{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 441, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0022695035460992908, "grad_norm": 8.668334007263184, "learning_rate": 0.0, "loss": 3.8005, "step": 1 }, { "epoch": 0.0045390070921985815, "grad_norm": 8.295294761657715, "learning_rate": 2.0000000000000003e-06, "loss": 4.304, "step": 2 }, { "epoch": 0.006808510638297872, "grad_norm": 7.432443618774414, "learning_rate": 4.000000000000001e-06, "loss": 2.7026, "step": 3 }, { "epoch": 0.009078014184397163, "grad_norm": 7.036699295043945, "learning_rate": 6e-06, "loss": 3.642, "step": 4 }, { "epoch": 0.011347517730496455, "grad_norm": 7.594095230102539, "learning_rate": 8.000000000000001e-06, "loss": 3.4302, "step": 5 }, { "epoch": 0.013617021276595745, "grad_norm": 8.705190658569336, "learning_rate": 1e-05, "loss": 3.6262, "step": 6 }, { "epoch": 0.015886524822695036, "grad_norm": 7.787868976593018, "learning_rate": 9.977064220183487e-06, "loss": 3.0892, "step": 7 }, { "epoch": 0.018156028368794326, "grad_norm": 8.02392292022705, "learning_rate": 9.954128440366973e-06, "loss": 3.4635, "step": 8 }, { "epoch": 0.020425531914893616, "grad_norm": 11.695192337036133, "learning_rate": 9.931192660550459e-06, "loss": 3.4897, "step": 9 }, { "epoch": 0.02269503546099291, "grad_norm": 15.6809663772583, "learning_rate": 9.908256880733946e-06, "loss": 3.7806, "step": 10 }, { "epoch": 0.0249645390070922, "grad_norm": 10.776519775390625, "learning_rate": 9.885321100917432e-06, "loss": 3.296, "step": 11 }, { "epoch": 0.02723404255319149, "grad_norm": 10.462336540222168, "learning_rate": 9.862385321100918e-06, "loss": 4.8394, "step": 12 }, { "epoch": 0.02950354609929078, "grad_norm": 10.901927947998047, "learning_rate": 9.839449541284404e-06, "loss": 4.9392, "step": 13 }, { "epoch": 0.03177304964539007, "grad_norm": 13.508086204528809, "learning_rate": 9.81651376146789e-06, "loss": 4.6349, "step": 14 }, { "epoch": 0.03404255319148936, "grad_norm": 13.002544403076172, "learning_rate": 9.793577981651376e-06, "loss": 4.5711, "step": 15 }, { "epoch": 0.03631205673758865, "grad_norm": 13.845036506652832, "learning_rate": 9.770642201834864e-06, "loss": 5.5628, "step": 16 }, { "epoch": 0.03858156028368794, "grad_norm": 16.927213668823242, "learning_rate": 9.74770642201835e-06, "loss": 5.0527, "step": 17 }, { "epoch": 0.04085106382978723, "grad_norm": 16.63279914855957, "learning_rate": 9.724770642201836e-06, "loss": 5.9276, "step": 18 }, { "epoch": 0.04312056737588652, "grad_norm": 16.575397491455078, "learning_rate": 9.701834862385322e-06, "loss": 7.6455, "step": 19 }, { "epoch": 0.04539007092198582, "grad_norm": 19.085927963256836, "learning_rate": 9.678899082568808e-06, "loss": 6.1837, "step": 20 }, { "epoch": 0.04765957446808511, "grad_norm": 17.73398780822754, "learning_rate": 9.655963302752295e-06, "loss": 6.988, "step": 21 }, { "epoch": 0.0499290780141844, "grad_norm": 17.629236221313477, "learning_rate": 9.633027522935781e-06, "loss": 6.2197, "step": 22 }, { "epoch": 0.05219858156028369, "grad_norm": 15.795450210571289, "learning_rate": 9.610091743119267e-06, "loss": 5.4883, "step": 23 }, { "epoch": 0.05446808510638298, "grad_norm": 18.902469635009766, "learning_rate": 9.587155963302753e-06, "loss": 6.4734, "step": 24 }, { "epoch": 0.05673758865248227, "grad_norm": 19.052209854125977, "learning_rate": 9.56422018348624e-06, "loss": 6.1945, "step": 25 }, { "epoch": 0.05900709219858156, "grad_norm": 13.770371437072754, "learning_rate": 9.541284403669727e-06, "loss": 6.4116, "step": 26 }, { "epoch": 0.06127659574468085, "grad_norm": 16.968936920166016, "learning_rate": 9.518348623853211e-06, "loss": 6.2594, "step": 27 }, { "epoch": 0.06354609929078014, "grad_norm": 17.31413459777832, "learning_rate": 9.495412844036697e-06, "loss": 6.1457, "step": 28 }, { "epoch": 0.06581560283687943, "grad_norm": 18.517250061035156, "learning_rate": 9.472477064220185e-06, "loss": 6.7135, "step": 29 }, { "epoch": 0.06808510638297872, "grad_norm": 19.75918960571289, "learning_rate": 9.44954128440367e-06, "loss": 6.1187, "step": 30 }, { "epoch": 0.07035460992907801, "grad_norm": 18.041967391967773, "learning_rate": 9.426605504587157e-06, "loss": 5.5628, "step": 31 }, { "epoch": 0.0726241134751773, "grad_norm": 20.323652267456055, "learning_rate": 9.403669724770643e-06, "loss": 6.3933, "step": 32 }, { "epoch": 0.0748936170212766, "grad_norm": 113.98054504394531, "learning_rate": 9.380733944954129e-06, "loss": 7.7604, "step": 33 }, { "epoch": 0.07716312056737588, "grad_norm": 17.7612361907959, "learning_rate": 9.357798165137616e-06, "loss": 5.9875, "step": 34 }, { "epoch": 0.07943262411347518, "grad_norm": 23.045015335083008, "learning_rate": 9.334862385321102e-06, "loss": 6.6675, "step": 35 }, { "epoch": 0.08170212765957446, "grad_norm": 20.38176155090332, "learning_rate": 9.311926605504588e-06, "loss": 7.1641, "step": 36 }, { "epoch": 0.08397163120567376, "grad_norm": 21.33348274230957, "learning_rate": 9.288990825688074e-06, "loss": 7.4257, "step": 37 }, { "epoch": 0.08624113475177304, "grad_norm": 18.836183547973633, "learning_rate": 9.26605504587156e-06, "loss": 7.1829, "step": 38 }, { "epoch": 0.08851063829787234, "grad_norm": 17.335561752319336, "learning_rate": 9.243119266055046e-06, "loss": 6.66, "step": 39 }, { "epoch": 0.09078014184397164, "grad_norm": 17.13735580444336, "learning_rate": 9.220183486238534e-06, "loss": 6.608, "step": 40 }, { "epoch": 0.09304964539007092, "grad_norm": 21.09581184387207, "learning_rate": 9.19724770642202e-06, "loss": 6.321, "step": 41 }, { "epoch": 0.09531914893617022, "grad_norm": 20.668155670166016, "learning_rate": 9.174311926605506e-06, "loss": 6.863, "step": 42 }, { "epoch": 0.0975886524822695, "grad_norm": 20.400651931762695, "learning_rate": 9.151376146788992e-06, "loss": 7.3757, "step": 43 }, { "epoch": 0.0998581560283688, "grad_norm": 19.266387939453125, "learning_rate": 9.128440366972477e-06, "loss": 6.3143, "step": 44 }, { "epoch": 0.10212765957446808, "grad_norm": 20.088226318359375, "learning_rate": 9.105504587155965e-06, "loss": 6.9608, "step": 45 }, { "epoch": 0.10439716312056738, "grad_norm": 20.868011474609375, "learning_rate": 9.08256880733945e-06, "loss": 6.8794, "step": 46 }, { "epoch": 0.10666666666666667, "grad_norm": 23.177440643310547, "learning_rate": 9.059633027522935e-06, "loss": 6.8755, "step": 47 }, { "epoch": 0.10893617021276596, "grad_norm": 21.705177307128906, "learning_rate": 9.036697247706423e-06, "loss": 7.3606, "step": 48 }, { "epoch": 0.11120567375886525, "grad_norm": 21.135578155517578, "learning_rate": 9.013761467889909e-06, "loss": 7.3758, "step": 49 }, { "epoch": 0.11347517730496454, "grad_norm": 22.788454055786133, "learning_rate": 8.990825688073395e-06, "loss": 7.0425, "step": 50 }, { "epoch": 0.11574468085106383, "grad_norm": 21.569185256958008, "learning_rate": 8.967889908256881e-06, "loss": 7.3048, "step": 51 }, { "epoch": 0.11801418439716312, "grad_norm": 26.286264419555664, "learning_rate": 8.944954128440367e-06, "loss": 8.1285, "step": 52 }, { "epoch": 0.12028368794326241, "grad_norm": 21.558218002319336, "learning_rate": 8.922018348623855e-06, "loss": 6.9357, "step": 53 }, { "epoch": 0.1225531914893617, "grad_norm": 19.515256881713867, "learning_rate": 8.89908256880734e-06, "loss": 7.2291, "step": 54 }, { "epoch": 0.12482269503546099, "grad_norm": 19.109468460083008, "learning_rate": 8.876146788990826e-06, "loss": 7.089, "step": 55 }, { "epoch": 0.1270921985815603, "grad_norm": 20.757980346679688, "learning_rate": 8.853211009174312e-06, "loss": 6.3171, "step": 56 }, { "epoch": 0.12936170212765957, "grad_norm": 19.058013916015625, "learning_rate": 8.830275229357798e-06, "loss": 6.9183, "step": 57 }, { "epoch": 0.13163120567375886, "grad_norm": 18.01837158203125, "learning_rate": 8.807339449541286e-06, "loss": 7.2458, "step": 58 }, { "epoch": 0.13390070921985817, "grad_norm": 22.41701316833496, "learning_rate": 8.784403669724772e-06, "loss": 6.7899, "step": 59 }, { "epoch": 0.13617021276595745, "grad_norm": 18.172842025756836, "learning_rate": 8.761467889908258e-06, "loss": 6.9066, "step": 60 }, { "epoch": 0.13843971631205673, "grad_norm": 18.6385555267334, "learning_rate": 8.738532110091744e-06, "loss": 6.5288, "step": 61 }, { "epoch": 0.14070921985815601, "grad_norm": 15.670263290405273, "learning_rate": 8.71559633027523e-06, "loss": 7.0239, "step": 62 }, { "epoch": 0.14297872340425533, "grad_norm": 17.126794815063477, "learning_rate": 8.692660550458716e-06, "loss": 6.3348, "step": 63 }, { "epoch": 0.1452482269503546, "grad_norm": 16.635543823242188, "learning_rate": 8.669724770642203e-06, "loss": 6.4536, "step": 64 }, { "epoch": 0.1475177304964539, "grad_norm": 16.395944595336914, "learning_rate": 8.646788990825688e-06, "loss": 7.2219, "step": 65 }, { "epoch": 0.1497872340425532, "grad_norm": 17.588932037353516, "learning_rate": 8.623853211009175e-06, "loss": 6.5138, "step": 66 }, { "epoch": 0.15205673758865249, "grad_norm": 16.589641571044922, "learning_rate": 8.600917431192661e-06, "loss": 6.9137, "step": 67 }, { "epoch": 0.15432624113475177, "grad_norm": 16.334035873413086, "learning_rate": 8.577981651376147e-06, "loss": 7.1514, "step": 68 }, { "epoch": 0.15659574468085105, "grad_norm": 16.68819236755371, "learning_rate": 8.555045871559633e-06, "loss": 7.0172, "step": 69 }, { "epoch": 0.15886524822695036, "grad_norm": 18.170339584350586, "learning_rate": 8.53211009174312e-06, "loss": 6.6805, "step": 70 }, { "epoch": 0.16113475177304964, "grad_norm": 18.31951332092285, "learning_rate": 8.509174311926605e-06, "loss": 7.2054, "step": 71 }, { "epoch": 0.16340425531914893, "grad_norm": 20.356067657470703, "learning_rate": 8.486238532110093e-06, "loss": 8.3907, "step": 72 }, { "epoch": 0.16567375886524824, "grad_norm": 21.215167999267578, "learning_rate": 8.463302752293579e-06, "loss": 8.1707, "step": 73 }, { "epoch": 0.16794326241134752, "grad_norm": 25.927398681640625, "learning_rate": 8.440366972477065e-06, "loss": 9.1306, "step": 74 }, { "epoch": 0.1702127659574468, "grad_norm": 16.74397850036621, "learning_rate": 8.41743119266055e-06, "loss": 8.1278, "step": 75 }, { "epoch": 0.1724822695035461, "grad_norm": 21.818443298339844, "learning_rate": 8.394495412844037e-06, "loss": 8.3416, "step": 76 }, { "epoch": 0.1747517730496454, "grad_norm": 24.894277572631836, "learning_rate": 8.371559633027524e-06, "loss": 8.4501, "step": 77 }, { "epoch": 0.17702127659574468, "grad_norm": 23.77277374267578, "learning_rate": 8.34862385321101e-06, "loss": 8.2249, "step": 78 }, { "epoch": 0.17929078014184396, "grad_norm": 25.31768226623535, "learning_rate": 8.325688073394496e-06, "loss": 8.2616, "step": 79 }, { "epoch": 0.18156028368794327, "grad_norm": 23.903696060180664, "learning_rate": 8.302752293577982e-06, "loss": 8.9545, "step": 80 }, { "epoch": 0.18382978723404256, "grad_norm": 29.891633987426758, "learning_rate": 8.279816513761468e-06, "loss": 8.643, "step": 81 }, { "epoch": 0.18609929078014184, "grad_norm": 19.98649787902832, "learning_rate": 8.256880733944956e-06, "loss": 10.0018, "step": 82 }, { "epoch": 0.18836879432624112, "grad_norm": 23.281627655029297, "learning_rate": 8.233944954128442e-06, "loss": 8.2297, "step": 83 }, { "epoch": 0.19063829787234043, "grad_norm": 24.43315887451172, "learning_rate": 8.211009174311926e-06, "loss": 7.6728, "step": 84 }, { "epoch": 0.19290780141843972, "grad_norm": 22.61714744567871, "learning_rate": 8.188073394495414e-06, "loss": 8.2104, "step": 85 }, { "epoch": 0.195177304964539, "grad_norm": 23.682811737060547, "learning_rate": 8.1651376146789e-06, "loss": 8.2789, "step": 86 }, { "epoch": 0.1974468085106383, "grad_norm": 19.421873092651367, "learning_rate": 8.142201834862386e-06, "loss": 8.1616, "step": 87 }, { "epoch": 0.1997163120567376, "grad_norm": 21.842182159423828, "learning_rate": 8.119266055045872e-06, "loss": 8.936, "step": 88 }, { "epoch": 0.20198581560283688, "grad_norm": 22.472448348999023, "learning_rate": 8.096330275229358e-06, "loss": 8.544, "step": 89 }, { "epoch": 0.20425531914893616, "grad_norm": 20.752517700195312, "learning_rate": 8.073394495412845e-06, "loss": 7.8675, "step": 90 }, { "epoch": 0.20652482269503547, "grad_norm": 18.82471466064453, "learning_rate": 8.050458715596331e-06, "loss": 7.1085, "step": 91 }, { "epoch": 0.20879432624113475, "grad_norm": 19.87750244140625, "learning_rate": 8.027522935779817e-06, "loss": 8.0477, "step": 92 }, { "epoch": 0.21106382978723404, "grad_norm": 20.857316970825195, "learning_rate": 8.004587155963303e-06, "loss": 7.497, "step": 93 }, { "epoch": 0.21333333333333335, "grad_norm": 22.878759384155273, "learning_rate": 7.981651376146789e-06, "loss": 7.6958, "step": 94 }, { "epoch": 0.21560283687943263, "grad_norm": 18.073413848876953, "learning_rate": 7.958715596330275e-06, "loss": 8.939, "step": 95 }, { "epoch": 0.2178723404255319, "grad_norm": 20.256135940551758, "learning_rate": 7.935779816513763e-06, "loss": 7.3753, "step": 96 }, { "epoch": 0.2201418439716312, "grad_norm": 20.141647338867188, "learning_rate": 7.912844036697249e-06, "loss": 7.4896, "step": 97 }, { "epoch": 0.2224113475177305, "grad_norm": 19.358707427978516, "learning_rate": 7.889908256880735e-06, "loss": 7.3408, "step": 98 }, { "epoch": 0.2246808510638298, "grad_norm": 21.06694793701172, "learning_rate": 7.86697247706422e-06, "loss": 6.8823, "step": 99 }, { "epoch": 0.22695035460992907, "grad_norm": 18.77146339416504, "learning_rate": 7.844036697247707e-06, "loss": 6.5458, "step": 100 }, { "epoch": 0.22921985815602836, "grad_norm": 20.78810691833496, "learning_rate": 7.821100917431194e-06, "loss": 7.4521, "step": 101 }, { "epoch": 0.23148936170212767, "grad_norm": 20.43685531616211, "learning_rate": 7.79816513761468e-06, "loss": 7.683, "step": 102 }, { "epoch": 0.23375886524822695, "grad_norm": 20.419296264648438, "learning_rate": 7.775229357798164e-06, "loss": 6.7302, "step": 103 }, { "epoch": 0.23602836879432623, "grad_norm": 20.838834762573242, "learning_rate": 7.752293577981652e-06, "loss": 7.8304, "step": 104 }, { "epoch": 0.23829787234042554, "grad_norm": 19.304853439331055, "learning_rate": 7.729357798165138e-06, "loss": 7.7083, "step": 105 }, { "epoch": 0.24056737588652483, "grad_norm": 22.665035247802734, "learning_rate": 7.706422018348626e-06, "loss": 7.0634, "step": 106 }, { "epoch": 0.2428368794326241, "grad_norm": 21.782527923583984, "learning_rate": 7.68348623853211e-06, "loss": 7.03, "step": 107 }, { "epoch": 0.2451063829787234, "grad_norm": 23.51955223083496, "learning_rate": 7.660550458715596e-06, "loss": 8.2088, "step": 108 }, { "epoch": 0.2473758865248227, "grad_norm": 26.1049747467041, "learning_rate": 7.637614678899084e-06, "loss": 8.0579, "step": 109 }, { "epoch": 0.24964539007092199, "grad_norm": 22.49606704711914, "learning_rate": 7.6146788990825695e-06, "loss": 7.9667, "step": 110 }, { "epoch": 0.2519148936170213, "grad_norm": 