033749, "grad_norm": 0.31277069270446384, "learning_rate": 1.7725496522704998e-06, "loss": 0.5526, "step": 620 }, { "epoch": 3.0145941015506232, "grad_norm": 0.29043269180216497, "learning_rate": 1.7563880861526656e-06, "loss": 0.5404, "step": 621 }, { "epoch": 3.0194588020674975, "grad_norm": 0.3212771308843742, "learning_rate": 1.7402848231239317e-06, "loss": 0.5547, "step": 622 }, { "epoch": 3.024323502584372, "grad_norm": 0.2668521911689649, "learning_rate": 1.7242401526363095e-06, "loss": 0.5477, "step": 623 }, { "epoch": 3.0291882031012465, "grad_norm": 0.2950497216407057, "learning_rate": 1.70825436308862e-06, "loss": 0.5448, "step": 624 }, { "epoch": 3.034052903618121, "grad_norm": 0.2966565330288766, "learning_rate": 1.692327741821312e-06, "loss": 0.5372, "step": 625 }, { "epoch": 3.0389176041349955, "grad_norm": 0.38207516406149145, "learning_rate": 1.676460575111306e-06, "loss": 0.5366, "step": 626 }, { "epoch": 3.0437823046518697, "grad_norm": 0.28121271303511336, "learning_rate": 1.6606531481668364e-06, "loss": 0.5487, "step": 627 }, { "epoch": 3.0486470051687444, "grad_norm": 0.2794768462350028, "learning_rate": 1.6449057451223354e-06, "loss": 0.5234, "step": 628 }, { "epoch": 3.0535117056856187, "grad_norm": 0.2782954360816407, "learning_rate": 1.6292186490333172e-06, "loss": 0.5376, "step": 629 }, { "epoch": 3.058376406202493, "grad_norm": 0.26576543916614165, "learning_rate": 1.6135921418712959e-06, "loss": 0.5507, "step": 630 }, { "epoch": 3.0632411067193677, "grad_norm": 0.2783844225548137, "learning_rate": 1.5980265045187139e-06, "loss": 0.5456, "step": 631 }, { "epoch": 3.068105807236242, "grad_norm": 0.25385924195209325, "learning_rate": 1.5825220167638945e-06, "loss": 0.5276, "step": 632 }, { "epoch": 3.0729705077531166, "grad_norm": 0.2876914071869914, "learning_rate": 1.567078957296016e-06, "loss": 0.5571, "step": 633 }, { "epoch": 3.077835208269991, "grad_norm": 0.2537991579424408, "learning_rate": 1.5516976037000941e-06, "loss": 0.5228, "step": 634 }, { "epoch": 3.082699908786865, "grad_norm": 0.27125482515487254, "learning_rate": 1.5363782324520033e-06, "loss": 0.5262, "step": 635 }, { "epoch": 3.08756460930374, "grad_norm": 0.281488864195662, "learning_rate": 1.5211211189134955e-06, "loss": 0.5108, "step": 636 }, { "epoch": 3.092429309820614, "grad_norm": 0.2706727582428474, "learning_rate": 1.5059265373272574e-06, "loss": 0.5164, "step": 637 }, { "epoch": 3.0972940103374884, "grad_norm": 0.2567150008917212, "learning_rate": 1.4907947608119866e-06, "loss": 0.5598, "step": 638 }, { "epoch": 3.102158710854363, "grad_norm": 0.2768365968017163, "learning_rate": 1.475726061357463e-06, "loss": 0.5513, "step": 639 }, { "epoch": 3.1070234113712374, "grad_norm": 0.2682662222558606, "learning_rate": 1.4607207098196851e-06, "loss": 0.5259, "step": 640 }, { "epoch": 3.111888111888112, "grad_norm": 0.28320106327360367, "learning_rate": 1.4457789759159813e-06, "loss": 0.5375, "step": 641 }, { "epoch": 3.1167528124049864, "grad_norm": 0.25671866918237374, "learning_rate": 1.430901128220174e-06, "loss": 0.5163, "step": 642 }, { "epoch": 3.1216175129218606, "grad_norm": 0.28732563915717585, "learning_rate": 1.4160874341577447e-06, "loss": 0.5438, "step": 643 }, { "epoch": 3.1264822134387353, "grad_norm": 0.28701229147569035, "learning_rate": 1.4013381600010278e-06, "loss": 0.5381, "step": 644 }, { "epoch": 3.1313469139556096, "grad_norm": 0.28561141311798793, "learning_rate": 1.3866535708644335e-06, "loss": 0.529, "step": 645 }, { "epoch": 3.136211614472484, "grad_norm": 0.24333010391866297, "learning_rate": 1.3720339306996666e-06, "loss": 0.5437, "step": 646 }, { "epoch": 3.1410763149893586, "grad_norm": 0.2722745636687491, "learning_rate": 1.3574795022910014e-06, "loss": 0.5428, "step": 647 }, { "epoch": 3.145941015506233, "grad_norm": 0.2568954295562564, "learning_rate": 1.3429905472505344e-06, "loss": 0.5397, "step": 648 }, { "epoch": 3.1508057160231075, "grad_norm": 0.25170741730384455, "learning_rate": 1.3285673260135073e-06, "loss": 0.5283, "step": 649 }, { "epoch": 3.155670416539982, "grad_norm": 0.26738323267511876, "learning_rate": 1.314210097833607e-06, "loss": 0.5153, "step": 650 }, { "epoch": 3.160535117056856, "grad_norm": 0.2694029384612985, "learning_rate": 1.2999191207783129e-06, "loss": 0.5513, "step": 651 }, { "epoch": 3.165399817573731, "grad_norm": 0.2782571426006946, "learning_rate": 1.2856946517242608e-06, "loss": 0.5477, "step": 652 }, { "epoch": 3.170264518090605, "grad_norm": 0.2762183925606223, "learning_rate": 1.2715369463526173e-06, "loss": 0.5427, "step": 653 }, { "epoch": 3.1751292186074793, "grad_norm": 0.2835159805990978, "learning_rate": 1.257446259144494e-06, "loss": 0.5226, "step": 654 }, { "epoch": 3.179993919124354, "grad_norm": 0.26890956558835943, "learning_rate": 1.2434228433763657e-06, "loss": 0.5343, "step": 655 }, { "epoch": 3.1848586196412283, "grad_norm": 0.2803447620021645, "learning_rate": 1.2294669511155193e-06, "loss": 0.5654, "step": 656 }, { "epoch": 3.1897233201581026, "grad_norm": 0.2661570140851626, "learning_rate": 1.215578833215526e-06, "loss": 0.5409, "step": 657 }, { "epoch": 3.1945880206749773, "grad_norm": 0.27003678848886215, "learning_rate": 1.201758739311728e-06, "loss": 0.5345, "step": 658 }, { "epoch": 3.1994527211918515, "grad_norm": 0.2674174888141013, "learning_rate": 1.1880069178167586e-06, "loss": 0.5307, "step": 659 }, { "epoch": 3.2043174217087262, "grad_norm": 0.24818687405691206, "learning_rate": 1.1743236159160654e-06, "loss": 0.5344, "step": 660 }, { "epoch": 3.2091821222256005, "grad_norm": 0.2833097485030651, "learning_rate": 1.1607090795634802e-06, "loss": 0.5592, "step": 661 }, { "epoch": 3.2140468227424748, "grad_norm": 0.2573692960542338, "learning_rate": 1.1471635534767877e-06, "loss": 0.5472, "step": 662 }, { "epoch": 3.2189115232593495, "grad_norm": 0.263451951366132, "learning_rate": 1.133687281133331e-06, "loss": 0.5328, "step": 663 }, { "epoch": 3.2237762237762237, "grad_norm": 0.2795435812812608, "learning_rate": 1.1202805047656406e-06, "loss": 0.5414, "step": 664 }, { "epoch": 3.228640924293098, "grad_norm": 0.26767226279986783, "learning_rate": 1.1069434653570633e-06, "loss": 0.5229, "step": 665 }, { "epoch": 3.2335056248099727, "grad_norm": 0.2769305726098865, "learning_rate": 1.0936764026374547e-06, "loss": 0.5461, "step": 666 }, { "epoch": 3.238370325326847, "grad_norm": 0.2683721043300211, "learning_rate": 1.0804795550788473e-06, "loss": 0.5335, "step": 667 }, { "epoch": 3.2432350258437217, "grad_norm": 0.2586540690024237, "learning_rate": 1.0673531598911824e-06, "loss": 0.5301, "step": 668 }, { "epoch": 3.248099726360596, "grad_norm": 0.2585610952363775, "learning_rate": 1.0542974530180327e-06, "loss": 0.5506, "step": 669 }, { "epoch": 3.2529644268774702, "grad_norm": 0.28629317209593635, "learning_rate": 1.0413126691323667e-06, "loss": 0.5403, "step": 670 }, { "epoch": 3.257829127394345, "grad_norm": 0.2986383589927962, "learning_rate": 1.0283990416323336e-06, "loss": 0.5357, "step": 671 }, { "epoch": 3.262693827911219, "grad_norm": 0.2783311166127385, "learning_rate": 1.0155568026370637e-06, "loss": 0.5514, "step": 672 }, { "epoch": 3.2675585284280935, "grad_norm": 0.27270574343916193, "learning_rate": 1.0027861829824953e-06, "loss": 0.5521, "step": 673 }, { "epoch": 3.272423228944968, "grad_norm": 0.264287931479055, "learning_rate": 9.900874122172294e-07, "loss": 0.528, "step": 674 }, { "epoch": 3.2772879294618424, "grad_norm": 0.2749075097836974, "learning_rate": 9.774607185984004e-07, "loss": 0.5364, "step": 675 }, { "epoch": 3.282152629978717, "grad_norm": 0.2939999425635478, "learning_rate": 9.649063290875771e-07, "loss": 0.5598, "step": 676 }, { "epoch": 3.2870173304955914, "grad_norm": 0.33844964787035414, "learning_rate": 9.524244693466773e-07, "loss": 0.5429, "step": 677 }, { "epoch": 3.2918820310124657, "grad_norm": 0.26009160940043535, "learning_rate": 9.400153637339182e-07, "loss": 0.5413, "step": 678 }, { "epoch": 3.2967467315293404, "grad_norm": 0.29667100052103135, "learning_rate": 9.276792352997782e-07, "loss": 0.5725, "step": 679 }, { "epoch": 3.3016114320462147, "grad_norm": 0.2594635976467923, "learning_rate": 9.154163057829879e-07, "loss": 0.5181, "step": 680 }, { "epoch": 3.306476132563089, "grad_norm": 0.3042798389896856, "learning_rate": 9.032267956065516e-07, "loss": 0.5594, "step": 681 }, { "epoch": 3.3113408330799636, "grad_norm": 0.27115691672006864, "learning_rate": 8.911109238737748e-07, "loss": 0.5152, "step": 682 }, { "epoch": 3.316205533596838, "grad_norm": 0.28660219142821347, "learning_rate": 8.790689083643328e-07, "loss": 0.5708, "step": 683 }, { "epoch": 3.321070234113712, "grad_norm": 0.27926912732786296, "learning_rate": 8.671009655303531e-07, "loss": 0.5575, "step": 684 }, { "epoch": 3.325934934630587, "grad_norm": 0.23754677679704442, "learning_rate": 8.552073104925296e-07, "loss": 0.5267, "step": 685 }, { "epoch": 3.330799635147461, "grad_norm": 0.25142692556805524, "learning_rate": 8.433881570362484e-07, "loss": 0.5299, "step": 686 }, { "epoch": 3.335664335664336, "grad_norm": 0.26738368080924196, "learning_rate": 8.316437176077491e-07, "loss": 0.5492, "step": 687 }, { "epoch": 3.34052903618121, "grad_norm": 0.2849351188328476, "learning_rate": 8.199742033103091e-07, "loss": 0.5315, "step": 688 }, { "epoch": 3.3453937366980844, "grad_norm": 0.262350504323181, "learning_rate": 8.083798239004408e-07, "loss": 0.5458, "step": 689 }, { "epoch": 3.350258437214959, "grad_norm": 0.2678230062738687, "learning_rate": 7.968607877841333e-07, "loss": 0.5574, "step": 690 }, { "epoch": 3.3551231377318333, "grad_norm": 0.250760824199836, "learning_rate": 7.854173020130906e-07, "loss": 0.5384, "step": 691 }, { "epoch": 3.359987838248708, "grad_norm": 0.2646454489095381, "learning_rate": 7.740495722810271e-07, "loss": 0.534, "step": 692 }, { "epoch": 3.3648525387655823, "grad_norm": 0.2874912380934125, "learning_rate": 7.627578029199562e-07, "loss": 0.5574, "step": 693 }, { "epoch": 3.3697172392824566, "grad_norm": 0.26117055690787866, "learning_rate": 7.515421968965242e-07, "loss": 0.5413, "step": 694 }, { "epoch": 3.374581939799331, "grad_norm": 0.27749657198179634, "learning_rate": 7.404029558083653e-07, "loss": 0.5301, "step": 695 }, { "epoch": 3.3794466403162056, "grad_norm": 0.27232903727854973, "learning_rate": 7.293402798804667e-07, "loss": 0.5434, "step": 696 }, { "epoch": 3.38431134083308, "grad_norm": 0.5426235578901134, "learning_rate": 7.183543679615834e-07, "loss": 0.5442, "step": 697 }, { "epoch": 3.3891760413499545, "grad_norm": 0.2673299942613958, "learning_rate": 7.074454175206524e-07, "loss": 0.5621, "step": 698 }, { "epoch": 3.394040741866829, "grad_norm": 0.269226772191099, "learning_rate": 6.966136246432492e-07, "loss": 0.5279, "step": 699 }, { "epoch": 3.398905442383703, "grad_norm": 0.2485253898279206, "learning_rate": 6.858591840280627e-07, "loss": 0.5316, "step": 700 }, { "epoch": 3.4037701429005778, "grad_norm": 0.26619259707291715, "learning_rate": 6.751822889833926e-07, "loss": 0.5503, "step": 701 }, { "epoch": 3.408634843417452, "grad_norm": 0.2755743118570231, "learning_rate": 6.645831314236817e-07, "loss": 0.5364, "step": 702 }, { "epoch": 3.4134995439343268, "grad_norm": 0.2623575079453286, "learning_rate": 6.540619018660555e-07, "loss": 0.5329, "step": 703 }, { "epoch": 3.418364244451201, "grad_norm": 0.2999782351004191, "learning_rate": 6.436187894269086e-07, "loss": 0.5477, "step": 704 }, { "epoch": 3.4232289449680753, "grad_norm": 0.3155770599805052, "learning_rate": 6.332539818184985e-07, "loss": 0.5273, "step": 705 }, { "epoch": 3.42809364548495, "grad_norm": 0.2481315893130342, "learning_rate": 6.229676653455719e-07, "loss": 0.5409, "step": 706 }, { "epoch": 3.4329583460018243, "grad_norm": 0.26832697306240966, "learning_rate": 6.127600249020216e-07, "loss": 0.5452, "step": 707 }, { "epoch": 3.4378230465186985, "grad_norm": 0.2696685856730689, "learning_rate": 6.026312439675553e-07, "loss": 0.5338, "step": 708 }, { "epoch": 3.4426877470355732, "grad_norm": 0.2767819640520473, "learning_rate": 5.925815046044026e-07, "loss": 0.5375, "step": 709 }, { "epoch": 3.4475524475524475, "grad_norm": 0.26416581654552523, "learning_rate": 5.826109874540409e-07, "loss": 0.5399, "step": 710 }, { "epoch": 3.4524171480693218, "grad_norm": 0.2860445380423454, "learning_rate": 5.727198717339511e-07, "loss": 0.5683, "step": 711 }, { "epoch": 3.4572818485861965, "grad_norm": 0.28746477125025693, "learning_rate": 5.6290833523439e-07, "loss": 0.5453, "step": 712 }, { "epoch": 3.4621465491030707, "grad_norm": 0.27123616812056267, "learning_rate": 5.531765543152002e-07, "loss": 0.547, "step": 713 }, { "epoch": 3.4670112496199454, "grad_norm": 0.27064766684975, "learning_rate": 5.435247039026398e-07, "loss": 0.5246, "step": 714 }, { "epoch": 3.4718759501368197, "grad_norm": 0.2675591802760159, "learning_rate": 5.33952957486234e-07, "loss": 0.5371, "step": 715 }, { "epoch": 3.476740650653694, "grad_norm": 0.2577337953283578, "learning_rate": 5.244614871156612e-07, "loss": 0.5532, "step": 716 }, { "epoch": 3.4816053511705687, "grad_norm": 0.2765336326699086, "learning_rate": 5.150504633976572e-07, "loss": 0.5288, "step": 717 }, { "epoch": 3.486470051687443, "grad_norm": 0.2552545600116987, "learning_rate": 5.057200554929509e-07, "loss": 0.559, "step": 718 }, { "epoch": 3.4913347522043177, "grad_norm": 0.2577474961856747, "learning_rate": 4.964704311132224e-07, "loss": 0.5327, "step": 719 }, { "epoch": 3.496199452721192, "grad_norm": 0.2544135497241495, "learning_rate": 4.873017565180871e-07, "loss": 0.5315, "step": 720 }, { "epoch": 3.501064153238066, "grad_norm": 0.2613617825216244, "learning_rate": 4.782141965121129e-07, "loss": 0.5452, "step": 721 }, { "epoch": 3.5059288537549405, "grad_norm": 0.2570853485283409, "learning_rate": 4.6920791444184934e-07, "loss": 0.5366, "step": 722 }, { "epoch": 3.510793554271815, "grad_norm": 0.25029425661462223, "learning_rate": 4.602830721928997e-07, "loss": 0.532, "step": 723 }, { "epoch": 3.5156582547886894, "grad_norm": 0.25969941492008564, "learning_rate": 4.5143983018700485e-07, "loss": 0.5493, "step": 724 }, { "epoch": 3.520522955305564, "grad_norm": 0.2969063406368926, "learning_rate": 4.4267834737916295e-07, "loss": 0.556, "step": 725 }, { "epoch": 3.5253876558224384, "grad_norm": 0.2625151132858115, "learning_rate": 4.33998781254773e-07, "loss": 0.5613, "step": 726 }, { "epoch": 3.5302523563393127, "grad_norm": 0.2581320642349313, "learning_rate": 4.2540128782679934e-07, "loss": 0.5343, "step": 727 }, { "epoch": 3.5351170568561874, "grad_norm": 0.2803545127872987, "learning_rate": 4.1688602163297564e-07, "loss": 0.5394, "step": 728 }, { "epoch": 3.5399817573730616, "grad_norm": 0.2950953986558406, "learning_rate": 4.0845313573301736e-07, "loss": 0.5561, "step": 729 }, { "epoch": 3.5448464578899364, "grad_norm": 0.2684371721126504, "learning_rate": 4.001027817058789e-07, "loss": 0.5315, "step": 730 }, { "epoch": 3.5497111584068106, "grad_norm": 0.25452762713534766, "learning_rate": 3.9183510964702463e-07, "loss": 0.535, "step": 731 }, { "epoch": 3.554575858923685, "grad_norm": 0.27284279000641687, "learning_rate": 3.836502681657289e-07, "loss": 0.5376, "step": 732 }, { "epoch": 3.5594405594405596, "grad_norm": 0.28341394245584633, "learning_rate": 3.755484043824131e-07, "loss": 0.5556, "step": 733 }, { "epoch": 3.564305259957434, "grad_norm": 0.25237362907086613, "learning_rate": 3.675296639259912e-07, "loss": 0.5512, "step": 734 }, { "epoch": 3.5691699604743086, "grad_norm": 0.276525141793876, "learning_rate": 3.595941909312595e-07, "loss": 0.5246, "step": 735 }, { "epoch": 3.574034660991183, "grad_norm": 0.2526380857652992, "learning_rate": 3.517421280363004e-07, "loss": 0.5449, "step": 736 }, { "epoch": 3.578899361508057, "grad_norm": 0.26206050395341407, "learning_rate": 3.439736163799251e-07, "loss": 0.5235, "step": 737 }, { "epoch": 3.5837640620249314, "grad_norm": 0.25356408590019436, "learning_rate": 3.362887955991301e-07, "loss": 0.521, "step": 738 }, { "epoch": 3.588628762541806, "grad_norm": 0.24019814987325147, "learning_rate": 3.2868780382658895e-07, "loss": 0.5264, "step": 739 }, { "epoch": 3.5934934630586803, "grad_norm": 0.25285707964888665, "learning_rate": 3.2117077768817395e-07, "loss": 0.5621, "step": 740 }, { "epoch": 3.598358163575555, "grad_norm": 0.27260229620262144, "learning_rate": 3.1373785230049356e-07, "loss": 0.5524, "step": 741 }, { "epoch": 3.6032228640924293, "grad_norm": 0.2722440992730437, "learning_rate": 3.0638916126846885e-07, "loss": 0.5525, "step": 742 }, { "epoch": 3.6080875646093036, "grad_norm": 0.2634649687327327, "learning_rate": 2.991248366829291e-07, "loss": 0.5495, "step": 743 }, { "epoch": 3.6129522651261783, "grad_norm": 0.2615603819542947, "learning_rate": 2.91945009118238e-07, "loss": 0.541, "step": 744 }, { "epoch": 3.6178169656430526, "grad_norm": 0.7358681365578488, "learning_rate": 2.848498076299483e-07, "loss": 0.5432, "step": 745 }, { "epoch": 3.6226816661599273, "grad_norm": 0.388594899763495, "learning_rate": 2.7783935975247867e-07, "loss": 0.5294, "step": 746 }, { "epoch": 3.6275463666768015, "grad_norm": 0.25790443727551016, "learning_rate": 2.7091379149682683e-07, "loss": 0.527, "step": 747 }, { "epoch": 3.632411067193676, "grad_norm": 0.2630355426758199, "learning_rate": 2.6407322734829763e-07, "loss": 0.5337, "step": 748 }, { "epoch": 3.63727576771055, "grad_norm": 0.24636200962143406, "learning_rate": 2.573177902642726e-07, "loss": 0.5336, "step": 749 }, { "epoch": 3.6421404682274248, "grad_norm": 0.2503473601342059, "learning_rate": 2.506476016719922e-07, "loss": 0.5278, "step": 750 }, { "epoch": 3.647005168744299, "grad_norm": 0.2646923021723898, "learning_rate": 2.440627814663804e-07, "loss": 0.5458, "step": 751 }, { "epoch": 3.6518698692611737, "grad_norm": 0.28062789745222055, "learning_rate": 2.3756344800788421e-07, "loss": 0.5404, "step": 752 }, { "epoch": 3.656734569778048, "grad_norm": 0.25703027388085775, "learning_rate": 2.3114971812034981e-07, "loss": 0.5481, "step": 753 }, { "epoch": 3.6615992702949223, "grad_norm": 0.3008462495958372, "learning_rate": 2.2482170708892083e-07, "loss": 0.5665, "step": 754 }, { "epoch": 3.666463970811797, "grad_norm": 0.25601999403821707, "learning_rate": 2.1857952865796616e-07, "loss": 0.5635, "step": 755 }, { "epoch": 3.6713286713286712, "grad_norm": 0.27138561209769946, "learning_rate": 2.124232950290367e-07, "loss": 0.5453, "step": 756 }, { "epoch": 3.676193371845546, "grad_norm": 0.2513593785822902, "learning_rate": 2.0635311685884675e-07, "loss": 0.5274, "step": 757 }, { "epoch": 3.68105807236242, "grad_norm": 0.2565399270175768, "learning_rate": 2.0036910325728521e-07, "loss": 0.5332, "step": 758 }, { "epoch": 3.6859227728792945, "grad_norm": 0.28415452387362666, "learning_rate": 1.9447136178545766e-07, "loss": 0.5676, "step": 759 }, { "epoch": 3.690787473396169, "grad_norm": 0.25144424003282845, "learning_rate": 1.8865999845374794e-07, "loss": 0.5401, "step": 760 }, { "epoch": 3.6956521739130435, "grad_norm": 0.2712363196347405, "learning_rate": 1.8293511771991624e-07, "loss": 0.5571, "step": 761 }, { "epoch": 3.700516874429918, "grad_norm": 0.27491234015674665, "learning_rate": 1.7729682248721848e-07, "loss": 0.5219, "step": 762 }, { "epoch": 3.7053815749467924, "grad_norm": 0.2522812744244863, "learning_rate": 1.7174521410256162e-07, "loss": 0.5326, "step": 763 }, { "epoch": 3.7102462754636667, "grad_norm": 0.2990835989369813, "learning_rate": 1.6628039235467686e-07, "loss": 0.5286, "step": 764 }, { "epoch": 3.715110975980541, "grad_norm": 0.2565780884237795, "learning_rate": 1.6090245547232707e-07, "loss": 0.5412, "step": 765 }, { "epoch": 3.7199756764974157, "grad_norm": 0.2607318374047698, "learning_rate": 1.5561150012254446e-07, "loss": 0.5473, "step": 766 }, { "epoch": 3.72484037701429, "grad_norm": 0.26802482318696, "learning_rate": 1.5040762140888843e-07, "loss": 0.5286, "step": 767 }, { "epoch": 3.7297050775311646, "grad_norm": 0.357300151073744, "learning_rate": 1.4529091286973994e-07, "loss": 0.5407, "step": 768 }, { "epoch": 3.734569778048039, "grad_norm": 0.29304284304963035, "learning_rate": 1.402614664766172e-07, "loss": 0.5739, "step": 769 }, { "epoch": 3.739434478564913, "grad_norm": 0.26120344800544076, "learning_rate": 1.353193726325247e-07, "loss": 0.5561, "step": 770 }, { "epoch": 3.744299179081788, "grad_norm": 0.27896242544117483, "learning_rate": 1.3046472017032685e-07, "loss": 0.5494, "step": 771 }, { "epoch": 3.749163879598662, "grad_norm": 0.27994163089285834, "learning_rate": 1.2569759635115086e-07, "loss": 0.5632, "step": 772 }, { "epoch": 3.754028580115537, "grad_norm": 0.37095939164121267, "learning_rate": 1.210180868628219e-07, "loss": 0.5346, "step": 773 }, { "epoch": 3.758893280632411, "grad_norm": 0.25582404015705934, "learning_rate": 1.1642627581831767e-07, "loss": 0.5269, "step": 774 }, { "epoch": 3.7637579811492854, "grad_norm": 0.24741824170121834, "learning_rate": 1.1192224575425848e-07, "loss": 0.553, "step": 775 }, { "epoch": 3.7686226816661597, "grad_norm": 0.26013412811119957, "learning_rate": 1.0750607762942622e-07, "loss": 0.5443, "step": 776 }, { "epoch": 3.7734873821830344, "grad_norm": 0.23937616552802693, "learning_rate": 1.0317785082330555e-07, "loss": 0.542, "step": 777 }, { "epoch": 3.7783520826999086, "grad_norm": 0.27662471609042066, "learning_rate": 9.89376431346606e-08, "loss": 0.565, "step": 778 }, { "epoch": 3.7832167832167833, "grad_norm": 0.2770174712299304, "learning_rate": 9.478553078013042e-08, "loss": 0.5341, "step": 779 }, { "epoch": 3.7880814837336576, "grad_norm": 0.25467569265119394, "learning_rate": 9.072158839286748e-08, "loss": 0.54, "step": 780 }, { "epoch": 3.792946184250532, "grad_norm": 0.26951634651330447, "learning_rate": 8.674588902118919e-08, "loss": 0.5236, "step": 781 }, { "epoch": 3.7978108847674066, "grad_norm": 0.259821430769431, "learning_rate": 8.285850412726837e-08, "loss": 0.5335, "step": 782 }, { "epoch": 3.802675585284281, "grad_norm": 0.29661093064338573, "learning_rate": 7.905950358584768e-08, "loss": 0.5584, "step": 783 }, { "epoch": 3.8075402858011556, "grad_norm": 0.29153984224623186, "learning_rate": 7.534895568298395e-08, "loss": 0.5477, "step": 784 }, { "epoch": 3.81240498631803, "grad_norm": 0.25718490251334, "learning_rate": 7.172692711482022e-08, "loss": 0.5608, "step": 785 }, { "epoch": 3.817269686834904, "grad_norm": 0.2896914739263431, "learning_rate": 6.819348298638839e-08, "loss": 0.5624, "step": 786 }, { "epoch": 3.822134387351779, "grad_norm": 0.2516018017568526, "learning_rate": 6.474868681043578e-08, "loss": 0.5313, "step": 787 }, { "epoch": 3.826999087868653, "grad_norm": 0.2537588977378279, "learning_rate": 6.13926005062876e-08, "loss": 0.5241, "step": 788 }, { "epoch": 3.8318637883855278, "grad_norm": 0.26163242207815546, "learning_rate": 5.8125284398730666e-08, "loss": 0.5238, "step": 789 }, { "epoch": 3.836728488902402, "grad_norm": 0.2753207652054593, "learning_rate": 5.4946797216931524e-08, "loss": 0.5493, "step": 790 }, { "epoch": 3.8415931894192763, "grad_norm": 0.4014078763583581, "learning_rate": 5.185719609337836e-08, "loss": 0.525, "step": 791 }, { "epoch": 3.8464578899361506, "grad_norm": 0.2889768926689584, "learning_rate": 4.885653656285627e-08, "loss": 0.5322, "step": 792 }, { "epoch": 3.8513225904530253, "grad_norm": 0.3102463020818238, "learning_rate": 4.5944872561448084e-08, "loss": 0.5648, "step": 793 }, { "epoch": 3.8561872909698995, "grad_norm": 0.2540205640986455, "learning_rate": 4.3122256425563444e-08, "loss": 0.543, "step": 794 }, { "epoch": 3.8610519914867742, "grad_norm": 0.27043507557046537, "learning_rate": 4.038873889100237e-08, "loss": 0.5556, "step": 795 }, { "epoch": 3.8659166920036485, "grad_norm": 0.26891814006504855, "learning_rate": 3.77443690920376e-08, "loss": 0.5717, "step": 796 }, { "epoch": 3.870781392520523, "grad_norm": 0.23077813601697678, "learning_rate": 3.518919456053649e-08, "loss": 0.5387, "step": 797 }, { "epoch": 3.8756460930373975, "grad_norm": 0.3299888054451032, "learning_rate": 3.2723261225102164e-08, "loss": 0.5498, "step": 798 }, { "epoch": 3.8805107935542718, "grad_norm": 0.2695699953679799, "learning_rate": 3.034661341025258e-08, "loss": 0.5393, "step": 799 }, { "epoch": 3.8853754940711465, "grad_norm": 0.26264746207922285, "learning_rate": 2.8059293835620006e-08, "loss": 0.5367, "step": 800 }, { "epoch": 3.8902401945880207, "grad_norm": 0.2906233561953433, "learning_rate": 2.5861343615184997e-08, "loss": 0.5483, "step": 801 }, { "epoch": 3.895104895104895, "grad_norm": 0.26082308979138996, "learning_rate": 2.3752802256536423e-08, "loss": 0.5509, "step": 802 }, { "epoch": 3.8999695956217693, "grad_norm": 0.26243414502263285, "learning_rate": 2.173370766016314e-08, "loss": 0.5244, "step": 803 }, { "epoch": 3.904834296138644, "grad_norm": 0.2396313840427589, "learning_rate": 1.98040961187701e-08, "loss": 0.5252, "step": 804 }, { "epoch": 3.9096989966555182, "grad_norm": 0.26749637488953376, "learning_rate": 1.7964002316628316e-08, "loss": 0.5454, "step": 805 }, { "epoch": 3.914563697172393, "grad_norm": 0.28231761799640104, "learning_rate": 1.6213459328950355e-08, "loss": 0.565, "step": 806 }, { "epoch": 3.919428397689267, "grad_norm": 0.2511696096664254, "learning_rate": 1.4552498621295264e-08, "loss": 0.5233, "step": 807 }, { "epoch": 3.9242930982061415, "grad_norm": 0.22862186801123288, "learning_rate": 1.2981150049004021e-08, "loss": 0.5337, "step": 808 }, { "epoch": 3.929157798723016, "grad_norm": 0.24897660074063854, "learning_rate": 1.1499441856663296e-08, "loss": 0.5578, "step": 809 }, { "epoch": 3.9340224992398904, "grad_norm": 0.26710346275879765, "learning_rate": 1.0107400677596413e-08, "loss": 0.5639, "step": 810 }, { "epoch": 3.938887199756765, "grad_norm": 0.25817900061264243, "learning_rate": 8.805051533384846e-09, "loss": 0.5397, "step": 811 }, { "epoch": 3.9437519002736394, "grad_norm": 0.25661445582035397, "learning_rate": 7.59241783341913e-09, "loss": 0.5365, "step": 812 }, { "epoch": 3.9486166007905137, "grad_norm": 0.2677011754772838, "learning_rate": 6.469521374477539e-09, "loss": 0.5353, "step": 813 }, { "epoch": 3.9534813013073884, "grad_norm": 0.2864530495225435, "learning_rate": 5.436382340335833e-09, "loss": 0.5441, "step": 814 }, { "epoch": 3.9583460018242627, "grad_norm": 0.2415904761955439, "learning_rate": 4.493019301401447e-09, "loss": 0.5262, "step": 815 }, { "epoch": 3.9632107023411374, "grad_norm": 0.2657479635991742, "learning_rate": 3.6394492143820847e-09, "loss": 0.5425, "step": 816 }, { "epoch": 3.9680754028580116, "grad_norm": 0.2443786914100295, "learning_rate": 2.875687421980966e-09, "loss": 0.5457, "step": 817 }, { "epoch": 3.972940103374886, "grad_norm": 0.2693045612925708, "learning_rate": 2.201747652618713e-09, "loss": 0.5411, "step": 818 }, { "epoch": 3.97780480389176, "grad_norm": 0.3342079334008971, "learning_rate": 1.6176420201902132e-09, "loss": 0.5469, "step": 819 }, { "epoch": 3.982669504408635, "grad_norm": 0.27406984681523167, "learning_rate": 1.1233810238425735e-09, "loss": 0.5498, "step": 820 }, { "epoch": 3.987534204925509, "grad_norm": 0.27439832616969007, "learning_rate": 7.189735477913795e-10, "loss": 0.5326, "step": 821 }, { "epoch": 3.992398905442384, "grad_norm": 0.25816930859088183, "learning_rate": 4.0442686115582665e-10, "loss": 0.5297, "step": 822 }, { "epoch": 3.997263605959258, "grad_norm": 0.2715657849904006, "learning_rate": 1.797466178327101e-10, "loss": 0.5398, "step": 823 }, { "epoch": 4.0, "grad_norm": 0.350890890063273, "learning_rate": 4.4936856390398465e-11, "loss": 0.5195, "step": 824 }, { "epoch": 4.0, "step": 824, "total_flos": 1671471016509440.0, "train_loss": 0.5990438958973561, "train_runtime": 156717.3164, "train_samples_per_second": 0.671, "train_steps_per_second": 0.005 } ], "logging_steps": 1, "max_steps": 824, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1671471016509440.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }