{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1234.567901234568, "eval_steps": 500, "global_step": 20000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.06172839506172839, "learning_rate": 5e-09, "loss": 8.604, "step": 1 }, { "epoch": 1.2345679012345678, "learning_rate": 1e-07, "loss": 8.0873, "step": 20 }, { "epoch": 2.4691358024691357, "learning_rate": 2e-07, "loss": 7.8074, "step": 40 }, { "epoch": 3.7037037037037037, "learning_rate": 3e-07, "loss": 7.0763, "step": 60 }, { "epoch": 4.938271604938271, "learning_rate": 4e-07, "loss": 6.2969, "step": 80 }, { "epoch": 6.172839506172839, "learning_rate": 5e-07, "loss": 5.9334, "step": 100 }, { "epoch": 7.407407407407407, "learning_rate": 6e-07, "loss": 5.4919, "step": 120 }, { "epoch": 8.641975308641975, "learning_rate": 7e-07, "loss": 5.0659, "step": 140 }, { "epoch": 9.876543209876543, "learning_rate": 8e-07, "loss": 4.9089, "step": 160 }, { "epoch": 11.11111111111111, "learning_rate": 9e-07, "loss": 4.7144, "step": 180 }, { "epoch": 12.345679012345679, "learning_rate": 1e-06, "loss": 4.7373, "step": 200 }, { "epoch": 13.580246913580247, "learning_rate": 9.997245010407738e-07, "loss": 4.3848, "step": 220 }, { "epoch": 14.814814814814815, "learning_rate": 9.994490020815477e-07, "loss": 4.3457, "step": 240 }, { "epoch": 16.049382716049383, "learning_rate": 9.991735031223215e-07, "loss": 4.2217, "step": 260 }, { "epoch": 17.28395061728395, "learning_rate": 9.988980041630952e-07, "loss": 4.1273, "step": 280 }, { "epoch": 18.51851851851852, "learning_rate": 9.986225052038692e-07, "loss": 4.0123, "step": 300 }, { "epoch": 19.753086419753085, "learning_rate": 9.98347006244643e-07, "loss": 4.0784, "step": 320 }, { "epoch": 20.987654320987655, "learning_rate": 9.98071507285417e-07, "loss": 3.9415, "step": 340 }, { "epoch": 22.22222222222222, "learning_rate": 9.977960083261906e-07, "loss": 3.843, "step": 360 }, { "epoch": 23.45679012345679, "learning_rate": 9.975205093669647e-07, "loss": 3.8174, "step": 380 }, { "epoch": 24.691358024691358, "learning_rate": 9.972450104077383e-07, "loss": 3.7376, "step": 400 }, { "epoch": 25.925925925925927, "learning_rate": 9.969695114485122e-07, "loss": 3.7876, "step": 420 }, { "epoch": 27.160493827160494, "learning_rate": 9.96694012489286e-07, "loss": 3.7585, "step": 440 }, { "epoch": 28.395061728395063, "learning_rate": 9.9641851353006e-07, "loss": 3.6304, "step": 460 }, { "epoch": 29.62962962962963, "learning_rate": 9.961430145708338e-07, "loss": 3.6751, "step": 480 }, { "epoch": 30.864197530864196, "learning_rate": 9.958675156116076e-07, "loss": 3.677, "step": 500 }, { "epoch": 32.098765432098766, "learning_rate": 9.955920166523815e-07, "loss": 3.6556, "step": 520 }, { "epoch": 33.333333333333336, "learning_rate": 9.953165176931551e-07, "loss": 3.5897, "step": 540 }, { "epoch": 34.5679012345679, "learning_rate": 9.950410187339292e-07, "loss": 3.7304, "step": 560 }, { "epoch": 35.80246913580247, "learning_rate": 9.94765519774703e-07, "loss": 3.568, "step": 580 }, { "epoch": 37.03703703703704, "learning_rate": 9.94490020815477e-07, "loss": 3.6207, "step": 600 }, { "epoch": 38.27160493827161, "learning_rate": 9.942145218562508e-07, "loss": 3.4759, "step": 620 }, { "epoch": 39.50617283950617, "learning_rate": 9.939390228970246e-07, "loss": 3.4513, "step": 640 }, { "epoch": 40.74074074074074, "learning_rate": 9.936635239377985e-07, "loss": 3.372, "step": 660 }, { "epoch": 41.97530864197531, "learning_rate": 9.933880249785724e-07, "loss": 3.2601, "step": 680 }, { "epoch": 43.20987654320987, "learning_rate": 9.93112526019346e-07, "loss": 3.3071, "step": 700 }, { "epoch": 44.44444444444444, "learning_rate": 9.9283702706012e-07, "loss": 3.2768, "step": 720 }, { "epoch": 45.67901234567901, "learning_rate": 9.925615281008937e-07, "loss": 3.3103, "step": 740 }, { "epoch": 46.91358024691358, "learning_rate": 9.922860291416678e-07, "loss": 3.2807, "step": 760 }, { "epoch": 48.148148148148145, "learning_rate": 9.920105301824414e-07, "loss": 3.1839, "step": 780 }, { "epoch": 49.382716049382715, "learning_rate": 9.917350312232155e-07, "loss": 3.1689, "step": 800 }, { "epoch": 50.617283950617285, "learning_rate": 9.914595322639892e-07, "loss": 3.17, "step": 820 }, { "epoch": 51.851851851851855, "learning_rate": 9.91184033304763e-07, "loss": 3.1598, "step": 840 }, { "epoch": 53.08641975308642, "learning_rate": 9.909085343455369e-07, "loss": 3.1215, "step": 860 }, { "epoch": 54.32098765432099, "learning_rate": 9.906330353863107e-07, "loss": 3.102, "step": 880 }, { "epoch": 55.55555555555556, "learning_rate": 9.903575364270846e-07, "loss": 3.0819, "step": 900 }, { "epoch": 56.79012345679013, "learning_rate": 9.900820374678584e-07, "loss": 3.0729, "step": 920 }, { "epoch": 58.02469135802469, "learning_rate": 9.898065385086323e-07, "loss": 3.0639, "step": 940 }, { "epoch": 59.25925925925926, "learning_rate": 9.89531039549406e-07, "loss": 3.0172, "step": 960 }, { "epoch": 60.49382716049383, "learning_rate": 9.8925554059018e-07, "loss": 3.0463, "step": 980 }, { "epoch": 61.72839506172839, "learning_rate": 9.889800416309537e-07, "loss": 2.9424, "step": 1000 }, { "epoch": 62.96296296296296, "learning_rate": 9.887045426717277e-07, "loss": 3.0018, "step": 1020 }, { "epoch": 64.19753086419753, "learning_rate": 9.884290437125014e-07, "loss": 3.0268, "step": 1040 }, { "epoch": 65.4320987654321, "learning_rate": 9.881535447532755e-07, "loss": 3.0157, "step": 1060 }, { "epoch": 66.66666666666667, "learning_rate": 9.878780457940491e-07, "loss": 2.9853, "step": 1080 }, { "epoch": 67.90123456790124, "learning_rate": 9.87602546834823e-07, "loss": 2.8881, "step": 1100 }, { "epoch": 69.1358024691358, "learning_rate": 9.873270478755968e-07, "loss": 2.965, "step": 1120 }, { "epoch": 70.37037037037037, "learning_rate": 9.870515489163707e-07, "loss": 2.9127, "step": 1140 }, { "epoch": 71.60493827160494, "learning_rate": 9.867760499571445e-07, "loss": 2.8881, "step": 1160 }, { "epoch": 72.8395061728395, "learning_rate": 9.865005509979184e-07, "loss": 2.8964, "step": 1180 }, { "epoch": 74.07407407407408, "learning_rate": 9.862250520386923e-07, "loss": 2.932, "step": 1200 }, { "epoch": 75.30864197530865, "learning_rate": 9.85949553079466e-07, "loss": 2.9062, "step": 1220 }, { "epoch": 76.54320987654322, "learning_rate": 9.8567405412024e-07, "loss": 2.9141, "step": 1240 }, { "epoch": 77.77777777777777, "learning_rate": 9.853985551610136e-07, "loss": 2.8072, "step": 1260 }, { "epoch": 79.01234567901234, "learning_rate": 9.851230562017877e-07, "loss": 2.8403, "step": 1280 }, { "epoch": 80.24691358024691, "learning_rate": 9.848475572425613e-07, "loss": 2.8484, "step": 1300 }, { "epoch": 81.48148148148148, "learning_rate": 9.845720582833354e-07, "loss": 2.8565, "step": 1320 }, { "epoch": 82.71604938271605, "learning_rate": 9.842965593241093e-07, "loss": 2.8241, "step": 1340 }, { "epoch": 83.95061728395062, "learning_rate": 9.840210603648831e-07, "loss": 2.8383, "step": 1360 }, { "epoch": 85.18518518518519, "learning_rate": 9.837455614056568e-07, "loss": 2.8188, "step": 1380 }, { "epoch": 86.41975308641975, "learning_rate": 9.834700624464309e-07, "loss": 2.8681, "step": 1400 }, { "epoch": 87.65432098765432, "learning_rate": 9.831945634872045e-07, "loss": 2.7453, "step": 1420 }, { "epoch": 88.88888888888889, "learning_rate": 9.829190645279786e-07, "loss": 2.7488, "step": 1440 }, { "epoch": 90.12345679012346, "learning_rate": 9.826435655687522e-07, "loss": 2.7859, "step": 1460 }, { "epoch": 91.35802469135803, "learning_rate": 9.82368066609526e-07, "loss": 2.8079, "step": 1480 }, { "epoch": 92.5925925925926, "learning_rate": 9.820925676503e-07, "loss": 2.717, "step": 1500 }, { "epoch": 93.82716049382717, "learning_rate": 9.818170686910738e-07, "loss": 2.7502, "step": 1520 }, { "epoch": 95.06172839506173, "learning_rate": 9.815415697318477e-07, "loss": 2.7395, "step": 1540 }, { "epoch": 96.29629629629629, "learning_rate": 9.812660707726215e-07, "loss": 2.7172, "step": 1560 }, { "epoch": 97.53086419753086, "learning_rate": 9.809905718133954e-07, "loss": 2.6894, "step": 1580 }, { "epoch": 98.76543209876543, "learning_rate": 9.807150728541692e-07, "loss": 2.7527, "step": 1600 }, { "epoch": 100.0, "learning_rate": 9.80439573894943e-07, "loss": 2.7461, "step": 1620 }, { "epoch": 101.23456790123457, "learning_rate": 9.801640749357167e-07, "loss": 2.782, "step": 1640 }, { "epoch": 102.46913580246914, "learning_rate": 9.798885759764908e-07, "loss": 2.7753, "step": 1660 }, { "epoch": 103.70370370370371, "learning_rate": 9.796130770172645e-07, "loss": 2.7902, "step": 1680 }, { "epoch": 104.93827160493827, "learning_rate": 9.793375780580385e-07, "loss": 2.7305, "step": 1700 }, { "epoch": 106.17283950617283, "learning_rate": 9.790620790988122e-07, "loss": 2.7476, "step": 1720 }, { "epoch": 107.4074074074074, "learning_rate": 9.787865801395862e-07, "loss": 2.715, "step": 1740 }, { "epoch": 108.64197530864197, "learning_rate": 9.785110811803599e-07, "loss": 2.6883, "step": 1760 }, { "epoch": 109.87654320987654, "learning_rate": 9.782355822211337e-07, "loss": 2.6921, "step": 1780 }, { "epoch": 111.11111111111111, "learning_rate": 9.779600832619076e-07, "loss": 2.7132, "step": 1800 }, { "epoch": 112.34567901234568, "learning_rate": 9.776845843026815e-07, "loss": 2.6779, "step": 1820 }, { "epoch": 113.58024691358025, "learning_rate": 9.774090853434553e-07, "loss": 2.6119, "step": 1840 }, { "epoch": 114.81481481481481, "learning_rate": 9.771335863842292e-07, "loss": 2.6716, "step": 1860 }, { "epoch": 116.04938271604938, "learning_rate": 9.76858087425003e-07, "loss": 2.6666, "step": 1880 }, { "epoch": 117.28395061728395, "learning_rate": 9.765825884657767e-07, "loss": 2.6476, "step": 1900 }, { "epoch": 118.51851851851852, "learning_rate": 9.763070895065508e-07, "loss": 2.6393, "step": 1920 }, { "epoch": 119.75308641975309, "learning_rate": 9.760315905473244e-07, "loss": 2.627, "step": 1940 }, { "epoch": 120.98765432098766, "learning_rate": 9.757560915880985e-07, "loss": 2.6067, "step": 1960 }, { "epoch": 122.22222222222223, "learning_rate": 9.754805926288721e-07, "loss": 2.6015, "step": 1980 }, { "epoch": 123.45679012345678, "learning_rate": 9.752050936696462e-07, "loss": 2.6428, "step": 2000 }, { "epoch": 124.69135802469135, "learning_rate": 9.749295947104198e-07, "loss": 2.6251, "step": 2020 }, { "epoch": 125.92592592592592, "learning_rate": 9.746540957511937e-07, "loss": 2.655, "step": 2040 }, { "epoch": 127.1604938271605, "learning_rate": 9.743785967919676e-07, "loss": 2.5351, "step": 2060 }, { "epoch": 128.39506172839506, "learning_rate": 9.741030978327416e-07, "loss": 2.582, "step": 2080 }, { "epoch": 129.62962962962962, "learning_rate": 9.738275988735153e-07, "loss": 2.5874, "step": 2100 }, { "epoch": 130.8641975308642, "learning_rate": 9.735520999142893e-07, "loss": 2.5603, "step": 2120 }, { "epoch": 132.09876543209876, "learning_rate": 9.73276600955063e-07, "loss": 2.5398, "step": 2140 }, { "epoch": 133.33333333333334, "learning_rate": 9.730011019958369e-07, "loss": 2.5265, "step": 2160 }, { "epoch": 134.5679012345679, "learning_rate": 9.727256030366107e-07, "loss": 2.6271, "step": 2180 }, { "epoch": 135.80246913580248, "learning_rate": 9.724501040773846e-07, "loss": 2.5626, "step": 2200 }, { "epoch": 137.03703703703704, "learning_rate": 9.721746051181584e-07, "loss": 2.5425, "step": 2220 }, { "epoch": 138.2716049382716, "learning_rate": 9.718991061589323e-07, "loss": 2.5251, "step": 2240 }, { "epoch": 139.50617283950618, "learning_rate": 9.716236071997061e-07, "loss": 2.5817, "step": 2260 }, { "epoch": 140.74074074074073, "learning_rate": 9.7134810824048e-07, "loss": 2.4888, "step": 2280 }, { "epoch": 141.97530864197532, "learning_rate": 9.710726092812539e-07, "loss": 2.5426, "step": 2300 }, { "epoch": 143.20987654320987, "learning_rate": 9.707971103220275e-07, "loss": 2.5293, "step": 2320 }, { "epoch": 144.44444444444446, "learning_rate": 9.705216113628016e-07, "loss": 2.4874, "step": 2340 }, { "epoch": 145.679012345679, "learning_rate": 9.702461124035752e-07, "loss": 2.5487, "step": 2360 }, { "epoch": 146.91358024691357, "learning_rate": 9.699706134443493e-07, "loss": 2.5153, "step": 2380 }, { "epoch": 148.14814814814815, "learning_rate": 9.69695114485123e-07, "loss": 2.4468, "step": 2400 }, { "epoch": 149.3827160493827, "learning_rate": 9.69419615525897e-07, "loss": 2.4731, "step": 2420 }, { "epoch": 150.6172839506173, "learning_rate": 9.691441165666707e-07, "loss": 2.5007, "step": 2440 }, { "epoch": 151.85185185185185, "learning_rate": 9.688686176074445e-07, "loss": 2.4948, "step": 2460 }, { "epoch": 153.08641975308643, "learning_rate": 9.685931186482184e-07, "loss": 2.4867, "step": 2480 }, { "epoch": 154.320987654321, "learning_rate": 9.683176196889922e-07, "loss": 2.4654, "step": 2500 }, { "epoch": 155.55555555555554, "learning_rate": 9.68042120729766e-07, "loss": 2.4621, "step": 2520 }, { "epoch": 156.79012345679013, "learning_rate": 9.6776662177054e-07, "loss": 2.4738, "step": 2540 }, { "epoch": 158.02469135802468, "learning_rate": 9.674911228113138e-07, "loss": 2.4562, "step": 2560 }, { "epoch": 159.25925925925927, "learning_rate": 9.672156238520875e-07, "loss": 2.4937, "step": 2580 }, { "epoch": 160.49382716049382, "learning_rate": 9.669401248928615e-07, "loss": 2.4574, "step": 2600 }, { "epoch": 161.7283950617284, "learning_rate": 9.666646259336352e-07, "loss": 2.4642, "step": 2620 }, { "epoch": 162.96296296296296, "learning_rate": 9.663891269744093e-07, "loss": 2.4736, "step": 2640 }, { "epoch": 164.19753086419752, "learning_rate": 9.66113628015183e-07, "loss": 2.4926, "step": 2660 }, { "epoch": 165.4320987654321, "learning_rate": 9.65838129055957e-07, "loss": 2.4323, "step": 2680 }, { "epoch": 166.66666666666666, "learning_rate": 9.655626300967306e-07, "loss": 2.4508, "step": 2700 }, { "epoch": 167.90123456790124, "learning_rate": 9.652871311375045e-07, "loss": 2.4295, "step": 2720 }, { "epoch": 169.1358024691358, "learning_rate": 9.650116321782783e-07, "loss": 2.4753, "step": 2740 }, { "epoch": 170.37037037037038, "learning_rate": 9.647361332190522e-07, "loss": 2.4323, "step": 2760 }, { "epoch": 171.60493827160494, "learning_rate": 9.64460634259826e-07, "loss": 2.392, "step": 2780 }, { "epoch": 172.8395061728395, "learning_rate": 9.641851353006e-07, "loss": 2.4579, "step": 2800 }, { "epoch": 174.07407407407408, "learning_rate": 9.639096363413738e-07, "loss": 2.4091, "step": 2820 }, { "epoch": 175.30864197530863, "learning_rate": 9.636341373821476e-07, "loss": 2.3802, "step": 2840 }, { "epoch": 176.54320987654322, "learning_rate": 9.633586384229215e-07, "loss": 2.3483, "step": 2860 }, { "epoch": 177.77777777777777, "learning_rate": 9.630831394636953e-07, "loss": 2.374, "step": 2880 }, { "epoch": 179.01234567901236, "learning_rate": 9.628076405044692e-07, "loss": 2.414, "step": 2900 }, { "epoch": 180.2469135802469, "learning_rate": 9.62532141545243e-07, "loss": 2.3971, "step": 2920 }, { "epoch": 181.4814814814815, "learning_rate": 9.62256642586017e-07, "loss": 2.3508, "step": 2940 }, { "epoch": 182.71604938271605, "learning_rate": 9.619811436267908e-07, "loss": 2.4072, "step": 2960 }, { "epoch": 183.9506172839506, "learning_rate": 9.617056446675646e-07, "loss": 2.3853, "step": 2980 }, { "epoch": 185.1851851851852, "learning_rate": 9.614301457083383e-07, "loss": 2.4256, "step": 3000 }, { "epoch": 186.41975308641975, "learning_rate": 9.611546467491124e-07, "loss": 2.3795, "step": 3020 }, { "epoch": 187.65432098765433, "learning_rate": 9.60879147789886e-07, "loss": 2.3763, "step": 3040 }, { "epoch": 188.88888888888889, "learning_rate": 9.6060364883066e-07, "loss": 2.3474, "step": 3060 }, { "epoch": 190.12345679012347, "learning_rate": 9.603281498714337e-07, "loss": 2.4074, "step": 3080 }, { "epoch": 191.35802469135803, "learning_rate": 9.600526509122076e-07, "loss": 2.3438, "step": 3100 }, { "epoch": 192.59259259259258, "learning_rate": 9.597771519529814e-07, "loss": 2.3209, "step": 3120 }, { "epoch": 193.82716049382717, "learning_rate": 9.595016529937553e-07, "loss": 2.3364, "step": 3140 }, { "epoch": 195.06172839506172, "learning_rate": 9.592261540345292e-07, "loss": 2.3624, "step": 3160 }, { "epoch": 196.2962962962963, "learning_rate": 9.58950655075303e-07, "loss": 2.3004, "step": 3180 }, { "epoch": 197.53086419753086, "learning_rate": 9.586751561160769e-07, "loss": 2.2904, "step": 3200 }, { "epoch": 198.76543209876544, "learning_rate": 9.583996571568507e-07, "loss": 2.2971, "step": 3220 }, { "epoch": 200.0, "learning_rate": 9.581241581976246e-07, "loss": 2.3364, "step": 3240 }, { "epoch": 201.23456790123456, "learning_rate": 9.578486592383982e-07, "loss": 2.3191, "step": 3260 }, { "epoch": 202.46913580246914, "learning_rate": 9.575731602791723e-07, "loss": 2.3663, "step": 3280 }, { "epoch": 203.7037037037037, "learning_rate": 9.57297661319946e-07, "loss": 2.3649, "step": 3300 }, { "epoch": 204.93827160493828, "learning_rate": 9.5702216236072e-07, "loss": 2.2762, "step": 3320 }, { "epoch": 206.17283950617283, "learning_rate": 9.567466634014937e-07, "loss": 2.315, "step": 3340 }, { "epoch": 207.40740740740742, "learning_rate": 9.564711644422677e-07, "loss": 2.2924, "step": 3360 }, { "epoch": 208.64197530864197, "learning_rate": 9.561956654830414e-07, "loss": 2.2383, "step": 3380 }, { "epoch": 209.87654320987653, "learning_rate": 9.559201665238153e-07, "loss": 2.2903, "step": 3400 }, { "epoch": 211.11111111111111, "learning_rate": 9.556446675645891e-07, "loss": 2.3423, "step": 3420 }, { "epoch": 212.34567901234567, "learning_rate": 9.55369168605363e-07, "loss": 2.2747, "step": 3440 }, { "epoch": 213.58024691358025, "learning_rate": 9.550936696461368e-07, "loss": 2.2997, "step": 3460 }, { "epoch": 214.8148148148148, "learning_rate": 9.548181706869107e-07, "loss": 2.2166, "step": 3480 }, { "epoch": 216.0493827160494, "learning_rate": 9.545426717276845e-07, "loss": 2.349, "step": 3500 }, { "epoch": 217.28395061728395, "learning_rate": 9.542671727684582e-07, "loss": 2.2522, "step": 3520 }, { "epoch": 218.5185185185185, "learning_rate": 9.539916738092323e-07, "loss": 2.2854, "step": 3540 }, { "epoch": 219.7530864197531, "learning_rate": 9.537161748500061e-07, "loss": 2.2806, "step": 3560 }, { "epoch": 220.98765432098764, "learning_rate": 9.5344067589078e-07, "loss": 2.233, "step": 3580 }, { "epoch": 222.22222222222223, "learning_rate": 9.531651769315538e-07, "loss": 2.2588, "step": 3600 }, { "epoch": 223.45679012345678, "learning_rate": 9.528896779723277e-07, "loss": 2.2729, "step": 3620 }, { "epoch": 224.69135802469137, "learning_rate": 9.526141790131015e-07, "loss": 2.2818, "step": 3640 }, { "epoch": 225.92592592592592, "learning_rate": 9.523386800538753e-07, "loss": 2.2291, "step": 3660 }, { "epoch": 227.1604938271605, "learning_rate": 9.520631810946491e-07, "loss": 2.2552, "step": 3680 }, { "epoch": 228.39506172839506, "learning_rate": 9.51787682135423e-07, "loss": 2.2028, "step": 3700 }, { "epoch": 229.62962962962962, "learning_rate": 9.515121831761969e-07, "loss": 2.1948, "step": 3720 }, { "epoch": 230.8641975308642, "learning_rate": 9.512366842169707e-07, "loss": 2.2981, "step": 3740 }, { "epoch": 232.09876543209876, "learning_rate": 9.509611852577446e-07, "loss": 2.2519, "step": 3760 }, { "epoch": 233.33333333333334, "learning_rate": 9.506856862985184e-07, "loss": 2.2159, "step": 3780 }, { "epoch": 234.5679012345679, "learning_rate": 9.504101873392922e-07, "loss": 2.2122, "step": 3800 }, { "epoch": 235.80246913580248, "learning_rate": 9.501346883800661e-07, "loss": 2.2165, "step": 3820 }, { "epoch": 237.03703703703704, "learning_rate": 9.498591894208399e-07, "loss": 2.2362, "step": 3840 }, { "epoch": 238.2716049382716, "learning_rate": 9.495836904616138e-07, "loss": 2.1995, "step": 3860 }, { "epoch": 239.50617283950618, "learning_rate": 9.493081915023877e-07, "loss": 2.248, "step": 3880 }, { "epoch": 240.74074074074073, "learning_rate": 9.490326925431615e-07, "loss": 2.1703, "step": 3900 }, { "epoch": 241.97530864197532, "learning_rate": 9.487571935839353e-07, "loss": 2.1987, "step": 3920 }, { "epoch": 243.20987654320987, "learning_rate": 9.484816946247091e-07, "loss": 2.2023, "step": 3940 }, { "epoch": 244.44444444444446, "learning_rate": 9.48206195665483e-07, "loss": 2.2292, "step": 3960 }, { "epoch": 245.679012345679, "learning_rate": 9.479306967062568e-07, "loss": 2.1746, "step": 3980 }, { "epoch": 246.91358024691357, "learning_rate": 9.476551977470307e-07, "loss": 2.1809, "step": 4000 }, { "epoch": 248.14814814814815, "learning_rate": 9.473796987878046e-07, "loss": 2.1631, "step": 4020 }, { "epoch": 249.3827160493827, "learning_rate": 9.471041998285784e-07, "loss": 2.1437, "step": 4040 }, { "epoch": 250.6172839506173, "learning_rate": 9.468287008693522e-07, "loss": 2.1719, "step": 4060 }, { "epoch": 251.85185185185185, "learning_rate": 9.46553201910126e-07, "loss": 2.1754, "step": 4080 }, { "epoch": 253.08641975308643, "learning_rate": 9.462777029508999e-07, "loss": 2.172, "step": 4100 }, { "epoch": 254.320987654321, "learning_rate": 9.460022039916737e-07, "loss": 2.2135, "step": 4120 }, { "epoch": 255.55555555555554, "learning_rate": 9.457267050324476e-07, "loss": 2.1143, "step": 4140 }, { "epoch": 256.7901234567901, "learning_rate": 9.454512060732215e-07, "loss": 2.1804, "step": 4160 }, { "epoch": 258.0246913580247, "learning_rate": 9.451757071139952e-07, "loss": 2.147, "step": 4180 }, { "epoch": 259.25925925925924, "learning_rate": 9.449002081547691e-07, "loss": 2.1618, "step": 4200 }, { "epoch": 260.4938271604938, "learning_rate": 9.446247091955429e-07, "loss": 2.1434, "step": 4220 }, { "epoch": 261.7283950617284, "learning_rate": 9.443492102363168e-07, "loss": 2.1535, "step": 4240 }, { "epoch": 262.962962962963, "learning_rate": 9.440737112770907e-07, "loss": 2.2116, "step": 4260 }, { "epoch": 264.1975308641975, "learning_rate": 9.437982123178645e-07, "loss": 2.1857, "step": 4280 }, { "epoch": 265.4320987654321, "learning_rate": 9.435227133586384e-07, "loss": 2.1337, "step": 4300 }, { "epoch": 266.6666666666667, "learning_rate": 9.432472143994122e-07, "loss": 2.1554, "step": 4320 }, { "epoch": 267.9012345679012, "learning_rate": 9.429717154401861e-07, "loss": 2.1565, "step": 4340 }, { "epoch": 269.1358024691358, "learning_rate": 9.4269621648096e-07, "loss": 2.168, "step": 4360 }, { "epoch": 270.3703703703704, "learning_rate": 9.424207175217338e-07, "loss": 2.1392, "step": 4380 }, { "epoch": 271.60493827160496, "learning_rate": 9.421452185625077e-07, "loss": 2.1726, "step": 4400 }, { "epoch": 272.8395061728395, "learning_rate": 9.418697196032815e-07, "loss": 2.135, "step": 4420 }, { "epoch": 274.0740740740741, "learning_rate": 9.415942206440553e-07, "loss": 2.1329, "step": 4440 }, { "epoch": 275.30864197530866, "learning_rate": 9.413187216848291e-07, "loss": 2.1334, "step": 4460 }, { "epoch": 276.5432098765432, "learning_rate": 9.41043222725603e-07, "loss": 2.1309, "step": 4480 }, { "epoch": 277.77777777777777, "learning_rate": 9.407677237663769e-07, "loss": 2.0872, "step": 4500 }, { "epoch": 279.01234567901236, "learning_rate": 9.404922248071507e-07, "loss": 2.1426, "step": 4520 }, { "epoch": 280.24691358024694, "learning_rate": 9.402167258479246e-07, "loss": 2.1331, "step": 4540 }, { "epoch": 281.48148148148147, "learning_rate": 9.399412268886984e-07, "loss": 2.0859, "step": 4560 }, { "epoch": 282.71604938271605, "learning_rate": 9.396657279294723e-07, "loss": 2.0755, "step": 4580 }, { "epoch": 283.95061728395063, "learning_rate": 9.39390228970246e-07, "loss": 2.1203, "step": 4600 }, { "epoch": 285.18518518518516, "learning_rate": 9.391147300110199e-07, "loss": 2.0846, "step": 4620 }, { "epoch": 286.41975308641975, "learning_rate": 9.388392310517938e-07, "loss": 2.1284, "step": 4640 }, { "epoch": 287.65432098765433, "learning_rate": 9.385637320925677e-07, "loss": 2.107, "step": 4660 }, { "epoch": 288.8888888888889, "learning_rate": 9.382882331333415e-07, "loss": 2.2206, "step": 4680 }, { "epoch": 290.12345679012344, "learning_rate": 9.380127341741153e-07, "loss": 2.2475, "step": 4700 }, { "epoch": 291.358024691358, "learning_rate": 9.377372352148891e-07, "loss": 2.1887, "step": 4720 }, { "epoch": 292.5925925925926, "learning_rate": 9.37461736255663e-07, "loss": 2.1352, "step": 4740 }, { "epoch": 293.82716049382714, "learning_rate": 9.371862372964368e-07, "loss": 2.1565, "step": 4760 }, { "epoch": 295.0617283950617, "learning_rate": 9.369107383372107e-07, "loss": 2.1574, "step": 4780 }, { "epoch": 296.2962962962963, "learning_rate": 9.366352393779845e-07, "loss": 2.1384, "step": 4800 }, { "epoch": 297.5308641975309, "learning_rate": 9.363597404187584e-07, "loss": 2.1534, "step": 4820 }, { "epoch": 298.7654320987654, "learning_rate": 9.360842414595322e-07, "loss": 2.0941, "step": 4840 }, { "epoch": 300.0, "learning_rate": 9.35808742500306e-07, "loss": 2.101, "step": 4860 }, { "epoch": 301.2345679012346, "learning_rate": 9.355332435410799e-07, "loss": 2.1181, "step": 4880 }, { "epoch": 302.4691358024691, "learning_rate": 9.352577445818537e-07, "loss": 2.0771, "step": 4900 }, { "epoch": 303.7037037037037, "learning_rate": 9.349822456226276e-07, "loss": 2.0886, "step": 4920 }, { "epoch": 304.9382716049383, "learning_rate": 9.347067466634014e-07, "loss": 2.0715, "step": 4940 }, { "epoch": 306.17283950617286, "learning_rate": 9.344312477041753e-07, "loss": 2.0883, "step": 4960 }, { "epoch": 307.4074074074074, "learning_rate": 9.34155748744949e-07, "loss": 2.0767, "step": 4980 }, { "epoch": 308.641975308642, "learning_rate": 9.338802497857229e-07, "loss": 2.0757, "step": 5000 }, { "epoch": 309.87654320987656, "learning_rate": 9.336047508264968e-07, "loss": 2.0775, "step": 5020 }, { "epoch": 311.1111111111111, "learning_rate": 9.333292518672707e-07, "loss": 2.0763, "step": 5040 }, { "epoch": 312.34567901234567, "learning_rate": 9.330537529080446e-07, "loss": 2.065, "step": 5060 }, { "epoch": 313.58024691358025, "learning_rate": 9.327782539488184e-07, "loss": 2.0996, "step": 5080 }, { "epoch": 314.81481481481484, "learning_rate": 9.325027549895923e-07, "loss": 2.0837, "step": 5100 }, { "epoch": 316.04938271604937, "learning_rate": 9.322272560303662e-07, "loss": 2.0985, "step": 5120 }, { "epoch": 317.28395061728395, "learning_rate": 9.319517570711399e-07, "loss": 2.0662, "step": 5140 }, { "epoch": 318.51851851851853, "learning_rate": 9.316762581119138e-07, "loss": 2.1054, "step": 5160 }, { "epoch": 319.75308641975306, "learning_rate": 9.314007591526876e-07, "loss": 2.0688, "step": 5180 }, { "epoch": 320.98765432098764, "learning_rate": 9.311252601934615e-07, "loss": 2.06, "step": 5200 }, { "epoch": 322.22222222222223, "learning_rate": 9.308497612342353e-07, "loss": 2.0608, "step": 5220 }, { "epoch": 323.4567901234568, "learning_rate": 9.305742622750092e-07, "loss": 2.0238, "step": 5240 }, { "epoch": 324.69135802469134, "learning_rate": 9.30298763315783e-07, "loss": 2.0672, "step": 5260 }, { "epoch": 325.9259259259259, "learning_rate": 9.300232643565568e-07, "loss": 2.0045, "step": 5280 }, { "epoch": 327.1604938271605, "learning_rate": 9.297477653973307e-07, "loss": 2.0297, "step": 5300 }, { "epoch": 328.39506172839504, "learning_rate": 9.294722664381045e-07, "loss": 2.0939, "step": 5320 }, { "epoch": 329.6296296296296, "learning_rate": 9.291967674788784e-07, "loss": 2.0309, "step": 5340 }, { "epoch": 330.8641975308642, "learning_rate": 9.289212685196523e-07, "loss": 2.0221, "step": 5360 }, { "epoch": 332.0987654320988, "learning_rate": 9.286457695604261e-07, "loss": 2.0629, "step": 5380 }, { "epoch": 333.3333333333333, "learning_rate": 9.283702706011999e-07, "loss": 2.0113, "step": 5400 }, { "epoch": 334.5679012345679, "learning_rate": 9.280947716419737e-07, "loss": 2.0351, "step": 5420 }, { "epoch": 335.8024691358025, "learning_rate": 9.278192726827476e-07, "loss": 2.0535, "step": 5440 }, { "epoch": 337.037037037037, "learning_rate": 9.275437737235214e-07, "loss": 2.0653, "step": 5460 }, { "epoch": 338.2716049382716, "learning_rate": 9.272682747642953e-07, "loss": 2.0103, "step": 5480 }, { "epoch": 339.5061728395062, "learning_rate": 9.269927758050692e-07, "loss": 2.0367, "step": 5500 }, { "epoch": 340.74074074074076, "learning_rate": 9.267172768458429e-07, "loss": 1.9869, "step": 5520 }, { "epoch": 341.9753086419753, "learning_rate": 9.264417778866168e-07, "loss": 2.0831, "step": 5540 }, { "epoch": 343.2098765432099, "learning_rate": 9.261662789273906e-07, "loss": 2.0198, "step": 5560 }, { "epoch": 344.44444444444446, "learning_rate": 9.258907799681645e-07, "loss": 2.0057, "step": 5580 }, { "epoch": 345.679012345679, "learning_rate": 9.256152810089383e-07, "loss": 1.9973, "step": 5600 }, { "epoch": 346.91358024691357, "learning_rate": 9.253397820497122e-07, "loss": 2.0431, "step": 5620 }, { "epoch": 348.14814814814815, "learning_rate": 9.250642830904861e-07, "loss": 2.0132, "step": 5640 }, { "epoch": 349.38271604938274, "learning_rate": 9.247887841312599e-07, "loss": 2.0589, "step": 5660 }, { "epoch": 350.61728395061726, "learning_rate": 9.245132851720337e-07, "loss": 1.9975, "step": 5680 }, { "epoch": 351.85185185185185, "learning_rate": 9.242377862128075e-07, "loss": 2.0196, "step": 5700 }, { "epoch": 353.08641975308643, "learning_rate": 9.239622872535814e-07, "loss": 1.9605, "step": 5720 }, { "epoch": 354.320987654321, "learning_rate": 9.236867882943551e-07, "loss": 2.0043, "step": 5740 }, { "epoch": 355.55555555555554, "learning_rate": 9.234112893351291e-07, "loss": 1.9835, "step": 5760 }, { "epoch": 356.7901234567901, "learning_rate": 9.23135790375903e-07, "loss": 2.0274, "step": 5780 }, { "epoch": 358.0246913580247, "learning_rate": 9.228602914166768e-07, "loss": 2.0303, "step": 5800 }, { "epoch": 359.25925925925924, "learning_rate": 9.225847924574507e-07, "loss": 1.9691, "step": 5820 }, { "epoch": 360.4938271604938, "learning_rate": 9.223092934982245e-07, "loss": 2.0049, "step": 5840 }, { "epoch": 361.7283950617284, "learning_rate": 9.220337945389984e-07, "loss": 1.9652, "step": 5860 }, { "epoch": 362.962962962963, "learning_rate": 9.217582955797723e-07, "loss": 2.019, "step": 5880 }, { "epoch": 364.1975308641975, "learning_rate": 9.214827966205461e-07, "loss": 1.9819, "step": 5900 }, { "epoch": 365.4320987654321, "learning_rate": 9.2120729766132e-07, "loss": 2.0201, "step": 5920 }, { "epoch": 366.6666666666667, "learning_rate": 9.209317987020937e-07, "loss": 1.9934, "step": 5940 }, { "epoch": 367.9012345679012, "learning_rate": 9.206562997428676e-07, "loss": 1.9566, "step": 5960 }, { "epoch": 369.1358024691358, "learning_rate": 9.203808007836415e-07, "loss": 1.9902, "step": 5980 }, { "epoch": 370.3703703703704, "learning_rate": 9.201053018244152e-07, "loss": 2.0059, "step": 6000 }, { "epoch": 371.60493827160496, "learning_rate": 9.198298028651892e-07, "loss": 1.988, "step": 6020 }, { "epoch": 372.8395061728395, "learning_rate": 9.19554303905963e-07, "loss": 1.9659, "step": 6040 }, { "epoch": 374.0740740740741, "learning_rate": 9.192788049467368e-07, "loss": 2.0319, "step": 6060 }, { "epoch": 375.30864197530866, "learning_rate": 9.190033059875106e-07, "loss": 1.9308, "step": 6080 }, { "epoch": 376.5432098765432, "learning_rate": 9.187278070282845e-07, "loss": 1.967, "step": 6100 }, { "epoch": 377.77777777777777, "learning_rate": 9.184523080690584e-07, "loss": 2.0184, "step": 6120 }, { "epoch": 379.01234567901236, "learning_rate": 9.181768091098322e-07, "loss": 1.9865, "step": 6140 }, { "epoch": 380.24691358024694, "learning_rate": 9.179013101506061e-07, "loss": 1.9415, "step": 6160 }, { "epoch": 381.48148148148147, "learning_rate": 9.176258111913799e-07, "loss": 1.9619, "step": 6180 }, { "epoch": 382.71604938271605, "learning_rate": 9.173503122321538e-07, "loss": 1.949, "step": 6200 }, { "epoch": 383.95061728395063, "learning_rate": 9.170748132729275e-07, "loss": 1.9467, "step": 6220 }, { "epoch": 385.18518518518516, "learning_rate": 9.167993143137014e-07, "loss": 1.9691, "step": 6240 }, { "epoch": 386.41975308641975, "learning_rate": 9.165238153544753e-07, "loss": 1.9643, "step": 6260 }, { "epoch": 387.65432098765433, "learning_rate": 9.162483163952491e-07, "loss": 1.942, "step": 6280 }, { "epoch": 388.8888888888889, "learning_rate": 9.15972817436023e-07, "loss": 1.9002, "step": 6300 }, { "epoch": 390.12345679012344, "learning_rate": 9.156973184767968e-07, "loss": 1.9965, "step": 6320 }, { "epoch": 391.358024691358, "learning_rate": 9.154218195175706e-07, "loss": 1.9343, "step": 6340 }, { "epoch": 392.5925925925926, "learning_rate": 9.151463205583446e-07, "loss": 1.931, "step": 6360 }, { "epoch": 393.82716049382714, "learning_rate": 9.148708215991183e-07, "loss": 1.9628, "step": 6380 }, { "epoch": 395.0617283950617, "learning_rate": 9.145953226398922e-07, "loss": 1.9752, "step": 6400 }, { "epoch": 396.2962962962963, "learning_rate": 9.14319823680666e-07, "loss": 1.9499, "step": 6420 }, { "epoch": 397.5308641975309, "learning_rate": 9.140443247214399e-07, "loss": 1.9546, "step": 6440 }, { "epoch": 398.7654320987654, "learning_rate": 9.137688257622137e-07, "loss": 1.8583, "step": 6460 }, { "epoch": 400.0, "learning_rate": 9.134933268029875e-07, "loss": 1.9405, "step": 6480 }, { "epoch": 401.2345679012346, "learning_rate": 9.132178278437614e-07, "loss": 1.941, "step": 6500 }, { "epoch": 402.4691358024691, "learning_rate": 9.129423288845352e-07, "loss": 1.9432, "step": 6520 }, { "epoch": 403.7037037037037, "learning_rate": 9.126668299253092e-07, "loss": 1.9603, "step": 6540 }, { "epoch": 404.9382716049383, "learning_rate": 9.12391330966083e-07, "loss": 1.9456, "step": 6560 }, { "epoch": 406.17283950617286, "learning_rate": 9.121158320068569e-07, "loss": 1.9488, "step": 6580 }, { "epoch": 407.4074074074074, "learning_rate": 9.118403330476307e-07, "loss": 1.9248, "step": 6600 }, { "epoch": 408.641975308642, "learning_rate": 9.115648340884045e-07, "loss": 1.8897, "step": 6620 }, { "epoch": 409.87654320987656, "learning_rate": 9.112893351291784e-07, "loss": 1.9315, "step": 6640 }, { "epoch": 411.1111111111111, "learning_rate": 9.110138361699522e-07, "loss": 1.9599, "step": 6660 }, { "epoch": 412.34567901234567, "learning_rate": 9.107383372107261e-07, "loss": 1.9441, "step": 6680 }, { "epoch": 413.58024691358025, "learning_rate": 9.104628382515e-07, "loss": 1.8974, "step": 6700 }, { "epoch": 414.81481481481484, "learning_rate": 9.101873392922738e-07, "loss": 1.9078, "step": 6720 }, { "epoch": 416.04938271604937, "learning_rate": 9.099118403330477e-07, "loss": 1.9587, "step": 6740 }, { "epoch": 417.28395061728395, "learning_rate": 9.096363413738214e-07, "loss": 2.0016, "step": 6760 }, { "epoch": 418.51851851851853, "learning_rate": 9.093608424145953e-07, "loss": 1.9557, "step": 6780 }, { "epoch": 419.75308641975306, "learning_rate": 9.090853434553691e-07, "loss": 1.9719, "step": 6800 }, { "epoch": 420.98765432098764, "learning_rate": 9.08809844496143e-07, "loss": 1.9779, "step": 6820 }, { "epoch": 422.22222222222223, "learning_rate": 9.085343455369169e-07, "loss": 1.9754, "step": 6840 }, { "epoch": 423.4567901234568, "learning_rate": 9.082588465776907e-07, "loss": 2.0078, "step": 6860 }, { "epoch": 424.69135802469134, "learning_rate": 9.079833476184645e-07, "loss": 1.9856, "step": 6880 }, { "epoch": 425.9259259259259, "learning_rate": 9.077078486592383e-07, "loss": 1.9698, "step": 6900 }, { "epoch": 427.1604938271605, "learning_rate": 9.074323497000122e-07, "loss": 1.9826, "step": 6920 }, { "epoch": 428.39506172839504, "learning_rate": 9.07156850740786e-07, "loss": 1.9513, "step": 6940 }, { "epoch": 429.6296296296296, "learning_rate": 9.068813517815599e-07, "loss": 1.93, "step": 6960 }, { "epoch": 430.8641975308642, "learning_rate": 9.066058528223339e-07, "loss": 1.9779, "step": 6980 }, { "epoch": 432.0987654320988, "learning_rate": 9.063303538631076e-07, "loss": 1.9937, "step": 7000 }, { "epoch": 433.3333333333333, "learning_rate": 9.060548549038814e-07, "loss": 1.955, "step": 7020 }, { "epoch": 434.5679012345679, "learning_rate": 9.057793559446552e-07, "loss": 1.9652, "step": 7040 }, { "epoch": 435.8024691358025, "learning_rate": 9.055038569854291e-07, "loss": 1.9568, "step": 7060 }, { "epoch": 437.037037037037, "learning_rate": 9.05228358026203e-07, "loss": 1.9787, "step": 7080 }, { "epoch": 438.2716049382716, "learning_rate": 9.049528590669768e-07, "loss": 1.9137, "step": 7100 }, { "epoch": 439.5061728395062, "learning_rate": 9.046773601077507e-07, "loss": 1.9314, "step": 7120 }, { "epoch": 440.74074074074076, "learning_rate": 9.044018611485244e-07, "loss": 1.9961, "step": 7140 }, { "epoch": 441.9753086419753, "learning_rate": 9.041263621892983e-07, "loss": 1.9303, "step": 7160 }, { "epoch": 443.2098765432099, "learning_rate": 9.038508632300721e-07, "loss": 1.982, "step": 7180 }, { "epoch": 444.44444444444446, "learning_rate": 9.03575364270846e-07, "loss": 1.9133, "step": 7200 }, { "epoch": 445.679012345679, "learning_rate": 9.032998653116199e-07, "loss": 1.9376, "step": 7220 }, { "epoch": 446.91358024691357, "learning_rate": 9.030243663523937e-07, "loss": 1.9254, "step": 7240 }, { "epoch": 448.14814814814815, "learning_rate": 9.027488673931676e-07, "loss": 1.9491, "step": 7260 }, { "epoch": 449.38271604938274, "learning_rate": 9.024733684339414e-07, "loss": 1.9455, "step": 7280 }, { "epoch": 450.61728395061726, "learning_rate": 9.021978694747153e-07, "loss": 1.9128, "step": 7300 }, { "epoch": 451.85185185185185, "learning_rate": 9.019223705154892e-07, "loss": 1.9006, "step": 7320 }, { "epoch": 453.08641975308643, "learning_rate": 9.016468715562629e-07, "loss": 1.9172, "step": 7340 }, { "epoch": 454.320987654321, "learning_rate": 9.013713725970369e-07, "loss": 1.9754, "step": 7360 }, { "epoch": 455.55555555555554, "learning_rate": 9.010958736378107e-07, "loss": 1.9759, "step": 7380 }, { "epoch": 456.7901234567901, "learning_rate": 9.008203746785846e-07, "loss": 1.9452, "step": 7400 }, { "epoch": 458.0246913580247, "learning_rate": 9.005448757193583e-07, "loss": 1.9618, "step": 7420 }, { "epoch": 459.25925925925924, "learning_rate": 9.002693767601322e-07, "loss": 1.9364, "step": 7440 }, { "epoch": 460.4938271604938, "learning_rate": 8.999938778009061e-07, "loss": 1.9513, "step": 7460 }, { "epoch": 461.7283950617284, "learning_rate": 8.997183788416799e-07, "loss": 1.9473, "step": 7480 }, { "epoch": 462.962962962963, "learning_rate": 8.994428798824538e-07, "loss": 1.9159, "step": 7500 }, { "epoch": 464.1975308641975, "learning_rate": 8.991673809232276e-07, "loss": 1.9195, "step": 7520 }, { "epoch": 465.4320987654321, "learning_rate": 8.988918819640015e-07, "loss": 1.9647, "step": 7540 }, { "epoch": 466.6666666666667, "learning_rate": 8.986163830047752e-07, "loss": 1.895, "step": 7560 }, { "epoch": 467.9012345679012, "learning_rate": 8.983408840455491e-07, "loss": 1.9408, "step": 7580 }, { "epoch": 469.1358024691358, "learning_rate": 8.98065385086323e-07, "loss": 1.978, "step": 7600 }, { "epoch": 470.3703703703704, "learning_rate": 8.977898861270968e-07, "loss": 1.9085, "step": 7620 }, { "epoch": 471.60493827160496, "learning_rate": 8.975143871678707e-07, "loss": 1.9833, "step": 7640 }, { "epoch": 472.8395061728395, "learning_rate": 8.972388882086445e-07, "loss": 1.9559, "step": 7660 }, { "epoch": 474.0740740740741, "learning_rate": 8.969633892494183e-07, "loss": 1.9333, "step": 7680 }, { "epoch": 475.30864197530866, "learning_rate": 8.966878902901923e-07, "loss": 1.9075, "step": 7700 }, { "epoch": 476.5432098765432, "learning_rate": 8.96412391330966e-07, "loss": 1.9343, "step": 7720 }, { "epoch": 477.77777777777777, "learning_rate": 8.961368923717399e-07, "loss": 1.9107, "step": 7740 }, { "epoch": 479.01234567901236, "learning_rate": 8.958613934125137e-07, "loss": 1.9344, "step": 7760 }, { "epoch": 480.24691358024694, "learning_rate": 8.955858944532876e-07, "loss": 1.9044, "step": 7780 }, { "epoch": 481.48148148148147, "learning_rate": 8.953103954940614e-07, "loss": 1.974, "step": 7800 }, { "epoch": 482.71604938271605, "learning_rate": 8.950348965348353e-07, "loss": 1.9241, "step": 7820 }, { "epoch": 483.95061728395063, "learning_rate": 8.947593975756091e-07, "loss": 1.9377, "step": 7840 }, { "epoch": 485.18518518518516, "learning_rate": 8.944838986163829e-07, "loss": 1.9326, "step": 7860 }, { "epoch": 486.41975308641975, "learning_rate": 8.942083996571568e-07, "loss": 1.9028, "step": 7880 }, { "epoch": 487.65432098765433, "learning_rate": 8.939329006979306e-07, "loss": 1.8872, "step": 7900 }, { "epoch": 488.8888888888889, "learning_rate": 8.936574017387045e-07, "loss": 1.904, "step": 7920 }, { "epoch": 490.12345679012344, "learning_rate": 8.933819027794784e-07, "loss": 1.8897, "step": 7940 }, { "epoch": 491.358024691358, "learning_rate": 8.931064038202521e-07, "loss": 1.9026, "step": 7960 }, { "epoch": 492.5925925925926, "learning_rate": 8.92830904861026e-07, "loss": 1.9287, "step": 7980 }, { "epoch": 493.82716049382714, "learning_rate": 8.925554059017998e-07, "loss": 1.8277, "step": 8000 }, { "epoch": 495.0617283950617, "learning_rate": 8.922799069425738e-07, "loss": 1.8716, "step": 8020 }, { "epoch": 496.2962962962963, "learning_rate": 8.920044079833476e-07, "loss": 1.8907, "step": 8040 }, { "epoch": 497.5308641975309, "learning_rate": 8.917289090241215e-07, "loss": 1.8754, "step": 8060 }, { "epoch": 498.7654320987654, "learning_rate": 8.914534100648954e-07, "loss": 1.8713, "step": 8080 }, { "epoch": 500.0, "learning_rate": 8.911779111056691e-07, "loss": 1.8645, "step": 8100 }, { "epoch": 501.2345679012346, "learning_rate": 8.90902412146443e-07, "loss": 1.896, "step": 8120 }, { "epoch": 502.4691358024691, "learning_rate": 8.906269131872168e-07, "loss": 1.8824, "step": 8140 }, { "epoch": 503.7037037037037, "learning_rate": 8.903514142279907e-07, "loss": 1.8612, "step": 8160 }, { "epoch": 504.9382716049383, "learning_rate": 8.900759152687646e-07, "loss": 1.8747, "step": 8180 }, { "epoch": 506.17283950617286, "learning_rate": 8.898004163095384e-07, "loss": 1.8882, "step": 8200 }, { "epoch": 507.4074074074074, "learning_rate": 8.895249173503122e-07, "loss": 1.8858, "step": 8220 }, { "epoch": 508.641975308642, "learning_rate": 8.89249418391086e-07, "loss": 1.8599, "step": 8240 }, { "epoch": 509.87654320987656, "learning_rate": 8.889739194318599e-07, "loss": 1.9073, "step": 8260 }, { "epoch": 511.1111111111111, "learning_rate": 8.886984204726337e-07, "loss": 1.9222, "step": 8280 }, { "epoch": 512.3456790123457, "learning_rate": 8.884229215134076e-07, "loss": 1.904, "step": 8300 }, { "epoch": 513.5802469135803, "learning_rate": 8.881474225541814e-07, "loss": 1.8662, "step": 8320 }, { "epoch": 514.8148148148148, "learning_rate": 8.878719235949553e-07, "loss": 1.8384, "step": 8340 }, { "epoch": 516.0493827160494, "learning_rate": 8.875964246357292e-07, "loss": 1.9238, "step": 8360 }, { "epoch": 517.283950617284, "learning_rate": 8.873209256765029e-07, "loss": 1.8626, "step": 8380 }, { "epoch": 518.5185185185185, "learning_rate": 8.870454267172768e-07, "loss": 1.9077, "step": 8400 }, { "epoch": 519.7530864197531, "learning_rate": 8.867699277580506e-07, "loss": 1.8783, "step": 8420 }, { "epoch": 520.9876543209876, "learning_rate": 8.864944287988245e-07, "loss": 1.8721, "step": 8440 }, { "epoch": 522.2222222222222, "learning_rate": 8.862189298395984e-07, "loss": 1.8961, "step": 8460 }, { "epoch": 523.4567901234568, "learning_rate": 8.859434308803721e-07, "loss": 1.8552, "step": 8480 }, { "epoch": 524.6913580246913, "learning_rate": 8.85667931921146e-07, "loss": 1.9263, "step": 8500 }, { "epoch": 525.925925925926, "learning_rate": 8.853924329619198e-07, "loss": 1.8674, "step": 8520 }, { "epoch": 527.1604938271605, "learning_rate": 8.851169340026937e-07, "loss": 1.8876, "step": 8540 }, { "epoch": 528.395061728395, "learning_rate": 8.848414350434676e-07, "loss": 1.8834, "step": 8560 }, { "epoch": 529.6296296296297, "learning_rate": 8.845659360842414e-07, "loss": 1.8467, "step": 8580 }, { "epoch": 530.8641975308642, "learning_rate": 8.842904371250153e-07, "loss": 1.8957, "step": 8600 }, { "epoch": 532.0987654320987, "learning_rate": 8.840149381657891e-07, "loss": 1.8911, "step": 8620 }, { "epoch": 533.3333333333334, "learning_rate": 8.837394392065629e-07, "loss": 1.8994, "step": 8640 }, { "epoch": 534.5679012345679, "learning_rate": 8.834639402473367e-07, "loss": 1.9276, "step": 8660 }, { "epoch": 535.8024691358024, "learning_rate": 8.831884412881107e-07, "loss": 1.8605, "step": 8680 }, { "epoch": 537.0370370370371, "learning_rate": 8.829129423288845e-07, "loss": 1.8733, "step": 8700 }, { "epoch": 538.2716049382716, "learning_rate": 8.826374433696583e-07, "loss": 1.9128, "step": 8720 }, { "epoch": 539.5061728395061, "learning_rate": 8.823619444104322e-07, "loss": 1.8563, "step": 8740 }, { "epoch": 540.7407407407408, "learning_rate": 8.82086445451206e-07, "loss": 1.8647, "step": 8760 }, { "epoch": 541.9753086419753, "learning_rate": 8.818109464919799e-07, "loss": 1.8478, "step": 8780 }, { "epoch": 543.2098765432099, "learning_rate": 8.815354475327538e-07, "loss": 1.877, "step": 8800 }, { "epoch": 544.4444444444445, "learning_rate": 8.812599485735276e-07, "loss": 1.8432, "step": 8820 }, { "epoch": 545.679012345679, "learning_rate": 8.809844496143015e-07, "loss": 1.8245, "step": 8840 }, { "epoch": 546.9135802469136, "learning_rate": 8.807089506550753e-07, "loss": 1.841, "step": 8860 }, { "epoch": 548.1481481481482, "learning_rate": 8.804334516958492e-07, "loss": 1.8609, "step": 8880 }, { "epoch": 549.3827160493827, "learning_rate": 8.80157952736623e-07, "loss": 1.8815, "step": 8900 }, { "epoch": 550.6172839506173, "learning_rate": 8.798824537773968e-07, "loss": 1.8866, "step": 8920 }, { "epoch": 551.8518518518518, "learning_rate": 8.796069548181707e-07, "loss": 1.8573, "step": 8940 }, { "epoch": 553.0864197530864, "learning_rate": 8.793314558589445e-07, "loss": 1.8837, "step": 8960 }, { "epoch": 554.320987654321, "learning_rate": 8.790559568997184e-07, "loss": 1.8875, "step": 8980 }, { "epoch": 555.5555555555555, "learning_rate": 8.787804579404922e-07, "loss": 1.934, "step": 9000 }, { "epoch": 556.7901234567901, "learning_rate": 8.78504958981266e-07, "loss": 1.9294, "step": 9020 }, { "epoch": 558.0246913580247, "learning_rate": 8.782294600220397e-07, "loss": 2.0228, "step": 9040 }, { "epoch": 559.2592592592592, "learning_rate": 8.779539610628137e-07, "loss": 2.0074, "step": 9060 }, { "epoch": 560.4938271604939, "learning_rate": 8.776784621035876e-07, "loss": 1.8819, "step": 9080 }, { "epoch": 561.7283950617284, "learning_rate": 8.774029631443614e-07, "loss": 1.8354, "step": 9100 }, { "epoch": 562.9629629629629, "learning_rate": 8.771274641851353e-07, "loss": 1.8683, "step": 9120 }, { "epoch": 564.1975308641976, "learning_rate": 8.768519652259091e-07, "loss": 1.8644, "step": 9140 }, { "epoch": 565.4320987654321, "learning_rate": 8.76576466266683e-07, "loss": 1.8822, "step": 9160 }, { "epoch": 566.6666666666666, "learning_rate": 8.763009673074568e-07, "loss": 1.8544, "step": 9180 }, { "epoch": 567.9012345679013, "learning_rate": 8.760254683482306e-07, "loss": 1.8507, "step": 9200 }, { "epoch": 569.1358024691358, "learning_rate": 8.757499693890045e-07, "loss": 1.8816, "step": 9220 }, { "epoch": 570.3703703703703, "learning_rate": 8.754744704297783e-07, "loss": 1.7993, "step": 9240 }, { "epoch": 571.604938271605, "learning_rate": 8.751989714705522e-07, "loss": 1.8231, "step": 9260 }, { "epoch": 572.8395061728395, "learning_rate": 8.74923472511326e-07, "loss": 1.8354, "step": 9280 }, { "epoch": 574.074074074074, "learning_rate": 8.746479735520998e-07, "loss": 1.8731, "step": 9300 }, { "epoch": 575.3086419753087, "learning_rate": 8.743724745928737e-07, "loss": 1.8377, "step": 9320 }, { "epoch": 576.5432098765432, "learning_rate": 8.740969756336475e-07, "loss": 1.8211, "step": 9340 }, { "epoch": 577.7777777777778, "learning_rate": 8.738214766744214e-07, "loss": 1.8321, "step": 9360 }, { "epoch": 579.0123456790124, "learning_rate": 8.735459777151952e-07, "loss": 1.8091, "step": 9380 }, { "epoch": 580.2469135802469, "learning_rate": 8.732704787559691e-07, "loss": 1.7772, "step": 9400 }, { "epoch": 581.4814814814815, "learning_rate": 8.72994979796743e-07, "loss": 1.7844, "step": 9420 }, { "epoch": 582.716049382716, "learning_rate": 8.727194808375168e-07, "loss": 1.7728, "step": 9440 }, { "epoch": 583.9506172839506, "learning_rate": 8.724439818782906e-07, "loss": 1.7777, "step": 9460 }, { "epoch": 585.1851851851852, "learning_rate": 8.721684829190644e-07, "loss": 1.7895, "step": 9480 }, { "epoch": 586.4197530864197, "learning_rate": 8.718929839598383e-07, "loss": 1.7949, "step": 9500 }, { "epoch": 587.6543209876543, "learning_rate": 8.716174850006122e-07, "loss": 1.7314, "step": 9520 }, { "epoch": 588.8888888888889, "learning_rate": 8.713419860413861e-07, "loss": 1.7573, "step": 9540 }, { "epoch": 590.1234567901234, "learning_rate": 8.710664870821599e-07, "loss": 1.7663, "step": 9560 }, { "epoch": 591.358024691358, "learning_rate": 8.707909881229337e-07, "loss": 1.8203, "step": 9580 }, { "epoch": 592.5925925925926, "learning_rate": 8.705154891637076e-07, "loss": 1.8092, "step": 9600 }, { "epoch": 593.8271604938271, "learning_rate": 8.702399902044814e-07, "loss": 1.7717, "step": 9620 }, { "epoch": 595.0617283950618, "learning_rate": 8.699644912452553e-07, "loss": 1.7992, "step": 9640 }, { "epoch": 596.2962962962963, "learning_rate": 8.69688992286029e-07, "loss": 1.7772, "step": 9660 }, { "epoch": 597.5308641975308, "learning_rate": 8.69413493326803e-07, "loss": 1.7884, "step": 9680 }, { "epoch": 598.7654320987655, "learning_rate": 8.691379943675769e-07, "loss": 1.7618, "step": 9700 }, { "epoch": 600.0, "learning_rate": 8.688624954083506e-07, "loss": 1.7789, "step": 9720 }, { "epoch": 601.2345679012345, "learning_rate": 8.685869964491245e-07, "loss": 1.7624, "step": 9740 }, { "epoch": 602.4691358024692, "learning_rate": 8.683114974898983e-07, "loss": 1.7588, "step": 9760 }, { "epoch": 603.7037037037037, "learning_rate": 8.680359985306722e-07, "loss": 1.793, "step": 9780 }, { "epoch": 604.9382716049382, "learning_rate": 8.677604995714461e-07, "loss": 1.7527, "step": 9800 }, { "epoch": 606.1728395061729, "learning_rate": 8.674850006122198e-07, "loss": 1.7472, "step": 9820 }, { "epoch": 607.4074074074074, "learning_rate": 8.672095016529937e-07, "loss": 1.8087, "step": 9840 }, { "epoch": 608.641975308642, "learning_rate": 8.669340026937675e-07, "loss": 1.7727, "step": 9860 }, { "epoch": 609.8765432098766, "learning_rate": 8.666585037345414e-07, "loss": 1.7672, "step": 9880 }, { "epoch": 611.1111111111111, "learning_rate": 8.663830047753152e-07, "loss": 1.7614, "step": 9900 }, { "epoch": 612.3456790123457, "learning_rate": 8.661075058160891e-07, "loss": 1.7775, "step": 9920 }, { "epoch": 613.5802469135803, "learning_rate": 8.65832006856863e-07, "loss": 1.7512, "step": 9940 }, { "epoch": 614.8148148148148, "learning_rate": 8.655565078976368e-07, "loss": 1.7858, "step": 9960 }, { "epoch": 616.0493827160494, "learning_rate": 8.652810089384107e-07, "loss": 1.8064, "step": 9980 }, { "epoch": 617.283950617284, "learning_rate": 8.650055099791844e-07, "loss": 1.7649, "step": 10000 }, { "epoch": 618.5185185185185, "learning_rate": 8.647300110199584e-07, "loss": 1.8184, "step": 10020 }, { "epoch": 619.7530864197531, "learning_rate": 8.644545120607322e-07, "loss": 1.7532, "step": 10040 }, { "epoch": 620.9876543209876, "learning_rate": 8.64179013101506e-07, "loss": 1.7751, "step": 10060 }, { "epoch": 622.2222222222222, "learning_rate": 8.639035141422799e-07, "loss": 1.7995, "step": 10080 }, { "epoch": 623.4567901234568, "learning_rate": 8.636280151830536e-07, "loss": 1.7737, "step": 10100 }, { "epoch": 624.6913580246913, "learning_rate": 8.633525162238275e-07, "loss": 1.7962, "step": 10120 }, { "epoch": 625.925925925926, "learning_rate": 8.630770172646013e-07, "loss": 1.8228, "step": 10140 }, { "epoch": 627.1604938271605, "learning_rate": 8.628015183053752e-07, "loss": 1.8136, "step": 10160 }, { "epoch": 628.395061728395, "learning_rate": 8.625260193461491e-07, "loss": 1.7708, "step": 10180 }, { "epoch": 629.6296296296297, "learning_rate": 8.622505203869229e-07, "loss": 1.7872, "step": 10200 }, { "epoch": 630.8641975308642, "learning_rate": 8.619750214276968e-07, "loss": 1.7869, "step": 10220 }, { "epoch": 632.0987654320987, "learning_rate": 8.616995224684706e-07, "loss": 1.8117, "step": 10240 }, { "epoch": 633.3333333333334, "learning_rate": 8.614240235092445e-07, "loss": 1.7404, "step": 10260 }, { "epoch": 634.5679012345679, "learning_rate": 8.611485245500185e-07, "loss": 1.7706, "step": 10280 }, { "epoch": 635.8024691358024, "learning_rate": 8.608730255907922e-07, "loss": 1.7781, "step": 10300 }, { "epoch": 637.0370370370371, "learning_rate": 8.605975266315661e-07, "loss": 1.798, "step": 10320 }, { "epoch": 638.2716049382716, "learning_rate": 8.603220276723399e-07, "loss": 1.7768, "step": 10340 }, { "epoch": 639.5061728395061, "learning_rate": 8.600465287131137e-07, "loss": 1.7392, "step": 10360 }, { "epoch": 640.7407407407408, "learning_rate": 8.597710297538874e-07, "loss": 1.801, "step": 10380 }, { "epoch": 641.9753086419753, "learning_rate": 8.594955307946614e-07, "loss": 1.8121, "step": 10400 }, { "epoch": 643.2098765432099, "learning_rate": 8.592200318354353e-07, "loss": 1.7606, "step": 10420 }, { "epoch": 644.4444444444445, "learning_rate": 8.589445328762091e-07, "loss": 1.8174, "step": 10440 }, { "epoch": 645.679012345679, "learning_rate": 8.58669033916983e-07, "loss": 1.7442, "step": 10460 }, { "epoch": 646.9135802469136, "learning_rate": 8.583935349577568e-07, "loss": 1.7462, "step": 10480 }, { "epoch": 648.1481481481482, "learning_rate": 8.581180359985307e-07, "loss": 1.7649, "step": 10500 }, { "epoch": 649.3827160493827, "learning_rate": 8.578425370393046e-07, "loss": 1.7519, "step": 10520 }, { "epoch": 650.6172839506173, "learning_rate": 8.575670380800783e-07, "loss": 1.7684, "step": 10540 }, { "epoch": 651.8518518518518, "learning_rate": 8.572915391208522e-07, "loss": 1.7459, "step": 10560 }, { "epoch": 653.0864197530864, "learning_rate": 8.57016040161626e-07, "loss": 1.7555, "step": 10580 }, { "epoch": 654.320987654321, "learning_rate": 8.567405412023999e-07, "loss": 1.7332, "step": 10600 }, { "epoch": 655.5555555555555, "learning_rate": 8.564650422431737e-07, "loss": 1.7313, "step": 10620 }, { "epoch": 656.7901234567901, "learning_rate": 8.561895432839475e-07, "loss": 1.7064, "step": 10640 }, { "epoch": 658.0246913580247, "learning_rate": 8.559140443247214e-07, "loss": 1.7381, "step": 10660 }, { "epoch": 659.2592592592592, "learning_rate": 8.556385453654952e-07, "loss": 1.7343, "step": 10680 }, { "epoch": 660.4938271604939, "learning_rate": 8.553630464062691e-07, "loss": 1.7368, "step": 10700 }, { "epoch": 661.7283950617284, "learning_rate": 8.550875474470429e-07, "loss": 1.727, "step": 10720 }, { "epoch": 662.9629629629629, "learning_rate": 8.548120484878168e-07, "loss": 1.7363, "step": 10740 }, { "epoch": 664.1975308641976, "learning_rate": 8.545365495285906e-07, "loss": 1.7531, "step": 10760 }, { "epoch": 665.4320987654321, "learning_rate": 8.542610505693645e-07, "loss": 1.7282, "step": 10780 }, { "epoch": 666.6666666666666, "learning_rate": 8.539855516101383e-07, "loss": 1.7276, "step": 10800 }, { "epoch": 667.9012345679013, "learning_rate": 8.537100526509121e-07, "loss": 1.7316, "step": 10820 }, { "epoch": 669.1358024691358, "learning_rate": 8.53434553691686e-07, "loss": 1.7049, "step": 10840 }, { "epoch": 670.3703703703703, "learning_rate": 8.531590547324598e-07, "loss": 1.7183, "step": 10860 }, { "epoch": 671.604938271605, "learning_rate": 8.528835557732337e-07, "loss": 1.7383, "step": 10880 }, { "epoch": 672.8395061728395, "learning_rate": 8.526080568140074e-07, "loss": 1.7376, "step": 10900 }, { "epoch": 674.074074074074, "learning_rate": 8.523325578547813e-07, "loss": 1.7909, "step": 10920 }, { "epoch": 675.3086419753087, "learning_rate": 8.520570588955552e-07, "loss": 1.7334, "step": 10940 }, { "epoch": 676.5432098765432, "learning_rate": 8.51781559936329e-07, "loss": 1.7561, "step": 10960 }, { "epoch": 677.7777777777778, "learning_rate": 8.515060609771029e-07, "loss": 1.6731, "step": 10980 }, { "epoch": 679.0123456790124, "learning_rate": 8.512305620178768e-07, "loss": 1.737, "step": 11000 }, { "epoch": 680.2469135802469, "learning_rate": 8.509550630586507e-07, "loss": 1.7584, "step": 11020 }, { "epoch": 681.4814814814815, "learning_rate": 8.506795640994246e-07, "loss": 1.7177, "step": 11040 }, { "epoch": 682.716049382716, "learning_rate": 8.504040651401984e-07, "loss": 1.7428, "step": 11060 }, { "epoch": 683.9506172839506, "learning_rate": 8.501285661809722e-07, "loss": 1.7631, "step": 11080 }, { "epoch": 685.1851851851852, "learning_rate": 8.49853067221746e-07, "loss": 1.7386, "step": 11100 }, { "epoch": 686.4197530864197, "learning_rate": 8.495775682625199e-07, "loss": 1.7397, "step": 11120 }, { "epoch": 687.6543209876543, "learning_rate": 8.493020693032938e-07, "loss": 1.748, "step": 11140 }, { "epoch": 688.8888888888889, "learning_rate": 8.490265703440676e-07, "loss": 1.7534, "step": 11160 }, { "epoch": 690.1234567901234, "learning_rate": 8.487510713848414e-07, "loss": 1.7246, "step": 11180 }, { "epoch": 691.358024691358, "learning_rate": 8.484755724256152e-07, "loss": 1.7368, "step": 11200 }, { "epoch": 692.5925925925926, "learning_rate": 8.482000734663891e-07, "loss": 1.7433, "step": 11220 }, { "epoch": 693.8271604938271, "learning_rate": 8.479245745071629e-07, "loss": 1.6926, "step": 11240 }, { "epoch": 695.0617283950618, "learning_rate": 8.476490755479368e-07, "loss": 1.7433, "step": 11260 }, { "epoch": 696.2962962962963, "learning_rate": 8.473735765887107e-07, "loss": 1.7399, "step": 11280 }, { "epoch": 697.5308641975308, "learning_rate": 8.470980776294845e-07, "loss": 1.7287, "step": 11300 }, { "epoch": 698.7654320987655, "learning_rate": 8.468225786702584e-07, "loss": 1.724, "step": 11320 }, { "epoch": 700.0, "learning_rate": 8.465470797110321e-07, "loss": 1.7264, "step": 11340 }, { "epoch": 701.2345679012345, "learning_rate": 8.462715807518059e-07, "loss": 1.6885, "step": 11360 }, { "epoch": 702.4691358024692, "learning_rate": 8.459960817925798e-07, "loss": 1.7409, "step": 11380 }, { "epoch": 703.7037037037037, "learning_rate": 8.457205828333537e-07, "loss": 1.7205, "step": 11400 }, { "epoch": 704.9382716049382, "learning_rate": 8.454450838741276e-07, "loss": 1.7151, "step": 11420 }, { "epoch": 706.1728395061729, "learning_rate": 8.451695849149013e-07, "loss": 1.7348, "step": 11440 }, { "epoch": 707.4074074074074, "learning_rate": 8.448940859556752e-07, "loss": 1.7653, "step": 11460 }, { "epoch": 708.641975308642, "learning_rate": 8.44618586996449e-07, "loss": 1.6979, "step": 11480 }, { "epoch": 709.8765432098766, "learning_rate": 8.443430880372229e-07, "loss": 1.7564, "step": 11500 }, { "epoch": 711.1111111111111, "learning_rate": 8.440675890779968e-07, "loss": 1.7528, "step": 11520 }, { "epoch": 712.3456790123457, "learning_rate": 8.437920901187706e-07, "loss": 1.7172, "step": 11540 }, { "epoch": 713.5802469135803, "learning_rate": 8.435165911595445e-07, "loss": 1.7624, "step": 11560 }, { "epoch": 714.8148148148148, "learning_rate": 8.432410922003183e-07, "loss": 1.7049, "step": 11580 }, { "epoch": 716.0493827160494, "learning_rate": 8.429655932410922e-07, "loss": 1.6822, "step": 11600 }, { "epoch": 717.283950617284, "learning_rate": 8.426900942818659e-07, "loss": 1.7359, "step": 11620 }, { "epoch": 718.5185185185185, "learning_rate": 8.424145953226398e-07, "loss": 1.6829, "step": 11640 }, { "epoch": 719.7530864197531, "learning_rate": 8.421390963634137e-07, "loss": 1.7477, "step": 11660 }, { "epoch": 720.9876543209876, "learning_rate": 8.418635974041875e-07, "loss": 1.7161, "step": 11680 }, { "epoch": 722.2222222222222, "learning_rate": 8.415880984449614e-07, "loss": 1.7509, "step": 11700 }, { "epoch": 723.4567901234568, "learning_rate": 8.413125994857352e-07, "loss": 1.7336, "step": 11720 }, { "epoch": 724.6913580246913, "learning_rate": 8.410371005265091e-07, "loss": 1.7179, "step": 11740 }, { "epoch": 725.925925925926, "learning_rate": 8.40761601567283e-07, "loss": 1.7154, "step": 11760 }, { "epoch": 727.1604938271605, "learning_rate": 8.404861026080568e-07, "loss": 1.7359, "step": 11780 }, { "epoch": 728.395061728395, "learning_rate": 8.402106036488307e-07, "loss": 1.7177, "step": 11800 }, { "epoch": 729.6296296296297, "learning_rate": 8.399351046896045e-07, "loss": 1.6956, "step": 11820 }, { "epoch": 730.8641975308642, "learning_rate": 8.396596057303784e-07, "loss": 1.7127, "step": 11840 }, { "epoch": 732.0987654320987, "learning_rate": 8.393841067711522e-07, "loss": 1.7155, "step": 11860 }, { "epoch": 733.3333333333334, "learning_rate": 8.39108607811926e-07, "loss": 1.7437, "step": 11880 }, { "epoch": 734.5679012345679, "learning_rate": 8.388331088526999e-07, "loss": 1.7857, "step": 11900 }, { "epoch": 735.8024691358024, "learning_rate": 8.385576098934737e-07, "loss": 1.7504, "step": 11920 }, { "epoch": 737.0370370370371, "learning_rate": 8.382821109342476e-07, "loss": 1.7573, "step": 11940 }, { "epoch": 738.2716049382716, "learning_rate": 8.380066119750214e-07, "loss": 1.7569, "step": 11960 }, { "epoch": 739.5061728395061, "learning_rate": 8.377311130157952e-07, "loss": 1.7422, "step": 11980 }, { "epoch": 740.7407407407408, "learning_rate": 8.37455614056569e-07, "loss": 1.7292, "step": 12000 }, { "epoch": 741.9753086419753, "learning_rate": 8.371801150973429e-07, "loss": 1.7548, "step": 12020 }, { "epoch": 743.2098765432099, "learning_rate": 8.369046161381168e-07, "loss": 1.7435, "step": 12040 }, { "epoch": 744.4444444444445, "learning_rate": 8.366291171788906e-07, "loss": 1.73, "step": 12060 }, { "epoch": 745.679012345679, "learning_rate": 8.363536182196645e-07, "loss": 1.7321, "step": 12080 }, { "epoch": 746.9135802469136, "learning_rate": 8.360781192604383e-07, "loss": 1.7358, "step": 12100 }, { "epoch": 748.1481481481482, "learning_rate": 8.358026203012122e-07, "loss": 1.7249, "step": 12120 }, { "epoch": 749.3827160493827, "learning_rate": 8.355271213419861e-07, "loss": 1.744, "step": 12140 }, { "epoch": 750.6172839506173, "learning_rate": 8.352516223827598e-07, "loss": 1.7205, "step": 12160 }, { "epoch": 751.8518518518518, "learning_rate": 8.349761234235337e-07, "loss": 1.7333, "step": 12180 }, { "epoch": 753.0864197530864, "learning_rate": 8.347006244643075e-07, "loss": 1.7223, "step": 12200 }, { "epoch": 754.320987654321, "learning_rate": 8.344251255050814e-07, "loss": 1.7959, "step": 12220 }, { "epoch": 755.5555555555555, "learning_rate": 8.341496265458553e-07, "loss": 1.7236, "step": 12240 }, { "epoch": 756.7901234567901, "learning_rate": 8.33874127586629e-07, "loss": 1.6977, "step": 12260 }, { "epoch": 758.0246913580247, "learning_rate": 8.335986286274029e-07, "loss": 1.7903, "step": 12280 }, { "epoch": 759.2592592592592, "learning_rate": 8.333231296681767e-07, "loss": 1.8314, "step": 12300 }, { "epoch": 760.4938271604939, "learning_rate": 8.330476307089506e-07, "loss": 1.7828, "step": 12320 }, { "epoch": 761.7283950617284, "learning_rate": 8.327721317497245e-07, "loss": 1.7989, "step": 12340 }, { "epoch": 762.9629629629629, "learning_rate": 8.324966327904983e-07, "loss": 1.8263, "step": 12360 }, { "epoch": 764.1975308641976, "learning_rate": 8.322211338312722e-07, "loss": 1.7722, "step": 12380 }, { "epoch": 765.4320987654321, "learning_rate": 8.31945634872046e-07, "loss": 1.7722, "step": 12400 }, { "epoch": 766.6666666666666, "learning_rate": 8.316701359128198e-07, "loss": 1.8189, "step": 12420 }, { "epoch": 767.9012345679013, "learning_rate": 8.313946369535936e-07, "loss": 1.8084, "step": 12440 }, { "epoch": 769.1358024691358, "learning_rate": 8.311191379943675e-07, "loss": 1.8459, "step": 12460 }, { "epoch": 770.3703703703703, "learning_rate": 8.308436390351413e-07, "loss": 1.8127, "step": 12480 }, { "epoch": 771.604938271605, "learning_rate": 8.305681400759153e-07, "loss": 1.8462, "step": 12500 }, { "epoch": 772.8395061728395, "learning_rate": 8.302926411166891e-07, "loss": 1.8975, "step": 12520 }, { "epoch": 774.074074074074, "learning_rate": 8.300171421574629e-07, "loss": 1.8836, "step": 12540 }, { "epoch": 775.3086419753087, "learning_rate": 8.297416431982368e-07, "loss": 1.8912, "step": 12560 }, { "epoch": 776.5432098765432, "learning_rate": 8.294661442390106e-07, "loss": 1.962, "step": 12580 }, { "epoch": 777.7777777777778, "learning_rate": 8.291906452797846e-07, "loss": 1.9474, "step": 12600 }, { "epoch": 779.0123456790124, "learning_rate": 8.289151463205584e-07, "loss": 1.9509, "step": 12620 }, { "epoch": 780.2469135802469, "learning_rate": 8.286396473613322e-07, "loss": 1.9723, "step": 12640 }, { "epoch": 781.4814814814815, "learning_rate": 8.283641484021061e-07, "loss": 2.0032, "step": 12660 }, { "epoch": 782.716049382716, "learning_rate": 8.280886494428799e-07, "loss": 2.0202, "step": 12680 }, { "epoch": 783.9506172839506, "learning_rate": 8.278131504836536e-07, "loss": 2.0187, "step": 12700 }, { "epoch": 785.1851851851852, "learning_rate": 8.275376515244275e-07, "loss": 2.0322, "step": 12720 }, { "epoch": 786.4197530864197, "learning_rate": 8.272621525652014e-07, "loss": 1.9868, "step": 12740 }, { "epoch": 787.6543209876543, "learning_rate": 8.269866536059753e-07, "loss": 2.0095, "step": 12760 }, { "epoch": 788.8888888888889, "learning_rate": 8.267111546467491e-07, "loss": 2.0626, "step": 12780 }, { "epoch": 790.1234567901234, "learning_rate": 8.264356556875229e-07, "loss": 1.9852, "step": 12800 }, { "epoch": 791.358024691358, "learning_rate": 8.261601567282967e-07, "loss": 2.1492, "step": 12820 }, { "epoch": 792.5925925925926, "learning_rate": 8.258846577690706e-07, "loss": 2.1298, "step": 12840 }, { "epoch": 793.8271604938271, "learning_rate": 8.256091588098445e-07, "loss": 2.0899, "step": 12860 }, { "epoch": 795.0617283950618, "learning_rate": 8.253336598506183e-07, "loss": 2.1285, "step": 12880 }, { "epoch": 796.2962962962963, "learning_rate": 8.250581608913922e-07, "loss": 2.1273, "step": 12900 }, { "epoch": 797.5308641975308, "learning_rate": 8.24782661932166e-07, "loss": 2.0783, "step": 12920 }, { "epoch": 798.7654320987655, "learning_rate": 8.245071629729399e-07, "loss": 2.0597, "step": 12940 }, { "epoch": 800.0, "learning_rate": 8.242316640137136e-07, "loss": 2.0814, "step": 12960 }, { "epoch": 801.2345679012345, "learning_rate": 8.239561650544875e-07, "loss": 2.0731, "step": 12980 }, { "epoch": 802.4691358024692, "learning_rate": 8.236806660952614e-07, "loss": 2.0179, "step": 13000 }, { "epoch": 803.7037037037037, "learning_rate": 8.234051671360352e-07, "loss": 2.056, "step": 13020 }, { "epoch": 804.9382716049382, "learning_rate": 8.231296681768091e-07, "loss": 1.9941, "step": 13040 }, { "epoch": 806.1728395061729, "learning_rate": 8.228541692175829e-07, "loss": 1.9576, "step": 13060 }, { "epoch": 807.4074074074074, "learning_rate": 8.225786702583567e-07, "loss": 1.9323, "step": 13080 }, { "epoch": 808.641975308642, "learning_rate": 8.223031712991305e-07, "loss": 1.9424, "step": 13100 }, { "epoch": 809.8765432098766, "learning_rate": 8.220276723399044e-07, "loss": 1.9416, "step": 13120 }, { "epoch": 811.1111111111111, "learning_rate": 8.217521733806783e-07, "loss": 1.9588, "step": 13140 }, { "epoch": 812.3456790123457, "learning_rate": 8.214766744214521e-07, "loss": 1.91, "step": 13160 }, { "epoch": 813.5802469135803, "learning_rate": 8.21201175462226e-07, "loss": 1.9721, "step": 13180 }, { "epoch": 814.8148148148148, "learning_rate": 8.209256765029998e-07, "loss": 1.912, "step": 13200 }, { "epoch": 816.0493827160494, "learning_rate": 8.206501775437737e-07, "loss": 1.9495, "step": 13220 }, { "epoch": 817.283950617284, "learning_rate": 8.203746785845476e-07, "loss": 1.9077, "step": 13240 }, { "epoch": 818.5185185185185, "learning_rate": 8.200991796253214e-07, "loss": 1.9338, "step": 13260 }, { "epoch": 819.7530864197531, "learning_rate": 8.198236806660953e-07, "loss": 1.9473, "step": 13280 }, { "epoch": 820.9876543209876, "learning_rate": 8.195481817068691e-07, "loss": 1.9889, "step": 13300 }, { "epoch": 822.2222222222222, "learning_rate": 8.19272682747643e-07, "loss": 1.9169, "step": 13320 }, { "epoch": 823.4567901234568, "learning_rate": 8.189971837884167e-07, "loss": 1.9493, "step": 13340 }, { "epoch": 824.6913580246913, "learning_rate": 8.187216848291906e-07, "loss": 1.9277, "step": 13360 }, { "epoch": 825.925925925926, "learning_rate": 8.184461858699645e-07, "loss": 1.8767, "step": 13380 }, { "epoch": 827.1604938271605, "learning_rate": 8.181706869107383e-07, "loss": 1.9362, "step": 13400 }, { "epoch": 828.395061728395, "learning_rate": 8.178951879515122e-07, "loss": 1.8912, "step": 13420 }, { "epoch": 829.6296296296297, "learning_rate": 8.17619688992286e-07, "loss": 1.9401, "step": 13440 }, { "epoch": 830.8641975308642, "learning_rate": 8.173441900330599e-07, "loss": 1.9745, "step": 13460 }, { "epoch": 832.0987654320987, "learning_rate": 8.170686910738338e-07, "loss": 1.9682, "step": 13480 }, { "epoch": 833.3333333333334, "learning_rate": 8.167931921146075e-07, "loss": 1.8886, "step": 13500 }, { "epoch": 834.5679012345679, "learning_rate": 8.165176931553814e-07, "loss": 1.858, "step": 13520 }, { "epoch": 835.8024691358024, "learning_rate": 8.162421941961552e-07, "loss": 1.8989, "step": 13540 }, { "epoch": 837.0370370370371, "learning_rate": 8.159666952369291e-07, "loss": 1.9077, "step": 13560 }, { "epoch": 838.2716049382716, "learning_rate": 8.156911962777029e-07, "loss": 1.8887, "step": 13580 }, { "epoch": 839.5061728395061, "learning_rate": 8.154156973184767e-07, "loss": 1.8853, "step": 13600 }, { "epoch": 840.7407407407408, "learning_rate": 8.151401983592506e-07, "loss": 1.8671, "step": 13620 }, { "epoch": 841.9753086419753, "learning_rate": 8.148646994000244e-07, "loss": 1.9438, "step": 13640 }, { "epoch": 843.2098765432099, "learning_rate": 8.145892004407983e-07, "loss": 1.9565, "step": 13660 }, { "epoch": 844.4444444444445, "learning_rate": 8.14313701481572e-07, "loss": 1.927, "step": 13680 }, { "epoch": 845.679012345679, "learning_rate": 8.14038202522346e-07, "loss": 1.9143, "step": 13700 }, { "epoch": 846.9135802469136, "learning_rate": 8.137627035631199e-07, "loss": 1.9466, "step": 13720 }, { "epoch": 848.1481481481482, "learning_rate": 8.134872046038937e-07, "loss": 1.9136, "step": 13740 }, { "epoch": 849.3827160493827, "learning_rate": 8.132117056446676e-07, "loss": 1.9526, "step": 13760 }, { "epoch": 850.6172839506173, "learning_rate": 8.129362066854413e-07, "loss": 1.9294, "step": 13780 }, { "epoch": 851.8518518518518, "learning_rate": 8.126607077262152e-07, "loss": 1.9162, "step": 13800 }, { "epoch": 853.0864197530864, "learning_rate": 8.12385208766989e-07, "loss": 1.9758, "step": 13820 }, { "epoch": 854.320987654321, "learning_rate": 8.121097098077629e-07, "loss": 1.9344, "step": 13840 }, { "epoch": 855.5555555555555, "learning_rate": 8.118342108485368e-07, "loss": 1.9263, "step": 13860 }, { "epoch": 856.7901234567901, "learning_rate": 8.115587118893105e-07, "loss": 1.9164, "step": 13880 }, { "epoch": 858.0246913580247, "learning_rate": 8.112832129300844e-07, "loss": 1.9291, "step": 13900 }, { "epoch": 859.2592592592592, "learning_rate": 8.110077139708582e-07, "loss": 1.9555, "step": 13920 }, { "epoch": 860.4938271604939, "learning_rate": 8.107322150116321e-07, "loss": 1.9301, "step": 13940 }, { "epoch": 861.7283950617284, "learning_rate": 8.104567160524059e-07, "loss": 1.9491, "step": 13960 }, { "epoch": 862.9629629629629, "learning_rate": 8.101812170931799e-07, "loss": 1.9694, "step": 13980 }, { "epoch": 864.1975308641976, "learning_rate": 8.099057181339538e-07, "loss": 1.9086, "step": 14000 }, { "epoch": 865.4320987654321, "learning_rate": 8.096302191747276e-07, "loss": 1.9431, "step": 14020 }, { "epoch": 866.6666666666666, "learning_rate": 8.093547202155014e-07, "loss": 1.9224, "step": 14040 }, { "epoch": 867.9012345679013, "learning_rate": 8.090792212562752e-07, "loss": 1.9335, "step": 14060 }, { "epoch": 869.1358024691358, "learning_rate": 8.088037222970491e-07, "loss": 1.9382, "step": 14080 }, { "epoch": 870.3703703703703, "learning_rate": 8.08528223337823e-07, "loss": 1.9268, "step": 14100 }, { "epoch": 871.604938271605, "learning_rate": 8.082527243785968e-07, "loss": 1.9787, "step": 14120 }, { "epoch": 872.8395061728395, "learning_rate": 8.079772254193706e-07, "loss": 1.9271, "step": 14140 }, { "epoch": 874.074074074074, "learning_rate": 8.077017264601444e-07, "loss": 1.9718, "step": 14160 }, { "epoch": 875.3086419753087, "learning_rate": 8.074262275009183e-07, "loss": 1.9799, "step": 14180 }, { "epoch": 876.5432098765432, "learning_rate": 8.071507285416921e-07, "loss": 1.9316, "step": 14200 }, { "epoch": 877.7777777777778, "learning_rate": 8.06875229582466e-07, "loss": 1.8673, "step": 14220 }, { "epoch": 879.0123456790124, "learning_rate": 8.065997306232399e-07, "loss": 1.9195, "step": 14240 }, { "epoch": 880.2469135802469, "learning_rate": 8.063242316640137e-07, "loss": 1.8892, "step": 14260 }, { "epoch": 881.4814814814815, "learning_rate": 8.060487327047876e-07, "loss": 1.9126, "step": 14280 }, { "epoch": 882.716049382716, "learning_rate": 8.057732337455613e-07, "loss": 1.8663, "step": 14300 }, { "epoch": 883.9506172839506, "learning_rate": 8.054977347863352e-07, "loss": 1.9217, "step": 14320 }, { "epoch": 885.1851851851852, "learning_rate": 8.05222235827109e-07, "loss": 1.9216, "step": 14340 }, { "epoch": 886.4197530864197, "learning_rate": 8.049467368678829e-07, "loss": 1.904, "step": 14360 }, { "epoch": 887.6543209876543, "learning_rate": 8.046712379086568e-07, "loss": 1.8645, "step": 14380 }, { "epoch": 888.8888888888889, "learning_rate": 8.043957389494306e-07, "loss": 1.8726, "step": 14400 }, { "epoch": 890.1234567901234, "learning_rate": 8.041202399902044e-07, "loss": 1.9218, "step": 14420 }, { "epoch": 891.358024691358, "learning_rate": 8.038447410309782e-07, "loss": 1.875, "step": 14440 }, { "epoch": 892.5925925925926, "learning_rate": 8.035692420717521e-07, "loss": 1.8218, "step": 14460 }, { "epoch": 893.8271604938271, "learning_rate": 8.03293743112526e-07, "loss": 1.8583, "step": 14480 }, { "epoch": 895.0617283950618, "learning_rate": 8.030182441532998e-07, "loss": 1.8696, "step": 14500 }, { "epoch": 896.2962962962963, "learning_rate": 8.027427451940737e-07, "loss": 1.883, "step": 14520 }, { "epoch": 897.5308641975308, "learning_rate": 8.024672462348475e-07, "loss": 1.9137, "step": 14540 }, { "epoch": 898.7654320987655, "learning_rate": 8.021917472756214e-07, "loss": 1.871, "step": 14560 }, { "epoch": 900.0, "learning_rate": 8.019162483163951e-07, "loss": 1.8984, "step": 14580 }, { "epoch": 901.2345679012345, "learning_rate": 8.01640749357169e-07, "loss": 1.8821, "step": 14600 }, { "epoch": 902.4691358024692, "learning_rate": 8.013652503979429e-07, "loss": 1.9334, "step": 14620 }, { "epoch": 903.7037037037037, "learning_rate": 8.010897514387167e-07, "loss": 1.9117, "step": 14640 }, { "epoch": 904.9382716049382, "learning_rate": 8.008142524794907e-07, "loss": 1.9062, "step": 14660 }, { "epoch": 906.1728395061729, "learning_rate": 8.005387535202643e-07, "loss": 1.8953, "step": 14680 }, { "epoch": 907.4074074074074, "learning_rate": 8.002632545610383e-07, "loss": 1.8603, "step": 14700 }, { "epoch": 908.641975308642, "learning_rate": 7.999877556018122e-07, "loss": 1.8817, "step": 14720 }, { "epoch": 909.8765432098766, "learning_rate": 7.99712256642586e-07, "loss": 1.8897, "step": 14740 }, { "epoch": 911.1111111111111, "learning_rate": 7.994367576833599e-07, "loss": 1.8911, "step": 14760 }, { "epoch": 912.3456790123457, "learning_rate": 7.991612587241337e-07, "loss": 1.9044, "step": 14780 }, { "epoch": 913.5802469135803, "learning_rate": 7.988857597649076e-07, "loss": 1.8823, "step": 14800 }, { "epoch": 914.8148148148148, "learning_rate": 7.986102608056815e-07, "loss": 1.8894, "step": 14820 }, { "epoch": 916.0493827160494, "learning_rate": 7.983347618464552e-07, "loss": 1.8829, "step": 14840 }, { "epoch": 917.283950617284, "learning_rate": 7.980592628872291e-07, "loss": 1.8715, "step": 14860 }, { "epoch": 918.5185185185185, "learning_rate": 7.977837639280029e-07, "loss": 1.8413, "step": 14880 }, { "epoch": 919.7530864197531, "learning_rate": 7.975082649687768e-07, "loss": 1.8672, "step": 14900 }, { "epoch": 920.9876543209876, "learning_rate": 7.972327660095507e-07, "loss": 1.9188, "step": 14920 }, { "epoch": 922.2222222222222, "learning_rate": 7.969572670503245e-07, "loss": 1.8789, "step": 14940 }, { "epoch": 923.4567901234568, "learning_rate": 7.966817680910983e-07, "loss": 1.8792, "step": 14960 }, { "epoch": 924.6913580246913, "learning_rate": 7.964062691318721e-07, "loss": 1.9256, "step": 14980 }, { "epoch": 925.925925925926, "learning_rate": 7.96130770172646e-07, "loss": 1.8604, "step": 15000 }, { "epoch": 927.1604938271605, "learning_rate": 7.958552712134197e-07, "loss": 1.8824, "step": 15020 }, { "epoch": 928.395061728395, "learning_rate": 7.955797722541937e-07, "loss": 1.845, "step": 15040 }, { "epoch": 929.6296296296297, "learning_rate": 7.953042732949675e-07, "loss": 1.8786, "step": 15060 }, { "epoch": 930.8641975308642, "learning_rate": 7.950287743357414e-07, "loss": 1.8718, "step": 15080 }, { "epoch": 932.0987654320987, "learning_rate": 7.947532753765153e-07, "loss": 1.8616, "step": 15100 }, { "epoch": 933.3333333333334, "learning_rate": 7.94477776417289e-07, "loss": 1.8385, "step": 15120 }, { "epoch": 934.5679012345679, "learning_rate": 7.942022774580629e-07, "loss": 1.8861, "step": 15140 }, { "epoch": 935.8024691358024, "learning_rate": 7.939267784988367e-07, "loss": 1.8108, "step": 15160 }, { "epoch": 937.0370370370371, "learning_rate": 7.936512795396106e-07, "loss": 1.8679, "step": 15180 }, { "epoch": 938.2716049382716, "learning_rate": 7.933757805803845e-07, "loss": 1.8664, "step": 15200 }, { "epoch": 939.5061728395061, "learning_rate": 7.931002816211582e-07, "loss": 1.8981, "step": 15220 }, { "epoch": 940.7407407407408, "learning_rate": 7.928247826619321e-07, "loss": 1.8679, "step": 15240 }, { "epoch": 941.9753086419753, "learning_rate": 7.925492837027059e-07, "loss": 1.8222, "step": 15260 }, { "epoch": 943.2098765432099, "learning_rate": 7.922737847434798e-07, "loss": 1.8878, "step": 15280 }, { "epoch": 944.4444444444445, "learning_rate": 7.919982857842536e-07, "loss": 1.9096, "step": 15300 }, { "epoch": 945.679012345679, "learning_rate": 7.917227868250275e-07, "loss": 1.9034, "step": 15320 }, { "epoch": 946.9135802469136, "learning_rate": 7.914472878658014e-07, "loss": 1.8802, "step": 15340 }, { "epoch": 948.1481481481482, "learning_rate": 7.911717889065752e-07, "loss": 1.935, "step": 15360 }, { "epoch": 949.3827160493827, "learning_rate": 7.908962899473489e-07, "loss": 1.8363, "step": 15380 }, { "epoch": 950.6172839506173, "learning_rate": 7.906207909881228e-07, "loss": 1.945, "step": 15400 }, { "epoch": 951.8518518518518, "learning_rate": 7.903452920288967e-07, "loss": 1.8431, "step": 15420 }, { "epoch": 953.0864197530864, "learning_rate": 7.900697930696705e-07, "loss": 1.9474, "step": 15440 }, { "epoch": 954.320987654321, "learning_rate": 7.897942941104444e-07, "loss": 1.8394, "step": 15460 }, { "epoch": 955.5555555555555, "learning_rate": 7.895187951512183e-07, "loss": 1.8496, "step": 15480 }, { "epoch": 956.7901234567901, "learning_rate": 7.892432961919921e-07, "loss": 1.8566, "step": 15500 }, { "epoch": 958.0246913580247, "learning_rate": 7.88967797232766e-07, "loss": 1.8255, "step": 15520 }, { "epoch": 959.2592592592592, "learning_rate": 7.886922982735398e-07, "loss": 1.8211, "step": 15540 }, { "epoch": 960.4938271604939, "learning_rate": 7.884167993143137e-07, "loss": 1.9098, "step": 15560 }, { "epoch": 961.7283950617284, "learning_rate": 7.881413003550876e-07, "loss": 1.8611, "step": 15580 }, { "epoch": 962.9629629629629, "learning_rate": 7.878658013958614e-07, "loss": 1.8489, "step": 15600 }, { "epoch": 964.1975308641976, "learning_rate": 7.875903024366353e-07, "loss": 1.8596, "step": 15620 }, { "epoch": 965.4320987654321, "learning_rate": 7.873148034774091e-07, "loss": 1.8228, "step": 15640 }, { "epoch": 966.6666666666666, "learning_rate": 7.870393045181829e-07, "loss": 1.8544, "step": 15660 }, { "epoch": 967.9012345679013, "learning_rate": 7.867638055589567e-07, "loss": 1.8485, "step": 15680 }, { "epoch": 969.1358024691358, "learning_rate": 7.864883065997306e-07, "loss": 1.8627, "step": 15700 }, { "epoch": 970.3703703703703, "learning_rate": 7.862128076405045e-07, "loss": 1.8513, "step": 15720 }, { "epoch": 971.604938271605, "learning_rate": 7.859373086812783e-07, "loss": 1.8237, "step": 15740 }, { "epoch": 972.8395061728395, "learning_rate": 7.856618097220521e-07, "loss": 1.8937, "step": 15760 }, { "epoch": 974.074074074074, "learning_rate": 7.853863107628259e-07, "loss": 1.8339, "step": 15780 }, { "epoch": 975.3086419753087, "learning_rate": 7.851108118035998e-07, "loss": 1.8441, "step": 15800 }, { "epoch": 976.5432098765432, "learning_rate": 7.848353128443737e-07, "loss": 1.8302, "step": 15820 }, { "epoch": 977.7777777777778, "learning_rate": 7.845598138851475e-07, "loss": 1.8206, "step": 15840 }, { "epoch": 979.0123456790124, "learning_rate": 7.842843149259214e-07, "loss": 1.8555, "step": 15860 }, { "epoch": 980.2469135802469, "learning_rate": 7.840088159666952e-07, "loss": 1.8069, "step": 15880 }, { "epoch": 981.4814814814815, "learning_rate": 7.837333170074691e-07, "loss": 1.8273, "step": 15900 }, { "epoch": 982.716049382716, "learning_rate": 7.834578180482428e-07, "loss": 1.7991, "step": 15920 }, { "epoch": 983.9506172839506, "learning_rate": 7.831823190890167e-07, "loss": 1.8335, "step": 15940 }, { "epoch": 985.1851851851852, "learning_rate": 7.829068201297906e-07, "loss": 1.8476, "step": 15960 }, { "epoch": 986.4197530864197, "learning_rate": 7.826313211705644e-07, "loss": 1.8351, "step": 15980 }, { "epoch": 987.6543209876543, "learning_rate": 7.823558222113382e-07, "loss": 1.8428, "step": 16000 }, { "epoch": 988.8888888888889, "learning_rate": 7.82080323252112e-07, "loss": 1.8176, "step": 16020 }, { "epoch": 990.1234567901234, "learning_rate": 7.818048242928859e-07, "loss": 1.83, "step": 16040 }, { "epoch": 991.358024691358, "learning_rate": 7.815293253336597e-07, "loss": 1.8648, "step": 16060 }, { "epoch": 992.5925925925926, "learning_rate": 7.812538263744336e-07, "loss": 1.8545, "step": 16080 }, { "epoch": 993.8271604938271, "learning_rate": 7.809783274152075e-07, "loss": 1.8217, "step": 16100 }, { "epoch": 995.0617283950618, "learning_rate": 7.807028284559813e-07, "loss": 1.7575, "step": 16120 }, { "epoch": 996.2962962962963, "learning_rate": 7.804273294967552e-07, "loss": 1.7868, "step": 16140 }, { "epoch": 997.5308641975308, "learning_rate": 7.80151830537529e-07, "loss": 1.8232, "step": 16160 }, { "epoch": 998.7654320987655, "learning_rate": 7.798763315783029e-07, "loss": 1.7882, "step": 16180 }, { "epoch": 1000.0, "learning_rate": 7.796008326190768e-07, "loss": 1.8071, "step": 16200 }, { "epoch": 1001.2345679012345, "learning_rate": 7.793253336598506e-07, "loss": 1.8153, "step": 16220 }, { "epoch": 1002.4691358024692, "learning_rate": 7.790498347006245e-07, "loss": 1.7843, "step": 16240 }, { "epoch": 1003.7037037037037, "learning_rate": 7.787743357413984e-07, "loss": 1.8265, "step": 16260 }, { "epoch": 1004.9382716049382, "learning_rate": 7.784988367821722e-07, "loss": 1.8141, "step": 16280 }, { "epoch": 1006.1728395061729, "learning_rate": 7.78223337822946e-07, "loss": 1.8397, "step": 16300 }, { "epoch": 1007.4074074074074, "learning_rate": 7.779478388637198e-07, "loss": 1.844, "step": 16320 }, { "epoch": 1008.641975308642, "learning_rate": 7.776723399044937e-07, "loss": 1.799, "step": 16340 }, { "epoch": 1009.8765432098766, "learning_rate": 7.773968409452675e-07, "loss": 1.8023, "step": 16360 }, { "epoch": 1011.1111111111111, "learning_rate": 7.771213419860414e-07, "loss": 1.8189, "step": 16380 }, { "epoch": 1012.3456790123457, "learning_rate": 7.768458430268152e-07, "loss": 1.7896, "step": 16400 }, { "epoch": 1013.5802469135803, "learning_rate": 7.765703440675891e-07, "loss": 1.7747, "step": 16420 }, { "epoch": 1014.8148148148148, "learning_rate": 7.76294845108363e-07, "loss": 1.8221, "step": 16440 }, { "epoch": 1016.0493827160494, "learning_rate": 7.760193461491367e-07, "loss": 1.8302, "step": 16460 }, { "epoch": 1017.283950617284, "learning_rate": 7.757438471899106e-07, "loss": 1.8115, "step": 16480 }, { "epoch": 1018.5185185185185, "learning_rate": 7.754683482306844e-07, "loss": 1.7948, "step": 16500 }, { "epoch": 1019.7530864197531, "learning_rate": 7.751928492714583e-07, "loss": 1.791, "step": 16520 }, { "epoch": 1020.9876543209876, "learning_rate": 7.749173503122321e-07, "loss": 1.8166, "step": 16540 }, { "epoch": 1022.2222222222222, "learning_rate": 7.746418513530059e-07, "loss": 1.8231, "step": 16560 }, { "epoch": 1023.4567901234568, "learning_rate": 7.743663523937798e-07, "loss": 1.7667, "step": 16580 }, { "epoch": 1024.6913580246915, "learning_rate": 7.740908534345536e-07, "loss": 1.8331, "step": 16600 }, { "epoch": 1025.9259259259259, "learning_rate": 7.738153544753275e-07, "loss": 1.8244, "step": 16620 }, { "epoch": 1027.1604938271605, "learning_rate": 7.735398555161013e-07, "loss": 1.8083, "step": 16640 }, { "epoch": 1028.3950617283951, "learning_rate": 7.732643565568752e-07, "loss": 1.9108, "step": 16660 }, { "epoch": 1029.6296296296296, "learning_rate": 7.729888575976491e-07, "loss": 1.8943, "step": 16680 }, { "epoch": 1030.8641975308642, "learning_rate": 7.727133586384229e-07, "loss": 1.8622, "step": 16700 }, { "epoch": 1032.0987654320988, "learning_rate": 7.724378596791968e-07, "loss": 1.8061, "step": 16720 }, { "epoch": 1033.3333333333333, "learning_rate": 7.721623607199706e-07, "loss": 1.8007, "step": 16740 }, { "epoch": 1034.567901234568, "learning_rate": 7.718868617607444e-07, "loss": 1.8463, "step": 16760 }, { "epoch": 1035.8024691358025, "learning_rate": 7.716113628015182e-07, "loss": 1.8533, "step": 16780 }, { "epoch": 1037.037037037037, "learning_rate": 7.713358638422921e-07, "loss": 1.8287, "step": 16800 }, { "epoch": 1038.2716049382716, "learning_rate": 7.710603648830659e-07, "loss": 1.8153, "step": 16820 }, { "epoch": 1039.5061728395062, "learning_rate": 7.707848659238397e-07, "loss": 1.7903, "step": 16840 }, { "epoch": 1040.7407407407406, "learning_rate": 7.705093669646136e-07, "loss": 1.8491, "step": 16860 }, { "epoch": 1041.9753086419753, "learning_rate": 7.702338680053874e-07, "loss": 1.8319, "step": 16880 }, { "epoch": 1043.20987654321, "learning_rate": 7.699583690461613e-07, "loss": 1.856, "step": 16900 }, { "epoch": 1044.4444444444443, "learning_rate": 7.696828700869351e-07, "loss": 1.8419, "step": 16920 }, { "epoch": 1045.679012345679, "learning_rate": 7.69407371127709e-07, "loss": 1.7753, "step": 16940 }, { "epoch": 1046.9135802469136, "learning_rate": 7.69131872168483e-07, "loss": 1.8129, "step": 16960 }, { "epoch": 1048.148148148148, "learning_rate": 7.688563732092568e-07, "loss": 1.7887, "step": 16980 }, { "epoch": 1049.3827160493827, "learning_rate": 7.685808742500307e-07, "loss": 1.8068, "step": 17000 }, { "epoch": 1050.6172839506173, "learning_rate": 7.683053752908044e-07, "loss": 1.8225, "step": 17020 }, { "epoch": 1051.851851851852, "learning_rate": 7.680298763315783e-07, "loss": 1.7596, "step": 17040 }, { "epoch": 1053.0864197530864, "learning_rate": 7.677543773723522e-07, "loss": 1.8343, "step": 17060 }, { "epoch": 1054.320987654321, "learning_rate": 7.674788784131259e-07, "loss": 1.7608, "step": 17080 }, { "epoch": 1055.5555555555557, "learning_rate": 7.672033794538998e-07, "loss": 1.8318, "step": 17100 }, { "epoch": 1056.79012345679, "learning_rate": 7.669278804946736e-07, "loss": 1.8261, "step": 17120 }, { "epoch": 1058.0246913580247, "learning_rate": 7.666523815354475e-07, "loss": 1.8249, "step": 17140 }, { "epoch": 1059.2592592592594, "learning_rate": 7.663768825762213e-07, "loss": 1.8174, "step": 17160 }, { "epoch": 1060.4938271604938, "learning_rate": 7.661013836169952e-07, "loss": 1.7851, "step": 17180 }, { "epoch": 1061.7283950617284, "learning_rate": 7.658258846577691e-07, "loss": 1.8058, "step": 17200 }, { "epoch": 1062.962962962963, "learning_rate": 7.655503856985429e-07, "loss": 1.8048, "step": 17220 }, { "epoch": 1064.1975308641975, "learning_rate": 7.652748867393169e-07, "loss": 1.7883, "step": 17240 }, { "epoch": 1065.432098765432, "learning_rate": 7.649993877800906e-07, "loss": 1.8055, "step": 17260 }, { "epoch": 1066.6666666666667, "learning_rate": 7.647238888208645e-07, "loss": 1.7948, "step": 17280 }, { "epoch": 1067.9012345679012, "learning_rate": 7.644483898616383e-07, "loss": 1.7925, "step": 17300 }, { "epoch": 1069.1358024691358, "learning_rate": 7.641728909024121e-07, "loss": 1.8294, "step": 17320 }, { "epoch": 1070.3703703703704, "learning_rate": 7.638973919431859e-07, "loss": 1.7673, "step": 17340 }, { "epoch": 1071.6049382716049, "learning_rate": 7.636218929839597e-07, "loss": 1.7872, "step": 17360 }, { "epoch": 1072.8395061728395, "learning_rate": 7.633463940247336e-07, "loss": 1.765, "step": 17380 }, { "epoch": 1074.0740740740741, "learning_rate": 7.630708950655074e-07, "loss": 1.7924, "step": 17400 }, { "epoch": 1075.3086419753085, "learning_rate": 7.627953961062813e-07, "loss": 1.7804, "step": 17420 }, { "epoch": 1076.5432098765432, "learning_rate": 7.625198971470552e-07, "loss": 1.7999, "step": 17440 }, { "epoch": 1077.7777777777778, "learning_rate": 7.62244398187829e-07, "loss": 1.8317, "step": 17460 }, { "epoch": 1079.0123456790122, "learning_rate": 7.619688992286029e-07, "loss": 1.7989, "step": 17480 }, { "epoch": 1080.2469135802469, "learning_rate": 7.616934002693767e-07, "loss": 1.8067, "step": 17500 }, { "epoch": 1081.4814814814815, "learning_rate": 7.614179013101506e-07, "loss": 1.798, "step": 17520 }, { "epoch": 1082.716049382716, "learning_rate": 7.611424023509245e-07, "loss": 1.7895, "step": 17540 }, { "epoch": 1083.9506172839506, "learning_rate": 7.608669033916982e-07, "loss": 1.7702, "step": 17560 }, { "epoch": 1085.1851851851852, "learning_rate": 7.605914044324721e-07, "loss": 1.7835, "step": 17580 }, { "epoch": 1086.4197530864199, "learning_rate": 7.603159054732459e-07, "loss": 1.7743, "step": 17600 }, { "epoch": 1087.6543209876543, "learning_rate": 7.600404065140197e-07, "loss": 1.835, "step": 17620 }, { "epoch": 1088.888888888889, "learning_rate": 7.597649075547935e-07, "loss": 1.7897, "step": 17640 }, { "epoch": 1090.1234567901236, "learning_rate": 7.594894085955674e-07, "loss": 1.7955, "step": 17660 }, { "epoch": 1091.358024691358, "learning_rate": 7.592139096363414e-07, "loss": 1.8113, "step": 17680 }, { "epoch": 1092.5925925925926, "learning_rate": 7.589384106771152e-07, "loss": 1.7714, "step": 17700 }, { "epoch": 1093.8271604938273, "learning_rate": 7.586629117178891e-07, "loss": 1.8433, "step": 17720 }, { "epoch": 1095.0617283950617, "learning_rate": 7.583874127586629e-07, "loss": 1.8022, "step": 17740 }, { "epoch": 1096.2962962962963, "learning_rate": 7.581119137994368e-07, "loss": 1.7671, "step": 17760 }, { "epoch": 1097.530864197531, "learning_rate": 7.578364148402107e-07, "loss": 1.7749, "step": 17780 }, { "epoch": 1098.7654320987654, "learning_rate": 7.575609158809845e-07, "loss": 1.7352, "step": 17800 }, { "epoch": 1100.0, "learning_rate": 7.572854169217584e-07, "loss": 1.7511, "step": 17820 }, { "epoch": 1101.2345679012346, "learning_rate": 7.570099179625321e-07, "loss": 1.7498, "step": 17840 }, { "epoch": 1102.469135802469, "learning_rate": 7.56734419003306e-07, "loss": 1.771, "step": 17860 }, { "epoch": 1103.7037037037037, "learning_rate": 7.564589200440798e-07, "loss": 1.7921, "step": 17880 }, { "epoch": 1104.9382716049383, "learning_rate": 7.561834210848536e-07, "loss": 1.7689, "step": 17900 }, { "epoch": 1106.1728395061727, "learning_rate": 7.559079221256275e-07, "loss": 1.7358, "step": 17920 }, { "epoch": 1107.4074074074074, "learning_rate": 7.556324231664013e-07, "loss": 1.7594, "step": 17940 }, { "epoch": 1108.641975308642, "learning_rate": 7.553569242071753e-07, "loss": 1.7568, "step": 17960 }, { "epoch": 1109.8765432098764, "learning_rate": 7.55081425247949e-07, "loss": 1.7872, "step": 17980 }, { "epoch": 1111.111111111111, "learning_rate": 7.548059262887229e-07, "loss": 1.8052, "step": 18000 }, { "epoch": 1112.3456790123457, "learning_rate": 7.545304273294968e-07, "loss": 1.757, "step": 18020 }, { "epoch": 1113.5802469135801, "learning_rate": 7.542549283702706e-07, "loss": 1.7756, "step": 18040 }, { "epoch": 1114.8148148148148, "learning_rate": 7.539794294110445e-07, "loss": 1.7773, "step": 18060 }, { "epoch": 1116.0493827160494, "learning_rate": 7.537039304518183e-07, "loss": 1.8416, "step": 18080 }, { "epoch": 1117.283950617284, "learning_rate": 7.534284314925921e-07, "loss": 1.7244, "step": 18100 }, { "epoch": 1118.5185185185185, "learning_rate": 7.531529325333659e-07, "loss": 1.7225, "step": 18120 }, { "epoch": 1119.7530864197531, "learning_rate": 7.528774335741398e-07, "loss": 1.7795, "step": 18140 }, { "epoch": 1120.9876543209878, "learning_rate": 7.526019346149136e-07, "loss": 1.768, "step": 18160 }, { "epoch": 1122.2222222222222, "learning_rate": 7.523264356556874e-07, "loss": 1.7673, "step": 18180 }, { "epoch": 1123.4567901234568, "learning_rate": 7.520509366964613e-07, "loss": 1.7372, "step": 18200 }, { "epoch": 1124.6913580246915, "learning_rate": 7.517754377372351e-07, "loss": 1.7272, "step": 18220 }, { "epoch": 1125.9259259259259, "learning_rate": 7.51499938778009e-07, "loss": 1.7696, "step": 18240 }, { "epoch": 1127.1604938271605, "learning_rate": 7.512244398187828e-07, "loss": 1.819, "step": 18260 }, { "epoch": 1128.3950617283951, "learning_rate": 7.509489408595567e-07, "loss": 1.7688, "step": 18280 }, { "epoch": 1129.6296296296296, "learning_rate": 7.506734419003306e-07, "loss": 1.7766, "step": 18300 }, { "epoch": 1130.8641975308642, "learning_rate": 7.503979429411043e-07, "loss": 1.7581, "step": 18320 }, { "epoch": 1132.0987654320988, "learning_rate": 7.501224439818783e-07, "loss": 1.7735, "step": 18340 }, { "epoch": 1133.3333333333333, "learning_rate": 7.498469450226521e-07, "loss": 1.7485, "step": 18360 }, { "epoch": 1134.567901234568, "learning_rate": 7.495714460634259e-07, "loss": 1.7472, "step": 18380 }, { "epoch": 1135.8024691358025, "learning_rate": 7.492959471041998e-07, "loss": 1.749, "step": 18400 }, { "epoch": 1137.037037037037, "learning_rate": 7.490204481449736e-07, "loss": 1.7946, "step": 18420 }, { "epoch": 1138.2716049382716, "learning_rate": 7.487449491857475e-07, "loss": 1.7932, "step": 18440 }, { "epoch": 1139.5061728395062, "learning_rate": 7.484694502265213e-07, "loss": 1.7318, "step": 18460 }, { "epoch": 1140.7407407407406, "learning_rate": 7.481939512672952e-07, "loss": 1.7591, "step": 18480 }, { "epoch": 1141.9753086419753, "learning_rate": 7.47918452308069e-07, "loss": 1.7951, "step": 18500 }, { "epoch": 1143.20987654321, "learning_rate": 7.476429533488429e-07, "loss": 1.7578, "step": 18520 }, { "epoch": 1144.4444444444443, "learning_rate": 7.473674543896168e-07, "loss": 1.7653, "step": 18540 }, { "epoch": 1145.679012345679, "learning_rate": 7.470919554303906e-07, "loss": 1.7731, "step": 18560 }, { "epoch": 1146.9135802469136, "learning_rate": 7.468164564711646e-07, "loss": 1.7214, "step": 18580 }, { "epoch": 1148.148148148148, "learning_rate": 7.465409575119383e-07, "loss": 1.775, "step": 18600 }, { "epoch": 1149.3827160493827, "learning_rate": 7.462654585527122e-07, "loss": 1.7218, "step": 18620 }, { "epoch": 1150.6172839506173, "learning_rate": 7.45989959593486e-07, "loss": 1.7347, "step": 18640 }, { "epoch": 1151.851851851852, "learning_rate": 7.457144606342598e-07, "loss": 1.7236, "step": 18660 }, { "epoch": 1153.0864197530864, "learning_rate": 7.454389616750337e-07, "loss": 1.7785, "step": 18680 }, { "epoch": 1154.320987654321, "learning_rate": 7.451634627158074e-07, "loss": 1.7863, "step": 18700 }, { "epoch": 1155.5555555555557, "learning_rate": 7.448879637565813e-07, "loss": 1.7431, "step": 18720 }, { "epoch": 1156.79012345679, "learning_rate": 7.446124647973551e-07, "loss": 1.8058, "step": 18740 }, { "epoch": 1158.0246913580247, "learning_rate": 7.44336965838129e-07, "loss": 1.7335, "step": 18760 }, { "epoch": 1159.2592592592594, "learning_rate": 7.440614668789029e-07, "loss": 1.7839, "step": 18780 }, { "epoch": 1160.4938271604938, "learning_rate": 7.437859679196767e-07, "loss": 1.7525, "step": 18800 }, { "epoch": 1161.7283950617284, "learning_rate": 7.435104689604506e-07, "loss": 1.7545, "step": 18820 }, { "epoch": 1162.962962962963, "learning_rate": 7.432349700012244e-07, "loss": 1.7494, "step": 18840 }, { "epoch": 1164.1975308641975, "learning_rate": 7.429594710419983e-07, "loss": 1.7774, "step": 18860 }, { "epoch": 1165.432098765432, "learning_rate": 7.426839720827722e-07, "loss": 1.7327, "step": 18880 }, { "epoch": 1166.6666666666667, "learning_rate": 7.424084731235459e-07, "loss": 1.7474, "step": 18900 }, { "epoch": 1167.9012345679012, "learning_rate": 7.421329741643198e-07, "loss": 1.7702, "step": 18920 }, { "epoch": 1169.1358024691358, "learning_rate": 7.418574752050936e-07, "loss": 1.7782, "step": 18940 }, { "epoch": 1170.3703703703704, "learning_rate": 7.415819762458675e-07, "loss": 1.7498, "step": 18960 }, { "epoch": 1171.6049382716049, "learning_rate": 7.413064772866412e-07, "loss": 1.7764, "step": 18980 }, { "epoch": 1172.8395061728395, "learning_rate": 7.410309783274151e-07, "loss": 1.6855, "step": 19000 }, { "epoch": 1174.0740740740741, "learning_rate": 7.40755479368189e-07, "loss": 1.764, "step": 19020 }, { "epoch": 1175.3086419753085, "learning_rate": 7.404799804089627e-07, "loss": 1.7617, "step": 19040 }, { "epoch": 1176.5432098765432, "learning_rate": 7.402044814497367e-07, "loss": 1.7556, "step": 19060 }, { "epoch": 1177.7777777777778, "learning_rate": 7.399289824905105e-07, "loss": 1.7351, "step": 19080 }, { "epoch": 1179.0123456790122, "learning_rate": 7.396534835312844e-07, "loss": 1.7619, "step": 19100 }, { "epoch": 1180.2469135802469, "learning_rate": 7.393779845720582e-07, "loss": 1.7406, "step": 19120 }, { "epoch": 1181.4814814814815, "learning_rate": 7.391024856128321e-07, "loss": 1.7334, "step": 19140 }, { "epoch": 1182.716049382716, "learning_rate": 7.38826986653606e-07, "loss": 1.7695, "step": 19160 }, { "epoch": 1183.9506172839506, "learning_rate": 7.385514876943798e-07, "loss": 1.7869, "step": 19180 }, { "epoch": 1185.1851851851852, "learning_rate": 7.382759887351537e-07, "loss": 1.7892, "step": 19200 }, { "epoch": 1186.4197530864199, "learning_rate": 7.380004897759275e-07, "loss": 1.7485, "step": 19220 }, { "epoch": 1187.6543209876543, "learning_rate": 7.377249908167013e-07, "loss": 1.7163, "step": 19240 }, { "epoch": 1188.888888888889, "learning_rate": 7.374494918574752e-07, "loss": 1.7288, "step": 19260 }, { "epoch": 1190.1234567901236, "learning_rate": 7.37173992898249e-07, "loss": 1.8203, "step": 19280 }, { "epoch": 1191.358024691358, "learning_rate": 7.36898493939023e-07, "loss": 1.7354, "step": 19300 }, { "epoch": 1192.5925925925926, "learning_rate": 7.366229949797967e-07, "loss": 1.7581, "step": 19320 }, { "epoch": 1193.8271604938273, "learning_rate": 7.363474960205706e-07, "loss": 1.7342, "step": 19340 }, { "epoch": 1195.0617283950617, "learning_rate": 7.360719970613444e-07, "loss": 1.7549, "step": 19360 }, { "epoch": 1196.2962962962963, "learning_rate": 7.357964981021183e-07, "loss": 1.7604, "step": 19380 }, { "epoch": 1197.530864197531, "learning_rate": 7.355209991428922e-07, "loss": 1.7603, "step": 19400 }, { "epoch": 1198.7654320987654, "learning_rate": 7.35245500183666e-07, "loss": 1.7071, "step": 19420 }, { "epoch": 1200.0, "learning_rate": 7.349700012244398e-07, "loss": 1.7339, "step": 19440 }, { "epoch": 1201.2345679012346, "learning_rate": 7.346945022652136e-07, "loss": 1.7343, "step": 19460 }, { "epoch": 1202.469135802469, "learning_rate": 7.344190033059875e-07, "loss": 1.7962, "step": 19480 }, { "epoch": 1203.7037037037037, "learning_rate": 7.341435043467614e-07, "loss": 1.7555, "step": 19500 }, { "epoch": 1204.9382716049383, "learning_rate": 7.338680053875351e-07, "loss": 1.7909, "step": 19520 }, { "epoch": 1206.1728395061727, "learning_rate": 7.33592506428309e-07, "loss": 1.7417, "step": 19540 }, { "epoch": 1207.4074074074074, "learning_rate": 7.333170074690828e-07, "loss": 1.7785, "step": 19560 }, { "epoch": 1208.641975308642, "learning_rate": 7.330415085098567e-07, "loss": 1.7561, "step": 19580 }, { "epoch": 1209.8765432098764, "learning_rate": 7.327660095506305e-07, "loss": 1.7791, "step": 19600 }, { "epoch": 1211.111111111111, "learning_rate": 7.324905105914044e-07, "loss": 1.7881, "step": 19620 }, { "epoch": 1212.3456790123457, "learning_rate": 7.322150116321783e-07, "loss": 1.8316, "step": 19640 }, { "epoch": 1213.5802469135801, "learning_rate": 7.31939512672952e-07, "loss": 2.3297, "step": 19660 }, { "epoch": 1214.8148148148148, "learning_rate": 7.31664013713726e-07, "loss": 3.0734, "step": 19680 }, { "epoch": 1216.0493827160494, "learning_rate": 7.313885147544998e-07, "loss": 3.3818, "step": 19700 }, { "epoch": 1217.283950617284, "learning_rate": 7.311130157952736e-07, "loss": 3.4044, "step": 19720 }, { "epoch": 1218.5185185185185, "learning_rate": 7.308375168360474e-07, "loss": 3.3076, "step": 19740 }, { "epoch": 1219.7530864197531, "learning_rate": 7.305620178768213e-07, "loss": 3.3052, "step": 19760 }, { "epoch": 1220.9876543209878, "learning_rate": 7.302865189175951e-07, "loss": 3.2461, "step": 19780 }, { "epoch": 1222.2222222222222, "learning_rate": 7.300110199583689e-07, "loss": 3.2139, "step": 19800 }, { "epoch": 1223.4567901234568, "learning_rate": 7.297355209991428e-07, "loss": 3.2006, "step": 19820 }, { "epoch": 1224.6913580246915, "learning_rate": 7.294600220399166e-07, "loss": 3.2578, "step": 19840 }, { "epoch": 1225.9259259259259, "learning_rate": 7.291845230806905e-07, "loss": 3.1139, "step": 19860 }, { "epoch": 1227.1604938271605, "learning_rate": 7.289090241214644e-07, "loss": 3.1, "step": 19880 }, { "epoch": 1228.3950617283951, "learning_rate": 7.286335251622382e-07, "loss": 3.158, "step": 19900 }, { "epoch": 1229.6296296296296, "learning_rate": 7.283580262030121e-07, "loss": 3.1806, "step": 19920 }, { "epoch": 1230.8641975308642, "learning_rate": 7.28082527243786e-07, "loss": 3.0692, "step": 19940 }, { "epoch": 1232.0987654320988, "learning_rate": 7.278070282845599e-07, "loss": 3.1239, "step": 19960 }, { "epoch": 1233.3333333333333, "learning_rate": 7.275315293253336e-07, "loss": 3.1122, "step": 19980 }, { "epoch": 1234.567901234568, "learning_rate": 7.272560303661075e-07, "loss": 3.0677, "step": 20000 } ], "logging_steps": 20, "max_steps": 65536, "num_input_tokens_seen": 0, "num_train_epochs": 4096, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.846857702971802e+16, "train_batch_size": 5, "trial_name": null, "trial_params": null }