22.109041213989258, "learning_rate": 7.5917431192660555e-06, "loss": 7.6524, "step": 111 }, { "epoch": 0.2541843971631206, "grad_norm": 29.959514617919922, "learning_rate": 7.568807339449542e-06, "loss": 7.4387, "step": 112 }, { "epoch": 0.25645390070921986, "grad_norm": 26.431915283203125, "learning_rate": 7.545871559633028e-06, "loss": 8.3805, "step": 113 }, { "epoch": 0.25872340425531914, "grad_norm": 23.73126792907715, "learning_rate": 7.522935779816515e-06, "loss": 8.1678, "step": 114 }, { "epoch": 0.26099290780141843, "grad_norm": 22.313522338867188, "learning_rate": 7.500000000000001e-06, "loss": 7.8506, "step": 115 }, { "epoch": 0.2632624113475177, "grad_norm": 22.92296028137207, "learning_rate": 7.477064220183486e-06, "loss": 9.2038, "step": 116 }, { "epoch": 0.265531914893617, "grad_norm": 25.42365837097168, "learning_rate": 7.454128440366973e-06, "loss": 7.1744, "step": 117 }, { "epoch": 0.26780141843971633, "grad_norm": 26.37105369567871, "learning_rate": 7.431192660550459e-06, "loss": 8.4327, "step": 118 }, { "epoch": 0.2700709219858156, "grad_norm": 25.781368255615234, "learning_rate": 7.408256880733946e-06, "loss": 8.4887, "step": 119 }, { "epoch": 0.2723404255319149, "grad_norm": 22.346729278564453, "learning_rate": 7.385321100917432e-06, "loss": 7.0309, "step": 120 }, { "epoch": 0.2746099290780142, "grad_norm": 20.371849060058594, "learning_rate": 7.362385321100918e-06, "loss": 8.3293, "step": 121 }, { "epoch": 0.27687943262411346, "grad_norm": 21.7130126953125, "learning_rate": 7.3394495412844045e-06, "loss": 8.1534, "step": 122 }, { "epoch": 0.27914893617021275, "grad_norm": 22.989255905151367, "learning_rate": 7.31651376146789e-06, "loss": 7.5064, "step": 123 }, { "epoch": 0.28141843971631203, "grad_norm": 24.327320098876953, "learning_rate": 7.293577981651376e-06, "loss": 7.5161, "step": 124 }, { "epoch": 0.28368794326241137, "grad_norm": 25.772855758666992, "learning_rate": 7.270642201834863e-06, "loss": 9.2367, "step": 125 }, { "epoch": 0.28595744680851065, "grad_norm": 23.472679138183594, "learning_rate": 7.247706422018349e-06, "loss": 8.3824, "step": 126 }, { "epoch": 0.28822695035460993, "grad_norm": 25.819732666015625, "learning_rate": 7.224770642201836e-06, "loss": 8.1064, "step": 127 }, { "epoch": 0.2904964539007092, "grad_norm": 21.62706756591797, "learning_rate": 7.201834862385322e-06, "loss": 8.2132, "step": 128 }, { "epoch": 0.2927659574468085, "grad_norm": 24.72386932373047, "learning_rate": 7.178899082568808e-06, "loss": 7.7798, "step": 129 }, { "epoch": 0.2950354609929078, "grad_norm": 21.803068161010742, "learning_rate": 7.155963302752295e-06, "loss": 8.3099, "step": 130 }, { "epoch": 0.29730496453900707, "grad_norm": 19.42896270751953, "learning_rate": 7.133027522935781e-06, "loss": 7.7609, "step": 131 }, { "epoch": 0.2995744680851064, "grad_norm": 23.633056640625, "learning_rate": 7.110091743119267e-06, "loss": 7.9642, "step": 132 }, { "epoch": 0.3018439716312057, "grad_norm": 24.548171997070312, "learning_rate": 7.087155963302753e-06, "loss": 8.6934, "step": 133 }, { "epoch": 0.30411347517730497, "grad_norm": 21.887115478515625, "learning_rate": 7.0642201834862385e-06, "loss": 7.4215, "step": 134 }, { "epoch": 0.30638297872340425, "grad_norm": 22.957767486572266, "learning_rate": 7.041284403669726e-06, "loss": 7.3627, "step": 135 }, { "epoch": 0.30865248226950354, "grad_norm": 19.477394104003906, "learning_rate": 7.018348623853211e-06, "loss": 7.8984, "step": 136 }, { "epoch": 0.3109219858156028, "grad_norm": 18.73714256286621, "learning_rate": 6.995412844036697e-06, "loss": 7.6329, "step": 137 }, { "epoch": 0.3131914893617021, "grad_norm": 17.952415466308594, "learning_rate": 6.972477064220184e-06, "loss": 8.396, "step": 138 }, { "epoch": 0.31546099290780144, "grad_norm": 20.545944213867188, "learning_rate": 6.94954128440367e-06, "loss": 7.6428, "step": 139 }, { "epoch": 0.3177304964539007, "grad_norm": 19.40607452392578, "learning_rate": 6.926605504587156e-06, "loss": 8.1202, "step": 140 }, { "epoch": 0.32, "grad_norm": 23.38299560546875, "learning_rate": 6.903669724770643e-06, "loss": 8.4539, "step": 141 }, { "epoch": 0.3222695035460993, "grad_norm": 18.970348358154297, "learning_rate": 6.880733944954129e-06, "loss": 7.5868, "step": 142 }, { "epoch": 0.3245390070921986, "grad_norm": 18.58732795715332, "learning_rate": 6.8577981651376156e-06, "loss": 7.5937, "step": 143 }, { "epoch": 0.32680851063829786, "grad_norm": 21.359020233154297, "learning_rate": 6.8348623853211015e-06, "loss": 8.809, "step": 144 }, { "epoch": 0.32907801418439714, "grad_norm": 19.462627410888672, "learning_rate": 6.8119266055045875e-06, "loss": 8.014, "step": 145 }, { "epoch": 0.3313475177304965, "grad_norm": 22.935861587524414, "learning_rate": 6.788990825688074e-06, "loss": 7.9825, "step": 146 }, { "epoch": 0.33361702127659576, "grad_norm": 21.756521224975586, "learning_rate": 6.76605504587156e-06, "loss": 7.5796, "step": 147 }, { "epoch": 0.33588652482269504, "grad_norm": 21.058975219726562, "learning_rate": 6.743119266055046e-06, "loss": 8.0842, "step": 148 }, { "epoch": 0.3381560283687943, "grad_norm": 18.209266662597656, "learning_rate": 6.720183486238533e-06, "loss": 7.3283, "step": 149 }, { "epoch": 0.3404255319148936, "grad_norm": 25.000167846679688, "learning_rate": 6.697247706422019e-06, "loss": 7.9868, "step": 150 }, { "epoch": 0.3426950354609929, "grad_norm": 18.630735397338867, "learning_rate": 6.674311926605506e-06, "loss": 8.1188, "step": 151 }, { "epoch": 0.3449645390070922, "grad_norm": 23.64411735534668, "learning_rate": 6.651376146788992e-06, "loss": 7.8335, "step": 152 }, { "epoch": 0.3472340425531915, "grad_norm": 22.36941909790039, "learning_rate": 6.628440366972477e-06, "loss": 7.7012, "step": 153 }, { "epoch": 0.3495035460992908, "grad_norm": 22.07706069946289, "learning_rate": 6.6055045871559645e-06, "loss": 9.0273, "step": 154 }, { "epoch": 0.3517730496453901, "grad_norm": 20.921728134155273, "learning_rate": 6.58256880733945e-06, "loss": 8.2902, "step": 155 }, { "epoch": 0.35404255319148936, "grad_norm": 20.814266204833984, "learning_rate": 6.559633027522936e-06, "loss": 7.2379, "step": 156 }, { "epoch": 0.35631205673758864, "grad_norm": 16.310928344726562, "learning_rate": 6.536697247706422e-06, "loss": 7.8278, "step": 157 }, { "epoch": 0.35858156028368793, "grad_norm": 20.13202667236328, "learning_rate": 6.513761467889908e-06, "loss": 7.7317, "step": 158 }, { "epoch": 0.3608510638297872, "grad_norm": 17.592784881591797, "learning_rate": 6.490825688073395e-06, "loss": 8.54, "step": 159 }, { "epoch": 0.36312056737588655, "grad_norm": 19.89832878112793, "learning_rate": 6.467889908256881e-06, "loss": 8.2364, "step": 160 }, { "epoch": 0.36539007092198583, "grad_norm": 22.617385864257812, "learning_rate": 6.444954128440367e-06, "loss": 7.4008, "step": 161 }, { "epoch": 0.3676595744680851, "grad_norm": 21.20064353942871, "learning_rate": 6.422018348623854e-06, "loss": 8.756, "step": 162 }, { "epoch": 0.3699290780141844, "grad_norm": 20.750295639038086, "learning_rate": 6.39908256880734e-06, "loss": 7.7185, "step": 163 }, { "epoch": 0.3721985815602837, "grad_norm": 22.090425491333008, "learning_rate": 6.376146788990826e-06, "loss": 7.3956, "step": 164 }, { "epoch": 0.37446808510638296, "grad_norm": 17.701717376708984, "learning_rate": 6.353211009174313e-06, "loss": 8.9048, "step": 165 }, { "epoch": 0.37673758865248225, "grad_norm": 20.98927116394043, "learning_rate": 6.330275229357799e-06, "loss": 8.8513, "step": 166 }, { "epoch": 0.3790070921985816, "grad_norm": 19.930639266967773, "learning_rate": 6.307339449541285e-06, "loss": 8.2171, "step": 167 }, { "epoch": 0.38127659574468087, "grad_norm": 22.12885284423828, "learning_rate": 6.284403669724771e-06, "loss": 6.9893, "step": 168 }, { "epoch": 0.38354609929078015, "grad_norm": 26.29765510559082, "learning_rate": 6.261467889908257e-06, "loss": 8.0526, "step": 169 }, { "epoch": 0.38581560283687943, "grad_norm": 21.80330467224121, "learning_rate": 6.238532110091744e-06, "loss": 8.3926, "step": 170 }, { "epoch": 0.3880851063829787, "grad_norm": 25.69621467590332, "learning_rate": 6.21559633027523e-06, "loss": 8.5675, "step": 171 }, { "epoch": 0.390354609929078, "grad_norm": 22.812883377075195, "learning_rate": 6.192660550458715e-06, "loss": 8.0201, "step": 172 }, { "epoch": 0.3926241134751773, "grad_norm": 19.11542320251465, "learning_rate": 6.169724770642203e-06, "loss": 7.8873, "step": 173 }, { "epoch": 0.3948936170212766, "grad_norm": 19.369619369506836, "learning_rate": 6.146788990825688e-06, "loss": 8.7483, "step": 174 }, { "epoch": 0.3971631205673759, "grad_norm": 19.47308921813965, "learning_rate": 6.123853211009176e-06, "loss": 8.1481, "step": 175 }, { "epoch": 0.3994326241134752, "grad_norm": 19.873310089111328, "learning_rate": 6.100917431192661e-06, "loss": 6.7817, "step": 176 }, { "epoch": 0.40170212765957447, "grad_norm": 17.962324142456055, "learning_rate": 6.077981651376147e-06, "loss": 7.9007, "step": 177 }, { "epoch": 0.40397163120567375, "grad_norm": 17.880413055419922, "learning_rate": 6.0550458715596335e-06, "loss": 8.3603, "step": 178 }, { "epoch": 0.40624113475177304, "grad_norm": 18.9908504486084, "learning_rate": 6.0321100917431195e-06, "loss": 7.706, "step": 179 }, { "epoch": 0.4085106382978723, "grad_norm": 20.410573959350586, "learning_rate": 6.0091743119266054e-06, "loss": 8.083, "step": 180 }, { "epoch": 0.41078014184397166, "grad_norm": 20.948680877685547, "learning_rate": 5.986238532110092e-06, "loss": 7.8692, "step": 181 }, { "epoch": 0.41304964539007094, "grad_norm": 20.41412353515625, "learning_rate": 5.963302752293578e-06, "loss": 8.4966, "step": 182 }, { "epoch": 0.4153191489361702, "grad_norm": 20.499412536621094, "learning_rate": 5.940366972477065e-06, "loss": 6.7302, "step": 183 }, { "epoch": 0.4175886524822695, "grad_norm": 22.926239013671875, "learning_rate": 5.917431192660551e-06, "loss": 8.5185, "step": 184 }, { "epoch": 0.4198581560283688, "grad_norm": 25.047666549682617, "learning_rate": 5.894495412844037e-06, "loss": 8.1966, "step": 185 }, { "epoch": 0.4221276595744681, "grad_norm": 20.390304565429688, "learning_rate": 5.871559633027524e-06, "loss": 8.7311, "step": 186 }, { "epoch": 0.42439716312056736, "grad_norm": 22.2208309173584, "learning_rate": 5.84862385321101e-06, "loss": 8.7518, "step": 187 }, { "epoch": 0.4266666666666667, "grad_norm": 21.088228225708008, "learning_rate": 5.825688073394496e-06, "loss": 9.1575, "step": 188 }, { "epoch": 0.428936170212766, "grad_norm": 20.080183029174805, "learning_rate": 5.8027522935779825e-06, "loss": 9.0417, "step": 189 }, { "epoch": 0.43120567375886526, "grad_norm": 21.319164276123047, "learning_rate": 5.7798165137614684e-06, "loss": 8.4924, "step": 190 }, { "epoch": 0.43347517730496454, "grad_norm": 21.390085220336914, "learning_rate": 5.756880733944955e-06, "loss": 9.2874, "step": 191 }, { "epoch": 0.4357446808510638, "grad_norm": 29.470535278320312, "learning_rate": 5.733944954128441e-06, "loss": 8.8299, "step": 192 }, { "epoch": 0.4380141843971631, "grad_norm": 20.854496002197266, "learning_rate": 5.711009174311926e-06, "loss": 7.7118, "step": 193 }, { "epoch": 0.4402836879432624, "grad_norm": 22.129270553588867, "learning_rate": 5.688073394495414e-06, "loss": 8.3762, "step": 194 }, { "epoch": 0.4425531914893617, "grad_norm": 24.74121856689453, "learning_rate": 5.665137614678899e-06, "loss": 8.5657, "step": 195 }, { "epoch": 0.444822695035461, "grad_norm": 20.86508560180664, "learning_rate": 5.642201834862385e-06, "loss": 9.9038, "step": 196 }, { "epoch": 0.4470921985815603, "grad_norm": 23.29728126525879, "learning_rate": 5.619266055045872e-06, "loss": 8.8565, "step": 197 }, { "epoch": 0.4493617021276596, "grad_norm": 21.94147491455078, "learning_rate": 5.596330275229358e-06, "loss": 9.0632, "step": 198 }, { "epoch": 0.45163120567375886, "grad_norm": 26.867765426635742, "learning_rate": 5.573394495412845e-06, "loss": 8.3582, "step": 199 }, { "epoch": 0.45390070921985815, "grad_norm": 24.374439239501953, "learning_rate": 5.5504587155963306e-06, "loss": 8.3285, "step": 200 }, { "epoch": 0.45617021276595743, "grad_norm": 20.702878952026367, "learning_rate": 5.5275229357798165e-06, "loss": 8.7522, "step": 201 }, { "epoch": 0.4584397163120567, "grad_norm": 21.596261978149414, "learning_rate": 5.504587155963303e-06, "loss": 9.9127, "step": 202 }, { "epoch": 0.46070921985815605, "grad_norm": 27.27617073059082, "learning_rate": 5.481651376146789e-06, "loss": 9.2612, "step": 203 }, { "epoch": 0.46297872340425533, "grad_norm": 22.221073150634766, "learning_rate": 5.458715596330275e-06, "loss": 8.5588, "step": 204 }, { "epoch": 0.4652482269503546, "grad_norm": 21.73520278930664, "learning_rate": 5.435779816513762e-06, "loss": 8.8134, "step": 205 }, { "epoch": 0.4675177304964539, "grad_norm": 20.27106475830078, "learning_rate": 5.412844036697248e-06, "loss": 9.9369, "step": 206 }, { "epoch": 0.4697872340425532, "grad_norm": 20.44472312927246, "learning_rate": 5.389908256880735e-06, "loss": 9.6772, "step": 207 }, { "epoch": 0.47205673758865246, "grad_norm": 25.24410057067871, "learning_rate": 5.366972477064221e-06, "loss": 8.6581, "step": 208 }, { "epoch": 0.47432624113475175, "grad_norm": 22.4099178314209, "learning_rate": 5.344036697247707e-06, "loss": 9.1995, "step": 209 }, { "epoch": 0.4765957446808511, "grad_norm": 22.774166107177734, "learning_rate": 5.3211009174311936e-06, "loss": 8.8857, "step": 210 }, { "epoch": 0.47886524822695037, "grad_norm": 24.243854522705078, "learning_rate": 5.2981651376146795e-06, "loss": 9.5173, "step": 211 }, { "epoch": 0.48113475177304965, "grad_norm": 22.734128952026367, "learning_rate": 5.275229357798165e-06, "loss": 8.7894, "step": 212 }, { "epoch": 0.48340425531914893, "grad_norm": 22.62639045715332, "learning_rate": 5.252293577981652e-06, "loss": 8.9936, "step": 213 }, { "epoch": 0.4856737588652482, "grad_norm": 19.773698806762695, "learning_rate": 5.229357798165137e-06, "loss": 9.3617, "step": 214 }, { "epoch": 0.4879432624113475, "grad_norm": 27.143184661865234, "learning_rate": 5.206422018348625e-06, "loss": 7.9743, "step": 215 }, { "epoch": 0.4902127659574468, "grad_norm": 22.81350326538086, "learning_rate": 5.18348623853211e-06, "loss": 9.6583, "step": 216 }, { "epoch": 0.4924822695035461, "grad_norm": 20.42306900024414, "learning_rate": 5.160550458715596e-06, "loss": 8.7309, "step": 217 }, { "epoch": 0.4947517730496454, "grad_norm": 19.569499969482422, "learning_rate": 5.137614678899083e-06, "loss": 8.734, "step": 218 }, { "epoch": 0.4970212765957447, "grad_norm": 18.316558837890625, "learning_rate": 5.114678899082569e-06, "loss": 9.5716, "step": 219 }, { "epoch": 0.49929078014184397, "grad_norm": 22.866342544555664, "learning_rate": 5.091743119266055e-06, "loss": 7.9844, "step": 220 }, { "epoch": 0.5015602836879433, "grad_norm": 21.872119903564453, "learning_rate": 5.068807339449542e-06, "loss": 8.9667, "step": 221 }, { "epoch": 0.5038297872340426, "grad_norm": 24.32941246032715, "learning_rate": 5.045871559633028e-06, "loss": 9.702, "step": 222 }, { "epoch": 0.5060992907801418, "grad_norm": 20.190793991088867, "learning_rate": 5.0229357798165144e-06, "loss": 9.0069, "step": 223 }, { "epoch": 0.5083687943262412, "grad_norm": 26.227453231811523, "learning_rate": 5e-06, "loss": 8.9535, "step": 224 }, { "epoch": 0.5106382978723404, "grad_norm": 21.43755340576172, "learning_rate": 4.977064220183486e-06, "loss": 8.8703, "step": 225 }, { "epoch": 0.5129078014184397, "grad_norm": 24.589296340942383, "learning_rate": 4.954128440366973e-06, "loss": 8.6701, "step": 226 }, { "epoch": 0.5151773049645391, "grad_norm": 21.564857482910156, "learning_rate": 4.931192660550459e-06, "loss": 8.5241, "step": 227 }, { "epoch": 0.5174468085106383, "grad_norm": 23.29122543334961, "learning_rate": 4.908256880733945e-06, "loss": 8.6373, "step": 228 }, { "epoch": 0.5197163120567376, "grad_norm": 24.149982452392578, "learning_rate": 4.885321100917432e-06, "loss": 9.853, "step": 229 }, { "epoch": 0.5219858156028369, "grad_norm": 21.790416717529297, "learning_rate": 4.862385321100918e-06, "loss": 9.0991, "step": 230 }, { "epoch": 0.5242553191489362, "grad_norm": 24.31171989440918, "learning_rate": 4.839449541284404e-06, "loss": 9.005, "step": 231 }, { "epoch": 0.5265248226950354, "grad_norm": 21.59621238708496, "learning_rate": 4.816513761467891e-06, "loss": 9.4747, "step": 232 }, { "epoch": 0.5287943262411348, "grad_norm": 22.780820846557617, "learning_rate": 4.793577981651377e-06, "loss": 8.7142, "step": 233 }, { "epoch": 0.531063829787234, "grad_norm": 22.83574676513672, "learning_rate": 4.770642201834863e-06, "loss": 8.5958, "step": 234 }, { "epoch": 0.5333333333333333, "grad_norm": 23.332508087158203, "learning_rate": 4.7477064220183485e-06, "loss": 9.4362, "step": 235 }, { "epoch": 0.5356028368794327, "grad_norm": 26.2183895111084, "learning_rate": 4.724770642201835e-06, "loss": 8.2966, "step": 236 }, { "epoch": 0.5378723404255319, "grad_norm": 22.304824829101562, "learning_rate": 4.701834862385321e-06, "loss": 8.6217, "step": 237 }, { "epoch": 0.5401418439716312, "grad_norm": 21.023757934570312, "learning_rate": 4.678899082568808e-06, "loss": 9.4907, "step": 238 }, { "epoch": 0.5424113475177305, "grad_norm": 23.659706115722656, "learning_rate": 4.655963302752294e-06, "loss": 8.7256, "step": 239 }, { "epoch": 0.5446808510638298, "grad_norm": 21.11109733581543, "learning_rate": 4.63302752293578e-06, "loss": 9.4949, "step": 240 }, { "epoch": 0.546950354609929, "grad_norm": 23.401512145996094, "learning_rate": 4.610091743119267e-06, "loss": 7.9954, "step": 241 }, { "epoch": 0.5492198581560284, "grad_norm": 22.936824798583984, "learning_rate": 4.587155963302753e-06, "loss": 8.9379, "step": 242 }, { "epoch": 0.5514893617021277, "grad_norm": 22.5874080657959, "learning_rate": 4.564220183486239e-06, "loss": 8.8174, "step": 243 }, { "epoch": 0.5537588652482269, "grad_norm": 21.39436912536621, "learning_rate": 4.541284403669725e-06, "loss": 9.2327, "step": 244 }, { "epoch": 0.5560283687943263, "grad_norm": 17.799089431762695, "learning_rate": 4.5183486238532115e-06, "loss": 8.1766, "step": 245 }, { "epoch": 0.5582978723404255, "grad_norm": 19.959014892578125, "learning_rate": 4.4954128440366975e-06, "loss": 8.6151, "step": 246 }, { "epoch": 0.5605673758865248, "grad_norm": 23.883373260498047, "learning_rate": 4.4724770642201834e-06, "loss": 8.5234, "step": 247 }, { "epoch": 0.5628368794326241, "grad_norm": 24.65569305419922, "learning_rate": 4.44954128440367e-06, "loss": 8.6096, "step": 248 }, { "epoch": 0.5651063829787234, "grad_norm": 20.192543029785156, "learning_rate": 4.426605504587156e-06, "loss": 8.2989, "step": 249 }, { "epoch": 0.5673758865248227, "grad_norm": 24.154382705688477, "learning_rate": 4.403669724770643e-06, "loss": 9.0628, "step": 250 }, { "epoch": 0.569645390070922, "grad_norm": 23.96573829650879, "learning_rate": 4.380733944954129e-06, "loss": 9.4036, "step": 251 }, { "epoch": 0.5719148936170213, "grad_norm": 22.239057540893555, "learning_rate": 4.357798165137615e-06, "loss": 9.0679, "step": 252 }, { "epoch": 0.5741843971631205, "grad_norm": 21.915634155273438, "learning_rate": 4.334862385321102e-06, "loss": 9.3959, "step": 253 }, { "epoch": 0.5764539007092199, "grad_norm": 26.115306854248047, "learning_rate": 4.311926605504588e-06, "loss": 9.0681, "step": 254 }, { "epoch": 0.5787234042553191, "grad_norm": 20.699838638305664, "learning_rate": 4.288990825688074e-06, "loss": 8.4086, "step": 255 }, { "epoch": 0.5809929078014184, "grad_norm": 33.57377624511719, "learning_rate": 4.26605504587156e-06, "loss": 8.9626, "step": 256 }, { "epoch": 0.5832624113475178, "grad_norm": 23.978317260742188, "learning_rate": 4.2431192660550464e-06, "loss": 8.7844, "step": 257 }, { "epoch": 0.585531914893617, "grad_norm": 20.900381088256836, "learning_rate": 4.220183486238532e-06, "loss": 8.0864, "step": 258 }, { "epoch": 0.5878014184397163, "grad_norm": 20.382389068603516, "learning_rate": 4.197247706422018e-06, "loss": 7.9051, "step": 259 }, { "epoch": 0.5900709219858156, "grad_norm": 20.69447135925293, "learning_rate": 4.174311926605505e-06, "loss": 9.7578, "step": 260 }, { "epoch": 0.5923404255319149, "grad_norm": 19.204599380493164, "learning_rate": 4.151376146788991e-06, "loss": 9.2602, "step": 261 }, { "epoch": 0.5946099290780141, "grad_norm": 23.776403427124023, "learning_rate": 4.128440366972478e-06, "loss": 9.5354, "step": 262 }, { "epoch": 0.5968794326241135, "grad_norm": 22.453596115112305, "learning_rate": 4.105504587155963e-06, "loss": 9.0892, "step": 263 }, { "epoch": 0.5991489361702128, "grad_norm": 26.120044708251953, "learning_rate": 4.08256880733945e-06, "loss": 8.25, "step": 264 }, { "epoch": 0.601418439716312, "grad_norm": 25.392539978027344, "learning_rate": 4.059633027522936e-06, "loss": 8.9119, "step": 265 }, { "epoch": 0.6036879432624114, "grad_norm": 25.169811248779297, "learning_rate": 4.036697247706423e-06, "loss": 9.2287, "step": 266 }, { "epoch": 0.6059574468085106, "grad_norm": 23.787094116210938, "learning_rate": 4.013761467889909e-06, "loss": 9.264, "step": 267 }, { "epoch": 0.6082269503546099, "grad_norm": 22.346942901611328, "learning_rate": 3.9908256880733945e-06, "loss": 9.9034, "step": 268 }, { "epoch": 0.6104964539007092, "grad_norm": 23.25787353515625, "learning_rate": 3.967889908256881e-06, "loss": 9.3452, "step": 269 }, { "epoch": 0.6127659574468085, "grad_norm": 23.456954956054688, "learning_rate": 3.944954128440367e-06, "loss": 9.7988, "step": 270 }, { "epoch": 0.6150354609929078, "grad_norm": 20.742055892944336, "learning_rate": 3.922018348623853e-06, "loss": 9.5773, "step": 271 }, { "epoch": 0.6173049645390071, "grad_norm": 22.536502838134766, "learning_rate": 3.89908256880734e-06, "loss": 8.4121, "step": 272 }, { "epoch": 0.6195744680851064, "grad_norm": 19.590784072875977, "learning_rate": 3.876146788990826e-06, "loss": 8.1515, "step": 273 }, { "epoch": 0.6218439716312056, "grad_norm": 22.402301788330078, "learning_rate": 3.853211009174313e-06, "loss": 9.1177, "step": 274 }, { "epoch": 0.624113475177305, "grad_norm": 21.9833984375, "learning_rate": 3.830275229357798e-06, "loss": 9.0071, "step": 275 }, { "epoch": 0.6263829787234042, "grad_norm": 22.869976043701172, "learning_rate": 3.8073394495412848e-06, "loss": 8.6188, "step": 276 }, { "epoch": 0.6286524822695035, "grad_norm": 19.955623626708984, "learning_rate": 3.784403669724771e-06, "loss": 8.7453, "step": 277 }, { "epoch": 0.6309219858156029, "grad_norm": 20.201040267944336, "learning_rate": 3.7614678899082575e-06, "loss": 9.2329, "step": 278 }, { "epoch": 0.6331914893617021, "grad_norm": 24.440963745117188, "learning_rate": 3.738532110091743e-06, "loss": 9.5977, "step": 279 }, { "epoch": 0.6354609929078014, "grad_norm": 21.767749786376953, "learning_rate": 3.7155963302752295e-06, "loss": 10.2118, "step": 280 }, { "epoch": 0.6377304964539007, "grad_norm": 20.093414306640625, "learning_rate": 3.692660550458716e-06, "loss": 8.6707, "step": 281 }, { "epoch": 0.64, "grad_norm": 25.830089569091797, "learning_rate": 3.6697247706422022e-06, "loss": 9.0973, "step": 282 }, { "epoch": 0.6422695035460992, "grad_norm": 25.09172821044922, "learning_rate": 3.646788990825688e-06, "loss": 8.2879, "step": 283 }, { "epoch": 0.6445390070921986, "grad_norm": 22.130929946899414, "learning_rate": 3.6238532110091746e-06, "loss": 9.45, "step": 284 }, { "epoch": 0.6468085106382979, "grad_norm": 21.386566162109375, "learning_rate": 3.600917431192661e-06, "loss": 8.6722, "step": 285 }, { "epoch": 0.6490780141843971, "grad_norm": 23.362714767456055, "learning_rate": 3.5779816513761473e-06, "loss": 8.4233, "step": 286 }, { "epoch": 0.6513475177304965, "grad_norm": 20.452402114868164, "learning_rate": 3.5550458715596333e-06, "loss": 7.2916, "step": 287 }, { "epoch": 0.6536170212765957, "grad_norm": 23.259218215942383, "learning_rate": 3.5321100917431193e-06, "loss": 8.7541, "step": 288 }, { "epoch": 0.655886524822695, "grad_norm": 21.25058937072754, "learning_rate": 3.5091743119266056e-06, "loss": 8.5045, "step": 289 }, { "epoch": 0.6581560283687943, "grad_norm": 20.266357421875, "learning_rate": 3.486238532110092e-06, "loss": 8.429, "step": 290 }, { "epoch": 0.6604255319148936, "grad_norm": 19.669076919555664, "learning_rate": 3.463302752293578e-06, "loss": 8.9195, "step": 291 }, { "epoch": 0.662695035460993, "grad_norm": 20.31602668762207, "learning_rate": 3.4403669724770644e-06, "loss": 7.8789, "step": 292 }, { "epoch": 0.6649645390070922, "grad_norm": 20.338945388793945, "learning_rate": 3.4174311926605508e-06, "loss": 9.4938, "step": 293 }, { "epoch": 0.6672340425531915, "grad_norm": 21.29444122314453, "learning_rate": 3.394495412844037e-06, "loss": 9.2899, "step": 294 }, { "epoch": 0.6695035460992907, "grad_norm": 19.27189826965332, "learning_rate": 3.371559633027523e-06, "loss": 8.6158, "step": 295 }, { "epoch": 0.6717730496453901, "grad_norm": 19.7462215423584, "learning_rate": 3.3486238532110095e-06, "loss": 8.5196, "step": 296 }, { "epoch": 0.6740425531914893, "grad_norm": 20.589706420898438, "learning_rate": 3.325688073394496e-06, "loss": 8.8257, "step": 297 }, { "epoch": 0.6763120567375887, "grad_norm": 23.5162410736084, "learning_rate": 3.3027522935779823e-06, "loss": 8.7799, "step": 298 }, { "epoch": 0.678581560283688, "grad_norm": 21.263465881347656, "learning_rate": 3.279816513761468e-06, "loss": 8.5593, "step": 299 }, { "epoch": 0.6808510638297872, "grad_norm": 24.811080932617188, "learning_rate": 3.256880733944954e-06, "loss": 9.29, "step": 300 }, { "epoch": 0.6831205673758866, "grad_norm": 24.241764068603516, "learning_rate": 3.2339449541284406e-06, "loss": 8.9021, "step": 301 }, { "epoch": 0.6853900709219858, "grad_norm": 20.97438621520996, "learning_rate": 3.211009174311927e-06, "loss": 8.3882, "step": 302 }, { "epoch": 0.6876595744680851, "grad_norm": 19.46367073059082, "learning_rate": 3.188073394495413e-06, "loss": 8.6959, "step": 303 }, { "epoch": 0.6899290780141843, "grad_norm": 20.273815155029297, "learning_rate": 3.1651376146788993e-06, "loss": 8.5618, "step": 304 }, { "epoch": 0.6921985815602837, "grad_norm": 20.108722686767578, "learning_rate": 3.1422018348623857e-06, "loss": 8.7455, "step": 305 }, { "epoch": 0.694468085106383, "grad_norm": 20.470699310302734, "learning_rate": 3.119266055045872e-06, "loss": 9.0647, "step": 306 }, { "epoch": 0.6967375886524823, "grad_norm": 23.111759185791016, "learning_rate": 3.0963302752293576e-06, "loss": 7.7973, "step": 307 }, { "epoch": 0.6990070921985816, "grad_norm": 19.48809814453125, "learning_rate": 3.073394495412844e-06, "loss": 8.6149, "step": 308 }, { "epoch": 0.7012765957446808, "grad_norm": 20.433012008666992, "learning_rate": 3.0504587155963304e-06, "loss": 9.6679, "step": 309 }, { "epoch": 0.7035460992907802, "grad_norm": 21.91651153564453, "learning_rate": 3.0275229357798168e-06, "loss": 9.0232, "step": 310 }, { "epoch": 0.7058156028368794, "grad_norm": 22.22764778137207, "learning_rate": 3.0045871559633027e-06, "loss": 8.4506, "step": 311 }, { "epoch": 0.7080851063829787, "grad_norm": 24.07482147216797, "learning_rate": 2.981651376146789e-06, "loss": 8.5839, "step": 312 }, { "epoch": 0.7103546099290781, "grad_norm": 22.27802085876465, "learning_rate": 2.9587155963302755e-06, "loss": 8.5646, "step": 313 }, { "epoch": 0.7126241134751773, "grad_norm": 26.386104583740234, "learning_rate": 2.935779816513762e-06, "loss": 9.4434, "step": 314 }, { "epoch": 0.7148936170212766, "grad_norm": 25.210561752319336, "learning_rate": 2.912844036697248e-06, "loss": 9.5896, "step": 315 }, { "epoch": 0.7171631205673759, "grad_norm": 23.556467056274414, "learning_rate": 2.8899082568807342e-06, "loss": 9.4062, "step": 316 }, { "epoch": 0.7194326241134752, "grad_norm": 20.907451629638672, "learning_rate": 2.8669724770642206e-06, "loss": 9.2768, "step": 317 }, { "epoch": 0.7217021276595744, "grad_norm": 24.085954666137695, "learning_rate": 2.844036697247707e-06, "loss": 9.0089, "step": 318 }, { "epoch": 0.7239716312056738, "grad_norm": 19.62236976623535, "learning_rate": 2.8211009174311925e-06, "loss": 8.8469, "step": 319 }, { "epoch": 0.7262411347517731, "grad_norm": 20.33197593688965, "learning_rate": 2.798165137614679e-06, "loss": 9.6477, "step": 320 }, { "epoch": 0.7285106382978723, "grad_norm": 22.44576644897461, "learning_rate": 2.7752293577981653e-06, "loss": 8.399, "step": 321 }, { "epoch": 0.7307801418439717, "grad_norm": 25.211545944213867, "learning_rate": 2.7522935779816517e-06, "loss": 9.9376, "step": 322 }, { "epoch": 0.7330496453900709, "grad_norm": 22.72049903869629, "learning_rate": 2.7293577981651376e-06, "loss": 8.8572, "step": 323 }, { "epoch": 0.7353191489361702, "grad_norm": 22.22250747680664, "learning_rate": 2.706422018348624e-06, "loss": 7.9473, "step": 324 }, { "epoch": 0.7375886524822695, "grad_norm": 23.077878952026367, "learning_rate": 2.6834862385321104e-06, "loss": 7.9867, "step": 325 }, { "epoch": 0.7398581560283688, "grad_norm": 21.07669448852539, "learning_rate": 2.6605504587155968e-06, "loss": 9.5314, "step": 326 }, { "epoch": 0.7421276595744681, "grad_norm": 22.29209327697754, "learning_rate": 2.6376146788990823e-06, "loss": 10.4723, "step": 327 }, { "epoch": 0.7443971631205674, "grad_norm": 21.446693420410156, "learning_rate": 2.6146788990825687e-06, "loss": 9.4333, "step": 328 }, { "epoch": 0.7466666666666667, "grad_norm": 21.224918365478516, "learning_rate": 2.591743119266055e-06, "loss": 9.1956, "step": 329 }, { "epoch": 0.7489361702127659, "grad_norm": 19.541072845458984, "learning_rate": 2.5688073394495415e-06, "loss": 8.7495, "step": 330 }, { "epoch": 0.7512056737588653, "grad_norm": 22.24167823791504, "learning_rate": 2.5458715596330274e-06, "loss": 7.7455, "step": 331 }, { "epoch": 0.7534751773049645, "grad_norm": 23.247812271118164, "learning_rate": 2.522935779816514e-06, "loss": 9.2308, "step": 332 }, { "epoch": 0.7557446808510638, "grad_norm": 25.327579498291016, "learning_rate": 2.5e-06, "loss": 8.6432, "step": 333 }, { "epoch": 0.7580141843971632, "grad_norm": 19.60987663269043, "learning_rate": 2.4770642201834866e-06, "loss": 7.8816, "step": 334 }, { "epoch": 0.7602836879432624, "grad_norm": 23.883792877197266, "learning_rate": 2.4541284403669725e-06, "loss": 8.0843, "step": 335 }, { "epoch": 0.7625531914893617, "grad_norm": 22.443225860595703, "learning_rate": 2.431192660550459e-06, "loss": 8.6025, "step": 336 }, { "epoch": 0.764822695035461, "grad_norm": 24.618696212768555, "learning_rate": 2.4082568807339453e-06, "loss": 8.8902, "step": 337 }, { "epoch": 0.7670921985815603, "grad_norm": 21.362323760986328, "learning_rate": 2.3853211009174317e-06, "loss": 8.1767, "step": 338 }, { "epoch": 0.7693617021276595, "grad_norm": 19.34098243713379, "learning_rate": 2.3623853211009177e-06, "loss": 9.1628, "step": 339 }, { "epoch": 0.7716312056737589, "grad_norm": 23.454626083374023, "learning_rate": 2.339449541284404e-06, "loss": 8.6701, "step": 340 }, { "epoch": 0.7739007092198582, "grad_norm": 22.39373016357422, "learning_rate": 2.31651376146789e-06, "loss": 9.0315, "step": 341 }, { "epoch": 0.7761702127659574, "grad_norm": 22.340145111083984, "learning_rate": 2.2935779816513764e-06, "loss": 8.4421, "step": 342 }, { "epoch": 0.7784397163120568, "grad_norm": 19.80050277709961, "learning_rate": 2.2706422018348624e-06, "loss": 9.991, "step": 343 }, { "epoch": 0.780709219858156, "grad_norm": 27.38515853881836, "learning_rate": 2.2477064220183487e-06, "loss": 8.7005, "step": 344 }, { "epoch": 0.7829787234042553, "grad_norm": 26.323341369628906, "learning_rate": 2.224770642201835e-06, "loss": 8.9239, "step": 345 }, { "epoch": 0.7852482269503546, "grad_norm": 29.13960838317871, "learning_rate": 2.2018348623853215e-06, "loss": 8.4935, "step": 346 }, { "epoch": 0.7875177304964539, "grad_norm": 23.07470703125, "learning_rate": 2.1788990825688075e-06, "loss": 9.0144, "step": 347 }, { "epoch": 0.7897872340425532, "grad_norm": 23.885528564453125, "learning_rate": 2.155963302752294e-06, "loss": 8.5971, "step": 348 }, { "epoch": 0.7920567375886525, "grad_norm": 26.535350799560547, "learning_rate": 2.13302752293578e-06, "loss": 9.4921, "step": 349 }, { "epoch": 0.7943262411347518, "grad_norm": 31.360124588012695, "learning_rate": 2.110091743119266e-06, "loss": 9.2596, "step": 350 }, { "epoch": 0.796595744680851, "grad_norm": 26.082653045654297, "learning_rate": 2.0871559633027526e-06, "loss": 8.3412, "step": 351 }, { "epoch": 0.7988652482269504, "grad_norm": 29.84249496459961, "learning_rate": 2.064220183486239e-06, "loss": 8.3945, "step": 352 }, { "epoch": 0.8011347517730496, "grad_norm": 23.817001342773438, "learning_rate": 2.041284403669725e-06, "loss": 9.1283, "step": 353 }, { "epoch": 0.8034042553191489, "grad_norm": 23.801820755004883, "learning_rate": 2.0183486238532113e-06, "loss": 8.1482, "step": 354 }, { "epoch": 0.8056737588652483, "grad_norm": 21.827836990356445, "learning_rate": 1.9954128440366973e-06, "loss": 9.7213, "step": 355 }, { "epoch": 0.8079432624113475, "grad_norm": 23.56734848022461, "learning_rate": 1.9724770642201837e-06, "loss": 9.2384, "step": 356 }, { "epoch": 0.8102127659574468, "grad_norm": 23.761621475219727, "learning_rate": 1.94954128440367e-06, "loss": 9.2796, "step": 357 }, { "epoch": 0.8124822695035461, "grad_norm": 26.117843627929688, "learning_rate": 1.9266055045871564e-06, "loss": 8.9294, "step": 358 }, { "epoch": 0.8147517730496454, "grad_norm": 23.002927780151367, "learning_rate": 1.9036697247706424e-06, "loss": 9.3011, "step": 359 }, { "epoch": 0.8170212765957446, "grad_norm": 24.2608585357666, "learning_rate": 1.8807339449541288e-06, "loss": 9.5672, "step": 360 }, { "epoch": 0.819290780141844, "grad_norm": 23.872974395751953, "learning_rate": 1.8577981651376147e-06, "loss": 8.4479, "step": 361 }, { "epoch": 0.8215602836879433, "grad_norm": 24.643653869628906, "learning_rate": 1.8348623853211011e-06, "loss": 9.3534, "step": 362 }, { "epoch": 0.8238297872340425, "grad_norm": 23.47624969482422, "learning_rate": 1.8119266055045873e-06, "loss": 8.9452, "step": 363 }, { "epoch": 0.8260992907801419, "grad_norm": 30.683324813842773, "learning_rate": 1.7889908256880737e-06, "loss": 9.1146, "step": 364 }, { "epoch": 0.8283687943262411, "grad_norm": 24.093713760375977, "learning_rate": 1.7660550458715596e-06, "loss": 8.5803, "step": 365 }, { "epoch": 0.8306382978723404, "grad_norm": 25.56736183166504, "learning_rate": 1.743119266055046e-06, "loss": 9.0811, "step": 366 }, { "epoch": 0.8329078014184397, "grad_norm": 22.663944244384766, "learning_rate": 1.7201834862385322e-06, "loss": 8.3341, "step": 367 }, { "epoch": 0.835177304964539, "grad_norm": 26.666257858276367, "learning_rate": 1.6972477064220186e-06, "loss": 9.2764, "step": 368 }, { "epoch": 0.8374468085106384, "grad_norm": 26.197025299072266, "learning_rate": 1.6743119266055047e-06, "loss": 9.2512, "step": 369 }, { "epoch": 0.8397163120567376, "grad_norm": 22.855541229248047, "learning_rate": 1.6513761467889911e-06, "loss": 10.4676, "step": 370 }, { "epoch": 0.8419858156028369, "grad_norm": 25.121883392333984, "learning_rate": 1.628440366972477e-06, "loss": 8.1274, "step": 371 }, { "epoch": 0.8442553191489361, "grad_norm": 24.458892822265625, "learning_rate": 1.6055045871559635e-06, "loss": 9.7478, "step": 372 }, { "epoch": 0.8465248226950355, "grad_norm": 26.895700454711914, "learning_rate": 1.5825688073394496e-06, "loss": 9.2536, "step": 373 }, { "epoch": 0.8487943262411347, "grad_norm": 25.79054069519043, "learning_rate": 1.559633027522936e-06, "loss": 8.397, "step": 374 }, { "epoch": 0.851063829787234, "grad_norm": 21.99020767211914, "learning_rate": 1.536697247706422e-06, "loss": 9.3287, "step": 375 }, { "epoch": 0.8533333333333334, "grad_norm": 22.8013973236084, "learning_rate": 1.5137614678899084e-06, "loss": 9.5124, "step": 376 }, { "epoch": 0.8556028368794326, "grad_norm": 23.19257926940918, "learning_rate": 1.4908256880733945e-06, "loss": 9.6086, "step": 377 }, { "epoch": 0.857872340425532, "grad_norm": 25.23111343383789, "learning_rate": 1.467889908256881e-06, "loss": 8.9162, "step": 378 }, { "epoch": 0.8601418439716312, "grad_norm": 20.868675231933594, "learning_rate": 1.4449541284403671e-06, "loss": 8.3255, "step": 379 }, { "epoch": 0.8624113475177305, "grad_norm": 24.87611198425293, "learning_rate": 1.4220183486238535e-06, "loss": 9.4666, "step": 380 }, { "epoch": 0.8646808510638297, "grad_norm": 22.679014205932617, "learning_rate": 1.3990825688073395e-06, "loss": 9.4336, "step": 381 }, { "epoch": 0.8669503546099291, "grad_norm": 24.08158302307129, "learning_rate": 1.3761467889908258e-06, "loss": 10.109, "step": 382 }, { "epoch": 0.8692198581560284, "grad_norm": 24.750272750854492, "learning_rate": 1.353211009174312e-06, "loss": 9.4976, "step": 383 }, { "epoch": 0.8714893617021277, "grad_norm": 26.413402557373047, "learning_rate": 1.3302752293577984e-06, "loss": 9.062, "step": 384 }, { "epoch": 0.873758865248227, "grad_norm": 23.175153732299805, "learning_rate": 1.3073394495412844e-06, "loss": 9.1572, "step": 385 }, { "epoch": 0.8760283687943262, "grad_norm": 29.42748260498047, "learning_rate": 1.2844036697247707e-06, "loss": 9.0716, "step": 386 }, { "epoch": 0.8782978723404256, "grad_norm": 29.94127082824707, "learning_rate": 1.261467889908257e-06, "loss": 9.0406, "step": 387 }, { "epoch": 0.8805673758865248, "grad_norm": 21.167320251464844, "learning_rate": 1.2385321100917433e-06, "loss": 9.6334, "step": 388 }, { "epoch": 0.8828368794326241, "grad_norm": 25.066551208496094, "learning_rate": 1.2155963302752295e-06, "loss": 9.1221, "step": 389 }, { "epoch": 0.8851063829787233, "grad_norm": 21.799222946166992, "learning_rate": 1.1926605504587159e-06, "loss": 8.0991, "step": 390 }, { "epoch": 0.8873758865248227, "grad_norm": 26.113718032836914, "learning_rate": 1.169724770642202e-06, "loss": 9.624, "step": 391 }, { "epoch": 0.889645390070922, "grad_norm": 24.098979949951172, "learning_rate": 1.1467889908256882e-06, "loss": 8.2496, "step": 392 }, { "epoch": 0.8919148936170213, "grad_norm": 20.74020767211914, "learning_rate": 1.1238532110091744e-06, "loss": 8.6058, "step": 393 }, { "epoch": 0.8941843971631206, "grad_norm": 26.36321258544922, "learning_rate": 1.1009174311926608e-06, "loss": 8.2644, "step": 394 }, { "epoch": 0.8964539007092198, "grad_norm": 25.446441650390625, "learning_rate": 1.077981651376147e-06, "loss": 9.3619, "step": 395 }, { "epoch": 0.8987234042553192, "grad_norm": 26.684640884399414, "learning_rate": 1.055045871559633e-06, "loss": 9.1501, "step": 396 }, { "epoch": 0.9009929078014184, "grad_norm": 23.125703811645508, "learning_rate": 1.0321100917431195e-06, "loss": 9.535, "step": 397 }, { "epoch": 0.9032624113475177, "grad_norm": 23.205198287963867, "learning_rate": 1.0091743119266057e-06, "loss": 9.1145, "step": 398 }, { "epoch": 0.9055319148936171, "grad_norm": 22.298166275024414, "learning_rate": 9.862385321100918e-07, "loss": 9.2637, "step": 399 }, { "epoch": 0.9078014184397163, "grad_norm": 21.34535789489746, "learning_rate": 9.633027522935782e-07, "loss": 8.6863, "step": 400 }, { "epoch": 0.9100709219858156, "grad_norm": 21.357372283935547, "learning_rate": 9.403669724770644e-07, "loss": 10.1072, "step": 401 }, { "epoch": 0.9123404255319149, "grad_norm": 21.2343807220459, "learning_rate": 9.174311926605506e-07, "loss": 7.5841, "step": 402 }, { "epoch": 0.9146099290780142, "grad_norm": 22.121732711791992, "learning_rate": 8.944954128440368e-07, "loss": 7.8203, "step": 403 }, { "epoch": 0.9168794326241134, "grad_norm": 26.971887588500977, "learning_rate": 8.71559633027523e-07, "loss": 8.4254, "step": 404 }, { "epoch": 0.9191489361702128, "grad_norm": 25.824979782104492, "learning_rate": 8.486238532110093e-07, "loss": 7.9721, "step": 405 }, { "epoch": 0.9214184397163121, "grad_norm": 26.73249053955078, "learning_rate": 8.256880733944956e-07, "loss": 9.965, "step": 406 }, { "epoch": 0.9236879432624113, "grad_norm": 24.988204956054688, "learning_rate": 8.027522935779817e-07, "loss": 9.5348, "step": 407 }, { "epoch": 0.9259574468085107, "grad_norm": 21.955488204956055, "learning_rate": 7.79816513761468e-07, "loss": 8.2987, "step": 408 }, { "epoch": 0.9282269503546099, "grad_norm": 25.078189849853516, "learning_rate": 7.568807339449542e-07, "loss": 10.1475, "step": 409 }, { "epoch": 0.9304964539007092, "grad_norm": 25.054447174072266, "learning_rate": 7.339449541284405e-07, "loss": 9.8734, "step": 410 }, { "epoch": 0.9327659574468085, "grad_norm": 25.63347816467285, "learning_rate": 7.110091743119267e-07, "loss": 8.7758, "step": 411 }, { "epoch": 0.9350354609929078, "grad_norm": 24.229883193969727, "learning_rate": 6.880733944954129e-07, "loss": 8.0827, "step": 412 }, { "epoch": 0.9373049645390071, "grad_norm": 20.565967559814453, "learning_rate": 6.651376146788992e-07, "loss": 9.0098, "step": 413 }, { "epoch": 0.9395744680851064, "grad_norm": 24.123233795166016, "learning_rate": 6.422018348623854e-07, "loss": 9.2069, "step": 414 }, { "epoch": 0.9418439716312057, "grad_norm": 22.128360748291016, "learning_rate": 6.192660550458716e-07, "loss": 8.415, "step": 415 }, { "epoch": 0.9441134751773049, "grad_norm": 23.930240631103516, "learning_rate": 5.963302752293579e-07, "loss": 9.4488, "step": 416 }, { "epoch": 0.9463829787234043, "grad_norm": 22.53655242919922, "learning_rate": 5.733944954128441e-07, "loss": 8.3644, "step": 417 }, { "epoch": 0.9486524822695035, "grad_norm": 25.482990264892578, "learning_rate": 5.504587155963304e-07, "loss": 8.3868, "step": 418 }, { "epoch": 0.9509219858156028, "grad_norm": 22.252609252929688, "learning_rate": 5.275229357798165e-07, "loss": 9.1029, "step": 419 }, { "epoch": 0.9531914893617022, "grad_norm": 25.317054748535156, "learning_rate": 5.045871559633028e-07, "loss": 9.3756, "step": 420 }, { "epoch": 0.9554609929078014, "grad_norm": 21.1016845703125, "learning_rate": 4.816513761467891e-07, "loss": 8.3244, "step": 421 }, { "epoch": 0.9577304964539007, "grad_norm": 25.95676040649414, "learning_rate": 4.587155963302753e-07, "loss": 9.461, "step": 422 }, { "epoch": 0.96, "grad_norm": 20.646509170532227, "learning_rate": 4.357798165137615e-07, "loss": 9.355, "step": 423 }, { "epoch": 0.9622695035460993, "grad_norm": 22.419015884399414, "learning_rate": 4.128440366972478e-07, "loss": 8.9192, "step": 424 }, { "epoch": 0.9645390070921985, "grad_norm": 24.076786041259766, "learning_rate": 3.89908256880734e-07, "loss": 8.826, "step": 425 }, { "epoch": 0.9668085106382979, "grad_norm": 25.495689392089844, "learning_rate": 3.6697247706422023e-07, "loss": 9.478, "step": 426 }, { "epoch": 0.9690780141843972, "grad_norm": 23.184534072875977, "learning_rate": 3.4403669724770646e-07, "loss": 9.2445, "step": 427 }, { "epoch": 0.9713475177304964, "grad_norm": 22.28815269470215, "learning_rate": 3.211009174311927e-07, "loss": 8.3576, "step": 428 }, { "epoch": 0.9736170212765958, "grad_norm": 22.839277267456055, "learning_rate": 2.9816513761467896e-07, "loss": 10.0624, "step": 429 }, { "epoch": 0.975886524822695, "grad_norm": 24.83416748046875, "learning_rate": 2.752293577981652e-07, "loss": 9.006, "step": 430 }, { "epoch": 0.9781560283687943, "grad_norm": 21.34706687927246, "learning_rate": 2.522935779816514e-07, "loss": 9.4307, "step": 431 }, { "epoch": 0.9804255319148936, "grad_norm": 25.04865264892578, "learning_rate": 2.2935779816513764e-07, "loss": 8.6046, "step": 432 }, { "epoch": 0.9826950354609929, "grad_norm": 29.690914154052734, "learning_rate": 2.064220183486239e-07, "loss": 8.7655, "step": 433 }, { "epoch": 0.9849645390070922, "grad_norm": 25.26012420654297, "learning_rate": 1.8348623853211012e-07, "loss": 9.4779, "step": 434 }, { "epoch": 0.9872340425531915, "grad_norm": 20.789047241210938, "learning_rate": 1.6055045871559634e-07, "loss": 9.2229, "step": 435 }, { "epoch": 0.9895035460992908, "grad_norm": 26.303882598876953, "learning_rate": 1.376146788990826e-07, "loss": 9.2579, "step": 436 }, { "epoch": 0.99177304964539, "grad_norm": 22.816631317138672, "learning_rate": 1.1467889908256882e-07, "loss": 8.6126, "step": 437 }, { "epoch": 0.9940425531914894, "grad_norm": 22.665773391723633, "learning_rate": 9.174311926605506e-08, "loss": 8.982, "step": 438 }, { "epoch": 0.9963120567375886, "grad_norm": 23.514062881469727, "learning_rate": 6.88073394495413e-08, "loss": 7.9313, "step": 439 }, { "epoch": 0.9985815602836879, "grad_norm": 29.320030212402344, "learning_rate": 4.587155963302753e-08, "loss": 9.6989, "step": 440 }, { "epoch": 1.0, "grad_norm": 40.22016906738281, "learning_rate": 2.2935779816513765e-08, "loss": 9.939, "step": 441 } ], "logging_steps": 1, "max_steps": 441, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }