{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 17120, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.841121495327103e-05, "grad_norm": 31.84286880493164, "learning_rate": 0.0, "loss": 3.7822, "step": 1 }, { "epoch": 0.00011682242990654206, "grad_norm": 35.21309280395508, "learning_rate": 3.891050583657588e-08, "loss": 4.4639, "step": 2 }, { "epoch": 0.00017523364485981307, "grad_norm": 34.248172760009766, "learning_rate": 7.782101167315175e-08, "loss": 3.7852, "step": 3 }, { "epoch": 0.00023364485981308412, "grad_norm": 32.99418640136719, "learning_rate": 1.1673151750972764e-07, "loss": 4.0238, "step": 4 }, { "epoch": 0.0002920560747663551, "grad_norm": 37.22806167602539, "learning_rate": 1.556420233463035e-07, "loss": 4.5984, "step": 5 }, { "epoch": 0.00035046728971962614, "grad_norm": 33.26788330078125, "learning_rate": 1.9455252918287938e-07, "loss": 4.2639, "step": 6 }, { "epoch": 0.0004088785046728972, "grad_norm": 40.822933197021484, "learning_rate": 2.3346303501945529e-07, "loss": 4.4375, "step": 7 }, { "epoch": 0.00046728971962616824, "grad_norm": 38.654258728027344, "learning_rate": 2.7237354085603116e-07, "loss": 4.5127, "step": 8 }, { "epoch": 0.0005257009345794393, "grad_norm": 45.71051788330078, "learning_rate": 3.11284046692607e-07, "loss": 5.0216, "step": 9 }, { "epoch": 0.0005841121495327102, "grad_norm": 40.50577163696289, "learning_rate": 3.501945525291829e-07, "loss": 4.1172, "step": 10 }, { "epoch": 0.0006425233644859813, "grad_norm": 33.795921325683594, "learning_rate": 3.8910505836575877e-07, "loss": 4.1615, "step": 11 }, { "epoch": 0.0007009345794392523, "grad_norm": 41.553070068359375, "learning_rate": 4.2801556420233467e-07, "loss": 5.058, "step": 12 }, { "epoch": 0.0007593457943925234, "grad_norm": 23.553016662597656, "learning_rate": 4.6692607003891057e-07, "loss": 3.2109, "step": 13 }, { "epoch": 0.0008177570093457944, "grad_norm": 34.817420959472656, "learning_rate": 5.058365758754865e-07, "loss": 4.1759, "step": 14 }, { "epoch": 0.0008761682242990654, "grad_norm": 43.874267578125, "learning_rate": 5.447470817120623e-07, "loss": 4.6764, "step": 15 }, { "epoch": 0.0009345794392523365, "grad_norm": 39.04008102416992, "learning_rate": 5.836575875486382e-07, "loss": 4.7142, "step": 16 }, { "epoch": 0.0009929906542056075, "grad_norm": 31.863849639892578, "learning_rate": 6.22568093385214e-07, "loss": 3.6338, "step": 17 }, { "epoch": 0.0010514018691588785, "grad_norm": 35.01355743408203, "learning_rate": 6.6147859922179e-07, "loss": 3.9198, "step": 18 }, { "epoch": 0.0011098130841121496, "grad_norm": 29.39601707458496, "learning_rate": 7.003891050583658e-07, "loss": 4.0156, "step": 19 }, { "epoch": 0.0011682242990654205, "grad_norm": 32.81162643432617, "learning_rate": 7.392996108949417e-07, "loss": 4.2828, "step": 20 }, { "epoch": 0.0012266355140186916, "grad_norm": 34.70088195800781, "learning_rate": 7.782101167315175e-07, "loss": 4.1455, "step": 21 }, { "epoch": 0.0012850467289719626, "grad_norm": 27.530187606811523, "learning_rate": 8.171206225680935e-07, "loss": 3.6583, "step": 22 }, { "epoch": 0.0013434579439252337, "grad_norm": 26.04412841796875, "learning_rate": 8.560311284046693e-07, "loss": 3.0712, "step": 23 }, { "epoch": 0.0014018691588785046, "grad_norm": 34.17292785644531, "learning_rate": 8.949416342412452e-07, "loss": 3.9795, "step": 24 }, { "epoch": 0.0014602803738317756, "grad_norm": 29.091951370239258, "learning_rate": 9.338521400778211e-07, "loss": 3.5593, "step": 25 }, { "epoch": 0.0015186915887850467, "grad_norm": 23.607545852661133, "learning_rate": 9.72762645914397e-07, "loss": 3.357, "step": 26 }, { "epoch": 0.0015771028037383178, "grad_norm": 25.332595825195312, "learning_rate": 1.011673151750973e-06, "loss": 3.2791, "step": 27 }, { "epoch": 0.0016355140186915889, "grad_norm": 30.250402450561523, "learning_rate": 1.0505836575875487e-06, "loss": 3.5143, "step": 28 }, { "epoch": 0.0016939252336448597, "grad_norm": 18.312883377075195, "learning_rate": 1.0894941634241247e-06, "loss": 2.9457, "step": 29 }, { "epoch": 0.0017523364485981308, "grad_norm": 19.0147647857666, "learning_rate": 1.1284046692607004e-06, "loss": 2.9594, "step": 30 }, { "epoch": 0.001810747663551402, "grad_norm": 16.256895065307617, "learning_rate": 1.1673151750972764e-06, "loss": 2.4716, "step": 31 }, { "epoch": 0.001869158878504673, "grad_norm": 24.22671890258789, "learning_rate": 1.2062256809338523e-06, "loss": 3.6266, "step": 32 }, { "epoch": 0.0019275700934579438, "grad_norm": 14.252118110656738, "learning_rate": 1.245136186770428e-06, "loss": 2.9769, "step": 33 }, { "epoch": 0.001985981308411215, "grad_norm": 17.749858856201172, "learning_rate": 1.2840466926070038e-06, "loss": 3.1564, "step": 34 }, { "epoch": 0.0020443925233644858, "grad_norm": 14.896815299987793, "learning_rate": 1.32295719844358e-06, "loss": 2.9778, "step": 35 }, { "epoch": 0.002102803738317757, "grad_norm": 13.463164329528809, "learning_rate": 1.3618677042801557e-06, "loss": 2.969, "step": 36 }, { "epoch": 0.002161214953271028, "grad_norm": 9.797528266906738, "learning_rate": 1.4007782101167317e-06, "loss": 2.3151, "step": 37 }, { "epoch": 0.0022196261682242992, "grad_norm": 11.281667709350586, "learning_rate": 1.4396887159533074e-06, "loss": 2.8371, "step": 38 }, { "epoch": 0.00227803738317757, "grad_norm": 12.921883583068848, "learning_rate": 1.4785992217898834e-06, "loss": 3.2094, "step": 39 }, { "epoch": 0.002336448598130841, "grad_norm": 6.257059097290039, "learning_rate": 1.5175097276264591e-06, "loss": 1.9972, "step": 40 }, { "epoch": 0.0023948598130841122, "grad_norm": 5.924483776092529, "learning_rate": 1.556420233463035e-06, "loss": 2.401, "step": 41 }, { "epoch": 0.002453271028037383, "grad_norm": 5.507547855377197, "learning_rate": 1.5953307392996108e-06, "loss": 2.3466, "step": 42 }, { "epoch": 0.0025116822429906544, "grad_norm": 6.737466335296631, "learning_rate": 1.634241245136187e-06, "loss": 2.528, "step": 43 }, { "epoch": 0.0025700934579439253, "grad_norm": 5.491589546203613, "learning_rate": 1.6731517509727627e-06, "loss": 2.5077, "step": 44 }, { "epoch": 0.002628504672897196, "grad_norm": 5.353943824768066, "learning_rate": 1.7120622568093387e-06, "loss": 2.5695, "step": 45 }, { "epoch": 0.0026869158878504674, "grad_norm": 5.043283939361572, "learning_rate": 1.7509727626459144e-06, "loss": 2.5556, "step": 46 }, { "epoch": 0.0027453271028037383, "grad_norm": 6.1692609786987305, "learning_rate": 1.7898832684824904e-06, "loss": 2.9989, "step": 47 }, { "epoch": 0.002803738317757009, "grad_norm": 4.435984134674072, "learning_rate": 1.8287937743190661e-06, "loss": 2.573, "step": 48 }, { "epoch": 0.0028621495327102804, "grad_norm": 4.688198089599609, "learning_rate": 1.8677042801556423e-06, "loss": 2.5361, "step": 49 }, { "epoch": 0.0029205607476635513, "grad_norm": 4.864237308502197, "learning_rate": 1.906614785992218e-06, "loss": 2.365, "step": 50 }, { "epoch": 0.0029789719626168226, "grad_norm": 4.092289924621582, "learning_rate": 1.945525291828794e-06, "loss": 1.9493, "step": 51 }, { "epoch": 0.0030373831775700934, "grad_norm": 2.666468381881714, "learning_rate": 1.9844357976653695e-06, "loss": 1.5999, "step": 52 }, { "epoch": 0.0030957943925233643, "grad_norm": 4.792476654052734, "learning_rate": 2.023346303501946e-06, "loss": 2.4831, "step": 53 }, { "epoch": 0.0031542056074766356, "grad_norm": 4.213903427124023, "learning_rate": 2.0622568093385214e-06, "loss": 2.6076, "step": 54 }, { "epoch": 0.0032126168224299065, "grad_norm": 2.6928203105926514, "learning_rate": 2.1011673151750974e-06, "loss": 2.3025, "step": 55 }, { "epoch": 0.0032710280373831778, "grad_norm": 3.0561423301696777, "learning_rate": 2.1400778210116734e-06, "loss": 2.0095, "step": 56 }, { "epoch": 0.0033294392523364486, "grad_norm": 2.419400691986084, "learning_rate": 2.1789883268482493e-06, "loss": 2.0477, "step": 57 }, { "epoch": 0.0033878504672897195, "grad_norm": 3.531447172164917, "learning_rate": 2.217898832684825e-06, "loss": 2.7264, "step": 58 }, { "epoch": 0.0034462616822429908, "grad_norm": 2.129260540008545, "learning_rate": 2.256809338521401e-06, "loss": 1.9608, "step": 59 }, { "epoch": 0.0035046728971962616, "grad_norm": 2.8845431804656982, "learning_rate": 2.2957198443579768e-06, "loss": 2.3001, "step": 60 }, { "epoch": 0.0035630841121495325, "grad_norm": 2.5538947582244873, "learning_rate": 2.3346303501945527e-06, "loss": 2.148, "step": 61 }, { "epoch": 0.003621495327102804, "grad_norm": 2.140758752822876, "learning_rate": 2.3735408560311287e-06, "loss": 1.9543, "step": 62 }, { "epoch": 0.0036799065420560747, "grad_norm": 2.7994370460510254, "learning_rate": 2.4124513618677046e-06, "loss": 2.6891, "step": 63 }, { "epoch": 0.003738317757009346, "grad_norm": 2.152406930923462, "learning_rate": 2.45136186770428e-06, "loss": 2.2818, "step": 64 }, { "epoch": 0.003796728971962617, "grad_norm": 2.0455806255340576, "learning_rate": 2.490272373540856e-06, "loss": 2.2763, "step": 65 }, { "epoch": 0.0038551401869158877, "grad_norm": 2.292008399963379, "learning_rate": 2.529182879377432e-06, "loss": 2.5195, "step": 66 }, { "epoch": 0.003913551401869159, "grad_norm": 2.067502498626709, "learning_rate": 2.5680933852140076e-06, "loss": 2.2382, "step": 67 }, { "epoch": 0.00397196261682243, "grad_norm": 2.152416706085205, "learning_rate": 2.607003891050584e-06, "loss": 2.5511, "step": 68 }, { "epoch": 0.004030373831775701, "grad_norm": 1.9699448347091675, "learning_rate": 2.64591439688716e-06, "loss": 1.6176, "step": 69 }, { "epoch": 0.0040887850467289715, "grad_norm": 1.9851597547531128, "learning_rate": 2.6848249027237355e-06, "loss": 2.1491, "step": 70 }, { "epoch": 0.004147196261682243, "grad_norm": 1.6645936965942383, "learning_rate": 2.7237354085603114e-06, "loss": 1.8716, "step": 71 }, { "epoch": 0.004205607476635514, "grad_norm": 1.9071528911590576, "learning_rate": 2.7626459143968874e-06, "loss": 1.8516, "step": 72 }, { "epoch": 0.004264018691588785, "grad_norm": 2.7870047092437744, "learning_rate": 2.8015564202334633e-06, "loss": 2.8142, "step": 73 }, { "epoch": 0.004322429906542056, "grad_norm": 2.0872249603271484, "learning_rate": 2.840466926070039e-06, "loss": 2.1623, "step": 74 }, { "epoch": 0.004380841121495327, "grad_norm": 1.911794662475586, "learning_rate": 2.879377431906615e-06, "loss": 1.9305, "step": 75 }, { "epoch": 0.0044392523364485985, "grad_norm": 2.5954651832580566, "learning_rate": 2.918287937743191e-06, "loss": 2.6115, "step": 76 }, { "epoch": 0.004497663551401869, "grad_norm": 1.8730735778808594, "learning_rate": 2.9571984435797667e-06, "loss": 1.99, "step": 77 }, { "epoch": 0.00455607476635514, "grad_norm": 1.7896742820739746, "learning_rate": 2.9961089494163427e-06, "loss": 2.0182, "step": 78 }, { "epoch": 0.004614485981308411, "grad_norm": 2.1686785221099854, "learning_rate": 3.0350194552529182e-06, "loss": 2.2209, "step": 79 }, { "epoch": 0.004672897196261682, "grad_norm": 2.3083789348602295, "learning_rate": 3.0739299610894946e-06, "loss": 2.4084, "step": 80 }, { "epoch": 0.004731308411214954, "grad_norm": 2.032923698425293, "learning_rate": 3.11284046692607e-06, "loss": 1.6149, "step": 81 }, { "epoch": 0.0047897196261682245, "grad_norm": 2.38382887840271, "learning_rate": 3.151750972762646e-06, "loss": 1.9926, "step": 82 }, { "epoch": 0.004848130841121495, "grad_norm": 2.2879409790039062, "learning_rate": 3.1906614785992216e-06, "loss": 2.2067, "step": 83 }, { "epoch": 0.004906542056074766, "grad_norm": 1.9808266162872314, "learning_rate": 3.229571984435798e-06, "loss": 1.8174, "step": 84 }, { "epoch": 0.004964953271028037, "grad_norm": 2.465371608734131, "learning_rate": 3.268482490272374e-06, "loss": 2.3992, "step": 85 }, { "epoch": 0.005023364485981309, "grad_norm": 2.1129279136657715, "learning_rate": 3.3073929961089495e-06, "loss": 2.0672, "step": 86 }, { "epoch": 0.00508177570093458, "grad_norm": 2.369851589202881, "learning_rate": 3.3463035019455255e-06, "loss": 2.1381, "step": 87 }, { "epoch": 0.0051401869158878505, "grad_norm": 2.2727296352386475, "learning_rate": 3.385214007782102e-06, "loss": 1.9156, "step": 88 }, { "epoch": 0.005198598130841121, "grad_norm": 3.135746955871582, "learning_rate": 3.4241245136186774e-06, "loss": 1.8125, "step": 89 }, { "epoch": 0.005257009345794392, "grad_norm": 2.346846103668213, "learning_rate": 3.4630350194552533e-06, "loss": 1.9368, "step": 90 }, { "epoch": 0.005315420560747664, "grad_norm": 2.5220091342926025, "learning_rate": 3.501945525291829e-06, "loss": 1.9957, "step": 91 }, { "epoch": 0.005373831775700935, "grad_norm": 2.434330940246582, "learning_rate": 3.5408560311284052e-06, "loss": 2.1891, "step": 92 }, { "epoch": 0.005432242990654206, "grad_norm": 2.8450565338134766, "learning_rate": 3.5797665369649808e-06, "loss": 2.1789, "step": 93 }, { "epoch": 0.0054906542056074766, "grad_norm": 2.723118782043457, "learning_rate": 3.6186770428015567e-06, "loss": 2.1093, "step": 94 }, { "epoch": 0.005549065420560747, "grad_norm": 2.7940146923065186, "learning_rate": 3.6575875486381323e-06, "loss": 1.9224, "step": 95 }, { "epoch": 0.005607476635514018, "grad_norm": 2.4439799785614014, "learning_rate": 3.6964980544747086e-06, "loss": 1.805, "step": 96 }, { "epoch": 0.00566588785046729, "grad_norm": 2.3494460582733154, "learning_rate": 3.7354085603112846e-06, "loss": 1.7407, "step": 97 }, { "epoch": 0.005724299065420561, "grad_norm": 2.268099308013916, "learning_rate": 3.77431906614786e-06, "loss": 1.7342, "step": 98 }, { "epoch": 0.005782710280373832, "grad_norm": 2.7889764308929443, "learning_rate": 3.813229571984436e-06, "loss": 1.8445, "step": 99 }, { "epoch": 0.005841121495327103, "grad_norm": 1.861730933189392, "learning_rate": 3.8521400778210125e-06, "loss": 1.4596, "step": 100 }, { "epoch": 0.0058995327102803734, "grad_norm": 2.376873254776001, "learning_rate": 3.891050583657588e-06, "loss": 1.7919, "step": 101 }, { "epoch": 0.005957943925233645, "grad_norm": 2.4196879863739014, "learning_rate": 3.9299610894941635e-06, "loss": 1.5392, "step": 102 }, { "epoch": 0.006016355140186916, "grad_norm": 3.1383919715881348, "learning_rate": 3.968871595330739e-06, "loss": 2.2386, "step": 103 }, { "epoch": 0.006074766355140187, "grad_norm": 3.176295280456543, "learning_rate": 4.0077821011673154e-06, "loss": 2.051, "step": 104 }, { "epoch": 0.006133177570093458, "grad_norm": 2.5430245399475098, "learning_rate": 4.046692607003892e-06, "loss": 1.7581, "step": 105 }, { "epoch": 0.006191588785046729, "grad_norm": 2.467442512512207, "learning_rate": 4.085603112840467e-06, "loss": 1.6097, "step": 106 }, { "epoch": 0.00625, "grad_norm": 2.5841660499572754, "learning_rate": 4.124513618677043e-06, "loss": 1.5197, "step": 107 }, { "epoch": 0.006308411214953271, "grad_norm": 2.9651458263397217, "learning_rate": 4.163424124513619e-06, "loss": 1.7719, "step": 108 }, { "epoch": 0.006366822429906542, "grad_norm": 3.029406785964966, "learning_rate": 4.202334630350195e-06, "loss": 1.859, "step": 109 }, { "epoch": 0.006425233644859813, "grad_norm": 2.5220563411712646, "learning_rate": 4.24124513618677e-06, "loss": 1.544, "step": 110 }, { "epoch": 0.006483644859813084, "grad_norm": 2.7453689575195312, "learning_rate": 4.280155642023347e-06, "loss": 1.6488, "step": 111 }, { "epoch": 0.0065420560747663555, "grad_norm": 2.480900764465332, "learning_rate": 4.319066147859923e-06, "loss": 1.6881, "step": 112 }, { "epoch": 0.006600467289719626, "grad_norm": 2.4640634059906006, "learning_rate": 4.357976653696499e-06, "loss": 1.6866, "step": 113 }, { "epoch": 0.006658878504672897, "grad_norm": 2.5860795974731445, "learning_rate": 4.396887159533074e-06, "loss": 1.6759, "step": 114 }, { "epoch": 0.006717289719626168, "grad_norm": 2.4451327323913574, "learning_rate": 4.43579766536965e-06, "loss": 1.6344, "step": 115 }, { "epoch": 0.006775700934579439, "grad_norm": 2.3526103496551514, "learning_rate": 4.474708171206226e-06, "loss": 1.5083, "step": 116 }, { "epoch": 0.006834112149532711, "grad_norm": 2.030806303024292, "learning_rate": 4.513618677042802e-06, "loss": 1.504, "step": 117 }, { "epoch": 0.0068925233644859816, "grad_norm": 2.547431707382202, "learning_rate": 4.552529182879378e-06, "loss": 1.6034, "step": 118 }, { "epoch": 0.006950934579439252, "grad_norm": 2.03373122215271, "learning_rate": 4.5914396887159535e-06, "loss": 1.4152, "step": 119 }, { "epoch": 0.007009345794392523, "grad_norm": 1.8380388021469116, "learning_rate": 4.63035019455253e-06, "loss": 1.539, "step": 120 }, { "epoch": 0.007067757009345794, "grad_norm": 2.606928586959839, "learning_rate": 4.669260700389105e-06, "loss": 1.8779, "step": 121 }, { "epoch": 0.007126168224299065, "grad_norm": 2.1764094829559326, "learning_rate": 4.708171206225681e-06, "loss": 1.5018, "step": 122 }, { "epoch": 0.007184579439252337, "grad_norm": 2.1749391555786133, "learning_rate": 4.747081712062257e-06, "loss": 1.5416, "step": 123 }, { "epoch": 0.007242990654205608, "grad_norm": 2.2552244663238525, "learning_rate": 4.785992217898833e-06, "loss": 1.5472, "step": 124 }, { "epoch": 0.0073014018691588784, "grad_norm": 2.097898483276367, "learning_rate": 4.824902723735409e-06, "loss": 1.304, "step": 125 }, { "epoch": 0.007359813084112149, "grad_norm": 2.2080564498901367, "learning_rate": 4.863813229571985e-06, "loss": 1.4705, "step": 126 }, { "epoch": 0.00741822429906542, "grad_norm": 1.834836721420288, "learning_rate": 4.90272373540856e-06, "loss": 1.3439, "step": 127 }, { "epoch": 0.007476635514018692, "grad_norm": 1.8449205160140991, "learning_rate": 4.941634241245137e-06, "loss": 1.51, "step": 128 }, { "epoch": 0.007535046728971963, "grad_norm": 2.0409204959869385, "learning_rate": 4.980544747081712e-06, "loss": 1.3389, "step": 129 }, { "epoch": 0.007593457943925234, "grad_norm": 2.070204019546509, "learning_rate": 5.019455252918289e-06, "loss": 1.2992, "step": 130 }, { "epoch": 0.0076518691588785045, "grad_norm": 2.171759843826294, "learning_rate": 5.058365758754864e-06, "loss": 1.5914, "step": 131 }, { "epoch": 0.007710280373831775, "grad_norm": 1.7592191696166992, "learning_rate": 5.09727626459144e-06, "loss": 1.5135, "step": 132 }, { "epoch": 0.007768691588785047, "grad_norm": 1.8720201253890991, "learning_rate": 5.136186770428015e-06, "loss": 1.462, "step": 133 }, { "epoch": 0.007827102803738318, "grad_norm": 1.7488421201705933, "learning_rate": 5.175097276264592e-06, "loss": 1.3032, "step": 134 }, { "epoch": 0.007885514018691588, "grad_norm": 1.5655500888824463, "learning_rate": 5.214007782101168e-06, "loss": 1.3933, "step": 135 }, { "epoch": 0.00794392523364486, "grad_norm": 1.9015209674835205, "learning_rate": 5.2529182879377435e-06, "loss": 1.5979, "step": 136 }, { "epoch": 0.008002336448598131, "grad_norm": 1.9914659261703491, "learning_rate": 5.29182879377432e-06, "loss": 1.6797, "step": 137 }, { "epoch": 0.008060747663551401, "grad_norm": 1.691657304763794, "learning_rate": 5.330739299610895e-06, "loss": 1.1212, "step": 138 }, { "epoch": 0.008119158878504673, "grad_norm": 1.3386796712875366, "learning_rate": 5.369649805447471e-06, "loss": 1.191, "step": 139 }, { "epoch": 0.008177570093457943, "grad_norm": 1.77560293674469, "learning_rate": 5.4085603112840465e-06, "loss": 1.5073, "step": 140 }, { "epoch": 0.008235981308411215, "grad_norm": 1.6654335260391235, "learning_rate": 5.447470817120623e-06, "loss": 1.4199, "step": 141 }, { "epoch": 0.008294392523364487, "grad_norm": 2.3191192150115967, "learning_rate": 5.486381322957199e-06, "loss": 1.7325, "step": 142 }, { "epoch": 0.008352803738317757, "grad_norm": 1.8757704496383667, "learning_rate": 5.525291828793775e-06, "loss": 1.4858, "step": 143 }, { "epoch": 0.008411214953271028, "grad_norm": 1.5209918022155762, "learning_rate": 5.564202334630351e-06, "loss": 1.5523, "step": 144 }, { "epoch": 0.008469626168224298, "grad_norm": 1.6074031591415405, "learning_rate": 5.603112840466927e-06, "loss": 1.4046, "step": 145 }, { "epoch": 0.00852803738317757, "grad_norm": 1.6176358461380005, "learning_rate": 5.642023346303502e-06, "loss": 1.3248, "step": 146 }, { "epoch": 0.008586448598130842, "grad_norm": 1.6601272821426392, "learning_rate": 5.680933852140078e-06, "loss": 1.3334, "step": 147 }, { "epoch": 0.008644859813084112, "grad_norm": 1.2782461643218994, "learning_rate": 5.719844357976654e-06, "loss": 1.226, "step": 148 }, { "epoch": 0.008703271028037383, "grad_norm": 1.6805312633514404, "learning_rate": 5.75875486381323e-06, "loss": 1.4201, "step": 149 }, { "epoch": 0.008761682242990653, "grad_norm": 1.6510714292526245, "learning_rate": 5.797665369649806e-06, "loss": 1.3637, "step": 150 }, { "epoch": 0.008820093457943925, "grad_norm": 1.9411746263504028, "learning_rate": 5.836575875486382e-06, "loss": 1.5592, "step": 151 }, { "epoch": 0.008878504672897197, "grad_norm": 1.2212388515472412, "learning_rate": 5.875486381322958e-06, "loss": 1.2587, "step": 152 }, { "epoch": 0.008936915887850467, "grad_norm": 1.5524768829345703, "learning_rate": 5.9143968871595335e-06, "loss": 1.5344, "step": 153 }, { "epoch": 0.008995327102803739, "grad_norm": 1.4386409521102905, "learning_rate": 5.953307392996109e-06, "loss": 1.485, "step": 154 }, { "epoch": 0.009053738317757009, "grad_norm": 1.3831202983856201, "learning_rate": 5.992217898832685e-06, "loss": 1.3201, "step": 155 }, { "epoch": 0.00911214953271028, "grad_norm": 1.3753271102905273, "learning_rate": 6.031128404669261e-06, "loss": 1.2795, "step": 156 }, { "epoch": 0.009170560747663552, "grad_norm": 1.607718825340271, "learning_rate": 6.0700389105058364e-06, "loss": 1.47, "step": 157 }, { "epoch": 0.009228971962616822, "grad_norm": 1.317451000213623, "learning_rate": 6.108949416342414e-06, "loss": 1.3507, "step": 158 }, { "epoch": 0.009287383177570094, "grad_norm": 1.714583396911621, "learning_rate": 6.147859922178989e-06, "loss": 1.5826, "step": 159 }, { "epoch": 0.009345794392523364, "grad_norm": 2.0219550132751465, "learning_rate": 6.186770428015565e-06, "loss": 1.6471, "step": 160 }, { "epoch": 0.009404205607476636, "grad_norm": 1.2225918769836426, "learning_rate": 6.22568093385214e-06, "loss": 1.3999, "step": 161 }, { "epoch": 0.009462616822429907, "grad_norm": 1.7326321601867676, "learning_rate": 6.264591439688717e-06, "loss": 1.5223, "step": 162 }, { "epoch": 0.009521028037383177, "grad_norm": 1.353668212890625, "learning_rate": 6.303501945525292e-06, "loss": 1.3163, "step": 163 }, { "epoch": 0.009579439252336449, "grad_norm": 1.6277002096176147, "learning_rate": 6.342412451361868e-06, "loss": 1.3562, "step": 164 }, { "epoch": 0.009637850467289719, "grad_norm": 1.6317918300628662, "learning_rate": 6.381322957198443e-06, "loss": 1.6397, "step": 165 }, { "epoch": 0.00969626168224299, "grad_norm": 1.5360376834869385, "learning_rate": 6.4202334630350205e-06, "loss": 1.4557, "step": 166 }, { "epoch": 0.009754672897196262, "grad_norm": 1.4034239053726196, "learning_rate": 6.459143968871596e-06, "loss": 1.5142, "step": 167 }, { "epoch": 0.009813084112149532, "grad_norm": 1.575932502746582, "learning_rate": 6.4980544747081715e-06, "loss": 1.625, "step": 168 }, { "epoch": 0.009871495327102804, "grad_norm": 1.4946646690368652, "learning_rate": 6.536964980544748e-06, "loss": 1.4705, "step": 169 }, { "epoch": 0.009929906542056074, "grad_norm": 1.336839199066162, "learning_rate": 6.5758754863813235e-06, "loss": 1.2553, "step": 170 }, { "epoch": 0.009988317757009346, "grad_norm": 1.6631031036376953, "learning_rate": 6.614785992217899e-06, "loss": 1.3612, "step": 171 }, { "epoch": 0.010046728971962618, "grad_norm": 1.4717555046081543, "learning_rate": 6.6536964980544745e-06, "loss": 1.3404, "step": 172 }, { "epoch": 0.010105140186915888, "grad_norm": 1.3945587873458862, "learning_rate": 6.692607003891051e-06, "loss": 1.5069, "step": 173 }, { "epoch": 0.01016355140186916, "grad_norm": 1.7516685724258423, "learning_rate": 6.731517509727627e-06, "loss": 1.4621, "step": 174 }, { "epoch": 0.01022196261682243, "grad_norm": 1.6674896478652954, "learning_rate": 6.770428015564204e-06, "loss": 1.68, "step": 175 }, { "epoch": 0.010280373831775701, "grad_norm": 1.3589872121810913, "learning_rate": 6.809338521400779e-06, "loss": 1.3595, "step": 176 }, { "epoch": 0.010338785046728973, "grad_norm": 1.480765461921692, "learning_rate": 6.848249027237355e-06, "loss": 1.3786, "step": 177 }, { "epoch": 0.010397196261682243, "grad_norm": 1.6068288087844849, "learning_rate": 6.88715953307393e-06, "loss": 1.4249, "step": 178 }, { "epoch": 0.010455607476635514, "grad_norm": 1.1281330585479736, "learning_rate": 6.926070038910507e-06, "loss": 1.1455, "step": 179 }, { "epoch": 0.010514018691588784, "grad_norm": 1.5735583305358887, "learning_rate": 6.964980544747082e-06, "loss": 1.5929, "step": 180 }, { "epoch": 0.010572429906542056, "grad_norm": 1.6554112434387207, "learning_rate": 7.003891050583658e-06, "loss": 1.6526, "step": 181 }, { "epoch": 0.010630841121495328, "grad_norm": 3.6226673126220703, "learning_rate": 7.042801556420235e-06, "loss": 1.403, "step": 182 }, { "epoch": 0.010689252336448598, "grad_norm": 1.3957520723342896, "learning_rate": 7.0817120622568105e-06, "loss": 1.1883, "step": 183 }, { "epoch": 0.01074766355140187, "grad_norm": 1.1640360355377197, "learning_rate": 7.120622568093386e-06, "loss": 1.5054, "step": 184 }, { "epoch": 0.01080607476635514, "grad_norm": 1.363552451133728, "learning_rate": 7.1595330739299615e-06, "loss": 1.4603, "step": 185 }, { "epoch": 0.010864485981308411, "grad_norm": 1.397360920906067, "learning_rate": 7.198443579766538e-06, "loss": 1.5273, "step": 186 }, { "epoch": 0.010922897196261683, "grad_norm": 1.4758033752441406, "learning_rate": 7.2373540856031134e-06, "loss": 1.4009, "step": 187 }, { "epoch": 0.010981308411214953, "grad_norm": 1.2147091627120972, "learning_rate": 7.276264591439689e-06, "loss": 1.5511, "step": 188 }, { "epoch": 0.011039719626168225, "grad_norm": 1.3872100114822388, "learning_rate": 7.3151750972762645e-06, "loss": 1.2013, "step": 189 }, { "epoch": 0.011098130841121495, "grad_norm": 1.3288483619689941, "learning_rate": 7.354085603112842e-06, "loss": 1.5317, "step": 190 }, { "epoch": 0.011156542056074767, "grad_norm": 1.7791733741760254, "learning_rate": 7.392996108949417e-06, "loss": 1.2498, "step": 191 }, { "epoch": 0.011214953271028037, "grad_norm": 1.5582916736602783, "learning_rate": 7.431906614785993e-06, "loss": 1.4055, "step": 192 }, { "epoch": 0.011273364485981308, "grad_norm": 1.4596476554870605, "learning_rate": 7.470817120622569e-06, "loss": 1.4265, "step": 193 }, { "epoch": 0.01133177570093458, "grad_norm": 1.568749189376831, "learning_rate": 7.509727626459145e-06, "loss": 1.3247, "step": 194 }, { "epoch": 0.01139018691588785, "grad_norm": 1.4087659120559692, "learning_rate": 7.54863813229572e-06, "loss": 1.2918, "step": 195 }, { "epoch": 0.011448598130841122, "grad_norm": 2.3633508682250977, "learning_rate": 7.587548638132296e-06, "loss": 1.2101, "step": 196 }, { "epoch": 0.011507009345794392, "grad_norm": 1.637161135673523, "learning_rate": 7.626459143968872e-06, "loss": 1.2711, "step": 197 }, { "epoch": 0.011565420560747663, "grad_norm": 2.0802724361419678, "learning_rate": 7.665369649805449e-06, "loss": 1.3342, "step": 198 }, { "epoch": 0.011623831775700935, "grad_norm": 1.1647957563400269, "learning_rate": 7.704280155642025e-06, "loss": 1.2003, "step": 199 }, { "epoch": 0.011682242990654205, "grad_norm": 2.063438653945923, "learning_rate": 7.7431906614786e-06, "loss": 1.4656, "step": 200 }, { "epoch": 0.011740654205607477, "grad_norm": 2.1548383235931396, "learning_rate": 7.782101167315176e-06, "loss": 1.4023, "step": 201 }, { "epoch": 0.011799065420560747, "grad_norm": 1.5088032484054565, "learning_rate": 7.821011673151752e-06, "loss": 1.3871, "step": 202 }, { "epoch": 0.011857476635514019, "grad_norm": 1.7542258501052856, "learning_rate": 7.859922178988327e-06, "loss": 1.4184, "step": 203 }, { "epoch": 0.01191588785046729, "grad_norm": 1.2683261632919312, "learning_rate": 7.898832684824903e-06, "loss": 1.0874, "step": 204 }, { "epoch": 0.01197429906542056, "grad_norm": 1.5747392177581787, "learning_rate": 7.937743190661478e-06, "loss": 1.401, "step": 205 }, { "epoch": 0.012032710280373832, "grad_norm": 1.1827270984649658, "learning_rate": 7.976653696498056e-06, "loss": 1.2878, "step": 206 }, { "epoch": 0.012091121495327102, "grad_norm": 1.9290642738342285, "learning_rate": 8.015564202334631e-06, "loss": 1.168, "step": 207 }, { "epoch": 0.012149532710280374, "grad_norm": 1.9174387454986572, "learning_rate": 8.054474708171207e-06, "loss": 1.4566, "step": 208 }, { "epoch": 0.012207943925233646, "grad_norm": 1.539029598236084, "learning_rate": 8.093385214007784e-06, "loss": 1.2569, "step": 209 }, { "epoch": 0.012266355140186916, "grad_norm": 2.3458385467529297, "learning_rate": 8.132295719844358e-06, "loss": 1.4921, "step": 210 }, { "epoch": 0.012324766355140187, "grad_norm": 2.053891658782959, "learning_rate": 8.171206225680935e-06, "loss": 1.3877, "step": 211 }, { "epoch": 0.012383177570093457, "grad_norm": 1.6933178901672363, "learning_rate": 8.21011673151751e-06, "loss": 1.3638, "step": 212 }, { "epoch": 0.012441588785046729, "grad_norm": 1.8378078937530518, "learning_rate": 8.249027237354086e-06, "loss": 1.2074, "step": 213 }, { "epoch": 0.0125, "grad_norm": 1.495967984199524, "learning_rate": 8.287937743190662e-06, "loss": 1.4036, "step": 214 }, { "epoch": 0.01255841121495327, "grad_norm": 1.9557543992996216, "learning_rate": 8.326848249027239e-06, "loss": 1.2179, "step": 215 }, { "epoch": 0.012616822429906542, "grad_norm": 1.33173668384552, "learning_rate": 8.365758754863815e-06, "loss": 1.4466, "step": 216 }, { "epoch": 0.012675233644859812, "grad_norm": 1.7046515941619873, "learning_rate": 8.40466926070039e-06, "loss": 1.5057, "step": 217 }, { "epoch": 0.012733644859813084, "grad_norm": 1.4211307764053345, "learning_rate": 8.443579766536966e-06, "loss": 1.2344, "step": 218 }, { "epoch": 0.012792056074766356, "grad_norm": 1.4582377672195435, "learning_rate": 8.48249027237354e-06, "loss": 1.3461, "step": 219 }, { "epoch": 0.012850467289719626, "grad_norm": 1.4100450277328491, "learning_rate": 8.521400778210117e-06, "loss": 0.9689, "step": 220 }, { "epoch": 0.012908878504672898, "grad_norm": 1.5575066804885864, "learning_rate": 8.560311284046693e-06, "loss": 1.5264, "step": 221 }, { "epoch": 0.012967289719626168, "grad_norm": 1.1709001064300537, "learning_rate": 8.59922178988327e-06, "loss": 1.4827, "step": 222 }, { "epoch": 0.01302570093457944, "grad_norm": 1.3787814378738403, "learning_rate": 8.638132295719846e-06, "loss": 1.3363, "step": 223 }, { "epoch": 0.013084112149532711, "grad_norm": 2.1408963203430176, "learning_rate": 8.677042801556421e-06, "loss": 1.4411, "step": 224 }, { "epoch": 0.013142523364485981, "grad_norm": 1.2695794105529785, "learning_rate": 8.715953307392997e-06, "loss": 1.3153, "step": 225 }, { "epoch": 0.013200934579439253, "grad_norm": 1.8964893817901611, "learning_rate": 8.754863813229572e-06, "loss": 1.3939, "step": 226 }, { "epoch": 0.013259345794392523, "grad_norm": 2.45070743560791, "learning_rate": 8.793774319066148e-06, "loss": 1.3994, "step": 227 }, { "epoch": 0.013317757009345794, "grad_norm": 1.324045181274414, "learning_rate": 8.832684824902725e-06, "loss": 1.4079, "step": 228 }, { "epoch": 0.013376168224299066, "grad_norm": 1.6450096368789673, "learning_rate": 8.8715953307393e-06, "loss": 1.2142, "step": 229 }, { "epoch": 0.013434579439252336, "grad_norm": 1.8283209800720215, "learning_rate": 8.910505836575877e-06, "loss": 1.284, "step": 230 }, { "epoch": 0.013492990654205608, "grad_norm": 2.0421133041381836, "learning_rate": 8.949416342412452e-06, "loss": 1.4154, "step": 231 }, { "epoch": 0.013551401869158878, "grad_norm": 1.4445379972457886, "learning_rate": 8.988326848249028e-06, "loss": 1.4071, "step": 232 }, { "epoch": 0.01360981308411215, "grad_norm": 1.6832178831100464, "learning_rate": 9.027237354085603e-06, "loss": 1.5048, "step": 233 }, { "epoch": 0.013668224299065421, "grad_norm": 2.351515769958496, "learning_rate": 9.06614785992218e-06, "loss": 1.3659, "step": 234 }, { "epoch": 0.013726635514018691, "grad_norm": 1.1647690534591675, "learning_rate": 9.105058365758756e-06, "loss": 1.483, "step": 235 }, { "epoch": 0.013785046728971963, "grad_norm": 1.1271331310272217, "learning_rate": 9.14396887159533e-06, "loss": 1.4025, "step": 236 }, { "epoch": 0.013843457943925233, "grad_norm": 1.3190566301345825, "learning_rate": 9.182879377431907e-06, "loss": 1.1103, "step": 237 }, { "epoch": 0.013901869158878505, "grad_norm": 1.649169921875, "learning_rate": 9.221789883268483e-06, "loss": 1.366, "step": 238 }, { "epoch": 0.013960280373831777, "grad_norm": 1.5920424461364746, "learning_rate": 9.26070038910506e-06, "loss": 1.5089, "step": 239 }, { "epoch": 0.014018691588785047, "grad_norm": 1.4876009225845337, "learning_rate": 9.299610894941634e-06, "loss": 1.4025, "step": 240 }, { "epoch": 0.014077102803738318, "grad_norm": 1.5066723823547363, "learning_rate": 9.33852140077821e-06, "loss": 1.3738, "step": 241 }, { "epoch": 0.014135514018691588, "grad_norm": 1.354206919670105, "learning_rate": 9.377431906614787e-06, "loss": 1.468, "step": 242 }, { "epoch": 0.01419392523364486, "grad_norm": 3.378335952758789, "learning_rate": 9.416342412451362e-06, "loss": 1.2453, "step": 243 }, { "epoch": 0.01425233644859813, "grad_norm": 1.3755742311477661, "learning_rate": 9.455252918287938e-06, "loss": 1.3787, "step": 244 }, { "epoch": 0.014310747663551402, "grad_norm": 1.5116811990737915, "learning_rate": 9.494163424124515e-06, "loss": 1.3733, "step": 245 }, { "epoch": 0.014369158878504673, "grad_norm": 1.6115128993988037, "learning_rate": 9.533073929961091e-06, "loss": 1.7103, "step": 246 }, { "epoch": 0.014427570093457943, "grad_norm": 2.052733898162842, "learning_rate": 9.571984435797666e-06, "loss": 1.2578, "step": 247 }, { "epoch": 0.014485981308411215, "grad_norm": 1.410198450088501, "learning_rate": 9.610894941634242e-06, "loss": 1.2574, "step": 248 }, { "epoch": 0.014544392523364485, "grad_norm": 1.193721890449524, "learning_rate": 9.649805447470818e-06, "loss": 1.0535, "step": 249 }, { "epoch": 0.014602803738317757, "grad_norm": 2.0893149375915527, "learning_rate": 9.688715953307393e-06, "loss": 1.3915, "step": 250 }, { "epoch": 0.014661214953271029, "grad_norm": 1.6133357286453247, "learning_rate": 9.72762645914397e-06, "loss": 1.466, "step": 251 }, { "epoch": 0.014719626168224299, "grad_norm": 1.5012151002883911, "learning_rate": 9.766536964980546e-06, "loss": 1.5305, "step": 252 }, { "epoch": 0.01477803738317757, "grad_norm": 1.4603248834609985, "learning_rate": 9.80544747081712e-06, "loss": 1.5139, "step": 253 }, { "epoch": 0.01483644859813084, "grad_norm": 2.360508918762207, "learning_rate": 9.844357976653699e-06, "loss": 1.4451, "step": 254 }, { "epoch": 0.014894859813084112, "grad_norm": 1.5451586246490479, "learning_rate": 9.883268482490273e-06, "loss": 1.4275, "step": 255 }, { "epoch": 0.014953271028037384, "grad_norm": 1.7690850496292114, "learning_rate": 9.92217898832685e-06, "loss": 1.4239, "step": 256 }, { "epoch": 0.015011682242990654, "grad_norm": 1.7625333070755005, "learning_rate": 9.961089494163424e-06, "loss": 1.0643, "step": 257 }, { "epoch": 0.015070093457943926, "grad_norm": 1.0751389265060425, "learning_rate": 1e-05, "loss": 1.2148, "step": 258 }, { "epoch": 0.015128504672897196, "grad_norm": 1.4937119483947754, "learning_rate": 1.0038910505836577e-05, "loss": 1.6281, "step": 259 }, { "epoch": 0.015186915887850467, "grad_norm": 2.01366925239563, "learning_rate": 1.0077821011673152e-05, "loss": 1.3039, "step": 260 }, { "epoch": 0.015245327102803739, "grad_norm": 1.4176101684570312, "learning_rate": 1.0116731517509728e-05, "loss": 1.3734, "step": 261 }, { "epoch": 0.015303738317757009, "grad_norm": 1.935526967048645, "learning_rate": 1.0155642023346303e-05, "loss": 1.3398, "step": 262 }, { "epoch": 0.01536214953271028, "grad_norm": 1.5547583103179932, "learning_rate": 1.019455252918288e-05, "loss": 1.2843, "step": 263 }, { "epoch": 0.01542056074766355, "grad_norm": 1.5880682468414307, "learning_rate": 1.0233463035019456e-05, "loss": 1.2135, "step": 264 }, { "epoch": 0.015478971962616822, "grad_norm": 1.8832465410232544, "learning_rate": 1.027237354085603e-05, "loss": 1.5121, "step": 265 }, { "epoch": 0.015537383177570094, "grad_norm": 2.2740108966827393, "learning_rate": 1.0311284046692607e-05, "loss": 1.347, "step": 266 }, { "epoch": 0.015595794392523364, "grad_norm": 1.3046505451202393, "learning_rate": 1.0350194552529185e-05, "loss": 1.4718, "step": 267 }, { "epoch": 0.015654205607476636, "grad_norm": 1.976101279258728, "learning_rate": 1.0389105058365761e-05, "loss": 1.3706, "step": 268 }, { "epoch": 0.015712616822429908, "grad_norm": 1.1528974771499634, "learning_rate": 1.0428015564202336e-05, "loss": 1.3795, "step": 269 }, { "epoch": 0.015771028037383176, "grad_norm": 1.955560564994812, "learning_rate": 1.0466926070038912e-05, "loss": 1.2765, "step": 270 }, { "epoch": 0.015829439252336448, "grad_norm": 1.7155479192733765, "learning_rate": 1.0505836575875487e-05, "loss": 1.5496, "step": 271 }, { "epoch": 0.01588785046728972, "grad_norm": 1.6262788772583008, "learning_rate": 1.0544747081712063e-05, "loss": 1.2337, "step": 272 }, { "epoch": 0.01594626168224299, "grad_norm": 2.9456138610839844, "learning_rate": 1.058365758754864e-05, "loss": 1.3865, "step": 273 }, { "epoch": 0.016004672897196263, "grad_norm": 1.2361648082733154, "learning_rate": 1.0622568093385214e-05, "loss": 1.3006, "step": 274 }, { "epoch": 0.01606308411214953, "grad_norm": 1.4322906732559204, "learning_rate": 1.066147859922179e-05, "loss": 1.1997, "step": 275 }, { "epoch": 0.016121495327102803, "grad_norm": 1.9512925148010254, "learning_rate": 1.0700389105058367e-05, "loss": 1.3357, "step": 276 }, { "epoch": 0.016179906542056074, "grad_norm": 1.4462569952011108, "learning_rate": 1.0739299610894942e-05, "loss": 1.2436, "step": 277 }, { "epoch": 0.016238317757009346, "grad_norm": 1.5476371049880981, "learning_rate": 1.0778210116731518e-05, "loss": 1.6555, "step": 278 }, { "epoch": 0.016296728971962618, "grad_norm": 2.4475715160369873, "learning_rate": 1.0817120622568093e-05, "loss": 1.4375, "step": 279 }, { "epoch": 0.016355140186915886, "grad_norm": 1.3418320417404175, "learning_rate": 1.085603112840467e-05, "loss": 1.3096, "step": 280 }, { "epoch": 0.016413551401869158, "grad_norm": 1.9926563501358032, "learning_rate": 1.0894941634241246e-05, "loss": 1.1159, "step": 281 }, { "epoch": 0.01647196261682243, "grad_norm": 2.4229423999786377, "learning_rate": 1.093385214007782e-05, "loss": 1.4155, "step": 282 }, { "epoch": 0.0165303738317757, "grad_norm": 1.551529884338379, "learning_rate": 1.0972762645914398e-05, "loss": 1.428, "step": 283 }, { "epoch": 0.016588785046728973, "grad_norm": 2.726527452468872, "learning_rate": 1.1011673151750975e-05, "loss": 1.6418, "step": 284 }, { "epoch": 0.01664719626168224, "grad_norm": 1.63002610206604, "learning_rate": 1.105058365758755e-05, "loss": 1.3447, "step": 285 }, { "epoch": 0.016705607476635513, "grad_norm": 2.208163022994995, "learning_rate": 1.1089494163424126e-05, "loss": 1.3448, "step": 286 }, { "epoch": 0.016764018691588785, "grad_norm": 1.8606606721878052, "learning_rate": 1.1128404669260702e-05, "loss": 1.5278, "step": 287 }, { "epoch": 0.016822429906542057, "grad_norm": 1.4196088314056396, "learning_rate": 1.1167315175097277e-05, "loss": 1.2239, "step": 288 }, { "epoch": 0.01688084112149533, "grad_norm": 1.2964590787887573, "learning_rate": 1.1206225680933853e-05, "loss": 1.1435, "step": 289 }, { "epoch": 0.016939252336448597, "grad_norm": 2.4436545372009277, "learning_rate": 1.124513618677043e-05, "loss": 1.3331, "step": 290 }, { "epoch": 0.01699766355140187, "grad_norm": 1.3741917610168457, "learning_rate": 1.1284046692607004e-05, "loss": 1.0998, "step": 291 }, { "epoch": 0.01705607476635514, "grad_norm": 1.9986906051635742, "learning_rate": 1.132295719844358e-05, "loss": 1.5164, "step": 292 }, { "epoch": 0.01711448598130841, "grad_norm": 1.2211792469024658, "learning_rate": 1.1361867704280155e-05, "loss": 1.5301, "step": 293 }, { "epoch": 0.017172897196261683, "grad_norm": 1.4970054626464844, "learning_rate": 1.1400778210116732e-05, "loss": 1.2841, "step": 294 }, { "epoch": 0.01723130841121495, "grad_norm": 1.7681095600128174, "learning_rate": 1.1439688715953308e-05, "loss": 1.1665, "step": 295 }, { "epoch": 0.017289719626168223, "grad_norm": 5.729231357574463, "learning_rate": 1.1478599221789883e-05, "loss": 1.2661, "step": 296 }, { "epoch": 0.017348130841121495, "grad_norm": 1.201163411140442, "learning_rate": 1.151750972762646e-05, "loss": 1.2795, "step": 297 }, { "epoch": 0.017406542056074767, "grad_norm": 1.6788537502288818, "learning_rate": 1.1556420233463036e-05, "loss": 1.3598, "step": 298 }, { "epoch": 0.01746495327102804, "grad_norm": 1.3787049055099487, "learning_rate": 1.1595330739299612e-05, "loss": 1.3357, "step": 299 }, { "epoch": 0.017523364485981307, "grad_norm": 1.6637828350067139, "learning_rate": 1.1634241245136188e-05, "loss": 1.2939, "step": 300 }, { "epoch": 0.01758177570093458, "grad_norm": 1.2494251728057861, "learning_rate": 1.1673151750972765e-05, "loss": 1.3484, "step": 301 }, { "epoch": 0.01764018691588785, "grad_norm": 2.8364076614379883, "learning_rate": 1.171206225680934e-05, "loss": 1.5266, "step": 302 }, { "epoch": 0.017698598130841122, "grad_norm": 1.286298155784607, "learning_rate": 1.1750972762645916e-05, "loss": 1.1431, "step": 303 }, { "epoch": 0.017757009345794394, "grad_norm": 2.454500436782837, "learning_rate": 1.1789883268482492e-05, "loss": 1.3135, "step": 304 }, { "epoch": 0.017815420560747662, "grad_norm": 9.060373306274414, "learning_rate": 1.1828793774319067e-05, "loss": 1.3167, "step": 305 }, { "epoch": 0.017873831775700934, "grad_norm": 2.257373809814453, "learning_rate": 1.1867704280155643e-05, "loss": 1.3415, "step": 306 }, { "epoch": 0.017932242990654206, "grad_norm": 1.4382643699645996, "learning_rate": 1.1906614785992218e-05, "loss": 1.1453, "step": 307 }, { "epoch": 0.017990654205607477, "grad_norm": 1.6143581867218018, "learning_rate": 1.1945525291828794e-05, "loss": 1.1998, "step": 308 }, { "epoch": 0.01804906542056075, "grad_norm": 3.2458577156066895, "learning_rate": 1.198443579766537e-05, "loss": 1.4582, "step": 309 }, { "epoch": 0.018107476635514017, "grad_norm": 1.6662765741348267, "learning_rate": 1.2023346303501945e-05, "loss": 1.2482, "step": 310 }, { "epoch": 0.01816588785046729, "grad_norm": 2.0883898735046387, "learning_rate": 1.2062256809338522e-05, "loss": 1.5248, "step": 311 }, { "epoch": 0.01822429906542056, "grad_norm": 2.252927303314209, "learning_rate": 1.2101167315175098e-05, "loss": 1.16, "step": 312 }, { "epoch": 0.018282710280373832, "grad_norm": 1.5365843772888184, "learning_rate": 1.2140077821011673e-05, "loss": 1.2407, "step": 313 }, { "epoch": 0.018341121495327104, "grad_norm": 2.658440113067627, "learning_rate": 1.217898832684825e-05, "loss": 1.2772, "step": 314 }, { "epoch": 0.018399532710280372, "grad_norm": 1.6580018997192383, "learning_rate": 1.2217898832684827e-05, "loss": 1.3921, "step": 315 }, { "epoch": 0.018457943925233644, "grad_norm": 1.910559892654419, "learning_rate": 1.2256809338521402e-05, "loss": 1.2245, "step": 316 }, { "epoch": 0.018516355140186916, "grad_norm": 1.8390958309173584, "learning_rate": 1.2295719844357978e-05, "loss": 1.1787, "step": 317 }, { "epoch": 0.018574766355140188, "grad_norm": 1.6221544742584229, "learning_rate": 1.2334630350194555e-05, "loss": 1.2082, "step": 318 }, { "epoch": 0.01863317757009346, "grad_norm": 1.8172858953475952, "learning_rate": 1.237354085603113e-05, "loss": 1.3644, "step": 319 }, { "epoch": 0.018691588785046728, "grad_norm": 2.592200517654419, "learning_rate": 1.2412451361867706e-05, "loss": 1.3922, "step": 320 }, { "epoch": 0.01875, "grad_norm": 1.2820597887039185, "learning_rate": 1.245136186770428e-05, "loss": 1.2658, "step": 321 }, { "epoch": 0.01880841121495327, "grad_norm": 2.2714462280273438, "learning_rate": 1.2490272373540857e-05, "loss": 1.2812, "step": 322 }, { "epoch": 0.018866822429906543, "grad_norm": 1.2072625160217285, "learning_rate": 1.2529182879377433e-05, "loss": 1.4477, "step": 323 }, { "epoch": 0.018925233644859814, "grad_norm": 1.6278235912322998, "learning_rate": 1.2568093385214008e-05, "loss": 1.6845, "step": 324 }, { "epoch": 0.018983644859813083, "grad_norm": 1.514339804649353, "learning_rate": 1.2607003891050584e-05, "loss": 1.435, "step": 325 }, { "epoch": 0.019042056074766354, "grad_norm": 2.1946423053741455, "learning_rate": 1.264591439688716e-05, "loss": 1.0509, "step": 326 }, { "epoch": 0.019100467289719626, "grad_norm": 1.5938775539398193, "learning_rate": 1.2684824902723735e-05, "loss": 1.496, "step": 327 }, { "epoch": 0.019158878504672898, "grad_norm": 1.772943377494812, "learning_rate": 1.2723735408560312e-05, "loss": 1.4643, "step": 328 }, { "epoch": 0.01921728971962617, "grad_norm": 2.160695791244507, "learning_rate": 1.2762645914396887e-05, "loss": 1.6076, "step": 329 }, { "epoch": 0.019275700934579438, "grad_norm": 1.4268856048583984, "learning_rate": 1.2801556420233463e-05, "loss": 1.3865, "step": 330 }, { "epoch": 0.01933411214953271, "grad_norm": 2.08288311958313, "learning_rate": 1.2840466926070041e-05, "loss": 1.2155, "step": 331 }, { "epoch": 0.01939252336448598, "grad_norm": 1.9151605367660522, "learning_rate": 1.2879377431906617e-05, "loss": 1.6097, "step": 332 }, { "epoch": 0.019450934579439253, "grad_norm": 1.8239128589630127, "learning_rate": 1.2918287937743192e-05, "loss": 1.2721, "step": 333 }, { "epoch": 0.019509345794392525, "grad_norm": 2.823413848876953, "learning_rate": 1.2957198443579768e-05, "loss": 1.3555, "step": 334 }, { "epoch": 0.019567757009345793, "grad_norm": 1.884080410003662, "learning_rate": 1.2996108949416343e-05, "loss": 1.2, "step": 335 }, { "epoch": 0.019626168224299065, "grad_norm": 3.3040966987609863, "learning_rate": 1.303501945525292e-05, "loss": 1.5164, "step": 336 }, { "epoch": 0.019684579439252337, "grad_norm": 3.3111798763275146, "learning_rate": 1.3073929961089496e-05, "loss": 1.4255, "step": 337 }, { "epoch": 0.01974299065420561, "grad_norm": 2.0908350944519043, "learning_rate": 1.311284046692607e-05, "loss": 1.3927, "step": 338 }, { "epoch": 0.01980140186915888, "grad_norm": 2.2945308685302734, "learning_rate": 1.3151750972762647e-05, "loss": 1.1519, "step": 339 }, { "epoch": 0.01985981308411215, "grad_norm": 1.8033912181854248, "learning_rate": 1.3190661478599223e-05, "loss": 1.2267, "step": 340 }, { "epoch": 0.01991822429906542, "grad_norm": 1.2134621143341064, "learning_rate": 1.3229571984435798e-05, "loss": 1.3395, "step": 341 }, { "epoch": 0.01997663551401869, "grad_norm": 1.4423414468765259, "learning_rate": 1.3268482490272374e-05, "loss": 1.325, "step": 342 }, { "epoch": 0.020035046728971963, "grad_norm": 1.8154739141464233, "learning_rate": 1.3307392996108949e-05, "loss": 1.3617, "step": 343 }, { "epoch": 0.020093457943925235, "grad_norm": 1.4677138328552246, "learning_rate": 1.3346303501945525e-05, "loss": 1.1254, "step": 344 }, { "epoch": 0.020151869158878503, "grad_norm": 1.9476221799850464, "learning_rate": 1.3385214007782102e-05, "loss": 1.5725, "step": 345 }, { "epoch": 0.020210280373831775, "grad_norm": 2.2834506034851074, "learning_rate": 1.3424124513618676e-05, "loss": 1.3957, "step": 346 }, { "epoch": 0.020268691588785047, "grad_norm": 2.0587236881256104, "learning_rate": 1.3463035019455255e-05, "loss": 1.4079, "step": 347 }, { "epoch": 0.02032710280373832, "grad_norm": 1.4780995845794678, "learning_rate": 1.3501945525291831e-05, "loss": 1.3314, "step": 348 }, { "epoch": 0.02038551401869159, "grad_norm": 3.1661059856414795, "learning_rate": 1.3540856031128407e-05, "loss": 1.2801, "step": 349 }, { "epoch": 0.02044392523364486, "grad_norm": 1.8320159912109375, "learning_rate": 1.3579766536964982e-05, "loss": 1.2609, "step": 350 }, { "epoch": 0.02050233644859813, "grad_norm": 3.699516773223877, "learning_rate": 1.3618677042801558e-05, "loss": 1.4896, "step": 351 }, { "epoch": 0.020560747663551402, "grad_norm": 1.4171041250228882, "learning_rate": 1.3657587548638133e-05, "loss": 1.159, "step": 352 }, { "epoch": 0.020619158878504674, "grad_norm": 4.355107307434082, "learning_rate": 1.369649805447471e-05, "loss": 1.1859, "step": 353 }, { "epoch": 0.020677570093457946, "grad_norm": 1.8509668111801147, "learning_rate": 1.3735408560311286e-05, "loss": 1.2373, "step": 354 }, { "epoch": 0.020735981308411214, "grad_norm": 3.3084685802459717, "learning_rate": 1.377431906614786e-05, "loss": 1.6294, "step": 355 }, { "epoch": 0.020794392523364486, "grad_norm": 2.4984209537506104, "learning_rate": 1.3813229571984437e-05, "loss": 1.2299, "step": 356 }, { "epoch": 0.020852803738317757, "grad_norm": 1.576987862586975, "learning_rate": 1.3852140077821013e-05, "loss": 1.1337, "step": 357 }, { "epoch": 0.02091121495327103, "grad_norm": 3.284095525741577, "learning_rate": 1.3891050583657588e-05, "loss": 1.1345, "step": 358 }, { "epoch": 0.0209696261682243, "grad_norm": 2.052417755126953, "learning_rate": 1.3929961089494164e-05, "loss": 1.1885, "step": 359 }, { "epoch": 0.02102803738317757, "grad_norm": 1.5221375226974487, "learning_rate": 1.3968871595330739e-05, "loss": 1.3396, "step": 360 }, { "epoch": 0.02108644859813084, "grad_norm": 3.1098389625549316, "learning_rate": 1.4007782101167315e-05, "loss": 1.3385, "step": 361 }, { "epoch": 0.021144859813084112, "grad_norm": 2.159512758255005, "learning_rate": 1.4046692607003892e-05, "loss": 1.2873, "step": 362 }, { "epoch": 0.021203271028037384, "grad_norm": 2.145066976547241, "learning_rate": 1.408560311284047e-05, "loss": 1.347, "step": 363 }, { "epoch": 0.021261682242990656, "grad_norm": 3.112206220626831, "learning_rate": 1.4124513618677045e-05, "loss": 1.4792, "step": 364 }, { "epoch": 0.021320093457943924, "grad_norm": 1.4213600158691406, "learning_rate": 1.4163424124513621e-05, "loss": 1.3269, "step": 365 }, { "epoch": 0.021378504672897196, "grad_norm": 3.0408082008361816, "learning_rate": 1.4202334630350196e-05, "loss": 1.1936, "step": 366 }, { "epoch": 0.021436915887850468, "grad_norm": 1.501939296722412, "learning_rate": 1.4241245136186772e-05, "loss": 1.2776, "step": 367 }, { "epoch": 0.02149532710280374, "grad_norm": 1.9699512720108032, "learning_rate": 1.4280155642023348e-05, "loss": 1.3906, "step": 368 }, { "epoch": 0.02155373831775701, "grad_norm": 1.9381736516952515, "learning_rate": 1.4319066147859923e-05, "loss": 1.286, "step": 369 }, { "epoch": 0.02161214953271028, "grad_norm": 1.4725713729858398, "learning_rate": 1.43579766536965e-05, "loss": 1.2344, "step": 370 }, { "epoch": 0.02167056074766355, "grad_norm": 1.8259637355804443, "learning_rate": 1.4396887159533076e-05, "loss": 1.2102, "step": 371 }, { "epoch": 0.021728971962616823, "grad_norm": 2.2772278785705566, "learning_rate": 1.443579766536965e-05, "loss": 1.3281, "step": 372 }, { "epoch": 0.021787383177570094, "grad_norm": 1.6024014949798584, "learning_rate": 1.4474708171206227e-05, "loss": 1.1856, "step": 373 }, { "epoch": 0.021845794392523366, "grad_norm": 2.0029098987579346, "learning_rate": 1.4513618677042802e-05, "loss": 1.3755, "step": 374 }, { "epoch": 0.021904205607476634, "grad_norm": 2.1500885486602783, "learning_rate": 1.4552529182879378e-05, "loss": 1.3635, "step": 375 }, { "epoch": 0.021962616822429906, "grad_norm": 1.6833380460739136, "learning_rate": 1.4591439688715954e-05, "loss": 1.0447, "step": 376 }, { "epoch": 0.022021028037383178, "grad_norm": 2.28104567527771, "learning_rate": 1.4630350194552529e-05, "loss": 1.3632, "step": 377 }, { "epoch": 0.02207943925233645, "grad_norm": 1.675765872001648, "learning_rate": 1.4669260700389105e-05, "loss": 1.3003, "step": 378 }, { "epoch": 0.022137850467289718, "grad_norm": 2.3115880489349365, "learning_rate": 1.4708171206225683e-05, "loss": 1.4994, "step": 379 }, { "epoch": 0.02219626168224299, "grad_norm": 1.7221922874450684, "learning_rate": 1.4747081712062258e-05, "loss": 1.3905, "step": 380 }, { "epoch": 0.02225467289719626, "grad_norm": 1.7255231142044067, "learning_rate": 1.4785992217898835e-05, "loss": 1.0083, "step": 381 }, { "epoch": 0.022313084112149533, "grad_norm": 2.138835906982422, "learning_rate": 1.4824902723735411e-05, "loss": 1.3436, "step": 382 }, { "epoch": 0.022371495327102805, "grad_norm": 1.6272398233413696, "learning_rate": 1.4863813229571986e-05, "loss": 1.0701, "step": 383 }, { "epoch": 0.022429906542056073, "grad_norm": 1.814086675643921, "learning_rate": 1.4902723735408562e-05, "loss": 1.3019, "step": 384 }, { "epoch": 0.022488317757009345, "grad_norm": 2.454840660095215, "learning_rate": 1.4941634241245138e-05, "loss": 1.3077, "step": 385 }, { "epoch": 0.022546728971962617, "grad_norm": 1.756789207458496, "learning_rate": 1.4980544747081713e-05, "loss": 1.1558, "step": 386 }, { "epoch": 0.02260514018691589, "grad_norm": 1.5280381441116333, "learning_rate": 1.501945525291829e-05, "loss": 1.0242, "step": 387 }, { "epoch": 0.02266355140186916, "grad_norm": 2.9307103157043457, "learning_rate": 1.5058365758754864e-05, "loss": 1.1325, "step": 388 }, { "epoch": 0.02272196261682243, "grad_norm": 1.6338396072387695, "learning_rate": 1.509727626459144e-05, "loss": 1.2186, "step": 389 }, { "epoch": 0.0227803738317757, "grad_norm": 2.986337661743164, "learning_rate": 1.5136186770428017e-05, "loss": 1.1924, "step": 390 }, { "epoch": 0.02283878504672897, "grad_norm": 1.4284594058990479, "learning_rate": 1.5175097276264592e-05, "loss": 1.4101, "step": 391 }, { "epoch": 0.022897196261682243, "grad_norm": 3.7522706985473633, "learning_rate": 1.5214007782101168e-05, "loss": 1.5536, "step": 392 }, { "epoch": 0.022955607476635515, "grad_norm": 1.8182909488677979, "learning_rate": 1.5252918287937744e-05, "loss": 1.2084, "step": 393 }, { "epoch": 0.023014018691588783, "grad_norm": 3.1324617862701416, "learning_rate": 1.529182879377432e-05, "loss": 1.144, "step": 394 }, { "epoch": 0.023072429906542055, "grad_norm": 3.282989978790283, "learning_rate": 1.5330739299610897e-05, "loss": 1.4681, "step": 395 }, { "epoch": 0.023130841121495327, "grad_norm": 1.5332355499267578, "learning_rate": 1.5369649805447472e-05, "loss": 1.2691, "step": 396 }, { "epoch": 0.0231892523364486, "grad_norm": 3.6967341899871826, "learning_rate": 1.540856031128405e-05, "loss": 1.4534, "step": 397 }, { "epoch": 0.02324766355140187, "grad_norm": 4.086015224456787, "learning_rate": 1.5447470817120625e-05, "loss": 1.4088, "step": 398 }, { "epoch": 0.02330607476635514, "grad_norm": 1.4478925466537476, "learning_rate": 1.54863813229572e-05, "loss": 1.3349, "step": 399 }, { "epoch": 0.02336448598130841, "grad_norm": 3.1488497257232666, "learning_rate": 1.5525291828793777e-05, "loss": 1.2738, "step": 400 }, { "epoch": 0.023422897196261682, "grad_norm": 1.9914350509643555, "learning_rate": 1.5564202334630352e-05, "loss": 1.1734, "step": 401 }, { "epoch": 0.023481308411214954, "grad_norm": 2.2396445274353027, "learning_rate": 1.5603112840466927e-05, "loss": 1.1309, "step": 402 }, { "epoch": 0.023539719626168226, "grad_norm": 1.8573297262191772, "learning_rate": 1.5642023346303505e-05, "loss": 1.2573, "step": 403 }, { "epoch": 0.023598130841121494, "grad_norm": 2.2725698947906494, "learning_rate": 1.568093385214008e-05, "loss": 1.3463, "step": 404 }, { "epoch": 0.023656542056074766, "grad_norm": 2.0452311038970947, "learning_rate": 1.5719844357976654e-05, "loss": 1.1513, "step": 405 }, { "epoch": 0.023714953271028037, "grad_norm": 2.026968002319336, "learning_rate": 1.575875486381323e-05, "loss": 1.388, "step": 406 }, { "epoch": 0.02377336448598131, "grad_norm": 2.1804707050323486, "learning_rate": 1.5797665369649807e-05, "loss": 1.3518, "step": 407 }, { "epoch": 0.02383177570093458, "grad_norm": 2.1957879066467285, "learning_rate": 1.583657587548638e-05, "loss": 1.0794, "step": 408 }, { "epoch": 0.02389018691588785, "grad_norm": 2.8645713329315186, "learning_rate": 1.5875486381322956e-05, "loss": 1.0776, "step": 409 }, { "epoch": 0.02394859813084112, "grad_norm": 2.4060170650482178, "learning_rate": 1.5914396887159534e-05, "loss": 1.2863, "step": 410 }, { "epoch": 0.024007009345794392, "grad_norm": 1.5507196187973022, "learning_rate": 1.5953307392996112e-05, "loss": 1.0093, "step": 411 }, { "epoch": 0.024065420560747664, "grad_norm": 2.855026960372925, "learning_rate": 1.5992217898832687e-05, "loss": 1.3006, "step": 412 }, { "epoch": 0.024123831775700936, "grad_norm": 1.4767861366271973, "learning_rate": 1.6031128404669262e-05, "loss": 1.305, "step": 413 }, { "epoch": 0.024182242990654204, "grad_norm": 2.9079930782318115, "learning_rate": 1.607003891050584e-05, "loss": 1.4192, "step": 414 }, { "epoch": 0.024240654205607476, "grad_norm": 1.503280758857727, "learning_rate": 1.6108949416342414e-05, "loss": 1.1844, "step": 415 }, { "epoch": 0.024299065420560748, "grad_norm": 3.468829393386841, "learning_rate": 1.614785992217899e-05, "loss": 1.3716, "step": 416 }, { "epoch": 0.02435747663551402, "grad_norm": 1.7262266874313354, "learning_rate": 1.6186770428015567e-05, "loss": 1.2536, "step": 417 }, { "epoch": 0.02441588785046729, "grad_norm": 2.4013595581054688, "learning_rate": 1.6225680933852142e-05, "loss": 1.1511, "step": 418 }, { "epoch": 0.02447429906542056, "grad_norm": 2.3760247230529785, "learning_rate": 1.6264591439688717e-05, "loss": 1.2021, "step": 419 }, { "epoch": 0.02453271028037383, "grad_norm": 2.2389535903930664, "learning_rate": 1.630350194552529e-05, "loss": 1.2666, "step": 420 }, { "epoch": 0.024591121495327103, "grad_norm": 3.704648017883301, "learning_rate": 1.634241245136187e-05, "loss": 1.4682, "step": 421 }, { "epoch": 0.024649532710280374, "grad_norm": 2.70398211479187, "learning_rate": 1.6381322957198444e-05, "loss": 1.2517, "step": 422 }, { "epoch": 0.024707943925233646, "grad_norm": 1.794443964958191, "learning_rate": 1.642023346303502e-05, "loss": 1.3905, "step": 423 }, { "epoch": 0.024766355140186914, "grad_norm": 4.0089240074157715, "learning_rate": 1.6459143968871597e-05, "loss": 1.4066, "step": 424 }, { "epoch": 0.024824766355140186, "grad_norm": 1.9966015815734863, "learning_rate": 1.649805447470817e-05, "loss": 1.4169, "step": 425 }, { "epoch": 0.024883177570093458, "grad_norm": 4.676424026489258, "learning_rate": 1.6536964980544746e-05, "loss": 1.2118, "step": 426 }, { "epoch": 0.02494158878504673, "grad_norm": 2.0918989181518555, "learning_rate": 1.6575875486381324e-05, "loss": 1.1492, "step": 427 }, { "epoch": 0.025, "grad_norm": 3.4002180099487305, "learning_rate": 1.6614785992217902e-05, "loss": 1.2608, "step": 428 }, { "epoch": 0.02505841121495327, "grad_norm": 3.197075366973877, "learning_rate": 1.6653696498054477e-05, "loss": 1.3572, "step": 429 }, { "epoch": 0.02511682242990654, "grad_norm": 1.6208709478378296, "learning_rate": 1.6692607003891052e-05, "loss": 1.3386, "step": 430 }, { "epoch": 0.025175233644859813, "grad_norm": 2.377290725708008, "learning_rate": 1.673151750972763e-05, "loss": 1.4101, "step": 431 }, { "epoch": 0.025233644859813085, "grad_norm": 3.3717172145843506, "learning_rate": 1.6770428015564204e-05, "loss": 1.123, "step": 432 }, { "epoch": 0.025292056074766357, "grad_norm": 1.62939453125, "learning_rate": 1.680933852140078e-05, "loss": 1.2846, "step": 433 }, { "epoch": 0.025350467289719625, "grad_norm": 3.4085843563079834, "learning_rate": 1.6848249027237357e-05, "loss": 1.2236, "step": 434 }, { "epoch": 0.025408878504672897, "grad_norm": 2.1364481449127197, "learning_rate": 1.6887159533073932e-05, "loss": 1.4254, "step": 435 }, { "epoch": 0.02546728971962617, "grad_norm": 1.9074382781982422, "learning_rate": 1.6926070038910507e-05, "loss": 1.281, "step": 436 }, { "epoch": 0.02552570093457944, "grad_norm": 2.249279022216797, "learning_rate": 1.696498054474708e-05, "loss": 1.1579, "step": 437 }, { "epoch": 0.02558411214953271, "grad_norm": 3.2048025131225586, "learning_rate": 1.700389105058366e-05, "loss": 1.4694, "step": 438 }, { "epoch": 0.02564252336448598, "grad_norm": 1.7292165756225586, "learning_rate": 1.7042801556420234e-05, "loss": 1.2354, "step": 439 }, { "epoch": 0.02570093457943925, "grad_norm": 2.696512460708618, "learning_rate": 1.708171206225681e-05, "loss": 1.1169, "step": 440 }, { "epoch": 0.025759345794392523, "grad_norm": 1.8692134618759155, "learning_rate": 1.7120622568093387e-05, "loss": 1.0356, "step": 441 }, { "epoch": 0.025817757009345795, "grad_norm": 2.770620584487915, "learning_rate": 1.715953307392996e-05, "loss": 1.2712, "step": 442 }, { "epoch": 0.025876168224299067, "grad_norm": 3.27828311920166, "learning_rate": 1.719844357976654e-05, "loss": 1.1534, "step": 443 }, { "epoch": 0.025934579439252335, "grad_norm": 2.4051570892333984, "learning_rate": 1.7237354085603114e-05, "loss": 1.1092, "step": 444 }, { "epoch": 0.025992990654205607, "grad_norm": 3.642495632171631, "learning_rate": 1.7276264591439692e-05, "loss": 1.2165, "step": 445 }, { "epoch": 0.02605140186915888, "grad_norm": 3.1313700675964355, "learning_rate": 1.7315175097276267e-05, "loss": 1.2244, "step": 446 }, { "epoch": 0.02610981308411215, "grad_norm": 3.8536863327026367, "learning_rate": 1.7354085603112842e-05, "loss": 1.198, "step": 447 }, { "epoch": 0.026168224299065422, "grad_norm": 5.031702995300293, "learning_rate": 1.739299610894942e-05, "loss": 1.3294, "step": 448 }, { "epoch": 0.02622663551401869, "grad_norm": 2.146904230117798, "learning_rate": 1.7431906614785994e-05, "loss": 1.1359, "step": 449 }, { "epoch": 0.026285046728971962, "grad_norm": 5.715206146240234, "learning_rate": 1.747081712062257e-05, "loss": 1.3057, "step": 450 }, { "epoch": 0.026343457943925234, "grad_norm": 2.161189556121826, "learning_rate": 1.7509727626459144e-05, "loss": 1.1602, "step": 451 }, { "epoch": 0.026401869158878506, "grad_norm": 2.9094927310943604, "learning_rate": 1.7548638132295722e-05, "loss": 1.3898, "step": 452 }, { "epoch": 0.026460280373831777, "grad_norm": 3.2491493225097656, "learning_rate": 1.7587548638132297e-05, "loss": 1.2195, "step": 453 }, { "epoch": 0.026518691588785046, "grad_norm": 2.0198662281036377, "learning_rate": 1.762645914396887e-05, "loss": 1.3108, "step": 454 }, { "epoch": 0.026577102803738317, "grad_norm": 2.9111709594726562, "learning_rate": 1.766536964980545e-05, "loss": 1.2258, "step": 455 }, { "epoch": 0.02663551401869159, "grad_norm": 5.05986213684082, "learning_rate": 1.7704280155642024e-05, "loss": 1.2603, "step": 456 }, { "epoch": 0.02669392523364486, "grad_norm": 3.432844638824463, "learning_rate": 1.77431906614786e-05, "loss": 1.2365, "step": 457 }, { "epoch": 0.026752336448598132, "grad_norm": 3.7346951961517334, "learning_rate": 1.7782101167315177e-05, "loss": 1.2714, "step": 458 }, { "epoch": 0.0268107476635514, "grad_norm": 4.130128860473633, "learning_rate": 1.7821011673151755e-05, "loss": 1.4391, "step": 459 }, { "epoch": 0.026869158878504672, "grad_norm": 1.6355608701705933, "learning_rate": 1.785992217898833e-05, "loss": 1.098, "step": 460 }, { "epoch": 0.026927570093457944, "grad_norm": 4.654291152954102, "learning_rate": 1.7898832684824904e-05, "loss": 1.329, "step": 461 }, { "epoch": 0.026985981308411216, "grad_norm": 2.406367301940918, "learning_rate": 1.7937743190661482e-05, "loss": 1.3732, "step": 462 }, { "epoch": 0.027044392523364488, "grad_norm": 3.3066062927246094, "learning_rate": 1.7976653696498057e-05, "loss": 1.2586, "step": 463 }, { "epoch": 0.027102803738317756, "grad_norm": 2.735236406326294, "learning_rate": 1.801556420233463e-05, "loss": 1.1763, "step": 464 }, { "epoch": 0.027161214953271028, "grad_norm": 2.525296688079834, "learning_rate": 1.8054474708171206e-05, "loss": 1.2431, "step": 465 }, { "epoch": 0.0272196261682243, "grad_norm": 3.4743359088897705, "learning_rate": 1.8093385214007784e-05, "loss": 1.2766, "step": 466 }, { "epoch": 0.02727803738317757, "grad_norm": 1.4962488412857056, "learning_rate": 1.813229571984436e-05, "loss": 1.0632, "step": 467 }, { "epoch": 0.027336448598130843, "grad_norm": 1.7545108795166016, "learning_rate": 1.8171206225680934e-05, "loss": 1.0315, "step": 468 }, { "epoch": 0.02739485981308411, "grad_norm": 3.565288543701172, "learning_rate": 1.8210116731517512e-05, "loss": 1.392, "step": 469 }, { "epoch": 0.027453271028037383, "grad_norm": 1.5407205820083618, "learning_rate": 1.8249027237354087e-05, "loss": 1.1187, "step": 470 }, { "epoch": 0.027511682242990654, "grad_norm": 2.846142530441284, "learning_rate": 1.828793774319066e-05, "loss": 1.3651, "step": 471 }, { "epoch": 0.027570093457943926, "grad_norm": 2.692035436630249, "learning_rate": 1.832684824902724e-05, "loss": 1.2663, "step": 472 }, { "epoch": 0.027628504672897198, "grad_norm": 2.0065455436706543, "learning_rate": 1.8365758754863814e-05, "loss": 1.2951, "step": 473 }, { "epoch": 0.027686915887850466, "grad_norm": 2.2175991535186768, "learning_rate": 1.840466926070039e-05, "loss": 1.2234, "step": 474 }, { "epoch": 0.027745327102803738, "grad_norm": 2.8456578254699707, "learning_rate": 1.8443579766536967e-05, "loss": 1.2783, "step": 475 }, { "epoch": 0.02780373831775701, "grad_norm": 2.1102540493011475, "learning_rate": 1.8482490272373545e-05, "loss": 1.5735, "step": 476 }, { "epoch": 0.02786214953271028, "grad_norm": 1.8255071640014648, "learning_rate": 1.852140077821012e-05, "loss": 1.1715, "step": 477 }, { "epoch": 0.027920560747663553, "grad_norm": 2.1361637115478516, "learning_rate": 1.8560311284046694e-05, "loss": 1.2762, "step": 478 }, { "epoch": 0.02797897196261682, "grad_norm": 2.0373902320861816, "learning_rate": 1.859922178988327e-05, "loss": 1.3655, "step": 479 }, { "epoch": 0.028037383177570093, "grad_norm": 1.2904365062713623, "learning_rate": 1.8638132295719847e-05, "loss": 1.113, "step": 480 }, { "epoch": 0.028095794392523365, "grad_norm": 2.863893747329712, "learning_rate": 1.867704280155642e-05, "loss": 1.4202, "step": 481 }, { "epoch": 0.028154205607476637, "grad_norm": 1.8654392957687378, "learning_rate": 1.8715953307392996e-05, "loss": 1.0051, "step": 482 }, { "epoch": 0.028212616822429905, "grad_norm": 2.4121851921081543, "learning_rate": 1.8754863813229574e-05, "loss": 1.2982, "step": 483 }, { "epoch": 0.028271028037383177, "grad_norm": 2.4695467948913574, "learning_rate": 1.879377431906615e-05, "loss": 1.231, "step": 484 }, { "epoch": 0.02832943925233645, "grad_norm": 2.003063678741455, "learning_rate": 1.8832684824902724e-05, "loss": 1.3958, "step": 485 }, { "epoch": 0.02838785046728972, "grad_norm": 1.3830673694610596, "learning_rate": 1.8871595330739302e-05, "loss": 1.1656, "step": 486 }, { "epoch": 0.02844626168224299, "grad_norm": 2.508168935775757, "learning_rate": 1.8910505836575877e-05, "loss": 1.1004, "step": 487 }, { "epoch": 0.02850467289719626, "grad_norm": 1.9760276079177856, "learning_rate": 1.894941634241245e-05, "loss": 1.2989, "step": 488 }, { "epoch": 0.02856308411214953, "grad_norm": 1.629319429397583, "learning_rate": 1.898832684824903e-05, "loss": 1.3729, "step": 489 }, { "epoch": 0.028621495327102803, "grad_norm": 2.4082398414611816, "learning_rate": 1.9027237354085604e-05, "loss": 1.0139, "step": 490 }, { "epoch": 0.028679906542056075, "grad_norm": 2.8832454681396484, "learning_rate": 1.9066147859922182e-05, "loss": 1.3404, "step": 491 }, { "epoch": 0.028738317757009347, "grad_norm": 1.911480188369751, "learning_rate": 1.9105058365758757e-05, "loss": 1.0807, "step": 492 }, { "epoch": 0.028796728971962615, "grad_norm": 2.704854726791382, "learning_rate": 1.914396887159533e-05, "loss": 1.2821, "step": 493 }, { "epoch": 0.028855140186915887, "grad_norm": 4.638606071472168, "learning_rate": 1.918287937743191e-05, "loss": 1.3461, "step": 494 }, { "epoch": 0.02891355140186916, "grad_norm": 3.2233400344848633, "learning_rate": 1.9221789883268484e-05, "loss": 1.289, "step": 495 }, { "epoch": 0.02897196261682243, "grad_norm": 3.56569766998291, "learning_rate": 1.926070038910506e-05, "loss": 1.2376, "step": 496 }, { "epoch": 0.029030373831775702, "grad_norm": 1.7111605405807495, "learning_rate": 1.9299610894941637e-05, "loss": 1.1509, "step": 497 }, { "epoch": 0.02908878504672897, "grad_norm": 2.7014434337615967, "learning_rate": 1.933852140077821e-05, "loss": 1.0026, "step": 498 }, { "epoch": 0.029147196261682242, "grad_norm": 3.5476229190826416, "learning_rate": 1.9377431906614786e-05, "loss": 1.1345, "step": 499 }, { "epoch": 0.029205607476635514, "grad_norm": 2.314882516860962, "learning_rate": 1.9416342412451364e-05, "loss": 1.3607, "step": 500 }, { "epoch": 0.029264018691588786, "grad_norm": 3.3307554721832275, "learning_rate": 1.945525291828794e-05, "loss": 1.1693, "step": 501 }, { "epoch": 0.029322429906542057, "grad_norm": 2.5822761058807373, "learning_rate": 1.9494163424124514e-05, "loss": 1.2747, "step": 502 }, { "epoch": 0.029380841121495326, "grad_norm": 1.9356762170791626, "learning_rate": 1.9533073929961092e-05, "loss": 1.1671, "step": 503 }, { "epoch": 0.029439252336448597, "grad_norm": 2.5774033069610596, "learning_rate": 1.9571984435797667e-05, "loss": 1.3749, "step": 504 }, { "epoch": 0.02949766355140187, "grad_norm": 1.8908836841583252, "learning_rate": 1.961089494163424e-05, "loss": 1.2218, "step": 505 }, { "epoch": 0.02955607476635514, "grad_norm": 2.9175875186920166, "learning_rate": 1.964980544747082e-05, "loss": 1.3064, "step": 506 }, { "epoch": 0.029614485981308412, "grad_norm": 2.183757781982422, "learning_rate": 1.9688715953307397e-05, "loss": 1.1965, "step": 507 }, { "epoch": 0.02967289719626168, "grad_norm": 2.404592275619507, "learning_rate": 1.9727626459143972e-05, "loss": 1.0713, "step": 508 }, { "epoch": 0.029731308411214952, "grad_norm": 2.554231643676758, "learning_rate": 1.9766536964980547e-05, "loss": 1.2871, "step": 509 }, { "epoch": 0.029789719626168224, "grad_norm": 1.7013460397720337, "learning_rate": 1.980544747081712e-05, "loss": 1.2911, "step": 510 }, { "epoch": 0.029848130841121496, "grad_norm": 2.061117649078369, "learning_rate": 1.98443579766537e-05, "loss": 1.0981, "step": 511 }, { "epoch": 0.029906542056074768, "grad_norm": 2.834296226501465, "learning_rate": 1.9883268482490274e-05, "loss": 1.0837, "step": 512 }, { "epoch": 0.029964953271028036, "grad_norm": 2.029097080230713, "learning_rate": 1.992217898832685e-05, "loss": 1.3065, "step": 513 }, { "epoch": 0.030023364485981308, "grad_norm": 2.3933486938476562, "learning_rate": 1.9961089494163427e-05, "loss": 1.0953, "step": 514 }, { "epoch": 0.03008177570093458, "grad_norm": 3.586760997772217, "learning_rate": 2e-05, "loss": 1.1174, "step": 515 }, { "epoch": 0.03014018691588785, "grad_norm": 1.7857744693756104, "learning_rate": 1.9999999821046714e-05, "loss": 1.0457, "step": 516 }, { "epoch": 0.030198598130841123, "grad_norm": 2.3569421768188477, "learning_rate": 1.9999999284186857e-05, "loss": 1.3463, "step": 517 }, { "epoch": 0.03025700934579439, "grad_norm": 3.0496909618377686, "learning_rate": 1.9999998389420453e-05, "loss": 1.2137, "step": 518 }, { "epoch": 0.030315420560747663, "grad_norm": 1.460052251815796, "learning_rate": 1.999999713674753e-05, "loss": 0.9212, "step": 519 }, { "epoch": 0.030373831775700934, "grad_norm": 1.7643228769302368, "learning_rate": 1.9999995526168134e-05, "loss": 1.087, "step": 520 }, { "epoch": 0.030432242990654206, "grad_norm": 1.7851886749267578, "learning_rate": 1.999999355768232e-05, "loss": 1.0364, "step": 521 }, { "epoch": 0.030490654205607478, "grad_norm": 1.5348033905029297, "learning_rate": 1.9999991231290166e-05, "loss": 1.3014, "step": 522 }, { "epoch": 0.030549065420560746, "grad_norm": 2.0309462547302246, "learning_rate": 1.9999988546991748e-05, "loss": 1.2732, "step": 523 }, { "epoch": 0.030607476635514018, "grad_norm": 1.8335403203964233, "learning_rate": 1.9999985504787168e-05, "loss": 1.2029, "step": 524 }, { "epoch": 0.03066588785046729, "grad_norm": 1.5673408508300781, "learning_rate": 1.999998210467653e-05, "loss": 1.3276, "step": 525 }, { "epoch": 0.03072429906542056, "grad_norm": 1.8798092603683472, "learning_rate": 1.9999978346659955e-05, "loss": 1.4349, "step": 526 }, { "epoch": 0.030782710280373833, "grad_norm": 1.853727102279663, "learning_rate": 1.9999974230737586e-05, "loss": 1.0815, "step": 527 }, { "epoch": 0.0308411214953271, "grad_norm": 2.256683588027954, "learning_rate": 1.9999969756909557e-05, "loss": 1.2094, "step": 528 }, { "epoch": 0.030899532710280373, "grad_norm": 2.6905324459075928, "learning_rate": 1.999996492517604e-05, "loss": 1.1457, "step": 529 }, { "epoch": 0.030957943925233645, "grad_norm": 2.316230297088623, "learning_rate": 1.99999597355372e-05, "loss": 1.22, "step": 530 }, { "epoch": 0.031016355140186917, "grad_norm": 2.068396806716919, "learning_rate": 1.9999954187993226e-05, "loss": 1.2326, "step": 531 }, { "epoch": 0.03107476635514019, "grad_norm": 2.977083444595337, "learning_rate": 1.999994828254432e-05, "loss": 1.1921, "step": 532 }, { "epoch": 0.031133177570093457, "grad_norm": 1.585005521774292, "learning_rate": 1.9999942019190686e-05, "loss": 1.1439, "step": 533 }, { "epoch": 0.03119158878504673, "grad_norm": 3.118023633956909, "learning_rate": 1.9999935397932555e-05, "loss": 1.1169, "step": 534 }, { "epoch": 0.03125, "grad_norm": 2.837801218032837, "learning_rate": 1.999992841877016e-05, "loss": 1.1004, "step": 535 }, { "epoch": 0.03130841121495327, "grad_norm": 2.54064679145813, "learning_rate": 1.9999921081703753e-05, "loss": 1.23, "step": 536 }, { "epoch": 0.03136682242990654, "grad_norm": 3.624938488006592, "learning_rate": 1.9999913386733594e-05, "loss": 1.1871, "step": 537 }, { "epoch": 0.031425233644859815, "grad_norm": 2.03853440284729, "learning_rate": 1.999990533385996e-05, "loss": 1.0592, "step": 538 }, { "epoch": 0.03148364485981309, "grad_norm": 2.0799694061279297, "learning_rate": 1.9999896923083137e-05, "loss": 1.1597, "step": 539 }, { "epoch": 0.03154205607476635, "grad_norm": 3.9620039463043213, "learning_rate": 1.9999888154403432e-05, "loss": 1.2195, "step": 540 }, { "epoch": 0.03160046728971962, "grad_norm": 2.04266095161438, "learning_rate": 1.9999879027821154e-05, "loss": 1.0717, "step": 541 }, { "epoch": 0.031658878504672895, "grad_norm": 3.43805193901062, "learning_rate": 1.9999869543336626e-05, "loss": 1.2921, "step": 542 }, { "epoch": 0.03171728971962617, "grad_norm": 1.7838190793991089, "learning_rate": 1.99998597009502e-05, "loss": 1.0242, "step": 543 }, { "epoch": 0.03177570093457944, "grad_norm": 2.5599477291107178, "learning_rate": 1.9999849500662214e-05, "loss": 1.0106, "step": 544 }, { "epoch": 0.03183411214953271, "grad_norm": 3.293955087661743, "learning_rate": 1.9999838942473044e-05, "loss": 1.2647, "step": 545 }, { "epoch": 0.03189252336448598, "grad_norm": 2.7960591316223145, "learning_rate": 1.9999828026383058e-05, "loss": 1.2201, "step": 546 }, { "epoch": 0.031950934579439254, "grad_norm": 3.561811923980713, "learning_rate": 1.9999816752392657e-05, "loss": 1.3153, "step": 547 }, { "epoch": 0.032009345794392526, "grad_norm": 1.5864484310150146, "learning_rate": 1.9999805120502232e-05, "loss": 1.0108, "step": 548 }, { "epoch": 0.0320677570093458, "grad_norm": 2.428577423095703, "learning_rate": 1.9999793130712212e-05, "loss": 1.2764, "step": 549 }, { "epoch": 0.03212616822429906, "grad_norm": 3.3176429271698, "learning_rate": 1.9999780783023023e-05, "loss": 1.142, "step": 550 }, { "epoch": 0.032184579439252334, "grad_norm": 1.7131956815719604, "learning_rate": 1.9999768077435102e-05, "loss": 0.977, "step": 551 }, { "epoch": 0.032242990654205606, "grad_norm": 5.150472164154053, "learning_rate": 1.9999755013948906e-05, "loss": 1.2644, "step": 552 }, { "epoch": 0.03230140186915888, "grad_norm": 2.1892549991607666, "learning_rate": 1.9999741592564903e-05, "loss": 1.1285, "step": 553 }, { "epoch": 0.03235981308411215, "grad_norm": 3.9116015434265137, "learning_rate": 1.9999727813283575e-05, "loss": 1.0362, "step": 554 }, { "epoch": 0.03241822429906542, "grad_norm": 2.203915596008301, "learning_rate": 1.9999713676105412e-05, "loss": 1.1524, "step": 555 }, { "epoch": 0.03247663551401869, "grad_norm": 3.343796968460083, "learning_rate": 1.9999699181030922e-05, "loss": 1.0072, "step": 556 }, { "epoch": 0.032535046728971964, "grad_norm": 3.402475595474243, "learning_rate": 1.9999684328060625e-05, "loss": 1.1762, "step": 557 }, { "epoch": 0.032593457943925236, "grad_norm": 2.610105514526367, "learning_rate": 1.999966911719505e-05, "loss": 1.0768, "step": 558 }, { "epoch": 0.03265186915887851, "grad_norm": 2.568542957305908, "learning_rate": 1.9999653548434744e-05, "loss": 1.1294, "step": 559 }, { "epoch": 0.03271028037383177, "grad_norm": 2.570829391479492, "learning_rate": 1.9999637621780258e-05, "loss": 1.0258, "step": 560 }, { "epoch": 0.032768691588785044, "grad_norm": 1.9993139505386353, "learning_rate": 1.999962133723217e-05, "loss": 1.256, "step": 561 }, { "epoch": 0.032827102803738316, "grad_norm": 3.1247498989105225, "learning_rate": 1.999960469479106e-05, "loss": 1.1238, "step": 562 }, { "epoch": 0.03288551401869159, "grad_norm": 3.25508713722229, "learning_rate": 1.999958769445752e-05, "loss": 1.218, "step": 563 }, { "epoch": 0.03294392523364486, "grad_norm": 16.317907333374023, "learning_rate": 1.9999570336232163e-05, "loss": 1.1004, "step": 564 }, { "epoch": 0.03300233644859813, "grad_norm": 2.3158466815948486, "learning_rate": 1.999955262011561e-05, "loss": 0.944, "step": 565 }, { "epoch": 0.0330607476635514, "grad_norm": 2.6193177700042725, "learning_rate": 1.999953454610849e-05, "loss": 1.1266, "step": 566 }, { "epoch": 0.033119158878504674, "grad_norm": 3.165767192840576, "learning_rate": 1.999951611421146e-05, "loss": 1.2132, "step": 567 }, { "epoch": 0.033177570093457946, "grad_norm": 2.127276659011841, "learning_rate": 1.999949732442517e-05, "loss": 1.3766, "step": 568 }, { "epoch": 0.03323598130841122, "grad_norm": 2.4176409244537354, "learning_rate": 1.9999478176750298e-05, "loss": 1.0384, "step": 569 }, { "epoch": 0.03329439252336448, "grad_norm": 1.6843266487121582, "learning_rate": 1.9999458671187524e-05, "loss": 1.1635, "step": 570 }, { "epoch": 0.033352803738317754, "grad_norm": 1.9258311986923218, "learning_rate": 1.999943880773755e-05, "loss": 1.1686, "step": 571 }, { "epoch": 0.033411214953271026, "grad_norm": 2.4399659633636475, "learning_rate": 1.9999418586401092e-05, "loss": 1.2794, "step": 572 }, { "epoch": 0.0334696261682243, "grad_norm": 2.2673099040985107, "learning_rate": 1.9999398007178863e-05, "loss": 1.032, "step": 573 }, { "epoch": 0.03352803738317757, "grad_norm": 2.36928653717041, "learning_rate": 1.9999377070071604e-05, "loss": 1.1325, "step": 574 }, { "epoch": 0.03358644859813084, "grad_norm": 1.9600461721420288, "learning_rate": 1.9999355775080064e-05, "loss": 1.1889, "step": 575 }, { "epoch": 0.03364485981308411, "grad_norm": 2.484238386154175, "learning_rate": 1.999933412220501e-05, "loss": 1.0062, "step": 576 }, { "epoch": 0.033703271028037385, "grad_norm": 2.3236560821533203, "learning_rate": 1.999931211144721e-05, "loss": 1.034, "step": 577 }, { "epoch": 0.03376168224299066, "grad_norm": 2.359050989151001, "learning_rate": 1.9999289742807457e-05, "loss": 1.322, "step": 578 }, { "epoch": 0.03382009345794393, "grad_norm": 1.8532071113586426, "learning_rate": 1.9999267016286546e-05, "loss": 1.0869, "step": 579 }, { "epoch": 0.03387850467289719, "grad_norm": 1.8836647272109985, "learning_rate": 1.99992439318853e-05, "loss": 1.0704, "step": 580 }, { "epoch": 0.033936915887850465, "grad_norm": 2.3032302856445312, "learning_rate": 1.9999220489604533e-05, "loss": 1.1358, "step": 581 }, { "epoch": 0.03399532710280374, "grad_norm": 1.7518291473388672, "learning_rate": 1.9999196689445092e-05, "loss": 0.9443, "step": 582 }, { "epoch": 0.03405373831775701, "grad_norm": 2.3658838272094727, "learning_rate": 1.999917253140783e-05, "loss": 1.0694, "step": 583 }, { "epoch": 0.03411214953271028, "grad_norm": 1.9865968227386475, "learning_rate": 1.9999148015493602e-05, "loss": 1.0866, "step": 584 }, { "epoch": 0.03417056074766355, "grad_norm": 1.923218846321106, "learning_rate": 1.99991231417033e-05, "loss": 1.237, "step": 585 }, { "epoch": 0.03422897196261682, "grad_norm": 2.7998995780944824, "learning_rate": 1.99990979100378e-05, "loss": 1.1304, "step": 586 }, { "epoch": 0.034287383177570095, "grad_norm": 2.2312257289886475, "learning_rate": 1.9999072320498012e-05, "loss": 1.0616, "step": 587 }, { "epoch": 0.03434579439252337, "grad_norm": 2.4397213459014893, "learning_rate": 1.9999046373084852e-05, "loss": 1.2209, "step": 588 }, { "epoch": 0.03440420560747664, "grad_norm": 2.085838556289673, "learning_rate": 1.999902006779925e-05, "loss": 1.1589, "step": 589 }, { "epoch": 0.0344626168224299, "grad_norm": 3.171468496322632, "learning_rate": 1.9998993404642144e-05, "loss": 1.1452, "step": 590 }, { "epoch": 0.034521028037383175, "grad_norm": 2.653693437576294, "learning_rate": 1.999896638361449e-05, "loss": 1.2847, "step": 591 }, { "epoch": 0.03457943925233645, "grad_norm": 1.9463233947753906, "learning_rate": 1.999893900471725e-05, "loss": 1.1752, "step": 592 }, { "epoch": 0.03463785046728972, "grad_norm": 1.7947118282318115, "learning_rate": 1.9998911267951415e-05, "loss": 1.1554, "step": 593 }, { "epoch": 0.03469626168224299, "grad_norm": 3.326876401901245, "learning_rate": 1.999888317331797e-05, "loss": 1.1585, "step": 594 }, { "epoch": 0.03475467289719626, "grad_norm": 1.8141770362854004, "learning_rate": 1.999885472081792e-05, "loss": 0.9818, "step": 595 }, { "epoch": 0.034813084112149534, "grad_norm": 2.6401185989379883, "learning_rate": 1.9998825910452283e-05, "loss": 0.8964, "step": 596 }, { "epoch": 0.034871495327102806, "grad_norm": 2.638119697570801, "learning_rate": 1.9998796742222098e-05, "loss": 1.0138, "step": 597 }, { "epoch": 0.03492990654205608, "grad_norm": 1.6811312437057495, "learning_rate": 1.9998767216128397e-05, "loss": 0.9876, "step": 598 }, { "epoch": 0.03498831775700935, "grad_norm": 2.371574878692627, "learning_rate": 1.9998737332172247e-05, "loss": 1.0047, "step": 599 }, { "epoch": 0.035046728971962614, "grad_norm": 2.4222412109375, "learning_rate": 1.9998707090354713e-05, "loss": 1.025, "step": 600 }, { "epoch": 0.035105140186915886, "grad_norm": 1.9225196838378906, "learning_rate": 1.999867649067688e-05, "loss": 1.1286, "step": 601 }, { "epoch": 0.03516355140186916, "grad_norm": 3.224348545074463, "learning_rate": 1.999864553313984e-05, "loss": 1.3988, "step": 602 }, { "epoch": 0.03522196261682243, "grad_norm": 2.033034324645996, "learning_rate": 1.99986142177447e-05, "loss": 1.2958, "step": 603 }, { "epoch": 0.0352803738317757, "grad_norm": 2.324662685394287, "learning_rate": 1.9998582544492585e-05, "loss": 1.2407, "step": 604 }, { "epoch": 0.03533878504672897, "grad_norm": 1.3882884979248047, "learning_rate": 1.999855051338462e-05, "loss": 1.0016, "step": 605 }, { "epoch": 0.035397196261682244, "grad_norm": 2.5514426231384277, "learning_rate": 1.9998518124421965e-05, "loss": 1.1188, "step": 606 }, { "epoch": 0.035455607476635516, "grad_norm": 1.7007876634597778, "learning_rate": 1.999848537760577e-05, "loss": 1.0227, "step": 607 }, { "epoch": 0.03551401869158879, "grad_norm": 2.520913600921631, "learning_rate": 1.999845227293721e-05, "loss": 1.0982, "step": 608 }, { "epoch": 0.03557242990654206, "grad_norm": 1.761207103729248, "learning_rate": 1.9998418810417472e-05, "loss": 1.1745, "step": 609 }, { "epoch": 0.035630841121495324, "grad_norm": 3.3356969356536865, "learning_rate": 1.9998384990047746e-05, "loss": 1.2086, "step": 610 }, { "epoch": 0.035689252336448596, "grad_norm": 1.6330256462097168, "learning_rate": 1.999835081182925e-05, "loss": 1.1399, "step": 611 }, { "epoch": 0.03574766355140187, "grad_norm": 1.8788508176803589, "learning_rate": 1.9998316275763202e-05, "loss": 1.0033, "step": 612 }, { "epoch": 0.03580607476635514, "grad_norm": 1.5718249082565308, "learning_rate": 1.9998281381850844e-05, "loss": 0.8775, "step": 613 }, { "epoch": 0.03586448598130841, "grad_norm": 2.245757579803467, "learning_rate": 1.9998246130093416e-05, "loss": 1.2967, "step": 614 }, { "epoch": 0.03592289719626168, "grad_norm": 1.701989769935608, "learning_rate": 1.999821052049219e-05, "loss": 1.0508, "step": 615 }, { "epoch": 0.035981308411214954, "grad_norm": 1.988359808921814, "learning_rate": 1.999817455304843e-05, "loss": 1.1411, "step": 616 }, { "epoch": 0.036039719626168226, "grad_norm": 1.919487476348877, "learning_rate": 1.9998138227763434e-05, "loss": 1.1033, "step": 617 }, { "epoch": 0.0360981308411215, "grad_norm": 1.629300832748413, "learning_rate": 1.9998101544638496e-05, "loss": 0.981, "step": 618 }, { "epoch": 0.03615654205607477, "grad_norm": 2.061046838760376, "learning_rate": 1.9998064503674927e-05, "loss": 1.1657, "step": 619 }, { "epoch": 0.036214953271028034, "grad_norm": 1.8137987852096558, "learning_rate": 1.9998027104874057e-05, "loss": 1.2464, "step": 620 }, { "epoch": 0.036273364485981306, "grad_norm": 1.5786690711975098, "learning_rate": 1.9997989348237227e-05, "loss": 0.9716, "step": 621 }, { "epoch": 0.03633177570093458, "grad_norm": 1.7764878273010254, "learning_rate": 1.9997951233765782e-05, "loss": 0.9822, "step": 622 }, { "epoch": 0.03639018691588785, "grad_norm": 1.4954850673675537, "learning_rate": 1.9997912761461088e-05, "loss": 1.3008, "step": 623 }, { "epoch": 0.03644859813084112, "grad_norm": 2.595201015472412, "learning_rate": 1.999787393132452e-05, "loss": 1.2091, "step": 624 }, { "epoch": 0.03650700934579439, "grad_norm": 1.5435808897018433, "learning_rate": 1.9997834743357473e-05, "loss": 1.0517, "step": 625 }, { "epoch": 0.036565420560747665, "grad_norm": 2.405470132827759, "learning_rate": 1.9997795197561344e-05, "loss": 1.2098, "step": 626 }, { "epoch": 0.03662383177570094, "grad_norm": 3.0401759147644043, "learning_rate": 1.9997755293937557e-05, "loss": 1.1805, "step": 627 }, { "epoch": 0.03668224299065421, "grad_norm": 2.706899642944336, "learning_rate": 1.999771503248753e-05, "loss": 1.0323, "step": 628 }, { "epoch": 0.03674065420560748, "grad_norm": 2.3196754455566406, "learning_rate": 1.999767441321271e-05, "loss": 1.206, "step": 629 }, { "epoch": 0.036799065420560745, "grad_norm": 1.6959818601608276, "learning_rate": 1.9997633436114547e-05, "loss": 1.144, "step": 630 }, { "epoch": 0.03685747663551402, "grad_norm": 2.0241401195526123, "learning_rate": 1.9997592101194512e-05, "loss": 1.2124, "step": 631 }, { "epoch": 0.03691588785046729, "grad_norm": 1.5823668241500854, "learning_rate": 1.999755040845408e-05, "loss": 0.9554, "step": 632 }, { "epoch": 0.03697429906542056, "grad_norm": 1.857229232788086, "learning_rate": 1.999750835789475e-05, "loss": 1.0033, "step": 633 }, { "epoch": 0.03703271028037383, "grad_norm": 1.7365278005599976, "learning_rate": 1.999746594951802e-05, "loss": 1.2106, "step": 634 }, { "epoch": 0.0370911214953271, "grad_norm": 1.9225022792816162, "learning_rate": 1.9997423183325406e-05, "loss": 1.0743, "step": 635 }, { "epoch": 0.037149532710280375, "grad_norm": 2.467470169067383, "learning_rate": 1.9997380059318447e-05, "loss": 1.1445, "step": 636 }, { "epoch": 0.03720794392523365, "grad_norm": 2.3219621181488037, "learning_rate": 1.9997336577498682e-05, "loss": 1.0832, "step": 637 }, { "epoch": 0.03726635514018692, "grad_norm": 2.2541892528533936, "learning_rate": 1.9997292737867667e-05, "loss": 1.131, "step": 638 }, { "epoch": 0.03732476635514019, "grad_norm": 1.8378976583480835, "learning_rate": 1.999724854042697e-05, "loss": 1.171, "step": 639 }, { "epoch": 0.037383177570093455, "grad_norm": 1.9609096050262451, "learning_rate": 1.9997203985178177e-05, "loss": 1.2389, "step": 640 }, { "epoch": 0.03744158878504673, "grad_norm": 1.8252707719802856, "learning_rate": 1.9997159072122877e-05, "loss": 0.953, "step": 641 }, { "epoch": 0.0375, "grad_norm": 2.0889217853546143, "learning_rate": 1.9997113801262683e-05, "loss": 1.0868, "step": 642 }, { "epoch": 0.03755841121495327, "grad_norm": 2.2654175758361816, "learning_rate": 1.9997068172599214e-05, "loss": 0.9836, "step": 643 }, { "epoch": 0.03761682242990654, "grad_norm": 2.160914659500122, "learning_rate": 1.99970221861341e-05, "loss": 1.0423, "step": 644 }, { "epoch": 0.037675233644859814, "grad_norm": 2.886401414871216, "learning_rate": 1.9996975841868987e-05, "loss": 1.1502, "step": 645 }, { "epoch": 0.037733644859813086, "grad_norm": 2.07828950881958, "learning_rate": 1.999692913980554e-05, "loss": 0.8931, "step": 646 }, { "epoch": 0.03779205607476636, "grad_norm": 2.5995023250579834, "learning_rate": 1.999688207994542e-05, "loss": 1.1721, "step": 647 }, { "epoch": 0.03785046728971963, "grad_norm": 1.8576146364212036, "learning_rate": 1.9996834662290323e-05, "loss": 1.0221, "step": 648 }, { "epoch": 0.037908878504672894, "grad_norm": 2.146653413772583, "learning_rate": 1.9996786886841937e-05, "loss": 0.9993, "step": 649 }, { "epoch": 0.037967289719626166, "grad_norm": 2.588948965072632, "learning_rate": 1.999673875360198e-05, "loss": 1.0831, "step": 650 }, { "epoch": 0.03802570093457944, "grad_norm": 2.237334728240967, "learning_rate": 1.9996690262572164e-05, "loss": 1.1466, "step": 651 }, { "epoch": 0.03808411214953271, "grad_norm": 2.572789430618286, "learning_rate": 1.9996641413754232e-05, "loss": 1.0292, "step": 652 }, { "epoch": 0.03814252336448598, "grad_norm": 2.6626994609832764, "learning_rate": 1.9996592207149933e-05, "loss": 1.1395, "step": 653 }, { "epoch": 0.03820093457943925, "grad_norm": 2.4375011920928955, "learning_rate": 1.9996542642761024e-05, "loss": 1.1188, "step": 654 }, { "epoch": 0.038259345794392524, "grad_norm": 2.1550540924072266, "learning_rate": 1.9996492720589284e-05, "loss": 1.2155, "step": 655 }, { "epoch": 0.038317757009345796, "grad_norm": 2.5797882080078125, "learning_rate": 1.9996442440636496e-05, "loss": 1.2664, "step": 656 }, { "epoch": 0.03837616822429907, "grad_norm": 1.8831509351730347, "learning_rate": 1.9996391802904454e-05, "loss": 0.8827, "step": 657 }, { "epoch": 0.03843457943925234, "grad_norm": 2.309903860092163, "learning_rate": 1.9996340807394983e-05, "loss": 1.0092, "step": 658 }, { "epoch": 0.038492990654205604, "grad_norm": 2.618882179260254, "learning_rate": 1.99962894541099e-05, "loss": 1.3542, "step": 659 }, { "epoch": 0.038551401869158876, "grad_norm": 2.1678168773651123, "learning_rate": 1.9996237743051045e-05, "loss": 0.9352, "step": 660 }, { "epoch": 0.03860981308411215, "grad_norm": 1.7903237342834473, "learning_rate": 1.999618567422027e-05, "loss": 0.8841, "step": 661 }, { "epoch": 0.03866822429906542, "grad_norm": 2.0450055599212646, "learning_rate": 1.9996133247619433e-05, "loss": 0.9643, "step": 662 }, { "epoch": 0.03872663551401869, "grad_norm": 2.020010471343994, "learning_rate": 1.9996080463250422e-05, "loss": 0.8434, "step": 663 }, { "epoch": 0.03878504672897196, "grad_norm": 2.9763171672821045, "learning_rate": 1.999602732111511e-05, "loss": 1.0712, "step": 664 }, { "epoch": 0.038843457943925234, "grad_norm": 1.7679904699325562, "learning_rate": 1.9995973821215413e-05, "loss": 1.1093, "step": 665 }, { "epoch": 0.038901869158878506, "grad_norm": 2.717536211013794, "learning_rate": 1.9995919963553237e-05, "loss": 0.9624, "step": 666 }, { "epoch": 0.03896028037383178, "grad_norm": 1.5656986236572266, "learning_rate": 1.9995865748130518e-05, "loss": 1.0197, "step": 667 }, { "epoch": 0.03901869158878505, "grad_norm": 1.8260269165039062, "learning_rate": 1.9995811174949186e-05, "loss": 0.9752, "step": 668 }, { "epoch": 0.039077102803738314, "grad_norm": 1.869411826133728, "learning_rate": 1.9995756244011204e-05, "loss": 0.8097, "step": 669 }, { "epoch": 0.039135514018691586, "grad_norm": 2.526343584060669, "learning_rate": 1.9995700955318533e-05, "loss": 1.0383, "step": 670 }, { "epoch": 0.03919392523364486, "grad_norm": 2.5987043380737305, "learning_rate": 1.9995645308873148e-05, "loss": 1.2661, "step": 671 }, { "epoch": 0.03925233644859813, "grad_norm": 2.432476043701172, "learning_rate": 1.999558930467705e-05, "loss": 1.2021, "step": 672 }, { "epoch": 0.0393107476635514, "grad_norm": 2.2789671421051025, "learning_rate": 1.9995532942732237e-05, "loss": 0.9871, "step": 673 }, { "epoch": 0.03936915887850467, "grad_norm": 1.5607625246047974, "learning_rate": 1.9995476223040725e-05, "loss": 0.9526, "step": 674 }, { "epoch": 0.039427570093457945, "grad_norm": 1.973783254623413, "learning_rate": 1.9995419145604554e-05, "loss": 0.9711, "step": 675 }, { "epoch": 0.03948598130841122, "grad_norm": 1.77592933177948, "learning_rate": 1.9995361710425752e-05, "loss": 0.9702, "step": 676 }, { "epoch": 0.03954439252336449, "grad_norm": 1.734860897064209, "learning_rate": 1.9995303917506386e-05, "loss": 0.9842, "step": 677 }, { "epoch": 0.03960280373831776, "grad_norm": 1.9079740047454834, "learning_rate": 1.999524576684852e-05, "loss": 1.0402, "step": 678 }, { "epoch": 0.039661214953271025, "grad_norm": 2.365936040878296, "learning_rate": 1.9995187258454237e-05, "loss": 1.2233, "step": 679 }, { "epoch": 0.0397196261682243, "grad_norm": 1.848352313041687, "learning_rate": 1.9995128392325628e-05, "loss": 1.1099, "step": 680 }, { "epoch": 0.03977803738317757, "grad_norm": 1.693482756614685, "learning_rate": 1.9995069168464804e-05, "loss": 0.8826, "step": 681 }, { "epoch": 0.03983644859813084, "grad_norm": 2.5307528972625732, "learning_rate": 1.999500958687388e-05, "loss": 1.0758, "step": 682 }, { "epoch": 0.03989485981308411, "grad_norm": 2.0345563888549805, "learning_rate": 1.9994949647554995e-05, "loss": 1.0431, "step": 683 }, { "epoch": 0.03995327102803738, "grad_norm": 1.7072676420211792, "learning_rate": 1.9994889350510288e-05, "loss": 1.0232, "step": 684 }, { "epoch": 0.040011682242990655, "grad_norm": 2.286285877227783, "learning_rate": 1.999482869574192e-05, "loss": 1.133, "step": 685 }, { "epoch": 0.04007009345794393, "grad_norm": 3.9406192302703857, "learning_rate": 1.999476768325206e-05, "loss": 1.1832, "step": 686 }, { "epoch": 0.0401285046728972, "grad_norm": 3.6309282779693604, "learning_rate": 1.9994706313042896e-05, "loss": 1.1824, "step": 687 }, { "epoch": 0.04018691588785047, "grad_norm": 2.21750807762146, "learning_rate": 1.9994644585116618e-05, "loss": 1.1085, "step": 688 }, { "epoch": 0.040245327102803735, "grad_norm": 2.8415157794952393, "learning_rate": 1.9994582499475438e-05, "loss": 1.1959, "step": 689 }, { "epoch": 0.04030373831775701, "grad_norm": 2.008552074432373, "learning_rate": 1.9994520056121582e-05, "loss": 0.9588, "step": 690 }, { "epoch": 0.04036214953271028, "grad_norm": 1.8468704223632812, "learning_rate": 1.9994457255057283e-05, "loss": 1.0715, "step": 691 }, { "epoch": 0.04042056074766355, "grad_norm": 2.191112995147705, "learning_rate": 1.9994394096284783e-05, "loss": 1.2005, "step": 692 }, { "epoch": 0.04047897196261682, "grad_norm": 3.732393503189087, "learning_rate": 1.999433057980635e-05, "loss": 1.236, "step": 693 }, { "epoch": 0.040537383177570094, "grad_norm": 2.7906060218811035, "learning_rate": 1.999426670562425e-05, "loss": 1.0901, "step": 694 }, { "epoch": 0.040595794392523366, "grad_norm": 2.1061277389526367, "learning_rate": 1.9994202473740775e-05, "loss": 0.9403, "step": 695 }, { "epoch": 0.04065420560747664, "grad_norm": 4.177405834197998, "learning_rate": 1.9994137884158225e-05, "loss": 1.1161, "step": 696 }, { "epoch": 0.04071261682242991, "grad_norm": 2.1985912322998047, "learning_rate": 1.9994072936878907e-05, "loss": 1.1717, "step": 697 }, { "epoch": 0.04077102803738318, "grad_norm": 2.170470952987671, "learning_rate": 1.9994007631905147e-05, "loss": 1.1049, "step": 698 }, { "epoch": 0.040829439252336445, "grad_norm": 2.2201316356658936, "learning_rate": 1.9993941969239284e-05, "loss": 1.211, "step": 699 }, { "epoch": 0.04088785046728972, "grad_norm": 2.841648578643799, "learning_rate": 1.9993875948883665e-05, "loss": 1.1113, "step": 700 }, { "epoch": 0.04094626168224299, "grad_norm": 2.314493179321289, "learning_rate": 1.9993809570840653e-05, "loss": 1.0467, "step": 701 }, { "epoch": 0.04100467289719626, "grad_norm": 2.030144691467285, "learning_rate": 1.9993742835112632e-05, "loss": 1.1327, "step": 702 }, { "epoch": 0.04106308411214953, "grad_norm": 3.7651195526123047, "learning_rate": 1.9993675741701977e-05, "loss": 0.9556, "step": 703 }, { "epoch": 0.041121495327102804, "grad_norm": 1.4993505477905273, "learning_rate": 1.99936082906111e-05, "loss": 0.8669, "step": 704 }, { "epoch": 0.041179906542056076, "grad_norm": 2.83172607421875, "learning_rate": 1.999354048184241e-05, "loss": 1.0848, "step": 705 }, { "epoch": 0.04123831775700935, "grad_norm": 2.0574827194213867, "learning_rate": 1.9993472315398336e-05, "loss": 1.0425, "step": 706 }, { "epoch": 0.04129672897196262, "grad_norm": 2.0239622592926025, "learning_rate": 1.999340379128132e-05, "loss": 0.9216, "step": 707 }, { "epoch": 0.04135514018691589, "grad_norm": 3.3861308097839355, "learning_rate": 1.9993334909493804e-05, "loss": 1.0402, "step": 708 }, { "epoch": 0.041413551401869156, "grad_norm": 3.4333972930908203, "learning_rate": 1.9993265670038265e-05, "loss": 1.2017, "step": 709 }, { "epoch": 0.04147196261682243, "grad_norm": 4.396484375, "learning_rate": 1.999319607291718e-05, "loss": 1.2065, "step": 710 }, { "epoch": 0.0415303738317757, "grad_norm": 2.5422260761260986, "learning_rate": 1.999312611813303e-05, "loss": 1.1138, "step": 711 }, { "epoch": 0.04158878504672897, "grad_norm": 3.8681623935699463, "learning_rate": 1.9993055805688334e-05, "loss": 1.2616, "step": 712 }, { "epoch": 0.04164719626168224, "grad_norm": 1.9424421787261963, "learning_rate": 1.9992985135585593e-05, "loss": 1.2613, "step": 713 }, { "epoch": 0.041705607476635514, "grad_norm": 2.8428795337677, "learning_rate": 1.9992914107827346e-05, "loss": 0.9351, "step": 714 }, { "epoch": 0.041764018691588786, "grad_norm": 2.6414074897766113, "learning_rate": 1.9992842722416133e-05, "loss": 1.0124, "step": 715 }, { "epoch": 0.04182242990654206, "grad_norm": 2.244563341140747, "learning_rate": 1.9992770979354507e-05, "loss": 1.1243, "step": 716 }, { "epoch": 0.04188084112149533, "grad_norm": 2.5771243572235107, "learning_rate": 1.9992698878645037e-05, "loss": 1.0151, "step": 717 }, { "epoch": 0.0419392523364486, "grad_norm": 3.213040590286255, "learning_rate": 1.9992626420290308e-05, "loss": 1.1801, "step": 718 }, { "epoch": 0.041997663551401866, "grad_norm": 2.5186684131622314, "learning_rate": 1.999255360429291e-05, "loss": 1.0307, "step": 719 }, { "epoch": 0.04205607476635514, "grad_norm": 3.0024755001068115, "learning_rate": 1.999248043065544e-05, "loss": 1.1422, "step": 720 }, { "epoch": 0.04211448598130841, "grad_norm": 2.674057722091675, "learning_rate": 1.999240689938053e-05, "loss": 1.3025, "step": 721 }, { "epoch": 0.04217289719626168, "grad_norm": 2.847308874130249, "learning_rate": 1.9992333010470806e-05, "loss": 0.9651, "step": 722 }, { "epoch": 0.04223130841121495, "grad_norm": 2.5711493492126465, "learning_rate": 1.999225876392892e-05, "loss": 0.9948, "step": 723 }, { "epoch": 0.042289719626168225, "grad_norm": 3.0010697841644287, "learning_rate": 1.9992184159757513e-05, "loss": 1.0393, "step": 724 }, { "epoch": 0.0423481308411215, "grad_norm": 2.2450203895568848, "learning_rate": 1.999210919795927e-05, "loss": 1.0428, "step": 725 }, { "epoch": 0.04240654205607477, "grad_norm": 3.561497926712036, "learning_rate": 1.999203387853687e-05, "loss": 1.1142, "step": 726 }, { "epoch": 0.04246495327102804, "grad_norm": 2.0211100578308105, "learning_rate": 1.9991958201493003e-05, "loss": 1.1132, "step": 727 }, { "epoch": 0.04252336448598131, "grad_norm": 2.3377416133880615, "learning_rate": 1.9991882166830384e-05, "loss": 1.0599, "step": 728 }, { "epoch": 0.04258177570093458, "grad_norm": 2.622380018234253, "learning_rate": 1.9991805774551736e-05, "loss": 0.9396, "step": 729 }, { "epoch": 0.04264018691588785, "grad_norm": 2.8736326694488525, "learning_rate": 1.9991729024659785e-05, "loss": 1.2061, "step": 730 }, { "epoch": 0.04269859813084112, "grad_norm": 3.387558937072754, "learning_rate": 1.9991651917157283e-05, "loss": 1.1852, "step": 731 }, { "epoch": 0.04275700934579439, "grad_norm": 2.15539813041687, "learning_rate": 1.9991574452046992e-05, "loss": 1.0872, "step": 732 }, { "epoch": 0.04281542056074766, "grad_norm": 2.1929118633270264, "learning_rate": 1.9991496629331682e-05, "loss": 0.932, "step": 733 }, { "epoch": 0.042873831775700935, "grad_norm": 2.1090376377105713, "learning_rate": 1.9991418449014136e-05, "loss": 0.9705, "step": 734 }, { "epoch": 0.04293224299065421, "grad_norm": 1.8888763189315796, "learning_rate": 1.9991339911097155e-05, "loss": 0.9176, "step": 735 }, { "epoch": 0.04299065420560748, "grad_norm": 2.0042731761932373, "learning_rate": 1.999126101558355e-05, "loss": 1.1891, "step": 736 }, { "epoch": 0.04304906542056075, "grad_norm": 1.9514341354370117, "learning_rate": 1.999118176247614e-05, "loss": 1.035, "step": 737 }, { "epoch": 0.04310747663551402, "grad_norm": 2.198596954345703, "learning_rate": 1.9991102151777765e-05, "loss": 1.2565, "step": 738 }, { "epoch": 0.04316588785046729, "grad_norm": 2.3085479736328125, "learning_rate": 1.999102218349128e-05, "loss": 1.1126, "step": 739 }, { "epoch": 0.04322429906542056, "grad_norm": 2.4535114765167236, "learning_rate": 1.999094185761954e-05, "loss": 1.0117, "step": 740 }, { "epoch": 0.04328271028037383, "grad_norm": 1.5993577241897583, "learning_rate": 1.9990861174165422e-05, "loss": 1.1597, "step": 741 }, { "epoch": 0.0433411214953271, "grad_norm": 2.6192331314086914, "learning_rate": 1.9990780133131814e-05, "loss": 1.0874, "step": 742 }, { "epoch": 0.043399532710280374, "grad_norm": 2.1215732097625732, "learning_rate": 1.9990698734521614e-05, "loss": 1.0314, "step": 743 }, { "epoch": 0.043457943925233646, "grad_norm": 2.0095582008361816, "learning_rate": 1.9990616978337737e-05, "loss": 1.0132, "step": 744 }, { "epoch": 0.04351635514018692, "grad_norm": 2.0367722511291504, "learning_rate": 1.999053486458311e-05, "loss": 0.9039, "step": 745 }, { "epoch": 0.04357476635514019, "grad_norm": 2.3351118564605713, "learning_rate": 1.9990452393260673e-05, "loss": 1.1046, "step": 746 }, { "epoch": 0.04363317757009346, "grad_norm": 2.2794554233551025, "learning_rate": 1.9990369564373373e-05, "loss": 1.0062, "step": 747 }, { "epoch": 0.04369158878504673, "grad_norm": 1.8975811004638672, "learning_rate": 1.999028637792418e-05, "loss": 1.0163, "step": 748 }, { "epoch": 0.04375, "grad_norm": 2.229740858078003, "learning_rate": 1.9990202833916065e-05, "loss": 0.9177, "step": 749 }, { "epoch": 0.04380841121495327, "grad_norm": 1.628617525100708, "learning_rate": 1.9990118932352028e-05, "loss": 0.8382, "step": 750 }, { "epoch": 0.04386682242990654, "grad_norm": 4.047518253326416, "learning_rate": 1.9990034673235064e-05, "loss": 1.0208, "step": 751 }, { "epoch": 0.04392523364485981, "grad_norm": 2.031609296798706, "learning_rate": 1.9989950056568187e-05, "loss": 0.8429, "step": 752 }, { "epoch": 0.043983644859813084, "grad_norm": 2.376095771789551, "learning_rate": 1.9989865082354432e-05, "loss": 1.0695, "step": 753 }, { "epoch": 0.044042056074766356, "grad_norm": 3.766042947769165, "learning_rate": 1.9989779750596832e-05, "loss": 0.987, "step": 754 }, { "epoch": 0.04410046728971963, "grad_norm": 2.6169111728668213, "learning_rate": 1.9989694061298453e-05, "loss": 1.0995, "step": 755 }, { "epoch": 0.0441588785046729, "grad_norm": 2.4259369373321533, "learning_rate": 1.9989608014462353e-05, "loss": 1.0796, "step": 756 }, { "epoch": 0.04421728971962617, "grad_norm": 2.474452018737793, "learning_rate": 1.9989521610091614e-05, "loss": 0.9814, "step": 757 }, { "epoch": 0.044275700934579436, "grad_norm": 2.2125484943389893, "learning_rate": 1.998943484818933e-05, "loss": 0.9715, "step": 758 }, { "epoch": 0.04433411214953271, "grad_norm": 2.177039384841919, "learning_rate": 1.99893477287586e-05, "loss": 1.1413, "step": 759 }, { "epoch": 0.04439252336448598, "grad_norm": 2.6206820011138916, "learning_rate": 1.998926025180255e-05, "loss": 0.9458, "step": 760 }, { "epoch": 0.04445093457943925, "grad_norm": 3.192233085632324, "learning_rate": 1.998917241732431e-05, "loss": 1.2086, "step": 761 }, { "epoch": 0.04450934579439252, "grad_norm": 2.222564935684204, "learning_rate": 1.9989084225327014e-05, "loss": 1.0884, "step": 762 }, { "epoch": 0.044567757009345794, "grad_norm": 2.6541390419006348, "learning_rate": 1.998899567581383e-05, "loss": 1.016, "step": 763 }, { "epoch": 0.044626168224299066, "grad_norm": 3.360452651977539, "learning_rate": 1.9988906768787924e-05, "loss": 1.0438, "step": 764 }, { "epoch": 0.04468457943925234, "grad_norm": 2.525628089904785, "learning_rate": 1.9988817504252473e-05, "loss": 1.0125, "step": 765 }, { "epoch": 0.04474299065420561, "grad_norm": 2.788709878921509, "learning_rate": 1.998872788221068e-05, "loss": 0.9996, "step": 766 }, { "epoch": 0.04480140186915888, "grad_norm": 2.528841495513916, "learning_rate": 1.9988637902665748e-05, "loss": 1.1714, "step": 767 }, { "epoch": 0.044859813084112146, "grad_norm": 2.4887826442718506, "learning_rate": 1.9988547565620896e-05, "loss": 1.0572, "step": 768 }, { "epoch": 0.04491822429906542, "grad_norm": 2.651378870010376, "learning_rate": 1.998845687107936e-05, "loss": 1.1406, "step": 769 }, { "epoch": 0.04497663551401869, "grad_norm": 2.2242884635925293, "learning_rate": 1.9988365819044384e-05, "loss": 1.0132, "step": 770 }, { "epoch": 0.04503504672897196, "grad_norm": 2.778388023376465, "learning_rate": 1.9988274409519226e-05, "loss": 1.2159, "step": 771 }, { "epoch": 0.04509345794392523, "grad_norm": 1.8661587238311768, "learning_rate": 1.9988182642507162e-05, "loss": 0.9916, "step": 772 }, { "epoch": 0.045151869158878505, "grad_norm": 2.617737054824829, "learning_rate": 1.9988090518011475e-05, "loss": 1.2595, "step": 773 }, { "epoch": 0.04521028037383178, "grad_norm": 2.289071559906006, "learning_rate": 1.998799803603546e-05, "loss": 1.1983, "step": 774 }, { "epoch": 0.04526869158878505, "grad_norm": 2.3999016284942627, "learning_rate": 1.9987905196582428e-05, "loss": 1.0145, "step": 775 }, { "epoch": 0.04532710280373832, "grad_norm": 2.257807493209839, "learning_rate": 1.9987811999655703e-05, "loss": 1.1751, "step": 776 }, { "epoch": 0.04538551401869159, "grad_norm": 1.7933709621429443, "learning_rate": 1.9987718445258614e-05, "loss": 0.9951, "step": 777 }, { "epoch": 0.04544392523364486, "grad_norm": 1.7474539279937744, "learning_rate": 1.998762453339452e-05, "loss": 1.1846, "step": 778 }, { "epoch": 0.04550233644859813, "grad_norm": 2.4682929515838623, "learning_rate": 1.9987530264066777e-05, "loss": 1.1335, "step": 779 }, { "epoch": 0.0455607476635514, "grad_norm": 2.1319901943206787, "learning_rate": 1.9987435637278757e-05, "loss": 0.9348, "step": 780 }, { "epoch": 0.04561915887850467, "grad_norm": 2.5231878757476807, "learning_rate": 1.9987340653033847e-05, "loss": 1.1641, "step": 781 }, { "epoch": 0.04567757009345794, "grad_norm": 1.9022237062454224, "learning_rate": 1.998724531133545e-05, "loss": 0.978, "step": 782 }, { "epoch": 0.045735981308411215, "grad_norm": 2.110976457595825, "learning_rate": 1.998714961218698e-05, "loss": 0.8815, "step": 783 }, { "epoch": 0.04579439252336449, "grad_norm": 1.9908509254455566, "learning_rate": 1.9987053555591856e-05, "loss": 0.886, "step": 784 }, { "epoch": 0.04585280373831776, "grad_norm": 2.219407081604004, "learning_rate": 1.998695714155352e-05, "loss": 1.0292, "step": 785 }, { "epoch": 0.04591121495327103, "grad_norm": 1.9471944570541382, "learning_rate": 1.9986860370075417e-05, "loss": 1.0002, "step": 786 }, { "epoch": 0.0459696261682243, "grad_norm": 2.3203446865081787, "learning_rate": 1.998676324116102e-05, "loss": 1.2363, "step": 787 }, { "epoch": 0.04602803738317757, "grad_norm": 1.8508399724960327, "learning_rate": 1.9986665754813798e-05, "loss": 1.0566, "step": 788 }, { "epoch": 0.04608644859813084, "grad_norm": 1.8353514671325684, "learning_rate": 1.998656791103724e-05, "loss": 0.9212, "step": 789 }, { "epoch": 0.04614485981308411, "grad_norm": 2.795598030090332, "learning_rate": 1.998646970983485e-05, "loss": 0.993, "step": 790 }, { "epoch": 0.04620327102803738, "grad_norm": 1.8669240474700928, "learning_rate": 1.9986371151210146e-05, "loss": 0.8838, "step": 791 }, { "epoch": 0.046261682242990654, "grad_norm": 2.6618380546569824, "learning_rate": 1.9986272235166652e-05, "loss": 1.1319, "step": 792 }, { "epoch": 0.046320093457943926, "grad_norm": 1.8367879390716553, "learning_rate": 1.9986172961707912e-05, "loss": 0.9939, "step": 793 }, { "epoch": 0.0463785046728972, "grad_norm": 1.9543187618255615, "learning_rate": 1.9986073330837467e-05, "loss": 1.0828, "step": 794 }, { "epoch": 0.04643691588785047, "grad_norm": 2.0490641593933105, "learning_rate": 1.99859733425589e-05, "loss": 1.1238, "step": 795 }, { "epoch": 0.04649532710280374, "grad_norm": 1.9087579250335693, "learning_rate": 1.9985872996875777e-05, "loss": 0.9146, "step": 796 }, { "epoch": 0.04655373831775701, "grad_norm": 1.6276237964630127, "learning_rate": 1.998577229379169e-05, "loss": 0.9948, "step": 797 }, { "epoch": 0.04661214953271028, "grad_norm": 1.9569454193115234, "learning_rate": 1.9985671233310253e-05, "loss": 0.9536, "step": 798 }, { "epoch": 0.04667056074766355, "grad_norm": 1.7666555643081665, "learning_rate": 1.9985569815435077e-05, "loss": 0.8383, "step": 799 }, { "epoch": 0.04672897196261682, "grad_norm": 1.5569654703140259, "learning_rate": 1.9985468040169785e-05, "loss": 0.9411, "step": 800 }, { "epoch": 0.04678738317757009, "grad_norm": 2.1946401596069336, "learning_rate": 1.9985365907518033e-05, "loss": 0.985, "step": 801 }, { "epoch": 0.046845794392523364, "grad_norm": 1.4459716081619263, "learning_rate": 1.9985263417483467e-05, "loss": 0.7108, "step": 802 }, { "epoch": 0.046904205607476636, "grad_norm": 2.8025124073028564, "learning_rate": 1.998516057006976e-05, "loss": 1.0712, "step": 803 }, { "epoch": 0.04696261682242991, "grad_norm": 2.047515869140625, "learning_rate": 1.998505736528059e-05, "loss": 1.1094, "step": 804 }, { "epoch": 0.04702102803738318, "grad_norm": 2.280317783355713, "learning_rate": 1.998495380311965e-05, "loss": 0.9043, "step": 805 }, { "epoch": 0.04707943925233645, "grad_norm": 1.6667401790618896, "learning_rate": 1.9984849883590648e-05, "loss": 0.8846, "step": 806 }, { "epoch": 0.04713785046728972, "grad_norm": 3.1820645332336426, "learning_rate": 1.99847456066973e-05, "loss": 1.0907, "step": 807 }, { "epoch": 0.04719626168224299, "grad_norm": 2.357353687286377, "learning_rate": 1.998464097244335e-05, "loss": 1.1527, "step": 808 }, { "epoch": 0.04725467289719626, "grad_norm": 2.6252646446228027, "learning_rate": 1.998453598083253e-05, "loss": 0.9624, "step": 809 }, { "epoch": 0.04731308411214953, "grad_norm": 2.2223241329193115, "learning_rate": 1.9984430631868605e-05, "loss": 1.0853, "step": 810 }, { "epoch": 0.0473714953271028, "grad_norm": 1.6617746353149414, "learning_rate": 1.9984324925555338e-05, "loss": 0.6559, "step": 811 }, { "epoch": 0.047429906542056074, "grad_norm": 1.3097045421600342, "learning_rate": 1.998421886189652e-05, "loss": 0.9522, "step": 812 }, { "epoch": 0.047488317757009346, "grad_norm": 3.0901038646698, "learning_rate": 1.9984112440895943e-05, "loss": 0.9662, "step": 813 }, { "epoch": 0.04754672897196262, "grad_norm": 1.5346531867980957, "learning_rate": 1.998400566255742e-05, "loss": 0.9677, "step": 814 }, { "epoch": 0.04760514018691589, "grad_norm": 1.8180792331695557, "learning_rate": 1.9983898526884764e-05, "loss": 0.9556, "step": 815 }, { "epoch": 0.04766355140186916, "grad_norm": 3.0883638858795166, "learning_rate": 1.998379103388182e-05, "loss": 0.8558, "step": 816 }, { "epoch": 0.04772196261682243, "grad_norm": 1.807097315788269, "learning_rate": 1.998368318355243e-05, "loss": 0.868, "step": 817 }, { "epoch": 0.0477803738317757, "grad_norm": 3.0463318824768066, "learning_rate": 1.9983574975900454e-05, "loss": 0.9724, "step": 818 }, { "epoch": 0.04783878504672897, "grad_norm": 1.6792807579040527, "learning_rate": 1.9983466410929764e-05, "loss": 0.853, "step": 819 }, { "epoch": 0.04789719626168224, "grad_norm": 2.391634464263916, "learning_rate": 1.998335748864425e-05, "loss": 1.0701, "step": 820 }, { "epoch": 0.04795560747663551, "grad_norm": 2.138232707977295, "learning_rate": 1.9983248209047803e-05, "loss": 1.1396, "step": 821 }, { "epoch": 0.048014018691588785, "grad_norm": 3.185770273208618, "learning_rate": 1.998313857214434e-05, "loss": 1.2386, "step": 822 }, { "epoch": 0.04807242990654206, "grad_norm": 1.4211006164550781, "learning_rate": 1.9983028577937785e-05, "loss": 0.9109, "step": 823 }, { "epoch": 0.04813084112149533, "grad_norm": 2.2773756980895996, "learning_rate": 1.998291822643207e-05, "loss": 0.939, "step": 824 }, { "epoch": 0.0481892523364486, "grad_norm": 2.356933832168579, "learning_rate": 1.9982807517631152e-05, "loss": 1.057, "step": 825 }, { "epoch": 0.04824766355140187, "grad_norm": 2.1161205768585205, "learning_rate": 1.9982696451538987e-05, "loss": 1.15, "step": 826 }, { "epoch": 0.04830607476635514, "grad_norm": 2.5407114028930664, "learning_rate": 1.9982585028159552e-05, "loss": 0.986, "step": 827 }, { "epoch": 0.04836448598130841, "grad_norm": 1.9910489320755005, "learning_rate": 1.9982473247496837e-05, "loss": 1.0935, "step": 828 }, { "epoch": 0.04842289719626168, "grad_norm": 2.707254409790039, "learning_rate": 1.998236110955484e-05, "loss": 0.9755, "step": 829 }, { "epoch": 0.04848130841121495, "grad_norm": 1.538620114326477, "learning_rate": 1.9982248614337575e-05, "loss": 0.7482, "step": 830 }, { "epoch": 0.04853971962616822, "grad_norm": 1.9500941038131714, "learning_rate": 1.998213576184907e-05, "loss": 0.8902, "step": 831 }, { "epoch": 0.048598130841121495, "grad_norm": 2.2196826934814453, "learning_rate": 1.9982022552093357e-05, "loss": 0.8326, "step": 832 }, { "epoch": 0.04865654205607477, "grad_norm": 1.4515700340270996, "learning_rate": 1.9981908985074497e-05, "loss": 0.9286, "step": 833 }, { "epoch": 0.04871495327102804, "grad_norm": 2.919398546218872, "learning_rate": 1.9981795060796554e-05, "loss": 0.9701, "step": 834 }, { "epoch": 0.04877336448598131, "grad_norm": 1.7254879474639893, "learning_rate": 1.99816807792636e-05, "loss": 0.8756, "step": 835 }, { "epoch": 0.04883177570093458, "grad_norm": 2.0519039630889893, "learning_rate": 1.998156614047973e-05, "loss": 0.983, "step": 836 }, { "epoch": 0.048890186915887854, "grad_norm": 1.8474680185317993, "learning_rate": 1.9981451144449042e-05, "loss": 0.8609, "step": 837 }, { "epoch": 0.04894859813084112, "grad_norm": 1.7275789976119995, "learning_rate": 1.9981335791175655e-05, "loss": 0.8913, "step": 838 }, { "epoch": 0.04900700934579439, "grad_norm": 2.3785362243652344, "learning_rate": 1.99812200806637e-05, "loss": 1.1265, "step": 839 }, { "epoch": 0.04906542056074766, "grad_norm": 1.9935705661773682, "learning_rate": 1.9981104012917312e-05, "loss": 0.9161, "step": 840 }, { "epoch": 0.049123831775700934, "grad_norm": 2.7527637481689453, "learning_rate": 1.998098758794065e-05, "loss": 0.9344, "step": 841 }, { "epoch": 0.049182242990654206, "grad_norm": 1.7919594049453735, "learning_rate": 1.998087080573788e-05, "loss": 0.9563, "step": 842 }, { "epoch": 0.04924065420560748, "grad_norm": 2.2187132835388184, "learning_rate": 1.998075366631318e-05, "loss": 1.1328, "step": 843 }, { "epoch": 0.04929906542056075, "grad_norm": 2.3309004306793213, "learning_rate": 1.9980636169670747e-05, "loss": 1.0312, "step": 844 }, { "epoch": 0.04935747663551402, "grad_norm": 2.1143696308135986, "learning_rate": 1.998051831581478e-05, "loss": 1.0529, "step": 845 }, { "epoch": 0.04941588785046729, "grad_norm": 3.876493215560913, "learning_rate": 1.99804001047495e-05, "loss": 0.9158, "step": 846 }, { "epoch": 0.049474299065420564, "grad_norm": 2.004589557647705, "learning_rate": 1.998028153647914e-05, "loss": 0.9211, "step": 847 }, { "epoch": 0.04953271028037383, "grad_norm": 3.0234880447387695, "learning_rate": 1.9980162611007943e-05, "loss": 1.1661, "step": 848 }, { "epoch": 0.0495911214953271, "grad_norm": 2.1471235752105713, "learning_rate": 1.9980043328340158e-05, "loss": 1.0822, "step": 849 }, { "epoch": 0.04964953271028037, "grad_norm": 2.9894051551818848, "learning_rate": 1.9979923688480066e-05, "loss": 0.9516, "step": 850 }, { "epoch": 0.049707943925233644, "grad_norm": 2.1845548152923584, "learning_rate": 1.997980369143194e-05, "loss": 0.8639, "step": 851 }, { "epoch": 0.049766355140186916, "grad_norm": 2.455106735229492, "learning_rate": 1.997968333720008e-05, "loss": 1.3103, "step": 852 }, { "epoch": 0.04982476635514019, "grad_norm": 2.0660722255706787, "learning_rate": 1.9979562625788792e-05, "loss": 0.9528, "step": 853 }, { "epoch": 0.04988317757009346, "grad_norm": 1.9410924911499023, "learning_rate": 1.9979441557202396e-05, "loss": 1.2446, "step": 854 }, { "epoch": 0.04994158878504673, "grad_norm": 1.7232787609100342, "learning_rate": 1.9979320131445224e-05, "loss": 0.852, "step": 855 }, { "epoch": 0.05, "grad_norm": 3.174436092376709, "learning_rate": 1.997919834852162e-05, "loss": 1.1362, "step": 856 }, { "epoch": 0.05005841121495327, "grad_norm": 1.8266505002975464, "learning_rate": 1.997907620843595e-05, "loss": 0.9372, "step": 857 }, { "epoch": 0.05011682242990654, "grad_norm": 1.9383310079574585, "learning_rate": 1.997895371119258e-05, "loss": 0.7558, "step": 858 }, { "epoch": 0.05017523364485981, "grad_norm": 2.3884363174438477, "learning_rate": 1.9978830856795898e-05, "loss": 1.0832, "step": 859 }, { "epoch": 0.05023364485981308, "grad_norm": 2.467599868774414, "learning_rate": 1.9978707645250293e-05, "loss": 1.0047, "step": 860 }, { "epoch": 0.050292056074766354, "grad_norm": 2.4163408279418945, "learning_rate": 1.9978584076560183e-05, "loss": 0.826, "step": 861 }, { "epoch": 0.050350467289719626, "grad_norm": 2.206724166870117, "learning_rate": 1.9978460150729986e-05, "loss": 0.7623, "step": 862 }, { "epoch": 0.0504088785046729, "grad_norm": 2.3285436630249023, "learning_rate": 1.9978335867764144e-05, "loss": 1.0629, "step": 863 }, { "epoch": 0.05046728971962617, "grad_norm": 2.7422127723693848, "learning_rate": 1.9978211227667096e-05, "loss": 1.0772, "step": 864 }, { "epoch": 0.05052570093457944, "grad_norm": 1.5663294792175293, "learning_rate": 1.997808623044331e-05, "loss": 0.968, "step": 865 }, { "epoch": 0.05058411214953271, "grad_norm": 2.121805429458618, "learning_rate": 1.9977960876097255e-05, "loss": 0.9441, "step": 866 }, { "epoch": 0.05064252336448598, "grad_norm": 2.0491092205047607, "learning_rate": 1.9977835164633423e-05, "loss": 1.0255, "step": 867 }, { "epoch": 0.05070093457943925, "grad_norm": 2.1019489765167236, "learning_rate": 1.9977709096056306e-05, "loss": 1.2474, "step": 868 }, { "epoch": 0.05075934579439252, "grad_norm": 1.9567499160766602, "learning_rate": 1.997758267037042e-05, "loss": 1.0364, "step": 869 }, { "epoch": 0.05081775700934579, "grad_norm": 1.6939926147460938, "learning_rate": 1.9977455887580292e-05, "loss": 1.0645, "step": 870 }, { "epoch": 0.050876168224299065, "grad_norm": 2.0989608764648438, "learning_rate": 1.9977328747690456e-05, "loss": 0.952, "step": 871 }, { "epoch": 0.05093457943925234, "grad_norm": 2.1650583744049072, "learning_rate": 1.9977201250705464e-05, "loss": 1.1451, "step": 872 }, { "epoch": 0.05099299065420561, "grad_norm": 2.576693058013916, "learning_rate": 1.997707339662988e-05, "loss": 0.9213, "step": 873 }, { "epoch": 0.05105140186915888, "grad_norm": 1.816054105758667, "learning_rate": 1.997694518546828e-05, "loss": 0.8854, "step": 874 }, { "epoch": 0.05110981308411215, "grad_norm": 1.8410842418670654, "learning_rate": 1.997681661722525e-05, "loss": 0.9813, "step": 875 }, { "epoch": 0.05116822429906542, "grad_norm": 2.565608501434326, "learning_rate": 1.9976687691905394e-05, "loss": 0.9262, "step": 876 }, { "epoch": 0.05122663551401869, "grad_norm": 2.436504602432251, "learning_rate": 1.9976558409513328e-05, "loss": 1.1195, "step": 877 }, { "epoch": 0.05128504672897196, "grad_norm": 1.9234185218811035, "learning_rate": 1.9976428770053672e-05, "loss": 0.9707, "step": 878 }, { "epoch": 0.05134345794392523, "grad_norm": 2.541698694229126, "learning_rate": 1.9976298773531072e-05, "loss": 1.0248, "step": 879 }, { "epoch": 0.0514018691588785, "grad_norm": 1.7557276487350464, "learning_rate": 1.9976168419950183e-05, "loss": 0.9638, "step": 880 }, { "epoch": 0.051460280373831775, "grad_norm": 2.2584941387176514, "learning_rate": 1.9976037709315664e-05, "loss": 0.9452, "step": 881 }, { "epoch": 0.05151869158878505, "grad_norm": 1.9785817861557007, "learning_rate": 1.9975906641632194e-05, "loss": 1.1061, "step": 882 }, { "epoch": 0.05157710280373832, "grad_norm": 2.1459498405456543, "learning_rate": 1.9975775216904468e-05, "loss": 1.0425, "step": 883 }, { "epoch": 0.05163551401869159, "grad_norm": 2.050344228744507, "learning_rate": 1.997564343513719e-05, "loss": 1.1973, "step": 884 }, { "epoch": 0.05169392523364486, "grad_norm": 1.6793769598007202, "learning_rate": 1.9975511296335072e-05, "loss": 0.8104, "step": 885 }, { "epoch": 0.051752336448598134, "grad_norm": 1.3335747718811035, "learning_rate": 1.9975378800502847e-05, "loss": 0.8836, "step": 886 }, { "epoch": 0.0518107476635514, "grad_norm": 1.5509313344955444, "learning_rate": 1.9975245947645253e-05, "loss": 0.8215, "step": 887 }, { "epoch": 0.05186915887850467, "grad_norm": 1.8106988668441772, "learning_rate": 1.997511273776705e-05, "loss": 1.019, "step": 888 }, { "epoch": 0.05192757009345794, "grad_norm": 1.80986487865448, "learning_rate": 1.9974979170873004e-05, "loss": 1.1901, "step": 889 }, { "epoch": 0.051985981308411214, "grad_norm": 1.4550368785858154, "learning_rate": 1.9974845246967892e-05, "loss": 0.8544, "step": 890 }, { "epoch": 0.052044392523364486, "grad_norm": 2.4179341793060303, "learning_rate": 1.997471096605651e-05, "loss": 1.0704, "step": 891 }, { "epoch": 0.05210280373831776, "grad_norm": 1.7740228176116943, "learning_rate": 1.997457632814367e-05, "loss": 1.0374, "step": 892 }, { "epoch": 0.05216121495327103, "grad_norm": 1.993959903717041, "learning_rate": 1.997444133323418e-05, "loss": 1.0605, "step": 893 }, { "epoch": 0.0522196261682243, "grad_norm": 2.6435298919677734, "learning_rate": 1.9974305981332877e-05, "loss": 1.0522, "step": 894 }, { "epoch": 0.05227803738317757, "grad_norm": 1.8473753929138184, "learning_rate": 1.9974170272444604e-05, "loss": 0.858, "step": 895 }, { "epoch": 0.052336448598130844, "grad_norm": 2.1560821533203125, "learning_rate": 1.997403420657422e-05, "loss": 0.8975, "step": 896 }, { "epoch": 0.05239485981308411, "grad_norm": 2.443715810775757, "learning_rate": 1.9973897783726593e-05, "loss": 0.9048, "step": 897 }, { "epoch": 0.05245327102803738, "grad_norm": 2.539245843887329, "learning_rate": 1.9973761003906606e-05, "loss": 0.9067, "step": 898 }, { "epoch": 0.05251168224299065, "grad_norm": 2.529493570327759, "learning_rate": 1.9973623867119155e-05, "loss": 0.8899, "step": 899 }, { "epoch": 0.052570093457943924, "grad_norm": 2.4977760314941406, "learning_rate": 1.9973486373369148e-05, "loss": 1.1196, "step": 900 }, { "epoch": 0.052628504672897196, "grad_norm": 2.5603981018066406, "learning_rate": 1.9973348522661506e-05, "loss": 1.0499, "step": 901 }, { "epoch": 0.05268691588785047, "grad_norm": 2.401890277862549, "learning_rate": 1.9973210315001163e-05, "loss": 1.0345, "step": 902 }, { "epoch": 0.05274532710280374, "grad_norm": 2.286613941192627, "learning_rate": 1.997307175039307e-05, "loss": 1.1221, "step": 903 }, { "epoch": 0.05280373831775701, "grad_norm": 2.9092302322387695, "learning_rate": 1.9972932828842177e-05, "loss": 0.9972, "step": 904 }, { "epoch": 0.05286214953271028, "grad_norm": 1.6794123649597168, "learning_rate": 1.9972793550353458e-05, "loss": 0.9279, "step": 905 }, { "epoch": 0.052920560747663555, "grad_norm": 4.265973091125488, "learning_rate": 1.9972653914931902e-05, "loss": 0.9468, "step": 906 }, { "epoch": 0.05297897196261682, "grad_norm": 2.2987382411956787, "learning_rate": 1.9972513922582507e-05, "loss": 0.9642, "step": 907 }, { "epoch": 0.05303738317757009, "grad_norm": 2.6488091945648193, "learning_rate": 1.997237357331028e-05, "loss": 0.852, "step": 908 }, { "epoch": 0.05309579439252336, "grad_norm": 4.267969131469727, "learning_rate": 1.9972232867120248e-05, "loss": 1.0185, "step": 909 }, { "epoch": 0.053154205607476634, "grad_norm": 3.508708953857422, "learning_rate": 1.9972091804017446e-05, "loss": 1.0184, "step": 910 }, { "epoch": 0.053212616822429906, "grad_norm": 2.6537604331970215, "learning_rate": 1.9971950384006918e-05, "loss": 0.9535, "step": 911 }, { "epoch": 0.05327102803738318, "grad_norm": 1.8273639678955078, "learning_rate": 1.997180860709373e-05, "loss": 0.927, "step": 912 }, { "epoch": 0.05332943925233645, "grad_norm": 2.2537319660186768, "learning_rate": 1.9971666473282957e-05, "loss": 0.9837, "step": 913 }, { "epoch": 0.05338785046728972, "grad_norm": 2.447763204574585, "learning_rate": 1.9971523982579682e-05, "loss": 0.94, "step": 914 }, { "epoch": 0.05344626168224299, "grad_norm": 2.268514633178711, "learning_rate": 1.997138113498901e-05, "loss": 1.1853, "step": 915 }, { "epoch": 0.053504672897196265, "grad_norm": 3.0485270023345947, "learning_rate": 1.9971237930516048e-05, "loss": 1.0469, "step": 916 }, { "epoch": 0.05356308411214953, "grad_norm": 2.239579677581787, "learning_rate": 1.9971094369165926e-05, "loss": 0.9755, "step": 917 }, { "epoch": 0.0536214953271028, "grad_norm": 1.8437409400939941, "learning_rate": 1.997095045094378e-05, "loss": 0.967, "step": 918 }, { "epoch": 0.05367990654205607, "grad_norm": 2.3486104011535645, "learning_rate": 1.997080617585476e-05, "loss": 0.9364, "step": 919 }, { "epoch": 0.053738317757009345, "grad_norm": 1.6643673181533813, "learning_rate": 1.9970661543904035e-05, "loss": 0.7346, "step": 920 }, { "epoch": 0.05379672897196262, "grad_norm": 2.04067325592041, "learning_rate": 1.9970516555096776e-05, "loss": 1.0066, "step": 921 }, { "epoch": 0.05385514018691589, "grad_norm": 1.893990397453308, "learning_rate": 1.997037120943817e-05, "loss": 0.8413, "step": 922 }, { "epoch": 0.05391355140186916, "grad_norm": 2.136812448501587, "learning_rate": 1.9970225506933426e-05, "loss": 1.1084, "step": 923 }, { "epoch": 0.05397196261682243, "grad_norm": 2.4160592555999756, "learning_rate": 1.9970079447587757e-05, "loss": 0.9987, "step": 924 }, { "epoch": 0.0540303738317757, "grad_norm": 1.6101447343826294, "learning_rate": 1.9969933031406386e-05, "loss": 0.7854, "step": 925 }, { "epoch": 0.054088785046728975, "grad_norm": 1.9359678030014038, "learning_rate": 1.9969786258394558e-05, "loss": 0.9913, "step": 926 }, { "epoch": 0.05414719626168224, "grad_norm": 2.9709768295288086, "learning_rate": 1.9969639128557524e-05, "loss": 0.9832, "step": 927 }, { "epoch": 0.05420560747663551, "grad_norm": 1.4892611503601074, "learning_rate": 1.996949164190055e-05, "loss": 0.7537, "step": 928 }, { "epoch": 0.05426401869158878, "grad_norm": 2.047776460647583, "learning_rate": 1.9969343798428916e-05, "loss": 0.9951, "step": 929 }, { "epoch": 0.054322429906542055, "grad_norm": 1.8847606182098389, "learning_rate": 1.9969195598147913e-05, "loss": 0.9814, "step": 930 }, { "epoch": 0.05438084112149533, "grad_norm": 2.395631790161133, "learning_rate": 1.9969047041062843e-05, "loss": 1.2027, "step": 931 }, { "epoch": 0.0544392523364486, "grad_norm": 2.5470528602600098, "learning_rate": 1.9968898127179025e-05, "loss": 0.9851, "step": 932 }, { "epoch": 0.05449766355140187, "grad_norm": 2.0016443729400635, "learning_rate": 1.996874885650179e-05, "loss": 0.8103, "step": 933 }, { "epoch": 0.05455607476635514, "grad_norm": 1.7423408031463623, "learning_rate": 1.9968599229036477e-05, "loss": 0.9084, "step": 934 }, { "epoch": 0.054614485981308414, "grad_norm": 1.8981355428695679, "learning_rate": 1.9968449244788443e-05, "loss": 1.0443, "step": 935 }, { "epoch": 0.054672897196261686, "grad_norm": 2.9868884086608887, "learning_rate": 1.9968298903763058e-05, "loss": 1.033, "step": 936 }, { "epoch": 0.05473130841121495, "grad_norm": 1.8401234149932861, "learning_rate": 1.99681482059657e-05, "loss": 1.1059, "step": 937 }, { "epoch": 0.05478971962616822, "grad_norm": 1.88363516330719, "learning_rate": 1.9967997151401763e-05, "loss": 0.9742, "step": 938 }, { "epoch": 0.054848130841121494, "grad_norm": 2.163285732269287, "learning_rate": 1.9967845740076656e-05, "loss": 0.8414, "step": 939 }, { "epoch": 0.054906542056074766, "grad_norm": 4.227875709533691, "learning_rate": 1.9967693971995792e-05, "loss": 0.9201, "step": 940 }, { "epoch": 0.05496495327102804, "grad_norm": 1.7737841606140137, "learning_rate": 1.996754184716461e-05, "loss": 0.9826, "step": 941 }, { "epoch": 0.05502336448598131, "grad_norm": 1.958332896232605, "learning_rate": 1.996738936558855e-05, "loss": 0.9314, "step": 942 }, { "epoch": 0.05508177570093458, "grad_norm": 2.0456223487854004, "learning_rate": 1.9967236527273072e-05, "loss": 1.0243, "step": 943 }, { "epoch": 0.05514018691588785, "grad_norm": 1.5303106307983398, "learning_rate": 1.9967083332223646e-05, "loss": 0.8785, "step": 944 }, { "epoch": 0.055198598130841124, "grad_norm": 1.4863743782043457, "learning_rate": 1.9966929780445752e-05, "loss": 0.8873, "step": 945 }, { "epoch": 0.055257009345794396, "grad_norm": 1.8162685632705688, "learning_rate": 1.996677587194489e-05, "loss": 1.1074, "step": 946 }, { "epoch": 0.05531542056074766, "grad_norm": 2.16066312789917, "learning_rate": 1.9966621606726563e-05, "loss": 0.9765, "step": 947 }, { "epoch": 0.05537383177570093, "grad_norm": 1.8644477128982544, "learning_rate": 1.9966466984796296e-05, "loss": 1.0158, "step": 948 }, { "epoch": 0.055432242990654204, "grad_norm": 1.6244113445281982, "learning_rate": 1.9966312006159625e-05, "loss": 0.8303, "step": 949 }, { "epoch": 0.055490654205607476, "grad_norm": 1.5949335098266602, "learning_rate": 1.9966156670822093e-05, "loss": 0.8507, "step": 950 }, { "epoch": 0.05554906542056075, "grad_norm": 1.8274977207183838, "learning_rate": 1.996600097878926e-05, "loss": 0.9203, "step": 951 }, { "epoch": 0.05560747663551402, "grad_norm": 2.367347240447998, "learning_rate": 1.99658449300667e-05, "loss": 0.9839, "step": 952 }, { "epoch": 0.05566588785046729, "grad_norm": 1.7627508640289307, "learning_rate": 1.9965688524659995e-05, "loss": 1.0603, "step": 953 }, { "epoch": 0.05572429906542056, "grad_norm": 2.2953574657440186, "learning_rate": 1.996553176257475e-05, "loss": 1.046, "step": 954 }, { "epoch": 0.055782710280373834, "grad_norm": 2.3259034156799316, "learning_rate": 1.996537464381657e-05, "loss": 1.1359, "step": 955 }, { "epoch": 0.055841121495327106, "grad_norm": 1.965043306350708, "learning_rate": 1.9965217168391075e-05, "loss": 1.1262, "step": 956 }, { "epoch": 0.05589953271028037, "grad_norm": 1.7047291994094849, "learning_rate": 1.996505933630391e-05, "loss": 0.9178, "step": 957 }, { "epoch": 0.05595794392523364, "grad_norm": 2.8486640453338623, "learning_rate": 1.9964901147560717e-05, "loss": 1.0472, "step": 958 }, { "epoch": 0.056016355140186914, "grad_norm": 2.1398425102233887, "learning_rate": 1.996474260216716e-05, "loss": 0.8814, "step": 959 }, { "epoch": 0.056074766355140186, "grad_norm": 3.2025949954986572, "learning_rate": 1.996458370012891e-05, "loss": 0.8851, "step": 960 }, { "epoch": 0.05613317757009346, "grad_norm": 2.0385286808013916, "learning_rate": 1.996442444145166e-05, "loss": 1.2211, "step": 961 }, { "epoch": 0.05619158878504673, "grad_norm": 2.269993543624878, "learning_rate": 1.996426482614111e-05, "loss": 1.1951, "step": 962 }, { "epoch": 0.05625, "grad_norm": 1.975446343421936, "learning_rate": 1.996410485420297e-05, "loss": 0.8218, "step": 963 }, { "epoch": 0.05630841121495327, "grad_norm": 1.5492337942123413, "learning_rate": 1.9963944525642966e-05, "loss": 1.021, "step": 964 }, { "epoch": 0.056366822429906545, "grad_norm": 1.7913854122161865, "learning_rate": 1.996378384046683e-05, "loss": 0.9544, "step": 965 }, { "epoch": 0.05642523364485981, "grad_norm": 1.9207265377044678, "learning_rate": 1.9963622798680326e-05, "loss": 0.9058, "step": 966 }, { "epoch": 0.05648364485981308, "grad_norm": 1.8008984327316284, "learning_rate": 1.9963461400289207e-05, "loss": 1.0644, "step": 967 }, { "epoch": 0.05654205607476635, "grad_norm": 2.3250365257263184, "learning_rate": 1.9963299645299254e-05, "loss": 0.944, "step": 968 }, { "epoch": 0.056600467289719625, "grad_norm": 1.6780451536178589, "learning_rate": 1.9963137533716256e-05, "loss": 0.9593, "step": 969 }, { "epoch": 0.0566588785046729, "grad_norm": 2.422816276550293, "learning_rate": 1.996297506554601e-05, "loss": 0.984, "step": 970 }, { "epoch": 0.05671728971962617, "grad_norm": 1.302551031112671, "learning_rate": 1.9962812240794344e-05, "loss": 0.8318, "step": 971 }, { "epoch": 0.05677570093457944, "grad_norm": 1.867315411567688, "learning_rate": 1.9962649059467078e-05, "loss": 0.9533, "step": 972 }, { "epoch": 0.05683411214953271, "grad_norm": 1.7055193185806274, "learning_rate": 1.9962485521570044e-05, "loss": 0.9176, "step": 973 }, { "epoch": 0.05689252336448598, "grad_norm": 1.8406949043273926, "learning_rate": 1.9962321627109107e-05, "loss": 0.8714, "step": 974 }, { "epoch": 0.056950934579439255, "grad_norm": 1.8778560161590576, "learning_rate": 1.9962157376090126e-05, "loss": 0.9319, "step": 975 }, { "epoch": 0.05700934579439252, "grad_norm": 1.91749107837677, "learning_rate": 1.9961992768518984e-05, "loss": 0.9416, "step": 976 }, { "epoch": 0.05706775700934579, "grad_norm": 1.33247971534729, "learning_rate": 1.9961827804401572e-05, "loss": 0.9903, "step": 977 }, { "epoch": 0.05712616822429906, "grad_norm": 2.018059253692627, "learning_rate": 1.996166248374379e-05, "loss": 0.929, "step": 978 }, { "epoch": 0.057184579439252335, "grad_norm": 1.9867018461227417, "learning_rate": 1.996149680655156e-05, "loss": 1.1033, "step": 979 }, { "epoch": 0.05724299065420561, "grad_norm": 1.639553189277649, "learning_rate": 1.9961330772830808e-05, "loss": 0.8251, "step": 980 }, { "epoch": 0.05730140186915888, "grad_norm": 1.5882385969161987, "learning_rate": 1.996116438258748e-05, "loss": 0.9503, "step": 981 }, { "epoch": 0.05735981308411215, "grad_norm": 2.22918438911438, "learning_rate": 1.9960997635827527e-05, "loss": 1.0421, "step": 982 }, { "epoch": 0.05741822429906542, "grad_norm": 2.176974058151245, "learning_rate": 1.996083053255692e-05, "loss": 1.1835, "step": 983 }, { "epoch": 0.057476635514018694, "grad_norm": 1.811576247215271, "learning_rate": 1.9960663072781637e-05, "loss": 0.8727, "step": 984 }, { "epoch": 0.057535046728971966, "grad_norm": 1.467742681503296, "learning_rate": 1.9960495256507678e-05, "loss": 0.8406, "step": 985 }, { "epoch": 0.05759345794392523, "grad_norm": 1.8373154401779175, "learning_rate": 1.996032708374104e-05, "loss": 0.9964, "step": 986 }, { "epoch": 0.0576518691588785, "grad_norm": 1.6620280742645264, "learning_rate": 1.9960158554487748e-05, "loss": 1.0993, "step": 987 }, { "epoch": 0.057710280373831774, "grad_norm": 1.8151620626449585, "learning_rate": 1.9959989668753835e-05, "loss": 1.1124, "step": 988 }, { "epoch": 0.057768691588785046, "grad_norm": 2.7846174240112305, "learning_rate": 1.995982042654534e-05, "loss": 1.1506, "step": 989 }, { "epoch": 0.05782710280373832, "grad_norm": 2.833338975906372, "learning_rate": 1.9959650827868323e-05, "loss": 1.0503, "step": 990 }, { "epoch": 0.05788551401869159, "grad_norm": 2.03955340385437, "learning_rate": 1.9959480872728857e-05, "loss": 0.9262, "step": 991 }, { "epoch": 0.05794392523364486, "grad_norm": 1.5486639738082886, "learning_rate": 1.995931056113302e-05, "loss": 0.8302, "step": 992 }, { "epoch": 0.05800233644859813, "grad_norm": 2.1168015003204346, "learning_rate": 1.9959139893086908e-05, "loss": 1.073, "step": 993 }, { "epoch": 0.058060747663551404, "grad_norm": 1.5095912218093872, "learning_rate": 1.9958968868596633e-05, "loss": 0.8766, "step": 994 }, { "epoch": 0.058119158878504676, "grad_norm": 1.995832920074463, "learning_rate": 1.9958797487668314e-05, "loss": 1.2209, "step": 995 }, { "epoch": 0.05817757009345794, "grad_norm": 2.4105966091156006, "learning_rate": 1.9958625750308087e-05, "loss": 0.9572, "step": 996 }, { "epoch": 0.05823598130841121, "grad_norm": 2.247588872909546, "learning_rate": 1.995845365652209e-05, "loss": 0.9467, "step": 997 }, { "epoch": 0.058294392523364484, "grad_norm": 1.8882514238357544, "learning_rate": 1.9958281206316497e-05, "loss": 0.9709, "step": 998 }, { "epoch": 0.058352803738317756, "grad_norm": 1.4931666851043701, "learning_rate": 1.995810839969747e-05, "loss": 0.837, "step": 999 }, { "epoch": 0.05841121495327103, "grad_norm": 2.293414354324341, "learning_rate": 1.995793523667119e-05, "loss": 1.0696, "step": 1000 }, { "epoch": 0.0584696261682243, "grad_norm": 1.6830387115478516, "learning_rate": 1.9957761717243868e-05, "loss": 1.0292, "step": 1001 }, { "epoch": 0.05852803738317757, "grad_norm": 2.242434501647949, "learning_rate": 1.99575878414217e-05, "loss": 1.1044, "step": 1002 }, { "epoch": 0.05858644859813084, "grad_norm": 1.8947081565856934, "learning_rate": 1.995741360921092e-05, "loss": 1.2036, "step": 1003 }, { "epoch": 0.058644859813084114, "grad_norm": 2.1248223781585693, "learning_rate": 1.995723902061776e-05, "loss": 1.0882, "step": 1004 }, { "epoch": 0.058703271028037386, "grad_norm": 1.3530209064483643, "learning_rate": 1.9957064075648466e-05, "loss": 0.9314, "step": 1005 }, { "epoch": 0.05876168224299065, "grad_norm": 1.935583472251892, "learning_rate": 1.9956888774309303e-05, "loss": 0.9897, "step": 1006 }, { "epoch": 0.05882009345794392, "grad_norm": 1.6351889371871948, "learning_rate": 1.9956713116606544e-05, "loss": 1.1065, "step": 1007 }, { "epoch": 0.058878504672897194, "grad_norm": 2.0450830459594727, "learning_rate": 1.9956537102546476e-05, "loss": 1.1152, "step": 1008 }, { "epoch": 0.058936915887850466, "grad_norm": 1.671181082725525, "learning_rate": 1.99563607321354e-05, "loss": 0.9907, "step": 1009 }, { "epoch": 0.05899532710280374, "grad_norm": 1.7395853996276855, "learning_rate": 1.9956184005379625e-05, "loss": 0.9774, "step": 1010 }, { "epoch": 0.05905373831775701, "grad_norm": 1.7470176219940186, "learning_rate": 1.995600692228548e-05, "loss": 0.9463, "step": 1011 }, { "epoch": 0.05911214953271028, "grad_norm": 1.7530840635299683, "learning_rate": 1.9955829482859296e-05, "loss": 0.9342, "step": 1012 }, { "epoch": 0.05917056074766355, "grad_norm": 1.4489161968231201, "learning_rate": 1.9955651687107433e-05, "loss": 0.817, "step": 1013 }, { "epoch": 0.059228971962616825, "grad_norm": 3.1723804473876953, "learning_rate": 1.995547353503625e-05, "loss": 1.0778, "step": 1014 }, { "epoch": 0.0592873831775701, "grad_norm": 1.886487364768982, "learning_rate": 1.995529502665212e-05, "loss": 0.8766, "step": 1015 }, { "epoch": 0.05934579439252336, "grad_norm": 4.204010486602783, "learning_rate": 1.995511616196144e-05, "loss": 1.0447, "step": 1016 }, { "epoch": 0.05940420560747663, "grad_norm": 2.850670337677002, "learning_rate": 1.9954936940970605e-05, "loss": 0.9766, "step": 1017 }, { "epoch": 0.059462616822429905, "grad_norm": 1.927808165550232, "learning_rate": 1.9954757363686034e-05, "loss": 0.9073, "step": 1018 }, { "epoch": 0.05952102803738318, "grad_norm": 1.6553452014923096, "learning_rate": 1.995457743011415e-05, "loss": 0.8131, "step": 1019 }, { "epoch": 0.05957943925233645, "grad_norm": 2.671975612640381, "learning_rate": 1.995439714026139e-05, "loss": 1.0102, "step": 1020 }, { "epoch": 0.05963785046728972, "grad_norm": 1.5396946668624878, "learning_rate": 1.9954216494134217e-05, "loss": 0.6661, "step": 1021 }, { "epoch": 0.05969626168224299, "grad_norm": 2.7867865562438965, "learning_rate": 1.9954035491739087e-05, "loss": 1.1453, "step": 1022 }, { "epoch": 0.05975467289719626, "grad_norm": 2.1099891662597656, "learning_rate": 1.9953854133082486e-05, "loss": 1.0808, "step": 1023 }, { "epoch": 0.059813084112149535, "grad_norm": 2.1019303798675537, "learning_rate": 1.9953672418170895e-05, "loss": 0.9996, "step": 1024 }, { "epoch": 0.05987149532710281, "grad_norm": 2.4491004943847656, "learning_rate": 1.9953490347010825e-05, "loss": 0.9663, "step": 1025 }, { "epoch": 0.05992990654205607, "grad_norm": 2.549213171005249, "learning_rate": 1.9953307919608794e-05, "loss": 0.9038, "step": 1026 }, { "epoch": 0.05998831775700934, "grad_norm": 2.4575719833374023, "learning_rate": 1.9953125135971328e-05, "loss": 1.3035, "step": 1027 }, { "epoch": 0.060046728971962615, "grad_norm": 3.630098581314087, "learning_rate": 1.9952941996104968e-05, "loss": 1.111, "step": 1028 }, { "epoch": 0.06010514018691589, "grad_norm": 3.6876111030578613, "learning_rate": 1.995275850001627e-05, "loss": 1.1573, "step": 1029 }, { "epoch": 0.06016355140186916, "grad_norm": 2.967266321182251, "learning_rate": 1.99525746477118e-05, "loss": 1.0591, "step": 1030 }, { "epoch": 0.06022196261682243, "grad_norm": 2.843449115753174, "learning_rate": 1.9952390439198138e-05, "loss": 1.0419, "step": 1031 }, { "epoch": 0.0602803738317757, "grad_norm": 2.3433868885040283, "learning_rate": 1.9952205874481882e-05, "loss": 0.9904, "step": 1032 }, { "epoch": 0.060338785046728974, "grad_norm": 2.2755134105682373, "learning_rate": 1.9952020953569634e-05, "loss": 0.955, "step": 1033 }, { "epoch": 0.060397196261682246, "grad_norm": 1.8302170038223267, "learning_rate": 1.9951835676468006e-05, "loss": 0.8585, "step": 1034 }, { "epoch": 0.06045560747663552, "grad_norm": 1.7368472814559937, "learning_rate": 1.9951650043183644e-05, "loss": 1.0335, "step": 1035 }, { "epoch": 0.06051401869158878, "grad_norm": 2.6326587200164795, "learning_rate": 1.995146405372318e-05, "loss": 0.9586, "step": 1036 }, { "epoch": 0.060572429906542054, "grad_norm": 1.3952580690383911, "learning_rate": 1.9951277708093273e-05, "loss": 0.801, "step": 1037 }, { "epoch": 0.060630841121495326, "grad_norm": 2.154667377471924, "learning_rate": 1.99510910063006e-05, "loss": 1.1445, "step": 1038 }, { "epoch": 0.0606892523364486, "grad_norm": 2.221604824066162, "learning_rate": 1.9950903948351827e-05, "loss": 0.9477, "step": 1039 }, { "epoch": 0.06074766355140187, "grad_norm": 2.824115037918091, "learning_rate": 1.9950716534253667e-05, "loss": 0.912, "step": 1040 }, { "epoch": 0.06080607476635514, "grad_norm": 1.9156889915466309, "learning_rate": 1.9950528764012817e-05, "loss": 0.8866, "step": 1041 }, { "epoch": 0.06086448598130841, "grad_norm": 2.0517332553863525, "learning_rate": 1.9950340637635998e-05, "loss": 0.9973, "step": 1042 }, { "epoch": 0.060922897196261684, "grad_norm": 2.0428075790405273, "learning_rate": 1.9950152155129947e-05, "loss": 0.9426, "step": 1043 }, { "epoch": 0.060981308411214956, "grad_norm": 2.7193078994750977, "learning_rate": 1.994996331650141e-05, "loss": 1.0607, "step": 1044 }, { "epoch": 0.06103971962616823, "grad_norm": 1.853631615638733, "learning_rate": 1.9949774121757136e-05, "loss": 0.851, "step": 1045 }, { "epoch": 0.06109813084112149, "grad_norm": 2.4962949752807617, "learning_rate": 1.994958457090391e-05, "loss": 0.8601, "step": 1046 }, { "epoch": 0.061156542056074764, "grad_norm": 2.301140069961548, "learning_rate": 1.994939466394851e-05, "loss": 1.1527, "step": 1047 }, { "epoch": 0.061214953271028036, "grad_norm": 2.343777894973755, "learning_rate": 1.9949204400897732e-05, "loss": 1.2962, "step": 1048 }, { "epoch": 0.06127336448598131, "grad_norm": 2.051368236541748, "learning_rate": 1.994901378175839e-05, "loss": 1.004, "step": 1049 }, { "epoch": 0.06133177570093458, "grad_norm": 2.5737152099609375, "learning_rate": 1.99488228065373e-05, "loss": 1.2082, "step": 1050 }, { "epoch": 0.06139018691588785, "grad_norm": 1.6298985481262207, "learning_rate": 1.9948631475241302e-05, "loss": 0.9044, "step": 1051 }, { "epoch": 0.06144859813084112, "grad_norm": 1.792435884475708, "learning_rate": 1.994843978787724e-05, "loss": 1.0357, "step": 1052 }, { "epoch": 0.061507009345794394, "grad_norm": 1.7093415260314941, "learning_rate": 1.9948247744451977e-05, "loss": 0.8705, "step": 1053 }, { "epoch": 0.061565420560747666, "grad_norm": 3.8347060680389404, "learning_rate": 1.994805534497239e-05, "loss": 0.9191, "step": 1054 }, { "epoch": 0.06162383177570094, "grad_norm": 1.5813239812850952, "learning_rate": 1.9947862589445358e-05, "loss": 0.9007, "step": 1055 }, { "epoch": 0.0616822429906542, "grad_norm": 2.2858574390411377, "learning_rate": 1.994766947787778e-05, "loss": 1.0405, "step": 1056 }, { "epoch": 0.061740654205607474, "grad_norm": 1.9279664754867554, "learning_rate": 1.9947476010276576e-05, "loss": 1.1096, "step": 1057 }, { "epoch": 0.061799065420560746, "grad_norm": 1.804816484451294, "learning_rate": 1.9947282186648662e-05, "loss": 0.9021, "step": 1058 }, { "epoch": 0.06185747663551402, "grad_norm": 1.9088184833526611, "learning_rate": 1.994708800700098e-05, "loss": 0.9968, "step": 1059 }, { "epoch": 0.06191588785046729, "grad_norm": 1.9842971563339233, "learning_rate": 1.9946893471340477e-05, "loss": 1.082, "step": 1060 }, { "epoch": 0.06197429906542056, "grad_norm": 2.1674110889434814, "learning_rate": 1.9946698579674114e-05, "loss": 1.0113, "step": 1061 }, { "epoch": 0.06203271028037383, "grad_norm": 1.886522650718689, "learning_rate": 1.9946503332008873e-05, "loss": 0.7468, "step": 1062 }, { "epoch": 0.062091121495327105, "grad_norm": 2.2841544151306152, "learning_rate": 1.9946307728351737e-05, "loss": 0.8371, "step": 1063 }, { "epoch": 0.06214953271028038, "grad_norm": 1.7879679203033447, "learning_rate": 1.9946111768709703e-05, "loss": 1.0304, "step": 1064 }, { "epoch": 0.06220794392523365, "grad_norm": 3.9758338928222656, "learning_rate": 1.9945915453089795e-05, "loss": 1.1284, "step": 1065 }, { "epoch": 0.06226635514018691, "grad_norm": 1.9718042612075806, "learning_rate": 1.9945718781499032e-05, "loss": 1.0467, "step": 1066 }, { "epoch": 0.062324766355140185, "grad_norm": 2.17378830909729, "learning_rate": 1.994552175394445e-05, "loss": 0.8528, "step": 1067 }, { "epoch": 0.06238317757009346, "grad_norm": 1.3763747215270996, "learning_rate": 1.994532437043311e-05, "loss": 0.7691, "step": 1068 }, { "epoch": 0.06244158878504673, "grad_norm": 1.9397703409194946, "learning_rate": 1.994512663097207e-05, "loss": 0.9984, "step": 1069 }, { "epoch": 0.0625, "grad_norm": 2.29384708404541, "learning_rate": 1.9944928535568412e-05, "loss": 1.0324, "step": 1070 }, { "epoch": 0.06255841121495327, "grad_norm": 2.105978488922119, "learning_rate": 1.9944730084229218e-05, "loss": 0.8059, "step": 1071 }, { "epoch": 0.06261682242990654, "grad_norm": 1.4487301111221313, "learning_rate": 1.9944531276961596e-05, "loss": 0.9569, "step": 1072 }, { "epoch": 0.06267523364485982, "grad_norm": 2.2092318534851074, "learning_rate": 1.994433211377266e-05, "loss": 0.9138, "step": 1073 }, { "epoch": 0.06273364485981309, "grad_norm": 2.2629339694976807, "learning_rate": 1.9944132594669542e-05, "loss": 1.0621, "step": 1074 }, { "epoch": 0.06279205607476636, "grad_norm": 2.1412227153778076, "learning_rate": 1.994393271965938e-05, "loss": 1.098, "step": 1075 }, { "epoch": 0.06285046728971963, "grad_norm": 2.1901285648345947, "learning_rate": 1.9943732488749328e-05, "loss": 0.9825, "step": 1076 }, { "epoch": 0.0629088785046729, "grad_norm": 1.6595274209976196, "learning_rate": 1.9943531901946552e-05, "loss": 0.9828, "step": 1077 }, { "epoch": 0.06296728971962617, "grad_norm": 1.5883798599243164, "learning_rate": 1.9943330959258228e-05, "loss": 0.7781, "step": 1078 }, { "epoch": 0.06302570093457945, "grad_norm": 2.487004518508911, "learning_rate": 1.9943129660691555e-05, "loss": 0.9162, "step": 1079 }, { "epoch": 0.0630841121495327, "grad_norm": 1.8369429111480713, "learning_rate": 1.994292800625373e-05, "loss": 0.9465, "step": 1080 }, { "epoch": 0.06314252336448598, "grad_norm": 1.7376034259796143, "learning_rate": 1.9942725995951978e-05, "loss": 1.1365, "step": 1081 }, { "epoch": 0.06320093457943925, "grad_norm": 1.5645625591278076, "learning_rate": 1.9942523629793523e-05, "loss": 1.1003, "step": 1082 }, { "epoch": 0.06325934579439252, "grad_norm": 1.6781522035598755, "learning_rate": 1.994232090778561e-05, "loss": 1.0056, "step": 1083 }, { "epoch": 0.06331775700934579, "grad_norm": 1.9139364957809448, "learning_rate": 1.9942117829935496e-05, "loss": 0.9586, "step": 1084 }, { "epoch": 0.06337616822429906, "grad_norm": 7.239262104034424, "learning_rate": 1.9941914396250447e-05, "loss": 0.9922, "step": 1085 }, { "epoch": 0.06343457943925233, "grad_norm": 2.148601531982422, "learning_rate": 1.9941710606737743e-05, "loss": 0.9302, "step": 1086 }, { "epoch": 0.0634929906542056, "grad_norm": 1.4099048376083374, "learning_rate": 1.994150646140468e-05, "loss": 0.8567, "step": 1087 }, { "epoch": 0.06355140186915888, "grad_norm": 2.3588309288024902, "learning_rate": 1.9941301960258566e-05, "loss": 0.9797, "step": 1088 }, { "epoch": 0.06360981308411215, "grad_norm": 1.8252464532852173, "learning_rate": 1.9941097103306716e-05, "loss": 1.0753, "step": 1089 }, { "epoch": 0.06366822429906542, "grad_norm": 2.0444886684417725, "learning_rate": 1.9940891890556468e-05, "loss": 0.93, "step": 1090 }, { "epoch": 0.06372663551401869, "grad_norm": 1.75873863697052, "learning_rate": 1.994068632201516e-05, "loss": 1.0441, "step": 1091 }, { "epoch": 0.06378504672897196, "grad_norm": 1.9217807054519653, "learning_rate": 1.9940480397690153e-05, "loss": 0.9402, "step": 1092 }, { "epoch": 0.06384345794392524, "grad_norm": 1.8753278255462646, "learning_rate": 1.9940274117588815e-05, "loss": 1.2259, "step": 1093 }, { "epoch": 0.06390186915887851, "grad_norm": 2.2196438312530518, "learning_rate": 1.9940067481718532e-05, "loss": 0.9751, "step": 1094 }, { "epoch": 0.06396028037383178, "grad_norm": 1.6323736906051636, "learning_rate": 1.99398604900867e-05, "loss": 0.867, "step": 1095 }, { "epoch": 0.06401869158878505, "grad_norm": 1.7348361015319824, "learning_rate": 1.9939653142700724e-05, "loss": 0.9403, "step": 1096 }, { "epoch": 0.06407710280373832, "grad_norm": 1.5506447553634644, "learning_rate": 1.9939445439568023e-05, "loss": 1.043, "step": 1097 }, { "epoch": 0.0641355140186916, "grad_norm": 1.7384591102600098, "learning_rate": 1.993923738069604e-05, "loss": 1.0106, "step": 1098 }, { "epoch": 0.06419392523364487, "grad_norm": 1.560964822769165, "learning_rate": 1.9939028966092213e-05, "loss": 1.0161, "step": 1099 }, { "epoch": 0.06425233644859812, "grad_norm": 2.281275749206543, "learning_rate": 1.9938820195764003e-05, "loss": 0.9236, "step": 1100 }, { "epoch": 0.0643107476635514, "grad_norm": 1.6457886695861816, "learning_rate": 1.9938611069718888e-05, "loss": 0.942, "step": 1101 }, { "epoch": 0.06436915887850467, "grad_norm": 2.348402976989746, "learning_rate": 1.9938401587964344e-05, "loss": 0.935, "step": 1102 }, { "epoch": 0.06442757009345794, "grad_norm": 1.746235966682434, "learning_rate": 1.9938191750507875e-05, "loss": 0.9779, "step": 1103 }, { "epoch": 0.06448598130841121, "grad_norm": 3.338423728942871, "learning_rate": 1.9937981557356986e-05, "loss": 1.0703, "step": 1104 }, { "epoch": 0.06454439252336448, "grad_norm": 1.8334763050079346, "learning_rate": 1.9937771008519205e-05, "loss": 0.9926, "step": 1105 }, { "epoch": 0.06460280373831775, "grad_norm": 2.4220383167266846, "learning_rate": 1.9937560104002064e-05, "loss": 0.9202, "step": 1106 }, { "epoch": 0.06466121495327103, "grad_norm": 2.2998549938201904, "learning_rate": 1.9937348843813115e-05, "loss": 0.9291, "step": 1107 }, { "epoch": 0.0647196261682243, "grad_norm": 3.7736599445343018, "learning_rate": 1.9937137227959914e-05, "loss": 1.0301, "step": 1108 }, { "epoch": 0.06477803738317757, "grad_norm": 2.3734660148620605, "learning_rate": 1.993692525645004e-05, "loss": 1.0418, "step": 1109 }, { "epoch": 0.06483644859813084, "grad_norm": 1.602410912513733, "learning_rate": 1.993671292929108e-05, "loss": 0.9209, "step": 1110 }, { "epoch": 0.06489485981308411, "grad_norm": 3.152744770050049, "learning_rate": 1.993650024649062e-05, "loss": 0.9986, "step": 1111 }, { "epoch": 0.06495327102803738, "grad_norm": 1.5282350778579712, "learning_rate": 1.993628720805629e-05, "loss": 0.9533, "step": 1112 }, { "epoch": 0.06501168224299066, "grad_norm": 2.7875173091888428, "learning_rate": 1.993607381399571e-05, "loss": 1.2345, "step": 1113 }, { "epoch": 0.06507009345794393, "grad_norm": 2.028057813644409, "learning_rate": 1.9935860064316513e-05, "loss": 1.0273, "step": 1114 }, { "epoch": 0.0651285046728972, "grad_norm": 1.5650556087493896, "learning_rate": 1.9935645959026352e-05, "loss": 0.9507, "step": 1115 }, { "epoch": 0.06518691588785047, "grad_norm": 2.8704676628112793, "learning_rate": 1.993543149813289e-05, "loss": 1.0663, "step": 1116 }, { "epoch": 0.06524532710280374, "grad_norm": 1.3004084825515747, "learning_rate": 1.99352166816438e-05, "loss": 0.8348, "step": 1117 }, { "epoch": 0.06530373831775702, "grad_norm": 2.4928834438323975, "learning_rate": 1.9935001509566772e-05, "loss": 0.9801, "step": 1118 }, { "epoch": 0.06536214953271029, "grad_norm": 2.542391777038574, "learning_rate": 1.9934785981909507e-05, "loss": 0.8914, "step": 1119 }, { "epoch": 0.06542056074766354, "grad_norm": 2.2277097702026367, "learning_rate": 1.9934570098679723e-05, "loss": 1.1575, "step": 1120 }, { "epoch": 0.06547897196261682, "grad_norm": 1.5721325874328613, "learning_rate": 1.993435385988514e-05, "loss": 0.8939, "step": 1121 }, { "epoch": 0.06553738317757009, "grad_norm": 3.2750327587127686, "learning_rate": 1.9934137265533503e-05, "loss": 0.9941, "step": 1122 }, { "epoch": 0.06559579439252336, "grad_norm": 2.028277635574341, "learning_rate": 1.9933920315632557e-05, "loss": 1.0348, "step": 1123 }, { "epoch": 0.06565420560747663, "grad_norm": 2.881986141204834, "learning_rate": 1.9933703010190078e-05, "loss": 0.9365, "step": 1124 }, { "epoch": 0.0657126168224299, "grad_norm": 1.4585227966308594, "learning_rate": 1.993348534921383e-05, "loss": 0.9627, "step": 1125 }, { "epoch": 0.06577102803738318, "grad_norm": 2.2979488372802734, "learning_rate": 1.9933267332711615e-05, "loss": 1.0889, "step": 1126 }, { "epoch": 0.06582943925233645, "grad_norm": 1.9356017112731934, "learning_rate": 1.9933048960691228e-05, "loss": 0.9277, "step": 1127 }, { "epoch": 0.06588785046728972, "grad_norm": 1.8648890256881714, "learning_rate": 1.9932830233160488e-05, "loss": 1.0081, "step": 1128 }, { "epoch": 0.06594626168224299, "grad_norm": 2.8722264766693115, "learning_rate": 1.9932611150127225e-05, "loss": 0.9149, "step": 1129 }, { "epoch": 0.06600467289719626, "grad_norm": 1.3534646034240723, "learning_rate": 1.9932391711599275e-05, "loss": 0.8876, "step": 1130 }, { "epoch": 0.06606308411214953, "grad_norm": 2.333091974258423, "learning_rate": 1.9932171917584496e-05, "loss": 0.989, "step": 1131 }, { "epoch": 0.0661214953271028, "grad_norm": 2.607196092605591, "learning_rate": 1.9931951768090755e-05, "loss": 1.0747, "step": 1132 }, { "epoch": 0.06617990654205608, "grad_norm": 1.9509050846099854, "learning_rate": 1.9931731263125926e-05, "loss": 0.9769, "step": 1133 }, { "epoch": 0.06623831775700935, "grad_norm": 3.463514566421509, "learning_rate": 1.993151040269791e-05, "loss": 1.1148, "step": 1134 }, { "epoch": 0.06629672897196262, "grad_norm": 1.4024981260299683, "learning_rate": 1.9931289186814604e-05, "loss": 0.8064, "step": 1135 }, { "epoch": 0.06635514018691589, "grad_norm": 3.365387201309204, "learning_rate": 1.9931067615483927e-05, "loss": 0.9029, "step": 1136 }, { "epoch": 0.06641355140186916, "grad_norm": 2.4246180057525635, "learning_rate": 1.9930845688713815e-05, "loss": 1.067, "step": 1137 }, { "epoch": 0.06647196261682244, "grad_norm": 2.099381446838379, "learning_rate": 1.99306234065122e-05, "loss": 0.9508, "step": 1138 }, { "epoch": 0.06653037383177571, "grad_norm": 2.392556667327881, "learning_rate": 1.9930400768887048e-05, "loss": 0.9276, "step": 1139 }, { "epoch": 0.06658878504672897, "grad_norm": 1.7848774194717407, "learning_rate": 1.993017777584632e-05, "loss": 0.9066, "step": 1140 }, { "epoch": 0.06664719626168224, "grad_norm": 1.434564471244812, "learning_rate": 1.9929954427398e-05, "loss": 0.8299, "step": 1141 }, { "epoch": 0.06670560747663551, "grad_norm": 2.214189291000366, "learning_rate": 1.9929730723550084e-05, "loss": 0.8364, "step": 1142 }, { "epoch": 0.06676401869158878, "grad_norm": 1.9577558040618896, "learning_rate": 1.9929506664310576e-05, "loss": 1.0372, "step": 1143 }, { "epoch": 0.06682242990654205, "grad_norm": 1.746868371963501, "learning_rate": 1.9929282249687495e-05, "loss": 0.8601, "step": 1144 }, { "epoch": 0.06688084112149532, "grad_norm": 1.569650411605835, "learning_rate": 1.9929057479688877e-05, "loss": 0.7542, "step": 1145 }, { "epoch": 0.0669392523364486, "grad_norm": 2.28975248336792, "learning_rate": 1.992883235432276e-05, "loss": 0.8771, "step": 1146 }, { "epoch": 0.06699766355140187, "grad_norm": 1.8110569715499878, "learning_rate": 1.9928606873597206e-05, "loss": 0.9767, "step": 1147 }, { "epoch": 0.06705607476635514, "grad_norm": 2.2776918411254883, "learning_rate": 1.9928381037520285e-05, "loss": 1.0092, "step": 1148 }, { "epoch": 0.06711448598130841, "grad_norm": 1.5575401782989502, "learning_rate": 1.9928154846100077e-05, "loss": 0.7796, "step": 1149 }, { "epoch": 0.06717289719626168, "grad_norm": 1.8626700639724731, "learning_rate": 1.9927928299344675e-05, "loss": 0.8364, "step": 1150 }, { "epoch": 0.06723130841121495, "grad_norm": 1.8004449605941772, "learning_rate": 1.9927701397262198e-05, "loss": 1.0575, "step": 1151 }, { "epoch": 0.06728971962616823, "grad_norm": 1.750531554222107, "learning_rate": 1.992747413986076e-05, "loss": 1.063, "step": 1152 }, { "epoch": 0.0673481308411215, "grad_norm": 1.649978756904602, "learning_rate": 1.992724652714849e-05, "loss": 1.0936, "step": 1153 }, { "epoch": 0.06740654205607477, "grad_norm": 2.025684118270874, "learning_rate": 1.9927018559133543e-05, "loss": 0.9038, "step": 1154 }, { "epoch": 0.06746495327102804, "grad_norm": 1.611706018447876, "learning_rate": 1.9926790235824076e-05, "loss": 1.0866, "step": 1155 }, { "epoch": 0.06752336448598131, "grad_norm": 1.8889316320419312, "learning_rate": 1.9926561557228258e-05, "loss": 0.9232, "step": 1156 }, { "epoch": 0.06758177570093458, "grad_norm": 1.817462682723999, "learning_rate": 1.9926332523354272e-05, "loss": 0.9408, "step": 1157 }, { "epoch": 0.06764018691588786, "grad_norm": 1.5879900455474854, "learning_rate": 1.992610313421032e-05, "loss": 0.9603, "step": 1158 }, { "epoch": 0.06769859813084113, "grad_norm": 1.6279844045639038, "learning_rate": 1.9925873389804614e-05, "loss": 0.8592, "step": 1159 }, { "epoch": 0.06775700934579439, "grad_norm": 1.660894513130188, "learning_rate": 1.9925643290145368e-05, "loss": 1.0322, "step": 1160 }, { "epoch": 0.06781542056074766, "grad_norm": 2.134969472885132, "learning_rate": 1.9925412835240826e-05, "loss": 0.9864, "step": 1161 }, { "epoch": 0.06787383177570093, "grad_norm": 1.2365294694900513, "learning_rate": 1.9925182025099234e-05, "loss": 0.8536, "step": 1162 }, { "epoch": 0.0679322429906542, "grad_norm": 2.9140548706054688, "learning_rate": 1.9924950859728846e-05, "loss": 0.9455, "step": 1163 }, { "epoch": 0.06799065420560747, "grad_norm": 1.8330143690109253, "learning_rate": 1.9924719339137943e-05, "loss": 0.7803, "step": 1164 }, { "epoch": 0.06804906542056074, "grad_norm": 2.3410847187042236, "learning_rate": 1.9924487463334808e-05, "loss": 1.0688, "step": 1165 }, { "epoch": 0.06810747663551402, "grad_norm": 2.7086474895477295, "learning_rate": 1.9924255232327746e-05, "loss": 1.0863, "step": 1166 }, { "epoch": 0.06816588785046729, "grad_norm": 2.4889116287231445, "learning_rate": 1.992402264612506e-05, "loss": 1.1554, "step": 1167 }, { "epoch": 0.06822429906542056, "grad_norm": 2.205076217651367, "learning_rate": 1.992378970473508e-05, "loss": 1.0263, "step": 1168 }, { "epoch": 0.06828271028037383, "grad_norm": 2.345505714416504, "learning_rate": 1.992355640816614e-05, "loss": 0.9351, "step": 1169 }, { "epoch": 0.0683411214953271, "grad_norm": 1.8939768075942993, "learning_rate": 1.992332275642659e-05, "loss": 1.0092, "step": 1170 }, { "epoch": 0.06839953271028038, "grad_norm": 1.6703588962554932, "learning_rate": 1.9923088749524798e-05, "loss": 0.9609, "step": 1171 }, { "epoch": 0.06845794392523365, "grad_norm": 2.506964921951294, "learning_rate": 1.9922854387469133e-05, "loss": 1.0595, "step": 1172 }, { "epoch": 0.06851635514018692, "grad_norm": 2.3328373432159424, "learning_rate": 1.9922619670267983e-05, "loss": 1.0127, "step": 1173 }, { "epoch": 0.06857476635514019, "grad_norm": 2.305602788925171, "learning_rate": 1.9922384597929753e-05, "loss": 0.9157, "step": 1174 }, { "epoch": 0.06863317757009346, "grad_norm": 1.667596697807312, "learning_rate": 1.9922149170462854e-05, "loss": 1.0085, "step": 1175 }, { "epoch": 0.06869158878504673, "grad_norm": 2.1179115772247314, "learning_rate": 1.9921913387875715e-05, "loss": 0.9791, "step": 1176 }, { "epoch": 0.06875, "grad_norm": 2.454700231552124, "learning_rate": 1.9921677250176768e-05, "loss": 0.9305, "step": 1177 }, { "epoch": 0.06880841121495328, "grad_norm": 1.793745756149292, "learning_rate": 1.9921440757374467e-05, "loss": 1.0898, "step": 1178 }, { "epoch": 0.06886682242990654, "grad_norm": 4.063565254211426, "learning_rate": 1.9921203909477283e-05, "loss": 0.9684, "step": 1179 }, { "epoch": 0.0689252336448598, "grad_norm": 1.2870346307754517, "learning_rate": 1.9920966706493686e-05, "loss": 0.8318, "step": 1180 }, { "epoch": 0.06898364485981308, "grad_norm": 5.614635467529297, "learning_rate": 1.9920729148432166e-05, "loss": 1.0897, "step": 1181 }, { "epoch": 0.06904205607476635, "grad_norm": 2.1349785327911377, "learning_rate": 1.992049123530123e-05, "loss": 0.8985, "step": 1182 }, { "epoch": 0.06910046728971962, "grad_norm": 3.8864517211914062, "learning_rate": 1.9920252967109387e-05, "loss": 0.794, "step": 1183 }, { "epoch": 0.0691588785046729, "grad_norm": 2.271613121032715, "learning_rate": 1.9920014343865165e-05, "loss": 1.0132, "step": 1184 }, { "epoch": 0.06921728971962617, "grad_norm": 1.9539682865142822, "learning_rate": 1.9919775365577113e-05, "loss": 1.0216, "step": 1185 }, { "epoch": 0.06927570093457944, "grad_norm": 3.938863515853882, "learning_rate": 1.991953603225377e-05, "loss": 1.0169, "step": 1186 }, { "epoch": 0.06933411214953271, "grad_norm": 1.6922250986099243, "learning_rate": 1.9919296343903718e-05, "loss": 1.19, "step": 1187 }, { "epoch": 0.06939252336448598, "grad_norm": 2.7351274490356445, "learning_rate": 1.9919056300535526e-05, "loss": 0.9582, "step": 1188 }, { "epoch": 0.06945093457943925, "grad_norm": 1.6308810710906982, "learning_rate": 1.9918815902157788e-05, "loss": 0.9131, "step": 1189 }, { "epoch": 0.06950934579439252, "grad_norm": 1.435073971748352, "learning_rate": 1.9918575148779102e-05, "loss": 0.9513, "step": 1190 }, { "epoch": 0.0695677570093458, "grad_norm": 2.0457875728607178, "learning_rate": 1.9918334040408095e-05, "loss": 0.9169, "step": 1191 }, { "epoch": 0.06962616822429907, "grad_norm": 1.8448344469070435, "learning_rate": 1.991809257705339e-05, "loss": 1.1217, "step": 1192 }, { "epoch": 0.06968457943925234, "grad_norm": 2.031508684158325, "learning_rate": 1.9917850758723628e-05, "loss": 0.942, "step": 1193 }, { "epoch": 0.06974299065420561, "grad_norm": 1.7826287746429443, "learning_rate": 1.991760858542747e-05, "loss": 0.922, "step": 1194 }, { "epoch": 0.06980140186915888, "grad_norm": 1.7681804895401, "learning_rate": 1.9917366057173576e-05, "loss": 0.8409, "step": 1195 }, { "epoch": 0.06985981308411215, "grad_norm": 1.4224016666412354, "learning_rate": 1.9917123173970632e-05, "loss": 0.9867, "step": 1196 }, { "epoch": 0.06991822429906543, "grad_norm": 1.6624507904052734, "learning_rate": 1.991687993582733e-05, "loss": 0.8573, "step": 1197 }, { "epoch": 0.0699766355140187, "grad_norm": 1.6536681652069092, "learning_rate": 1.9916636342752374e-05, "loss": 0.9811, "step": 1198 }, { "epoch": 0.07003504672897196, "grad_norm": 1.743377447128296, "learning_rate": 1.9916392394754483e-05, "loss": 0.8658, "step": 1199 }, { "epoch": 0.07009345794392523, "grad_norm": 2.354041337966919, "learning_rate": 1.9916148091842385e-05, "loss": 1.0578, "step": 1200 }, { "epoch": 0.0701518691588785, "grad_norm": 1.7721045017242432, "learning_rate": 1.9915903434024834e-05, "loss": 0.9411, "step": 1201 }, { "epoch": 0.07021028037383177, "grad_norm": 2.4312074184417725, "learning_rate": 1.9915658421310574e-05, "loss": 1.014, "step": 1202 }, { "epoch": 0.07026869158878504, "grad_norm": 1.5287748575210571, "learning_rate": 1.991541305370838e-05, "loss": 0.848, "step": 1203 }, { "epoch": 0.07032710280373831, "grad_norm": 1.8467363119125366, "learning_rate": 1.9915167331227035e-05, "loss": 0.8864, "step": 1204 }, { "epoch": 0.07038551401869159, "grad_norm": 2.3971807956695557, "learning_rate": 1.991492125387533e-05, "loss": 1.3305, "step": 1205 }, { "epoch": 0.07044392523364486, "grad_norm": 1.4164888858795166, "learning_rate": 1.991467482166207e-05, "loss": 0.8895, "step": 1206 }, { "epoch": 0.07050233644859813, "grad_norm": 2.1155097484588623, "learning_rate": 1.9914428034596085e-05, "loss": 1.0183, "step": 1207 }, { "epoch": 0.0705607476635514, "grad_norm": 1.931864619255066, "learning_rate": 1.9914180892686202e-05, "loss": 1.0308, "step": 1208 }, { "epoch": 0.07061915887850467, "grad_norm": 3.477329730987549, "learning_rate": 1.991393339594126e-05, "loss": 1.0629, "step": 1209 }, { "epoch": 0.07067757009345794, "grad_norm": 2.033775806427002, "learning_rate": 1.9913685544370133e-05, "loss": 0.9928, "step": 1210 }, { "epoch": 0.07073598130841122, "grad_norm": 3.44413161277771, "learning_rate": 1.9913437337981673e-05, "loss": 1.0351, "step": 1211 }, { "epoch": 0.07079439252336449, "grad_norm": 1.77936589717865, "learning_rate": 1.9913188776784776e-05, "loss": 1.1247, "step": 1212 }, { "epoch": 0.07085280373831776, "grad_norm": 2.032287120819092, "learning_rate": 1.9912939860788336e-05, "loss": 0.7352, "step": 1213 }, { "epoch": 0.07091121495327103, "grad_norm": 2.595862627029419, "learning_rate": 1.991269059000126e-05, "loss": 0.9306, "step": 1214 }, { "epoch": 0.0709696261682243, "grad_norm": 1.5243034362792969, "learning_rate": 1.9912440964432468e-05, "loss": 0.6662, "step": 1215 }, { "epoch": 0.07102803738317758, "grad_norm": 1.9893152713775635, "learning_rate": 1.99121909840909e-05, "loss": 0.8522, "step": 1216 }, { "epoch": 0.07108644859813085, "grad_norm": 2.2400925159454346, "learning_rate": 1.9911940648985495e-05, "loss": 1.147, "step": 1217 }, { "epoch": 0.07114485981308412, "grad_norm": 1.6131230592727661, "learning_rate": 1.991168995912522e-05, "loss": 0.9577, "step": 1218 }, { "epoch": 0.07120327102803738, "grad_norm": 2.064711809158325, "learning_rate": 1.9911438914519045e-05, "loss": 0.9664, "step": 1219 }, { "epoch": 0.07126168224299065, "grad_norm": 1.6169739961624146, "learning_rate": 1.9911187515175953e-05, "loss": 0.9995, "step": 1220 }, { "epoch": 0.07132009345794392, "grad_norm": 2.2474820613861084, "learning_rate": 1.9910935761104943e-05, "loss": 0.9119, "step": 1221 }, { "epoch": 0.07137850467289719, "grad_norm": 1.618799090385437, "learning_rate": 1.9910683652315024e-05, "loss": 1.0117, "step": 1222 }, { "epoch": 0.07143691588785046, "grad_norm": 2.218634605407715, "learning_rate": 1.991043118881522e-05, "loss": 0.9595, "step": 1223 }, { "epoch": 0.07149532710280374, "grad_norm": 1.6658719778060913, "learning_rate": 1.991017837061457e-05, "loss": 0.7887, "step": 1224 }, { "epoch": 0.071553738317757, "grad_norm": 2.315864086151123, "learning_rate": 1.990992519772212e-05, "loss": 0.7643, "step": 1225 }, { "epoch": 0.07161214953271028, "grad_norm": 3.477241277694702, "learning_rate": 1.990967167014693e-05, "loss": 1.0069, "step": 1226 }, { "epoch": 0.07167056074766355, "grad_norm": 2.398040533065796, "learning_rate": 1.9909417787898077e-05, "loss": 0.984, "step": 1227 }, { "epoch": 0.07172897196261682, "grad_norm": 2.389641761779785, "learning_rate": 1.9909163550984644e-05, "loss": 1.019, "step": 1228 }, { "epoch": 0.0717873831775701, "grad_norm": 1.563790202140808, "learning_rate": 1.9908908959415734e-05, "loss": 1.0047, "step": 1229 }, { "epoch": 0.07184579439252337, "grad_norm": 2.4391841888427734, "learning_rate": 1.9908654013200455e-05, "loss": 0.9529, "step": 1230 }, { "epoch": 0.07190420560747664, "grad_norm": 1.757702112197876, "learning_rate": 1.9908398712347938e-05, "loss": 0.8273, "step": 1231 }, { "epoch": 0.07196261682242991, "grad_norm": 1.0163698196411133, "learning_rate": 1.990814305686731e-05, "loss": 0.8136, "step": 1232 }, { "epoch": 0.07202102803738318, "grad_norm": 2.7616868019104004, "learning_rate": 1.990788704676773e-05, "loss": 1.1883, "step": 1233 }, { "epoch": 0.07207943925233645, "grad_norm": 1.663914442062378, "learning_rate": 1.9907630682058357e-05, "loss": 1.0177, "step": 1234 }, { "epoch": 0.07213785046728972, "grad_norm": 3.025235891342163, "learning_rate": 1.990737396274837e-05, "loss": 1.0558, "step": 1235 }, { "epoch": 0.072196261682243, "grad_norm": 1.9546401500701904, "learning_rate": 1.9907116888846954e-05, "loss": 0.7478, "step": 1236 }, { "epoch": 0.07225467289719627, "grad_norm": 2.3083817958831787, "learning_rate": 1.9906859460363307e-05, "loss": 0.9325, "step": 1237 }, { "epoch": 0.07231308411214954, "grad_norm": 1.6537318229675293, "learning_rate": 1.9906601677306653e-05, "loss": 0.9153, "step": 1238 }, { "epoch": 0.0723714953271028, "grad_norm": 1.7020660638809204, "learning_rate": 1.9906343539686203e-05, "loss": 0.8813, "step": 1239 }, { "epoch": 0.07242990654205607, "grad_norm": 2.3670732975006104, "learning_rate": 1.990608504751121e-05, "loss": 0.7229, "step": 1240 }, { "epoch": 0.07248831775700934, "grad_norm": 1.6058160066604614, "learning_rate": 1.9905826200790918e-05, "loss": 0.843, "step": 1241 }, { "epoch": 0.07254672897196261, "grad_norm": 1.8619391918182373, "learning_rate": 1.9905566999534594e-05, "loss": 0.8963, "step": 1242 }, { "epoch": 0.07260514018691588, "grad_norm": 2.513638496398926, "learning_rate": 1.990530744375151e-05, "loss": 0.7994, "step": 1243 }, { "epoch": 0.07266355140186916, "grad_norm": 1.5209132432937622, "learning_rate": 1.9905047533450967e-05, "loss": 0.9536, "step": 1244 }, { "epoch": 0.07272196261682243, "grad_norm": 2.8493435382843018, "learning_rate": 1.9904787268642253e-05, "loss": 1.0802, "step": 1245 }, { "epoch": 0.0727803738317757, "grad_norm": 1.2657060623168945, "learning_rate": 1.9904526649334695e-05, "loss": 0.8514, "step": 1246 }, { "epoch": 0.07283878504672897, "grad_norm": 2.448259115219116, "learning_rate": 1.990426567553761e-05, "loss": 1.0452, "step": 1247 }, { "epoch": 0.07289719626168224, "grad_norm": 2.622363805770874, "learning_rate": 1.9904004347260353e-05, "loss": 0.948, "step": 1248 }, { "epoch": 0.07295560747663551, "grad_norm": 1.6062043905258179, "learning_rate": 1.9903742664512264e-05, "loss": 0.8204, "step": 1249 }, { "epoch": 0.07301401869158879, "grad_norm": 3.205775260925293, "learning_rate": 1.9903480627302713e-05, "loss": 1.0063, "step": 1250 }, { "epoch": 0.07307242990654206, "grad_norm": 1.472486138343811, "learning_rate": 1.9903218235641078e-05, "loss": 0.9207, "step": 1251 }, { "epoch": 0.07313084112149533, "grad_norm": 2.4446322917938232, "learning_rate": 1.9902955489536752e-05, "loss": 1.0339, "step": 1252 }, { "epoch": 0.0731892523364486, "grad_norm": 2.3076984882354736, "learning_rate": 1.9902692388999135e-05, "loss": 0.9997, "step": 1253 }, { "epoch": 0.07324766355140187, "grad_norm": 1.7439571619033813, "learning_rate": 1.990242893403765e-05, "loss": 0.9502, "step": 1254 }, { "epoch": 0.07330607476635514, "grad_norm": 1.7363296747207642, "learning_rate": 1.990216512466172e-05, "loss": 0.8355, "step": 1255 }, { "epoch": 0.07336448598130842, "grad_norm": 2.6725268363952637, "learning_rate": 1.9901900960880792e-05, "loss": 1.2421, "step": 1256 }, { "epoch": 0.07342289719626169, "grad_norm": 1.7591331005096436, "learning_rate": 1.9901636442704316e-05, "loss": 0.8689, "step": 1257 }, { "epoch": 0.07348130841121496, "grad_norm": 2.3608546257019043, "learning_rate": 1.9901371570141763e-05, "loss": 0.7942, "step": 1258 }, { "epoch": 0.07353971962616822, "grad_norm": 2.8176755905151367, "learning_rate": 1.9901106343202607e-05, "loss": 1.0083, "step": 1259 }, { "epoch": 0.07359813084112149, "grad_norm": 1.6124101877212524, "learning_rate": 1.9900840761896348e-05, "loss": 0.8906, "step": 1260 }, { "epoch": 0.07365654205607476, "grad_norm": 4.051169395446777, "learning_rate": 1.9900574826232487e-05, "loss": 1.0567, "step": 1261 }, { "epoch": 0.07371495327102803, "grad_norm": 1.7916724681854248, "learning_rate": 1.9900308536220545e-05, "loss": 0.9351, "step": 1262 }, { "epoch": 0.0737733644859813, "grad_norm": 3.168017625808716, "learning_rate": 1.990004189187005e-05, "loss": 1.0297, "step": 1263 }, { "epoch": 0.07383177570093458, "grad_norm": 1.478761076927185, "learning_rate": 1.9899774893190545e-05, "loss": 0.7007, "step": 1264 }, { "epoch": 0.07389018691588785, "grad_norm": 1.330185055732727, "learning_rate": 1.989950754019159e-05, "loss": 0.9327, "step": 1265 }, { "epoch": 0.07394859813084112, "grad_norm": 2.3887996673583984, "learning_rate": 1.9899239832882748e-05, "loss": 0.8004, "step": 1266 }, { "epoch": 0.07400700934579439, "grad_norm": 1.670502781867981, "learning_rate": 1.9898971771273607e-05, "loss": 1.0467, "step": 1267 }, { "epoch": 0.07406542056074766, "grad_norm": 2.1236495971679688, "learning_rate": 1.9898703355373755e-05, "loss": 1.0677, "step": 1268 }, { "epoch": 0.07412383177570094, "grad_norm": 1.6829419136047363, "learning_rate": 1.9898434585192802e-05, "loss": 1.0317, "step": 1269 }, { "epoch": 0.0741822429906542, "grad_norm": 1.8081542253494263, "learning_rate": 1.9898165460740366e-05, "loss": 0.8917, "step": 1270 }, { "epoch": 0.07424065420560748, "grad_norm": 2.3248324394226074, "learning_rate": 1.989789598202608e-05, "loss": 1.0306, "step": 1271 }, { "epoch": 0.07429906542056075, "grad_norm": 1.8758734464645386, "learning_rate": 1.9897626149059593e-05, "loss": 1.007, "step": 1272 }, { "epoch": 0.07435747663551402, "grad_norm": 2.505953550338745, "learning_rate": 1.9897355961850554e-05, "loss": 0.9835, "step": 1273 }, { "epoch": 0.0744158878504673, "grad_norm": 1.7373285293579102, "learning_rate": 1.9897085420408637e-05, "loss": 0.989, "step": 1274 }, { "epoch": 0.07447429906542057, "grad_norm": 2.0605838298797607, "learning_rate": 1.989681452474353e-05, "loss": 0.8549, "step": 1275 }, { "epoch": 0.07453271028037384, "grad_norm": 1.8946421146392822, "learning_rate": 1.9896543274864918e-05, "loss": 0.8663, "step": 1276 }, { "epoch": 0.07459112149532711, "grad_norm": 1.624323844909668, "learning_rate": 1.989627167078252e-05, "loss": 0.8841, "step": 1277 }, { "epoch": 0.07464953271028038, "grad_norm": 2.0618906021118164, "learning_rate": 1.9895999712506048e-05, "loss": 0.8735, "step": 1278 }, { "epoch": 0.07470794392523364, "grad_norm": 1.592384934425354, "learning_rate": 1.9895727400045245e-05, "loss": 0.6877, "step": 1279 }, { "epoch": 0.07476635514018691, "grad_norm": 2.9370062351226807, "learning_rate": 1.9895454733409844e-05, "loss": 1.0621, "step": 1280 }, { "epoch": 0.07482476635514018, "grad_norm": 1.43294095993042, "learning_rate": 1.989518171260962e-05, "loss": 1.0292, "step": 1281 }, { "epoch": 0.07488317757009345, "grad_norm": 1.635885238647461, "learning_rate": 1.989490833765433e-05, "loss": 0.9664, "step": 1282 }, { "epoch": 0.07494158878504673, "grad_norm": 1.9229251146316528, "learning_rate": 1.9894634608553766e-05, "loss": 0.7605, "step": 1283 }, { "epoch": 0.075, "grad_norm": 1.4545713663101196, "learning_rate": 1.9894360525317726e-05, "loss": 0.8626, "step": 1284 }, { "epoch": 0.07505841121495327, "grad_norm": 2.2512640953063965, "learning_rate": 1.9894086087956015e-05, "loss": 1.0913, "step": 1285 }, { "epoch": 0.07511682242990654, "grad_norm": 1.6536091566085815, "learning_rate": 1.9893811296478458e-05, "loss": 0.921, "step": 1286 }, { "epoch": 0.07517523364485981, "grad_norm": 4.286558151245117, "learning_rate": 1.9893536150894888e-05, "loss": 1.1755, "step": 1287 }, { "epoch": 0.07523364485981308, "grad_norm": 2.8542001247406006, "learning_rate": 1.9893260651215158e-05, "loss": 0.9961, "step": 1288 }, { "epoch": 0.07529205607476636, "grad_norm": 2.1377904415130615, "learning_rate": 1.989298479744912e-05, "loss": 0.7871, "step": 1289 }, { "epoch": 0.07535046728971963, "grad_norm": 1.584661841392517, "learning_rate": 1.9892708589606653e-05, "loss": 0.7654, "step": 1290 }, { "epoch": 0.0754088785046729, "grad_norm": 1.7620943784713745, "learning_rate": 1.989243202769764e-05, "loss": 0.8187, "step": 1291 }, { "epoch": 0.07546728971962617, "grad_norm": 2.524728775024414, "learning_rate": 1.989215511173198e-05, "loss": 1.0381, "step": 1292 }, { "epoch": 0.07552570093457944, "grad_norm": 2.7205216884613037, "learning_rate": 1.9891877841719586e-05, "loss": 1.0039, "step": 1293 }, { "epoch": 0.07558411214953271, "grad_norm": 2.063404083251953, "learning_rate": 1.9891600217670382e-05, "loss": 0.9691, "step": 1294 }, { "epoch": 0.07564252336448599, "grad_norm": 2.2235124111175537, "learning_rate": 1.9891322239594298e-05, "loss": 1.0022, "step": 1295 }, { "epoch": 0.07570093457943926, "grad_norm": 2.4510021209716797, "learning_rate": 1.9891043907501292e-05, "loss": 0.8664, "step": 1296 }, { "epoch": 0.07575934579439253, "grad_norm": 2.259232997894287, "learning_rate": 1.9890765221401314e-05, "loss": 0.9805, "step": 1297 }, { "epoch": 0.07581775700934579, "grad_norm": 2.6180038452148438, "learning_rate": 1.9890486181304353e-05, "loss": 1.0704, "step": 1298 }, { "epoch": 0.07587616822429906, "grad_norm": 2.7364282608032227, "learning_rate": 1.9890206787220384e-05, "loss": 0.8641, "step": 1299 }, { "epoch": 0.07593457943925233, "grad_norm": 2.880228281021118, "learning_rate": 1.9889927039159412e-05, "loss": 0.8777, "step": 1300 }, { "epoch": 0.0759929906542056, "grad_norm": 3.0905895233154297, "learning_rate": 1.988964693713145e-05, "loss": 0.9331, "step": 1301 }, { "epoch": 0.07605140186915887, "grad_norm": 2.7248408794403076, "learning_rate": 1.9889366481146522e-05, "loss": 1.0398, "step": 1302 }, { "epoch": 0.07610981308411215, "grad_norm": 1.693497896194458, "learning_rate": 1.9889085671214662e-05, "loss": 0.857, "step": 1303 }, { "epoch": 0.07616822429906542, "grad_norm": 2.8162357807159424, "learning_rate": 1.9888804507345924e-05, "loss": 0.814, "step": 1304 }, { "epoch": 0.07622663551401869, "grad_norm": 1.3861998319625854, "learning_rate": 1.9888522989550375e-05, "loss": 0.8128, "step": 1305 }, { "epoch": 0.07628504672897196, "grad_norm": 2.2300190925598145, "learning_rate": 1.9888241117838084e-05, "loss": 1.1369, "step": 1306 }, { "epoch": 0.07634345794392523, "grad_norm": 1.9064668416976929, "learning_rate": 1.9887958892219138e-05, "loss": 0.838, "step": 1307 }, { "epoch": 0.0764018691588785, "grad_norm": 3.167393207550049, "learning_rate": 1.9887676312703646e-05, "loss": 0.9534, "step": 1308 }, { "epoch": 0.07646028037383178, "grad_norm": 1.581313133239746, "learning_rate": 1.988739337930172e-05, "loss": 1.0333, "step": 1309 }, { "epoch": 0.07651869158878505, "grad_norm": 1.805376410484314, "learning_rate": 1.9887110092023478e-05, "loss": 0.8508, "step": 1310 }, { "epoch": 0.07657710280373832, "grad_norm": 1.783828854560852, "learning_rate": 1.9886826450879065e-05, "loss": 0.9573, "step": 1311 }, { "epoch": 0.07663551401869159, "grad_norm": 1.757554054260254, "learning_rate": 1.9886542455878636e-05, "loss": 0.9788, "step": 1312 }, { "epoch": 0.07669392523364486, "grad_norm": 1.8316813707351685, "learning_rate": 1.9886258107032352e-05, "loss": 0.8934, "step": 1313 }, { "epoch": 0.07675233644859814, "grad_norm": 1.904044508934021, "learning_rate": 1.988597340435039e-05, "loss": 0.8169, "step": 1314 }, { "epoch": 0.0768107476635514, "grad_norm": 1.630946397781372, "learning_rate": 1.988568834784294e-05, "loss": 1.1131, "step": 1315 }, { "epoch": 0.07686915887850468, "grad_norm": 3.128999710083008, "learning_rate": 1.98854029375202e-05, "loss": 1.1447, "step": 1316 }, { "epoch": 0.07692757009345795, "grad_norm": 1.934432864189148, "learning_rate": 1.988511717339239e-05, "loss": 0.8461, "step": 1317 }, { "epoch": 0.07698598130841121, "grad_norm": 2.2016544342041016, "learning_rate": 1.988483105546974e-05, "loss": 1.0063, "step": 1318 }, { "epoch": 0.07704439252336448, "grad_norm": 1.6440143585205078, "learning_rate": 1.9884544583762486e-05, "loss": 0.9573, "step": 1319 }, { "epoch": 0.07710280373831775, "grad_norm": 1.4685276746749878, "learning_rate": 1.988425775828088e-05, "loss": 0.6844, "step": 1320 }, { "epoch": 0.07716121495327102, "grad_norm": 2.28715443611145, "learning_rate": 1.988397057903519e-05, "loss": 0.8828, "step": 1321 }, { "epoch": 0.0772196261682243, "grad_norm": 1.5978806018829346, "learning_rate": 1.9883683046035696e-05, "loss": 0.9705, "step": 1322 }, { "epoch": 0.07727803738317757, "grad_norm": 2.677616834640503, "learning_rate": 1.9883395159292687e-05, "loss": 0.8497, "step": 1323 }, { "epoch": 0.07733644859813084, "grad_norm": 2.0654489994049072, "learning_rate": 1.9883106918816468e-05, "loss": 0.8113, "step": 1324 }, { "epoch": 0.07739485981308411, "grad_norm": 2.077786922454834, "learning_rate": 1.9882818324617355e-05, "loss": 0.7863, "step": 1325 }, { "epoch": 0.07745327102803738, "grad_norm": 3.062776803970337, "learning_rate": 1.9882529376705673e-05, "loss": 0.978, "step": 1326 }, { "epoch": 0.07751168224299065, "grad_norm": 1.9882627725601196, "learning_rate": 1.9882240075091768e-05, "loss": 0.7863, "step": 1327 }, { "epoch": 0.07757009345794393, "grad_norm": 1.4715464115142822, "learning_rate": 1.9881950419785992e-05, "loss": 0.9364, "step": 1328 }, { "epoch": 0.0776285046728972, "grad_norm": 2.147468090057373, "learning_rate": 1.9881660410798715e-05, "loss": 1.0825, "step": 1329 }, { "epoch": 0.07768691588785047, "grad_norm": 1.5815905332565308, "learning_rate": 1.988137004814031e-05, "loss": 0.6814, "step": 1330 }, { "epoch": 0.07774532710280374, "grad_norm": 2.558891534805298, "learning_rate": 1.9881079331821177e-05, "loss": 0.8093, "step": 1331 }, { "epoch": 0.07780373831775701, "grad_norm": 2.352200746536255, "learning_rate": 1.9880788261851716e-05, "loss": 0.8034, "step": 1332 }, { "epoch": 0.07786214953271028, "grad_norm": 1.4907312393188477, "learning_rate": 1.988049683824235e-05, "loss": 1.0043, "step": 1333 }, { "epoch": 0.07792056074766356, "grad_norm": 2.450376272201538, "learning_rate": 1.9880205061003503e-05, "loss": 1.0555, "step": 1334 }, { "epoch": 0.07797897196261683, "grad_norm": 1.8667423725128174, "learning_rate": 1.987991293014562e-05, "loss": 1.0052, "step": 1335 }, { "epoch": 0.0780373831775701, "grad_norm": 1.976367712020874, "learning_rate": 1.987962044567916e-05, "loss": 1.0018, "step": 1336 }, { "epoch": 0.07809579439252337, "grad_norm": 2.1440224647521973, "learning_rate": 1.9879327607614587e-05, "loss": 0.9469, "step": 1337 }, { "epoch": 0.07815420560747663, "grad_norm": 1.522589087486267, "learning_rate": 1.987903441596238e-05, "loss": 0.8013, "step": 1338 }, { "epoch": 0.0782126168224299, "grad_norm": 1.9214842319488525, "learning_rate": 1.987874087073304e-05, "loss": 1.0715, "step": 1339 }, { "epoch": 0.07827102803738317, "grad_norm": 1.918275237083435, "learning_rate": 1.9878446971937068e-05, "loss": 0.8718, "step": 1340 }, { "epoch": 0.07832943925233644, "grad_norm": 1.600773811340332, "learning_rate": 1.9878152719584983e-05, "loss": 0.8084, "step": 1341 }, { "epoch": 0.07838785046728972, "grad_norm": 2.562948703765869, "learning_rate": 1.9877858113687315e-05, "loss": 0.8178, "step": 1342 }, { "epoch": 0.07844626168224299, "grad_norm": 1.8181037902832031, "learning_rate": 1.9877563154254613e-05, "loss": 0.9763, "step": 1343 }, { "epoch": 0.07850467289719626, "grad_norm": 2.022200107574463, "learning_rate": 1.987726784129743e-05, "loss": 0.8759, "step": 1344 }, { "epoch": 0.07856308411214953, "grad_norm": 1.7590941190719604, "learning_rate": 1.9876972174826336e-05, "loss": 1.1624, "step": 1345 }, { "epoch": 0.0786214953271028, "grad_norm": 2.3767855167388916, "learning_rate": 1.9876676154851914e-05, "loss": 0.924, "step": 1346 }, { "epoch": 0.07867990654205607, "grad_norm": 2.782088279724121, "learning_rate": 1.987637978138476e-05, "loss": 1.1551, "step": 1347 }, { "epoch": 0.07873831775700935, "grad_norm": 1.7518177032470703, "learning_rate": 1.987608305443548e-05, "loss": 0.9487, "step": 1348 }, { "epoch": 0.07879672897196262, "grad_norm": 2.3824734687805176, "learning_rate": 1.987578597401469e-05, "loss": 0.9228, "step": 1349 }, { "epoch": 0.07885514018691589, "grad_norm": 1.643764853477478, "learning_rate": 1.9875488540133033e-05, "loss": 0.8003, "step": 1350 }, { "epoch": 0.07891355140186916, "grad_norm": 2.1775331497192383, "learning_rate": 1.987519075280114e-05, "loss": 0.9481, "step": 1351 }, { "epoch": 0.07897196261682243, "grad_norm": 3.122748613357544, "learning_rate": 1.9874892612029683e-05, "loss": 0.9482, "step": 1352 }, { "epoch": 0.0790303738317757, "grad_norm": 2.162600040435791, "learning_rate": 1.9874594117829325e-05, "loss": 0.9985, "step": 1353 }, { "epoch": 0.07908878504672898, "grad_norm": 1.8119676113128662, "learning_rate": 1.987429527021075e-05, "loss": 0.7903, "step": 1354 }, { "epoch": 0.07914719626168225, "grad_norm": 1.8433923721313477, "learning_rate": 1.9873996069184654e-05, "loss": 0.8871, "step": 1355 }, { "epoch": 0.07920560747663552, "grad_norm": 1.8839293718338013, "learning_rate": 1.9873696514761748e-05, "loss": 0.9296, "step": 1356 }, { "epoch": 0.07926401869158879, "grad_norm": 1.7626969814300537, "learning_rate": 1.9873396606952752e-05, "loss": 0.8996, "step": 1357 }, { "epoch": 0.07932242990654205, "grad_norm": 1.6507207155227661, "learning_rate": 1.98730963457684e-05, "loss": 0.9171, "step": 1358 }, { "epoch": 0.07938084112149532, "grad_norm": 1.8320969343185425, "learning_rate": 1.9872795731219434e-05, "loss": 0.9517, "step": 1359 }, { "epoch": 0.0794392523364486, "grad_norm": 2.5695111751556396, "learning_rate": 1.9872494763316622e-05, "loss": 1.0781, "step": 1360 }, { "epoch": 0.07949766355140186, "grad_norm": 2.681544065475464, "learning_rate": 1.9872193442070727e-05, "loss": 0.9294, "step": 1361 }, { "epoch": 0.07955607476635514, "grad_norm": 1.8827084302902222, "learning_rate": 1.987189176749254e-05, "loss": 0.9027, "step": 1362 }, { "epoch": 0.07961448598130841, "grad_norm": 1.942812204360962, "learning_rate": 1.9871589739592857e-05, "loss": 0.9508, "step": 1363 }, { "epoch": 0.07967289719626168, "grad_norm": 1.966726541519165, "learning_rate": 1.9871287358382484e-05, "loss": 0.9214, "step": 1364 }, { "epoch": 0.07973130841121495, "grad_norm": 1.711805820465088, "learning_rate": 1.9870984623872247e-05, "loss": 0.8955, "step": 1365 }, { "epoch": 0.07978971962616822, "grad_norm": 3.0360846519470215, "learning_rate": 1.987068153607298e-05, "loss": 1.0745, "step": 1366 }, { "epoch": 0.0798481308411215, "grad_norm": 2.0792124271392822, "learning_rate": 1.987037809499553e-05, "loss": 0.9282, "step": 1367 }, { "epoch": 0.07990654205607477, "grad_norm": 1.8394410610198975, "learning_rate": 1.987007430065076e-05, "loss": 1.0775, "step": 1368 }, { "epoch": 0.07996495327102804, "grad_norm": 1.7337042093276978, "learning_rate": 1.9869770153049538e-05, "loss": 1.0564, "step": 1369 }, { "epoch": 0.08002336448598131, "grad_norm": 1.75840425491333, "learning_rate": 1.9869465652202756e-05, "loss": 0.8912, "step": 1370 }, { "epoch": 0.08008177570093458, "grad_norm": 1.832231879234314, "learning_rate": 1.9869160798121308e-05, "loss": 0.8624, "step": 1371 }, { "epoch": 0.08014018691588785, "grad_norm": 1.5570157766342163, "learning_rate": 1.9868855590816105e-05, "loss": 0.9728, "step": 1372 }, { "epoch": 0.08019859813084113, "grad_norm": 2.2494113445281982, "learning_rate": 1.9868550030298072e-05, "loss": 0.9344, "step": 1373 }, { "epoch": 0.0802570093457944, "grad_norm": 1.1272821426391602, "learning_rate": 1.9868244116578145e-05, "loss": 0.9579, "step": 1374 }, { "epoch": 0.08031542056074767, "grad_norm": 1.8241599798202515, "learning_rate": 1.9867937849667272e-05, "loss": 0.8822, "step": 1375 }, { "epoch": 0.08037383177570094, "grad_norm": 1.646852731704712, "learning_rate": 1.9867631229576413e-05, "loss": 0.8951, "step": 1376 }, { "epoch": 0.08043224299065421, "grad_norm": 1.5869203805923462, "learning_rate": 1.986732425631655e-05, "loss": 0.8901, "step": 1377 }, { "epoch": 0.08049065420560747, "grad_norm": 2.0258755683898926, "learning_rate": 1.986701692989866e-05, "loss": 0.9033, "step": 1378 }, { "epoch": 0.08054906542056074, "grad_norm": 1.9039405584335327, "learning_rate": 1.9866709250333746e-05, "loss": 0.6685, "step": 1379 }, { "epoch": 0.08060747663551401, "grad_norm": 1.922206163406372, "learning_rate": 1.9866401217632823e-05, "loss": 0.9696, "step": 1380 }, { "epoch": 0.08066588785046729, "grad_norm": 1.2870792150497437, "learning_rate": 1.986609283180691e-05, "loss": 0.7724, "step": 1381 }, { "epoch": 0.08072429906542056, "grad_norm": 2.0244967937469482, "learning_rate": 1.9865784092867047e-05, "loss": 0.9218, "step": 1382 }, { "epoch": 0.08078271028037383, "grad_norm": 2.43060040473938, "learning_rate": 1.9865475000824288e-05, "loss": 0.846, "step": 1383 }, { "epoch": 0.0808411214953271, "grad_norm": 1.584519624710083, "learning_rate": 1.9865165555689692e-05, "loss": 0.7585, "step": 1384 }, { "epoch": 0.08089953271028037, "grad_norm": 2.146472930908203, "learning_rate": 1.986485575747433e-05, "loss": 1.1106, "step": 1385 }, { "epoch": 0.08095794392523364, "grad_norm": 1.6186060905456543, "learning_rate": 1.98645456061893e-05, "loss": 0.8168, "step": 1386 }, { "epoch": 0.08101635514018692, "grad_norm": 2.413200855255127, "learning_rate": 1.986423510184569e-05, "loss": 0.896, "step": 1387 }, { "epoch": 0.08107476635514019, "grad_norm": 2.0319364070892334, "learning_rate": 1.9863924244454627e-05, "loss": 0.7273, "step": 1388 }, { "epoch": 0.08113317757009346, "grad_norm": 1.4720804691314697, "learning_rate": 1.9863613034027224e-05, "loss": 0.9194, "step": 1389 }, { "epoch": 0.08119158878504673, "grad_norm": 1.9683761596679688, "learning_rate": 1.986330147057463e-05, "loss": 0.6799, "step": 1390 }, { "epoch": 0.08125, "grad_norm": 2.440528154373169, "learning_rate": 1.9862989554107988e-05, "loss": 1.0978, "step": 1391 }, { "epoch": 0.08130841121495327, "grad_norm": 1.4763708114624023, "learning_rate": 1.9862677284638465e-05, "loss": 1.018, "step": 1392 }, { "epoch": 0.08136682242990655, "grad_norm": 3.159855365753174, "learning_rate": 1.9862364662177235e-05, "loss": 0.9551, "step": 1393 }, { "epoch": 0.08142523364485982, "grad_norm": 2.497652769088745, "learning_rate": 1.9862051686735493e-05, "loss": 1.0481, "step": 1394 }, { "epoch": 0.08148364485981309, "grad_norm": 1.3978914022445679, "learning_rate": 1.9861738358324434e-05, "loss": 0.7091, "step": 1395 }, { "epoch": 0.08154205607476636, "grad_norm": 3.5652737617492676, "learning_rate": 1.9861424676955276e-05, "loss": 1.1835, "step": 1396 }, { "epoch": 0.08160046728971962, "grad_norm": 2.1314384937286377, "learning_rate": 1.9861110642639244e-05, "loss": 0.8803, "step": 1397 }, { "epoch": 0.08165887850467289, "grad_norm": 3.9496829509735107, "learning_rate": 1.986079625538758e-05, "loss": 1.0109, "step": 1398 }, { "epoch": 0.08171728971962616, "grad_norm": 1.7689971923828125, "learning_rate": 1.9860481515211533e-05, "loss": 0.8477, "step": 1399 }, { "epoch": 0.08177570093457943, "grad_norm": 3.7728097438812256, "learning_rate": 1.986016642212237e-05, "loss": 1.1275, "step": 1400 }, { "epoch": 0.0818341121495327, "grad_norm": 1.6294522285461426, "learning_rate": 1.9859850976131366e-05, "loss": 1.0448, "step": 1401 }, { "epoch": 0.08189252336448598, "grad_norm": 1.0394089221954346, "learning_rate": 1.9859535177249817e-05, "loss": 0.6473, "step": 1402 }, { "epoch": 0.08195093457943925, "grad_norm": 3.064969301223755, "learning_rate": 1.9859219025489017e-05, "loss": 0.9777, "step": 1403 }, { "epoch": 0.08200934579439252, "grad_norm": 2.358618974685669, "learning_rate": 1.9858902520860284e-05, "loss": 0.9367, "step": 1404 }, { "epoch": 0.0820677570093458, "grad_norm": 2.8669168949127197, "learning_rate": 1.9858585663374953e-05, "loss": 0.9816, "step": 1405 }, { "epoch": 0.08212616822429906, "grad_norm": 2.5258069038391113, "learning_rate": 1.9858268453044356e-05, "loss": 1.0343, "step": 1406 }, { "epoch": 0.08218457943925234, "grad_norm": 1.9042638540267944, "learning_rate": 1.985795088987985e-05, "loss": 1.085, "step": 1407 }, { "epoch": 0.08224299065420561, "grad_norm": 1.9707233905792236, "learning_rate": 1.9857632973892796e-05, "loss": 0.8077, "step": 1408 }, { "epoch": 0.08230140186915888, "grad_norm": 2.302198648452759, "learning_rate": 1.985731470509458e-05, "loss": 0.7856, "step": 1409 }, { "epoch": 0.08235981308411215, "grad_norm": 1.6232599020004272, "learning_rate": 1.985699608349659e-05, "loss": 0.8396, "step": 1410 }, { "epoch": 0.08241822429906542, "grad_norm": 2.3911471366882324, "learning_rate": 1.985667710911023e-05, "loss": 0.8049, "step": 1411 }, { "epoch": 0.0824766355140187, "grad_norm": 2.698530912399292, "learning_rate": 1.9856357781946913e-05, "loss": 0.8111, "step": 1412 }, { "epoch": 0.08253504672897197, "grad_norm": 2.130528450012207, "learning_rate": 1.985603810201807e-05, "loss": 1.0134, "step": 1413 }, { "epoch": 0.08259345794392524, "grad_norm": 2.3575518131256104, "learning_rate": 1.9855718069335142e-05, "loss": 0.9694, "step": 1414 }, { "epoch": 0.08265186915887851, "grad_norm": 2.2462568283081055, "learning_rate": 1.985539768390959e-05, "loss": 0.8952, "step": 1415 }, { "epoch": 0.08271028037383178, "grad_norm": 1.881705403327942, "learning_rate": 1.9855076945752865e-05, "loss": 0.8267, "step": 1416 }, { "epoch": 0.08276869158878504, "grad_norm": 2.995727300643921, "learning_rate": 1.985475585487646e-05, "loss": 0.8842, "step": 1417 }, { "epoch": 0.08282710280373831, "grad_norm": 1.6627529859542847, "learning_rate": 1.9854434411291868e-05, "loss": 0.8439, "step": 1418 }, { "epoch": 0.08288551401869158, "grad_norm": 2.836901903152466, "learning_rate": 1.9854112615010585e-05, "loss": 0.88, "step": 1419 }, { "epoch": 0.08294392523364486, "grad_norm": 1.904231071472168, "learning_rate": 1.9853790466044133e-05, "loss": 0.7432, "step": 1420 }, { "epoch": 0.08300233644859813, "grad_norm": 1.8867639303207397, "learning_rate": 1.985346796440404e-05, "loss": 0.8531, "step": 1421 }, { "epoch": 0.0830607476635514, "grad_norm": 1.459639072418213, "learning_rate": 1.9853145110101853e-05, "loss": 0.6957, "step": 1422 }, { "epoch": 0.08311915887850467, "grad_norm": 2.0096092224121094, "learning_rate": 1.9852821903149122e-05, "loss": 0.9125, "step": 1423 }, { "epoch": 0.08317757009345794, "grad_norm": 1.9227675199508667, "learning_rate": 1.9852498343557415e-05, "loss": 1.134, "step": 1424 }, { "epoch": 0.08323598130841121, "grad_norm": 1.6121915578842163, "learning_rate": 1.9852174431338316e-05, "loss": 0.7889, "step": 1425 }, { "epoch": 0.08329439252336449, "grad_norm": 1.622851014137268, "learning_rate": 1.9851850166503417e-05, "loss": 1.0105, "step": 1426 }, { "epoch": 0.08335280373831776, "grad_norm": 1.699034333229065, "learning_rate": 1.9851525549064324e-05, "loss": 0.8232, "step": 1427 }, { "epoch": 0.08341121495327103, "grad_norm": 2.1776368618011475, "learning_rate": 1.9851200579032652e-05, "loss": 1.1673, "step": 1428 }, { "epoch": 0.0834696261682243, "grad_norm": 2.6851906776428223, "learning_rate": 1.9850875256420036e-05, "loss": 0.7955, "step": 1429 }, { "epoch": 0.08352803738317757, "grad_norm": 1.6610184907913208, "learning_rate": 1.9850549581238115e-05, "loss": 0.6588, "step": 1430 }, { "epoch": 0.08358644859813084, "grad_norm": 2.4345459938049316, "learning_rate": 1.9850223553498546e-05, "loss": 0.9013, "step": 1431 }, { "epoch": 0.08364485981308412, "grad_norm": 2.202242612838745, "learning_rate": 1.9849897173213003e-05, "loss": 0.7622, "step": 1432 }, { "epoch": 0.08370327102803739, "grad_norm": 3.4627561569213867, "learning_rate": 1.984957044039316e-05, "loss": 0.8024, "step": 1433 }, { "epoch": 0.08376168224299066, "grad_norm": 1.8191680908203125, "learning_rate": 1.9849243355050716e-05, "loss": 0.9104, "step": 1434 }, { "epoch": 0.08382009345794393, "grad_norm": 2.6289477348327637, "learning_rate": 1.984891591719738e-05, "loss": 1.1096, "step": 1435 }, { "epoch": 0.0838785046728972, "grad_norm": 2.410902976989746, "learning_rate": 1.9848588126844867e-05, "loss": 0.8115, "step": 1436 }, { "epoch": 0.08393691588785046, "grad_norm": 1.7899526357650757, "learning_rate": 1.9848259984004906e-05, "loss": 0.8995, "step": 1437 }, { "epoch": 0.08399532710280373, "grad_norm": 2.9282116889953613, "learning_rate": 1.9847931488689243e-05, "loss": 0.7973, "step": 1438 }, { "epoch": 0.084053738317757, "grad_norm": 2.8076257705688477, "learning_rate": 1.9847602640909643e-05, "loss": 0.9122, "step": 1439 }, { "epoch": 0.08411214953271028, "grad_norm": 1.6405035257339478, "learning_rate": 1.9847273440677864e-05, "loss": 0.774, "step": 1440 }, { "epoch": 0.08417056074766355, "grad_norm": 2.2754688262939453, "learning_rate": 1.98469438880057e-05, "loss": 0.9573, "step": 1441 }, { "epoch": 0.08422897196261682, "grad_norm": 2.1068365573883057, "learning_rate": 1.9846613982904933e-05, "loss": 0.8804, "step": 1442 }, { "epoch": 0.08428738317757009, "grad_norm": 1.8042184114456177, "learning_rate": 1.984628372538738e-05, "loss": 1.0468, "step": 1443 }, { "epoch": 0.08434579439252336, "grad_norm": 2.7051186561584473, "learning_rate": 1.984595311546486e-05, "loss": 0.8234, "step": 1444 }, { "epoch": 0.08440420560747663, "grad_norm": 1.9527028799057007, "learning_rate": 1.9845622153149204e-05, "loss": 0.9, "step": 1445 }, { "epoch": 0.0844626168224299, "grad_norm": 1.5854591131210327, "learning_rate": 1.9845290838452257e-05, "loss": 0.9311, "step": 1446 }, { "epoch": 0.08452102803738318, "grad_norm": 2.0000391006469727, "learning_rate": 1.9844959171385877e-05, "loss": 0.9024, "step": 1447 }, { "epoch": 0.08457943925233645, "grad_norm": 1.8415178060531616, "learning_rate": 1.9844627151961933e-05, "loss": 0.6929, "step": 1448 }, { "epoch": 0.08463785046728972, "grad_norm": 1.879141092300415, "learning_rate": 1.9844294780192313e-05, "loss": 0.7039, "step": 1449 }, { "epoch": 0.084696261682243, "grad_norm": 2.089843273162842, "learning_rate": 1.9843962056088907e-05, "loss": 1.003, "step": 1450 }, { "epoch": 0.08475467289719626, "grad_norm": 1.8718558549880981, "learning_rate": 1.984362897966363e-05, "loss": 0.8614, "step": 1451 }, { "epoch": 0.08481308411214954, "grad_norm": 1.807824969291687, "learning_rate": 1.98432955509284e-05, "loss": 0.8918, "step": 1452 }, { "epoch": 0.08487149532710281, "grad_norm": 2.041700601577759, "learning_rate": 1.9842961769895147e-05, "loss": 1.1063, "step": 1453 }, { "epoch": 0.08492990654205608, "grad_norm": 1.5992043018341064, "learning_rate": 1.9842627636575823e-05, "loss": 0.8877, "step": 1454 }, { "epoch": 0.08498831775700935, "grad_norm": 1.5491623878479004, "learning_rate": 1.9842293150982385e-05, "loss": 1.0024, "step": 1455 }, { "epoch": 0.08504672897196262, "grad_norm": 1.3558712005615234, "learning_rate": 1.98419583131268e-05, "loss": 0.7647, "step": 1456 }, { "epoch": 0.08510514018691588, "grad_norm": 1.7252323627471924, "learning_rate": 1.9841623123021056e-05, "loss": 0.8975, "step": 1457 }, { "epoch": 0.08516355140186915, "grad_norm": 2.3830525875091553, "learning_rate": 1.9841287580677152e-05, "loss": 0.9981, "step": 1458 }, { "epoch": 0.08522196261682242, "grad_norm": 2.206333875656128, "learning_rate": 1.9840951686107093e-05, "loss": 1.0882, "step": 1459 }, { "epoch": 0.0852803738317757, "grad_norm": 1.3425835371017456, "learning_rate": 1.9840615439322907e-05, "loss": 0.9368, "step": 1460 }, { "epoch": 0.08533878504672897, "grad_norm": 1.5843079090118408, "learning_rate": 1.9840278840336617e-05, "loss": 0.9321, "step": 1461 }, { "epoch": 0.08539719626168224, "grad_norm": 1.8655918836593628, "learning_rate": 1.9839941889160282e-05, "loss": 1.0523, "step": 1462 }, { "epoch": 0.08545560747663551, "grad_norm": 1.8019261360168457, "learning_rate": 1.9839604585805957e-05, "loss": 0.7889, "step": 1463 }, { "epoch": 0.08551401869158878, "grad_norm": 1.9358223676681519, "learning_rate": 1.983926693028571e-05, "loss": 0.8994, "step": 1464 }, { "epoch": 0.08557242990654206, "grad_norm": 2.150047540664673, "learning_rate": 1.9838928922611634e-05, "loss": 0.914, "step": 1465 }, { "epoch": 0.08563084112149533, "grad_norm": 2.948190212249756, "learning_rate": 1.9838590562795822e-05, "loss": 1.0379, "step": 1466 }, { "epoch": 0.0856892523364486, "grad_norm": 1.882500171661377, "learning_rate": 1.9838251850850385e-05, "loss": 0.7213, "step": 1467 }, { "epoch": 0.08574766355140187, "grad_norm": 1.9901485443115234, "learning_rate": 1.9837912786787442e-05, "loss": 0.722, "step": 1468 }, { "epoch": 0.08580607476635514, "grad_norm": 1.584920048713684, "learning_rate": 1.9837573370619135e-05, "loss": 0.9041, "step": 1469 }, { "epoch": 0.08586448598130841, "grad_norm": 1.441156268119812, "learning_rate": 1.9837233602357608e-05, "loss": 0.775, "step": 1470 }, { "epoch": 0.08592289719626169, "grad_norm": 1.7691787481307983, "learning_rate": 1.9836893482015026e-05, "loss": 1.1078, "step": 1471 }, { "epoch": 0.08598130841121496, "grad_norm": 1.644418716430664, "learning_rate": 1.983655300960355e-05, "loss": 0.9574, "step": 1472 }, { "epoch": 0.08603971962616823, "grad_norm": 1.4219082593917847, "learning_rate": 1.9836212185135383e-05, "loss": 0.818, "step": 1473 }, { "epoch": 0.0860981308411215, "grad_norm": 1.6426646709442139, "learning_rate": 1.983587100862271e-05, "loss": 0.8844, "step": 1474 }, { "epoch": 0.08615654205607477, "grad_norm": 1.6474093198776245, "learning_rate": 1.9835529480077745e-05, "loss": 0.9867, "step": 1475 }, { "epoch": 0.08621495327102804, "grad_norm": 1.1810888051986694, "learning_rate": 1.9835187599512716e-05, "loss": 0.7318, "step": 1476 }, { "epoch": 0.0862733644859813, "grad_norm": 2.2405760288238525, "learning_rate": 1.9834845366939855e-05, "loss": 0.8536, "step": 1477 }, { "epoch": 0.08633177570093457, "grad_norm": 1.4903196096420288, "learning_rate": 1.983450278237141e-05, "loss": 0.9343, "step": 1478 }, { "epoch": 0.08639018691588785, "grad_norm": 2.0085363388061523, "learning_rate": 1.9834159845819646e-05, "loss": 0.8941, "step": 1479 }, { "epoch": 0.08644859813084112, "grad_norm": 1.3892043828964233, "learning_rate": 1.9833816557296837e-05, "loss": 0.7536, "step": 1480 }, { "epoch": 0.08650700934579439, "grad_norm": 1.5463873147964478, "learning_rate": 1.9833472916815264e-05, "loss": 0.849, "step": 1481 }, { "epoch": 0.08656542056074766, "grad_norm": 7.186009407043457, "learning_rate": 1.9833128924387233e-05, "loss": 0.7482, "step": 1482 }, { "epoch": 0.08662383177570093, "grad_norm": 1.6378198862075806, "learning_rate": 1.983278458002505e-05, "loss": 0.8844, "step": 1483 }, { "epoch": 0.0866822429906542, "grad_norm": 1.8029124736785889, "learning_rate": 1.9832439883741038e-05, "loss": 0.8665, "step": 1484 }, { "epoch": 0.08674065420560748, "grad_norm": 1.6775963306427002, "learning_rate": 1.9832094835547543e-05, "loss": 0.9656, "step": 1485 }, { "epoch": 0.08679906542056075, "grad_norm": 1.746297836303711, "learning_rate": 1.983174943545691e-05, "loss": 0.9296, "step": 1486 }, { "epoch": 0.08685747663551402, "grad_norm": 2.0308470726013184, "learning_rate": 1.9831403683481496e-05, "loss": 1.0578, "step": 1487 }, { "epoch": 0.08691588785046729, "grad_norm": 1.5603042840957642, "learning_rate": 1.9831057579633685e-05, "loss": 0.9295, "step": 1488 }, { "epoch": 0.08697429906542056, "grad_norm": 1.4531351327896118, "learning_rate": 1.9830711123925853e-05, "loss": 0.936, "step": 1489 }, { "epoch": 0.08703271028037383, "grad_norm": 1.8755995035171509, "learning_rate": 1.983036431637041e-05, "loss": 0.9935, "step": 1490 }, { "epoch": 0.0870911214953271, "grad_norm": 2.079712152481079, "learning_rate": 1.9830017156979764e-05, "loss": 0.9116, "step": 1491 }, { "epoch": 0.08714953271028038, "grad_norm": 1.8078417778015137, "learning_rate": 1.982966964576634e-05, "loss": 0.9313, "step": 1492 }, { "epoch": 0.08720794392523365, "grad_norm": 2.7168314456939697, "learning_rate": 1.9829321782742578e-05, "loss": 0.7716, "step": 1493 }, { "epoch": 0.08726635514018692, "grad_norm": 3.4602057933807373, "learning_rate": 1.9828973567920923e-05, "loss": 0.9781, "step": 1494 }, { "epoch": 0.0873247663551402, "grad_norm": 1.9290395975112915, "learning_rate": 1.9828625001313843e-05, "loss": 0.9493, "step": 1495 }, { "epoch": 0.08738317757009346, "grad_norm": 2.6260077953338623, "learning_rate": 1.9828276082933815e-05, "loss": 0.7816, "step": 1496 }, { "epoch": 0.08744158878504672, "grad_norm": 1.4941822290420532, "learning_rate": 1.982792681279332e-05, "loss": 0.6924, "step": 1497 }, { "epoch": 0.0875, "grad_norm": 1.5773411989212036, "learning_rate": 1.9827577190904862e-05, "loss": 0.785, "step": 1498 }, { "epoch": 0.08755841121495327, "grad_norm": 2.4297192096710205, "learning_rate": 1.9827227217280955e-05, "loss": 0.8554, "step": 1499 }, { "epoch": 0.08761682242990654, "grad_norm": 1.4795094728469849, "learning_rate": 1.9826876891934126e-05, "loss": 0.8752, "step": 1500 }, { "epoch": 0.08767523364485981, "grad_norm": 2.3561747074127197, "learning_rate": 1.9826526214876912e-05, "loss": 0.942, "step": 1501 }, { "epoch": 0.08773364485981308, "grad_norm": 1.5691083669662476, "learning_rate": 1.982617518612186e-05, "loss": 0.9, "step": 1502 }, { "epoch": 0.08779205607476635, "grad_norm": 2.1014461517333984, "learning_rate": 1.9825823805681543e-05, "loss": 0.8545, "step": 1503 }, { "epoch": 0.08785046728971962, "grad_norm": 1.4484449625015259, "learning_rate": 1.9825472073568527e-05, "loss": 0.8754, "step": 1504 }, { "epoch": 0.0879088785046729, "grad_norm": 2.019963026046753, "learning_rate": 1.9825119989795407e-05, "loss": 0.8476, "step": 1505 }, { "epoch": 0.08796728971962617, "grad_norm": 1.528015375137329, "learning_rate": 1.9824767554374783e-05, "loss": 0.7593, "step": 1506 }, { "epoch": 0.08802570093457944, "grad_norm": 1.6938550472259521, "learning_rate": 1.9824414767319267e-05, "loss": 0.7666, "step": 1507 }, { "epoch": 0.08808411214953271, "grad_norm": 1.8905627727508545, "learning_rate": 1.9824061628641486e-05, "loss": 0.8596, "step": 1508 }, { "epoch": 0.08814252336448598, "grad_norm": 1.9108550548553467, "learning_rate": 1.982370813835408e-05, "loss": 1.0203, "step": 1509 }, { "epoch": 0.08820093457943926, "grad_norm": 1.7791129350662231, "learning_rate": 1.9823354296469702e-05, "loss": 0.9433, "step": 1510 }, { "epoch": 0.08825934579439253, "grad_norm": 1.7893584966659546, "learning_rate": 1.9823000103001012e-05, "loss": 0.8956, "step": 1511 }, { "epoch": 0.0883177570093458, "grad_norm": 1.6081949472427368, "learning_rate": 1.9822645557960693e-05, "loss": 0.8954, "step": 1512 }, { "epoch": 0.08837616822429907, "grad_norm": 2.081634998321533, "learning_rate": 1.9822290661361432e-05, "loss": 0.8168, "step": 1513 }, { "epoch": 0.08843457943925234, "grad_norm": 1.5638353824615479, "learning_rate": 1.9821935413215926e-05, "loss": 0.697, "step": 1514 }, { "epoch": 0.08849299065420561, "grad_norm": 2.153350830078125, "learning_rate": 1.9821579813536897e-05, "loss": 1.026, "step": 1515 }, { "epoch": 0.08855140186915887, "grad_norm": 1.7664176225662231, "learning_rate": 1.9821223862337066e-05, "loss": 1.0772, "step": 1516 }, { "epoch": 0.08860981308411214, "grad_norm": 2.586961030960083, "learning_rate": 1.9820867559629174e-05, "loss": 1.0052, "step": 1517 }, { "epoch": 0.08866822429906542, "grad_norm": 1.8971065282821655, "learning_rate": 1.9820510905425977e-05, "loss": 1.0922, "step": 1518 }, { "epoch": 0.08872663551401869, "grad_norm": 2.611898422241211, "learning_rate": 1.982015389974024e-05, "loss": 0.9444, "step": 1519 }, { "epoch": 0.08878504672897196, "grad_norm": 1.6644680500030518, "learning_rate": 1.9819796542584734e-05, "loss": 0.95, "step": 1520 }, { "epoch": 0.08884345794392523, "grad_norm": 2.729663848876953, "learning_rate": 1.9819438833972254e-05, "loss": 0.8999, "step": 1521 }, { "epoch": 0.0889018691588785, "grad_norm": 2.0593252182006836, "learning_rate": 1.9819080773915603e-05, "loss": 1.0002, "step": 1522 }, { "epoch": 0.08896028037383177, "grad_norm": 1.8846924304962158, "learning_rate": 1.9818722362427594e-05, "loss": 0.9088, "step": 1523 }, { "epoch": 0.08901869158878505, "grad_norm": 1.6758506298065186, "learning_rate": 1.9818363599521055e-05, "loss": 0.9391, "step": 1524 }, { "epoch": 0.08907710280373832, "grad_norm": 1.5419636964797974, "learning_rate": 1.9818004485208827e-05, "loss": 0.7497, "step": 1525 }, { "epoch": 0.08913551401869159, "grad_norm": 2.4117915630340576, "learning_rate": 1.9817645019503765e-05, "loss": 0.9575, "step": 1526 }, { "epoch": 0.08919392523364486, "grad_norm": 1.493260383605957, "learning_rate": 1.9817285202418733e-05, "loss": 0.9515, "step": 1527 }, { "epoch": 0.08925233644859813, "grad_norm": 2.1827783584594727, "learning_rate": 1.981692503396661e-05, "loss": 0.8606, "step": 1528 }, { "epoch": 0.0893107476635514, "grad_norm": 1.7598869800567627, "learning_rate": 1.981656451416028e-05, "loss": 0.8739, "step": 1529 }, { "epoch": 0.08936915887850468, "grad_norm": 1.9783002138137817, "learning_rate": 1.981620364301265e-05, "loss": 0.9146, "step": 1530 }, { "epoch": 0.08942757009345795, "grad_norm": 2.159109592437744, "learning_rate": 1.9815842420536645e-05, "loss": 1.0158, "step": 1531 }, { "epoch": 0.08948598130841122, "grad_norm": 1.7864221334457397, "learning_rate": 1.9815480846745182e-05, "loss": 1.0262, "step": 1532 }, { "epoch": 0.08954439252336449, "grad_norm": 1.552927851676941, "learning_rate": 1.9815118921651205e-05, "loss": 0.8814, "step": 1533 }, { "epoch": 0.08960280373831776, "grad_norm": 1.3450462818145752, "learning_rate": 1.9814756645267668e-05, "loss": 1.0301, "step": 1534 }, { "epoch": 0.08966121495327103, "grad_norm": 1.2028297185897827, "learning_rate": 1.981439401760754e-05, "loss": 0.7255, "step": 1535 }, { "epoch": 0.08971962616822429, "grad_norm": 2.0444045066833496, "learning_rate": 1.9814031038683793e-05, "loss": 1.114, "step": 1536 }, { "epoch": 0.08977803738317756, "grad_norm": 1.4642837047576904, "learning_rate": 1.9813667708509426e-05, "loss": 0.8628, "step": 1537 }, { "epoch": 0.08983644859813084, "grad_norm": 1.8854418992996216, "learning_rate": 1.9813304027097438e-05, "loss": 1.0492, "step": 1538 }, { "epoch": 0.08989485981308411, "grad_norm": 2.2014989852905273, "learning_rate": 1.9812939994460846e-05, "loss": 1.0566, "step": 1539 }, { "epoch": 0.08995327102803738, "grad_norm": 1.6597179174423218, "learning_rate": 1.9812575610612678e-05, "loss": 0.9904, "step": 1540 }, { "epoch": 0.09001168224299065, "grad_norm": 2.215672016143799, "learning_rate": 1.981221087556598e-05, "loss": 0.927, "step": 1541 }, { "epoch": 0.09007009345794392, "grad_norm": 1.6745073795318604, "learning_rate": 1.98118457893338e-05, "loss": 0.8428, "step": 1542 }, { "epoch": 0.0901285046728972, "grad_norm": 2.1553561687469482, "learning_rate": 1.981148035192921e-05, "loss": 0.9262, "step": 1543 }, { "epoch": 0.09018691588785047, "grad_norm": 1.6370164155960083, "learning_rate": 1.981111456336529e-05, "loss": 0.8548, "step": 1544 }, { "epoch": 0.09024532710280374, "grad_norm": 1.8536103963851929, "learning_rate": 1.981074842365512e-05, "loss": 0.875, "step": 1545 }, { "epoch": 0.09030373831775701, "grad_norm": 1.7545381784439087, "learning_rate": 1.9810381932811822e-05, "loss": 0.7289, "step": 1546 }, { "epoch": 0.09036214953271028, "grad_norm": 1.9883267879486084, "learning_rate": 1.98100150908485e-05, "loss": 0.7832, "step": 1547 }, { "epoch": 0.09042056074766355, "grad_norm": 1.6238279342651367, "learning_rate": 1.9809647897778287e-05, "loss": 0.7586, "step": 1548 }, { "epoch": 0.09047897196261682, "grad_norm": 2.0498340129852295, "learning_rate": 1.980928035361433e-05, "loss": 1.1772, "step": 1549 }, { "epoch": 0.0905373831775701, "grad_norm": 1.6854751110076904, "learning_rate": 1.9808912458369774e-05, "loss": 0.8138, "step": 1550 }, { "epoch": 0.09059579439252337, "grad_norm": 3.050798177719116, "learning_rate": 1.9808544212057797e-05, "loss": 0.8288, "step": 1551 }, { "epoch": 0.09065420560747664, "grad_norm": 1.6161270141601562, "learning_rate": 1.9808175614691572e-05, "loss": 0.8128, "step": 1552 }, { "epoch": 0.09071261682242991, "grad_norm": 3.12829852104187, "learning_rate": 1.980780666628429e-05, "loss": 1.0472, "step": 1553 }, { "epoch": 0.09077102803738318, "grad_norm": 2.204986810684204, "learning_rate": 1.9807437366849157e-05, "loss": 0.8799, "step": 1554 }, { "epoch": 0.09082943925233646, "grad_norm": 3.1424367427825928, "learning_rate": 1.9807067716399398e-05, "loss": 0.9013, "step": 1555 }, { "epoch": 0.09088785046728971, "grad_norm": 1.930604338645935, "learning_rate": 1.9806697714948235e-05, "loss": 0.7589, "step": 1556 }, { "epoch": 0.09094626168224298, "grad_norm": 1.8323227167129517, "learning_rate": 1.980632736250891e-05, "loss": 0.9629, "step": 1557 }, { "epoch": 0.09100467289719626, "grad_norm": 2.828594446182251, "learning_rate": 1.9805956659094686e-05, "loss": 1.1086, "step": 1558 }, { "epoch": 0.09106308411214953, "grad_norm": 2.022365093231201, "learning_rate": 1.980558560471882e-05, "loss": 0.9791, "step": 1559 }, { "epoch": 0.0911214953271028, "grad_norm": 2.4936039447784424, "learning_rate": 1.98052141993946e-05, "loss": 1.1256, "step": 1560 }, { "epoch": 0.09117990654205607, "grad_norm": 1.6338664293289185, "learning_rate": 1.980484244313532e-05, "loss": 0.7785, "step": 1561 }, { "epoch": 0.09123831775700934, "grad_norm": 2.0985679626464844, "learning_rate": 1.9804470335954278e-05, "loss": 0.8096, "step": 1562 }, { "epoch": 0.09129672897196262, "grad_norm": 1.842894196510315, "learning_rate": 1.9804097877864798e-05, "loss": 0.9326, "step": 1563 }, { "epoch": 0.09135514018691589, "grad_norm": 1.8115798234939575, "learning_rate": 1.9803725068880208e-05, "loss": 0.9676, "step": 1564 }, { "epoch": 0.09141355140186916, "grad_norm": 1.911331057548523, "learning_rate": 1.980335190901385e-05, "loss": 0.7404, "step": 1565 }, { "epoch": 0.09147196261682243, "grad_norm": 2.0593087673187256, "learning_rate": 1.9802978398279086e-05, "loss": 0.7459, "step": 1566 }, { "epoch": 0.0915303738317757, "grad_norm": 1.3308414220809937, "learning_rate": 1.9802604536689278e-05, "loss": 0.6948, "step": 1567 }, { "epoch": 0.09158878504672897, "grad_norm": 2.752220392227173, "learning_rate": 1.9802230324257806e-05, "loss": 0.9856, "step": 1568 }, { "epoch": 0.09164719626168225, "grad_norm": 1.3438186645507812, "learning_rate": 1.9801855760998067e-05, "loss": 0.7218, "step": 1569 }, { "epoch": 0.09170560747663552, "grad_norm": 2.637300968170166, "learning_rate": 1.9801480846923465e-05, "loss": 0.9859, "step": 1570 }, { "epoch": 0.09176401869158879, "grad_norm": 2.3036670684814453, "learning_rate": 1.980110558204742e-05, "loss": 0.8499, "step": 1571 }, { "epoch": 0.09182242990654206, "grad_norm": 2.312058448791504, "learning_rate": 1.980072996638336e-05, "loss": 0.9011, "step": 1572 }, { "epoch": 0.09188084112149533, "grad_norm": 1.9511947631835938, "learning_rate": 1.980035399994473e-05, "loss": 1.0346, "step": 1573 }, { "epoch": 0.0919392523364486, "grad_norm": 2.986764907836914, "learning_rate": 1.979997768274499e-05, "loss": 0.7916, "step": 1574 }, { "epoch": 0.09199766355140188, "grad_norm": 2.6883530616760254, "learning_rate": 1.9799601014797603e-05, "loss": 1.031, "step": 1575 }, { "epoch": 0.09205607476635513, "grad_norm": 2.636569023132324, "learning_rate": 1.979922399611605e-05, "loss": 0.9755, "step": 1576 }, { "epoch": 0.0921144859813084, "grad_norm": 2.1100246906280518, "learning_rate": 1.979884662671383e-05, "loss": 0.8785, "step": 1577 }, { "epoch": 0.09217289719626168, "grad_norm": 2.3160743713378906, "learning_rate": 1.9798468906604445e-05, "loss": 0.8914, "step": 1578 }, { "epoch": 0.09223130841121495, "grad_norm": 1.459859013557434, "learning_rate": 1.9798090835801418e-05, "loss": 0.8023, "step": 1579 }, { "epoch": 0.09228971962616822, "grad_norm": 2.377736806869507, "learning_rate": 1.9797712414318277e-05, "loss": 0.6673, "step": 1580 }, { "epoch": 0.09234813084112149, "grad_norm": 1.8885759115219116, "learning_rate": 1.9797333642168564e-05, "loss": 0.922, "step": 1581 }, { "epoch": 0.09240654205607476, "grad_norm": 2.330498456954956, "learning_rate": 1.979695451936584e-05, "loss": 0.852, "step": 1582 }, { "epoch": 0.09246495327102804, "grad_norm": 2.5432028770446777, "learning_rate": 1.979657504592367e-05, "loss": 0.8701, "step": 1583 }, { "epoch": 0.09252336448598131, "grad_norm": 1.9273066520690918, "learning_rate": 1.9796195221855637e-05, "loss": 1.0026, "step": 1584 }, { "epoch": 0.09258177570093458, "grad_norm": 3.523664951324463, "learning_rate": 1.979581504717534e-05, "loss": 0.8117, "step": 1585 }, { "epoch": 0.09264018691588785, "grad_norm": 1.7181013822555542, "learning_rate": 1.979543452189638e-05, "loss": 0.811, "step": 1586 }, { "epoch": 0.09269859813084112, "grad_norm": 2.8290317058563232, "learning_rate": 1.9795053646032375e-05, "loss": 0.8548, "step": 1587 }, { "epoch": 0.0927570093457944, "grad_norm": 1.7355116605758667, "learning_rate": 1.9794672419596966e-05, "loss": 0.8641, "step": 1588 }, { "epoch": 0.09281542056074767, "grad_norm": 2.0612783432006836, "learning_rate": 1.9794290842603785e-05, "loss": 0.8851, "step": 1589 }, { "epoch": 0.09287383177570094, "grad_norm": 3.9269638061523438, "learning_rate": 1.9793908915066497e-05, "loss": 0.8938, "step": 1590 }, { "epoch": 0.09293224299065421, "grad_norm": 1.736162781715393, "learning_rate": 1.979352663699877e-05, "loss": 0.9556, "step": 1591 }, { "epoch": 0.09299065420560748, "grad_norm": 3.2650747299194336, "learning_rate": 1.9793144008414282e-05, "loss": 0.8697, "step": 1592 }, { "epoch": 0.09304906542056075, "grad_norm": 1.538016438484192, "learning_rate": 1.9792761029326735e-05, "loss": 0.8261, "step": 1593 }, { "epoch": 0.09310747663551402, "grad_norm": 1.4787341356277466, "learning_rate": 1.979237769974983e-05, "loss": 0.7168, "step": 1594 }, { "epoch": 0.0931658878504673, "grad_norm": 2.488201141357422, "learning_rate": 1.979199401969729e-05, "loss": 0.9696, "step": 1595 }, { "epoch": 0.09322429906542055, "grad_norm": 1.871623158454895, "learning_rate": 1.9791609989182843e-05, "loss": 0.7577, "step": 1596 }, { "epoch": 0.09328271028037383, "grad_norm": 2.1463236808776855, "learning_rate": 1.979122560822024e-05, "loss": 0.9815, "step": 1597 }, { "epoch": 0.0933411214953271, "grad_norm": 1.560876727104187, "learning_rate": 1.979084087682323e-05, "loss": 0.9014, "step": 1598 }, { "epoch": 0.09339953271028037, "grad_norm": 1.7150249481201172, "learning_rate": 1.9790455795005588e-05, "loss": 0.9074, "step": 1599 }, { "epoch": 0.09345794392523364, "grad_norm": 1.8771615028381348, "learning_rate": 1.97900703627811e-05, "loss": 0.7739, "step": 1600 }, { "epoch": 0.09351635514018691, "grad_norm": 2.16631817817688, "learning_rate": 1.9789684580163553e-05, "loss": 1.0566, "step": 1601 }, { "epoch": 0.09357476635514018, "grad_norm": 2.2761216163635254, "learning_rate": 1.978929844716676e-05, "loss": 1.0406, "step": 1602 }, { "epoch": 0.09363317757009346, "grad_norm": 1.8371055126190186, "learning_rate": 1.9788911963804536e-05, "loss": 0.7351, "step": 1603 }, { "epoch": 0.09369158878504673, "grad_norm": 3.5290496349334717, "learning_rate": 1.9788525130090722e-05, "loss": 1.1212, "step": 1604 }, { "epoch": 0.09375, "grad_norm": 1.959128975868225, "learning_rate": 1.9788137946039155e-05, "loss": 0.8292, "step": 1605 }, { "epoch": 0.09380841121495327, "grad_norm": 3.7737088203430176, "learning_rate": 1.9787750411663695e-05, "loss": 0.9808, "step": 1606 }, { "epoch": 0.09386682242990654, "grad_norm": 2.202183723449707, "learning_rate": 1.978736252697821e-05, "loss": 1.077, "step": 1607 }, { "epoch": 0.09392523364485982, "grad_norm": 3.872947931289673, "learning_rate": 1.9786974291996585e-05, "loss": 1.0955, "step": 1608 }, { "epoch": 0.09398364485981309, "grad_norm": 1.7463369369506836, "learning_rate": 1.9786585706732717e-05, "loss": 0.8699, "step": 1609 }, { "epoch": 0.09404205607476636, "grad_norm": 2.259281873703003, "learning_rate": 1.978619677120051e-05, "loss": 0.8181, "step": 1610 }, { "epoch": 0.09410046728971963, "grad_norm": 3.6529836654663086, "learning_rate": 1.978580748541389e-05, "loss": 1.0272, "step": 1611 }, { "epoch": 0.0941588785046729, "grad_norm": 2.050065279006958, "learning_rate": 1.9785417849386783e-05, "loss": 0.7833, "step": 1612 }, { "epoch": 0.09421728971962617, "grad_norm": 5.2519330978393555, "learning_rate": 1.9785027863133134e-05, "loss": 0.9736, "step": 1613 }, { "epoch": 0.09427570093457945, "grad_norm": 1.7833008766174316, "learning_rate": 1.9784637526666907e-05, "loss": 0.9527, "step": 1614 }, { "epoch": 0.0943341121495327, "grad_norm": 3.850276231765747, "learning_rate": 1.978424684000207e-05, "loss": 0.9824, "step": 1615 }, { "epoch": 0.09439252336448598, "grad_norm": 3.39623761177063, "learning_rate": 1.9783855803152604e-05, "loss": 0.9784, "step": 1616 }, { "epoch": 0.09445093457943925, "grad_norm": 2.040248155593872, "learning_rate": 1.9783464416132507e-05, "loss": 0.8637, "step": 1617 }, { "epoch": 0.09450934579439252, "grad_norm": 3.09152889251709, "learning_rate": 1.9783072678955787e-05, "loss": 0.8812, "step": 1618 }, { "epoch": 0.09456775700934579, "grad_norm": 3.023146152496338, "learning_rate": 1.9782680591636462e-05, "loss": 0.9448, "step": 1619 }, { "epoch": 0.09462616822429906, "grad_norm": 2.1022729873657227, "learning_rate": 1.9782288154188564e-05, "loss": 0.7094, "step": 1620 }, { "epoch": 0.09468457943925233, "grad_norm": 4.170137405395508, "learning_rate": 1.9781895366626143e-05, "loss": 1.0954, "step": 1621 }, { "epoch": 0.0947429906542056, "grad_norm": 1.2094727754592896, "learning_rate": 1.9781502228963257e-05, "loss": 0.6348, "step": 1622 }, { "epoch": 0.09480140186915888, "grad_norm": 2.807992458343506, "learning_rate": 1.9781108741213973e-05, "loss": 0.8487, "step": 1623 }, { "epoch": 0.09485981308411215, "grad_norm": 3.090148448944092, "learning_rate": 1.9780714903392375e-05, "loss": 0.9295, "step": 1624 }, { "epoch": 0.09491822429906542, "grad_norm": 1.7081055641174316, "learning_rate": 1.9780320715512558e-05, "loss": 0.92, "step": 1625 }, { "epoch": 0.09497663551401869, "grad_norm": 2.185114622116089, "learning_rate": 1.9779926177588638e-05, "loss": 0.9504, "step": 1626 }, { "epoch": 0.09503504672897196, "grad_norm": 4.066847801208496, "learning_rate": 1.9779531289634725e-05, "loss": 0.9856, "step": 1627 }, { "epoch": 0.09509345794392524, "grad_norm": 2.8496954441070557, "learning_rate": 1.9779136051664958e-05, "loss": 1.1012, "step": 1628 }, { "epoch": 0.09515186915887851, "grad_norm": 2.5816574096679688, "learning_rate": 1.9778740463693483e-05, "loss": 0.9518, "step": 1629 }, { "epoch": 0.09521028037383178, "grad_norm": 1.736946702003479, "learning_rate": 1.9778344525734455e-05, "loss": 0.8664, "step": 1630 }, { "epoch": 0.09526869158878505, "grad_norm": 2.086721897125244, "learning_rate": 1.977794823780205e-05, "loss": 0.9021, "step": 1631 }, { "epoch": 0.09532710280373832, "grad_norm": 1.6036179065704346, "learning_rate": 1.9777551599910446e-05, "loss": 0.82, "step": 1632 }, { "epoch": 0.0953855140186916, "grad_norm": 2.099168539047241, "learning_rate": 1.977715461207384e-05, "loss": 0.8122, "step": 1633 }, { "epoch": 0.09544392523364487, "grad_norm": 1.6969940662384033, "learning_rate": 1.9776757274306445e-05, "loss": 1.0222, "step": 1634 }, { "epoch": 0.09550233644859812, "grad_norm": 2.0439236164093018, "learning_rate": 1.9776359586622477e-05, "loss": 1.1874, "step": 1635 }, { "epoch": 0.0955607476635514, "grad_norm": 1.5713903903961182, "learning_rate": 1.977596154903617e-05, "loss": 0.7205, "step": 1636 }, { "epoch": 0.09561915887850467, "grad_norm": 2.0240941047668457, "learning_rate": 1.9775563161561777e-05, "loss": 0.885, "step": 1637 }, { "epoch": 0.09567757009345794, "grad_norm": 1.6902655363082886, "learning_rate": 1.9775164424213543e-05, "loss": 0.8809, "step": 1638 }, { "epoch": 0.09573598130841121, "grad_norm": 2.101818323135376, "learning_rate": 1.9774765337005753e-05, "loss": 0.8567, "step": 1639 }, { "epoch": 0.09579439252336448, "grad_norm": 1.7948999404907227, "learning_rate": 1.977436589995268e-05, "loss": 0.9874, "step": 1640 }, { "epoch": 0.09585280373831775, "grad_norm": 1.7672703266143799, "learning_rate": 1.977396611306863e-05, "loss": 1.0737, "step": 1641 }, { "epoch": 0.09591121495327103, "grad_norm": 1.6490792036056519, "learning_rate": 1.9773565976367903e-05, "loss": 0.9421, "step": 1642 }, { "epoch": 0.0959696261682243, "grad_norm": 3.0401899814605713, "learning_rate": 1.9773165489864822e-05, "loss": 1.0334, "step": 1643 }, { "epoch": 0.09602803738317757, "grad_norm": 1.7901766300201416, "learning_rate": 1.9772764653573725e-05, "loss": 0.9805, "step": 1644 }, { "epoch": 0.09608644859813084, "grad_norm": 2.215501308441162, "learning_rate": 1.977236346750896e-05, "loss": 0.9638, "step": 1645 }, { "epoch": 0.09614485981308411, "grad_norm": 1.9185625314712524, "learning_rate": 1.9771961931684874e-05, "loss": 0.8557, "step": 1646 }, { "epoch": 0.09620327102803738, "grad_norm": 2.2430596351623535, "learning_rate": 1.9771560046115844e-05, "loss": 1.2236, "step": 1647 }, { "epoch": 0.09626168224299066, "grad_norm": 1.8280115127563477, "learning_rate": 1.9771157810816258e-05, "loss": 0.7872, "step": 1648 }, { "epoch": 0.09632009345794393, "grad_norm": 1.6615958213806152, "learning_rate": 1.9770755225800512e-05, "loss": 0.8417, "step": 1649 }, { "epoch": 0.0963785046728972, "grad_norm": 1.8698976039886475, "learning_rate": 1.977035229108301e-05, "loss": 0.8461, "step": 1650 }, { "epoch": 0.09643691588785047, "grad_norm": 2.348506450653076, "learning_rate": 1.9769949006678173e-05, "loss": 1.1034, "step": 1651 }, { "epoch": 0.09649532710280374, "grad_norm": 1.8915594816207886, "learning_rate": 1.976954537260044e-05, "loss": 1.0275, "step": 1652 }, { "epoch": 0.09655373831775702, "grad_norm": 2.5638794898986816, "learning_rate": 1.976914138886425e-05, "loss": 0.9365, "step": 1653 }, { "epoch": 0.09661214953271029, "grad_norm": 1.689927339553833, "learning_rate": 1.9768737055484067e-05, "loss": 1.013, "step": 1654 }, { "epoch": 0.09667056074766354, "grad_norm": 1.986106276512146, "learning_rate": 1.976833237247437e-05, "loss": 0.8304, "step": 1655 }, { "epoch": 0.09672897196261682, "grad_norm": 1.910451054573059, "learning_rate": 1.9767927339849627e-05, "loss": 0.8431, "step": 1656 }, { "epoch": 0.09678738317757009, "grad_norm": 1.76406729221344, "learning_rate": 1.976752195762434e-05, "loss": 0.8797, "step": 1657 }, { "epoch": 0.09684579439252336, "grad_norm": 1.8467042446136475, "learning_rate": 1.9767116225813027e-05, "loss": 0.8595, "step": 1658 }, { "epoch": 0.09690420560747663, "grad_norm": 1.4950053691864014, "learning_rate": 1.97667101444302e-05, "loss": 0.978, "step": 1659 }, { "epoch": 0.0969626168224299, "grad_norm": 1.7275121212005615, "learning_rate": 1.9766303713490392e-05, "loss": 0.9306, "step": 1660 }, { "epoch": 0.09702102803738318, "grad_norm": 1.5253212451934814, "learning_rate": 1.9765896933008156e-05, "loss": 0.9465, "step": 1661 }, { "epoch": 0.09707943925233645, "grad_norm": 1.676729679107666, "learning_rate": 1.9765489802998048e-05, "loss": 0.8424, "step": 1662 }, { "epoch": 0.09713785046728972, "grad_norm": 2.031646966934204, "learning_rate": 1.9765082323474634e-05, "loss": 0.8571, "step": 1663 }, { "epoch": 0.09719626168224299, "grad_norm": 1.8911052942276, "learning_rate": 1.9764674494452508e-05, "loss": 1.1059, "step": 1664 }, { "epoch": 0.09725467289719626, "grad_norm": 2.1676621437072754, "learning_rate": 1.976426631594626e-05, "loss": 0.9006, "step": 1665 }, { "epoch": 0.09731308411214953, "grad_norm": 1.6518397331237793, "learning_rate": 1.9763857787970503e-05, "loss": 0.8316, "step": 1666 }, { "epoch": 0.0973714953271028, "grad_norm": 1.3252601623535156, "learning_rate": 1.976344891053985e-05, "loss": 0.8221, "step": 1667 }, { "epoch": 0.09742990654205608, "grad_norm": 1.7094465494155884, "learning_rate": 1.9763039683668946e-05, "loss": 0.8781, "step": 1668 }, { "epoch": 0.09748831775700935, "grad_norm": 1.400722622871399, "learning_rate": 1.9762630107372432e-05, "loss": 0.7811, "step": 1669 }, { "epoch": 0.09754672897196262, "grad_norm": 2.064554452896118, "learning_rate": 1.9762220181664965e-05, "loss": 0.985, "step": 1670 }, { "epoch": 0.09760514018691589, "grad_norm": 1.3973281383514404, "learning_rate": 1.976180990656122e-05, "loss": 0.9635, "step": 1671 }, { "epoch": 0.09766355140186916, "grad_norm": 2.9462666511535645, "learning_rate": 1.9761399282075877e-05, "loss": 1.0244, "step": 1672 }, { "epoch": 0.09772196261682244, "grad_norm": 1.7012001276016235, "learning_rate": 1.9760988308223638e-05, "loss": 0.9185, "step": 1673 }, { "epoch": 0.09778037383177571, "grad_norm": 2.421828269958496, "learning_rate": 1.976057698501921e-05, "loss": 0.9131, "step": 1674 }, { "epoch": 0.09783878504672897, "grad_norm": 2.19384765625, "learning_rate": 1.9760165312477314e-05, "loss": 1.0015, "step": 1675 }, { "epoch": 0.09789719626168224, "grad_norm": 2.7042713165283203, "learning_rate": 1.9759753290612686e-05, "loss": 0.7743, "step": 1676 }, { "epoch": 0.09795560747663551, "grad_norm": 1.7481821775436401, "learning_rate": 1.975934091944007e-05, "loss": 0.9703, "step": 1677 }, { "epoch": 0.09801401869158878, "grad_norm": 1.6118868589401245, "learning_rate": 1.975892819897422e-05, "loss": 0.8513, "step": 1678 }, { "epoch": 0.09807242990654205, "grad_norm": 2.830660820007324, "learning_rate": 1.9758515129229918e-05, "loss": 0.9369, "step": 1679 }, { "epoch": 0.09813084112149532, "grad_norm": 1.716513752937317, "learning_rate": 1.9758101710221943e-05, "loss": 0.8035, "step": 1680 }, { "epoch": 0.0981892523364486, "grad_norm": 3.739403247833252, "learning_rate": 1.975768794196509e-05, "loss": 1.0095, "step": 1681 }, { "epoch": 0.09824766355140187, "grad_norm": 1.3364440202713013, "learning_rate": 1.975727382447417e-05, "loss": 0.8682, "step": 1682 }, { "epoch": 0.09830607476635514, "grad_norm": 2.120412588119507, "learning_rate": 1.9756859357764005e-05, "loss": 0.9957, "step": 1683 }, { "epoch": 0.09836448598130841, "grad_norm": 1.6280049085617065, "learning_rate": 1.975644454184943e-05, "loss": 0.8918, "step": 1684 }, { "epoch": 0.09842289719626168, "grad_norm": 1.8397235870361328, "learning_rate": 1.9756029376745287e-05, "loss": 1.0158, "step": 1685 }, { "epoch": 0.09848130841121495, "grad_norm": 1.6916722059249878, "learning_rate": 1.975561386246644e-05, "loss": 0.7294, "step": 1686 }, { "epoch": 0.09853971962616823, "grad_norm": 1.3853031396865845, "learning_rate": 1.9755197999027757e-05, "loss": 0.7366, "step": 1687 }, { "epoch": 0.0985981308411215, "grad_norm": 1.9131025075912476, "learning_rate": 1.9754781786444122e-05, "loss": 0.8014, "step": 1688 }, { "epoch": 0.09865654205607477, "grad_norm": 2.0002963542938232, "learning_rate": 1.9754365224730437e-05, "loss": 0.846, "step": 1689 }, { "epoch": 0.09871495327102804, "grad_norm": 2.208120107650757, "learning_rate": 1.9753948313901607e-05, "loss": 0.7921, "step": 1690 }, { "epoch": 0.09877336448598131, "grad_norm": 1.3783233165740967, "learning_rate": 1.9753531053972548e-05, "loss": 0.7607, "step": 1691 }, { "epoch": 0.09883177570093458, "grad_norm": 3.1907949447631836, "learning_rate": 1.9753113444958206e-05, "loss": 0.926, "step": 1692 }, { "epoch": 0.09889018691588786, "grad_norm": 1.7913610935211182, "learning_rate": 1.9752695486873516e-05, "loss": 0.801, "step": 1693 }, { "epoch": 0.09894859813084113, "grad_norm": 1.8997960090637207, "learning_rate": 1.9752277179733443e-05, "loss": 0.9133, "step": 1694 }, { "epoch": 0.09900700934579439, "grad_norm": 1.959707498550415, "learning_rate": 1.975185852355296e-05, "loss": 0.8038, "step": 1695 }, { "epoch": 0.09906542056074766, "grad_norm": 1.9978874921798706, "learning_rate": 1.9751439518347045e-05, "loss": 0.9534, "step": 1696 }, { "epoch": 0.09912383177570093, "grad_norm": 1.756245493888855, "learning_rate": 1.97510201641307e-05, "loss": 0.9546, "step": 1697 }, { "epoch": 0.0991822429906542, "grad_norm": 2.0474302768707275, "learning_rate": 1.975060046091893e-05, "loss": 0.7945, "step": 1698 }, { "epoch": 0.09924065420560747, "grad_norm": 1.781428337097168, "learning_rate": 1.975018040872676e-05, "loss": 0.9151, "step": 1699 }, { "epoch": 0.09929906542056074, "grad_norm": 1.5779017210006714, "learning_rate": 1.9749760007569224e-05, "loss": 1.0222, "step": 1700 }, { "epoch": 0.09935747663551402, "grad_norm": 1.1222758293151855, "learning_rate": 1.9749339257461367e-05, "loss": 0.7906, "step": 1701 }, { "epoch": 0.09941588785046729, "grad_norm": 2.121020793914795, "learning_rate": 1.9748918158418244e-05, "loss": 0.7987, "step": 1702 }, { "epoch": 0.09947429906542056, "grad_norm": 1.659645438194275, "learning_rate": 1.9748496710454934e-05, "loss": 0.9069, "step": 1703 }, { "epoch": 0.09953271028037383, "grad_norm": 1.992297649383545, "learning_rate": 1.9748074913586515e-05, "loss": 0.9084, "step": 1704 }, { "epoch": 0.0995911214953271, "grad_norm": 1.651262879371643, "learning_rate": 1.9747652767828085e-05, "loss": 0.8498, "step": 1705 }, { "epoch": 0.09964953271028038, "grad_norm": 1.9866281747817993, "learning_rate": 1.9747230273194755e-05, "loss": 0.7972, "step": 1706 }, { "epoch": 0.09970794392523365, "grad_norm": 2.4695420265197754, "learning_rate": 1.974680742970164e-05, "loss": 0.9646, "step": 1707 }, { "epoch": 0.09976635514018692, "grad_norm": 1.7983360290527344, "learning_rate": 1.974638423736388e-05, "loss": 0.8281, "step": 1708 }, { "epoch": 0.09982476635514019, "grad_norm": 1.6251462697982788, "learning_rate": 1.974596069619662e-05, "loss": 0.6898, "step": 1709 }, { "epoch": 0.09988317757009346, "grad_norm": 2.324321985244751, "learning_rate": 1.9745536806215024e-05, "loss": 0.9205, "step": 1710 }, { "epoch": 0.09994158878504673, "grad_norm": 1.824042797088623, "learning_rate": 1.9745112567434254e-05, "loss": 0.9955, "step": 1711 }, { "epoch": 0.1, "grad_norm": 1.8746535778045654, "learning_rate": 1.9744687979869494e-05, "loss": 0.7638, "step": 1712 }, { "epoch": 0.10005841121495328, "grad_norm": 2.164614200592041, "learning_rate": 1.9744263043535947e-05, "loss": 0.9729, "step": 1713 }, { "epoch": 0.10011682242990654, "grad_norm": 1.830432415008545, "learning_rate": 1.9743837758448822e-05, "loss": 0.7907, "step": 1714 }, { "epoch": 0.1001752336448598, "grad_norm": 2.4870548248291016, "learning_rate": 1.974341212462333e-05, "loss": 0.7855, "step": 1715 }, { "epoch": 0.10023364485981308, "grad_norm": 1.3017096519470215, "learning_rate": 1.974298614207472e-05, "loss": 0.8886, "step": 1716 }, { "epoch": 0.10029205607476635, "grad_norm": 1.7463834285736084, "learning_rate": 1.9742559810818224e-05, "loss": 0.9242, "step": 1717 }, { "epoch": 0.10035046728971962, "grad_norm": 3.0118939876556396, "learning_rate": 1.9742133130869107e-05, "loss": 0.9493, "step": 1718 }, { "epoch": 0.1004088785046729, "grad_norm": 4.212433338165283, "learning_rate": 1.974170610224264e-05, "loss": 0.9217, "step": 1719 }, { "epoch": 0.10046728971962617, "grad_norm": 2.334174156188965, "learning_rate": 1.974127872495411e-05, "loss": 0.9133, "step": 1720 }, { "epoch": 0.10052570093457944, "grad_norm": 2.016275405883789, "learning_rate": 1.9740850999018802e-05, "loss": 0.7298, "step": 1721 }, { "epoch": 0.10058411214953271, "grad_norm": 5.289222240447998, "learning_rate": 1.9740422924452038e-05, "loss": 0.9527, "step": 1722 }, { "epoch": 0.10064252336448598, "grad_norm": 2.4766430854797363, "learning_rate": 1.9739994501269132e-05, "loss": 0.9649, "step": 1723 }, { "epoch": 0.10070093457943925, "grad_norm": 3.510889768600464, "learning_rate": 1.973956572948542e-05, "loss": 0.8062, "step": 1724 }, { "epoch": 0.10075934579439252, "grad_norm": 1.8490923643112183, "learning_rate": 1.9739136609116243e-05, "loss": 1.0227, "step": 1725 }, { "epoch": 0.1008177570093458, "grad_norm": 2.378443717956543, "learning_rate": 1.9738707140176963e-05, "loss": 0.8512, "step": 1726 }, { "epoch": 0.10087616822429907, "grad_norm": 1.7471939325332642, "learning_rate": 1.9738277322682955e-05, "loss": 0.7822, "step": 1727 }, { "epoch": 0.10093457943925234, "grad_norm": 1.5788975954055786, "learning_rate": 1.9737847156649597e-05, "loss": 0.813, "step": 1728 }, { "epoch": 0.10099299065420561, "grad_norm": 1.7246719598770142, "learning_rate": 1.9737416642092288e-05, "loss": 0.8009, "step": 1729 }, { "epoch": 0.10105140186915888, "grad_norm": 1.9286447763442993, "learning_rate": 1.973698577902643e-05, "loss": 0.8264, "step": 1730 }, { "epoch": 0.10110981308411215, "grad_norm": 2.365823745727539, "learning_rate": 1.973655456746745e-05, "loss": 0.8468, "step": 1731 }, { "epoch": 0.10116822429906543, "grad_norm": 1.831999659538269, "learning_rate": 1.973612300743078e-05, "loss": 0.9478, "step": 1732 }, { "epoch": 0.1012266355140187, "grad_norm": 2.046635389328003, "learning_rate": 1.973569109893187e-05, "loss": 0.7946, "step": 1733 }, { "epoch": 0.10128504672897196, "grad_norm": 1.442053198814392, "learning_rate": 1.9735258841986175e-05, "loss": 0.6694, "step": 1734 }, { "epoch": 0.10134345794392523, "grad_norm": 2.762101888656616, "learning_rate": 1.973482623660916e-05, "loss": 0.8805, "step": 1735 }, { "epoch": 0.1014018691588785, "grad_norm": 1.266957402229309, "learning_rate": 1.9734393282816318e-05, "loss": 0.9607, "step": 1736 }, { "epoch": 0.10146028037383177, "grad_norm": 2.251291513442993, "learning_rate": 1.9733959980623134e-05, "loss": 0.8965, "step": 1737 }, { "epoch": 0.10151869158878504, "grad_norm": 2.0432465076446533, "learning_rate": 1.973352633004513e-05, "loss": 0.8301, "step": 1738 }, { "epoch": 0.10157710280373831, "grad_norm": 1.819504737854004, "learning_rate": 1.973309233109781e-05, "loss": 0.789, "step": 1739 }, { "epoch": 0.10163551401869159, "grad_norm": 2.3646674156188965, "learning_rate": 1.973265798379672e-05, "loss": 0.9275, "step": 1740 }, { "epoch": 0.10169392523364486, "grad_norm": 1.6392544507980347, "learning_rate": 1.97322232881574e-05, "loss": 0.9915, "step": 1741 }, { "epoch": 0.10175233644859813, "grad_norm": 1.9684373140335083, "learning_rate": 1.973178824419541e-05, "loss": 0.7179, "step": 1742 }, { "epoch": 0.1018107476635514, "grad_norm": 2.352365732192993, "learning_rate": 1.9731352851926325e-05, "loss": 1.0191, "step": 1743 }, { "epoch": 0.10186915887850467, "grad_norm": 1.4281351566314697, "learning_rate": 1.9730917111365718e-05, "loss": 0.7948, "step": 1744 }, { "epoch": 0.10192757009345794, "grad_norm": 4.827719211578369, "learning_rate": 1.9730481022529187e-05, "loss": 0.8601, "step": 1745 }, { "epoch": 0.10198598130841122, "grad_norm": 2.2329342365264893, "learning_rate": 1.9730044585432347e-05, "loss": 0.9983, "step": 1746 }, { "epoch": 0.10204439252336449, "grad_norm": 2.4460322856903076, "learning_rate": 1.9729607800090812e-05, "loss": 0.8672, "step": 1747 }, { "epoch": 0.10210280373831776, "grad_norm": 1.9007748365402222, "learning_rate": 1.9729170666520216e-05, "loss": 0.8554, "step": 1748 }, { "epoch": 0.10216121495327103, "grad_norm": 2.0034186840057373, "learning_rate": 1.9728733184736205e-05, "loss": 0.7378, "step": 1749 }, { "epoch": 0.1022196261682243, "grad_norm": 2.439919948577881, "learning_rate": 1.9728295354754436e-05, "loss": 1.0603, "step": 1750 }, { "epoch": 0.10227803738317758, "grad_norm": 2.761640787124634, "learning_rate": 1.972785717659058e-05, "loss": 1.1334, "step": 1751 }, { "epoch": 0.10233644859813085, "grad_norm": 3.693427324295044, "learning_rate": 1.9727418650260322e-05, "loss": 0.8334, "step": 1752 }, { "epoch": 0.10239485981308412, "grad_norm": 3.5497117042541504, "learning_rate": 1.9726979775779355e-05, "loss": 1.0128, "step": 1753 }, { "epoch": 0.10245327102803738, "grad_norm": 2.1107397079467773, "learning_rate": 1.972654055316338e-05, "loss": 0.7684, "step": 1754 }, { "epoch": 0.10251168224299065, "grad_norm": 2.190376043319702, "learning_rate": 1.9726100982428125e-05, "loss": 0.9107, "step": 1755 }, { "epoch": 0.10257009345794392, "grad_norm": 2.265418291091919, "learning_rate": 1.9725661063589325e-05, "loss": 0.8821, "step": 1756 }, { "epoch": 0.10262850467289719, "grad_norm": 1.8720624446868896, "learning_rate": 1.972522079666272e-05, "loss": 0.9829, "step": 1757 }, { "epoch": 0.10268691588785046, "grad_norm": 2.334522247314453, "learning_rate": 1.9724780181664064e-05, "loss": 0.9303, "step": 1758 }, { "epoch": 0.10274532710280374, "grad_norm": 1.716891884803772, "learning_rate": 1.9724339218609138e-05, "loss": 0.9324, "step": 1759 }, { "epoch": 0.102803738317757, "grad_norm": 2.018799066543579, "learning_rate": 1.9723897907513713e-05, "loss": 1.0347, "step": 1760 }, { "epoch": 0.10286214953271028, "grad_norm": 2.391186475753784, "learning_rate": 1.972345624839359e-05, "loss": 0.8672, "step": 1761 }, { "epoch": 0.10292056074766355, "grad_norm": 2.0627636909484863, "learning_rate": 1.972301424126457e-05, "loss": 1.0332, "step": 1762 }, { "epoch": 0.10297897196261682, "grad_norm": 1.8681501150131226, "learning_rate": 1.972257188614248e-05, "loss": 0.8816, "step": 1763 }, { "epoch": 0.1030373831775701, "grad_norm": 2.196596384048462, "learning_rate": 1.9722129183043154e-05, "loss": 0.9202, "step": 1764 }, { "epoch": 0.10309579439252337, "grad_norm": 1.9938938617706299, "learning_rate": 1.9721686131982427e-05, "loss": 0.7631, "step": 1765 }, { "epoch": 0.10315420560747664, "grad_norm": 2.3559093475341797, "learning_rate": 1.972124273297616e-05, "loss": 0.9573, "step": 1766 }, { "epoch": 0.10321261682242991, "grad_norm": 2.487239122390747, "learning_rate": 1.972079898604023e-05, "loss": 0.9309, "step": 1767 }, { "epoch": 0.10327102803738318, "grad_norm": 2.0039050579071045, "learning_rate": 1.972035489119051e-05, "loss": 0.9237, "step": 1768 }, { "epoch": 0.10332943925233645, "grad_norm": 1.5337411165237427, "learning_rate": 1.9719910448442893e-05, "loss": 0.955, "step": 1769 }, { "epoch": 0.10338785046728972, "grad_norm": 1.8069918155670166, "learning_rate": 1.9719465657813296e-05, "loss": 0.9318, "step": 1770 }, { "epoch": 0.103446261682243, "grad_norm": 1.3178205490112305, "learning_rate": 1.9719020519317628e-05, "loss": 0.6662, "step": 1771 }, { "epoch": 0.10350467289719627, "grad_norm": 1.5887757539749146, "learning_rate": 1.9718575032971828e-05, "loss": 0.9343, "step": 1772 }, { "epoch": 0.10356308411214954, "grad_norm": 1.7905186414718628, "learning_rate": 1.9718129198791836e-05, "loss": 0.8251, "step": 1773 }, { "epoch": 0.1036214953271028, "grad_norm": 1.6162465810775757, "learning_rate": 1.971768301679361e-05, "loss": 0.9342, "step": 1774 }, { "epoch": 0.10367990654205607, "grad_norm": 1.797282338142395, "learning_rate": 1.971723648699312e-05, "loss": 0.9962, "step": 1775 }, { "epoch": 0.10373831775700934, "grad_norm": 1.898902177810669, "learning_rate": 1.9716789609406345e-05, "loss": 1.0679, "step": 1776 }, { "epoch": 0.10379672897196261, "grad_norm": 1.47907292842865, "learning_rate": 1.9716342384049283e-05, "loss": 0.8622, "step": 1777 }, { "epoch": 0.10385514018691588, "grad_norm": 1.6730778217315674, "learning_rate": 1.9715894810937938e-05, "loss": 0.8258, "step": 1778 }, { "epoch": 0.10391355140186916, "grad_norm": 1.8848354816436768, "learning_rate": 1.971544689008833e-05, "loss": 0.8452, "step": 1779 }, { "epoch": 0.10397196261682243, "grad_norm": 1.4261916875839233, "learning_rate": 1.971499862151649e-05, "loss": 0.8198, "step": 1780 }, { "epoch": 0.1040303738317757, "grad_norm": 2.79071044921875, "learning_rate": 1.971455000523846e-05, "loss": 1.0232, "step": 1781 }, { "epoch": 0.10408878504672897, "grad_norm": 2.380924940109253, "learning_rate": 1.97141010412703e-05, "loss": 0.8867, "step": 1782 }, { "epoch": 0.10414719626168224, "grad_norm": 1.9224822521209717, "learning_rate": 1.9713651729628075e-05, "loss": 0.9307, "step": 1783 }, { "epoch": 0.10420560747663551, "grad_norm": 1.4275678396224976, "learning_rate": 1.971320207032787e-05, "loss": 0.9281, "step": 1784 }, { "epoch": 0.10426401869158879, "grad_norm": 1.9907203912734985, "learning_rate": 1.9712752063385773e-05, "loss": 0.8019, "step": 1785 }, { "epoch": 0.10432242990654206, "grad_norm": 1.8381708860397339, "learning_rate": 1.9712301708817896e-05, "loss": 1.0196, "step": 1786 }, { "epoch": 0.10438084112149533, "grad_norm": 3.128211498260498, "learning_rate": 1.971185100664035e-05, "loss": 0.8846, "step": 1787 }, { "epoch": 0.1044392523364486, "grad_norm": 1.7156306505203247, "learning_rate": 1.9711399956869278e-05, "loss": 0.9022, "step": 1788 }, { "epoch": 0.10449766355140187, "grad_norm": 1.9217166900634766, "learning_rate": 1.9710948559520813e-05, "loss": 0.8559, "step": 1789 }, { "epoch": 0.10455607476635514, "grad_norm": 1.329627513885498, "learning_rate": 1.9710496814611114e-05, "loss": 0.8835, "step": 1790 }, { "epoch": 0.10461448598130842, "grad_norm": 1.611405611038208, "learning_rate": 1.971004472215635e-05, "loss": 0.9917, "step": 1791 }, { "epoch": 0.10467289719626169, "grad_norm": 1.416218876838684, "learning_rate": 1.97095922821727e-05, "loss": 0.7711, "step": 1792 }, { "epoch": 0.10473130841121496, "grad_norm": 2.079219102859497, "learning_rate": 1.9709139494676356e-05, "loss": 1.1698, "step": 1793 }, { "epoch": 0.10478971962616822, "grad_norm": 2.2519588470458984, "learning_rate": 1.970868635968353e-05, "loss": 1.0829, "step": 1794 }, { "epoch": 0.10484813084112149, "grad_norm": 1.7508928775787354, "learning_rate": 1.970823287721043e-05, "loss": 1.0492, "step": 1795 }, { "epoch": 0.10490654205607476, "grad_norm": 1.5636515617370605, "learning_rate": 1.9707779047273296e-05, "loss": 0.8159, "step": 1796 }, { "epoch": 0.10496495327102803, "grad_norm": 1.8617615699768066, "learning_rate": 1.970732486988837e-05, "loss": 0.9129, "step": 1797 }, { "epoch": 0.1050233644859813, "grad_norm": 1.8431631326675415, "learning_rate": 1.97068703450719e-05, "loss": 1.0195, "step": 1798 }, { "epoch": 0.10508177570093458, "grad_norm": 1.6862398386001587, "learning_rate": 1.9706415472840157e-05, "loss": 0.9176, "step": 1799 }, { "epoch": 0.10514018691588785, "grad_norm": 1.681670069694519, "learning_rate": 1.9705960253209425e-05, "loss": 0.791, "step": 1800 }, { "epoch": 0.10519859813084112, "grad_norm": 1.7093528509140015, "learning_rate": 1.970550468619599e-05, "loss": 0.7985, "step": 1801 }, { "epoch": 0.10525700934579439, "grad_norm": 1.7405492067337036, "learning_rate": 1.9705048771816164e-05, "loss": 0.8457, "step": 1802 }, { "epoch": 0.10531542056074766, "grad_norm": 1.4548612833023071, "learning_rate": 1.970459251008626e-05, "loss": 0.9929, "step": 1803 }, { "epoch": 0.10537383177570094, "grad_norm": 2.073437452316284, "learning_rate": 1.9704135901022606e-05, "loss": 0.9982, "step": 1804 }, { "epoch": 0.1054322429906542, "grad_norm": 1.728155493736267, "learning_rate": 1.9703678944641554e-05, "loss": 0.8959, "step": 1805 }, { "epoch": 0.10549065420560748, "grad_norm": 1.2933253049850464, "learning_rate": 1.970322164095945e-05, "loss": 0.7006, "step": 1806 }, { "epoch": 0.10554906542056075, "grad_norm": 1.58533775806427, "learning_rate": 1.970276398999266e-05, "loss": 0.8573, "step": 1807 }, { "epoch": 0.10560747663551402, "grad_norm": 1.4463074207305908, "learning_rate": 1.9702305991757572e-05, "loss": 0.8373, "step": 1808 }, { "epoch": 0.1056658878504673, "grad_norm": 1.3959283828735352, "learning_rate": 1.970184764627057e-05, "loss": 1.0696, "step": 1809 }, { "epoch": 0.10572429906542057, "grad_norm": 1.441433310508728, "learning_rate": 1.9701388953548063e-05, "loss": 0.7337, "step": 1810 }, { "epoch": 0.10578271028037384, "grad_norm": 1.7928483486175537, "learning_rate": 1.9700929913606466e-05, "loss": 0.9783, "step": 1811 }, { "epoch": 0.10584112149532711, "grad_norm": 1.3552237749099731, "learning_rate": 1.970047052646221e-05, "loss": 0.7901, "step": 1812 }, { "epoch": 0.10589953271028038, "grad_norm": 1.9775052070617676, "learning_rate": 1.9700010792131733e-05, "loss": 1.0681, "step": 1813 }, { "epoch": 0.10595794392523364, "grad_norm": 1.5140234231948853, "learning_rate": 1.9699550710631495e-05, "loss": 0.7135, "step": 1814 }, { "epoch": 0.10601635514018691, "grad_norm": 1.2248616218566895, "learning_rate": 1.9699090281977958e-05, "loss": 0.6783, "step": 1815 }, { "epoch": 0.10607476635514018, "grad_norm": 1.5295891761779785, "learning_rate": 1.96986295061876e-05, "loss": 0.7996, "step": 1816 }, { "epoch": 0.10613317757009345, "grad_norm": 2.2120296955108643, "learning_rate": 1.969816838327692e-05, "loss": 0.7773, "step": 1817 }, { "epoch": 0.10619158878504673, "grad_norm": 1.5886682271957397, "learning_rate": 1.9697706913262412e-05, "loss": 0.7755, "step": 1818 }, { "epoch": 0.10625, "grad_norm": 1.4638757705688477, "learning_rate": 1.9697245096160603e-05, "loss": 0.8065, "step": 1819 }, { "epoch": 0.10630841121495327, "grad_norm": 1.1902036666870117, "learning_rate": 1.9696782931988012e-05, "loss": 0.7686, "step": 1820 }, { "epoch": 0.10636682242990654, "grad_norm": 2.177333116531372, "learning_rate": 1.9696320420761185e-05, "loss": 0.8521, "step": 1821 }, { "epoch": 0.10642523364485981, "grad_norm": 1.3340034484863281, "learning_rate": 1.9695857562496675e-05, "loss": 0.9767, "step": 1822 }, { "epoch": 0.10648364485981308, "grad_norm": 1.4656609296798706, "learning_rate": 1.9695394357211048e-05, "loss": 0.9269, "step": 1823 }, { "epoch": 0.10654205607476636, "grad_norm": 1.901045560836792, "learning_rate": 1.969493080492088e-05, "loss": 0.9248, "step": 1824 }, { "epoch": 0.10660046728971963, "grad_norm": 1.368613362312317, "learning_rate": 1.9694466905642765e-05, "loss": 0.8179, "step": 1825 }, { "epoch": 0.1066588785046729, "grad_norm": 1.873719334602356, "learning_rate": 1.9694002659393306e-05, "loss": 0.9215, "step": 1826 }, { "epoch": 0.10671728971962617, "grad_norm": 1.5580739974975586, "learning_rate": 1.9693538066189117e-05, "loss": 0.9117, "step": 1827 }, { "epoch": 0.10677570093457944, "grad_norm": 1.364532232284546, "learning_rate": 1.969307312604683e-05, "loss": 0.9429, "step": 1828 }, { "epoch": 0.10683411214953271, "grad_norm": 1.5947905778884888, "learning_rate": 1.969260783898308e-05, "loss": 0.8594, "step": 1829 }, { "epoch": 0.10689252336448599, "grad_norm": 2.531104803085327, "learning_rate": 1.969214220501452e-05, "loss": 0.9504, "step": 1830 }, { "epoch": 0.10695093457943926, "grad_norm": 1.781579613685608, "learning_rate": 1.9691676224157817e-05, "loss": 0.9008, "step": 1831 }, { "epoch": 0.10700934579439253, "grad_norm": 1.8423019647598267, "learning_rate": 1.9691209896429656e-05, "loss": 0.867, "step": 1832 }, { "epoch": 0.10706775700934579, "grad_norm": 1.303336262702942, "learning_rate": 1.9690743221846716e-05, "loss": 0.8147, "step": 1833 }, { "epoch": 0.10712616822429906, "grad_norm": 2.3345441818237305, "learning_rate": 1.9690276200425706e-05, "loss": 0.9187, "step": 1834 }, { "epoch": 0.10718457943925233, "grad_norm": 1.236685037612915, "learning_rate": 1.968980883218334e-05, "loss": 0.8808, "step": 1835 }, { "epoch": 0.1072429906542056, "grad_norm": 2.5295441150665283, "learning_rate": 1.9689341117136342e-05, "loss": 0.7521, "step": 1836 }, { "epoch": 0.10730140186915887, "grad_norm": 1.4598242044448853, "learning_rate": 1.968887305530146e-05, "loss": 0.704, "step": 1837 }, { "epoch": 0.10735981308411215, "grad_norm": 2.7084403038024902, "learning_rate": 1.9688404646695432e-05, "loss": 1.0353, "step": 1838 }, { "epoch": 0.10741822429906542, "grad_norm": 2.191612958908081, "learning_rate": 1.9687935891335038e-05, "loss": 0.8465, "step": 1839 }, { "epoch": 0.10747663551401869, "grad_norm": 1.564834475517273, "learning_rate": 1.9687466789237048e-05, "loss": 0.9199, "step": 1840 }, { "epoch": 0.10753504672897196, "grad_norm": 3.051368474960327, "learning_rate": 1.968699734041825e-05, "loss": 0.7985, "step": 1841 }, { "epoch": 0.10759345794392523, "grad_norm": 1.6552386283874512, "learning_rate": 1.9686527544895447e-05, "loss": 0.8123, "step": 1842 }, { "epoch": 0.1076518691588785, "grad_norm": 2.3319196701049805, "learning_rate": 1.968605740268546e-05, "loss": 0.8041, "step": 1843 }, { "epoch": 0.10771028037383178, "grad_norm": 2.5723392963409424, "learning_rate": 1.9685586913805105e-05, "loss": 0.8881, "step": 1844 }, { "epoch": 0.10776869158878505, "grad_norm": 2.4450197219848633, "learning_rate": 1.9685116078271224e-05, "loss": 0.9931, "step": 1845 }, { "epoch": 0.10782710280373832, "grad_norm": 2.0975072383880615, "learning_rate": 1.9684644896100673e-05, "loss": 1.11, "step": 1846 }, { "epoch": 0.10788551401869159, "grad_norm": 1.919787883758545, "learning_rate": 1.9684173367310315e-05, "loss": 0.9081, "step": 1847 }, { "epoch": 0.10794392523364486, "grad_norm": 4.5761003494262695, "learning_rate": 1.9683701491917026e-05, "loss": 1.1352, "step": 1848 }, { "epoch": 0.10800233644859814, "grad_norm": 3.1069536209106445, "learning_rate": 1.968322926993769e-05, "loss": 0.8756, "step": 1849 }, { "epoch": 0.1080607476635514, "grad_norm": 3.1656370162963867, "learning_rate": 1.968275670138921e-05, "loss": 0.9994, "step": 1850 }, { "epoch": 0.10811915887850468, "grad_norm": 2.0730209350585938, "learning_rate": 1.9682283786288504e-05, "loss": 0.8202, "step": 1851 }, { "epoch": 0.10817757009345795, "grad_norm": 1.561781644821167, "learning_rate": 1.9681810524652495e-05, "loss": 0.9145, "step": 1852 }, { "epoch": 0.10823598130841121, "grad_norm": 2.2083630561828613, "learning_rate": 1.9681336916498122e-05, "loss": 0.9163, "step": 1853 }, { "epoch": 0.10829439252336448, "grad_norm": 1.4836667776107788, "learning_rate": 1.9680862961842333e-05, "loss": 0.844, "step": 1854 }, { "epoch": 0.10835280373831775, "grad_norm": 2.047550678253174, "learning_rate": 1.9680388660702093e-05, "loss": 0.7253, "step": 1855 }, { "epoch": 0.10841121495327102, "grad_norm": 1.6283260583877563, "learning_rate": 1.967991401309438e-05, "loss": 0.8236, "step": 1856 }, { "epoch": 0.1084696261682243, "grad_norm": 2.1221683025360107, "learning_rate": 1.9679439019036178e-05, "loss": 0.8577, "step": 1857 }, { "epoch": 0.10852803738317757, "grad_norm": 1.5927067995071411, "learning_rate": 1.9678963678544492e-05, "loss": 0.9506, "step": 1858 }, { "epoch": 0.10858644859813084, "grad_norm": 1.5824975967407227, "learning_rate": 1.967848799163633e-05, "loss": 0.9017, "step": 1859 }, { "epoch": 0.10864485981308411, "grad_norm": 1.5376884937286377, "learning_rate": 1.967801195832872e-05, "loss": 0.9874, "step": 1860 }, { "epoch": 0.10870327102803738, "grad_norm": 1.3639124631881714, "learning_rate": 1.9677535578638694e-05, "loss": 0.7839, "step": 1861 }, { "epoch": 0.10876168224299065, "grad_norm": 1.325953483581543, "learning_rate": 1.9677058852583314e-05, "loss": 0.8012, "step": 1862 }, { "epoch": 0.10882009345794393, "grad_norm": 1.4277476072311401, "learning_rate": 1.967658178017963e-05, "loss": 0.8165, "step": 1863 }, { "epoch": 0.1088785046728972, "grad_norm": 1.3867236375808716, "learning_rate": 1.9676104361444724e-05, "loss": 0.8709, "step": 1864 }, { "epoch": 0.10893691588785047, "grad_norm": 1.7715550661087036, "learning_rate": 1.9675626596395678e-05, "loss": 1.1632, "step": 1865 }, { "epoch": 0.10899532710280374, "grad_norm": 1.3852616548538208, "learning_rate": 1.9675148485049597e-05, "loss": 1.0733, "step": 1866 }, { "epoch": 0.10905373831775701, "grad_norm": 1.3296912908554077, "learning_rate": 1.9674670027423587e-05, "loss": 0.8806, "step": 1867 }, { "epoch": 0.10911214953271028, "grad_norm": 1.848488450050354, "learning_rate": 1.9674191223534777e-05, "loss": 1.1607, "step": 1868 }, { "epoch": 0.10917056074766356, "grad_norm": 1.258955955505371, "learning_rate": 1.9673712073400305e-05, "loss": 0.9548, "step": 1869 }, { "epoch": 0.10922897196261683, "grad_norm": 1.2984896898269653, "learning_rate": 1.9673232577037313e-05, "loss": 0.9446, "step": 1870 }, { "epoch": 0.1092873831775701, "grad_norm": 1.2192782163619995, "learning_rate": 1.967275273446297e-05, "loss": 0.9184, "step": 1871 }, { "epoch": 0.10934579439252337, "grad_norm": 1.2347452640533447, "learning_rate": 1.9672272545694445e-05, "loss": 0.7668, "step": 1872 }, { "epoch": 0.10940420560747663, "grad_norm": 1.3433092832565308, "learning_rate": 1.9671792010748928e-05, "loss": 0.7638, "step": 1873 }, { "epoch": 0.1094626168224299, "grad_norm": 1.9099928140640259, "learning_rate": 1.9671311129643613e-05, "loss": 0.8631, "step": 1874 }, { "epoch": 0.10952102803738317, "grad_norm": 1.7923270463943481, "learning_rate": 1.9670829902395713e-05, "loss": 0.8583, "step": 1875 }, { "epoch": 0.10957943925233644, "grad_norm": 1.3189164400100708, "learning_rate": 1.9670348329022456e-05, "loss": 1.1337, "step": 1876 }, { "epoch": 0.10963785046728972, "grad_norm": 1.9358327388763428, "learning_rate": 1.966986640954107e-05, "loss": 0.8007, "step": 1877 }, { "epoch": 0.10969626168224299, "grad_norm": 1.786924123764038, "learning_rate": 1.966938414396881e-05, "loss": 0.8712, "step": 1878 }, { "epoch": 0.10975467289719626, "grad_norm": 1.2788797616958618, "learning_rate": 1.966890153232293e-05, "loss": 0.7687, "step": 1879 }, { "epoch": 0.10981308411214953, "grad_norm": 2.4143359661102295, "learning_rate": 1.9668418574620713e-05, "loss": 0.8456, "step": 1880 }, { "epoch": 0.1098714953271028, "grad_norm": 1.7079787254333496, "learning_rate": 1.9667935270879433e-05, "loss": 0.669, "step": 1881 }, { "epoch": 0.10992990654205607, "grad_norm": 2.682668685913086, "learning_rate": 1.9667451621116392e-05, "loss": 0.8977, "step": 1882 }, { "epoch": 0.10998831775700935, "grad_norm": 1.866428017616272, "learning_rate": 1.9666967625348907e-05, "loss": 0.9293, "step": 1883 }, { "epoch": 0.11004672897196262, "grad_norm": 2.108720302581787, "learning_rate": 1.966648328359429e-05, "loss": 0.9728, "step": 1884 }, { "epoch": 0.11010514018691589, "grad_norm": 1.7037887573242188, "learning_rate": 1.9665998595869883e-05, "loss": 1.0129, "step": 1885 }, { "epoch": 0.11016355140186916, "grad_norm": 1.683539628982544, "learning_rate": 1.9665513562193025e-05, "loss": 0.7285, "step": 1886 }, { "epoch": 0.11022196261682243, "grad_norm": 2.1561520099639893, "learning_rate": 1.9665028182581088e-05, "loss": 0.8674, "step": 1887 }, { "epoch": 0.1102803738317757, "grad_norm": 1.6845381259918213, "learning_rate": 1.9664542457051436e-05, "loss": 0.7591, "step": 1888 }, { "epoch": 0.11033878504672898, "grad_norm": 1.9364954233169556, "learning_rate": 1.9664056385621453e-05, "loss": 0.9188, "step": 1889 }, { "epoch": 0.11039719626168225, "grad_norm": 1.533801794052124, "learning_rate": 1.9663569968308537e-05, "loss": 0.8594, "step": 1890 }, { "epoch": 0.11045560747663552, "grad_norm": 1.4936518669128418, "learning_rate": 1.9663083205130104e-05, "loss": 0.6999, "step": 1891 }, { "epoch": 0.11051401869158879, "grad_norm": 2.6161630153656006, "learning_rate": 1.966259609610356e-05, "loss": 0.9787, "step": 1892 }, { "epoch": 0.11057242990654205, "grad_norm": 1.5611985921859741, "learning_rate": 1.9662108641246355e-05, "loss": 0.8243, "step": 1893 }, { "epoch": 0.11063084112149532, "grad_norm": 11.427597999572754, "learning_rate": 1.9661620840575927e-05, "loss": 1.0406, "step": 1894 }, { "epoch": 0.1106892523364486, "grad_norm": 1.727268099784851, "learning_rate": 1.9661132694109736e-05, "loss": 1.072, "step": 1895 }, { "epoch": 0.11074766355140186, "grad_norm": 2.591339349746704, "learning_rate": 1.9660644201865254e-05, "loss": 1.1691, "step": 1896 }, { "epoch": 0.11080607476635514, "grad_norm": 1.321518063545227, "learning_rate": 1.9660155363859966e-05, "loss": 0.9369, "step": 1897 }, { "epoch": 0.11086448598130841, "grad_norm": 2.606735944747925, "learning_rate": 1.9659666180111363e-05, "loss": 1.0831, "step": 1898 }, { "epoch": 0.11092289719626168, "grad_norm": 1.5576175451278687, "learning_rate": 1.9659176650636958e-05, "loss": 1.0654, "step": 1899 }, { "epoch": 0.11098130841121495, "grad_norm": 1.796794056892395, "learning_rate": 1.965868677545427e-05, "loss": 0.7974, "step": 1900 }, { "epoch": 0.11103971962616822, "grad_norm": 2.021371841430664, "learning_rate": 1.965819655458083e-05, "loss": 0.8989, "step": 1901 }, { "epoch": 0.1110981308411215, "grad_norm": 1.8356925249099731, "learning_rate": 1.9657705988034182e-05, "loss": 0.9095, "step": 1902 }, { "epoch": 0.11115654205607477, "grad_norm": 1.7307493686676025, "learning_rate": 1.965721507583189e-05, "loss": 1.0493, "step": 1903 }, { "epoch": 0.11121495327102804, "grad_norm": 1.562796950340271, "learning_rate": 1.9656723817991522e-05, "loss": 0.8735, "step": 1904 }, { "epoch": 0.11127336448598131, "grad_norm": 1.9513444900512695, "learning_rate": 1.9656232214530658e-05, "loss": 1.0244, "step": 1905 }, { "epoch": 0.11133177570093458, "grad_norm": 1.1816538572311401, "learning_rate": 1.9655740265466893e-05, "loss": 0.9083, "step": 1906 }, { "epoch": 0.11139018691588785, "grad_norm": 1.6560022830963135, "learning_rate": 1.9655247970817837e-05, "loss": 0.9097, "step": 1907 }, { "epoch": 0.11144859813084113, "grad_norm": 1.703262209892273, "learning_rate": 1.9654755330601104e-05, "loss": 0.9095, "step": 1908 }, { "epoch": 0.1115070093457944, "grad_norm": 1.3847929239273071, "learning_rate": 1.9654262344834335e-05, "loss": 0.9122, "step": 1909 }, { "epoch": 0.11156542056074767, "grad_norm": 1.6026049852371216, "learning_rate": 1.9653769013535163e-05, "loss": 0.7803, "step": 1910 }, { "epoch": 0.11162383177570094, "grad_norm": 1.982587218284607, "learning_rate": 1.9653275336721257e-05, "loss": 0.9076, "step": 1911 }, { "epoch": 0.11168224299065421, "grad_norm": 1.2341201305389404, "learning_rate": 1.9652781314410276e-05, "loss": 0.6953, "step": 1912 }, { "epoch": 0.11174065420560747, "grad_norm": 1.7407751083374023, "learning_rate": 1.96522869466199e-05, "loss": 0.9563, "step": 1913 }, { "epoch": 0.11179906542056074, "grad_norm": 1.301195740699768, "learning_rate": 1.9651792233367835e-05, "loss": 0.6746, "step": 1914 }, { "epoch": 0.11185747663551401, "grad_norm": 1.6017378568649292, "learning_rate": 1.9651297174671778e-05, "loss": 0.8106, "step": 1915 }, { "epoch": 0.11191588785046729, "grad_norm": 1.4247716665267944, "learning_rate": 1.965080177054945e-05, "loss": 0.9808, "step": 1916 }, { "epoch": 0.11197429906542056, "grad_norm": 1.153775691986084, "learning_rate": 1.965030602101858e-05, "loss": 0.8235, "step": 1917 }, { "epoch": 0.11203271028037383, "grad_norm": 1.8802562952041626, "learning_rate": 1.964980992609691e-05, "loss": 0.9435, "step": 1918 }, { "epoch": 0.1120911214953271, "grad_norm": 2.085048198699951, "learning_rate": 1.96493134858022e-05, "loss": 0.8083, "step": 1919 }, { "epoch": 0.11214953271028037, "grad_norm": 1.2927378416061401, "learning_rate": 1.9648816700152218e-05, "loss": 0.8646, "step": 1920 }, { "epoch": 0.11220794392523364, "grad_norm": 2.0029661655426025, "learning_rate": 1.964831956916474e-05, "loss": 0.9365, "step": 1921 }, { "epoch": 0.11226635514018692, "grad_norm": 1.700229287147522, "learning_rate": 1.964782209285756e-05, "loss": 0.8292, "step": 1922 }, { "epoch": 0.11232476635514019, "grad_norm": 2.112520694732666, "learning_rate": 1.964732427124848e-05, "loss": 1.055, "step": 1923 }, { "epoch": 0.11238317757009346, "grad_norm": 1.4485876560211182, "learning_rate": 1.9646826104355327e-05, "loss": 0.9269, "step": 1924 }, { "epoch": 0.11244158878504673, "grad_norm": 1.5796265602111816, "learning_rate": 1.9646327592195925e-05, "loss": 0.9404, "step": 1925 }, { "epoch": 0.1125, "grad_norm": 1.9359288215637207, "learning_rate": 1.9645828734788113e-05, "loss": 0.7494, "step": 1926 }, { "epoch": 0.11255841121495327, "grad_norm": 2.6332082748413086, "learning_rate": 1.964532953214975e-05, "loss": 0.8554, "step": 1927 }, { "epoch": 0.11261682242990655, "grad_norm": 1.761292815208435, "learning_rate": 1.96448299842987e-05, "loss": 0.9752, "step": 1928 }, { "epoch": 0.11267523364485982, "grad_norm": 1.6836265325546265, "learning_rate": 1.9644330091252845e-05, "loss": 0.9233, "step": 1929 }, { "epoch": 0.11273364485981309, "grad_norm": 1.9156136512756348, "learning_rate": 1.9643829853030075e-05, "loss": 0.9889, "step": 1930 }, { "epoch": 0.11279205607476636, "grad_norm": 1.6535230875015259, "learning_rate": 1.9643329269648292e-05, "loss": 0.9679, "step": 1931 }, { "epoch": 0.11285046728971962, "grad_norm": 1.786576509475708, "learning_rate": 1.9642828341125414e-05, "loss": 0.9855, "step": 1932 }, { "epoch": 0.11290887850467289, "grad_norm": 1.9854387044906616, "learning_rate": 1.9642327067479368e-05, "loss": 0.9, "step": 1933 }, { "epoch": 0.11296728971962616, "grad_norm": 1.7199162244796753, "learning_rate": 1.9641825448728098e-05, "loss": 0.9204, "step": 1934 }, { "epoch": 0.11302570093457943, "grad_norm": 1.958738923072815, "learning_rate": 1.9641323484889554e-05, "loss": 0.8591, "step": 1935 }, { "epoch": 0.1130841121495327, "grad_norm": 2.0427439212799072, "learning_rate": 1.9640821175981704e-05, "loss": 1.0112, "step": 1936 }, { "epoch": 0.11314252336448598, "grad_norm": 2.355638027191162, "learning_rate": 1.9640318522022528e-05, "loss": 0.934, "step": 1937 }, { "epoch": 0.11320093457943925, "grad_norm": 1.7040530443191528, "learning_rate": 1.963981552303001e-05, "loss": 0.823, "step": 1938 }, { "epoch": 0.11325934579439252, "grad_norm": 2.468135118484497, "learning_rate": 1.9639312179022158e-05, "loss": 0.8039, "step": 1939 }, { "epoch": 0.1133177570093458, "grad_norm": 1.7346669435501099, "learning_rate": 1.9638808490016984e-05, "loss": 0.8436, "step": 1940 }, { "epoch": 0.11337616822429906, "grad_norm": 1.7018661499023438, "learning_rate": 1.9638304456032516e-05, "loss": 0.847, "step": 1941 }, { "epoch": 0.11343457943925234, "grad_norm": 2.897209882736206, "learning_rate": 1.9637800077086795e-05, "loss": 0.8219, "step": 1942 }, { "epoch": 0.11349299065420561, "grad_norm": 1.3266754150390625, "learning_rate": 1.963729535319787e-05, "loss": 0.9364, "step": 1943 }, { "epoch": 0.11355140186915888, "grad_norm": 2.3050477504730225, "learning_rate": 1.9636790284383815e-05, "loss": 0.7219, "step": 1944 }, { "epoch": 0.11360981308411215, "grad_norm": 1.68769109249115, "learning_rate": 1.9636284870662693e-05, "loss": 0.8458, "step": 1945 }, { "epoch": 0.11366822429906542, "grad_norm": 1.8117883205413818, "learning_rate": 1.96357791120526e-05, "loss": 1.0197, "step": 1946 }, { "epoch": 0.1137266355140187, "grad_norm": 2.104874849319458, "learning_rate": 1.963527300857164e-05, "loss": 0.716, "step": 1947 }, { "epoch": 0.11378504672897197, "grad_norm": 1.9223848581314087, "learning_rate": 1.963476656023792e-05, "loss": 0.8214, "step": 1948 }, { "epoch": 0.11384345794392524, "grad_norm": 1.7762049436569214, "learning_rate": 1.963425976706957e-05, "loss": 0.8744, "step": 1949 }, { "epoch": 0.11390186915887851, "grad_norm": 3.6404476165771484, "learning_rate": 1.963375262908473e-05, "loss": 1.0071, "step": 1950 }, { "epoch": 0.11396028037383178, "grad_norm": 4.1409831047058105, "learning_rate": 1.963324514630155e-05, "loss": 0.801, "step": 1951 }, { "epoch": 0.11401869158878504, "grad_norm": 2.2213194370269775, "learning_rate": 1.963273731873819e-05, "loss": 0.8118, "step": 1952 }, { "epoch": 0.11407710280373831, "grad_norm": 2.2568137645721436, "learning_rate": 1.963222914641283e-05, "loss": 0.7901, "step": 1953 }, { "epoch": 0.11413551401869158, "grad_norm": 1.9884575605392456, "learning_rate": 1.9631720629343652e-05, "loss": 1.0393, "step": 1954 }, { "epoch": 0.11419392523364486, "grad_norm": 2.1219382286071777, "learning_rate": 1.9631211767548862e-05, "loss": 1.1035, "step": 1955 }, { "epoch": 0.11425233644859813, "grad_norm": 1.8758656978607178, "learning_rate": 1.963070256104667e-05, "loss": 0.9175, "step": 1956 }, { "epoch": 0.1143107476635514, "grad_norm": 1.5649938583374023, "learning_rate": 1.96301930098553e-05, "loss": 0.8649, "step": 1957 }, { "epoch": 0.11436915887850467, "grad_norm": 1.9309331178665161, "learning_rate": 1.9629683113992996e-05, "loss": 0.8138, "step": 1958 }, { "epoch": 0.11442757009345794, "grad_norm": 2.1624722480773926, "learning_rate": 1.9629172873477995e-05, "loss": 0.8816, "step": 1959 }, { "epoch": 0.11448598130841121, "grad_norm": 2.222507953643799, "learning_rate": 1.962866228832857e-05, "loss": 0.8893, "step": 1960 }, { "epoch": 0.11454439252336449, "grad_norm": 1.8775275945663452, "learning_rate": 1.9628151358562984e-05, "loss": 0.8659, "step": 1961 }, { "epoch": 0.11460280373831776, "grad_norm": 1.4958484172821045, "learning_rate": 1.9627640084199538e-05, "loss": 0.902, "step": 1962 }, { "epoch": 0.11466121495327103, "grad_norm": 2.175535202026367, "learning_rate": 1.9627128465256516e-05, "loss": 1.066, "step": 1963 }, { "epoch": 0.1147196261682243, "grad_norm": 1.2747360467910767, "learning_rate": 1.962661650175224e-05, "loss": 0.8779, "step": 1964 }, { "epoch": 0.11477803738317757, "grad_norm": 1.483927607536316, "learning_rate": 1.962610419370503e-05, "loss": 0.8733, "step": 1965 }, { "epoch": 0.11483644859813084, "grad_norm": 1.3283393383026123, "learning_rate": 1.9625591541133225e-05, "loss": 0.8304, "step": 1966 }, { "epoch": 0.11489485981308412, "grad_norm": 1.8732757568359375, "learning_rate": 1.9625078544055163e-05, "loss": 0.8898, "step": 1967 }, { "epoch": 0.11495327102803739, "grad_norm": 2.0499956607818604, "learning_rate": 1.9624565202489216e-05, "loss": 1.062, "step": 1968 }, { "epoch": 0.11501168224299066, "grad_norm": 1.7164969444274902, "learning_rate": 1.9624051516453752e-05, "loss": 0.9891, "step": 1969 }, { "epoch": 0.11507009345794393, "grad_norm": 1.2474396228790283, "learning_rate": 1.9623537485967153e-05, "loss": 0.7983, "step": 1970 }, { "epoch": 0.1151285046728972, "grad_norm": 1.987201452255249, "learning_rate": 1.9623023111047823e-05, "loss": 0.8993, "step": 1971 }, { "epoch": 0.11518691588785046, "grad_norm": 1.3481909036636353, "learning_rate": 1.9622508391714167e-05, "loss": 0.8637, "step": 1972 }, { "epoch": 0.11524532710280373, "grad_norm": 1.8130360841751099, "learning_rate": 1.962199332798461e-05, "loss": 0.7423, "step": 1973 }, { "epoch": 0.115303738317757, "grad_norm": 1.6359803676605225, "learning_rate": 1.962147791987758e-05, "loss": 0.9384, "step": 1974 }, { "epoch": 0.11536214953271028, "grad_norm": 1.6479318141937256, "learning_rate": 1.9620962167411536e-05, "loss": 0.8319, "step": 1975 }, { "epoch": 0.11542056074766355, "grad_norm": 3.0191609859466553, "learning_rate": 1.9620446070604925e-05, "loss": 1.0076, "step": 1976 }, { "epoch": 0.11547897196261682, "grad_norm": 1.853803038597107, "learning_rate": 1.9619929629476225e-05, "loss": 0.8475, "step": 1977 }, { "epoch": 0.11553738317757009, "grad_norm": 4.376775741577148, "learning_rate": 1.961941284404392e-05, "loss": 1.0015, "step": 1978 }, { "epoch": 0.11559579439252336, "grad_norm": 1.82154381275177, "learning_rate": 1.9618895714326506e-05, "loss": 0.9913, "step": 1979 }, { "epoch": 0.11565420560747663, "grad_norm": 2.5593857765197754, "learning_rate": 1.9618378240342487e-05, "loss": 0.8066, "step": 1980 }, { "epoch": 0.1157126168224299, "grad_norm": 2.816962957382202, "learning_rate": 1.9617860422110387e-05, "loss": 0.9185, "step": 1981 }, { "epoch": 0.11577102803738318, "grad_norm": 1.539476752281189, "learning_rate": 1.961734225964874e-05, "loss": 0.869, "step": 1982 }, { "epoch": 0.11582943925233645, "grad_norm": 2.37937068939209, "learning_rate": 1.961682375297609e-05, "loss": 0.9825, "step": 1983 }, { "epoch": 0.11588785046728972, "grad_norm": 3.7523326873779297, "learning_rate": 1.961630490211099e-05, "loss": 1.0228, "step": 1984 }, { "epoch": 0.115946261682243, "grad_norm": 1.2320863008499146, "learning_rate": 1.961578570707202e-05, "loss": 0.8721, "step": 1985 }, { "epoch": 0.11600467289719626, "grad_norm": 2.8550121784210205, "learning_rate": 1.9615266167877755e-05, "loss": 1.0335, "step": 1986 }, { "epoch": 0.11606308411214954, "grad_norm": 2.580745220184326, "learning_rate": 1.961474628454679e-05, "loss": 1.0417, "step": 1987 }, { "epoch": 0.11612149532710281, "grad_norm": 2.534489631652832, "learning_rate": 1.9614226057097736e-05, "loss": 0.9857, "step": 1988 }, { "epoch": 0.11617990654205608, "grad_norm": 2.315356492996216, "learning_rate": 1.9613705485549208e-05, "loss": 0.7301, "step": 1989 }, { "epoch": 0.11623831775700935, "grad_norm": 2.3857643604278564, "learning_rate": 1.9613184569919844e-05, "loss": 0.7478, "step": 1990 }, { "epoch": 0.11629672897196262, "grad_norm": 1.7515337467193604, "learning_rate": 1.9612663310228278e-05, "loss": 0.8663, "step": 1991 }, { "epoch": 0.11635514018691588, "grad_norm": 1.4348148107528687, "learning_rate": 1.9612141706493177e-05, "loss": 0.8399, "step": 1992 }, { "epoch": 0.11641355140186915, "grad_norm": 2.3647191524505615, "learning_rate": 1.9611619758733197e-05, "loss": 0.9336, "step": 1993 }, { "epoch": 0.11647196261682242, "grad_norm": 2.0718297958374023, "learning_rate": 1.9611097466967032e-05, "loss": 0.847, "step": 1994 }, { "epoch": 0.1165303738317757, "grad_norm": 1.1669672727584839, "learning_rate": 1.9610574831213367e-05, "loss": 0.8845, "step": 1995 }, { "epoch": 0.11658878504672897, "grad_norm": 2.1060311794281006, "learning_rate": 1.961005185149091e-05, "loss": 0.8597, "step": 1996 }, { "epoch": 0.11664719626168224, "grad_norm": 2.2279860973358154, "learning_rate": 1.960952852781838e-05, "loss": 0.856, "step": 1997 }, { "epoch": 0.11670560747663551, "grad_norm": 1.56061851978302, "learning_rate": 1.9609004860214504e-05, "loss": 0.9292, "step": 1998 }, { "epoch": 0.11676401869158878, "grad_norm": 1.7378987073898315, "learning_rate": 1.9608480848698027e-05, "loss": 1.0677, "step": 1999 }, { "epoch": 0.11682242990654206, "grad_norm": 1.9456093311309814, "learning_rate": 1.96079564932877e-05, "loss": 0.8554, "step": 2000 }, { "epoch": 0.11688084112149533, "grad_norm": 1.264199137687683, "learning_rate": 1.9607431794002298e-05, "loss": 0.9692, "step": 2001 }, { "epoch": 0.1169392523364486, "grad_norm": 2.0817108154296875, "learning_rate": 1.9606906750860593e-05, "loss": 1.1359, "step": 2002 }, { "epoch": 0.11699766355140187, "grad_norm": 1.4435796737670898, "learning_rate": 1.9606381363881377e-05, "loss": 0.6464, "step": 2003 }, { "epoch": 0.11705607476635514, "grad_norm": 1.5421756505966187, "learning_rate": 1.9605855633083455e-05, "loss": 0.9816, "step": 2004 }, { "epoch": 0.11711448598130841, "grad_norm": 1.3122588396072388, "learning_rate": 1.9605329558485647e-05, "loss": 0.8524, "step": 2005 }, { "epoch": 0.11717289719626169, "grad_norm": 3.2480483055114746, "learning_rate": 1.9604803140106775e-05, "loss": 0.8365, "step": 2006 }, { "epoch": 0.11723130841121496, "grad_norm": 1.3746049404144287, "learning_rate": 1.9604276377965687e-05, "loss": 0.9218, "step": 2007 }, { "epoch": 0.11728971962616823, "grad_norm": 4.101699352264404, "learning_rate": 1.960374927208123e-05, "loss": 0.6429, "step": 2008 }, { "epoch": 0.1173481308411215, "grad_norm": 1.5413621664047241, "learning_rate": 1.960322182247227e-05, "loss": 0.7063, "step": 2009 }, { "epoch": 0.11740654205607477, "grad_norm": 1.3456348180770874, "learning_rate": 1.960269402915769e-05, "loss": 0.832, "step": 2010 }, { "epoch": 0.11746495327102804, "grad_norm": 2.2533528804779053, "learning_rate": 1.960216589215638e-05, "loss": 0.7569, "step": 2011 }, { "epoch": 0.1175233644859813, "grad_norm": 1.3311645984649658, "learning_rate": 1.960163741148723e-05, "loss": 0.8798, "step": 2012 }, { "epoch": 0.11758177570093457, "grad_norm": 2.3371694087982178, "learning_rate": 1.960110858716917e-05, "loss": 1.242, "step": 2013 }, { "epoch": 0.11764018691588785, "grad_norm": 1.9954432249069214, "learning_rate": 1.960057941922112e-05, "loss": 1.0021, "step": 2014 }, { "epoch": 0.11769859813084112, "grad_norm": 1.511364459991455, "learning_rate": 1.9600049907662023e-05, "loss": 0.8867, "step": 2015 }, { "epoch": 0.11775700934579439, "grad_norm": 2.2615275382995605, "learning_rate": 1.9599520052510824e-05, "loss": 0.9524, "step": 2016 }, { "epoch": 0.11781542056074766, "grad_norm": 1.0187091827392578, "learning_rate": 1.959898985378649e-05, "loss": 0.7086, "step": 2017 }, { "epoch": 0.11787383177570093, "grad_norm": 3.616694450378418, "learning_rate": 1.9598459311507998e-05, "loss": 0.9563, "step": 2018 }, { "epoch": 0.1179322429906542, "grad_norm": 2.018338203430176, "learning_rate": 1.959792842569434e-05, "loss": 1.0424, "step": 2019 }, { "epoch": 0.11799065420560748, "grad_norm": 4.6404571533203125, "learning_rate": 1.959739719636451e-05, "loss": 1.0691, "step": 2020 }, { "epoch": 0.11804906542056075, "grad_norm": 2.0391926765441895, "learning_rate": 1.9596865623537524e-05, "loss": 0.8376, "step": 2021 }, { "epoch": 0.11810747663551402, "grad_norm": 3.7060933113098145, "learning_rate": 1.9596333707232403e-05, "loss": 1.0015, "step": 2022 }, { "epoch": 0.11816588785046729, "grad_norm": 1.5392279624938965, "learning_rate": 1.9595801447468196e-05, "loss": 1.0074, "step": 2023 }, { "epoch": 0.11822429906542056, "grad_norm": 2.319525718688965, "learning_rate": 1.959526884426394e-05, "loss": 0.9817, "step": 2024 }, { "epoch": 0.11828271028037383, "grad_norm": 2.1306347846984863, "learning_rate": 1.9594735897638707e-05, "loss": 0.9499, "step": 2025 }, { "epoch": 0.1183411214953271, "grad_norm": 1.673129677772522, "learning_rate": 1.9594202607611568e-05, "loss": 0.9758, "step": 2026 }, { "epoch": 0.11839953271028038, "grad_norm": 1.9286283254623413, "learning_rate": 1.9593668974201606e-05, "loss": 0.8245, "step": 2027 }, { "epoch": 0.11845794392523365, "grad_norm": 2.800696611404419, "learning_rate": 1.9593134997427926e-05, "loss": 0.8754, "step": 2028 }, { "epoch": 0.11851635514018692, "grad_norm": 1.4276223182678223, "learning_rate": 1.9592600677309638e-05, "loss": 0.8355, "step": 2029 }, { "epoch": 0.1185747663551402, "grad_norm": 2.578256845474243, "learning_rate": 1.959206601386586e-05, "loss": 0.8748, "step": 2030 }, { "epoch": 0.11863317757009346, "grad_norm": 2.1267077922821045, "learning_rate": 1.9591531007115736e-05, "loss": 0.9429, "step": 2031 }, { "epoch": 0.11869158878504672, "grad_norm": 1.5515174865722656, "learning_rate": 1.9590995657078408e-05, "loss": 0.791, "step": 2032 }, { "epoch": 0.11875, "grad_norm": 3.555314540863037, "learning_rate": 1.9590459963773043e-05, "loss": 1.0858, "step": 2033 }, { "epoch": 0.11880841121495327, "grad_norm": 1.5405813455581665, "learning_rate": 1.958992392721881e-05, "loss": 0.9007, "step": 2034 }, { "epoch": 0.11886682242990654, "grad_norm": 2.86578631401062, "learning_rate": 1.958938754743489e-05, "loss": 0.8401, "step": 2035 }, { "epoch": 0.11892523364485981, "grad_norm": 1.4808937311172485, "learning_rate": 1.9588850824440486e-05, "loss": 0.9536, "step": 2036 }, { "epoch": 0.11898364485981308, "grad_norm": 2.4180190563201904, "learning_rate": 1.9588313758254806e-05, "loss": 0.8476, "step": 2037 }, { "epoch": 0.11904205607476635, "grad_norm": 2.0069119930267334, "learning_rate": 1.9587776348897076e-05, "loss": 1.0442, "step": 2038 }, { "epoch": 0.11910046728971962, "grad_norm": 1.770485520362854, "learning_rate": 1.958723859638652e-05, "loss": 0.9217, "step": 2039 }, { "epoch": 0.1191588785046729, "grad_norm": 2.968249797821045, "learning_rate": 1.95867005007424e-05, "loss": 1.0801, "step": 2040 }, { "epoch": 0.11921728971962617, "grad_norm": 1.6107814311981201, "learning_rate": 1.9586162061983955e-05, "loss": 0.8298, "step": 2041 }, { "epoch": 0.11927570093457944, "grad_norm": 2.747710943222046, "learning_rate": 1.9585623280130473e-05, "loss": 0.8853, "step": 2042 }, { "epoch": 0.11933411214953271, "grad_norm": 2.173614740371704, "learning_rate": 1.958508415520123e-05, "loss": 0.9076, "step": 2043 }, { "epoch": 0.11939252336448598, "grad_norm": 2.354492425918579, "learning_rate": 1.9584544687215522e-05, "loss": 0.9424, "step": 2044 }, { "epoch": 0.11945093457943926, "grad_norm": 1.8296446800231934, "learning_rate": 1.9584004876192658e-05, "loss": 0.9873, "step": 2045 }, { "epoch": 0.11950934579439253, "grad_norm": 2.234866142272949, "learning_rate": 1.958346472215196e-05, "loss": 0.9663, "step": 2046 }, { "epoch": 0.1195677570093458, "grad_norm": 2.4729506969451904, "learning_rate": 1.9582924225112756e-05, "loss": 0.8412, "step": 2047 }, { "epoch": 0.11962616822429907, "grad_norm": 1.5506638288497925, "learning_rate": 1.9582383385094396e-05, "loss": 0.6653, "step": 2048 }, { "epoch": 0.11968457943925234, "grad_norm": 1.7873667478561401, "learning_rate": 1.958184220211623e-05, "loss": 0.9254, "step": 2049 }, { "epoch": 0.11974299065420561, "grad_norm": 1.8487478494644165, "learning_rate": 1.9581300676197635e-05, "loss": 0.9666, "step": 2050 }, { "epoch": 0.11980140186915887, "grad_norm": 1.6954400539398193, "learning_rate": 1.9580758807357987e-05, "loss": 0.8886, "step": 2051 }, { "epoch": 0.11985981308411214, "grad_norm": 1.8583296537399292, "learning_rate": 1.9580216595616682e-05, "loss": 0.8713, "step": 2052 }, { "epoch": 0.11991822429906542, "grad_norm": 1.7573362588882446, "learning_rate": 1.9579674040993126e-05, "loss": 0.8212, "step": 2053 }, { "epoch": 0.11997663551401869, "grad_norm": 1.4926161766052246, "learning_rate": 1.9579131143506736e-05, "loss": 0.8231, "step": 2054 }, { "epoch": 0.12003504672897196, "grad_norm": 1.4381909370422363, "learning_rate": 1.9578587903176944e-05, "loss": 0.8938, "step": 2055 }, { "epoch": 0.12009345794392523, "grad_norm": 1.53939950466156, "learning_rate": 1.9578044320023195e-05, "loss": 0.855, "step": 2056 }, { "epoch": 0.1201518691588785, "grad_norm": 1.3188775777816772, "learning_rate": 1.9577500394064942e-05, "loss": 0.9503, "step": 2057 }, { "epoch": 0.12021028037383177, "grad_norm": 1.6125496625900269, "learning_rate": 1.957695612532165e-05, "loss": 0.9743, "step": 2058 }, { "epoch": 0.12026869158878505, "grad_norm": 1.9122079610824585, "learning_rate": 1.9576411513812803e-05, "loss": 0.991, "step": 2059 }, { "epoch": 0.12032710280373832, "grad_norm": 1.3567806482315063, "learning_rate": 1.9575866559557894e-05, "loss": 0.8035, "step": 2060 }, { "epoch": 0.12038551401869159, "grad_norm": 1.5512267351150513, "learning_rate": 1.9575321262576422e-05, "loss": 0.9709, "step": 2061 }, { "epoch": 0.12044392523364486, "grad_norm": 1.515252947807312, "learning_rate": 1.9574775622887907e-05, "loss": 0.7988, "step": 2062 }, { "epoch": 0.12050233644859813, "grad_norm": 1.4285662174224854, "learning_rate": 1.9574229640511874e-05, "loss": 0.9012, "step": 2063 }, { "epoch": 0.1205607476635514, "grad_norm": 1.2601011991500854, "learning_rate": 1.957368331546787e-05, "loss": 0.7712, "step": 2064 }, { "epoch": 0.12061915887850468, "grad_norm": 1.4295214414596558, "learning_rate": 1.9573136647775442e-05, "loss": 0.878, "step": 2065 }, { "epoch": 0.12067757009345795, "grad_norm": 1.359188199043274, "learning_rate": 1.9572589637454163e-05, "loss": 0.8048, "step": 2066 }, { "epoch": 0.12073598130841122, "grad_norm": 1.771178126335144, "learning_rate": 1.9572042284523605e-05, "loss": 1.0418, "step": 2067 }, { "epoch": 0.12079439252336449, "grad_norm": 1.5019460916519165, "learning_rate": 1.9571494589003358e-05, "loss": 0.7849, "step": 2068 }, { "epoch": 0.12085280373831776, "grad_norm": 1.4837197065353394, "learning_rate": 1.957094655091303e-05, "loss": 0.7871, "step": 2069 }, { "epoch": 0.12091121495327103, "grad_norm": 1.7068241834640503, "learning_rate": 1.957039817027223e-05, "loss": 0.8378, "step": 2070 }, { "epoch": 0.12096962616822429, "grad_norm": 1.1869313716888428, "learning_rate": 1.9569849447100586e-05, "loss": 0.7933, "step": 2071 }, { "epoch": 0.12102803738317756, "grad_norm": 1.478782296180725, "learning_rate": 1.956930038141774e-05, "loss": 0.9342, "step": 2072 }, { "epoch": 0.12108644859813084, "grad_norm": 1.6682809591293335, "learning_rate": 1.956875097324334e-05, "loss": 1.1194, "step": 2073 }, { "epoch": 0.12114485981308411, "grad_norm": 1.2719895839691162, "learning_rate": 1.9568201222597053e-05, "loss": 0.8653, "step": 2074 }, { "epoch": 0.12120327102803738, "grad_norm": 1.5553632974624634, "learning_rate": 1.956765112949855e-05, "loss": 0.8161, "step": 2075 }, { "epoch": 0.12126168224299065, "grad_norm": 1.4132663011550903, "learning_rate": 1.9567100693967525e-05, "loss": 0.7618, "step": 2076 }, { "epoch": 0.12132009345794392, "grad_norm": 1.5965806245803833, "learning_rate": 1.9566549916023673e-05, "loss": 0.9201, "step": 2077 }, { "epoch": 0.1213785046728972, "grad_norm": 1.328471064567566, "learning_rate": 1.956599879568671e-05, "loss": 0.8024, "step": 2078 }, { "epoch": 0.12143691588785047, "grad_norm": 2.0835208892822266, "learning_rate": 1.9565447332976362e-05, "loss": 0.7846, "step": 2079 }, { "epoch": 0.12149532710280374, "grad_norm": 1.7284830808639526, "learning_rate": 1.9564895527912365e-05, "loss": 0.8567, "step": 2080 }, { "epoch": 0.12155373831775701, "grad_norm": 2.2119834423065186, "learning_rate": 1.9564343380514467e-05, "loss": 0.8946, "step": 2081 }, { "epoch": 0.12161214953271028, "grad_norm": 1.6201359033584595, "learning_rate": 1.956379089080243e-05, "loss": 0.9233, "step": 2082 }, { "epoch": 0.12167056074766355, "grad_norm": 1.6458009481430054, "learning_rate": 1.956323805879603e-05, "loss": 0.942, "step": 2083 }, { "epoch": 0.12172897196261682, "grad_norm": 1.656184196472168, "learning_rate": 1.9562684884515047e-05, "loss": 0.9015, "step": 2084 }, { "epoch": 0.1217873831775701, "grad_norm": 2.4053151607513428, "learning_rate": 1.956213136797929e-05, "loss": 0.8215, "step": 2085 }, { "epoch": 0.12184579439252337, "grad_norm": 1.6228493452072144, "learning_rate": 1.9561577509208564e-05, "loss": 0.9088, "step": 2086 }, { "epoch": 0.12190420560747664, "grad_norm": 2.4924561977386475, "learning_rate": 1.956102330822269e-05, "loss": 1.0564, "step": 2087 }, { "epoch": 0.12196261682242991, "grad_norm": 1.2530896663665771, "learning_rate": 1.9560468765041506e-05, "loss": 1.0038, "step": 2088 }, { "epoch": 0.12202102803738318, "grad_norm": 2.4665729999542236, "learning_rate": 1.955991387968486e-05, "loss": 0.8344, "step": 2089 }, { "epoch": 0.12207943925233646, "grad_norm": 1.5937721729278564, "learning_rate": 1.9559358652172607e-05, "loss": 0.8126, "step": 2090 }, { "epoch": 0.12213785046728971, "grad_norm": 1.5175200700759888, "learning_rate": 1.9558803082524626e-05, "loss": 0.7446, "step": 2091 }, { "epoch": 0.12219626168224298, "grad_norm": 2.7863197326660156, "learning_rate": 1.9558247170760796e-05, "loss": 0.9549, "step": 2092 }, { "epoch": 0.12225467289719626, "grad_norm": 1.599575161933899, "learning_rate": 1.9557690916901016e-05, "loss": 0.9187, "step": 2093 }, { "epoch": 0.12231308411214953, "grad_norm": 2.69303560256958, "learning_rate": 1.955713432096519e-05, "loss": 0.9507, "step": 2094 }, { "epoch": 0.1223714953271028, "grad_norm": 1.6627908945083618, "learning_rate": 1.9556577382973247e-05, "loss": 0.6626, "step": 2095 }, { "epoch": 0.12242990654205607, "grad_norm": 2.5890891551971436, "learning_rate": 1.9556020102945113e-05, "loss": 0.9773, "step": 2096 }, { "epoch": 0.12248831775700934, "grad_norm": 1.1371123790740967, "learning_rate": 1.955546248090074e-05, "loss": 0.8103, "step": 2097 }, { "epoch": 0.12254672897196262, "grad_norm": 2.040595531463623, "learning_rate": 1.955490451686008e-05, "loss": 0.9855, "step": 2098 }, { "epoch": 0.12260514018691589, "grad_norm": 2.417919635772705, "learning_rate": 1.955434621084311e-05, "loss": 1.0321, "step": 2099 }, { "epoch": 0.12266355140186916, "grad_norm": 2.459073781967163, "learning_rate": 1.95537875628698e-05, "loss": 0.708, "step": 2100 }, { "epoch": 0.12272196261682243, "grad_norm": 2.6881954669952393, "learning_rate": 1.955322857296015e-05, "loss": 0.915, "step": 2101 }, { "epoch": 0.1227803738317757, "grad_norm": 3.476675033569336, "learning_rate": 1.955266924113417e-05, "loss": 1.1439, "step": 2102 }, { "epoch": 0.12283878504672897, "grad_norm": 2.1220877170562744, "learning_rate": 1.9552109567411877e-05, "loss": 1.0249, "step": 2103 }, { "epoch": 0.12289719626168225, "grad_norm": 2.2203991413116455, "learning_rate": 1.9551549551813306e-05, "loss": 0.9978, "step": 2104 }, { "epoch": 0.12295560747663552, "grad_norm": 1.6644954681396484, "learning_rate": 1.9550989194358492e-05, "loss": 0.9096, "step": 2105 }, { "epoch": 0.12301401869158879, "grad_norm": 3.130478858947754, "learning_rate": 1.9550428495067496e-05, "loss": 1.0257, "step": 2106 }, { "epoch": 0.12307242990654206, "grad_norm": 1.673453450202942, "learning_rate": 1.9549867453960386e-05, "loss": 0.8883, "step": 2107 }, { "epoch": 0.12313084112149533, "grad_norm": 1.9922500848770142, "learning_rate": 1.954930607105724e-05, "loss": 0.8742, "step": 2108 }, { "epoch": 0.1231892523364486, "grad_norm": 1.4739956855773926, "learning_rate": 1.954874434637815e-05, "loss": 0.8397, "step": 2109 }, { "epoch": 0.12324766355140188, "grad_norm": 1.8045525550842285, "learning_rate": 1.954818227994322e-05, "loss": 0.7843, "step": 2110 }, { "epoch": 0.12330607476635513, "grad_norm": 1.7863690853118896, "learning_rate": 1.9547619871772575e-05, "loss": 0.9792, "step": 2111 }, { "epoch": 0.1233644859813084, "grad_norm": 1.867249608039856, "learning_rate": 1.954705712188633e-05, "loss": 0.9444, "step": 2112 }, { "epoch": 0.12342289719626168, "grad_norm": 2.2551982402801514, "learning_rate": 1.9546494030304637e-05, "loss": 0.7783, "step": 2113 }, { "epoch": 0.12348130841121495, "grad_norm": 1.45034921169281, "learning_rate": 1.9545930597047643e-05, "loss": 0.9068, "step": 2114 }, { "epoch": 0.12353971962616822, "grad_norm": 2.109328269958496, "learning_rate": 1.9545366822135516e-05, "loss": 0.9792, "step": 2115 }, { "epoch": 0.12359813084112149, "grad_norm": 2.1118276119232178, "learning_rate": 1.954480270558844e-05, "loss": 0.9416, "step": 2116 }, { "epoch": 0.12365654205607476, "grad_norm": 2.512341260910034, "learning_rate": 1.954423824742659e-05, "loss": 0.8329, "step": 2117 }, { "epoch": 0.12371495327102804, "grad_norm": 2.2602431774139404, "learning_rate": 1.9543673447670184e-05, "loss": 1.0042, "step": 2118 }, { "epoch": 0.12377336448598131, "grad_norm": 1.5624760389328003, "learning_rate": 1.9543108306339428e-05, "loss": 0.7911, "step": 2119 }, { "epoch": 0.12383177570093458, "grad_norm": 1.4248154163360596, "learning_rate": 1.9542542823454555e-05, "loss": 0.8994, "step": 2120 }, { "epoch": 0.12389018691588785, "grad_norm": 1.7786754369735718, "learning_rate": 1.9541976999035796e-05, "loss": 0.8318, "step": 2121 }, { "epoch": 0.12394859813084112, "grad_norm": 1.2647498846054077, "learning_rate": 1.9541410833103405e-05, "loss": 0.8231, "step": 2122 }, { "epoch": 0.1240070093457944, "grad_norm": 1.2993320226669312, "learning_rate": 1.954084432567765e-05, "loss": 0.874, "step": 2123 }, { "epoch": 0.12406542056074767, "grad_norm": 2.242427110671997, "learning_rate": 1.95402774767788e-05, "loss": 0.9229, "step": 2124 }, { "epoch": 0.12412383177570094, "grad_norm": 1.4531553983688354, "learning_rate": 1.953971028642715e-05, "loss": 0.8701, "step": 2125 }, { "epoch": 0.12418224299065421, "grad_norm": 2.4355857372283936, "learning_rate": 1.9539142754642997e-05, "loss": 1.0054, "step": 2126 }, { "epoch": 0.12424065420560748, "grad_norm": 2.067734718322754, "learning_rate": 1.953857488144665e-05, "loss": 1.0689, "step": 2127 }, { "epoch": 0.12429906542056075, "grad_norm": 1.388192892074585, "learning_rate": 1.953800666685844e-05, "loss": 0.888, "step": 2128 }, { "epoch": 0.12435747663551402, "grad_norm": 1.3620918989181519, "learning_rate": 1.9537438110898694e-05, "loss": 0.8221, "step": 2129 }, { "epoch": 0.1244158878504673, "grad_norm": 1.4113397598266602, "learning_rate": 1.9536869213587768e-05, "loss": 0.9208, "step": 2130 }, { "epoch": 0.12447429906542055, "grad_norm": 1.4440003633499146, "learning_rate": 1.9536299974946024e-05, "loss": 0.9674, "step": 2131 }, { "epoch": 0.12453271028037383, "grad_norm": 2.3994505405426025, "learning_rate": 1.9535730394993834e-05, "loss": 0.918, "step": 2132 }, { "epoch": 0.1245911214953271, "grad_norm": 1.6295316219329834, "learning_rate": 1.9535160473751585e-05, "loss": 0.7107, "step": 2133 }, { "epoch": 0.12464953271028037, "grad_norm": 2.6238396167755127, "learning_rate": 1.953459021123967e-05, "loss": 1.0414, "step": 2134 }, { "epoch": 0.12470794392523364, "grad_norm": 1.8394136428833008, "learning_rate": 1.9534019607478503e-05, "loss": 0.9668, "step": 2135 }, { "epoch": 0.12476635514018691, "grad_norm": 3.8928158283233643, "learning_rate": 1.9533448662488507e-05, "loss": 1.0262, "step": 2136 }, { "epoch": 0.12482476635514018, "grad_norm": 1.9709678888320923, "learning_rate": 1.9532877376290112e-05, "loss": 0.9389, "step": 2137 }, { "epoch": 0.12488317757009346, "grad_norm": 2.4036693572998047, "learning_rate": 1.9532305748903773e-05, "loss": 0.8625, "step": 2138 }, { "epoch": 0.12494158878504673, "grad_norm": 1.420194387435913, "learning_rate": 1.9531733780349938e-05, "loss": 0.8853, "step": 2139 }, { "epoch": 0.125, "grad_norm": 1.6347026824951172, "learning_rate": 1.9531161470649084e-05, "loss": 0.8488, "step": 2140 }, { "epoch": 0.12505841121495326, "grad_norm": 1.6923352479934692, "learning_rate": 1.9530588819821698e-05, "loss": 0.7709, "step": 2141 }, { "epoch": 0.12511682242990654, "grad_norm": 1.8173236846923828, "learning_rate": 1.953001582788827e-05, "loss": 0.9834, "step": 2142 }, { "epoch": 0.1251752336448598, "grad_norm": 1.7390292882919312, "learning_rate": 1.9529442494869307e-05, "loss": 0.7559, "step": 2143 }, { "epoch": 0.1252336448598131, "grad_norm": 1.7280726432800293, "learning_rate": 1.9528868820785335e-05, "loss": 0.7741, "step": 2144 }, { "epoch": 0.12529205607476634, "grad_norm": 1.7105318307876587, "learning_rate": 1.9528294805656883e-05, "loss": 0.9272, "step": 2145 }, { "epoch": 0.12535046728971963, "grad_norm": 1.6730098724365234, "learning_rate": 1.9527720449504492e-05, "loss": 1.1006, "step": 2146 }, { "epoch": 0.1254088785046729, "grad_norm": 2.0551836490631104, "learning_rate": 1.9527145752348722e-05, "loss": 0.8767, "step": 2147 }, { "epoch": 0.12546728971962617, "grad_norm": 1.630053162574768, "learning_rate": 1.9526570714210146e-05, "loss": 0.8955, "step": 2148 }, { "epoch": 0.12552570093457943, "grad_norm": 1.6350476741790771, "learning_rate": 1.9525995335109333e-05, "loss": 0.9055, "step": 2149 }, { "epoch": 0.12558411214953272, "grad_norm": 2.6431233882904053, "learning_rate": 1.9525419615066886e-05, "loss": 0.8222, "step": 2150 }, { "epoch": 0.12564252336448598, "grad_norm": 2.170226573944092, "learning_rate": 1.952484355410341e-05, "loss": 1.0771, "step": 2151 }, { "epoch": 0.12570093457943926, "grad_norm": 1.8984359502792358, "learning_rate": 1.9524267152239517e-05, "loss": 0.9075, "step": 2152 }, { "epoch": 0.12575934579439252, "grad_norm": 1.641667366027832, "learning_rate": 1.9523690409495842e-05, "loss": 1.0238, "step": 2153 }, { "epoch": 0.1258177570093458, "grad_norm": 2.5063154697418213, "learning_rate": 1.9523113325893028e-05, "loss": 0.7192, "step": 2154 }, { "epoch": 0.12587616822429906, "grad_norm": 1.7447021007537842, "learning_rate": 1.952253590145172e-05, "loss": 0.8024, "step": 2155 }, { "epoch": 0.12593457943925235, "grad_norm": 2.457141399383545, "learning_rate": 1.9521958136192597e-05, "loss": 0.8303, "step": 2156 }, { "epoch": 0.1259929906542056, "grad_norm": 1.6981638669967651, "learning_rate": 1.9521380030136332e-05, "loss": 0.9843, "step": 2157 }, { "epoch": 0.1260514018691589, "grad_norm": 1.9870649576187134, "learning_rate": 1.9520801583303612e-05, "loss": 0.9086, "step": 2158 }, { "epoch": 0.12610981308411215, "grad_norm": 2.581160306930542, "learning_rate": 1.9520222795715145e-05, "loss": 1.0924, "step": 2159 }, { "epoch": 0.1261682242990654, "grad_norm": 3.495041847229004, "learning_rate": 1.9519643667391645e-05, "loss": 1.0265, "step": 2160 }, { "epoch": 0.1262266355140187, "grad_norm": 1.7841355800628662, "learning_rate": 1.9519064198353838e-05, "loss": 0.7113, "step": 2161 }, { "epoch": 0.12628504672897195, "grad_norm": 1.3301875591278076, "learning_rate": 1.9518484388622463e-05, "loss": 0.7221, "step": 2162 }, { "epoch": 0.12634345794392524, "grad_norm": 1.547468900680542, "learning_rate": 1.951790423821827e-05, "loss": 0.6022, "step": 2163 }, { "epoch": 0.1264018691588785, "grad_norm": 2.4770169258117676, "learning_rate": 1.9517323747162033e-05, "loss": 1.0193, "step": 2164 }, { "epoch": 0.12646028037383178, "grad_norm": 2.587423801422119, "learning_rate": 1.9516742915474518e-05, "loss": 1.0644, "step": 2165 }, { "epoch": 0.12651869158878504, "grad_norm": 2.772038221359253, "learning_rate": 1.9516161743176518e-05, "loss": 0.9613, "step": 2166 }, { "epoch": 0.12657710280373832, "grad_norm": 2.8217525482177734, "learning_rate": 1.951558023028883e-05, "loss": 0.9774, "step": 2167 }, { "epoch": 0.12663551401869158, "grad_norm": 1.964812159538269, "learning_rate": 1.951499837683227e-05, "loss": 0.9398, "step": 2168 }, { "epoch": 0.12669392523364487, "grad_norm": 1.6968915462493896, "learning_rate": 1.9514416182827665e-05, "loss": 0.86, "step": 2169 }, { "epoch": 0.12675233644859812, "grad_norm": 1.6326261758804321, "learning_rate": 1.9513833648295846e-05, "loss": 0.9597, "step": 2170 }, { "epoch": 0.1268107476635514, "grad_norm": 1.7537388801574707, "learning_rate": 1.9513250773257667e-05, "loss": 0.9012, "step": 2171 }, { "epoch": 0.12686915887850467, "grad_norm": 1.7116895914077759, "learning_rate": 1.9512667557733984e-05, "loss": 0.8566, "step": 2172 }, { "epoch": 0.12692757009345795, "grad_norm": 1.6056491136550903, "learning_rate": 1.9512084001745676e-05, "loss": 0.9635, "step": 2173 }, { "epoch": 0.1269859813084112, "grad_norm": 1.8058407306671143, "learning_rate": 1.9511500105313627e-05, "loss": 0.9021, "step": 2174 }, { "epoch": 0.1270443925233645, "grad_norm": 1.6351425647735596, "learning_rate": 1.9510915868458738e-05, "loss": 0.9014, "step": 2175 }, { "epoch": 0.12710280373831775, "grad_norm": 1.807141661643982, "learning_rate": 1.9510331291201914e-05, "loss": 0.9807, "step": 2176 }, { "epoch": 0.12716121495327104, "grad_norm": 1.7184354066848755, "learning_rate": 1.950974637356408e-05, "loss": 0.9262, "step": 2177 }, { "epoch": 0.1272196261682243, "grad_norm": 1.5816761255264282, "learning_rate": 1.9509161115566173e-05, "loss": 0.9694, "step": 2178 }, { "epoch": 0.12727803738317758, "grad_norm": 1.6708210706710815, "learning_rate": 1.9508575517229136e-05, "loss": 0.8018, "step": 2179 }, { "epoch": 0.12733644859813084, "grad_norm": 1.9339133501052856, "learning_rate": 1.950798957857393e-05, "loss": 0.9865, "step": 2180 }, { "epoch": 0.1273948598130841, "grad_norm": 1.4421745538711548, "learning_rate": 1.950740329962152e-05, "loss": 0.8881, "step": 2181 }, { "epoch": 0.12745327102803738, "grad_norm": 1.4662296772003174, "learning_rate": 1.95068166803929e-05, "loss": 0.825, "step": 2182 }, { "epoch": 0.12751168224299064, "grad_norm": 2.0239503383636475, "learning_rate": 1.950622972090906e-05, "loss": 0.8449, "step": 2183 }, { "epoch": 0.12757009345794393, "grad_norm": 1.3273043632507324, "learning_rate": 1.9505642421191006e-05, "loss": 0.7681, "step": 2184 }, { "epoch": 0.1276285046728972, "grad_norm": 1.6246980428695679, "learning_rate": 1.950505478125976e-05, "loss": 0.7906, "step": 2185 }, { "epoch": 0.12768691588785047, "grad_norm": 1.435701608657837, "learning_rate": 1.9504466801136355e-05, "loss": 0.923, "step": 2186 }, { "epoch": 0.12774532710280373, "grad_norm": 1.8826570510864258, "learning_rate": 1.9503878480841832e-05, "loss": 0.9697, "step": 2187 }, { "epoch": 0.12780373831775702, "grad_norm": 2.458144187927246, "learning_rate": 1.950328982039725e-05, "loss": 1.0258, "step": 2188 }, { "epoch": 0.12786214953271027, "grad_norm": 3.004791021347046, "learning_rate": 1.950270081982368e-05, "loss": 0.9941, "step": 2189 }, { "epoch": 0.12792056074766356, "grad_norm": 1.3098596334457397, "learning_rate": 1.9502111479142195e-05, "loss": 0.8684, "step": 2190 }, { "epoch": 0.12797897196261682, "grad_norm": 1.5631266832351685, "learning_rate": 1.9501521798373893e-05, "loss": 0.909, "step": 2191 }, { "epoch": 0.1280373831775701, "grad_norm": 1.4615966081619263, "learning_rate": 1.950093177753988e-05, "loss": 0.8292, "step": 2192 }, { "epoch": 0.12809579439252336, "grad_norm": 4.870923042297363, "learning_rate": 1.950034141666127e-05, "loss": 0.965, "step": 2193 }, { "epoch": 0.12815420560747665, "grad_norm": 1.5502175092697144, "learning_rate": 1.9499750715759197e-05, "loss": 0.7886, "step": 2194 }, { "epoch": 0.1282126168224299, "grad_norm": 1.5137029886245728, "learning_rate": 1.9499159674854797e-05, "loss": 0.7854, "step": 2195 }, { "epoch": 0.1282710280373832, "grad_norm": 1.7050840854644775, "learning_rate": 1.9498568293969228e-05, "loss": 1.0099, "step": 2196 }, { "epoch": 0.12832943925233645, "grad_norm": 1.6109166145324707, "learning_rate": 1.9497976573123654e-05, "loss": 0.9562, "step": 2197 }, { "epoch": 0.12838785046728973, "grad_norm": 1.728627324104309, "learning_rate": 1.949738451233925e-05, "loss": 0.8768, "step": 2198 }, { "epoch": 0.128446261682243, "grad_norm": 1.5476157665252686, "learning_rate": 1.9496792111637215e-05, "loss": 0.6871, "step": 2199 }, { "epoch": 0.12850467289719625, "grad_norm": 0.9834863543510437, "learning_rate": 1.9496199371038743e-05, "loss": 0.6213, "step": 2200 }, { "epoch": 0.12856308411214953, "grad_norm": 1.5160695314407349, "learning_rate": 1.9495606290565054e-05, "loss": 0.7681, "step": 2201 }, { "epoch": 0.1286214953271028, "grad_norm": 1.777953863143921, "learning_rate": 1.949501287023737e-05, "loss": 0.9949, "step": 2202 }, { "epoch": 0.12867990654205608, "grad_norm": 1.2786939144134521, "learning_rate": 1.9494419110076932e-05, "loss": 1.041, "step": 2203 }, { "epoch": 0.12873831775700934, "grad_norm": 1.81165611743927, "learning_rate": 1.9493825010104993e-05, "loss": 0.8271, "step": 2204 }, { "epoch": 0.12879672897196262, "grad_norm": 1.5884790420532227, "learning_rate": 1.9493230570342815e-05, "loss": 0.7818, "step": 2205 }, { "epoch": 0.12885514018691588, "grad_norm": 1.9618654251098633, "learning_rate": 1.949263579081167e-05, "loss": 0.8894, "step": 2206 }, { "epoch": 0.12891355140186916, "grad_norm": 1.517261266708374, "learning_rate": 1.949204067153285e-05, "loss": 0.9368, "step": 2207 }, { "epoch": 0.12897196261682242, "grad_norm": 1.478273630142212, "learning_rate": 1.9491445212527655e-05, "loss": 0.8937, "step": 2208 }, { "epoch": 0.1290303738317757, "grad_norm": 1.844743013381958, "learning_rate": 1.9490849413817395e-05, "loss": 0.9756, "step": 2209 }, { "epoch": 0.12908878504672897, "grad_norm": 1.5157722234725952, "learning_rate": 1.9490253275423388e-05, "loss": 0.9619, "step": 2210 }, { "epoch": 0.12914719626168225, "grad_norm": 1.7846473455429077, "learning_rate": 1.9489656797366984e-05, "loss": 0.881, "step": 2211 }, { "epoch": 0.1292056074766355, "grad_norm": 1.2375940084457397, "learning_rate": 1.9489059979669522e-05, "loss": 0.8765, "step": 2212 }, { "epoch": 0.1292640186915888, "grad_norm": 1.6638274192810059, "learning_rate": 1.9488462822352363e-05, "loss": 0.8398, "step": 2213 }, { "epoch": 0.12932242990654205, "grad_norm": 1.46908438205719, "learning_rate": 1.948786532543688e-05, "loss": 0.8283, "step": 2214 }, { "epoch": 0.12938084112149534, "grad_norm": 2.024808645248413, "learning_rate": 1.9487267488944458e-05, "loss": 1.0041, "step": 2215 }, { "epoch": 0.1294392523364486, "grad_norm": 1.6343286037445068, "learning_rate": 1.9486669312896498e-05, "loss": 0.9164, "step": 2216 }, { "epoch": 0.12949766355140188, "grad_norm": 2.6822516918182373, "learning_rate": 1.94860707973144e-05, "loss": 0.8138, "step": 2217 }, { "epoch": 0.12955607476635514, "grad_norm": 2.1497442722320557, "learning_rate": 1.9485471942219595e-05, "loss": 0.8339, "step": 2218 }, { "epoch": 0.12961448598130842, "grad_norm": 3.1305294036865234, "learning_rate": 1.9484872747633513e-05, "loss": 0.9632, "step": 2219 }, { "epoch": 0.12967289719626168, "grad_norm": 2.3216426372528076, "learning_rate": 1.9484273213577598e-05, "loss": 0.8172, "step": 2220 }, { "epoch": 0.12973130841121494, "grad_norm": 3.7004714012145996, "learning_rate": 1.948367334007331e-05, "loss": 1.0098, "step": 2221 }, { "epoch": 0.12978971962616823, "grad_norm": 3.4792892932891846, "learning_rate": 1.9483073127142115e-05, "loss": 0.9599, "step": 2222 }, { "epoch": 0.12984813084112148, "grad_norm": 1.722934365272522, "learning_rate": 1.94824725748055e-05, "loss": 0.9684, "step": 2223 }, { "epoch": 0.12990654205607477, "grad_norm": 1.9190329313278198, "learning_rate": 1.9481871683084958e-05, "loss": 0.7529, "step": 2224 }, { "epoch": 0.12996495327102803, "grad_norm": 1.7163234949111938, "learning_rate": 1.948127045200199e-05, "loss": 0.8452, "step": 2225 }, { "epoch": 0.1300233644859813, "grad_norm": 1.9125689268112183, "learning_rate": 1.9480668881578116e-05, "loss": 0.9679, "step": 2226 }, { "epoch": 0.13008177570093457, "grad_norm": 4.176825046539307, "learning_rate": 1.9480066971834874e-05, "loss": 1.2044, "step": 2227 }, { "epoch": 0.13014018691588786, "grad_norm": 1.8433541059494019, "learning_rate": 1.94794647227938e-05, "loss": 0.7368, "step": 2228 }, { "epoch": 0.13019859813084111, "grad_norm": 1.5703692436218262, "learning_rate": 1.9478862134476452e-05, "loss": 1.0124, "step": 2229 }, { "epoch": 0.1302570093457944, "grad_norm": 1.6575652360916138, "learning_rate": 1.9478259206904397e-05, "loss": 0.6994, "step": 2230 }, { "epoch": 0.13031542056074766, "grad_norm": 1.3334524631500244, "learning_rate": 1.947765594009921e-05, "loss": 0.7927, "step": 2231 }, { "epoch": 0.13037383177570094, "grad_norm": 2.4164583683013916, "learning_rate": 1.9477052334082485e-05, "loss": 0.7878, "step": 2232 }, { "epoch": 0.1304322429906542, "grad_norm": 1.763602375984192, "learning_rate": 1.9476448388875828e-05, "loss": 0.952, "step": 2233 }, { "epoch": 0.1304906542056075, "grad_norm": 1.7953252792358398, "learning_rate": 1.947584410450085e-05, "loss": 1.0087, "step": 2234 }, { "epoch": 0.13054906542056074, "grad_norm": 1.6261332035064697, "learning_rate": 1.9475239480979185e-05, "loss": 0.7688, "step": 2235 }, { "epoch": 0.13060747663551403, "grad_norm": 1.802030324935913, "learning_rate": 1.9474634518332465e-05, "loss": 0.7784, "step": 2236 }, { "epoch": 0.1306658878504673, "grad_norm": 1.7898470163345337, "learning_rate": 1.9474029216582346e-05, "loss": 1.0129, "step": 2237 }, { "epoch": 0.13072429906542057, "grad_norm": 1.7592759132385254, "learning_rate": 1.9473423575750495e-05, "loss": 0.9959, "step": 2238 }, { "epoch": 0.13078271028037383, "grad_norm": 1.9694167375564575, "learning_rate": 1.9472817595858582e-05, "loss": 1.0345, "step": 2239 }, { "epoch": 0.1308411214953271, "grad_norm": 1.703255534172058, "learning_rate": 1.94722112769283e-05, "loss": 0.7664, "step": 2240 }, { "epoch": 0.13089953271028038, "grad_norm": 1.7907214164733887, "learning_rate": 1.9471604618981347e-05, "loss": 0.8166, "step": 2241 }, { "epoch": 0.13095794392523363, "grad_norm": 2.452772855758667, "learning_rate": 1.947099762203944e-05, "loss": 0.9693, "step": 2242 }, { "epoch": 0.13101635514018692, "grad_norm": 1.499796748161316, "learning_rate": 1.9470390286124303e-05, "loss": 0.9193, "step": 2243 }, { "epoch": 0.13107476635514018, "grad_norm": 1.6242505311965942, "learning_rate": 1.9469782611257662e-05, "loss": 0.8172, "step": 2244 }, { "epoch": 0.13113317757009346, "grad_norm": 1.275027871131897, "learning_rate": 1.946917459746128e-05, "loss": 0.7679, "step": 2245 }, { "epoch": 0.13119158878504672, "grad_norm": 1.4301282167434692, "learning_rate": 1.9468566244756915e-05, "loss": 0.6539, "step": 2246 }, { "epoch": 0.13125, "grad_norm": 1.4865171909332275, "learning_rate": 1.9467957553166338e-05, "loss": 0.9703, "step": 2247 }, { "epoch": 0.13130841121495326, "grad_norm": 1.2695425748825073, "learning_rate": 1.946734852271133e-05, "loss": 0.7312, "step": 2248 }, { "epoch": 0.13136682242990655, "grad_norm": 1.7373934984207153, "learning_rate": 1.9466739153413697e-05, "loss": 0.936, "step": 2249 }, { "epoch": 0.1314252336448598, "grad_norm": 1.5159684419631958, "learning_rate": 1.9466129445295245e-05, "loss": 0.7895, "step": 2250 }, { "epoch": 0.1314836448598131, "grad_norm": 1.8581416606903076, "learning_rate": 1.9465519398377797e-05, "loss": 0.6924, "step": 2251 }, { "epoch": 0.13154205607476635, "grad_norm": 1.8769936561584473, "learning_rate": 1.9464909012683182e-05, "loss": 0.7993, "step": 2252 }, { "epoch": 0.13160046728971964, "grad_norm": 1.6141175031661987, "learning_rate": 1.9464298288233254e-05, "loss": 0.9171, "step": 2253 }, { "epoch": 0.1316588785046729, "grad_norm": 2.0771138668060303, "learning_rate": 1.9463687225049867e-05, "loss": 0.7844, "step": 2254 }, { "epoch": 0.13171728971962618, "grad_norm": 1.5627765655517578, "learning_rate": 1.946307582315489e-05, "loss": 0.9188, "step": 2255 }, { "epoch": 0.13177570093457944, "grad_norm": 1.4796342849731445, "learning_rate": 1.946246408257021e-05, "loss": 0.7632, "step": 2256 }, { "epoch": 0.13183411214953272, "grad_norm": 1.191632866859436, "learning_rate": 1.9461852003317716e-05, "loss": 0.876, "step": 2257 }, { "epoch": 0.13189252336448598, "grad_norm": 1.5391275882720947, "learning_rate": 1.946123958541932e-05, "loss": 0.9086, "step": 2258 }, { "epoch": 0.13195093457943924, "grad_norm": 1.288428544998169, "learning_rate": 1.9460626828896934e-05, "loss": 0.7682, "step": 2259 }, { "epoch": 0.13200934579439252, "grad_norm": 1.3993414640426636, "learning_rate": 1.9460013733772498e-05, "loss": 1.2672, "step": 2260 }, { "epoch": 0.13206775700934578, "grad_norm": 1.3760648965835571, "learning_rate": 1.945940030006795e-05, "loss": 0.9234, "step": 2261 }, { "epoch": 0.13212616822429907, "grad_norm": 1.323211908340454, "learning_rate": 1.9458786527805246e-05, "loss": 0.8422, "step": 2262 }, { "epoch": 0.13218457943925233, "grad_norm": 1.7589178085327148, "learning_rate": 1.9458172417006347e-05, "loss": 0.9345, "step": 2263 }, { "epoch": 0.1322429906542056, "grad_norm": 1.8315207958221436, "learning_rate": 1.9457557967693245e-05, "loss": 0.754, "step": 2264 }, { "epoch": 0.13230140186915887, "grad_norm": 1.4759798049926758, "learning_rate": 1.9456943179887922e-05, "loss": 0.8385, "step": 2265 }, { "epoch": 0.13235981308411215, "grad_norm": 1.887169361114502, "learning_rate": 1.9456328053612387e-05, "loss": 0.9681, "step": 2266 }, { "epoch": 0.1324182242990654, "grad_norm": 1.6049891710281372, "learning_rate": 1.945571258888865e-05, "loss": 0.9202, "step": 2267 }, { "epoch": 0.1324766355140187, "grad_norm": 1.1329123973846436, "learning_rate": 1.945509678573874e-05, "loss": 0.6813, "step": 2268 }, { "epoch": 0.13253504672897196, "grad_norm": 2.2226555347442627, "learning_rate": 1.9454480644184704e-05, "loss": 0.9897, "step": 2269 }, { "epoch": 0.13259345794392524, "grad_norm": 1.552229881286621, "learning_rate": 1.9453864164248587e-05, "loss": 0.902, "step": 2270 }, { "epoch": 0.1326518691588785, "grad_norm": 1.2894973754882812, "learning_rate": 1.9453247345952458e-05, "loss": 0.7227, "step": 2271 }, { "epoch": 0.13271028037383178, "grad_norm": 2.0372326374053955, "learning_rate": 1.945263018931839e-05, "loss": 0.8196, "step": 2272 }, { "epoch": 0.13276869158878504, "grad_norm": 2.8557660579681396, "learning_rate": 1.945201269436847e-05, "loss": 0.8692, "step": 2273 }, { "epoch": 0.13282710280373833, "grad_norm": 1.4111113548278809, "learning_rate": 1.9451394861124802e-05, "loss": 0.9729, "step": 2274 }, { "epoch": 0.1328855140186916, "grad_norm": 1.9840983152389526, "learning_rate": 1.94507766896095e-05, "loss": 0.9906, "step": 2275 }, { "epoch": 0.13294392523364487, "grad_norm": 1.7939248085021973, "learning_rate": 1.9450158179844682e-05, "loss": 0.9904, "step": 2276 }, { "epoch": 0.13300233644859813, "grad_norm": 1.2948765754699707, "learning_rate": 1.9449539331852493e-05, "loss": 0.7244, "step": 2277 }, { "epoch": 0.13306074766355142, "grad_norm": 1.9376729726791382, "learning_rate": 1.9448920145655075e-05, "loss": 0.869, "step": 2278 }, { "epoch": 0.13311915887850467, "grad_norm": 2.245316743850708, "learning_rate": 1.9448300621274596e-05, "loss": 0.8106, "step": 2279 }, { "epoch": 0.13317757009345793, "grad_norm": 1.248378038406372, "learning_rate": 1.9447680758733224e-05, "loss": 0.7587, "step": 2280 }, { "epoch": 0.13323598130841122, "grad_norm": 1.4835885763168335, "learning_rate": 1.9447060558053142e-05, "loss": 0.8051, "step": 2281 }, { "epoch": 0.13329439252336447, "grad_norm": 2.413013458251953, "learning_rate": 1.9446440019256556e-05, "loss": 0.8932, "step": 2282 }, { "epoch": 0.13335280373831776, "grad_norm": 1.3811419010162354, "learning_rate": 1.9445819142365664e-05, "loss": 1.0961, "step": 2283 }, { "epoch": 0.13341121495327102, "grad_norm": 2.4434895515441895, "learning_rate": 1.9445197927402703e-05, "loss": 1.0109, "step": 2284 }, { "epoch": 0.1334696261682243, "grad_norm": 1.48432457447052, "learning_rate": 1.9444576374389892e-05, "loss": 0.8352, "step": 2285 }, { "epoch": 0.13352803738317756, "grad_norm": 1.9689807891845703, "learning_rate": 1.9443954483349485e-05, "loss": 1.2055, "step": 2286 }, { "epoch": 0.13358644859813085, "grad_norm": 1.5428528785705566, "learning_rate": 1.9443332254303734e-05, "loss": 0.9526, "step": 2287 }, { "epoch": 0.1336448598130841, "grad_norm": 1.275175929069519, "learning_rate": 1.9442709687274918e-05, "loss": 0.7222, "step": 2288 }, { "epoch": 0.1337032710280374, "grad_norm": 2.326038122177124, "learning_rate": 1.9442086782285308e-05, "loss": 0.9096, "step": 2289 }, { "epoch": 0.13376168224299065, "grad_norm": 1.5119587182998657, "learning_rate": 1.9441463539357207e-05, "loss": 0.822, "step": 2290 }, { "epoch": 0.13382009345794393, "grad_norm": 2.8581666946411133, "learning_rate": 1.9440839958512917e-05, "loss": 0.922, "step": 2291 }, { "epoch": 0.1338785046728972, "grad_norm": 1.851538062095642, "learning_rate": 1.9440216039774757e-05, "loss": 0.8692, "step": 2292 }, { "epoch": 0.13393691588785048, "grad_norm": 1.8176028728485107, "learning_rate": 1.943959178316506e-05, "loss": 0.9257, "step": 2293 }, { "epoch": 0.13399532710280374, "grad_norm": 2.050185441970825, "learning_rate": 1.9438967188706165e-05, "loss": 0.8276, "step": 2294 }, { "epoch": 0.13405373831775702, "grad_norm": 1.5676172971725464, "learning_rate": 1.943834225642043e-05, "loss": 0.8039, "step": 2295 }, { "epoch": 0.13411214953271028, "grad_norm": 2.0138514041900635, "learning_rate": 1.9437716986330215e-05, "loss": 1.0064, "step": 2296 }, { "epoch": 0.13417056074766356, "grad_norm": 1.4365806579589844, "learning_rate": 1.9437091378457905e-05, "loss": 0.9094, "step": 2297 }, { "epoch": 0.13422897196261682, "grad_norm": 2.623494863510132, "learning_rate": 1.943646543282589e-05, "loss": 0.9271, "step": 2298 }, { "epoch": 0.13428738317757008, "grad_norm": 2.4927151203155518, "learning_rate": 1.9435839149456576e-05, "loss": 0.8595, "step": 2299 }, { "epoch": 0.13434579439252337, "grad_norm": 1.9217815399169922, "learning_rate": 1.9435212528372372e-05, "loss": 0.8853, "step": 2300 }, { "epoch": 0.13440420560747662, "grad_norm": 2.172844648361206, "learning_rate": 1.943458556959571e-05, "loss": 0.7516, "step": 2301 }, { "epoch": 0.1344626168224299, "grad_norm": 2.1175129413604736, "learning_rate": 1.9433958273149026e-05, "loss": 0.8181, "step": 2302 }, { "epoch": 0.13452102803738317, "grad_norm": 1.754648208618164, "learning_rate": 1.943333063905477e-05, "loss": 0.8967, "step": 2303 }, { "epoch": 0.13457943925233645, "grad_norm": 1.9358748197555542, "learning_rate": 1.943270266733541e-05, "loss": 0.8744, "step": 2304 }, { "epoch": 0.1346378504672897, "grad_norm": 1.8521978855133057, "learning_rate": 1.943207435801342e-05, "loss": 0.8472, "step": 2305 }, { "epoch": 0.134696261682243, "grad_norm": 2.228025436401367, "learning_rate": 1.9431445711111286e-05, "loss": 1.0151, "step": 2306 }, { "epoch": 0.13475467289719625, "grad_norm": 1.8635164499282837, "learning_rate": 1.9430816726651508e-05, "loss": 0.9211, "step": 2307 }, { "epoch": 0.13481308411214954, "grad_norm": 1.8829259872436523, "learning_rate": 1.94301874046566e-05, "loss": 0.8587, "step": 2308 }, { "epoch": 0.1348714953271028, "grad_norm": 1.5566474199295044, "learning_rate": 1.9429557745149084e-05, "loss": 0.9107, "step": 2309 }, { "epoch": 0.13492990654205608, "grad_norm": 1.8426165580749512, "learning_rate": 1.9428927748151497e-05, "loss": 0.9333, "step": 2310 }, { "epoch": 0.13498831775700934, "grad_norm": 1.608204960823059, "learning_rate": 1.9428297413686382e-05, "loss": 0.9656, "step": 2311 }, { "epoch": 0.13504672897196263, "grad_norm": 1.9628266096115112, "learning_rate": 1.9427666741776307e-05, "loss": 0.9391, "step": 2312 }, { "epoch": 0.13510514018691588, "grad_norm": 1.8840471506118774, "learning_rate": 1.942703573244384e-05, "loss": 1.1284, "step": 2313 }, { "epoch": 0.13516355140186917, "grad_norm": 1.5505691766738892, "learning_rate": 1.9426404385711565e-05, "loss": 0.8938, "step": 2314 }, { "epoch": 0.13522196261682243, "grad_norm": 1.654295563697815, "learning_rate": 1.9425772701602082e-05, "loss": 0.7648, "step": 2315 }, { "epoch": 0.1352803738317757, "grad_norm": 2.5518581867218018, "learning_rate": 1.9425140680137994e-05, "loss": 0.9927, "step": 2316 }, { "epoch": 0.13533878504672897, "grad_norm": 2.3643290996551514, "learning_rate": 1.9424508321341924e-05, "loss": 0.9567, "step": 2317 }, { "epoch": 0.13539719626168226, "grad_norm": 1.3565150499343872, "learning_rate": 1.9423875625236503e-05, "loss": 0.7991, "step": 2318 }, { "epoch": 0.13545560747663551, "grad_norm": 1.7054442167282104, "learning_rate": 1.942324259184438e-05, "loss": 0.8664, "step": 2319 }, { "epoch": 0.13551401869158877, "grad_norm": 1.536068081855774, "learning_rate": 1.9422609221188208e-05, "loss": 0.856, "step": 2320 }, { "epoch": 0.13557242990654206, "grad_norm": 2.79118013381958, "learning_rate": 1.9421975513290653e-05, "loss": 0.923, "step": 2321 }, { "epoch": 0.13563084112149532, "grad_norm": 1.5614006519317627, "learning_rate": 1.9421341468174404e-05, "loss": 0.9482, "step": 2322 }, { "epoch": 0.1356892523364486, "grad_norm": 1.3475255966186523, "learning_rate": 1.942070708586215e-05, "loss": 0.6399, "step": 2323 }, { "epoch": 0.13574766355140186, "grad_norm": 3.797173500061035, "learning_rate": 1.9420072366376587e-05, "loss": 0.9155, "step": 2324 }, { "epoch": 0.13580607476635514, "grad_norm": 2.052088975906372, "learning_rate": 1.9419437309740447e-05, "loss": 1.0576, "step": 2325 }, { "epoch": 0.1358644859813084, "grad_norm": 5.312599182128906, "learning_rate": 1.9418801915976453e-05, "loss": 1.0961, "step": 2326 }, { "epoch": 0.1359228971962617, "grad_norm": 2.0151095390319824, "learning_rate": 1.941816618510734e-05, "loss": 0.9871, "step": 2327 }, { "epoch": 0.13598130841121495, "grad_norm": 2.3049514293670654, "learning_rate": 1.9417530117155872e-05, "loss": 0.8934, "step": 2328 }, { "epoch": 0.13603971962616823, "grad_norm": 4.015321731567383, "learning_rate": 1.941689371214481e-05, "loss": 0.959, "step": 2329 }, { "epoch": 0.1360981308411215, "grad_norm": 1.2557659149169922, "learning_rate": 1.9416256970096926e-05, "loss": 0.9377, "step": 2330 }, { "epoch": 0.13615654205607478, "grad_norm": 4.215086460113525, "learning_rate": 1.9415619891035014e-05, "loss": 0.9154, "step": 2331 }, { "epoch": 0.13621495327102803, "grad_norm": 1.2049167156219482, "learning_rate": 1.9414982474981877e-05, "loss": 0.7067, "step": 2332 }, { "epoch": 0.13627336448598132, "grad_norm": 3.042893648147583, "learning_rate": 1.9414344721960325e-05, "loss": 0.9374, "step": 2333 }, { "epoch": 0.13633177570093458, "grad_norm": 1.7844293117523193, "learning_rate": 1.9413706631993186e-05, "loss": 0.9281, "step": 2334 }, { "epoch": 0.13639018691588786, "grad_norm": 2.8060529232025146, "learning_rate": 1.9413068205103297e-05, "loss": 0.8026, "step": 2335 }, { "epoch": 0.13644859813084112, "grad_norm": 1.92228364944458, "learning_rate": 1.941242944131351e-05, "loss": 0.8199, "step": 2336 }, { "epoch": 0.1365070093457944, "grad_norm": 1.4321320056915283, "learning_rate": 1.9411790340646682e-05, "loss": 0.8176, "step": 2337 }, { "epoch": 0.13656542056074766, "grad_norm": 2.1824135780334473, "learning_rate": 1.941115090312569e-05, "loss": 0.8808, "step": 2338 }, { "epoch": 0.13662383177570092, "grad_norm": 1.4194376468658447, "learning_rate": 1.941051112877342e-05, "loss": 0.803, "step": 2339 }, { "epoch": 0.1366822429906542, "grad_norm": 1.4787163734436035, "learning_rate": 1.9409871017612765e-05, "loss": 0.7937, "step": 2340 }, { "epoch": 0.13674065420560746, "grad_norm": 1.850481629371643, "learning_rate": 1.9409230569666644e-05, "loss": 0.9486, "step": 2341 }, { "epoch": 0.13679906542056075, "grad_norm": 1.8147302865982056, "learning_rate": 1.9408589784957974e-05, "loss": 0.8565, "step": 2342 }, { "epoch": 0.136857476635514, "grad_norm": 1.6502013206481934, "learning_rate": 1.940794866350969e-05, "loss": 0.7261, "step": 2343 }, { "epoch": 0.1369158878504673, "grad_norm": 1.6533631086349487, "learning_rate": 1.9407307205344733e-05, "loss": 0.743, "step": 2344 }, { "epoch": 0.13697429906542055, "grad_norm": 1.2586803436279297, "learning_rate": 1.9406665410486067e-05, "loss": 0.8896, "step": 2345 }, { "epoch": 0.13703271028037384, "grad_norm": 2.704763174057007, "learning_rate": 1.9406023278956664e-05, "loss": 1.0143, "step": 2346 }, { "epoch": 0.1370911214953271, "grad_norm": 1.7220420837402344, "learning_rate": 1.94053808107795e-05, "loss": 0.8597, "step": 2347 }, { "epoch": 0.13714953271028038, "grad_norm": 1.9259142875671387, "learning_rate": 1.9404738005977574e-05, "loss": 0.8928, "step": 2348 }, { "epoch": 0.13720794392523364, "grad_norm": 1.6432901620864868, "learning_rate": 1.940409486457389e-05, "loss": 0.6449, "step": 2349 }, { "epoch": 0.13726635514018692, "grad_norm": 1.4009108543395996, "learning_rate": 1.9403451386591472e-05, "loss": 0.717, "step": 2350 }, { "epoch": 0.13732476635514018, "grad_norm": 2.222891092300415, "learning_rate": 1.9402807572053343e-05, "loss": 0.9903, "step": 2351 }, { "epoch": 0.13738317757009347, "grad_norm": 1.617327094078064, "learning_rate": 1.9402163420982548e-05, "loss": 0.7982, "step": 2352 }, { "epoch": 0.13744158878504673, "grad_norm": 1.6567468643188477, "learning_rate": 1.9401518933402142e-05, "loss": 0.8028, "step": 2353 }, { "epoch": 0.1375, "grad_norm": 1.6852692365646362, "learning_rate": 1.940087410933519e-05, "loss": 0.8485, "step": 2354 }, { "epoch": 0.13755841121495327, "grad_norm": 2.1554250717163086, "learning_rate": 1.9400228948804777e-05, "loss": 0.8753, "step": 2355 }, { "epoch": 0.13761682242990655, "grad_norm": 1.8515442609786987, "learning_rate": 1.9399583451833984e-05, "loss": 0.8365, "step": 2356 }, { "epoch": 0.1376752336448598, "grad_norm": 1.2523120641708374, "learning_rate": 1.9398937618445924e-05, "loss": 0.7912, "step": 2357 }, { "epoch": 0.13773364485981307, "grad_norm": 1.7641984224319458, "learning_rate": 1.9398291448663702e-05, "loss": 0.8817, "step": 2358 }, { "epoch": 0.13779205607476636, "grad_norm": 1.950477957725525, "learning_rate": 1.9397644942510453e-05, "loss": 1.0055, "step": 2359 }, { "epoch": 0.1378504672897196, "grad_norm": 1.4876614809036255, "learning_rate": 1.939699810000931e-05, "loss": 0.9415, "step": 2360 }, { "epoch": 0.1379088785046729, "grad_norm": 1.6346880197525024, "learning_rate": 1.939635092118343e-05, "loss": 0.9296, "step": 2361 }, { "epoch": 0.13796728971962616, "grad_norm": 1.5685089826583862, "learning_rate": 1.939570340605597e-05, "loss": 1.104, "step": 2362 }, { "epoch": 0.13802570093457944, "grad_norm": 1.2396317720413208, "learning_rate": 1.9395055554650107e-05, "loss": 0.7113, "step": 2363 }, { "epoch": 0.1380841121495327, "grad_norm": 1.6062967777252197, "learning_rate": 1.9394407366989026e-05, "loss": 0.9681, "step": 2364 }, { "epoch": 0.138142523364486, "grad_norm": 1.2211042642593384, "learning_rate": 1.9393758843095934e-05, "loss": 0.8261, "step": 2365 }, { "epoch": 0.13820093457943924, "grad_norm": 1.7589629888534546, "learning_rate": 1.939310998299403e-05, "loss": 0.9564, "step": 2366 }, { "epoch": 0.13825934579439253, "grad_norm": 1.6773548126220703, "learning_rate": 1.9392460786706548e-05, "loss": 0.9606, "step": 2367 }, { "epoch": 0.1383177570093458, "grad_norm": 1.4654006958007812, "learning_rate": 1.939181125425672e-05, "loss": 0.8079, "step": 2368 }, { "epoch": 0.13837616822429907, "grad_norm": 1.9239633083343506, "learning_rate": 1.939116138566779e-05, "loss": 0.9934, "step": 2369 }, { "epoch": 0.13843457943925233, "grad_norm": 1.27010977268219, "learning_rate": 1.939051118096302e-05, "loss": 0.7951, "step": 2370 }, { "epoch": 0.13849299065420562, "grad_norm": 1.3651009798049927, "learning_rate": 1.9389860640165678e-05, "loss": 0.8361, "step": 2371 }, { "epoch": 0.13855140186915887, "grad_norm": 1.8626887798309326, "learning_rate": 1.938920976329905e-05, "loss": 0.9186, "step": 2372 }, { "epoch": 0.13860981308411216, "grad_norm": 1.8514593839645386, "learning_rate": 1.9388558550386435e-05, "loss": 0.8782, "step": 2373 }, { "epoch": 0.13866822429906542, "grad_norm": 1.4590036869049072, "learning_rate": 1.938790700145113e-05, "loss": 0.7635, "step": 2374 }, { "epoch": 0.1387266355140187, "grad_norm": 1.2918946743011475, "learning_rate": 1.9387255116516463e-05, "loss": 0.7984, "step": 2375 }, { "epoch": 0.13878504672897196, "grad_norm": 1.5410200357437134, "learning_rate": 1.9386602895605768e-05, "loss": 0.7665, "step": 2376 }, { "epoch": 0.13884345794392525, "grad_norm": 1.4204939603805542, "learning_rate": 1.9385950338742377e-05, "loss": 0.6862, "step": 2377 }, { "epoch": 0.1389018691588785, "grad_norm": 1.4474955797195435, "learning_rate": 1.9385297445949657e-05, "loss": 0.9379, "step": 2378 }, { "epoch": 0.13896028037383176, "grad_norm": 3.1371147632598877, "learning_rate": 1.938464421725097e-05, "loss": 0.7498, "step": 2379 }, { "epoch": 0.13901869158878505, "grad_norm": 1.1336822509765625, "learning_rate": 1.9383990652669693e-05, "loss": 0.6137, "step": 2380 }, { "epoch": 0.1390771028037383, "grad_norm": 2.426262617111206, "learning_rate": 1.938333675222922e-05, "loss": 0.8591, "step": 2381 }, { "epoch": 0.1391355140186916, "grad_norm": 1.5721296072006226, "learning_rate": 1.9382682515952956e-05, "loss": 0.898, "step": 2382 }, { "epoch": 0.13919392523364485, "grad_norm": 1.8316030502319336, "learning_rate": 1.938202794386432e-05, "loss": 0.8793, "step": 2383 }, { "epoch": 0.13925233644859814, "grad_norm": 2.4851207733154297, "learning_rate": 1.938137303598673e-05, "loss": 0.919, "step": 2384 }, { "epoch": 0.1393107476635514, "grad_norm": 1.6195621490478516, "learning_rate": 1.9380717792343634e-05, "loss": 0.6659, "step": 2385 }, { "epoch": 0.13936915887850468, "grad_norm": 2.3066041469573975, "learning_rate": 1.9380062212958476e-05, "loss": 0.9141, "step": 2386 }, { "epoch": 0.13942757009345794, "grad_norm": 1.3198962211608887, "learning_rate": 1.9379406297854727e-05, "loss": 0.7081, "step": 2387 }, { "epoch": 0.13948598130841122, "grad_norm": 1.6661899089813232, "learning_rate": 1.937875004705586e-05, "loss": 0.7501, "step": 2388 }, { "epoch": 0.13954439252336448, "grad_norm": 1.367157220840454, "learning_rate": 1.937809346058536e-05, "loss": 0.6733, "step": 2389 }, { "epoch": 0.13960280373831777, "grad_norm": 1.441599726676941, "learning_rate": 1.937743653846673e-05, "loss": 0.8896, "step": 2390 }, { "epoch": 0.13966121495327102, "grad_norm": 1.627363681793213, "learning_rate": 1.937677928072348e-05, "loss": 0.7416, "step": 2391 }, { "epoch": 0.1397196261682243, "grad_norm": 1.493416666984558, "learning_rate": 1.9376121687379136e-05, "loss": 0.97, "step": 2392 }, { "epoch": 0.13977803738317757, "grad_norm": 1.6800273656845093, "learning_rate": 1.9375463758457228e-05, "loss": 0.9088, "step": 2393 }, { "epoch": 0.13983644859813085, "grad_norm": 1.7421941757202148, "learning_rate": 1.937480549398131e-05, "loss": 1.0408, "step": 2394 }, { "epoch": 0.1398948598130841, "grad_norm": 1.4421091079711914, "learning_rate": 1.9374146893974938e-05, "loss": 0.7953, "step": 2395 }, { "epoch": 0.1399532710280374, "grad_norm": 2.168898582458496, "learning_rate": 1.9373487958461688e-05, "loss": 0.8505, "step": 2396 }, { "epoch": 0.14001168224299065, "grad_norm": 1.5074037313461304, "learning_rate": 1.937282868746514e-05, "loss": 0.8643, "step": 2397 }, { "epoch": 0.1400700934579439, "grad_norm": 2.87268328666687, "learning_rate": 1.937216908100889e-05, "loss": 0.9351, "step": 2398 }, { "epoch": 0.1401285046728972, "grad_norm": 1.8017505407333374, "learning_rate": 1.9371509139116546e-05, "loss": 0.8548, "step": 2399 }, { "epoch": 0.14018691588785046, "grad_norm": 2.764395236968994, "learning_rate": 1.9370848861811726e-05, "loss": 0.8582, "step": 2400 }, { "epoch": 0.14024532710280374, "grad_norm": 1.5429911613464355, "learning_rate": 1.937018824911807e-05, "loss": 0.8786, "step": 2401 }, { "epoch": 0.140303738317757, "grad_norm": 1.839991569519043, "learning_rate": 1.936952730105921e-05, "loss": 0.7658, "step": 2402 }, { "epoch": 0.14036214953271028, "grad_norm": 2.2244787216186523, "learning_rate": 1.9368866017658808e-05, "loss": 0.9952, "step": 2403 }, { "epoch": 0.14042056074766354, "grad_norm": 1.4839046001434326, "learning_rate": 1.936820439894053e-05, "loss": 0.8571, "step": 2404 }, { "epoch": 0.14047897196261683, "grad_norm": 1.9050794839859009, "learning_rate": 1.936754244492806e-05, "loss": 1.0207, "step": 2405 }, { "epoch": 0.14053738317757009, "grad_norm": 1.6558921337127686, "learning_rate": 1.9366880155645083e-05, "loss": 0.8992, "step": 2406 }, { "epoch": 0.14059579439252337, "grad_norm": 1.6888128519058228, "learning_rate": 1.936621753111531e-05, "loss": 0.7069, "step": 2407 }, { "epoch": 0.14065420560747663, "grad_norm": 1.8984200954437256, "learning_rate": 1.9365554571362453e-05, "loss": 0.9086, "step": 2408 }, { "epoch": 0.14071261682242991, "grad_norm": 1.8680590391159058, "learning_rate": 1.9364891276410236e-05, "loss": 0.846, "step": 2409 }, { "epoch": 0.14077102803738317, "grad_norm": 2.331963539123535, "learning_rate": 1.936422764628241e-05, "loss": 0.994, "step": 2410 }, { "epoch": 0.14082943925233646, "grad_norm": 1.801468014717102, "learning_rate": 1.936356368100271e-05, "loss": 1.1409, "step": 2411 }, { "epoch": 0.14088785046728972, "grad_norm": 1.5943803787231445, "learning_rate": 1.9362899380594917e-05, "loss": 0.8961, "step": 2412 }, { "epoch": 0.140946261682243, "grad_norm": 1.602602481842041, "learning_rate": 1.9362234745082797e-05, "loss": 0.8971, "step": 2413 }, { "epoch": 0.14100467289719626, "grad_norm": 1.7152937650680542, "learning_rate": 1.9361569774490135e-05, "loss": 0.9331, "step": 2414 }, { "epoch": 0.14106308411214954, "grad_norm": 1.5587427616119385, "learning_rate": 1.936090446884074e-05, "loss": 0.8634, "step": 2415 }, { "epoch": 0.1411214953271028, "grad_norm": 1.5969469547271729, "learning_rate": 1.9360238828158416e-05, "loss": 0.888, "step": 2416 }, { "epoch": 0.1411799065420561, "grad_norm": 1.3935011625289917, "learning_rate": 1.9359572852466996e-05, "loss": 0.9446, "step": 2417 }, { "epoch": 0.14123831775700935, "grad_norm": 1.62607741355896, "learning_rate": 1.9358906541790305e-05, "loss": 0.9386, "step": 2418 }, { "epoch": 0.1412967289719626, "grad_norm": 1.9988807439804077, "learning_rate": 1.9358239896152192e-05, "loss": 0.9327, "step": 2419 }, { "epoch": 0.1413551401869159, "grad_norm": 1.607757568359375, "learning_rate": 1.9357572915576526e-05, "loss": 0.9526, "step": 2420 }, { "epoch": 0.14141355140186915, "grad_norm": 1.8315001726150513, "learning_rate": 1.935690560008717e-05, "loss": 0.9496, "step": 2421 }, { "epoch": 0.14147196261682243, "grad_norm": 1.117335319519043, "learning_rate": 1.935623794970801e-05, "loss": 0.8616, "step": 2422 }, { "epoch": 0.1415303738317757, "grad_norm": 1.3290382623672485, "learning_rate": 1.9355569964462942e-05, "loss": 0.8334, "step": 2423 }, { "epoch": 0.14158878504672898, "grad_norm": 1.5848960876464844, "learning_rate": 1.9354901644375876e-05, "loss": 0.9844, "step": 2424 }, { "epoch": 0.14164719626168223, "grad_norm": 1.2104663848876953, "learning_rate": 1.935423298947073e-05, "loss": 0.7992, "step": 2425 }, { "epoch": 0.14170560747663552, "grad_norm": 2.2223587036132812, "learning_rate": 1.935356399977143e-05, "loss": 0.8177, "step": 2426 }, { "epoch": 0.14176401869158878, "grad_norm": 1.3846111297607422, "learning_rate": 1.9352894675301926e-05, "loss": 0.9108, "step": 2427 }, { "epoch": 0.14182242990654206, "grad_norm": 2.288545608520508, "learning_rate": 1.935222501608617e-05, "loss": 0.8103, "step": 2428 }, { "epoch": 0.14188084112149532, "grad_norm": 1.46077561378479, "learning_rate": 1.9351555022148133e-05, "loss": 0.9387, "step": 2429 }, { "epoch": 0.1419392523364486, "grad_norm": 1.3164653778076172, "learning_rate": 1.9350884693511798e-05, "loss": 0.7217, "step": 2430 }, { "epoch": 0.14199766355140186, "grad_norm": 2.409350872039795, "learning_rate": 1.9350214030201148e-05, "loss": 0.9289, "step": 2431 }, { "epoch": 0.14205607476635515, "grad_norm": 1.092810034751892, "learning_rate": 1.9349543032240187e-05, "loss": 0.8346, "step": 2432 }, { "epoch": 0.1421144859813084, "grad_norm": 2.510282278060913, "learning_rate": 1.9348871699652936e-05, "loss": 0.9391, "step": 2433 }, { "epoch": 0.1421728971962617, "grad_norm": 1.4203954935073853, "learning_rate": 1.934820003246342e-05, "loss": 1.0179, "step": 2434 }, { "epoch": 0.14223130841121495, "grad_norm": 2.1504507064819336, "learning_rate": 1.934752803069568e-05, "loss": 0.787, "step": 2435 }, { "epoch": 0.14228971962616824, "grad_norm": 1.957305669784546, "learning_rate": 1.934685569437376e-05, "loss": 0.8688, "step": 2436 }, { "epoch": 0.1423481308411215, "grad_norm": 1.9144713878631592, "learning_rate": 1.9346183023521734e-05, "loss": 0.9898, "step": 2437 }, { "epoch": 0.14240654205607475, "grad_norm": 1.2160764932632446, "learning_rate": 1.934551001816367e-05, "loss": 0.7147, "step": 2438 }, { "epoch": 0.14246495327102804, "grad_norm": 2.109513759613037, "learning_rate": 1.934483667832366e-05, "loss": 0.8952, "step": 2439 }, { "epoch": 0.1425233644859813, "grad_norm": 1.0999155044555664, "learning_rate": 1.93441630040258e-05, "loss": 0.7688, "step": 2440 }, { "epoch": 0.14258177570093458, "grad_norm": 2.1048130989074707, "learning_rate": 1.93434889952942e-05, "loss": 0.7882, "step": 2441 }, { "epoch": 0.14264018691588784, "grad_norm": 1.2211964130401611, "learning_rate": 1.934281465215299e-05, "loss": 0.8238, "step": 2442 }, { "epoch": 0.14269859813084113, "grad_norm": 2.473916530609131, "learning_rate": 1.9342139974626296e-05, "loss": 0.7677, "step": 2443 }, { "epoch": 0.14275700934579438, "grad_norm": 1.5128381252288818, "learning_rate": 1.9341464962738274e-05, "loss": 0.7878, "step": 2444 }, { "epoch": 0.14281542056074767, "grad_norm": 1.7435745000839233, "learning_rate": 1.9340789616513072e-05, "loss": 0.8227, "step": 2445 }, { "epoch": 0.14287383177570093, "grad_norm": 1.3546979427337646, "learning_rate": 1.9340113935974873e-05, "loss": 0.9944, "step": 2446 }, { "epoch": 0.1429322429906542, "grad_norm": 1.6958158016204834, "learning_rate": 1.9339437921147854e-05, "loss": 0.9028, "step": 2447 }, { "epoch": 0.14299065420560747, "grad_norm": 1.375264286994934, "learning_rate": 1.9338761572056212e-05, "loss": 0.8947, "step": 2448 }, { "epoch": 0.14304906542056076, "grad_norm": 1.2289048433303833, "learning_rate": 1.9338084888724153e-05, "loss": 0.8447, "step": 2449 }, { "epoch": 0.143107476635514, "grad_norm": 1.7083097696304321, "learning_rate": 1.933740787117589e-05, "loss": 0.7668, "step": 2450 }, { "epoch": 0.1431658878504673, "grad_norm": 1.5752246379852295, "learning_rate": 1.933673051943567e-05, "loss": 0.8136, "step": 2451 }, { "epoch": 0.14322429906542056, "grad_norm": 1.3344329595565796, "learning_rate": 1.933605283352772e-05, "loss": 1.017, "step": 2452 }, { "epoch": 0.14328271028037384, "grad_norm": 1.5536279678344727, "learning_rate": 1.93353748134763e-05, "loss": 0.8274, "step": 2453 }, { "epoch": 0.1433411214953271, "grad_norm": 1.5317959785461426, "learning_rate": 1.933469645930568e-05, "loss": 0.8715, "step": 2454 }, { "epoch": 0.1433995327102804, "grad_norm": 1.2919836044311523, "learning_rate": 1.9334017771040134e-05, "loss": 0.7544, "step": 2455 }, { "epoch": 0.14345794392523364, "grad_norm": 1.2828302383422852, "learning_rate": 1.9333338748703956e-05, "loss": 0.7409, "step": 2456 }, { "epoch": 0.14351635514018693, "grad_norm": 1.2751909494400024, "learning_rate": 1.9332659392321446e-05, "loss": 0.8906, "step": 2457 }, { "epoch": 0.1435747663551402, "grad_norm": 1.4440983533859253, "learning_rate": 1.933197970191692e-05, "loss": 0.7434, "step": 2458 }, { "epoch": 0.14363317757009345, "grad_norm": 1.1647303104400635, "learning_rate": 1.9331299677514705e-05, "loss": 0.9465, "step": 2459 }, { "epoch": 0.14369158878504673, "grad_norm": 1.1881566047668457, "learning_rate": 1.933061931913914e-05, "loss": 0.7149, "step": 2460 }, { "epoch": 0.14375, "grad_norm": 1.3325450420379639, "learning_rate": 1.9329938626814572e-05, "loss": 0.6568, "step": 2461 }, { "epoch": 0.14380841121495327, "grad_norm": 1.7823476791381836, "learning_rate": 1.932925760056537e-05, "loss": 0.8712, "step": 2462 }, { "epoch": 0.14386682242990653, "grad_norm": 1.142785668373108, "learning_rate": 1.93285762404159e-05, "loss": 0.7683, "step": 2463 }, { "epoch": 0.14392523364485982, "grad_norm": 2.2573935985565186, "learning_rate": 1.9327894546390555e-05, "loss": 0.8664, "step": 2464 }, { "epoch": 0.14398364485981308, "grad_norm": 1.8790448904037476, "learning_rate": 1.9327212518513732e-05, "loss": 0.9079, "step": 2465 }, { "epoch": 0.14404205607476636, "grad_norm": 1.477314829826355, "learning_rate": 1.9326530156809838e-05, "loss": 0.6608, "step": 2466 }, { "epoch": 0.14410046728971962, "grad_norm": 1.8159410953521729, "learning_rate": 1.93258474613033e-05, "loss": 0.7064, "step": 2467 }, { "epoch": 0.1441588785046729, "grad_norm": 4.134999752044678, "learning_rate": 1.9325164432018547e-05, "loss": 0.927, "step": 2468 }, { "epoch": 0.14421728971962616, "grad_norm": 3.6329123973846436, "learning_rate": 1.932448106898003e-05, "loss": 0.8498, "step": 2469 }, { "epoch": 0.14427570093457945, "grad_norm": 2.4465746879577637, "learning_rate": 1.9323797372212204e-05, "loss": 0.8626, "step": 2470 }, { "epoch": 0.1443341121495327, "grad_norm": 1.778939127922058, "learning_rate": 1.932311334173954e-05, "loss": 1.0258, "step": 2471 }, { "epoch": 0.144392523364486, "grad_norm": 2.118380069732666, "learning_rate": 1.9322428977586515e-05, "loss": 0.8513, "step": 2472 }, { "epoch": 0.14445093457943925, "grad_norm": 1.7409653663635254, "learning_rate": 1.932174427977763e-05, "loss": 0.9751, "step": 2473 }, { "epoch": 0.14450934579439254, "grad_norm": 1.5064537525177002, "learning_rate": 1.932105924833739e-05, "loss": 0.759, "step": 2474 }, { "epoch": 0.1445677570093458, "grad_norm": 2.0055019855499268, "learning_rate": 1.932037388329031e-05, "loss": 0.9674, "step": 2475 }, { "epoch": 0.14462616822429908, "grad_norm": 1.4810315370559692, "learning_rate": 1.931968818466092e-05, "loss": 0.7067, "step": 2476 }, { "epoch": 0.14468457943925234, "grad_norm": 1.8493682146072388, "learning_rate": 1.9319002152473762e-05, "loss": 0.7773, "step": 2477 }, { "epoch": 0.1447429906542056, "grad_norm": 2.0311317443847656, "learning_rate": 1.931831578675339e-05, "loss": 1.0469, "step": 2478 }, { "epoch": 0.14480140186915888, "grad_norm": 1.6246262788772583, "learning_rate": 1.9317629087524364e-05, "loss": 0.7409, "step": 2479 }, { "epoch": 0.14485981308411214, "grad_norm": 1.979862928390503, "learning_rate": 1.931694205481127e-05, "loss": 0.8315, "step": 2480 }, { "epoch": 0.14491822429906542, "grad_norm": 1.746609091758728, "learning_rate": 1.9316254688638695e-05, "loss": 0.954, "step": 2481 }, { "epoch": 0.14497663551401868, "grad_norm": 1.4064527750015259, "learning_rate": 1.931556698903124e-05, "loss": 0.8909, "step": 2482 }, { "epoch": 0.14503504672897197, "grad_norm": 1.952569603919983, "learning_rate": 1.9314878956013518e-05, "loss": 0.9316, "step": 2483 }, { "epoch": 0.14509345794392522, "grad_norm": 1.5677032470703125, "learning_rate": 1.9314190589610153e-05, "loss": 0.8007, "step": 2484 }, { "epoch": 0.1451518691588785, "grad_norm": 2.1047370433807373, "learning_rate": 1.931350188984578e-05, "loss": 0.7738, "step": 2485 }, { "epoch": 0.14521028037383177, "grad_norm": 1.182144284248352, "learning_rate": 1.9312812856745053e-05, "loss": 0.6382, "step": 2486 }, { "epoch": 0.14526869158878505, "grad_norm": 2.382689952850342, "learning_rate": 1.931212349033263e-05, "loss": 0.9514, "step": 2487 }, { "epoch": 0.1453271028037383, "grad_norm": 1.4956223964691162, "learning_rate": 1.9311433790633184e-05, "loss": 0.7224, "step": 2488 }, { "epoch": 0.1453855140186916, "grad_norm": 1.7891886234283447, "learning_rate": 1.93107437576714e-05, "loss": 0.9462, "step": 2489 }, { "epoch": 0.14544392523364486, "grad_norm": 1.63215970993042, "learning_rate": 1.9310053391471975e-05, "loss": 0.8636, "step": 2490 }, { "epoch": 0.14550233644859814, "grad_norm": 1.2968521118164062, "learning_rate": 1.9309362692059617e-05, "loss": 0.8872, "step": 2491 }, { "epoch": 0.1455607476635514, "grad_norm": 2.037461280822754, "learning_rate": 1.9308671659459047e-05, "loss": 0.8879, "step": 2492 }, { "epoch": 0.14561915887850468, "grad_norm": 1.5917956829071045, "learning_rate": 1.9307980293694997e-05, "loss": 0.9699, "step": 2493 }, { "epoch": 0.14567757009345794, "grad_norm": 1.6218680143356323, "learning_rate": 1.9307288594792215e-05, "loss": 0.8337, "step": 2494 }, { "epoch": 0.14573598130841123, "grad_norm": 1.7922375202178955, "learning_rate": 1.9306596562775454e-05, "loss": 0.7279, "step": 2495 }, { "epoch": 0.14579439252336449, "grad_norm": 1.2972933053970337, "learning_rate": 1.9305904197669482e-05, "loss": 0.7651, "step": 2496 }, { "epoch": 0.14585280373831774, "grad_norm": 2.0071773529052734, "learning_rate": 1.9305211499499083e-05, "loss": 0.937, "step": 2497 }, { "epoch": 0.14591121495327103, "grad_norm": 1.596625566482544, "learning_rate": 1.9304518468289043e-05, "loss": 0.9043, "step": 2498 }, { "epoch": 0.1459696261682243, "grad_norm": 1.9312803745269775, "learning_rate": 1.930382510406417e-05, "loss": 0.9975, "step": 2499 }, { "epoch": 0.14602803738317757, "grad_norm": 1.6698417663574219, "learning_rate": 1.9303131406849277e-05, "loss": 0.8752, "step": 2500 }, { "epoch": 0.14608644859813083, "grad_norm": 1.9956361055374146, "learning_rate": 1.9302437376669197e-05, "loss": 0.7653, "step": 2501 }, { "epoch": 0.14614485981308412, "grad_norm": 1.40245521068573, "learning_rate": 1.9301743013548762e-05, "loss": 1.0903, "step": 2502 }, { "epoch": 0.14620327102803737, "grad_norm": 2.053107976913452, "learning_rate": 1.9301048317512836e-05, "loss": 0.7747, "step": 2503 }, { "epoch": 0.14626168224299066, "grad_norm": 1.7514287233352661, "learning_rate": 1.930035328858627e-05, "loss": 0.7806, "step": 2504 }, { "epoch": 0.14632009345794392, "grad_norm": 2.8587124347686768, "learning_rate": 1.9299657926793947e-05, "loss": 0.8598, "step": 2505 }, { "epoch": 0.1463785046728972, "grad_norm": 4.650218963623047, "learning_rate": 1.929896223216075e-05, "loss": 0.8012, "step": 2506 }, { "epoch": 0.14643691588785046, "grad_norm": 2.2730822563171387, "learning_rate": 1.929826620471158e-05, "loss": 1.0339, "step": 2507 }, { "epoch": 0.14649532710280375, "grad_norm": 2.581244707107544, "learning_rate": 1.9297569844471352e-05, "loss": 0.938, "step": 2508 }, { "epoch": 0.146553738317757, "grad_norm": 1.4548743963241577, "learning_rate": 1.9296873151464986e-05, "loss": 0.8186, "step": 2509 }, { "epoch": 0.1466121495327103, "grad_norm": 3.0063624382019043, "learning_rate": 1.9296176125717414e-05, "loss": 0.8383, "step": 2510 }, { "epoch": 0.14667056074766355, "grad_norm": 1.288910984992981, "learning_rate": 1.929547876725359e-05, "loss": 0.9396, "step": 2511 }, { "epoch": 0.14672897196261683, "grad_norm": 2.8149828910827637, "learning_rate": 1.9294781076098465e-05, "loss": 1.0699, "step": 2512 }, { "epoch": 0.1467873831775701, "grad_norm": 1.898949384689331, "learning_rate": 1.9294083052277016e-05, "loss": 0.8677, "step": 2513 }, { "epoch": 0.14684579439252338, "grad_norm": 1.8092880249023438, "learning_rate": 1.9293384695814222e-05, "loss": 0.715, "step": 2514 }, { "epoch": 0.14690420560747663, "grad_norm": 1.5576019287109375, "learning_rate": 1.9292686006735078e-05, "loss": 0.8865, "step": 2515 }, { "epoch": 0.14696261682242992, "grad_norm": 2.694023609161377, "learning_rate": 1.9291986985064595e-05, "loss": 0.8675, "step": 2516 }, { "epoch": 0.14702102803738318, "grad_norm": 1.676425576210022, "learning_rate": 1.9291287630827788e-05, "loss": 0.8239, "step": 2517 }, { "epoch": 0.14707943925233644, "grad_norm": 2.378574848175049, "learning_rate": 1.929058794404969e-05, "loss": 0.9339, "step": 2518 }, { "epoch": 0.14713785046728972, "grad_norm": 2.3173880577087402, "learning_rate": 1.9289887924755336e-05, "loss": 1.0407, "step": 2519 }, { "epoch": 0.14719626168224298, "grad_norm": 1.7060585021972656, "learning_rate": 1.928918757296979e-05, "loss": 0.8532, "step": 2520 }, { "epoch": 0.14725467289719626, "grad_norm": 2.6771297454833984, "learning_rate": 1.9288486888718107e-05, "loss": 0.8532, "step": 2521 }, { "epoch": 0.14731308411214952, "grad_norm": 1.601370930671692, "learning_rate": 1.9287785872025374e-05, "loss": 0.9353, "step": 2522 }, { "epoch": 0.1473714953271028, "grad_norm": 1.8302559852600098, "learning_rate": 1.9287084522916678e-05, "loss": 0.8922, "step": 2523 }, { "epoch": 0.14742990654205607, "grad_norm": 2.5574233531951904, "learning_rate": 1.928638284141712e-05, "loss": 0.9423, "step": 2524 }, { "epoch": 0.14748831775700935, "grad_norm": 1.9327470064163208, "learning_rate": 1.9285680827551812e-05, "loss": 0.684, "step": 2525 }, { "epoch": 0.1475467289719626, "grad_norm": 1.491551160812378, "learning_rate": 1.9284978481345885e-05, "loss": 0.9542, "step": 2526 }, { "epoch": 0.1476051401869159, "grad_norm": 2.024998188018799, "learning_rate": 1.9284275802824474e-05, "loss": 0.9439, "step": 2527 }, { "epoch": 0.14766355140186915, "grad_norm": 1.5136393308639526, "learning_rate": 1.9283572792012722e-05, "loss": 0.8431, "step": 2528 }, { "epoch": 0.14772196261682244, "grad_norm": 2.048527479171753, "learning_rate": 1.92828694489358e-05, "loss": 1.0583, "step": 2529 }, { "epoch": 0.1477803738317757, "grad_norm": 2.0382027626037598, "learning_rate": 1.9282165773618878e-05, "loss": 1.0316, "step": 2530 }, { "epoch": 0.14783878504672898, "grad_norm": 1.7164690494537354, "learning_rate": 1.9281461766087136e-05, "loss": 0.9649, "step": 2531 }, { "epoch": 0.14789719626168224, "grad_norm": 1.5205732583999634, "learning_rate": 1.9280757426365776e-05, "loss": 0.7626, "step": 2532 }, { "epoch": 0.14795560747663553, "grad_norm": 1.9244264364242554, "learning_rate": 1.928005275448001e-05, "loss": 1.1378, "step": 2533 }, { "epoch": 0.14801401869158878, "grad_norm": 1.8622820377349854, "learning_rate": 1.927934775045505e-05, "loss": 1.0372, "step": 2534 }, { "epoch": 0.14807242990654207, "grad_norm": 1.862683892250061, "learning_rate": 1.927864241431613e-05, "loss": 0.8722, "step": 2535 }, { "epoch": 0.14813084112149533, "grad_norm": 1.2214714288711548, "learning_rate": 1.9277936746088503e-05, "loss": 0.9387, "step": 2536 }, { "epoch": 0.14818925233644858, "grad_norm": 1.6913896799087524, "learning_rate": 1.9277230745797414e-05, "loss": 0.8539, "step": 2537 }, { "epoch": 0.14824766355140187, "grad_norm": 1.839219570159912, "learning_rate": 1.9276524413468142e-05, "loss": 0.8327, "step": 2538 }, { "epoch": 0.14830607476635513, "grad_norm": 1.342347264289856, "learning_rate": 1.9275817749125956e-05, "loss": 0.9783, "step": 2539 }, { "epoch": 0.1483644859813084, "grad_norm": 2.5641674995422363, "learning_rate": 1.9275110752796156e-05, "loss": 1.0056, "step": 2540 }, { "epoch": 0.14842289719626167, "grad_norm": 1.267248511314392, "learning_rate": 1.9274403424504044e-05, "loss": 0.8594, "step": 2541 }, { "epoch": 0.14848130841121496, "grad_norm": 2.0001091957092285, "learning_rate": 1.927369576427494e-05, "loss": 0.6774, "step": 2542 }, { "epoch": 0.14853971962616822, "grad_norm": 1.0881083011627197, "learning_rate": 1.9272987772134158e-05, "loss": 0.6597, "step": 2543 }, { "epoch": 0.1485981308411215, "grad_norm": 1.225950837135315, "learning_rate": 1.9272279448107054e-05, "loss": 0.809, "step": 2544 }, { "epoch": 0.14865654205607476, "grad_norm": 2.195735454559326, "learning_rate": 1.927157079221897e-05, "loss": 0.9681, "step": 2545 }, { "epoch": 0.14871495327102804, "grad_norm": 2.351184368133545, "learning_rate": 1.927086180449527e-05, "loss": 0.8437, "step": 2546 }, { "epoch": 0.1487733644859813, "grad_norm": 1.932349443435669, "learning_rate": 1.927015248496133e-05, "loss": 0.9019, "step": 2547 }, { "epoch": 0.1488317757009346, "grad_norm": 2.2761049270629883, "learning_rate": 1.926944283364254e-05, "loss": 1.0361, "step": 2548 }, { "epoch": 0.14889018691588785, "grad_norm": 2.224249839782715, "learning_rate": 1.9268732850564294e-05, "loss": 0.904, "step": 2549 }, { "epoch": 0.14894859813084113, "grad_norm": 4.618892192840576, "learning_rate": 1.9268022535752004e-05, "loss": 0.9201, "step": 2550 }, { "epoch": 0.1490070093457944, "grad_norm": 2.026883602142334, "learning_rate": 1.9267311889231096e-05, "loss": 0.9084, "step": 2551 }, { "epoch": 0.14906542056074767, "grad_norm": 2.3208673000335693, "learning_rate": 1.9266600911027e-05, "loss": 0.7951, "step": 2552 }, { "epoch": 0.14912383177570093, "grad_norm": 1.5036929845809937, "learning_rate": 1.926588960116517e-05, "loss": 0.8884, "step": 2553 }, { "epoch": 0.14918224299065422, "grad_norm": 1.6737827062606812, "learning_rate": 1.9265177959671053e-05, "loss": 0.69, "step": 2554 }, { "epoch": 0.14924065420560748, "grad_norm": 1.6971126794815063, "learning_rate": 1.9264465986570125e-05, "loss": 0.8066, "step": 2555 }, { "epoch": 0.14929906542056076, "grad_norm": 1.6339304447174072, "learning_rate": 1.926375368188787e-05, "loss": 0.9447, "step": 2556 }, { "epoch": 0.14935747663551402, "grad_norm": 1.9572598934173584, "learning_rate": 1.9263041045649777e-05, "loss": 0.9618, "step": 2557 }, { "epoch": 0.14941588785046728, "grad_norm": 1.4147390127182007, "learning_rate": 1.926232807788136e-05, "loss": 1.2033, "step": 2558 }, { "epoch": 0.14947429906542056, "grad_norm": 1.441226601600647, "learning_rate": 1.9261614778608125e-05, "loss": 0.9119, "step": 2559 }, { "epoch": 0.14953271028037382, "grad_norm": 1.5273675918579102, "learning_rate": 1.9260901147855608e-05, "loss": 0.813, "step": 2560 }, { "epoch": 0.1495911214953271, "grad_norm": 1.9077972173690796, "learning_rate": 1.9260187185649354e-05, "loss": 1.0092, "step": 2561 }, { "epoch": 0.14964953271028036, "grad_norm": 1.612104058265686, "learning_rate": 1.9259472892014907e-05, "loss": 0.8582, "step": 2562 }, { "epoch": 0.14970794392523365, "grad_norm": 1.7257003784179688, "learning_rate": 1.925875826697784e-05, "loss": 0.8223, "step": 2563 }, { "epoch": 0.1497663551401869, "grad_norm": 2.776137590408325, "learning_rate": 1.9258043310563724e-05, "loss": 0.922, "step": 2564 }, { "epoch": 0.1498247663551402, "grad_norm": 1.786677598953247, "learning_rate": 1.9257328022798155e-05, "loss": 0.781, "step": 2565 }, { "epoch": 0.14988317757009345, "grad_norm": 2.2818665504455566, "learning_rate": 1.925661240370673e-05, "loss": 0.845, "step": 2566 }, { "epoch": 0.14994158878504674, "grad_norm": 1.5554879903793335, "learning_rate": 1.9255896453315054e-05, "loss": 0.9336, "step": 2567 }, { "epoch": 0.15, "grad_norm": 1.5830940008163452, "learning_rate": 1.925518017164876e-05, "loss": 0.9029, "step": 2568 }, { "epoch": 0.15005841121495328, "grad_norm": 1.7071921825408936, "learning_rate": 1.925446355873349e-05, "loss": 0.7645, "step": 2569 }, { "epoch": 0.15011682242990654, "grad_norm": 3.1026642322540283, "learning_rate": 1.9253746614594876e-05, "loss": 0.9912, "step": 2570 }, { "epoch": 0.15017523364485982, "grad_norm": 1.7169662714004517, "learning_rate": 1.9253029339258586e-05, "loss": 0.8252, "step": 2571 }, { "epoch": 0.15023364485981308, "grad_norm": 2.072693347930908, "learning_rate": 1.9252311732750295e-05, "loss": 0.9499, "step": 2572 }, { "epoch": 0.15029205607476637, "grad_norm": 1.154496192932129, "learning_rate": 1.9251593795095683e-05, "loss": 0.917, "step": 2573 }, { "epoch": 0.15035046728971962, "grad_norm": 1.756633996963501, "learning_rate": 1.9250875526320446e-05, "loss": 0.7783, "step": 2574 }, { "epoch": 0.1504088785046729, "grad_norm": 2.1032633781433105, "learning_rate": 1.9250156926450293e-05, "loss": 0.8515, "step": 2575 }, { "epoch": 0.15046728971962617, "grad_norm": 1.9181439876556396, "learning_rate": 1.924943799551094e-05, "loss": 0.9645, "step": 2576 }, { "epoch": 0.15052570093457943, "grad_norm": 1.764671802520752, "learning_rate": 1.924871873352812e-05, "loss": 0.8496, "step": 2577 }, { "epoch": 0.1505841121495327, "grad_norm": 1.6072269678115845, "learning_rate": 1.9247999140527574e-05, "loss": 0.8918, "step": 2578 }, { "epoch": 0.15064252336448597, "grad_norm": 1.8028860092163086, "learning_rate": 1.924727921653506e-05, "loss": 0.8502, "step": 2579 }, { "epoch": 0.15070093457943926, "grad_norm": 1.6740801334381104, "learning_rate": 1.924655896157634e-05, "loss": 0.965, "step": 2580 }, { "epoch": 0.1507593457943925, "grad_norm": 1.5061893463134766, "learning_rate": 1.9245838375677196e-05, "loss": 0.8027, "step": 2581 }, { "epoch": 0.1508177570093458, "grad_norm": 1.5524488687515259, "learning_rate": 1.924511745886342e-05, "loss": 0.7313, "step": 2582 }, { "epoch": 0.15087616822429906, "grad_norm": 1.2648664712905884, "learning_rate": 1.9244396211160808e-05, "loss": 0.6261, "step": 2583 }, { "epoch": 0.15093457943925234, "grad_norm": 1.3777949810028076, "learning_rate": 1.9243674632595178e-05, "loss": 1.0343, "step": 2584 }, { "epoch": 0.1509929906542056, "grad_norm": 1.557958960533142, "learning_rate": 1.9242952723192357e-05, "loss": 0.983, "step": 2585 }, { "epoch": 0.15105140186915889, "grad_norm": 1.3021504878997803, "learning_rate": 1.924223048297818e-05, "loss": 0.748, "step": 2586 }, { "epoch": 0.15110981308411214, "grad_norm": 1.4190678596496582, "learning_rate": 1.9241507911978495e-05, "loss": 1.0192, "step": 2587 }, { "epoch": 0.15116822429906543, "grad_norm": 1.3599473237991333, "learning_rate": 1.9240785010219167e-05, "loss": 0.9082, "step": 2588 }, { "epoch": 0.1512266355140187, "grad_norm": 1.269688606262207, "learning_rate": 1.9240061777726068e-05, "loss": 0.7653, "step": 2589 }, { "epoch": 0.15128504672897197, "grad_norm": 2.145460844039917, "learning_rate": 1.923933821452508e-05, "loss": 0.7918, "step": 2590 }, { "epoch": 0.15134345794392523, "grad_norm": 1.4312535524368286, "learning_rate": 1.9238614320642104e-05, "loss": 0.8806, "step": 2591 }, { "epoch": 0.15140186915887852, "grad_norm": 1.6268960237503052, "learning_rate": 1.923789009610305e-05, "loss": 0.8607, "step": 2592 }, { "epoch": 0.15146028037383177, "grad_norm": 1.4835413694381714, "learning_rate": 1.923716554093383e-05, "loss": 1.0178, "step": 2593 }, { "epoch": 0.15151869158878506, "grad_norm": 1.0966594219207764, "learning_rate": 1.9236440655160385e-05, "loss": 0.7817, "step": 2594 }, { "epoch": 0.15157710280373832, "grad_norm": 1.7064374685287476, "learning_rate": 1.9235715438808655e-05, "loss": 1.0378, "step": 2595 }, { "epoch": 0.15163551401869158, "grad_norm": 1.0847580432891846, "learning_rate": 1.92349898919046e-05, "loss": 0.5715, "step": 2596 }, { "epoch": 0.15169392523364486, "grad_norm": 1.3609122037887573, "learning_rate": 1.9234264014474178e-05, "loss": 0.8817, "step": 2597 }, { "epoch": 0.15175233644859812, "grad_norm": 1.65287446975708, "learning_rate": 1.9233537806543383e-05, "loss": 0.835, "step": 2598 }, { "epoch": 0.1518107476635514, "grad_norm": 1.6088656187057495, "learning_rate": 1.9232811268138193e-05, "loss": 0.809, "step": 2599 }, { "epoch": 0.15186915887850466, "grad_norm": 1.527820348739624, "learning_rate": 1.9232084399284617e-05, "loss": 0.7688, "step": 2600 }, { "epoch": 0.15192757009345795, "grad_norm": 1.6577916145324707, "learning_rate": 1.9231357200008673e-05, "loss": 0.7599, "step": 2601 }, { "epoch": 0.1519859813084112, "grad_norm": 1.481357455253601, "learning_rate": 1.9230629670336383e-05, "loss": 0.8078, "step": 2602 }, { "epoch": 0.1520443925233645, "grad_norm": 1.7743103504180908, "learning_rate": 1.922990181029379e-05, "loss": 0.9461, "step": 2603 }, { "epoch": 0.15210280373831775, "grad_norm": 1.5081043243408203, "learning_rate": 1.922917361990694e-05, "loss": 0.8792, "step": 2604 }, { "epoch": 0.15216121495327103, "grad_norm": 1.5502022504806519, "learning_rate": 1.92284450992019e-05, "loss": 0.7408, "step": 2605 }, { "epoch": 0.1522196261682243, "grad_norm": 1.308375358581543, "learning_rate": 1.9227716248204742e-05, "loss": 0.7379, "step": 2606 }, { "epoch": 0.15227803738317758, "grad_norm": 2.0593533515930176, "learning_rate": 1.9226987066941548e-05, "loss": 1.0081, "step": 2607 }, { "epoch": 0.15233644859813084, "grad_norm": 1.4396615028381348, "learning_rate": 1.9226257555438428e-05, "loss": 0.8048, "step": 2608 }, { "epoch": 0.15239485981308412, "grad_norm": 3.850309133529663, "learning_rate": 1.9225527713721476e-05, "loss": 0.8339, "step": 2609 }, { "epoch": 0.15245327102803738, "grad_norm": 2.2437522411346436, "learning_rate": 1.9224797541816826e-05, "loss": 0.8984, "step": 2610 }, { "epoch": 0.15251168224299066, "grad_norm": 1.9773043394088745, "learning_rate": 1.9224067039750603e-05, "loss": 0.8386, "step": 2611 }, { "epoch": 0.15257009345794392, "grad_norm": 2.603581666946411, "learning_rate": 1.922333620754896e-05, "loss": 0.8937, "step": 2612 }, { "epoch": 0.1526285046728972, "grad_norm": 1.4873559474945068, "learning_rate": 1.9222605045238046e-05, "loss": 0.9582, "step": 2613 }, { "epoch": 0.15268691588785047, "grad_norm": 2.277404308319092, "learning_rate": 1.9221873552844035e-05, "loss": 0.9199, "step": 2614 }, { "epoch": 0.15274532710280375, "grad_norm": 1.473441243171692, "learning_rate": 1.9221141730393105e-05, "loss": 0.7772, "step": 2615 }, { "epoch": 0.152803738317757, "grad_norm": 1.8289278745651245, "learning_rate": 1.922040957791145e-05, "loss": 0.8655, "step": 2616 }, { "epoch": 0.15286214953271027, "grad_norm": 1.575886845588684, "learning_rate": 1.9219677095425277e-05, "loss": 0.8601, "step": 2617 }, { "epoch": 0.15292056074766355, "grad_norm": 1.8998562097549438, "learning_rate": 1.9218944282960792e-05, "loss": 0.8905, "step": 2618 }, { "epoch": 0.1529789719626168, "grad_norm": 1.549875259399414, "learning_rate": 1.9218211140544235e-05, "loss": 0.8238, "step": 2619 }, { "epoch": 0.1530373831775701, "grad_norm": 1.4623222351074219, "learning_rate": 1.921747766820184e-05, "loss": 0.7649, "step": 2620 }, { "epoch": 0.15309579439252335, "grad_norm": 1.5627076625823975, "learning_rate": 1.9216743865959854e-05, "loss": 0.7497, "step": 2621 }, { "epoch": 0.15315420560747664, "grad_norm": 1.3430038690567017, "learning_rate": 1.9216009733844546e-05, "loss": 0.9431, "step": 2622 }, { "epoch": 0.1532126168224299, "grad_norm": 4.493067264556885, "learning_rate": 1.921527527188219e-05, "loss": 0.7835, "step": 2623 }, { "epoch": 0.15327102803738318, "grad_norm": 1.8319941759109497, "learning_rate": 1.921454048009908e-05, "loss": 0.7692, "step": 2624 }, { "epoch": 0.15332943925233644, "grad_norm": 1.1710100173950195, "learning_rate": 1.92138053585215e-05, "loss": 0.7894, "step": 2625 }, { "epoch": 0.15338785046728973, "grad_norm": 1.5288444757461548, "learning_rate": 1.921306990717577e-05, "loss": 0.9329, "step": 2626 }, { "epoch": 0.15344626168224298, "grad_norm": 1.8954505920410156, "learning_rate": 1.921233412608821e-05, "loss": 0.9626, "step": 2627 }, { "epoch": 0.15350467289719627, "grad_norm": 1.7936526536941528, "learning_rate": 1.9211598015285155e-05, "loss": 0.8281, "step": 2628 }, { "epoch": 0.15356308411214953, "grad_norm": 1.325842022895813, "learning_rate": 1.9210861574792952e-05, "loss": 0.8071, "step": 2629 }, { "epoch": 0.1536214953271028, "grad_norm": 1.8502684831619263, "learning_rate": 1.9210124804637952e-05, "loss": 0.8413, "step": 2630 }, { "epoch": 0.15367990654205607, "grad_norm": 1.2983314990997314, "learning_rate": 1.9209387704846535e-05, "loss": 1.0207, "step": 2631 }, { "epoch": 0.15373831775700936, "grad_norm": 1.3637303113937378, "learning_rate": 1.9208650275445073e-05, "loss": 0.7936, "step": 2632 }, { "epoch": 0.15379672897196262, "grad_norm": 2.5967607498168945, "learning_rate": 1.9207912516459965e-05, "loss": 0.9008, "step": 2633 }, { "epoch": 0.1538551401869159, "grad_norm": 1.4521759748458862, "learning_rate": 1.9207174427917613e-05, "loss": 0.6243, "step": 2634 }, { "epoch": 0.15391355140186916, "grad_norm": 3.417670488357544, "learning_rate": 1.9206436009844435e-05, "loss": 0.8633, "step": 2635 }, { "epoch": 0.15397196261682242, "grad_norm": 1.3178791999816895, "learning_rate": 1.920569726226686e-05, "loss": 0.8248, "step": 2636 }, { "epoch": 0.1540303738317757, "grad_norm": 2.9291367530822754, "learning_rate": 1.9204958185211325e-05, "loss": 0.8043, "step": 2637 }, { "epoch": 0.15408878504672896, "grad_norm": 3.793461561203003, "learning_rate": 1.920421877870428e-05, "loss": 0.9556, "step": 2638 }, { "epoch": 0.15414719626168225, "grad_norm": 3.268324136734009, "learning_rate": 1.92034790427722e-05, "loss": 0.8755, "step": 2639 }, { "epoch": 0.1542056074766355, "grad_norm": 4.477619171142578, "learning_rate": 1.920273897744155e-05, "loss": 0.9058, "step": 2640 }, { "epoch": 0.1542640186915888, "grad_norm": 2.4974989891052246, "learning_rate": 1.9201998582738825e-05, "loss": 0.8222, "step": 2641 }, { "epoch": 0.15432242990654205, "grad_norm": 2.8629274368286133, "learning_rate": 1.9201257858690517e-05, "loss": 0.9301, "step": 2642 }, { "epoch": 0.15438084112149533, "grad_norm": 2.7398593425750732, "learning_rate": 1.920051680532314e-05, "loss": 0.9487, "step": 2643 }, { "epoch": 0.1544392523364486, "grad_norm": 2.056840419769287, "learning_rate": 1.9199775422663217e-05, "loss": 0.8431, "step": 2644 }, { "epoch": 0.15449766355140188, "grad_norm": 2.9208309650421143, "learning_rate": 1.9199033710737286e-05, "loss": 1.0254, "step": 2645 }, { "epoch": 0.15455607476635513, "grad_norm": 2.1408369541168213, "learning_rate": 1.919829166957189e-05, "loss": 0.931, "step": 2646 }, { "epoch": 0.15461448598130842, "grad_norm": 2.5572359561920166, "learning_rate": 1.919754929919358e-05, "loss": 0.9637, "step": 2647 }, { "epoch": 0.15467289719626168, "grad_norm": 2.692793607711792, "learning_rate": 1.919680659962894e-05, "loss": 1.0002, "step": 2648 }, { "epoch": 0.15473130841121496, "grad_norm": 1.8535457849502563, "learning_rate": 1.9196063570904543e-05, "loss": 0.9074, "step": 2649 }, { "epoch": 0.15478971962616822, "grad_norm": 2.1988027095794678, "learning_rate": 1.9195320213046984e-05, "loss": 0.7855, "step": 2650 }, { "epoch": 0.1548481308411215, "grad_norm": 1.63995361328125, "learning_rate": 1.9194576526082865e-05, "loss": 0.7907, "step": 2651 }, { "epoch": 0.15490654205607476, "grad_norm": 1.2943899631500244, "learning_rate": 1.9193832510038812e-05, "loss": 0.9282, "step": 2652 }, { "epoch": 0.15496495327102805, "grad_norm": 1.8957796096801758, "learning_rate": 1.9193088164941443e-05, "loss": 0.8781, "step": 2653 }, { "epoch": 0.1550233644859813, "grad_norm": 1.9688456058502197, "learning_rate": 1.9192343490817412e-05, "loss": 0.8286, "step": 2654 }, { "epoch": 0.1550817757009346, "grad_norm": 1.4485002756118774, "learning_rate": 1.9191598487693357e-05, "loss": 1.0225, "step": 2655 }, { "epoch": 0.15514018691588785, "grad_norm": 3.1250689029693604, "learning_rate": 1.919085315559595e-05, "loss": 0.8923, "step": 2656 }, { "epoch": 0.1551985981308411, "grad_norm": 2.3101561069488525, "learning_rate": 1.9190107494551865e-05, "loss": 0.9869, "step": 2657 }, { "epoch": 0.1552570093457944, "grad_norm": 2.0541000366210938, "learning_rate": 1.9189361504587792e-05, "loss": 1.0239, "step": 2658 }, { "epoch": 0.15531542056074765, "grad_norm": 2.0840530395507812, "learning_rate": 1.9188615185730428e-05, "loss": 0.9272, "step": 2659 }, { "epoch": 0.15537383177570094, "grad_norm": 1.4990626573562622, "learning_rate": 1.9187868538006484e-05, "loss": 0.9289, "step": 2660 }, { "epoch": 0.1554322429906542, "grad_norm": 1.985356330871582, "learning_rate": 1.9187121561442686e-05, "loss": 0.9138, "step": 2661 }, { "epoch": 0.15549065420560748, "grad_norm": 2.4071948528289795, "learning_rate": 1.9186374256065763e-05, "loss": 1.119, "step": 2662 }, { "epoch": 0.15554906542056074, "grad_norm": 1.3301291465759277, "learning_rate": 1.918562662190247e-05, "loss": 0.8776, "step": 2663 }, { "epoch": 0.15560747663551402, "grad_norm": 1.8502057790756226, "learning_rate": 1.9184878658979554e-05, "loss": 0.7685, "step": 2664 }, { "epoch": 0.15566588785046728, "grad_norm": 1.664453387260437, "learning_rate": 1.9184130367323797e-05, "loss": 1.0254, "step": 2665 }, { "epoch": 0.15572429906542057, "grad_norm": 1.372408390045166, "learning_rate": 1.9183381746961972e-05, "loss": 0.7864, "step": 2666 }, { "epoch": 0.15578271028037383, "grad_norm": 2.122457981109619, "learning_rate": 1.918263279792088e-05, "loss": 1.1577, "step": 2667 }, { "epoch": 0.1558411214953271, "grad_norm": 1.4922906160354614, "learning_rate": 1.9181883520227318e-05, "loss": 0.9941, "step": 2668 }, { "epoch": 0.15589953271028037, "grad_norm": 1.5975393056869507, "learning_rate": 1.918113391390811e-05, "loss": 0.9128, "step": 2669 }, { "epoch": 0.15595794392523366, "grad_norm": 1.3528687953948975, "learning_rate": 1.9180383978990083e-05, "loss": 1.0154, "step": 2670 }, { "epoch": 0.1560163551401869, "grad_norm": 1.3121488094329834, "learning_rate": 1.9179633715500076e-05, "loss": 0.7557, "step": 2671 }, { "epoch": 0.1560747663551402, "grad_norm": 1.6118983030319214, "learning_rate": 1.9178883123464946e-05, "loss": 0.9526, "step": 2672 }, { "epoch": 0.15613317757009346, "grad_norm": 1.2101044654846191, "learning_rate": 1.917813220291155e-05, "loss": 0.9205, "step": 2673 }, { "epoch": 0.15619158878504674, "grad_norm": 1.5502568483352661, "learning_rate": 1.917738095386677e-05, "loss": 1.0627, "step": 2674 }, { "epoch": 0.15625, "grad_norm": 1.2628538608551025, "learning_rate": 1.917662937635749e-05, "loss": 0.7728, "step": 2675 }, { "epoch": 0.15630841121495326, "grad_norm": 1.5362368822097778, "learning_rate": 1.9175877470410607e-05, "loss": 0.8485, "step": 2676 }, { "epoch": 0.15636682242990654, "grad_norm": 1.622599482536316, "learning_rate": 1.9175125236053043e-05, "loss": 1.0409, "step": 2677 }, { "epoch": 0.1564252336448598, "grad_norm": 1.639258623123169, "learning_rate": 1.917437267331171e-05, "loss": 0.8214, "step": 2678 }, { "epoch": 0.1564836448598131, "grad_norm": 3.6598873138427734, "learning_rate": 1.917361978221355e-05, "loss": 0.947, "step": 2679 }, { "epoch": 0.15654205607476634, "grad_norm": 1.79779851436615, "learning_rate": 1.9172866562785503e-05, "loss": 1.0518, "step": 2680 }, { "epoch": 0.15660046728971963, "grad_norm": 1.8147670030593872, "learning_rate": 1.917211301505453e-05, "loss": 0.8377, "step": 2681 }, { "epoch": 0.1566588785046729, "grad_norm": 2.246406078338623, "learning_rate": 1.9171359139047606e-05, "loss": 0.9673, "step": 2682 }, { "epoch": 0.15671728971962617, "grad_norm": 1.341888666152954, "learning_rate": 1.9170604934791703e-05, "loss": 1.0119, "step": 2683 }, { "epoch": 0.15677570093457943, "grad_norm": 2.4681460857391357, "learning_rate": 1.9169850402313824e-05, "loss": 1.036, "step": 2684 }, { "epoch": 0.15683411214953272, "grad_norm": 2.265291929244995, "learning_rate": 1.9169095541640967e-05, "loss": 0.8888, "step": 2685 }, { "epoch": 0.15689252336448598, "grad_norm": 1.9621820449829102, "learning_rate": 1.9168340352800153e-05, "loss": 0.7064, "step": 2686 }, { "epoch": 0.15695093457943926, "grad_norm": 2.39713716506958, "learning_rate": 1.9167584835818406e-05, "loss": 0.9737, "step": 2687 }, { "epoch": 0.15700934579439252, "grad_norm": 1.8199795484542847, "learning_rate": 1.9166828990722774e-05, "loss": 0.8265, "step": 2688 }, { "epoch": 0.1570677570093458, "grad_norm": 2.4427552223205566, "learning_rate": 1.9166072817540303e-05, "loss": 1.0444, "step": 2689 }, { "epoch": 0.15712616822429906, "grad_norm": 2.2589688301086426, "learning_rate": 1.916531631629806e-05, "loss": 0.9, "step": 2690 }, { "epoch": 0.15718457943925235, "grad_norm": 3.020653247833252, "learning_rate": 1.916455948702312e-05, "loss": 0.9284, "step": 2691 }, { "epoch": 0.1572429906542056, "grad_norm": 1.7851808071136475, "learning_rate": 1.916380232974257e-05, "loss": 0.8373, "step": 2692 }, { "epoch": 0.1573014018691589, "grad_norm": 1.621468186378479, "learning_rate": 1.9163044844483507e-05, "loss": 0.7426, "step": 2693 }, { "epoch": 0.15735981308411215, "grad_norm": 1.6590397357940674, "learning_rate": 1.9162287031273048e-05, "loss": 0.7753, "step": 2694 }, { "epoch": 0.1574182242990654, "grad_norm": 1.725970983505249, "learning_rate": 1.916152889013831e-05, "loss": 0.7647, "step": 2695 }, { "epoch": 0.1574766355140187, "grad_norm": 1.395389437675476, "learning_rate": 1.916077042110643e-05, "loss": 0.8976, "step": 2696 }, { "epoch": 0.15753504672897195, "grad_norm": 1.6351665258407593, "learning_rate": 1.9160011624204552e-05, "loss": 1.0468, "step": 2697 }, { "epoch": 0.15759345794392524, "grad_norm": 3.014604091644287, "learning_rate": 1.9159252499459835e-05, "loss": 1.0127, "step": 2698 }, { "epoch": 0.1576518691588785, "grad_norm": 1.8763223886489868, "learning_rate": 1.915849304689945e-05, "loss": 0.9211, "step": 2699 }, { "epoch": 0.15771028037383178, "grad_norm": 1.7745260000228882, "learning_rate": 1.9157733266550577e-05, "loss": 0.784, "step": 2700 }, { "epoch": 0.15776869158878504, "grad_norm": 2.6769416332244873, "learning_rate": 1.9156973158440405e-05, "loss": 0.9284, "step": 2701 }, { "epoch": 0.15782710280373832, "grad_norm": 1.9999279975891113, "learning_rate": 1.9156212722596148e-05, "loss": 0.8049, "step": 2702 }, { "epoch": 0.15788551401869158, "grad_norm": 1.2280430793762207, "learning_rate": 1.9155451959045014e-05, "loss": 0.7138, "step": 2703 }, { "epoch": 0.15794392523364487, "grad_norm": 1.4004526138305664, "learning_rate": 1.9154690867814237e-05, "loss": 0.7774, "step": 2704 }, { "epoch": 0.15800233644859812, "grad_norm": 1.5853261947631836, "learning_rate": 1.9153929448931056e-05, "loss": 0.8441, "step": 2705 }, { "epoch": 0.1580607476635514, "grad_norm": 1.3135957717895508, "learning_rate": 1.9153167702422717e-05, "loss": 0.8147, "step": 2706 }, { "epoch": 0.15811915887850467, "grad_norm": 1.6100053787231445, "learning_rate": 1.915240562831649e-05, "loss": 1.1597, "step": 2707 }, { "epoch": 0.15817757009345795, "grad_norm": 1.177474856376648, "learning_rate": 1.915164322663965e-05, "loss": 0.8653, "step": 2708 }, { "epoch": 0.1582359813084112, "grad_norm": 2.2247941493988037, "learning_rate": 1.9150880497419477e-05, "loss": 0.9432, "step": 2709 }, { "epoch": 0.1582943925233645, "grad_norm": 1.7766079902648926, "learning_rate": 1.9150117440683275e-05, "loss": 0.9428, "step": 2710 }, { "epoch": 0.15835280373831775, "grad_norm": 1.2859278917312622, "learning_rate": 1.9149354056458355e-05, "loss": 0.82, "step": 2711 }, { "epoch": 0.15841121495327104, "grad_norm": 1.8239715099334717, "learning_rate": 1.9148590344772036e-05, "loss": 0.8676, "step": 2712 }, { "epoch": 0.1584696261682243, "grad_norm": 1.263490080833435, "learning_rate": 1.9147826305651657e-05, "loss": 0.7944, "step": 2713 }, { "epoch": 0.15852803738317758, "grad_norm": 2.0518534183502197, "learning_rate": 1.9147061939124556e-05, "loss": 0.8834, "step": 2714 }, { "epoch": 0.15858644859813084, "grad_norm": 1.6122465133666992, "learning_rate": 1.9146297245218097e-05, "loss": 0.9313, "step": 2715 }, { "epoch": 0.1586448598130841, "grad_norm": 2.039891242980957, "learning_rate": 1.914553222395964e-05, "loss": 0.8576, "step": 2716 }, { "epoch": 0.15870327102803738, "grad_norm": 1.462379813194275, "learning_rate": 1.9144766875376578e-05, "loss": 0.8247, "step": 2717 }, { "epoch": 0.15876168224299064, "grad_norm": 3.0481793880462646, "learning_rate": 1.914400119949629e-05, "loss": 0.7943, "step": 2718 }, { "epoch": 0.15882009345794393, "grad_norm": 1.5525312423706055, "learning_rate": 1.9143235196346194e-05, "loss": 0.8941, "step": 2719 }, { "epoch": 0.1588785046728972, "grad_norm": 1.9497150182724, "learning_rate": 1.9142468865953692e-05, "loss": 0.966, "step": 2720 }, { "epoch": 0.15893691588785047, "grad_norm": 1.6757726669311523, "learning_rate": 1.914170220834622e-05, "loss": 0.9032, "step": 2721 }, { "epoch": 0.15899532710280373, "grad_norm": 1.5766286849975586, "learning_rate": 1.9140935223551216e-05, "loss": 0.6692, "step": 2722 }, { "epoch": 0.15905373831775702, "grad_norm": 2.362452983856201, "learning_rate": 1.9140167911596133e-05, "loss": 0.8107, "step": 2723 }, { "epoch": 0.15911214953271027, "grad_norm": 2.005826711654663, "learning_rate": 1.9139400272508428e-05, "loss": 0.9539, "step": 2724 }, { "epoch": 0.15917056074766356, "grad_norm": 2.2065658569335938, "learning_rate": 1.913863230631558e-05, "loss": 0.9617, "step": 2725 }, { "epoch": 0.15922897196261682, "grad_norm": 1.7972344160079956, "learning_rate": 1.913786401304507e-05, "loss": 0.8148, "step": 2726 }, { "epoch": 0.1592873831775701, "grad_norm": 1.714494228363037, "learning_rate": 1.91370953927244e-05, "loss": 0.9933, "step": 2727 }, { "epoch": 0.15934579439252336, "grad_norm": 1.504003882408142, "learning_rate": 1.9136326445381077e-05, "loss": 0.8893, "step": 2728 }, { "epoch": 0.15940420560747665, "grad_norm": 1.888912558555603, "learning_rate": 1.9135557171042626e-05, "loss": 0.9033, "step": 2729 }, { "epoch": 0.1594626168224299, "grad_norm": 1.4239498376846313, "learning_rate": 1.9134787569736573e-05, "loss": 0.8865, "step": 2730 }, { "epoch": 0.1595210280373832, "grad_norm": 1.1846519708633423, "learning_rate": 1.913401764149047e-05, "loss": 0.769, "step": 2731 }, { "epoch": 0.15957943925233645, "grad_norm": 1.5803087949752808, "learning_rate": 1.9133247386331866e-05, "loss": 0.7413, "step": 2732 }, { "epoch": 0.15963785046728973, "grad_norm": 1.685009241104126, "learning_rate": 1.9132476804288335e-05, "loss": 0.9277, "step": 2733 }, { "epoch": 0.159696261682243, "grad_norm": 1.4925616979599, "learning_rate": 1.9131705895387455e-05, "loss": 0.8468, "step": 2734 }, { "epoch": 0.15975467289719625, "grad_norm": 2.547146797180176, "learning_rate": 1.9130934659656818e-05, "loss": 0.6671, "step": 2735 }, { "epoch": 0.15981308411214953, "grad_norm": 1.4663338661193848, "learning_rate": 1.9130163097124027e-05, "loss": 0.7032, "step": 2736 }, { "epoch": 0.1598714953271028, "grad_norm": 1.2803843021392822, "learning_rate": 1.912939120781669e-05, "loss": 0.9422, "step": 2737 }, { "epoch": 0.15992990654205608, "grad_norm": 1.440319299697876, "learning_rate": 1.9128618991762442e-05, "loss": 0.735, "step": 2738 }, { "epoch": 0.15998831775700934, "grad_norm": 1.306405782699585, "learning_rate": 1.9127846448988922e-05, "loss": 0.7067, "step": 2739 }, { "epoch": 0.16004672897196262, "grad_norm": 1.228379487991333, "learning_rate": 1.912707357952377e-05, "loss": 0.7618, "step": 2740 }, { "epoch": 0.16010514018691588, "grad_norm": 1.4645215272903442, "learning_rate": 1.9126300383394654e-05, "loss": 0.8118, "step": 2741 }, { "epoch": 0.16016355140186916, "grad_norm": 1.6939448118209839, "learning_rate": 1.9125526860629252e-05, "loss": 1.0081, "step": 2742 }, { "epoch": 0.16022196261682242, "grad_norm": 1.7185039520263672, "learning_rate": 1.9124753011255237e-05, "loss": 0.8853, "step": 2743 }, { "epoch": 0.1602803738317757, "grad_norm": 1.4100092649459839, "learning_rate": 1.9123978835300313e-05, "loss": 0.9253, "step": 2744 }, { "epoch": 0.16033878504672897, "grad_norm": 1.5845708847045898, "learning_rate": 1.9123204332792192e-05, "loss": 0.8236, "step": 2745 }, { "epoch": 0.16039719626168225, "grad_norm": 1.1920067071914673, "learning_rate": 1.9122429503758586e-05, "loss": 0.8154, "step": 2746 }, { "epoch": 0.1604556074766355, "grad_norm": 1.2352700233459473, "learning_rate": 1.912165434822723e-05, "loss": 0.7085, "step": 2747 }, { "epoch": 0.1605140186915888, "grad_norm": 1.5204684734344482, "learning_rate": 1.912087886622587e-05, "loss": 0.7954, "step": 2748 }, { "epoch": 0.16057242990654205, "grad_norm": 1.5314807891845703, "learning_rate": 1.9120103057782255e-05, "loss": 0.7716, "step": 2749 }, { "epoch": 0.16063084112149534, "grad_norm": 2.430765151977539, "learning_rate": 1.9119326922924155e-05, "loss": 0.7883, "step": 2750 }, { "epoch": 0.1606892523364486, "grad_norm": 1.500716209411621, "learning_rate": 1.911855046167935e-05, "loss": 0.8267, "step": 2751 }, { "epoch": 0.16074766355140188, "grad_norm": 2.0016679763793945, "learning_rate": 1.9117773674075627e-05, "loss": 0.9287, "step": 2752 }, { "epoch": 0.16080607476635514, "grad_norm": 1.5884392261505127, "learning_rate": 1.9116996560140787e-05, "loss": 0.8041, "step": 2753 }, { "epoch": 0.16086448598130842, "grad_norm": 1.5320018529891968, "learning_rate": 1.911621911990265e-05, "loss": 0.8684, "step": 2754 }, { "epoch": 0.16092289719626168, "grad_norm": 1.7139990329742432, "learning_rate": 1.9115441353389036e-05, "loss": 0.8451, "step": 2755 }, { "epoch": 0.16098130841121494, "grad_norm": 1.2875895500183105, "learning_rate": 1.9114663260627783e-05, "loss": 0.7638, "step": 2756 }, { "epoch": 0.16103971962616823, "grad_norm": 1.5946608781814575, "learning_rate": 1.9113884841646736e-05, "loss": 0.7853, "step": 2757 }, { "epoch": 0.16109813084112148, "grad_norm": 1.39921236038208, "learning_rate": 1.9113106096473757e-05, "loss": 0.8609, "step": 2758 }, { "epoch": 0.16115654205607477, "grad_norm": 1.5684407949447632, "learning_rate": 1.9112327025136723e-05, "loss": 0.8808, "step": 2759 }, { "epoch": 0.16121495327102803, "grad_norm": 1.6259483098983765, "learning_rate": 1.9111547627663513e-05, "loss": 0.8427, "step": 2760 }, { "epoch": 0.1612733644859813, "grad_norm": 1.3985686302185059, "learning_rate": 1.9110767904082022e-05, "loss": 0.8372, "step": 2761 }, { "epoch": 0.16133177570093457, "grad_norm": 1.9142944812774658, "learning_rate": 1.9109987854420155e-05, "loss": 0.7358, "step": 2762 }, { "epoch": 0.16139018691588786, "grad_norm": 1.4561666250228882, "learning_rate": 1.9109207478705833e-05, "loss": 0.9175, "step": 2763 }, { "epoch": 0.16144859813084111, "grad_norm": 1.2578145265579224, "learning_rate": 1.9108426776966988e-05, "loss": 0.8743, "step": 2764 }, { "epoch": 0.1615070093457944, "grad_norm": 1.360825777053833, "learning_rate": 1.9107645749231558e-05, "loss": 0.7746, "step": 2765 }, { "epoch": 0.16156542056074766, "grad_norm": 1.3531304597854614, "learning_rate": 1.91068643955275e-05, "loss": 0.6481, "step": 2766 }, { "epoch": 0.16162383177570094, "grad_norm": 1.4520739316940308, "learning_rate": 1.9106082715882778e-05, "loss": 0.9198, "step": 2767 }, { "epoch": 0.1616822429906542, "grad_norm": 1.8557260036468506, "learning_rate": 1.9105300710325365e-05, "loss": 1.0174, "step": 2768 }, { "epoch": 0.1617406542056075, "grad_norm": 1.7936609983444214, "learning_rate": 1.910451837888325e-05, "loss": 0.9542, "step": 2769 }, { "epoch": 0.16179906542056074, "grad_norm": 1.7095128297805786, "learning_rate": 1.910373572158444e-05, "loss": 0.8204, "step": 2770 }, { "epoch": 0.16185747663551403, "grad_norm": 2.4232938289642334, "learning_rate": 1.9102952738456946e-05, "loss": 0.9394, "step": 2771 }, { "epoch": 0.1619158878504673, "grad_norm": 1.2334486246109009, "learning_rate": 1.9102169429528785e-05, "loss": 0.7588, "step": 2772 }, { "epoch": 0.16197429906542057, "grad_norm": 1.5394132137298584, "learning_rate": 1.9101385794827995e-05, "loss": 0.7823, "step": 2773 }, { "epoch": 0.16203271028037383, "grad_norm": 1.1141817569732666, "learning_rate": 1.9100601834382623e-05, "loss": 0.6168, "step": 2774 }, { "epoch": 0.1620911214953271, "grad_norm": 1.2535548210144043, "learning_rate": 1.909981754822073e-05, "loss": 0.7152, "step": 2775 }, { "epoch": 0.16214953271028038, "grad_norm": 4.062565803527832, "learning_rate": 1.9099032936370382e-05, "loss": 0.8401, "step": 2776 }, { "epoch": 0.16220794392523363, "grad_norm": 1.2783482074737549, "learning_rate": 1.909824799885966e-05, "loss": 0.8023, "step": 2777 }, { "epoch": 0.16226635514018692, "grad_norm": 1.509959101676941, "learning_rate": 1.9097462735716664e-05, "loss": 0.8618, "step": 2778 }, { "epoch": 0.16232476635514018, "grad_norm": 1.6107980012893677, "learning_rate": 1.909667714696949e-05, "loss": 0.8023, "step": 2779 }, { "epoch": 0.16238317757009346, "grad_norm": 1.4364358186721802, "learning_rate": 1.9095891232646266e-05, "loss": 0.844, "step": 2780 }, { "epoch": 0.16244158878504672, "grad_norm": 1.317057728767395, "learning_rate": 1.909510499277511e-05, "loss": 0.9761, "step": 2781 }, { "epoch": 0.1625, "grad_norm": 1.461371660232544, "learning_rate": 1.9094318427384165e-05, "loss": 1.005, "step": 2782 }, { "epoch": 0.16255841121495326, "grad_norm": 2.154916763305664, "learning_rate": 1.909353153650159e-05, "loss": 1.04, "step": 2783 }, { "epoch": 0.16261682242990655, "grad_norm": 1.5361157655715942, "learning_rate": 1.9092744320155535e-05, "loss": 0.7764, "step": 2784 }, { "epoch": 0.1626752336448598, "grad_norm": 1.740889072418213, "learning_rate": 1.9091956778374187e-05, "loss": 0.7978, "step": 2785 }, { "epoch": 0.1627336448598131, "grad_norm": 1.5888311862945557, "learning_rate": 1.9091168911185725e-05, "loss": 0.8029, "step": 2786 }, { "epoch": 0.16279205607476635, "grad_norm": 1.2554763555526733, "learning_rate": 1.9090380718618353e-05, "loss": 0.9556, "step": 2787 }, { "epoch": 0.16285046728971964, "grad_norm": 1.5198767185211182, "learning_rate": 1.9089592200700275e-05, "loss": 0.9817, "step": 2788 }, { "epoch": 0.1629088785046729, "grad_norm": 1.3526908159255981, "learning_rate": 1.908880335745972e-05, "loss": 0.9399, "step": 2789 }, { "epoch": 0.16296728971962618, "grad_norm": 1.4183059930801392, "learning_rate": 1.908801418892491e-05, "loss": 0.8057, "step": 2790 }, { "epoch": 0.16302570093457944, "grad_norm": 1.1147180795669556, "learning_rate": 1.90872246951241e-05, "loss": 0.7941, "step": 2791 }, { "epoch": 0.16308411214953272, "grad_norm": 1.6723653078079224, "learning_rate": 1.9086434876085548e-05, "loss": 0.8238, "step": 2792 }, { "epoch": 0.16314252336448598, "grad_norm": 1.0837366580963135, "learning_rate": 1.9085644731837513e-05, "loss": 0.8858, "step": 2793 }, { "epoch": 0.16320093457943924, "grad_norm": 1.7037909030914307, "learning_rate": 1.9084854262408278e-05, "loss": 0.8244, "step": 2794 }, { "epoch": 0.16325934579439252, "grad_norm": 1.313225269317627, "learning_rate": 1.9084063467826137e-05, "loss": 0.9883, "step": 2795 }, { "epoch": 0.16331775700934578, "grad_norm": 1.8604704141616821, "learning_rate": 1.9083272348119392e-05, "loss": 0.8888, "step": 2796 }, { "epoch": 0.16337616822429907, "grad_norm": 2.6164004802703857, "learning_rate": 1.9082480903316356e-05, "loss": 0.9836, "step": 2797 }, { "epoch": 0.16343457943925233, "grad_norm": 1.5229548215866089, "learning_rate": 1.9081689133445356e-05, "loss": 0.9211, "step": 2798 }, { "epoch": 0.1634929906542056, "grad_norm": 2.4349684715270996, "learning_rate": 1.9080897038534735e-05, "loss": 1.0628, "step": 2799 }, { "epoch": 0.16355140186915887, "grad_norm": 1.4400700330734253, "learning_rate": 1.9080104618612832e-05, "loss": 0.8548, "step": 2800 }, { "epoch": 0.16360981308411215, "grad_norm": 1.2326046228408813, "learning_rate": 1.9079311873708016e-05, "loss": 0.8132, "step": 2801 }, { "epoch": 0.1636682242990654, "grad_norm": 1.4221915006637573, "learning_rate": 1.907851880384866e-05, "loss": 0.705, "step": 2802 }, { "epoch": 0.1637266355140187, "grad_norm": 1.25681734085083, "learning_rate": 1.9077725409063148e-05, "loss": 0.9454, "step": 2803 }, { "epoch": 0.16378504672897196, "grad_norm": 2.0337915420532227, "learning_rate": 1.9076931689379873e-05, "loss": 1.015, "step": 2804 }, { "epoch": 0.16384345794392524, "grad_norm": 2.951873302459717, "learning_rate": 1.9076137644827243e-05, "loss": 0.7347, "step": 2805 }, { "epoch": 0.1639018691588785, "grad_norm": 2.2112557888031006, "learning_rate": 1.9075343275433686e-05, "loss": 1.1163, "step": 2806 }, { "epoch": 0.16396028037383178, "grad_norm": 1.6013681888580322, "learning_rate": 1.9074548581227618e-05, "loss": 0.8817, "step": 2807 }, { "epoch": 0.16401869158878504, "grad_norm": 1.4992495775222778, "learning_rate": 1.9073753562237494e-05, "loss": 0.8414, "step": 2808 }, { "epoch": 0.16407710280373833, "grad_norm": 1.2327359914779663, "learning_rate": 1.9072958218491763e-05, "loss": 0.87, "step": 2809 }, { "epoch": 0.1641355140186916, "grad_norm": 1.2935147285461426, "learning_rate": 1.9072162550018892e-05, "loss": 0.6925, "step": 2810 }, { "epoch": 0.16419392523364487, "grad_norm": 1.1771374940872192, "learning_rate": 1.9071366556847356e-05, "loss": 0.669, "step": 2811 }, { "epoch": 0.16425233644859813, "grad_norm": 1.2178425788879395, "learning_rate": 1.9070570239005648e-05, "loss": 0.6785, "step": 2812 }, { "epoch": 0.16431074766355142, "grad_norm": 1.4894040822982788, "learning_rate": 1.9069773596522266e-05, "loss": 0.7978, "step": 2813 }, { "epoch": 0.16436915887850467, "grad_norm": 2.0066165924072266, "learning_rate": 1.9068976629425725e-05, "loss": 0.8437, "step": 2814 }, { "epoch": 0.16442757009345793, "grad_norm": 1.637831449508667, "learning_rate": 1.906817933774455e-05, "loss": 0.7556, "step": 2815 }, { "epoch": 0.16448598130841122, "grad_norm": 1.6890745162963867, "learning_rate": 1.906738172150727e-05, "loss": 0.7893, "step": 2816 }, { "epoch": 0.16454439252336447, "grad_norm": 1.4700120687484741, "learning_rate": 1.9066583780742436e-05, "loss": 0.8122, "step": 2817 }, { "epoch": 0.16460280373831776, "grad_norm": 1.4675034284591675, "learning_rate": 1.906578551547861e-05, "loss": 0.7769, "step": 2818 }, { "epoch": 0.16466121495327102, "grad_norm": 1.2028920650482178, "learning_rate": 1.9064986925744358e-05, "loss": 0.7929, "step": 2819 }, { "epoch": 0.1647196261682243, "grad_norm": 1.3599178791046143, "learning_rate": 1.9064188011568264e-05, "loss": 0.9154, "step": 2820 }, { "epoch": 0.16477803738317756, "grad_norm": 1.490167498588562, "learning_rate": 1.906338877297892e-05, "loss": 1.0094, "step": 2821 }, { "epoch": 0.16483644859813085, "grad_norm": 1.9127541780471802, "learning_rate": 1.9062589210004932e-05, "loss": 0.9995, "step": 2822 }, { "epoch": 0.1648948598130841, "grad_norm": 2.041046142578125, "learning_rate": 1.906178932267492e-05, "loss": 0.9737, "step": 2823 }, { "epoch": 0.1649532710280374, "grad_norm": 1.373911738395691, "learning_rate": 1.9060989111017507e-05, "loss": 1.0642, "step": 2824 }, { "epoch": 0.16501168224299065, "grad_norm": 1.5366630554199219, "learning_rate": 1.906018857506134e-05, "loss": 0.8848, "step": 2825 }, { "epoch": 0.16507009345794393, "grad_norm": 1.431104063987732, "learning_rate": 1.9059387714835065e-05, "loss": 0.7179, "step": 2826 }, { "epoch": 0.1651285046728972, "grad_norm": 1.7242690324783325, "learning_rate": 1.9058586530367345e-05, "loss": 0.8791, "step": 2827 }, { "epoch": 0.16518691588785048, "grad_norm": 1.2323092222213745, "learning_rate": 1.905778502168686e-05, "loss": 0.8724, "step": 2828 }, { "epoch": 0.16524532710280374, "grad_norm": 1.596468210220337, "learning_rate": 1.905698318882229e-05, "loss": 0.8074, "step": 2829 }, { "epoch": 0.16530373831775702, "grad_norm": 1.3733431100845337, "learning_rate": 1.905618103180234e-05, "loss": 0.7294, "step": 2830 }, { "epoch": 0.16536214953271028, "grad_norm": 1.9529210329055786, "learning_rate": 1.9055378550655713e-05, "loss": 0.805, "step": 2831 }, { "epoch": 0.16542056074766356, "grad_norm": 1.7292485237121582, "learning_rate": 1.9054575745411135e-05, "loss": 0.8666, "step": 2832 }, { "epoch": 0.16547897196261682, "grad_norm": 2.6816227436065674, "learning_rate": 1.905377261609734e-05, "loss": 0.9631, "step": 2833 }, { "epoch": 0.16553738317757008, "grad_norm": 1.3026996850967407, "learning_rate": 1.9052969162743067e-05, "loss": 0.9058, "step": 2834 }, { "epoch": 0.16559579439252337, "grad_norm": 2.9068572521209717, "learning_rate": 1.905216538537708e-05, "loss": 0.9295, "step": 2835 }, { "epoch": 0.16565420560747662, "grad_norm": 1.1772282123565674, "learning_rate": 1.9051361284028137e-05, "loss": 0.979, "step": 2836 }, { "epoch": 0.1657126168224299, "grad_norm": 1.8038743734359741, "learning_rate": 1.905055685872502e-05, "loss": 0.8785, "step": 2837 }, { "epoch": 0.16577102803738317, "grad_norm": 1.5553362369537354, "learning_rate": 1.9049752109496526e-05, "loss": 0.7953, "step": 2838 }, { "epoch": 0.16582943925233645, "grad_norm": 1.2030214071273804, "learning_rate": 1.904894703637145e-05, "loss": 0.7982, "step": 2839 }, { "epoch": 0.1658878504672897, "grad_norm": 2.21329927444458, "learning_rate": 1.9048141639378616e-05, "loss": 0.8935, "step": 2840 }, { "epoch": 0.165946261682243, "grad_norm": 1.4154222011566162, "learning_rate": 1.9047335918546843e-05, "loss": 0.8148, "step": 2841 }, { "epoch": 0.16600467289719625, "grad_norm": 1.6662698984146118, "learning_rate": 1.9046529873904967e-05, "loss": 0.8363, "step": 2842 }, { "epoch": 0.16606308411214954, "grad_norm": 1.7220646142959595, "learning_rate": 1.9045723505481835e-05, "loss": 0.8886, "step": 2843 }, { "epoch": 0.1661214953271028, "grad_norm": 1.6968469619750977, "learning_rate": 1.9044916813306313e-05, "loss": 0.826, "step": 2844 }, { "epoch": 0.16617990654205608, "grad_norm": 1.972969889640808, "learning_rate": 1.9044109797407273e-05, "loss": 1.0329, "step": 2845 }, { "epoch": 0.16623831775700934, "grad_norm": 1.6217747926712036, "learning_rate": 1.9043302457813597e-05, "loss": 0.9774, "step": 2846 }, { "epoch": 0.16629672897196263, "grad_norm": 2.321925163269043, "learning_rate": 1.9042494794554177e-05, "loss": 0.9103, "step": 2847 }, { "epoch": 0.16635514018691588, "grad_norm": 1.6866095066070557, "learning_rate": 1.9041686807657925e-05, "loss": 0.832, "step": 2848 }, { "epoch": 0.16641355140186917, "grad_norm": 1.8793638944625854, "learning_rate": 1.9040878497153756e-05, "loss": 0.8445, "step": 2849 }, { "epoch": 0.16647196261682243, "grad_norm": 1.4737614393234253, "learning_rate": 1.9040069863070604e-05, "loss": 0.758, "step": 2850 }, { "epoch": 0.1665303738317757, "grad_norm": 1.3766556978225708, "learning_rate": 1.9039260905437404e-05, "loss": 0.7119, "step": 2851 }, { "epoch": 0.16658878504672897, "grad_norm": 2.120993137359619, "learning_rate": 1.9038451624283113e-05, "loss": 0.9747, "step": 2852 }, { "epoch": 0.16664719626168226, "grad_norm": 1.4583591222763062, "learning_rate": 1.9037642019636697e-05, "loss": 0.8088, "step": 2853 }, { "epoch": 0.16670560747663551, "grad_norm": 1.4852606058120728, "learning_rate": 1.9036832091527132e-05, "loss": 0.8064, "step": 2854 }, { "epoch": 0.16676401869158877, "grad_norm": 2.001452922821045, "learning_rate": 1.9036021839983403e-05, "loss": 0.8492, "step": 2855 }, { "epoch": 0.16682242990654206, "grad_norm": 1.2816916704177856, "learning_rate": 1.903521126503451e-05, "loss": 0.8261, "step": 2856 }, { "epoch": 0.16688084112149532, "grad_norm": 1.7923851013183594, "learning_rate": 1.9034400366709466e-05, "loss": 0.8656, "step": 2857 }, { "epoch": 0.1669392523364486, "grad_norm": 1.387657880783081, "learning_rate": 1.9033589145037292e-05, "loss": 0.7088, "step": 2858 }, { "epoch": 0.16699766355140186, "grad_norm": 1.957051157951355, "learning_rate": 1.9032777600047026e-05, "loss": 0.8784, "step": 2859 }, { "epoch": 0.16705607476635514, "grad_norm": 1.3867886066436768, "learning_rate": 1.903196573176771e-05, "loss": 0.9003, "step": 2860 }, { "epoch": 0.1671144859813084, "grad_norm": 1.5179166793823242, "learning_rate": 1.9031153540228398e-05, "loss": 0.884, "step": 2861 }, { "epoch": 0.1671728971962617, "grad_norm": 1.709492564201355, "learning_rate": 1.9030341025458163e-05, "loss": 0.924, "step": 2862 }, { "epoch": 0.16723130841121495, "grad_norm": 1.2017886638641357, "learning_rate": 1.9029528187486085e-05, "loss": 0.735, "step": 2863 }, { "epoch": 0.16728971962616823, "grad_norm": 2.440810441970825, "learning_rate": 1.902871502634126e-05, "loss": 0.9565, "step": 2864 }, { "epoch": 0.1673481308411215, "grad_norm": 1.1414709091186523, "learning_rate": 1.9027901542052786e-05, "loss": 0.6959, "step": 2865 }, { "epoch": 0.16740654205607478, "grad_norm": 3.277543306350708, "learning_rate": 1.9027087734649782e-05, "loss": 0.7957, "step": 2866 }, { "epoch": 0.16746495327102803, "grad_norm": 1.936920166015625, "learning_rate": 1.9026273604161368e-05, "loss": 0.8436, "step": 2867 }, { "epoch": 0.16752336448598132, "grad_norm": 2.69710373878479, "learning_rate": 1.902545915061669e-05, "loss": 0.9145, "step": 2868 }, { "epoch": 0.16758177570093458, "grad_norm": 1.5216907262802124, "learning_rate": 1.9024644374044892e-05, "loss": 0.878, "step": 2869 }, { "epoch": 0.16764018691588786, "grad_norm": 1.8168246746063232, "learning_rate": 1.902382927447514e-05, "loss": 1.0586, "step": 2870 }, { "epoch": 0.16769859813084112, "grad_norm": 2.6147587299346924, "learning_rate": 1.9023013851936603e-05, "loss": 1.0423, "step": 2871 }, { "epoch": 0.1677570093457944, "grad_norm": 1.7938721179962158, "learning_rate": 1.902219810645847e-05, "loss": 0.6016, "step": 2872 }, { "epoch": 0.16781542056074766, "grad_norm": 3.158048629760742, "learning_rate": 1.9021382038069934e-05, "loss": 1.0078, "step": 2873 }, { "epoch": 0.16787383177570092, "grad_norm": 1.5880217552185059, "learning_rate": 1.9020565646800203e-05, "loss": 0.9717, "step": 2874 }, { "epoch": 0.1679322429906542, "grad_norm": 3.9135935306549072, "learning_rate": 1.9019748932678493e-05, "loss": 0.9322, "step": 2875 }, { "epoch": 0.16799065420560746, "grad_norm": 1.692522644996643, "learning_rate": 1.901893189573404e-05, "loss": 0.8291, "step": 2876 }, { "epoch": 0.16804906542056075, "grad_norm": 1.6413654088974, "learning_rate": 1.9018114535996088e-05, "loss": 0.7179, "step": 2877 }, { "epoch": 0.168107476635514, "grad_norm": 3.5464608669281006, "learning_rate": 1.9017296853493885e-05, "loss": 1.0128, "step": 2878 }, { "epoch": 0.1681658878504673, "grad_norm": 3.3329780101776123, "learning_rate": 1.90164788482567e-05, "loss": 0.8771, "step": 2879 }, { "epoch": 0.16822429906542055, "grad_norm": 1.8678193092346191, "learning_rate": 1.9015660520313805e-05, "loss": 0.9525, "step": 2880 }, { "epoch": 0.16828271028037384, "grad_norm": 1.53624427318573, "learning_rate": 1.9014841869694492e-05, "loss": 0.6904, "step": 2881 }, { "epoch": 0.1683411214953271, "grad_norm": 2.1510210037231445, "learning_rate": 1.9014022896428065e-05, "loss": 0.8425, "step": 2882 }, { "epoch": 0.16839953271028038, "grad_norm": 2.2476296424865723, "learning_rate": 1.901320360054383e-05, "loss": 1.058, "step": 2883 }, { "epoch": 0.16845794392523364, "grad_norm": 1.7763543128967285, "learning_rate": 1.9012383982071112e-05, "loss": 0.88, "step": 2884 }, { "epoch": 0.16851635514018692, "grad_norm": 3.20918345451355, "learning_rate": 1.9011564041039245e-05, "loss": 0.9931, "step": 2885 }, { "epoch": 0.16857476635514018, "grad_norm": 1.917659878730774, "learning_rate": 1.9010743777477575e-05, "loss": 0.9004, "step": 2886 }, { "epoch": 0.16863317757009347, "grad_norm": 5.060914993286133, "learning_rate": 1.9009923191415462e-05, "loss": 1.1019, "step": 2887 }, { "epoch": 0.16869158878504673, "grad_norm": 2.391608476638794, "learning_rate": 1.900910228288227e-05, "loss": 0.917, "step": 2888 }, { "epoch": 0.16875, "grad_norm": 3.293442726135254, "learning_rate": 1.9008281051907392e-05, "loss": 0.776, "step": 2889 }, { "epoch": 0.16880841121495327, "grad_norm": 1.755357265472412, "learning_rate": 1.9007459498520203e-05, "loss": 0.9243, "step": 2890 }, { "epoch": 0.16886682242990655, "grad_norm": 2.055302143096924, "learning_rate": 1.9006637622750125e-05, "loss": 1.05, "step": 2891 }, { "epoch": 0.1689252336448598, "grad_norm": 2.0233352184295654, "learning_rate": 1.9005815424626556e-05, "loss": 0.9619, "step": 2892 }, { "epoch": 0.16898364485981307, "grad_norm": 2.1461801528930664, "learning_rate": 1.900499290417894e-05, "loss": 0.8687, "step": 2893 }, { "epoch": 0.16904205607476636, "grad_norm": 1.4154038429260254, "learning_rate": 1.9004170061436697e-05, "loss": 0.8855, "step": 2894 }, { "epoch": 0.1691004672897196, "grad_norm": 0.9353237748146057, "learning_rate": 1.9003346896429297e-05, "loss": 0.6219, "step": 2895 }, { "epoch": 0.1691588785046729, "grad_norm": 1.5522533655166626, "learning_rate": 1.9002523409186183e-05, "loss": 0.7349, "step": 2896 }, { "epoch": 0.16921728971962616, "grad_norm": 2.1875078678131104, "learning_rate": 1.9001699599736842e-05, "loss": 0.8977, "step": 2897 }, { "epoch": 0.16927570093457944, "grad_norm": 1.6921792030334473, "learning_rate": 1.9000875468110754e-05, "loss": 0.862, "step": 2898 }, { "epoch": 0.1693341121495327, "grad_norm": 2.010180950164795, "learning_rate": 1.9000051014337412e-05, "loss": 0.855, "step": 2899 }, { "epoch": 0.169392523364486, "grad_norm": 2.0920653343200684, "learning_rate": 1.8999226238446328e-05, "loss": 0.912, "step": 2900 }, { "epoch": 0.16945093457943924, "grad_norm": 1.3562511205673218, "learning_rate": 1.899840114046702e-05, "loss": 0.689, "step": 2901 }, { "epoch": 0.16950934579439253, "grad_norm": 1.3577371835708618, "learning_rate": 1.8997575720429017e-05, "loss": 0.7812, "step": 2902 }, { "epoch": 0.1695677570093458, "grad_norm": 1.818321704864502, "learning_rate": 1.8996749978361866e-05, "loss": 0.6557, "step": 2903 }, { "epoch": 0.16962616822429907, "grad_norm": 1.6084909439086914, "learning_rate": 1.8995923914295117e-05, "loss": 0.9534, "step": 2904 }, { "epoch": 0.16968457943925233, "grad_norm": 1.3271608352661133, "learning_rate": 1.8995097528258334e-05, "loss": 0.8243, "step": 2905 }, { "epoch": 0.16974299065420562, "grad_norm": 1.3000597953796387, "learning_rate": 1.89942708202811e-05, "loss": 0.9611, "step": 2906 }, { "epoch": 0.16980140186915887, "grad_norm": 1.2518404722213745, "learning_rate": 1.8993443790392994e-05, "loss": 0.6446, "step": 2907 }, { "epoch": 0.16985981308411216, "grad_norm": 1.9208507537841797, "learning_rate": 1.8992616438623627e-05, "loss": 0.7957, "step": 2908 }, { "epoch": 0.16991822429906542, "grad_norm": 1.3149036169052124, "learning_rate": 1.89917887650026e-05, "loss": 0.9497, "step": 2909 }, { "epoch": 0.1699766355140187, "grad_norm": 1.6991831064224243, "learning_rate": 1.8990960769559542e-05, "loss": 0.9938, "step": 2910 }, { "epoch": 0.17003504672897196, "grad_norm": 1.7541027069091797, "learning_rate": 1.899013245232409e-05, "loss": 0.8293, "step": 2911 }, { "epoch": 0.17009345794392525, "grad_norm": 1.7322813272476196, "learning_rate": 1.8989303813325884e-05, "loss": 0.8766, "step": 2912 }, { "epoch": 0.1701518691588785, "grad_norm": 1.9188417196273804, "learning_rate": 1.8988474852594584e-05, "loss": 1.2613, "step": 2913 }, { "epoch": 0.17021028037383176, "grad_norm": 1.449451208114624, "learning_rate": 1.898764557015986e-05, "loss": 0.8925, "step": 2914 }, { "epoch": 0.17026869158878505, "grad_norm": 1.7625864744186401, "learning_rate": 1.898681596605139e-05, "loss": 0.902, "step": 2915 }, { "epoch": 0.1703271028037383, "grad_norm": 1.4328831434249878, "learning_rate": 1.8985986040298866e-05, "loss": 0.7087, "step": 2916 }, { "epoch": 0.1703855140186916, "grad_norm": 1.4708958864212036, "learning_rate": 1.8985155792931997e-05, "loss": 0.6909, "step": 2917 }, { "epoch": 0.17044392523364485, "grad_norm": 1.3452861309051514, "learning_rate": 1.898432522398049e-05, "loss": 0.8523, "step": 2918 }, { "epoch": 0.17050233644859814, "grad_norm": 1.205212950706482, "learning_rate": 1.898349433347408e-05, "loss": 1.0137, "step": 2919 }, { "epoch": 0.1705607476635514, "grad_norm": 1.7604433298110962, "learning_rate": 1.89826631214425e-05, "loss": 0.9939, "step": 2920 }, { "epoch": 0.17061915887850468, "grad_norm": 1.4913721084594727, "learning_rate": 1.89818315879155e-05, "loss": 1.1408, "step": 2921 }, { "epoch": 0.17067757009345794, "grad_norm": 1.5540409088134766, "learning_rate": 1.898099973292284e-05, "loss": 0.599, "step": 2922 }, { "epoch": 0.17073598130841122, "grad_norm": 1.2559611797332764, "learning_rate": 1.89801675564943e-05, "loss": 0.9005, "step": 2923 }, { "epoch": 0.17079439252336448, "grad_norm": 2.207364797592163, "learning_rate": 1.8979335058659653e-05, "loss": 0.9467, "step": 2924 }, { "epoch": 0.17085280373831777, "grad_norm": 1.0944292545318604, "learning_rate": 1.8978502239448703e-05, "loss": 0.6327, "step": 2925 }, { "epoch": 0.17091121495327102, "grad_norm": 1.3513777256011963, "learning_rate": 1.8977669098891254e-05, "loss": 1.006, "step": 2926 }, { "epoch": 0.1709696261682243, "grad_norm": 1.431241512298584, "learning_rate": 1.8976835637017125e-05, "loss": 0.8425, "step": 2927 }, { "epoch": 0.17102803738317757, "grad_norm": 1.2946900129318237, "learning_rate": 1.8976001853856142e-05, "loss": 0.9029, "step": 2928 }, { "epoch": 0.17108644859813085, "grad_norm": 1.757436990737915, "learning_rate": 1.8975167749438157e-05, "loss": 0.9169, "step": 2929 }, { "epoch": 0.1711448598130841, "grad_norm": 2.1637396812438965, "learning_rate": 1.8974333323793014e-05, "loss": 0.945, "step": 2930 }, { "epoch": 0.1712032710280374, "grad_norm": 1.329927682876587, "learning_rate": 1.8973498576950578e-05, "loss": 0.733, "step": 2931 }, { "epoch": 0.17126168224299065, "grad_norm": 1.4973210096359253, "learning_rate": 1.8972663508940733e-05, "loss": 0.7068, "step": 2932 }, { "epoch": 0.1713200934579439, "grad_norm": 1.683161973953247, "learning_rate": 1.897182811979336e-05, "loss": 0.8311, "step": 2933 }, { "epoch": 0.1713785046728972, "grad_norm": 1.3820596933364868, "learning_rate": 1.897099240953836e-05, "loss": 0.7581, "step": 2934 }, { "epoch": 0.17143691588785046, "grad_norm": 1.2985775470733643, "learning_rate": 1.8970156378205642e-05, "loss": 0.8117, "step": 2935 }, { "epoch": 0.17149532710280374, "grad_norm": 1.8194130659103394, "learning_rate": 1.896932002582513e-05, "loss": 0.9786, "step": 2936 }, { "epoch": 0.171553738317757, "grad_norm": 1.72718346118927, "learning_rate": 1.8968483352426753e-05, "loss": 0.8504, "step": 2937 }, { "epoch": 0.17161214953271028, "grad_norm": 1.7429066896438599, "learning_rate": 1.8967646358040465e-05, "loss": 0.8824, "step": 2938 }, { "epoch": 0.17167056074766354, "grad_norm": 1.5187138319015503, "learning_rate": 1.8966809042696214e-05, "loss": 0.9121, "step": 2939 }, { "epoch": 0.17172897196261683, "grad_norm": 2.0075111389160156, "learning_rate": 1.8965971406423974e-05, "loss": 0.8225, "step": 2940 }, { "epoch": 0.17178738317757009, "grad_norm": 2.483288049697876, "learning_rate": 1.896513344925372e-05, "loss": 0.8402, "step": 2941 }, { "epoch": 0.17184579439252337, "grad_norm": 1.439171314239502, "learning_rate": 1.896429517121545e-05, "loss": 0.9899, "step": 2942 }, { "epoch": 0.17190420560747663, "grad_norm": 1.9548426866531372, "learning_rate": 1.8963456572339155e-05, "loss": 0.9332, "step": 2943 }, { "epoch": 0.17196261682242991, "grad_norm": 1.4884263277053833, "learning_rate": 1.8962617652654858e-05, "loss": 0.6413, "step": 2944 }, { "epoch": 0.17202102803738317, "grad_norm": 2.1592602729797363, "learning_rate": 1.8961778412192583e-05, "loss": 1.0522, "step": 2945 }, { "epoch": 0.17207943925233646, "grad_norm": 1.4967358112335205, "learning_rate": 1.8960938850982368e-05, "loss": 0.9506, "step": 2946 }, { "epoch": 0.17213785046728972, "grad_norm": 2.115034580230713, "learning_rate": 1.8960098969054253e-05, "loss": 0.9001, "step": 2947 }, { "epoch": 0.172196261682243, "grad_norm": 1.1847646236419678, "learning_rate": 1.895925876643831e-05, "loss": 0.8356, "step": 2948 }, { "epoch": 0.17225467289719626, "grad_norm": 1.307210087776184, "learning_rate": 1.8958418243164606e-05, "loss": 0.7288, "step": 2949 }, { "epoch": 0.17231308411214954, "grad_norm": 1.399925947189331, "learning_rate": 1.895757739926322e-05, "loss": 0.7862, "step": 2950 }, { "epoch": 0.1723714953271028, "grad_norm": 1.6798979043960571, "learning_rate": 1.895673623476425e-05, "loss": 0.8997, "step": 2951 }, { "epoch": 0.1724299065420561, "grad_norm": 1.7190409898757935, "learning_rate": 1.8955894749697802e-05, "loss": 0.9177, "step": 2952 }, { "epoch": 0.17248831775700935, "grad_norm": 0.9737632274627686, "learning_rate": 1.895505294409399e-05, "loss": 0.7019, "step": 2953 }, { "epoch": 0.1725467289719626, "grad_norm": 1.46738600730896, "learning_rate": 1.895421081798295e-05, "loss": 0.9583, "step": 2954 }, { "epoch": 0.1726051401869159, "grad_norm": 1.4250766038894653, "learning_rate": 1.895336837139481e-05, "loss": 0.9187, "step": 2955 }, { "epoch": 0.17266355140186915, "grad_norm": 2.2897632122039795, "learning_rate": 1.8952525604359733e-05, "loss": 1.0762, "step": 2956 }, { "epoch": 0.17272196261682243, "grad_norm": 1.1814427375793457, "learning_rate": 1.8951682516907878e-05, "loss": 0.8215, "step": 2957 }, { "epoch": 0.1727803738317757, "grad_norm": 1.772963285446167, "learning_rate": 1.8950839109069422e-05, "loss": 0.7468, "step": 2958 }, { "epoch": 0.17283878504672898, "grad_norm": 1.463577151298523, "learning_rate": 1.8949995380874544e-05, "loss": 0.865, "step": 2959 }, { "epoch": 0.17289719626168223, "grad_norm": 2.8455770015716553, "learning_rate": 1.894915133235345e-05, "loss": 0.8848, "step": 2960 }, { "epoch": 0.17295560747663552, "grad_norm": 1.5424811840057373, "learning_rate": 1.8948306963536345e-05, "loss": 0.8339, "step": 2961 }, { "epoch": 0.17301401869158878, "grad_norm": 2.1540732383728027, "learning_rate": 1.894746227445345e-05, "loss": 0.7834, "step": 2962 }, { "epoch": 0.17307242990654206, "grad_norm": 1.4003952741622925, "learning_rate": 1.8946617265135e-05, "loss": 0.8232, "step": 2963 }, { "epoch": 0.17313084112149532, "grad_norm": 1.2939621210098267, "learning_rate": 1.894577193561123e-05, "loss": 0.7722, "step": 2964 }, { "epoch": 0.1731892523364486, "grad_norm": 1.748508334159851, "learning_rate": 1.89449262859124e-05, "loss": 0.7674, "step": 2965 }, { "epoch": 0.17324766355140186, "grad_norm": 1.8258048295974731, "learning_rate": 1.8944080316068785e-05, "loss": 1.0026, "step": 2966 }, { "epoch": 0.17330607476635515, "grad_norm": 2.25620698928833, "learning_rate": 1.894323402611065e-05, "loss": 0.7499, "step": 2967 }, { "epoch": 0.1733644859813084, "grad_norm": 1.3892138004302979, "learning_rate": 1.8942387416068287e-05, "loss": 0.8198, "step": 2968 }, { "epoch": 0.1734228971962617, "grad_norm": 1.3496294021606445, "learning_rate": 1.8941540485972e-05, "loss": 0.7576, "step": 2969 }, { "epoch": 0.17348130841121495, "grad_norm": 1.5776958465576172, "learning_rate": 1.89406932358521e-05, "loss": 0.9284, "step": 2970 }, { "epoch": 0.17353971962616824, "grad_norm": 1.3954763412475586, "learning_rate": 1.8939845665738912e-05, "loss": 1.0304, "step": 2971 }, { "epoch": 0.1735981308411215, "grad_norm": 2.0665948390960693, "learning_rate": 1.8938997775662766e-05, "loss": 0.8575, "step": 2972 }, { "epoch": 0.17365654205607475, "grad_norm": 1.7309287786483765, "learning_rate": 1.8938149565654015e-05, "loss": 0.7068, "step": 2973 }, { "epoch": 0.17371495327102804, "grad_norm": 1.657002568244934, "learning_rate": 1.8937301035743013e-05, "loss": 0.8482, "step": 2974 }, { "epoch": 0.1737733644859813, "grad_norm": 1.463032603263855, "learning_rate": 1.8936452185960133e-05, "loss": 0.738, "step": 2975 }, { "epoch": 0.17383177570093458, "grad_norm": 2.1967267990112305, "learning_rate": 1.8935603016335752e-05, "loss": 0.8714, "step": 2976 }, { "epoch": 0.17389018691588784, "grad_norm": 1.7615383863449097, "learning_rate": 1.8934753526900262e-05, "loss": 0.8959, "step": 2977 }, { "epoch": 0.17394859813084113, "grad_norm": 3.4544663429260254, "learning_rate": 1.8933903717684067e-05, "loss": 0.9802, "step": 2978 }, { "epoch": 0.17400700934579438, "grad_norm": 1.9804704189300537, "learning_rate": 1.893305358871759e-05, "loss": 0.8121, "step": 2979 }, { "epoch": 0.17406542056074767, "grad_norm": 2.7800800800323486, "learning_rate": 1.8932203140031246e-05, "loss": 0.7941, "step": 2980 }, { "epoch": 0.17412383177570093, "grad_norm": 1.7078585624694824, "learning_rate": 1.893135237165548e-05, "loss": 0.7265, "step": 2981 }, { "epoch": 0.1741822429906542, "grad_norm": 2.9118781089782715, "learning_rate": 1.8930501283620743e-05, "loss": 0.8017, "step": 2982 }, { "epoch": 0.17424065420560747, "grad_norm": 1.601188063621521, "learning_rate": 1.892964987595749e-05, "loss": 0.7991, "step": 2983 }, { "epoch": 0.17429906542056076, "grad_norm": 2.2546157836914062, "learning_rate": 1.8928798148696195e-05, "loss": 0.8756, "step": 2984 }, { "epoch": 0.174357476635514, "grad_norm": 2.402509927749634, "learning_rate": 1.8927946101867348e-05, "loss": 0.9485, "step": 2985 }, { "epoch": 0.1744158878504673, "grad_norm": 1.4197195768356323, "learning_rate": 1.8927093735501437e-05, "loss": 0.9135, "step": 2986 }, { "epoch": 0.17447429906542056, "grad_norm": 2.7720963954925537, "learning_rate": 1.8926241049628972e-05, "loss": 0.8876, "step": 2987 }, { "epoch": 0.17453271028037384, "grad_norm": 2.427856206893921, "learning_rate": 1.892538804428047e-05, "loss": 1.0257, "step": 2988 }, { "epoch": 0.1745911214953271, "grad_norm": 2.801107406616211, "learning_rate": 1.8924534719486463e-05, "loss": 0.7597, "step": 2989 }, { "epoch": 0.1746495327102804, "grad_norm": 1.5761855840682983, "learning_rate": 1.892368107527749e-05, "loss": 0.7268, "step": 2990 }, { "epoch": 0.17470794392523364, "grad_norm": 2.287116765975952, "learning_rate": 1.8922827111684105e-05, "loss": 0.9634, "step": 2991 }, { "epoch": 0.17476635514018693, "grad_norm": 2.0502805709838867, "learning_rate": 1.892197282873687e-05, "loss": 0.6292, "step": 2992 }, { "epoch": 0.1748247663551402, "grad_norm": 2.006371021270752, "learning_rate": 1.8921118226466358e-05, "loss": 0.9207, "step": 2993 }, { "epoch": 0.17488317757009345, "grad_norm": 2.0063765048980713, "learning_rate": 1.892026330490316e-05, "loss": 0.8892, "step": 2994 }, { "epoch": 0.17494158878504673, "grad_norm": 1.23591947555542, "learning_rate": 1.8919408064077872e-05, "loss": 0.7657, "step": 2995 }, { "epoch": 0.175, "grad_norm": 1.709047555923462, "learning_rate": 1.8918552504021108e-05, "loss": 0.6611, "step": 2996 }, { "epoch": 0.17505841121495327, "grad_norm": 1.2365247011184692, "learning_rate": 1.8917696624763485e-05, "loss": 0.7942, "step": 2997 }, { "epoch": 0.17511682242990653, "grad_norm": 1.8931258916854858, "learning_rate": 1.8916840426335637e-05, "loss": 0.9095, "step": 2998 }, { "epoch": 0.17517523364485982, "grad_norm": 1.700862169265747, "learning_rate": 1.891598390876821e-05, "loss": 0.9874, "step": 2999 }, { "epoch": 0.17523364485981308, "grad_norm": 1.2932155132293701, "learning_rate": 1.8915127072091853e-05, "loss": 0.8471, "step": 3000 }, { "epoch": 0.17529205607476636, "grad_norm": 1.7869502305984497, "learning_rate": 1.8914269916337232e-05, "loss": 1.0001, "step": 3001 }, { "epoch": 0.17535046728971962, "grad_norm": 2.887511968612671, "learning_rate": 1.8913412441535037e-05, "loss": 0.8733, "step": 3002 }, { "epoch": 0.1754088785046729, "grad_norm": 1.4090012311935425, "learning_rate": 1.8912554647715947e-05, "loss": 0.8244, "step": 3003 }, { "epoch": 0.17546728971962616, "grad_norm": 2.520334005355835, "learning_rate": 1.8911696534910664e-05, "loss": 0.8139, "step": 3004 }, { "epoch": 0.17552570093457945, "grad_norm": 1.3686200380325317, "learning_rate": 1.8910838103149903e-05, "loss": 0.8335, "step": 3005 }, { "epoch": 0.1755841121495327, "grad_norm": 1.2268885374069214, "learning_rate": 1.890997935246439e-05, "loss": 0.8549, "step": 3006 }, { "epoch": 0.175642523364486, "grad_norm": 1.9571624994277954, "learning_rate": 1.8909120282884857e-05, "loss": 0.8728, "step": 3007 }, { "epoch": 0.17570093457943925, "grad_norm": 1.4283238649368286, "learning_rate": 1.890826089444205e-05, "loss": 0.8056, "step": 3008 }, { "epoch": 0.17575934579439254, "grad_norm": 1.790759563446045, "learning_rate": 1.890740118716673e-05, "loss": 0.8503, "step": 3009 }, { "epoch": 0.1758177570093458, "grad_norm": 2.140559434890747, "learning_rate": 1.8906541161089663e-05, "loss": 0.9751, "step": 3010 }, { "epoch": 0.17587616822429908, "grad_norm": 1.2718913555145264, "learning_rate": 1.8905680816241632e-05, "loss": 0.8632, "step": 3011 }, { "epoch": 0.17593457943925234, "grad_norm": 1.7935080528259277, "learning_rate": 1.890482015265343e-05, "loss": 1.0256, "step": 3012 }, { "epoch": 0.1759929906542056, "grad_norm": 1.4394365549087524, "learning_rate": 1.8903959170355858e-05, "loss": 0.6243, "step": 3013 }, { "epoch": 0.17605140186915888, "grad_norm": 1.4124715328216553, "learning_rate": 1.8903097869379733e-05, "loss": 0.7896, "step": 3014 }, { "epoch": 0.17610981308411214, "grad_norm": 1.6412646770477295, "learning_rate": 1.890223624975588e-05, "loss": 0.852, "step": 3015 }, { "epoch": 0.17616822429906542, "grad_norm": 1.5108529329299927, "learning_rate": 1.8901374311515144e-05, "loss": 1.0899, "step": 3016 }, { "epoch": 0.17622663551401868, "grad_norm": 1.4146748781204224, "learning_rate": 1.8900512054688366e-05, "loss": 0.6401, "step": 3017 }, { "epoch": 0.17628504672897197, "grad_norm": 1.2822321653366089, "learning_rate": 1.8899649479306406e-05, "loss": 0.727, "step": 3018 }, { "epoch": 0.17634345794392522, "grad_norm": 1.7733465433120728, "learning_rate": 1.889878658540014e-05, "loss": 0.8477, "step": 3019 }, { "epoch": 0.1764018691588785, "grad_norm": 1.7896555662155151, "learning_rate": 1.8897923373000452e-05, "loss": 0.9209, "step": 3020 }, { "epoch": 0.17646028037383177, "grad_norm": 1.3425629138946533, "learning_rate": 1.889705984213824e-05, "loss": 0.8659, "step": 3021 }, { "epoch": 0.17651869158878505, "grad_norm": 1.478243350982666, "learning_rate": 1.88961959928444e-05, "loss": 0.7779, "step": 3022 }, { "epoch": 0.1765771028037383, "grad_norm": 1.5210562944412231, "learning_rate": 1.889533182514986e-05, "loss": 0.831, "step": 3023 }, { "epoch": 0.1766355140186916, "grad_norm": 1.154624104499817, "learning_rate": 1.8894467339085544e-05, "loss": 0.718, "step": 3024 }, { "epoch": 0.17669392523364486, "grad_norm": 1.218605399131775, "learning_rate": 1.8893602534682396e-05, "loss": 0.7932, "step": 3025 }, { "epoch": 0.17675233644859814, "grad_norm": 1.7254328727722168, "learning_rate": 1.8892737411971365e-05, "loss": 0.8928, "step": 3026 }, { "epoch": 0.1768107476635514, "grad_norm": 1.854783058166504, "learning_rate": 1.889187197098341e-05, "loss": 1.0481, "step": 3027 }, { "epoch": 0.17686915887850468, "grad_norm": 1.354649305343628, "learning_rate": 1.8891006211749515e-05, "loss": 0.6674, "step": 3028 }, { "epoch": 0.17692757009345794, "grad_norm": 2.0310497283935547, "learning_rate": 1.8890140134300662e-05, "loss": 0.8285, "step": 3029 }, { "epoch": 0.17698598130841123, "grad_norm": 1.374139666557312, "learning_rate": 1.888927373866785e-05, "loss": 0.9033, "step": 3030 }, { "epoch": 0.17704439252336449, "grad_norm": 1.8692264556884766, "learning_rate": 1.8888407024882084e-05, "loss": 0.8696, "step": 3031 }, { "epoch": 0.17710280373831774, "grad_norm": 1.4057053327560425, "learning_rate": 1.888753999297438e-05, "loss": 0.9677, "step": 3032 }, { "epoch": 0.17716121495327103, "grad_norm": 1.552606225013733, "learning_rate": 1.8886672642975785e-05, "loss": 0.8569, "step": 3033 }, { "epoch": 0.1772196261682243, "grad_norm": 1.2505834102630615, "learning_rate": 1.888580497491733e-05, "loss": 0.803, "step": 3034 }, { "epoch": 0.17727803738317757, "grad_norm": 1.218161940574646, "learning_rate": 1.8884936988830072e-05, "loss": 0.6725, "step": 3035 }, { "epoch": 0.17733644859813083, "grad_norm": 2.1134769916534424, "learning_rate": 1.8884068684745077e-05, "loss": 0.9465, "step": 3036 }, { "epoch": 0.17739485981308412, "grad_norm": 2.735092878341675, "learning_rate": 1.8883200062693424e-05, "loss": 1.0415, "step": 3037 }, { "epoch": 0.17745327102803737, "grad_norm": 1.324831247329712, "learning_rate": 1.8882331122706196e-05, "loss": 0.7768, "step": 3038 }, { "epoch": 0.17751168224299066, "grad_norm": 1.6522561311721802, "learning_rate": 1.88814618648145e-05, "loss": 0.8821, "step": 3039 }, { "epoch": 0.17757009345794392, "grad_norm": 2.39347243309021, "learning_rate": 1.8880592289049443e-05, "loss": 0.6883, "step": 3040 }, { "epoch": 0.1776285046728972, "grad_norm": 2.939546823501587, "learning_rate": 1.887972239544215e-05, "loss": 0.8129, "step": 3041 }, { "epoch": 0.17768691588785046, "grad_norm": 2.0355443954467773, "learning_rate": 1.8878852184023754e-05, "loss": 0.9002, "step": 3042 }, { "epoch": 0.17774532710280375, "grad_norm": 2.0024681091308594, "learning_rate": 1.88779816548254e-05, "loss": 0.8883, "step": 3043 }, { "epoch": 0.177803738317757, "grad_norm": 2.0871269702911377, "learning_rate": 1.8877110807878246e-05, "loss": 0.7166, "step": 3044 }, { "epoch": 0.1778621495327103, "grad_norm": 1.787264347076416, "learning_rate": 1.8876239643213456e-05, "loss": 0.8442, "step": 3045 }, { "epoch": 0.17792056074766355, "grad_norm": 0.9127650260925293, "learning_rate": 1.8875368160862217e-05, "loss": 0.6991, "step": 3046 }, { "epoch": 0.17797897196261683, "grad_norm": 3.1178579330444336, "learning_rate": 1.8874496360855713e-05, "loss": 1.0163, "step": 3047 }, { "epoch": 0.1780373831775701, "grad_norm": 2.5720207691192627, "learning_rate": 1.887362424322515e-05, "loss": 0.6265, "step": 3048 }, { "epoch": 0.17809579439252338, "grad_norm": 2.668975591659546, "learning_rate": 1.8872751808001743e-05, "loss": 0.7125, "step": 3049 }, { "epoch": 0.17815420560747663, "grad_norm": 1.5562894344329834, "learning_rate": 1.887187905521671e-05, "loss": 0.7227, "step": 3050 }, { "epoch": 0.17821261682242992, "grad_norm": 2.8841724395751953, "learning_rate": 1.8871005984901298e-05, "loss": 0.9855, "step": 3051 }, { "epoch": 0.17827102803738318, "grad_norm": 3.312305212020874, "learning_rate": 1.8870132597086747e-05, "loss": 0.998, "step": 3052 }, { "epoch": 0.17832943925233644, "grad_norm": 2.2304463386535645, "learning_rate": 1.8869258891804318e-05, "loss": 0.9752, "step": 3053 }, { "epoch": 0.17838785046728972, "grad_norm": 2.057133913040161, "learning_rate": 1.8868384869085277e-05, "loss": 0.9128, "step": 3054 }, { "epoch": 0.17844626168224298, "grad_norm": 1.3696492910385132, "learning_rate": 1.8867510528960914e-05, "loss": 0.8312, "step": 3055 }, { "epoch": 0.17850467289719626, "grad_norm": 1.3626734018325806, "learning_rate": 1.886663587146252e-05, "loss": 0.8063, "step": 3056 }, { "epoch": 0.17856308411214952, "grad_norm": 3.0417420864105225, "learning_rate": 1.88657608966214e-05, "loss": 0.8577, "step": 3057 }, { "epoch": 0.1786214953271028, "grad_norm": 1.5759180784225464, "learning_rate": 1.8864885604468863e-05, "loss": 0.8202, "step": 3058 }, { "epoch": 0.17867990654205607, "grad_norm": 2.2562665939331055, "learning_rate": 1.8864009995036246e-05, "loss": 0.8175, "step": 3059 }, { "epoch": 0.17873831775700935, "grad_norm": 2.503028631210327, "learning_rate": 1.886313406835488e-05, "loss": 0.8121, "step": 3060 }, { "epoch": 0.1787967289719626, "grad_norm": 2.5989060401916504, "learning_rate": 1.886225782445612e-05, "loss": 0.9165, "step": 3061 }, { "epoch": 0.1788551401869159, "grad_norm": 1.9711834192276, "learning_rate": 1.8861381263371322e-05, "loss": 0.8655, "step": 3062 }, { "epoch": 0.17891355140186915, "grad_norm": 2.4742720127105713, "learning_rate": 1.8860504385131865e-05, "loss": 0.9554, "step": 3063 }, { "epoch": 0.17897196261682244, "grad_norm": 1.4672781229019165, "learning_rate": 1.8859627189769128e-05, "loss": 0.8422, "step": 3064 }, { "epoch": 0.1790303738317757, "grad_norm": 1.4518777132034302, "learning_rate": 1.8858749677314514e-05, "loss": 0.8385, "step": 3065 }, { "epoch": 0.17908878504672898, "grad_norm": 2.248915672302246, "learning_rate": 1.885787184779942e-05, "loss": 1.0362, "step": 3066 }, { "epoch": 0.17914719626168224, "grad_norm": 1.509896159172058, "learning_rate": 1.885699370125527e-05, "loss": 0.9854, "step": 3067 }, { "epoch": 0.17920560747663553, "grad_norm": 1.7324622869491577, "learning_rate": 1.885611523771349e-05, "loss": 0.8493, "step": 3068 }, { "epoch": 0.17926401869158878, "grad_norm": 2.022153377532959, "learning_rate": 1.8855236457205522e-05, "loss": 0.823, "step": 3069 }, { "epoch": 0.17932242990654207, "grad_norm": 1.7333794832229614, "learning_rate": 1.885435735976282e-05, "loss": 0.8768, "step": 3070 }, { "epoch": 0.17938084112149533, "grad_norm": 1.5203334093093872, "learning_rate": 1.885347794541685e-05, "loss": 0.954, "step": 3071 }, { "epoch": 0.17943925233644858, "grad_norm": 3.6685569286346436, "learning_rate": 1.885259821419908e-05, "loss": 0.9949, "step": 3072 }, { "epoch": 0.17949766355140187, "grad_norm": 1.688637614250183, "learning_rate": 1.8851718166140997e-05, "loss": 0.7453, "step": 3073 }, { "epoch": 0.17955607476635513, "grad_norm": 3.2581214904785156, "learning_rate": 1.8850837801274103e-05, "loss": 0.8172, "step": 3074 }, { "epoch": 0.1796144859813084, "grad_norm": 3.5004870891571045, "learning_rate": 1.8849957119629905e-05, "loss": 0.9492, "step": 3075 }, { "epoch": 0.17967289719626167, "grad_norm": 2.5155715942382812, "learning_rate": 1.884907612123992e-05, "loss": 0.876, "step": 3076 }, { "epoch": 0.17973130841121496, "grad_norm": 1.9268101453781128, "learning_rate": 1.8848194806135683e-05, "loss": 1.028, "step": 3077 }, { "epoch": 0.17978971962616822, "grad_norm": 1.6389918327331543, "learning_rate": 1.884731317434874e-05, "loss": 0.7684, "step": 3078 }, { "epoch": 0.1798481308411215, "grad_norm": 1.9606497287750244, "learning_rate": 1.8846431225910637e-05, "loss": 0.8027, "step": 3079 }, { "epoch": 0.17990654205607476, "grad_norm": 1.500134825706482, "learning_rate": 1.8845548960852948e-05, "loss": 0.8664, "step": 3080 }, { "epoch": 0.17996495327102804, "grad_norm": 1.5937507152557373, "learning_rate": 1.8844666379207238e-05, "loss": 0.8038, "step": 3081 }, { "epoch": 0.1800233644859813, "grad_norm": 1.4830513000488281, "learning_rate": 1.884378348100511e-05, "loss": 1.0178, "step": 3082 }, { "epoch": 0.1800817757009346, "grad_norm": 1.4580334424972534, "learning_rate": 1.884290026627815e-05, "loss": 0.767, "step": 3083 }, { "epoch": 0.18014018691588785, "grad_norm": 1.552445888519287, "learning_rate": 1.8842016735057984e-05, "loss": 0.7872, "step": 3084 }, { "epoch": 0.18019859813084113, "grad_norm": 1.717811942100525, "learning_rate": 1.8841132887376218e-05, "loss": 0.9245, "step": 3085 }, { "epoch": 0.1802570093457944, "grad_norm": 2.337658643722534, "learning_rate": 1.8840248723264497e-05, "loss": 0.9033, "step": 3086 }, { "epoch": 0.18031542056074767, "grad_norm": 1.8609312772750854, "learning_rate": 1.8839364242754458e-05, "loss": 1.0264, "step": 3087 }, { "epoch": 0.18037383177570093, "grad_norm": 1.4400874376296997, "learning_rate": 1.8838479445877766e-05, "loss": 1.0066, "step": 3088 }, { "epoch": 0.18043224299065422, "grad_norm": 1.5758366584777832, "learning_rate": 1.8837594332666075e-05, "loss": 0.8267, "step": 3089 }, { "epoch": 0.18049065420560748, "grad_norm": 2.1047003269195557, "learning_rate": 1.883670890315108e-05, "loss": 1.0488, "step": 3090 }, { "epoch": 0.18054906542056076, "grad_norm": 1.132633090019226, "learning_rate": 1.883582315736446e-05, "loss": 0.7138, "step": 3091 }, { "epoch": 0.18060747663551402, "grad_norm": 2.9465103149414062, "learning_rate": 1.8834937095337918e-05, "loss": 0.8017, "step": 3092 }, { "epoch": 0.18066588785046728, "grad_norm": 1.4209855794906616, "learning_rate": 1.8834050717103168e-05, "loss": 0.7849, "step": 3093 }, { "epoch": 0.18072429906542056, "grad_norm": 1.6786470413208008, "learning_rate": 1.8833164022691937e-05, "loss": 0.8283, "step": 3094 }, { "epoch": 0.18078271028037382, "grad_norm": 1.391873836517334, "learning_rate": 1.883227701213596e-05, "loss": 0.6749, "step": 3095 }, { "epoch": 0.1808411214953271, "grad_norm": 1.531596064567566, "learning_rate": 1.8831389685466976e-05, "loss": 0.9336, "step": 3096 }, { "epoch": 0.18089953271028036, "grad_norm": 1.3979434967041016, "learning_rate": 1.8830502042716753e-05, "loss": 0.9563, "step": 3097 }, { "epoch": 0.18095794392523365, "grad_norm": 1.7459933757781982, "learning_rate": 1.882961408391705e-05, "loss": 0.791, "step": 3098 }, { "epoch": 0.1810163551401869, "grad_norm": 2.3408362865448, "learning_rate": 1.8828725809099657e-05, "loss": 1.0122, "step": 3099 }, { "epoch": 0.1810747663551402, "grad_norm": 1.2304013967514038, "learning_rate": 1.882783721829636e-05, "loss": 0.8173, "step": 3100 }, { "epoch": 0.18113317757009345, "grad_norm": 2.4377903938293457, "learning_rate": 1.8826948311538968e-05, "loss": 0.9012, "step": 3101 }, { "epoch": 0.18119158878504674, "grad_norm": 1.582580804824829, "learning_rate": 1.8826059088859293e-05, "loss": 0.8523, "step": 3102 }, { "epoch": 0.18125, "grad_norm": 2.240889310836792, "learning_rate": 1.8825169550289156e-05, "loss": 1.0491, "step": 3103 }, { "epoch": 0.18130841121495328, "grad_norm": 1.1599016189575195, "learning_rate": 1.88242796958604e-05, "loss": 0.621, "step": 3104 }, { "epoch": 0.18136682242990654, "grad_norm": 1.2676509618759155, "learning_rate": 1.882338952560487e-05, "loss": 0.9197, "step": 3105 }, { "epoch": 0.18142523364485982, "grad_norm": 1.826957106590271, "learning_rate": 1.8822499039554428e-05, "loss": 0.9, "step": 3106 }, { "epoch": 0.18148364485981308, "grad_norm": 1.173315405845642, "learning_rate": 1.8821608237740947e-05, "loss": 0.7957, "step": 3107 }, { "epoch": 0.18154205607476637, "grad_norm": 1.8277426958084106, "learning_rate": 1.8820717120196304e-05, "loss": 0.8612, "step": 3108 }, { "epoch": 0.18160046728971962, "grad_norm": 1.457889199256897, "learning_rate": 1.8819825686952398e-05, "loss": 1.0309, "step": 3109 }, { "epoch": 0.1816588785046729, "grad_norm": 1.1942168474197388, "learning_rate": 1.881893393804113e-05, "loss": 0.8954, "step": 3110 }, { "epoch": 0.18171728971962617, "grad_norm": 1.7752013206481934, "learning_rate": 1.8818041873494416e-05, "loss": 0.9087, "step": 3111 }, { "epoch": 0.18177570093457943, "grad_norm": 1.404739499092102, "learning_rate": 1.881714949334419e-05, "loss": 0.8653, "step": 3112 }, { "epoch": 0.1818341121495327, "grad_norm": 1.148690104484558, "learning_rate": 1.8816256797622382e-05, "loss": 0.8714, "step": 3113 }, { "epoch": 0.18189252336448597, "grad_norm": 2.0831546783447266, "learning_rate": 1.8815363786360948e-05, "loss": 0.8886, "step": 3114 }, { "epoch": 0.18195093457943926, "grad_norm": 1.7137947082519531, "learning_rate": 1.8814470459591846e-05, "loss": 0.8373, "step": 3115 }, { "epoch": 0.1820093457943925, "grad_norm": 2.2688896656036377, "learning_rate": 1.881357681734705e-05, "loss": 1.0101, "step": 3116 }, { "epoch": 0.1820677570093458, "grad_norm": 1.9593212604522705, "learning_rate": 1.881268285965855e-05, "loss": 1.0321, "step": 3117 }, { "epoch": 0.18212616822429906, "grad_norm": 1.3524625301361084, "learning_rate": 1.8811788586558334e-05, "loss": 0.8228, "step": 3118 }, { "epoch": 0.18218457943925234, "grad_norm": 2.1811633110046387, "learning_rate": 1.881089399807841e-05, "loss": 0.9247, "step": 3119 }, { "epoch": 0.1822429906542056, "grad_norm": 1.2708607912063599, "learning_rate": 1.8809999094250794e-05, "loss": 0.8442, "step": 3120 }, { "epoch": 0.18230140186915889, "grad_norm": 1.4510385990142822, "learning_rate": 1.8809103875107523e-05, "loss": 0.8145, "step": 3121 }, { "epoch": 0.18235981308411214, "grad_norm": 1.45816171169281, "learning_rate": 1.8808208340680628e-05, "loss": 0.8515, "step": 3122 }, { "epoch": 0.18241822429906543, "grad_norm": 1.1380784511566162, "learning_rate": 1.8807312491002165e-05, "loss": 0.7826, "step": 3123 }, { "epoch": 0.1824766355140187, "grad_norm": 1.9220956563949585, "learning_rate": 1.88064163261042e-05, "loss": 0.8514, "step": 3124 }, { "epoch": 0.18253504672897197, "grad_norm": 1.7159873247146606, "learning_rate": 1.88055198460188e-05, "loss": 0.943, "step": 3125 }, { "epoch": 0.18259345794392523, "grad_norm": 1.1032053232192993, "learning_rate": 1.880462305077806e-05, "loss": 0.764, "step": 3126 }, { "epoch": 0.18265186915887852, "grad_norm": 2.134645462036133, "learning_rate": 1.8803725940414067e-05, "loss": 0.8473, "step": 3127 }, { "epoch": 0.18271028037383177, "grad_norm": 1.8888685703277588, "learning_rate": 1.8802828514958938e-05, "loss": 0.9746, "step": 3128 }, { "epoch": 0.18276869158878506, "grad_norm": 1.6274069547653198, "learning_rate": 1.8801930774444788e-05, "loss": 0.983, "step": 3129 }, { "epoch": 0.18282710280373832, "grad_norm": 1.9689754247665405, "learning_rate": 1.8801032718903743e-05, "loss": 0.9207, "step": 3130 }, { "epoch": 0.18288551401869158, "grad_norm": 1.2577698230743408, "learning_rate": 1.8800134348367954e-05, "loss": 0.7959, "step": 3131 }, { "epoch": 0.18294392523364486, "grad_norm": 1.6130810976028442, "learning_rate": 1.8799235662869574e-05, "loss": 0.8851, "step": 3132 }, { "epoch": 0.18300233644859812, "grad_norm": 7.8774919509887695, "learning_rate": 1.8798336662440762e-05, "loss": 0.946, "step": 3133 }, { "epoch": 0.1830607476635514, "grad_norm": 1.4259587526321411, "learning_rate": 1.879743734711369e-05, "loss": 0.7492, "step": 3134 }, { "epoch": 0.18311915887850466, "grad_norm": 1.1184704303741455, "learning_rate": 1.879653771692056e-05, "loss": 0.7374, "step": 3135 }, { "epoch": 0.18317757009345795, "grad_norm": 2.1413142681121826, "learning_rate": 1.8795637771893554e-05, "loss": 0.9491, "step": 3136 }, { "epoch": 0.1832359813084112, "grad_norm": 1.9222204685211182, "learning_rate": 1.879473751206489e-05, "loss": 1.0482, "step": 3137 }, { "epoch": 0.1832943925233645, "grad_norm": 1.2620906829833984, "learning_rate": 1.879383693746679e-05, "loss": 0.9199, "step": 3138 }, { "epoch": 0.18335280373831775, "grad_norm": 1.7844816446304321, "learning_rate": 1.8792936048131484e-05, "loss": 0.7418, "step": 3139 }, { "epoch": 0.18341121495327103, "grad_norm": 1.5056521892547607, "learning_rate": 1.8792034844091217e-05, "loss": 0.9684, "step": 3140 }, { "epoch": 0.1834696261682243, "grad_norm": 1.543994426727295, "learning_rate": 1.8791133325378238e-05, "loss": 0.8387, "step": 3141 }, { "epoch": 0.18352803738317758, "grad_norm": 1.624045729637146, "learning_rate": 1.879023149202482e-05, "loss": 1.0022, "step": 3142 }, { "epoch": 0.18358644859813084, "grad_norm": 1.7809995412826538, "learning_rate": 1.8789329344063234e-05, "loss": 0.887, "step": 3143 }, { "epoch": 0.18364485981308412, "grad_norm": 3.2794864177703857, "learning_rate": 1.8788426881525774e-05, "loss": 0.9577, "step": 3144 }, { "epoch": 0.18370327102803738, "grad_norm": 1.90341055393219, "learning_rate": 1.8787524104444737e-05, "loss": 0.9782, "step": 3145 }, { "epoch": 0.18376168224299066, "grad_norm": 1.4047433137893677, "learning_rate": 1.878662101285244e-05, "loss": 0.8072, "step": 3146 }, { "epoch": 0.18382009345794392, "grad_norm": 2.3645286560058594, "learning_rate": 1.8785717606781188e-05, "loss": 0.781, "step": 3147 }, { "epoch": 0.1838785046728972, "grad_norm": 1.2934448719024658, "learning_rate": 1.8784813886263335e-05, "loss": 0.7126, "step": 3148 }, { "epoch": 0.18393691588785047, "grad_norm": 1.8742786645889282, "learning_rate": 1.8783909851331215e-05, "loss": 0.8254, "step": 3149 }, { "epoch": 0.18399532710280375, "grad_norm": 1.333528757095337, "learning_rate": 1.8783005502017183e-05, "loss": 0.8888, "step": 3150 }, { "epoch": 0.184053738317757, "grad_norm": 1.3653874397277832, "learning_rate": 1.878210083835361e-05, "loss": 0.7777, "step": 3151 }, { "epoch": 0.18411214953271027, "grad_norm": 1.5885752439498901, "learning_rate": 1.8781195860372875e-05, "loss": 0.8266, "step": 3152 }, { "epoch": 0.18417056074766355, "grad_norm": 1.720741629600525, "learning_rate": 1.878029056810737e-05, "loss": 0.6707, "step": 3153 }, { "epoch": 0.1842289719626168, "grad_norm": 1.5687590837478638, "learning_rate": 1.8779384961589486e-05, "loss": 1.1411, "step": 3154 }, { "epoch": 0.1842873831775701, "grad_norm": 1.7243733406066895, "learning_rate": 1.8778479040851646e-05, "loss": 0.8432, "step": 3155 }, { "epoch": 0.18434579439252335, "grad_norm": 1.490924596786499, "learning_rate": 1.8777572805926267e-05, "loss": 0.8566, "step": 3156 }, { "epoch": 0.18440420560747664, "grad_norm": 1.3106447458267212, "learning_rate": 1.8776666256845787e-05, "loss": 0.8021, "step": 3157 }, { "epoch": 0.1844626168224299, "grad_norm": 2.257754325866699, "learning_rate": 1.877575939364265e-05, "loss": 1.1077, "step": 3158 }, { "epoch": 0.18452102803738318, "grad_norm": 1.3398709297180176, "learning_rate": 1.8774852216349312e-05, "loss": 0.8354, "step": 3159 }, { "epoch": 0.18457943925233644, "grad_norm": 2.2010254859924316, "learning_rate": 1.8773944724998248e-05, "loss": 0.8343, "step": 3160 }, { "epoch": 0.18463785046728973, "grad_norm": 1.5966691970825195, "learning_rate": 1.877303691962193e-05, "loss": 0.892, "step": 3161 }, { "epoch": 0.18469626168224298, "grad_norm": 1.1964352130889893, "learning_rate": 1.8772128800252855e-05, "loss": 0.9262, "step": 3162 }, { "epoch": 0.18475467289719627, "grad_norm": 1.4315851926803589, "learning_rate": 1.8771220366923518e-05, "loss": 0.7185, "step": 3163 }, { "epoch": 0.18481308411214953, "grad_norm": 1.0969582796096802, "learning_rate": 1.8770311619666443e-05, "loss": 0.758, "step": 3164 }, { "epoch": 0.1848714953271028, "grad_norm": 1.402584433555603, "learning_rate": 1.8769402558514144e-05, "loss": 0.9042, "step": 3165 }, { "epoch": 0.18492990654205607, "grad_norm": 1.6157066822052002, "learning_rate": 1.8768493183499164e-05, "loss": 0.9612, "step": 3166 }, { "epoch": 0.18498831775700936, "grad_norm": 1.5063344240188599, "learning_rate": 1.8767583494654044e-05, "loss": 0.7476, "step": 3167 }, { "epoch": 0.18504672897196262, "grad_norm": 1.5242093801498413, "learning_rate": 1.8766673492011353e-05, "loss": 0.8492, "step": 3168 }, { "epoch": 0.1851051401869159, "grad_norm": 1.298348069190979, "learning_rate": 1.8765763175603646e-05, "loss": 0.9153, "step": 3169 }, { "epoch": 0.18516355140186916, "grad_norm": 1.5277605056762695, "learning_rate": 1.8764852545463515e-05, "loss": 0.7343, "step": 3170 }, { "epoch": 0.18522196261682242, "grad_norm": 1.4077926874160767, "learning_rate": 1.876394160162355e-05, "loss": 0.8205, "step": 3171 }, { "epoch": 0.1852803738317757, "grad_norm": 1.0477467775344849, "learning_rate": 1.8763030344116346e-05, "loss": 0.8505, "step": 3172 }, { "epoch": 0.18533878504672896, "grad_norm": 1.7988367080688477, "learning_rate": 1.8762118772974533e-05, "loss": 1.0018, "step": 3173 }, { "epoch": 0.18539719626168225, "grad_norm": 1.4175894260406494, "learning_rate": 1.876120688823072e-05, "loss": 0.971, "step": 3174 }, { "epoch": 0.1854556074766355, "grad_norm": 1.2541594505310059, "learning_rate": 1.8760294689917556e-05, "loss": 0.747, "step": 3175 }, { "epoch": 0.1855140186915888, "grad_norm": 1.883185625076294, "learning_rate": 1.8759382178067684e-05, "loss": 0.9807, "step": 3176 }, { "epoch": 0.18557242990654205, "grad_norm": 1.5258753299713135, "learning_rate": 1.8758469352713767e-05, "loss": 1.064, "step": 3177 }, { "epoch": 0.18563084112149533, "grad_norm": 1.3784486055374146, "learning_rate": 1.875755621388847e-05, "loss": 1.1001, "step": 3178 }, { "epoch": 0.1856892523364486, "grad_norm": 1.2371197938919067, "learning_rate": 1.8756642761624478e-05, "loss": 0.9044, "step": 3179 }, { "epoch": 0.18574766355140188, "grad_norm": 1.8460708856582642, "learning_rate": 1.8755728995954486e-05, "loss": 1.0323, "step": 3180 }, { "epoch": 0.18580607476635513, "grad_norm": 1.0431056022644043, "learning_rate": 1.8754814916911194e-05, "loss": 0.8068, "step": 3181 }, { "epoch": 0.18586448598130842, "grad_norm": 2.2770678997039795, "learning_rate": 1.875390052452732e-05, "loss": 0.9711, "step": 3182 }, { "epoch": 0.18592289719626168, "grad_norm": 1.472814917564392, "learning_rate": 1.875298581883559e-05, "loss": 0.9998, "step": 3183 }, { "epoch": 0.18598130841121496, "grad_norm": 1.8966050148010254, "learning_rate": 1.8752070799868744e-05, "loss": 0.8228, "step": 3184 }, { "epoch": 0.18603971962616822, "grad_norm": 1.251752257347107, "learning_rate": 1.875115546765953e-05, "loss": 0.7287, "step": 3185 }, { "epoch": 0.1860981308411215, "grad_norm": 1.5648952722549438, "learning_rate": 1.8750239822240705e-05, "loss": 0.8154, "step": 3186 }, { "epoch": 0.18615654205607476, "grad_norm": 1.4098289012908936, "learning_rate": 1.8749323863645045e-05, "loss": 0.9063, "step": 3187 }, { "epoch": 0.18621495327102805, "grad_norm": 1.8165135383605957, "learning_rate": 1.874840759190533e-05, "loss": 0.9633, "step": 3188 }, { "epoch": 0.1862733644859813, "grad_norm": 1.4232295751571655, "learning_rate": 1.8747491007054356e-05, "loss": 0.789, "step": 3189 }, { "epoch": 0.1863317757009346, "grad_norm": 1.621295690536499, "learning_rate": 1.874657410912493e-05, "loss": 0.9433, "step": 3190 }, { "epoch": 0.18639018691588785, "grad_norm": 1.6011018753051758, "learning_rate": 1.8745656898149863e-05, "loss": 0.974, "step": 3191 }, { "epoch": 0.1864485981308411, "grad_norm": 1.0958430767059326, "learning_rate": 1.8744739374161985e-05, "loss": 0.6614, "step": 3192 }, { "epoch": 0.1865070093457944, "grad_norm": 2.092965841293335, "learning_rate": 1.8743821537194135e-05, "loss": 0.8544, "step": 3193 }, { "epoch": 0.18656542056074765, "grad_norm": 1.2221457958221436, "learning_rate": 1.8742903387279165e-05, "loss": 0.8844, "step": 3194 }, { "epoch": 0.18662383177570094, "grad_norm": 1.3910149335861206, "learning_rate": 1.8741984924449933e-05, "loss": 0.926, "step": 3195 }, { "epoch": 0.1866822429906542, "grad_norm": 1.5501834154129028, "learning_rate": 1.8741066148739314e-05, "loss": 0.9317, "step": 3196 }, { "epoch": 0.18674065420560748, "grad_norm": 1.4112765789031982, "learning_rate": 1.8740147060180185e-05, "loss": 0.9369, "step": 3197 }, { "epoch": 0.18679906542056074, "grad_norm": 1.2079280614852905, "learning_rate": 1.873922765880545e-05, "loss": 0.7876, "step": 3198 }, { "epoch": 0.18685747663551402, "grad_norm": 1.462408423423767, "learning_rate": 1.873830794464801e-05, "loss": 0.9972, "step": 3199 }, { "epoch": 0.18691588785046728, "grad_norm": 1.9002128839492798, "learning_rate": 1.8737387917740783e-05, "loss": 0.7825, "step": 3200 }, { "epoch": 0.18697429906542057, "grad_norm": 1.3507280349731445, "learning_rate": 1.87364675781167e-05, "loss": 0.8945, "step": 3201 }, { "epoch": 0.18703271028037383, "grad_norm": 1.057129979133606, "learning_rate": 1.8735546925808695e-05, "loss": 0.7536, "step": 3202 }, { "epoch": 0.1870911214953271, "grad_norm": 2.588361978530884, "learning_rate": 1.873462596084972e-05, "loss": 0.8706, "step": 3203 }, { "epoch": 0.18714953271028037, "grad_norm": 1.3952234983444214, "learning_rate": 1.8733704683272745e-05, "loss": 1.0326, "step": 3204 }, { "epoch": 0.18720794392523366, "grad_norm": 2.4438657760620117, "learning_rate": 1.8732783093110735e-05, "loss": 0.8538, "step": 3205 }, { "epoch": 0.1872663551401869, "grad_norm": 1.0558836460113525, "learning_rate": 1.873186119039667e-05, "loss": 0.5648, "step": 3206 }, { "epoch": 0.1873247663551402, "grad_norm": 3.064652681350708, "learning_rate": 1.8730938975163558e-05, "loss": 0.9005, "step": 3207 }, { "epoch": 0.18738317757009346, "grad_norm": 1.3302280902862549, "learning_rate": 1.8730016447444398e-05, "loss": 0.8554, "step": 3208 }, { "epoch": 0.18744158878504674, "grad_norm": 2.7381794452667236, "learning_rate": 1.8729093607272212e-05, "loss": 0.9313, "step": 3209 }, { "epoch": 0.1875, "grad_norm": 1.5809515714645386, "learning_rate": 1.8728170454680018e-05, "loss": 1.0007, "step": 3210 }, { "epoch": 0.18755841121495326, "grad_norm": 2.261014699935913, "learning_rate": 1.872724698970087e-05, "loss": 0.8915, "step": 3211 }, { "epoch": 0.18761682242990654, "grad_norm": 1.171051263809204, "learning_rate": 1.8726323212367816e-05, "loss": 0.8535, "step": 3212 }, { "epoch": 0.1876752336448598, "grad_norm": 1.2636646032333374, "learning_rate": 1.8725399122713914e-05, "loss": 0.7535, "step": 3213 }, { "epoch": 0.1877336448598131, "grad_norm": 1.7410402297973633, "learning_rate": 1.872447472077224e-05, "loss": 0.8487, "step": 3214 }, { "epoch": 0.18779205607476634, "grad_norm": 1.2506179809570312, "learning_rate": 1.872355000657588e-05, "loss": 0.7435, "step": 3215 }, { "epoch": 0.18785046728971963, "grad_norm": 2.3720693588256836, "learning_rate": 1.872262498015793e-05, "loss": 0.795, "step": 3216 }, { "epoch": 0.1879088785046729, "grad_norm": 1.280848741531372, "learning_rate": 1.8721699641551497e-05, "loss": 0.8806, "step": 3217 }, { "epoch": 0.18796728971962617, "grad_norm": 1.9624056816101074, "learning_rate": 1.8720773990789697e-05, "loss": 0.7974, "step": 3218 }, { "epoch": 0.18802570093457943, "grad_norm": 1.4463164806365967, "learning_rate": 1.8719848027905664e-05, "loss": 0.8605, "step": 3219 }, { "epoch": 0.18808411214953272, "grad_norm": 1.3494998216629028, "learning_rate": 1.8718921752932536e-05, "loss": 0.7308, "step": 3220 }, { "epoch": 0.18814252336448598, "grad_norm": 1.7234495878219604, "learning_rate": 1.8717995165903463e-05, "loss": 0.697, "step": 3221 }, { "epoch": 0.18820093457943926, "grad_norm": 1.5226160287857056, "learning_rate": 1.8717068266851614e-05, "loss": 0.9717, "step": 3222 }, { "epoch": 0.18825934579439252, "grad_norm": 1.618028163909912, "learning_rate": 1.871614105581016e-05, "loss": 0.7648, "step": 3223 }, { "epoch": 0.1883177570093458, "grad_norm": 1.5930217504501343, "learning_rate": 1.8715213532812288e-05, "loss": 0.8389, "step": 3224 }, { "epoch": 0.18837616822429906, "grad_norm": 1.3659964799880981, "learning_rate": 1.871428569789119e-05, "loss": 0.8046, "step": 3225 }, { "epoch": 0.18843457943925235, "grad_norm": 1.5415194034576416, "learning_rate": 1.8713357551080074e-05, "loss": 0.8988, "step": 3226 }, { "epoch": 0.1884929906542056, "grad_norm": 1.4333707094192505, "learning_rate": 1.871242909241217e-05, "loss": 0.8166, "step": 3227 }, { "epoch": 0.1885514018691589, "grad_norm": 2.3730382919311523, "learning_rate": 1.8711500321920698e-05, "loss": 0.942, "step": 3228 }, { "epoch": 0.18860981308411215, "grad_norm": 1.7396392822265625, "learning_rate": 1.87105712396389e-05, "loss": 0.8692, "step": 3229 }, { "epoch": 0.1886682242990654, "grad_norm": 1.5251483917236328, "learning_rate": 1.870964184560003e-05, "loss": 0.92, "step": 3230 }, { "epoch": 0.1887266355140187, "grad_norm": 1.9580105543136597, "learning_rate": 1.870871213983735e-05, "loss": 0.9608, "step": 3231 }, { "epoch": 0.18878504672897195, "grad_norm": 1.0943522453308105, "learning_rate": 1.870778212238414e-05, "loss": 0.8313, "step": 3232 }, { "epoch": 0.18884345794392524, "grad_norm": 2.201357841491699, "learning_rate": 1.8706851793273682e-05, "loss": 0.8921, "step": 3233 }, { "epoch": 0.1889018691588785, "grad_norm": 1.2264423370361328, "learning_rate": 1.8705921152539274e-05, "loss": 0.8548, "step": 3234 }, { "epoch": 0.18896028037383178, "grad_norm": 2.049701690673828, "learning_rate": 1.870499020021422e-05, "loss": 0.911, "step": 3235 }, { "epoch": 0.18901869158878504, "grad_norm": 1.238065481185913, "learning_rate": 1.8704058936331844e-05, "loss": 0.7675, "step": 3236 }, { "epoch": 0.18907710280373832, "grad_norm": 1.9052523374557495, "learning_rate": 1.8703127360925477e-05, "loss": 0.9233, "step": 3237 }, { "epoch": 0.18913551401869158, "grad_norm": 1.3873497247695923, "learning_rate": 1.870219547402846e-05, "loss": 0.7634, "step": 3238 }, { "epoch": 0.18919392523364487, "grad_norm": 1.1508443355560303, "learning_rate": 1.8701263275674142e-05, "loss": 0.6763, "step": 3239 }, { "epoch": 0.18925233644859812, "grad_norm": 1.6739000082015991, "learning_rate": 1.8700330765895895e-05, "loss": 0.7767, "step": 3240 }, { "epoch": 0.1893107476635514, "grad_norm": 1.9677923917770386, "learning_rate": 1.8699397944727086e-05, "loss": 0.8292, "step": 3241 }, { "epoch": 0.18936915887850467, "grad_norm": 1.6982543468475342, "learning_rate": 1.8698464812201105e-05, "loss": 0.7481, "step": 3242 }, { "epoch": 0.18942757009345795, "grad_norm": 1.7634562253952026, "learning_rate": 1.8697531368351345e-05, "loss": 0.7713, "step": 3243 }, { "epoch": 0.1894859813084112, "grad_norm": 2.242170572280884, "learning_rate": 1.869659761321123e-05, "loss": 0.7824, "step": 3244 }, { "epoch": 0.1895443925233645, "grad_norm": 1.638203740119934, "learning_rate": 1.8695663546814157e-05, "loss": 0.7259, "step": 3245 }, { "epoch": 0.18960280373831775, "grad_norm": 1.2044758796691895, "learning_rate": 1.869472916919357e-05, "loss": 0.7525, "step": 3246 }, { "epoch": 0.18966121495327104, "grad_norm": 2.2365033626556396, "learning_rate": 1.8693794480382916e-05, "loss": 0.7851, "step": 3247 }, { "epoch": 0.1897196261682243, "grad_norm": 1.767500877380371, "learning_rate": 1.8692859480415634e-05, "loss": 0.87, "step": 3248 }, { "epoch": 0.18977803738317758, "grad_norm": 2.0354175567626953, "learning_rate": 1.86919241693252e-05, "loss": 0.8294, "step": 3249 }, { "epoch": 0.18983644859813084, "grad_norm": 1.365010142326355, "learning_rate": 1.869098854714508e-05, "loss": 0.9095, "step": 3250 }, { "epoch": 0.1898948598130841, "grad_norm": 2.4183156490325928, "learning_rate": 1.869005261390877e-05, "loss": 0.7902, "step": 3251 }, { "epoch": 0.18995327102803738, "grad_norm": 1.9848167896270752, "learning_rate": 1.8689116369649763e-05, "loss": 0.8364, "step": 3252 }, { "epoch": 0.19001168224299064, "grad_norm": 1.392185926437378, "learning_rate": 1.8688179814401566e-05, "loss": 0.86, "step": 3253 }, { "epoch": 0.19007009345794393, "grad_norm": 1.7172764539718628, "learning_rate": 1.86872429481977e-05, "loss": 0.9281, "step": 3254 }, { "epoch": 0.1901285046728972, "grad_norm": 1.5065470933914185, "learning_rate": 1.86863057710717e-05, "loss": 0.7605, "step": 3255 }, { "epoch": 0.19018691588785047, "grad_norm": 1.2742102146148682, "learning_rate": 1.8685368283057105e-05, "loss": 0.8828, "step": 3256 }, { "epoch": 0.19024532710280373, "grad_norm": 2.4612364768981934, "learning_rate": 1.8684430484187467e-05, "loss": 0.9025, "step": 3257 }, { "epoch": 0.19030373831775702, "grad_norm": 1.401482105255127, "learning_rate": 1.868349237449635e-05, "loss": 0.732, "step": 3258 }, { "epoch": 0.19036214953271027, "grad_norm": 1.4385679960250854, "learning_rate": 1.8682553954017333e-05, "loss": 0.8949, "step": 3259 }, { "epoch": 0.19042056074766356, "grad_norm": 3.1291563510894775, "learning_rate": 1.8681615222784002e-05, "loss": 1.0085, "step": 3260 }, { "epoch": 0.19047897196261682, "grad_norm": 1.6661739349365234, "learning_rate": 1.8680676180829954e-05, "loss": 1.0154, "step": 3261 }, { "epoch": 0.1905373831775701, "grad_norm": 2.7918779850006104, "learning_rate": 1.8679736828188794e-05, "loss": 0.8068, "step": 3262 }, { "epoch": 0.19059579439252336, "grad_norm": 1.4216207265853882, "learning_rate": 1.867879716489415e-05, "loss": 0.7798, "step": 3263 }, { "epoch": 0.19065420560747665, "grad_norm": 1.4436382055282593, "learning_rate": 1.867785719097965e-05, "loss": 0.8199, "step": 3264 }, { "epoch": 0.1907126168224299, "grad_norm": 1.942930817604065, "learning_rate": 1.8676916906478934e-05, "loss": 0.9322, "step": 3265 }, { "epoch": 0.1907710280373832, "grad_norm": 1.7821813821792603, "learning_rate": 1.8675976311425656e-05, "loss": 0.734, "step": 3266 }, { "epoch": 0.19082943925233645, "grad_norm": 1.802340030670166, "learning_rate": 1.8675035405853478e-05, "loss": 0.8101, "step": 3267 }, { "epoch": 0.19088785046728973, "grad_norm": 2.106870174407959, "learning_rate": 1.8674094189796084e-05, "loss": 0.969, "step": 3268 }, { "epoch": 0.190946261682243, "grad_norm": 1.4611517190933228, "learning_rate": 1.8673152663287152e-05, "loss": 0.8465, "step": 3269 }, { "epoch": 0.19100467289719625, "grad_norm": 1.7462799549102783, "learning_rate": 1.8672210826360388e-05, "loss": 0.8676, "step": 3270 }, { "epoch": 0.19106308411214953, "grad_norm": 2.115528106689453, "learning_rate": 1.8671268679049493e-05, "loss": 0.9015, "step": 3271 }, { "epoch": 0.1911214953271028, "grad_norm": 1.5857980251312256, "learning_rate": 1.867032622138819e-05, "loss": 0.8004, "step": 3272 }, { "epoch": 0.19117990654205608, "grad_norm": 1.3418059349060059, "learning_rate": 1.866938345341021e-05, "loss": 0.8651, "step": 3273 }, { "epoch": 0.19123831775700934, "grad_norm": 1.569140076637268, "learning_rate": 1.86684403751493e-05, "loss": 0.733, "step": 3274 }, { "epoch": 0.19129672897196262, "grad_norm": 1.5872164964675903, "learning_rate": 1.8667496986639206e-05, "loss": 0.9122, "step": 3275 }, { "epoch": 0.19135514018691588, "grad_norm": 1.3346338272094727, "learning_rate": 1.86665532879137e-05, "loss": 0.9563, "step": 3276 }, { "epoch": 0.19141355140186916, "grad_norm": 2.1579363346099854, "learning_rate": 1.866560927900655e-05, "loss": 0.9922, "step": 3277 }, { "epoch": 0.19147196261682242, "grad_norm": 1.5979951620101929, "learning_rate": 1.8664664959951542e-05, "loss": 0.7817, "step": 3278 }, { "epoch": 0.1915303738317757, "grad_norm": 1.68778657913208, "learning_rate": 1.8663720330782484e-05, "loss": 0.8309, "step": 3279 }, { "epoch": 0.19158878504672897, "grad_norm": 1.4049848318099976, "learning_rate": 1.866277539153318e-05, "loss": 0.9157, "step": 3280 }, { "epoch": 0.19164719626168225, "grad_norm": 1.3819910287857056, "learning_rate": 1.8661830142237445e-05, "loss": 0.8897, "step": 3281 }, { "epoch": 0.1917056074766355, "grad_norm": 1.1575431823730469, "learning_rate": 1.8660884582929117e-05, "loss": 0.7549, "step": 3282 }, { "epoch": 0.1917640186915888, "grad_norm": 1.1868462562561035, "learning_rate": 1.865993871364203e-05, "loss": 0.8102, "step": 3283 }, { "epoch": 0.19182242990654205, "grad_norm": 1.7256519794464111, "learning_rate": 1.865899253441005e-05, "loss": 0.8778, "step": 3284 }, { "epoch": 0.19188084112149534, "grad_norm": 1.2125283479690552, "learning_rate": 1.865804604526703e-05, "loss": 0.736, "step": 3285 }, { "epoch": 0.1919392523364486, "grad_norm": 1.288792610168457, "learning_rate": 1.865709924624685e-05, "loss": 0.8718, "step": 3286 }, { "epoch": 0.19199766355140188, "grad_norm": 1.3313186168670654, "learning_rate": 1.8656152137383392e-05, "loss": 0.6817, "step": 3287 }, { "epoch": 0.19205607476635514, "grad_norm": 1.4094713926315308, "learning_rate": 1.865520471871056e-05, "loss": 0.8928, "step": 3288 }, { "epoch": 0.19211448598130842, "grad_norm": 1.5314323902130127, "learning_rate": 1.865425699026226e-05, "loss": 0.7531, "step": 3289 }, { "epoch": 0.19217289719626168, "grad_norm": 1.3436638116836548, "learning_rate": 1.8653308952072414e-05, "loss": 0.7767, "step": 3290 }, { "epoch": 0.19223130841121494, "grad_norm": 1.8493144512176514, "learning_rate": 1.865236060417495e-05, "loss": 0.7456, "step": 3291 }, { "epoch": 0.19228971962616823, "grad_norm": 1.3088964223861694, "learning_rate": 1.8651411946603807e-05, "loss": 0.7867, "step": 3292 }, { "epoch": 0.19234813084112148, "grad_norm": 1.410908818244934, "learning_rate": 1.8650462979392948e-05, "loss": 0.7628, "step": 3293 }, { "epoch": 0.19240654205607477, "grad_norm": 1.7601349353790283, "learning_rate": 1.8649513702576327e-05, "loss": 1.0149, "step": 3294 }, { "epoch": 0.19246495327102803, "grad_norm": 1.062230110168457, "learning_rate": 1.8648564116187927e-05, "loss": 0.7034, "step": 3295 }, { "epoch": 0.1925233644859813, "grad_norm": 1.3593796491622925, "learning_rate": 1.864761422026173e-05, "loss": 0.8193, "step": 3296 }, { "epoch": 0.19258177570093457, "grad_norm": 1.2018442153930664, "learning_rate": 1.864666401483173e-05, "loss": 0.7894, "step": 3297 }, { "epoch": 0.19264018691588786, "grad_norm": 1.454322099685669, "learning_rate": 1.8645713499931943e-05, "loss": 0.983, "step": 3298 }, { "epoch": 0.19269859813084111, "grad_norm": 1.3010281324386597, "learning_rate": 1.8644762675596383e-05, "loss": 0.9409, "step": 3299 }, { "epoch": 0.1927570093457944, "grad_norm": 1.3320341110229492, "learning_rate": 1.8643811541859085e-05, "loss": 0.7764, "step": 3300 }, { "epoch": 0.19281542056074766, "grad_norm": 1.2393656969070435, "learning_rate": 1.864286009875409e-05, "loss": 1.0402, "step": 3301 }, { "epoch": 0.19287383177570094, "grad_norm": 1.1947788000106812, "learning_rate": 1.8641908346315445e-05, "loss": 0.7964, "step": 3302 }, { "epoch": 0.1929322429906542, "grad_norm": 1.6919302940368652, "learning_rate": 1.8640956284577222e-05, "loss": 0.8281, "step": 3303 }, { "epoch": 0.1929906542056075, "grad_norm": 1.8848848342895508, "learning_rate": 1.8640003913573487e-05, "loss": 0.9126, "step": 3304 }, { "epoch": 0.19304906542056074, "grad_norm": 1.6472645998001099, "learning_rate": 1.8639051233338338e-05, "loss": 0.8022, "step": 3305 }, { "epoch": 0.19310747663551403, "grad_norm": 1.2169774770736694, "learning_rate": 1.863809824390586e-05, "loss": 0.809, "step": 3306 }, { "epoch": 0.1931658878504673, "grad_norm": 1.5815846920013428, "learning_rate": 1.8637144945310167e-05, "loss": 0.8981, "step": 3307 }, { "epoch": 0.19322429906542057, "grad_norm": 2.500075101852417, "learning_rate": 1.863619133758538e-05, "loss": 0.7884, "step": 3308 }, { "epoch": 0.19328271028037383, "grad_norm": 1.2086069583892822, "learning_rate": 1.8635237420765624e-05, "loss": 0.8335, "step": 3309 }, { "epoch": 0.1933411214953271, "grad_norm": 1.561293601989746, "learning_rate": 1.8634283194885045e-05, "loss": 0.9656, "step": 3310 }, { "epoch": 0.19339953271028038, "grad_norm": 2.1968770027160645, "learning_rate": 1.863332865997779e-05, "loss": 0.8084, "step": 3311 }, { "epoch": 0.19345794392523363, "grad_norm": 1.7116321325302124, "learning_rate": 1.8632373816078027e-05, "loss": 0.7499, "step": 3312 }, { "epoch": 0.19351635514018692, "grad_norm": 2.8121418952941895, "learning_rate": 1.8631418663219932e-05, "loss": 0.9819, "step": 3313 }, { "epoch": 0.19357476635514018, "grad_norm": 1.6726576089859009, "learning_rate": 1.8630463201437682e-05, "loss": 0.965, "step": 3314 }, { "epoch": 0.19363317757009346, "grad_norm": 2.6200790405273438, "learning_rate": 1.8629507430765484e-05, "loss": 0.8654, "step": 3315 }, { "epoch": 0.19369158878504672, "grad_norm": 1.3875178098678589, "learning_rate": 1.8628551351237542e-05, "loss": 0.6114, "step": 3316 }, { "epoch": 0.19375, "grad_norm": 2.453385591506958, "learning_rate": 1.8627594962888072e-05, "loss": 0.828, "step": 3317 }, { "epoch": 0.19380841121495326, "grad_norm": 3.021002769470215, "learning_rate": 1.8626638265751305e-05, "loss": 1.1255, "step": 3318 }, { "epoch": 0.19386682242990655, "grad_norm": 2.980292320251465, "learning_rate": 1.862568125986148e-05, "loss": 0.842, "step": 3319 }, { "epoch": 0.1939252336448598, "grad_norm": 2.7047507762908936, "learning_rate": 1.8624723945252853e-05, "loss": 0.9405, "step": 3320 }, { "epoch": 0.1939836448598131, "grad_norm": 1.434609055519104, "learning_rate": 1.862376632195969e-05, "loss": 0.883, "step": 3321 }, { "epoch": 0.19404205607476635, "grad_norm": 2.9239745140075684, "learning_rate": 1.8622808390016255e-05, "loss": 1.0626, "step": 3322 }, { "epoch": 0.19410046728971964, "grad_norm": 1.8766728639602661, "learning_rate": 1.8621850149456838e-05, "loss": 0.9619, "step": 3323 }, { "epoch": 0.1941588785046729, "grad_norm": 1.1987322568893433, "learning_rate": 1.8620891600315735e-05, "loss": 0.8723, "step": 3324 }, { "epoch": 0.19421728971962618, "grad_norm": 2.615104913711548, "learning_rate": 1.8619932742627255e-05, "loss": 0.8871, "step": 3325 }, { "epoch": 0.19427570093457944, "grad_norm": 2.0364112854003906, "learning_rate": 1.8618973576425716e-05, "loss": 0.8695, "step": 3326 }, { "epoch": 0.19433411214953272, "grad_norm": 2.04392147064209, "learning_rate": 1.8618014101745444e-05, "loss": 0.9005, "step": 3327 }, { "epoch": 0.19439252336448598, "grad_norm": 3.27270770072937, "learning_rate": 1.861705431862078e-05, "loss": 0.8188, "step": 3328 }, { "epoch": 0.19445093457943924, "grad_norm": 1.9481269121170044, "learning_rate": 1.8616094227086077e-05, "loss": 1.1446, "step": 3329 }, { "epoch": 0.19450934579439252, "grad_norm": 2.127098321914673, "learning_rate": 1.8615133827175694e-05, "loss": 0.8749, "step": 3330 }, { "epoch": 0.19456775700934578, "grad_norm": 1.4914467334747314, "learning_rate": 1.861417311892401e-05, "loss": 0.9227, "step": 3331 }, { "epoch": 0.19462616822429907, "grad_norm": 1.6843594312667847, "learning_rate": 1.8613212102365405e-05, "loss": 0.7677, "step": 3332 }, { "epoch": 0.19468457943925233, "grad_norm": 2.0080840587615967, "learning_rate": 1.8612250777534275e-05, "loss": 0.9817, "step": 3333 }, { "epoch": 0.1947429906542056, "grad_norm": 1.9053162336349487, "learning_rate": 1.861128914446503e-05, "loss": 1.0864, "step": 3334 }, { "epoch": 0.19480140186915887, "grad_norm": 1.5060266256332397, "learning_rate": 1.8610327203192082e-05, "loss": 0.8658, "step": 3335 }, { "epoch": 0.19485981308411215, "grad_norm": 1.6960020065307617, "learning_rate": 1.8609364953749862e-05, "loss": 0.8437, "step": 3336 }, { "epoch": 0.1949182242990654, "grad_norm": 1.3609709739685059, "learning_rate": 1.860840239617281e-05, "loss": 0.9676, "step": 3337 }, { "epoch": 0.1949766355140187, "grad_norm": 1.3913702964782715, "learning_rate": 1.8607439530495374e-05, "loss": 0.7309, "step": 3338 }, { "epoch": 0.19503504672897196, "grad_norm": 1.4615108966827393, "learning_rate": 1.860647635675202e-05, "loss": 0.8377, "step": 3339 }, { "epoch": 0.19509345794392524, "grad_norm": 1.6229000091552734, "learning_rate": 1.8605512874977218e-05, "loss": 0.9188, "step": 3340 }, { "epoch": 0.1951518691588785, "grad_norm": 1.6218998432159424, "learning_rate": 1.860454908520545e-05, "loss": 0.9036, "step": 3341 }, { "epoch": 0.19521028037383178, "grad_norm": 1.6099334955215454, "learning_rate": 1.8603584987471215e-05, "loss": 1.0408, "step": 3342 }, { "epoch": 0.19526869158878504, "grad_norm": 1.332518458366394, "learning_rate": 1.8602620581809017e-05, "loss": 0.9129, "step": 3343 }, { "epoch": 0.19532710280373833, "grad_norm": 1.1579338312149048, "learning_rate": 1.8601655868253368e-05, "loss": 0.7844, "step": 3344 }, { "epoch": 0.1953855140186916, "grad_norm": 2.714850664138794, "learning_rate": 1.8600690846838803e-05, "loss": 0.9046, "step": 3345 }, { "epoch": 0.19544392523364487, "grad_norm": 1.2681427001953125, "learning_rate": 1.8599725517599858e-05, "loss": 0.8479, "step": 3346 }, { "epoch": 0.19550233644859813, "grad_norm": 3.453691005706787, "learning_rate": 1.859875988057108e-05, "loss": 0.9161, "step": 3347 }, { "epoch": 0.19556074766355142, "grad_norm": 1.331811547279358, "learning_rate": 1.8597793935787036e-05, "loss": 0.7272, "step": 3348 }, { "epoch": 0.19561915887850467, "grad_norm": 3.481450080871582, "learning_rate": 1.859682768328229e-05, "loss": 0.8816, "step": 3349 }, { "epoch": 0.19567757009345793, "grad_norm": 1.5907845497131348, "learning_rate": 1.859586112309143e-05, "loss": 0.8471, "step": 3350 }, { "epoch": 0.19573598130841122, "grad_norm": 2.88736891746521, "learning_rate": 1.8594894255249046e-05, "loss": 0.9218, "step": 3351 }, { "epoch": 0.19579439252336447, "grad_norm": 1.4576514959335327, "learning_rate": 1.859392707978975e-05, "loss": 0.8856, "step": 3352 }, { "epoch": 0.19585280373831776, "grad_norm": 1.6272010803222656, "learning_rate": 1.8592959596748153e-05, "loss": 1.0829, "step": 3353 }, { "epoch": 0.19591121495327102, "grad_norm": 2.8932366371154785, "learning_rate": 1.859199180615888e-05, "loss": 0.8215, "step": 3354 }, { "epoch": 0.1959696261682243, "grad_norm": 1.131301999092102, "learning_rate": 1.859102370805657e-05, "loss": 0.5907, "step": 3355 }, { "epoch": 0.19602803738317756, "grad_norm": 1.8382455110549927, "learning_rate": 1.8590055302475872e-05, "loss": 0.8213, "step": 3356 }, { "epoch": 0.19608644859813085, "grad_norm": 2.125969886779785, "learning_rate": 1.8589086589451447e-05, "loss": 0.8853, "step": 3357 }, { "epoch": 0.1961448598130841, "grad_norm": 1.2586820125579834, "learning_rate": 1.858811756901797e-05, "loss": 0.9736, "step": 3358 }, { "epoch": 0.1962032710280374, "grad_norm": 1.8007720708847046, "learning_rate": 1.8587148241210116e-05, "loss": 0.8545, "step": 3359 }, { "epoch": 0.19626168224299065, "grad_norm": 1.1870911121368408, "learning_rate": 1.858617860606258e-05, "loss": 0.86, "step": 3360 }, { "epoch": 0.19632009345794393, "grad_norm": 1.542813777923584, "learning_rate": 1.8585208663610065e-05, "loss": 0.8183, "step": 3361 }, { "epoch": 0.1963785046728972, "grad_norm": 1.7232575416564941, "learning_rate": 1.858423841388729e-05, "loss": 0.8737, "step": 3362 }, { "epoch": 0.19643691588785048, "grad_norm": 1.2317957878112793, "learning_rate": 1.8583267856928974e-05, "loss": 0.7875, "step": 3363 }, { "epoch": 0.19649532710280374, "grad_norm": 1.2996323108673096, "learning_rate": 1.858229699276986e-05, "loss": 0.7759, "step": 3364 }, { "epoch": 0.19655373831775702, "grad_norm": 1.4491164684295654, "learning_rate": 1.858132582144469e-05, "loss": 0.9009, "step": 3365 }, { "epoch": 0.19661214953271028, "grad_norm": 1.2137012481689453, "learning_rate": 1.858035434298823e-05, "loss": 0.7466, "step": 3366 }, { "epoch": 0.19667056074766356, "grad_norm": 1.340202808380127, "learning_rate": 1.8579382557435247e-05, "loss": 0.8137, "step": 3367 }, { "epoch": 0.19672897196261682, "grad_norm": 1.3795427083969116, "learning_rate": 1.8578410464820523e-05, "loss": 0.7475, "step": 3368 }, { "epoch": 0.19678738317757008, "grad_norm": 1.4463354349136353, "learning_rate": 1.8577438065178843e-05, "loss": 0.922, "step": 3369 }, { "epoch": 0.19684579439252337, "grad_norm": 1.7539530992507935, "learning_rate": 1.8576465358545016e-05, "loss": 0.9468, "step": 3370 }, { "epoch": 0.19690420560747662, "grad_norm": 1.297863245010376, "learning_rate": 1.8575492344953856e-05, "loss": 0.8542, "step": 3371 }, { "epoch": 0.1969626168224299, "grad_norm": 1.827917456626892, "learning_rate": 1.857451902444019e-05, "loss": 0.9089, "step": 3372 }, { "epoch": 0.19702102803738317, "grad_norm": 1.3252536058425903, "learning_rate": 1.8573545397038844e-05, "loss": 0.8598, "step": 3373 }, { "epoch": 0.19707943925233645, "grad_norm": 1.200173020362854, "learning_rate": 1.8572571462784673e-05, "loss": 0.7511, "step": 3374 }, { "epoch": 0.1971378504672897, "grad_norm": 1.7655270099639893, "learning_rate": 1.8571597221712533e-05, "loss": 0.9115, "step": 3375 }, { "epoch": 0.197196261682243, "grad_norm": 1.5336493253707886, "learning_rate": 1.8570622673857293e-05, "loss": 0.9612, "step": 3376 }, { "epoch": 0.19725467289719625, "grad_norm": 1.4961944818496704, "learning_rate": 1.8569647819253832e-05, "loss": 1.0233, "step": 3377 }, { "epoch": 0.19731308411214954, "grad_norm": 1.2920466661453247, "learning_rate": 1.8568672657937044e-05, "loss": 0.7031, "step": 3378 }, { "epoch": 0.1973714953271028, "grad_norm": 1.0714585781097412, "learning_rate": 1.8567697189941826e-05, "loss": 0.6621, "step": 3379 }, { "epoch": 0.19742990654205608, "grad_norm": 1.2893990278244019, "learning_rate": 1.8566721415303087e-05, "loss": 0.8689, "step": 3380 }, { "epoch": 0.19748831775700934, "grad_norm": 1.6748775243759155, "learning_rate": 1.856574533405576e-05, "loss": 0.8618, "step": 3381 }, { "epoch": 0.19754672897196263, "grad_norm": 1.5148087739944458, "learning_rate": 1.8564768946234774e-05, "loss": 1.2432, "step": 3382 }, { "epoch": 0.19760514018691588, "grad_norm": 1.6273318529129028, "learning_rate": 1.856379225187508e-05, "loss": 0.8948, "step": 3383 }, { "epoch": 0.19766355140186917, "grad_norm": 1.6930880546569824, "learning_rate": 1.8562815251011626e-05, "loss": 0.9339, "step": 3384 }, { "epoch": 0.19772196261682243, "grad_norm": 1.4250898361206055, "learning_rate": 1.8561837943679386e-05, "loss": 0.8664, "step": 3385 }, { "epoch": 0.1977803738317757, "grad_norm": 2.1998188495635986, "learning_rate": 1.8560860329913337e-05, "loss": 1.0305, "step": 3386 }, { "epoch": 0.19783878504672897, "grad_norm": 1.6968777179718018, "learning_rate": 1.8559882409748467e-05, "loss": 1.0301, "step": 3387 }, { "epoch": 0.19789719626168226, "grad_norm": 1.8557791709899902, "learning_rate": 1.8558904183219776e-05, "loss": 0.8103, "step": 3388 }, { "epoch": 0.19795560747663551, "grad_norm": 1.7819242477416992, "learning_rate": 1.8557925650362277e-05, "loss": 0.7858, "step": 3389 }, { "epoch": 0.19801401869158877, "grad_norm": 1.8821475505828857, "learning_rate": 1.8556946811210993e-05, "loss": 0.9496, "step": 3390 }, { "epoch": 0.19807242990654206, "grad_norm": 1.9513520002365112, "learning_rate": 1.8555967665800958e-05, "loss": 0.9604, "step": 3391 }, { "epoch": 0.19813084112149532, "grad_norm": 1.3466103076934814, "learning_rate": 1.8554988214167214e-05, "loss": 0.7424, "step": 3392 }, { "epoch": 0.1981892523364486, "grad_norm": 2.3079264163970947, "learning_rate": 1.8554008456344815e-05, "loss": 0.9866, "step": 3393 }, { "epoch": 0.19824766355140186, "grad_norm": 1.3862862586975098, "learning_rate": 1.855302839236883e-05, "loss": 0.7673, "step": 3394 }, { "epoch": 0.19830607476635514, "grad_norm": 2.011906862258911, "learning_rate": 1.8552048022274333e-05, "loss": 0.9384, "step": 3395 }, { "epoch": 0.1983644859813084, "grad_norm": 1.6415581703186035, "learning_rate": 1.8551067346096418e-05, "loss": 0.8979, "step": 3396 }, { "epoch": 0.1984228971962617, "grad_norm": 1.0681525468826294, "learning_rate": 1.8550086363870178e-05, "loss": 0.866, "step": 3397 }, { "epoch": 0.19848130841121495, "grad_norm": 2.0954055786132812, "learning_rate": 1.8549105075630723e-05, "loss": 0.8474, "step": 3398 }, { "epoch": 0.19853971962616823, "grad_norm": 1.63160240650177, "learning_rate": 1.854812348141318e-05, "loss": 0.7718, "step": 3399 }, { "epoch": 0.1985981308411215, "grad_norm": 1.4644176959991455, "learning_rate": 1.8547141581252677e-05, "loss": 0.7312, "step": 3400 }, { "epoch": 0.19865654205607478, "grad_norm": 1.4683258533477783, "learning_rate": 1.8546159375184353e-05, "loss": 0.6195, "step": 3401 }, { "epoch": 0.19871495327102803, "grad_norm": 1.8164947032928467, "learning_rate": 1.854517686324337e-05, "loss": 0.9019, "step": 3402 }, { "epoch": 0.19877336448598132, "grad_norm": 1.9625146389007568, "learning_rate": 1.8544194045464888e-05, "loss": 0.716, "step": 3403 }, { "epoch": 0.19883177570093458, "grad_norm": 1.4036774635314941, "learning_rate": 1.854321092188408e-05, "loss": 0.7598, "step": 3404 }, { "epoch": 0.19889018691588786, "grad_norm": 1.7601779699325562, "learning_rate": 1.854222749253614e-05, "loss": 0.8873, "step": 3405 }, { "epoch": 0.19894859813084112, "grad_norm": 1.2835129499435425, "learning_rate": 1.854124375745626e-05, "loss": 0.7843, "step": 3406 }, { "epoch": 0.1990070093457944, "grad_norm": 1.2102882862091064, "learning_rate": 1.854025971667965e-05, "loss": 0.7546, "step": 3407 }, { "epoch": 0.19906542056074766, "grad_norm": 1.047641396522522, "learning_rate": 1.8539275370241525e-05, "loss": 0.6514, "step": 3408 }, { "epoch": 0.19912383177570092, "grad_norm": 1.7914730310440063, "learning_rate": 1.8538290718177126e-05, "loss": 0.9507, "step": 3409 }, { "epoch": 0.1991822429906542, "grad_norm": 1.4505888223648071, "learning_rate": 1.8537305760521684e-05, "loss": 0.8996, "step": 3410 }, { "epoch": 0.19924065420560746, "grad_norm": 2.0093636512756348, "learning_rate": 1.8536320497310457e-05, "loss": 0.7055, "step": 3411 }, { "epoch": 0.19929906542056075, "grad_norm": 1.9193451404571533, "learning_rate": 1.8535334928578708e-05, "loss": 0.7425, "step": 3412 }, { "epoch": 0.199357476635514, "grad_norm": 1.6037362813949585, "learning_rate": 1.8534349054361708e-05, "loss": 0.9968, "step": 3413 }, { "epoch": 0.1994158878504673, "grad_norm": 1.8752515316009521, "learning_rate": 1.8533362874694747e-05, "loss": 0.8545, "step": 3414 }, { "epoch": 0.19947429906542055, "grad_norm": 3.520718812942505, "learning_rate": 1.8532376389613113e-05, "loss": 0.9015, "step": 3415 }, { "epoch": 0.19953271028037384, "grad_norm": 1.396425485610962, "learning_rate": 1.8531389599152123e-05, "loss": 0.7617, "step": 3416 }, { "epoch": 0.1995911214953271, "grad_norm": 1.6158713102340698, "learning_rate": 1.8530402503347086e-05, "loss": 0.7257, "step": 3417 }, { "epoch": 0.19964953271028038, "grad_norm": 2.106628894805908, "learning_rate": 1.8529415102233333e-05, "loss": 0.9809, "step": 3418 }, { "epoch": 0.19970794392523364, "grad_norm": 2.4980392456054688, "learning_rate": 1.8528427395846212e-05, "loss": 0.8226, "step": 3419 }, { "epoch": 0.19976635514018692, "grad_norm": 1.781970739364624, "learning_rate": 1.852743938422106e-05, "loss": 0.8031, "step": 3420 }, { "epoch": 0.19982476635514018, "grad_norm": 1.4287865161895752, "learning_rate": 1.852645106739325e-05, "loss": 0.6852, "step": 3421 }, { "epoch": 0.19988317757009347, "grad_norm": 1.9759304523468018, "learning_rate": 1.8525462445398147e-05, "loss": 0.9871, "step": 3422 }, { "epoch": 0.19994158878504673, "grad_norm": 1.700670599937439, "learning_rate": 1.852447351827114e-05, "loss": 0.8412, "step": 3423 }, { "epoch": 0.2, "grad_norm": 1.5553423166275024, "learning_rate": 1.8523484286047623e-05, "loss": 0.7183, "step": 3424 }, { "epoch": 0.20005841121495327, "grad_norm": 1.2241829633712769, "learning_rate": 1.8522494748762995e-05, "loss": 0.8834, "step": 3425 }, { "epoch": 0.20011682242990655, "grad_norm": 1.4756925106048584, "learning_rate": 1.8521504906452678e-05, "loss": 0.7598, "step": 3426 }, { "epoch": 0.2001752336448598, "grad_norm": 1.8801573514938354, "learning_rate": 1.8520514759152095e-05, "loss": 1.0243, "step": 3427 }, { "epoch": 0.20023364485981307, "grad_norm": 1.4703763723373413, "learning_rate": 1.851952430689669e-05, "loss": 1.0352, "step": 3428 }, { "epoch": 0.20029205607476636, "grad_norm": 2.0795676708221436, "learning_rate": 1.8518533549721902e-05, "loss": 0.8312, "step": 3429 }, { "epoch": 0.2003504672897196, "grad_norm": 1.278365135192871, "learning_rate": 1.8517542487663202e-05, "loss": 0.8937, "step": 3430 }, { "epoch": 0.2004088785046729, "grad_norm": 1.6656148433685303, "learning_rate": 1.8516551120756057e-05, "loss": 0.7065, "step": 3431 }, { "epoch": 0.20046728971962616, "grad_norm": 2.0272960662841797, "learning_rate": 1.8515559449035944e-05, "loss": 0.9388, "step": 3432 }, { "epoch": 0.20052570093457944, "grad_norm": 1.3675079345703125, "learning_rate": 1.8514567472538363e-05, "loss": 0.921, "step": 3433 }, { "epoch": 0.2005841121495327, "grad_norm": 2.3620216846466064, "learning_rate": 1.851357519129881e-05, "loss": 1.0136, "step": 3434 }, { "epoch": 0.200642523364486, "grad_norm": 1.6268913745880127, "learning_rate": 1.8512582605352808e-05, "loss": 0.8352, "step": 3435 }, { "epoch": 0.20070093457943924, "grad_norm": 2.457549810409546, "learning_rate": 1.8511589714735875e-05, "loss": 0.9807, "step": 3436 }, { "epoch": 0.20075934579439253, "grad_norm": 1.5028560161590576, "learning_rate": 1.851059651948355e-05, "loss": 0.7783, "step": 3437 }, { "epoch": 0.2008177570093458, "grad_norm": 1.5624843835830688, "learning_rate": 1.850960301963138e-05, "loss": 0.8217, "step": 3438 }, { "epoch": 0.20087616822429907, "grad_norm": 1.4263784885406494, "learning_rate": 1.850860921521492e-05, "loss": 0.8446, "step": 3439 }, { "epoch": 0.20093457943925233, "grad_norm": 2.00182843208313, "learning_rate": 1.8507615106269743e-05, "loss": 0.9112, "step": 3440 }, { "epoch": 0.20099299065420562, "grad_norm": 1.5211611986160278, "learning_rate": 1.8506620692831427e-05, "loss": 0.8845, "step": 3441 }, { "epoch": 0.20105140186915887, "grad_norm": 1.3433691263198853, "learning_rate": 1.8505625974935566e-05, "loss": 0.8641, "step": 3442 }, { "epoch": 0.20110981308411216, "grad_norm": 1.250825047492981, "learning_rate": 1.8504630952617757e-05, "loss": 0.7063, "step": 3443 }, { "epoch": 0.20116822429906542, "grad_norm": 1.7543085813522339, "learning_rate": 1.8503635625913613e-05, "loss": 0.8015, "step": 3444 }, { "epoch": 0.2012266355140187, "grad_norm": 2.0452871322631836, "learning_rate": 1.850263999485876e-05, "loss": 0.7749, "step": 3445 }, { "epoch": 0.20128504672897196, "grad_norm": 4.738675117492676, "learning_rate": 1.850164405948883e-05, "loss": 0.7748, "step": 3446 }, { "epoch": 0.20134345794392525, "grad_norm": 1.4107204675674438, "learning_rate": 1.8500647819839472e-05, "loss": 0.7797, "step": 3447 }, { "epoch": 0.2014018691588785, "grad_norm": 1.4554060697555542, "learning_rate": 1.8499651275946337e-05, "loss": 0.6988, "step": 3448 }, { "epoch": 0.20146028037383176, "grad_norm": 2.071333646774292, "learning_rate": 1.8498654427845094e-05, "loss": 0.8781, "step": 3449 }, { "epoch": 0.20151869158878505, "grad_norm": 1.5429569482803345, "learning_rate": 1.8497657275571422e-05, "loss": 0.8714, "step": 3450 }, { "epoch": 0.2015771028037383, "grad_norm": 1.3995921611785889, "learning_rate": 1.849665981916101e-05, "loss": 0.9449, "step": 3451 }, { "epoch": 0.2016355140186916, "grad_norm": 1.4928793907165527, "learning_rate": 1.8495662058649553e-05, "loss": 0.9875, "step": 3452 }, { "epoch": 0.20169392523364485, "grad_norm": 2.103701591491699, "learning_rate": 1.8494663994072768e-05, "loss": 1.0641, "step": 3453 }, { "epoch": 0.20175233644859814, "grad_norm": 1.4787826538085938, "learning_rate": 1.8493665625466374e-05, "loss": 0.8609, "step": 3454 }, { "epoch": 0.2018107476635514, "grad_norm": 1.6970493793487549, "learning_rate": 1.84926669528661e-05, "loss": 0.7631, "step": 3455 }, { "epoch": 0.20186915887850468, "grad_norm": 1.835707187652588, "learning_rate": 1.849166797630769e-05, "loss": 0.8382, "step": 3456 }, { "epoch": 0.20192757009345794, "grad_norm": 1.8564358949661255, "learning_rate": 1.8490668695826902e-05, "loss": 0.8211, "step": 3457 }, { "epoch": 0.20198598130841122, "grad_norm": 1.692589282989502, "learning_rate": 1.8489669111459502e-05, "loss": 0.7812, "step": 3458 }, { "epoch": 0.20204439252336448, "grad_norm": 1.842659831047058, "learning_rate": 1.848866922324126e-05, "loss": 1.048, "step": 3459 }, { "epoch": 0.20210280373831777, "grad_norm": 1.4523600339889526, "learning_rate": 1.848766903120796e-05, "loss": 0.8019, "step": 3460 }, { "epoch": 0.20216121495327102, "grad_norm": 1.4122717380523682, "learning_rate": 1.848666853539541e-05, "loss": 0.9889, "step": 3461 }, { "epoch": 0.2022196261682243, "grad_norm": 1.6589365005493164, "learning_rate": 1.8485667735839413e-05, "loss": 0.8178, "step": 3462 }, { "epoch": 0.20227803738317757, "grad_norm": 1.1186778545379639, "learning_rate": 1.848466663257579e-05, "loss": 0.8193, "step": 3463 }, { "epoch": 0.20233644859813085, "grad_norm": 1.6038484573364258, "learning_rate": 1.8483665225640363e-05, "loss": 1.1088, "step": 3464 }, { "epoch": 0.2023948598130841, "grad_norm": 1.0951228141784668, "learning_rate": 1.8482663515068982e-05, "loss": 0.9162, "step": 3465 }, { "epoch": 0.2024532710280374, "grad_norm": 1.4284727573394775, "learning_rate": 1.84816615008975e-05, "loss": 0.797, "step": 3466 }, { "epoch": 0.20251168224299065, "grad_norm": 1.094081163406372, "learning_rate": 1.848065918316177e-05, "loss": 0.8332, "step": 3467 }, { "epoch": 0.2025700934579439, "grad_norm": 1.4695791006088257, "learning_rate": 1.8479656561897678e-05, "loss": 0.9755, "step": 3468 }, { "epoch": 0.2026285046728972, "grad_norm": 1.3107283115386963, "learning_rate": 1.8478653637141098e-05, "loss": 0.7659, "step": 3469 }, { "epoch": 0.20268691588785046, "grad_norm": 1.3841218948364258, "learning_rate": 1.847765040892793e-05, "loss": 0.9078, "step": 3470 }, { "epoch": 0.20274532710280374, "grad_norm": 1.5555377006530762, "learning_rate": 1.847664687729408e-05, "loss": 0.8697, "step": 3471 }, { "epoch": 0.202803738317757, "grad_norm": 1.0539151430130005, "learning_rate": 1.847564304227547e-05, "loss": 0.6983, "step": 3472 }, { "epoch": 0.20286214953271028, "grad_norm": 1.189073085784912, "learning_rate": 1.8474638903908016e-05, "loss": 0.7672, "step": 3473 }, { "epoch": 0.20292056074766354, "grad_norm": 1.1860700845718384, "learning_rate": 1.8473634462227667e-05, "loss": 0.75, "step": 3474 }, { "epoch": 0.20297897196261683, "grad_norm": 1.3404932022094727, "learning_rate": 1.847262971727037e-05, "loss": 0.7597, "step": 3475 }, { "epoch": 0.20303738317757009, "grad_norm": 1.4744317531585693, "learning_rate": 1.8471624669072077e-05, "loss": 0.9562, "step": 3476 }, { "epoch": 0.20309579439252337, "grad_norm": 1.1374962329864502, "learning_rate": 1.8470619317668774e-05, "loss": 0.6954, "step": 3477 }, { "epoch": 0.20315420560747663, "grad_norm": 1.946510672569275, "learning_rate": 1.8469613663096435e-05, "loss": 0.7395, "step": 3478 }, { "epoch": 0.20321261682242991, "grad_norm": 1.2590986490249634, "learning_rate": 1.846860770539105e-05, "loss": 0.6572, "step": 3479 }, { "epoch": 0.20327102803738317, "grad_norm": 1.9002783298492432, "learning_rate": 1.8467601444588633e-05, "loss": 0.8242, "step": 3480 }, { "epoch": 0.20332943925233646, "grad_norm": 1.2392147779464722, "learning_rate": 1.8466594880725188e-05, "loss": 0.9168, "step": 3481 }, { "epoch": 0.20338785046728972, "grad_norm": 1.4918525218963623, "learning_rate": 1.846558801383675e-05, "loss": 0.8464, "step": 3482 }, { "epoch": 0.203446261682243, "grad_norm": 1.6793808937072754, "learning_rate": 1.8464580843959344e-05, "loss": 0.8029, "step": 3483 }, { "epoch": 0.20350467289719626, "grad_norm": 1.2994675636291504, "learning_rate": 1.8463573371129027e-05, "loss": 0.9397, "step": 3484 }, { "epoch": 0.20356308411214954, "grad_norm": 2.2902743816375732, "learning_rate": 1.846256559538186e-05, "loss": 0.9199, "step": 3485 }, { "epoch": 0.2036214953271028, "grad_norm": 0.9070024490356445, "learning_rate": 1.8461557516753902e-05, "loss": 0.6263, "step": 3486 }, { "epoch": 0.2036799065420561, "grad_norm": 3.7507436275482178, "learning_rate": 1.8460549135281236e-05, "loss": 1.0001, "step": 3487 }, { "epoch": 0.20373831775700935, "grad_norm": 1.9254440069198608, "learning_rate": 1.8459540450999953e-05, "loss": 0.8994, "step": 3488 }, { "epoch": 0.2037967289719626, "grad_norm": 2.186089515686035, "learning_rate": 1.8458531463946153e-05, "loss": 0.8158, "step": 3489 }, { "epoch": 0.2038551401869159, "grad_norm": 1.2276993989944458, "learning_rate": 1.8457522174155955e-05, "loss": 0.8221, "step": 3490 }, { "epoch": 0.20391355140186915, "grad_norm": 1.8288263082504272, "learning_rate": 1.8456512581665475e-05, "loss": 0.749, "step": 3491 }, { "epoch": 0.20397196261682243, "grad_norm": 1.9825799465179443, "learning_rate": 1.8455502686510848e-05, "loss": 0.7703, "step": 3492 }, { "epoch": 0.2040303738317757, "grad_norm": 1.3652971982955933, "learning_rate": 1.8454492488728225e-05, "loss": 0.7352, "step": 3493 }, { "epoch": 0.20408878504672898, "grad_norm": 1.9230713844299316, "learning_rate": 1.8453481988353754e-05, "loss": 0.8965, "step": 3494 }, { "epoch": 0.20414719626168223, "grad_norm": 1.963942289352417, "learning_rate": 1.8452471185423604e-05, "loss": 0.888, "step": 3495 }, { "epoch": 0.20420560747663552, "grad_norm": 2.06675386428833, "learning_rate": 1.8451460079973952e-05, "loss": 0.9051, "step": 3496 }, { "epoch": 0.20426401869158878, "grad_norm": 1.9928842782974243, "learning_rate": 1.845044867204099e-05, "loss": 0.8163, "step": 3497 }, { "epoch": 0.20432242990654206, "grad_norm": 1.4099377393722534, "learning_rate": 1.8449436961660908e-05, "loss": 0.7043, "step": 3498 }, { "epoch": 0.20438084112149532, "grad_norm": 1.5278503894805908, "learning_rate": 1.8448424948869926e-05, "loss": 0.6622, "step": 3499 }, { "epoch": 0.2044392523364486, "grad_norm": 1.6695960760116577, "learning_rate": 1.844741263370426e-05, "loss": 0.8337, "step": 3500 }, { "epoch": 0.20449766355140186, "grad_norm": 1.9360847473144531, "learning_rate": 1.8446400016200142e-05, "loss": 0.9065, "step": 3501 }, { "epoch": 0.20455607476635515, "grad_norm": 1.5892508029937744, "learning_rate": 1.8445387096393812e-05, "loss": 0.9613, "step": 3502 }, { "epoch": 0.2046144859813084, "grad_norm": 1.4552589654922485, "learning_rate": 1.844437387432153e-05, "loss": 0.783, "step": 3503 }, { "epoch": 0.2046728971962617, "grad_norm": 2.54052996635437, "learning_rate": 1.8443360350019548e-05, "loss": 1.0251, "step": 3504 }, { "epoch": 0.20473130841121495, "grad_norm": 1.5491102933883667, "learning_rate": 1.844234652352415e-05, "loss": 0.9153, "step": 3505 }, { "epoch": 0.20478971962616824, "grad_norm": 1.565938949584961, "learning_rate": 1.8441332394871615e-05, "loss": 0.9814, "step": 3506 }, { "epoch": 0.2048481308411215, "grad_norm": 1.9119702577590942, "learning_rate": 1.844031796409825e-05, "loss": 0.8911, "step": 3507 }, { "epoch": 0.20490654205607475, "grad_norm": 1.66914963722229, "learning_rate": 1.843930323124035e-05, "loss": 0.8077, "step": 3508 }, { "epoch": 0.20496495327102804, "grad_norm": 1.8150463104248047, "learning_rate": 1.843828819633424e-05, "loss": 0.9625, "step": 3509 }, { "epoch": 0.2050233644859813, "grad_norm": 1.0766059160232544, "learning_rate": 1.843727285941625e-05, "loss": 0.9071, "step": 3510 }, { "epoch": 0.20508177570093458, "grad_norm": 1.2114036083221436, "learning_rate": 1.8436257220522718e-05, "loss": 0.8501, "step": 3511 }, { "epoch": 0.20514018691588784, "grad_norm": 1.3215141296386719, "learning_rate": 1.843524127968999e-05, "loss": 0.9678, "step": 3512 }, { "epoch": 0.20519859813084113, "grad_norm": 1.4756487607955933, "learning_rate": 1.8434225036954427e-05, "loss": 0.9929, "step": 3513 }, { "epoch": 0.20525700934579438, "grad_norm": 1.4723604917526245, "learning_rate": 1.843320849235241e-05, "loss": 0.9721, "step": 3514 }, { "epoch": 0.20531542056074767, "grad_norm": 1.26755690574646, "learning_rate": 1.8432191645920314e-05, "loss": 0.9099, "step": 3515 }, { "epoch": 0.20537383177570093, "grad_norm": 1.8224551677703857, "learning_rate": 1.8431174497694533e-05, "loss": 0.9678, "step": 3516 }, { "epoch": 0.2054322429906542, "grad_norm": 1.4403197765350342, "learning_rate": 1.8430157047711473e-05, "loss": 0.9123, "step": 3517 }, { "epoch": 0.20549065420560747, "grad_norm": 2.046687602996826, "learning_rate": 1.8429139296007552e-05, "loss": 0.8089, "step": 3518 }, { "epoch": 0.20554906542056076, "grad_norm": 2.0953121185302734, "learning_rate": 1.8428121242619193e-05, "loss": 0.7745, "step": 3519 }, { "epoch": 0.205607476635514, "grad_norm": 2.601100206375122, "learning_rate": 1.842710288758283e-05, "loss": 0.9025, "step": 3520 }, { "epoch": 0.2056658878504673, "grad_norm": 1.636977195739746, "learning_rate": 1.8426084230934916e-05, "loss": 0.7088, "step": 3521 }, { "epoch": 0.20572429906542056, "grad_norm": 2.136629581451416, "learning_rate": 1.8425065272711912e-05, "loss": 1.0076, "step": 3522 }, { "epoch": 0.20578271028037384, "grad_norm": 1.192103624343872, "learning_rate": 1.8424046012950274e-05, "loss": 0.6783, "step": 3523 }, { "epoch": 0.2058411214953271, "grad_norm": 1.9056594371795654, "learning_rate": 1.8423026451686493e-05, "loss": 0.7932, "step": 3524 }, { "epoch": 0.2058995327102804, "grad_norm": 1.772709608078003, "learning_rate": 1.842200658895706e-05, "loss": 1.0679, "step": 3525 }, { "epoch": 0.20595794392523364, "grad_norm": 1.5129585266113281, "learning_rate": 1.8420986424798472e-05, "loss": 0.7922, "step": 3526 }, { "epoch": 0.20601635514018693, "grad_norm": 1.7875357866287231, "learning_rate": 1.8419965959247243e-05, "loss": 0.8985, "step": 3527 }, { "epoch": 0.2060747663551402, "grad_norm": 1.7312372922897339, "learning_rate": 1.8418945192339892e-05, "loss": 0.8097, "step": 3528 }, { "epoch": 0.20613317757009345, "grad_norm": 1.803390622138977, "learning_rate": 1.8417924124112964e-05, "loss": 0.9575, "step": 3529 }, { "epoch": 0.20619158878504673, "grad_norm": 1.5581718683242798, "learning_rate": 1.841690275460299e-05, "loss": 0.855, "step": 3530 }, { "epoch": 0.20625, "grad_norm": 2.65433931350708, "learning_rate": 1.8415881083846537e-05, "loss": 1.0897, "step": 3531 }, { "epoch": 0.20630841121495327, "grad_norm": 1.1827521324157715, "learning_rate": 1.8414859111880164e-05, "loss": 0.9466, "step": 3532 }, { "epoch": 0.20636682242990653, "grad_norm": 1.7220945358276367, "learning_rate": 1.8413836838740452e-05, "loss": 0.9573, "step": 3533 }, { "epoch": 0.20642523364485982, "grad_norm": 1.1187340021133423, "learning_rate": 1.8412814264463987e-05, "loss": 0.8073, "step": 3534 }, { "epoch": 0.20648364485981308, "grad_norm": 1.1323539018630981, "learning_rate": 1.8411791389087367e-05, "loss": 0.6416, "step": 3535 }, { "epoch": 0.20654205607476636, "grad_norm": 1.6145380735397339, "learning_rate": 1.8410768212647204e-05, "loss": 0.9335, "step": 3536 }, { "epoch": 0.20660046728971962, "grad_norm": 1.8286635875701904, "learning_rate": 1.8409744735180113e-05, "loss": 0.9594, "step": 3537 }, { "epoch": 0.2066588785046729, "grad_norm": 1.3891552686691284, "learning_rate": 1.840872095672273e-05, "loss": 0.9017, "step": 3538 }, { "epoch": 0.20671728971962616, "grad_norm": 1.7164583206176758, "learning_rate": 1.8407696877311697e-05, "loss": 0.7575, "step": 3539 }, { "epoch": 0.20677570093457945, "grad_norm": 1.2985252141952515, "learning_rate": 1.8406672496983664e-05, "loss": 0.8753, "step": 3540 }, { "epoch": 0.2068341121495327, "grad_norm": 1.5596321821212769, "learning_rate": 1.8405647815775298e-05, "loss": 0.8769, "step": 3541 }, { "epoch": 0.206892523364486, "grad_norm": 1.5318092107772827, "learning_rate": 1.840462283372326e-05, "loss": 0.8465, "step": 3542 }, { "epoch": 0.20695093457943925, "grad_norm": 0.9763494729995728, "learning_rate": 1.8403597550864255e-05, "loss": 0.7805, "step": 3543 }, { "epoch": 0.20700934579439254, "grad_norm": 1.3406753540039062, "learning_rate": 1.8402571967234962e-05, "loss": 0.8497, "step": 3544 }, { "epoch": 0.2070677570093458, "grad_norm": 1.6144824028015137, "learning_rate": 1.8401546082872097e-05, "loss": 0.738, "step": 3545 }, { "epoch": 0.20712616822429908, "grad_norm": 1.613809585571289, "learning_rate": 1.840051989781237e-05, "loss": 0.8991, "step": 3546 }, { "epoch": 0.20718457943925234, "grad_norm": 1.4596112966537476, "learning_rate": 1.8399493412092516e-05, "loss": 0.7471, "step": 3547 }, { "epoch": 0.2072429906542056, "grad_norm": 1.0087040662765503, "learning_rate": 1.839846662574927e-05, "loss": 0.6765, "step": 3548 }, { "epoch": 0.20730140186915888, "grad_norm": 1.2846238613128662, "learning_rate": 1.839743953881938e-05, "loss": 0.7679, "step": 3549 }, { "epoch": 0.20735981308411214, "grad_norm": 1.8884267807006836, "learning_rate": 1.8396412151339605e-05, "loss": 0.9495, "step": 3550 }, { "epoch": 0.20741822429906542, "grad_norm": 1.719852328300476, "learning_rate": 1.839538446334672e-05, "loss": 0.903, "step": 3551 }, { "epoch": 0.20747663551401868, "grad_norm": 1.8086363077163696, "learning_rate": 1.8394356474877507e-05, "loss": 0.9377, "step": 3552 }, { "epoch": 0.20753504672897197, "grad_norm": 1.2443159818649292, "learning_rate": 1.8393328185968756e-05, "loss": 0.7806, "step": 3553 }, { "epoch": 0.20759345794392522, "grad_norm": 1.7241371870040894, "learning_rate": 1.839229959665727e-05, "loss": 0.8766, "step": 3554 }, { "epoch": 0.2076518691588785, "grad_norm": 1.873390793800354, "learning_rate": 1.8391270706979864e-05, "loss": 0.7328, "step": 3555 }, { "epoch": 0.20771028037383177, "grad_norm": 1.9124053716659546, "learning_rate": 1.839024151697336e-05, "loss": 0.8695, "step": 3556 }, { "epoch": 0.20776869158878505, "grad_norm": 1.6230274438858032, "learning_rate": 1.8389212026674595e-05, "loss": 0.5844, "step": 3557 }, { "epoch": 0.2078271028037383, "grad_norm": 1.3442915678024292, "learning_rate": 1.8388182236120418e-05, "loss": 0.671, "step": 3558 }, { "epoch": 0.2078855140186916, "grad_norm": 1.7317215204238892, "learning_rate": 1.8387152145347684e-05, "loss": 0.7655, "step": 3559 }, { "epoch": 0.20794392523364486, "grad_norm": 1.3186670541763306, "learning_rate": 1.8386121754393256e-05, "loss": 0.7564, "step": 3560 }, { "epoch": 0.20800233644859814, "grad_norm": 2.0030710697174072, "learning_rate": 1.8385091063294022e-05, "loss": 0.8517, "step": 3561 }, { "epoch": 0.2080607476635514, "grad_norm": 1.9695762395858765, "learning_rate": 1.838406007208686e-05, "loss": 0.7465, "step": 3562 }, { "epoch": 0.20811915887850468, "grad_norm": 1.7429375648498535, "learning_rate": 1.838302878080868e-05, "loss": 0.7051, "step": 3563 }, { "epoch": 0.20817757009345794, "grad_norm": 1.301954746246338, "learning_rate": 1.8381997189496384e-05, "loss": 0.7413, "step": 3564 }, { "epoch": 0.20823598130841123, "grad_norm": 1.639243483543396, "learning_rate": 1.83809652981869e-05, "loss": 0.9132, "step": 3565 }, { "epoch": 0.20829439252336449, "grad_norm": 1.854836106300354, "learning_rate": 1.8379933106917158e-05, "loss": 0.8438, "step": 3566 }, { "epoch": 0.20835280373831774, "grad_norm": 1.3888899087905884, "learning_rate": 1.8378900615724097e-05, "loss": 0.8665, "step": 3567 }, { "epoch": 0.20841121495327103, "grad_norm": 2.181989908218384, "learning_rate": 1.8377867824644676e-05, "loss": 0.8742, "step": 3568 }, { "epoch": 0.2084696261682243, "grad_norm": 1.8556381464004517, "learning_rate": 1.8376834733715853e-05, "loss": 0.9366, "step": 3569 }, { "epoch": 0.20852803738317757, "grad_norm": 1.486741065979004, "learning_rate": 1.837580134297461e-05, "loss": 0.9937, "step": 3570 }, { "epoch": 0.20858644859813083, "grad_norm": 1.216598629951477, "learning_rate": 1.837476765245793e-05, "loss": 0.7301, "step": 3571 }, { "epoch": 0.20864485981308412, "grad_norm": 1.4924474954605103, "learning_rate": 1.8373733662202813e-05, "loss": 0.6882, "step": 3572 }, { "epoch": 0.20870327102803737, "grad_norm": 1.929900884628296, "learning_rate": 1.8372699372246255e-05, "loss": 0.8166, "step": 3573 }, { "epoch": 0.20876168224299066, "grad_norm": 1.5020684003829956, "learning_rate": 1.8371664782625287e-05, "loss": 0.8881, "step": 3574 }, { "epoch": 0.20882009345794392, "grad_norm": 1.1528575420379639, "learning_rate": 1.837062989337693e-05, "loss": 0.6449, "step": 3575 }, { "epoch": 0.2088785046728972, "grad_norm": 1.2277498245239258, "learning_rate": 1.8369594704538226e-05, "loss": 0.7831, "step": 3576 }, { "epoch": 0.20893691588785046, "grad_norm": 1.601645588874817, "learning_rate": 1.8368559216146223e-05, "loss": 0.9547, "step": 3577 }, { "epoch": 0.20899532710280375, "grad_norm": 1.6633100509643555, "learning_rate": 1.8367523428237984e-05, "loss": 0.9586, "step": 3578 }, { "epoch": 0.209053738317757, "grad_norm": 1.7535650730133057, "learning_rate": 1.836648734085058e-05, "loss": 0.9385, "step": 3579 }, { "epoch": 0.2091121495327103, "grad_norm": 1.737040400505066, "learning_rate": 1.8365450954021095e-05, "loss": 0.8995, "step": 3580 }, { "epoch": 0.20917056074766355, "grad_norm": 1.77913236618042, "learning_rate": 1.8364414267786615e-05, "loss": 1.0151, "step": 3581 }, { "epoch": 0.20922897196261683, "grad_norm": 1.226340889930725, "learning_rate": 1.836337728218425e-05, "loss": 0.6923, "step": 3582 }, { "epoch": 0.2092873831775701, "grad_norm": 2.526205539703369, "learning_rate": 1.836233999725112e-05, "loss": 0.8079, "step": 3583 }, { "epoch": 0.20934579439252338, "grad_norm": 1.722811222076416, "learning_rate": 1.8361302413024336e-05, "loss": 0.7653, "step": 3584 }, { "epoch": 0.20940420560747663, "grad_norm": 2.318674325942993, "learning_rate": 1.836026452954104e-05, "loss": 0.9323, "step": 3585 }, { "epoch": 0.20946261682242992, "grad_norm": 1.9957854747772217, "learning_rate": 1.8359226346838382e-05, "loss": 0.8375, "step": 3586 }, { "epoch": 0.20952102803738318, "grad_norm": 1.2912732362747192, "learning_rate": 1.835818786495352e-05, "loss": 0.8511, "step": 3587 }, { "epoch": 0.20957943925233644, "grad_norm": 2.05546236038208, "learning_rate": 1.8357149083923613e-05, "loss": 0.9013, "step": 3588 }, { "epoch": 0.20963785046728972, "grad_norm": 1.5074001550674438, "learning_rate": 1.8356110003785847e-05, "loss": 0.8649, "step": 3589 }, { "epoch": 0.20969626168224298, "grad_norm": 2.271939516067505, "learning_rate": 1.835507062457741e-05, "loss": 0.8367, "step": 3590 }, { "epoch": 0.20975467289719626, "grad_norm": 1.9530842304229736, "learning_rate": 1.8354030946335505e-05, "loss": 0.8614, "step": 3591 }, { "epoch": 0.20981308411214952, "grad_norm": 1.3411598205566406, "learning_rate": 1.8352990969097335e-05, "loss": 0.7879, "step": 3592 }, { "epoch": 0.2098714953271028, "grad_norm": 1.2463253736495972, "learning_rate": 1.8351950692900127e-05, "loss": 0.7586, "step": 3593 }, { "epoch": 0.20992990654205607, "grad_norm": 1.7867995500564575, "learning_rate": 1.8350910117781112e-05, "loss": 1.0232, "step": 3594 }, { "epoch": 0.20998831775700935, "grad_norm": 1.1866742372512817, "learning_rate": 1.8349869243777536e-05, "loss": 0.7636, "step": 3595 }, { "epoch": 0.2100467289719626, "grad_norm": 1.9838577508926392, "learning_rate": 1.834882807092665e-05, "loss": 0.8798, "step": 3596 }, { "epoch": 0.2101051401869159, "grad_norm": 1.52101469039917, "learning_rate": 1.8347786599265713e-05, "loss": 0.8735, "step": 3597 }, { "epoch": 0.21016355140186915, "grad_norm": 1.3007220029830933, "learning_rate": 1.8346744828832007e-05, "loss": 0.7049, "step": 3598 }, { "epoch": 0.21022196261682244, "grad_norm": 1.8269526958465576, "learning_rate": 1.834570275966282e-05, "loss": 0.9399, "step": 3599 }, { "epoch": 0.2102803738317757, "grad_norm": 1.8941364288330078, "learning_rate": 1.8344660391795437e-05, "loss": 1.0154, "step": 3600 }, { "epoch": 0.21033878504672898, "grad_norm": 1.4968161582946777, "learning_rate": 1.8343617725267172e-05, "loss": 0.706, "step": 3601 }, { "epoch": 0.21039719626168224, "grad_norm": 1.492566466331482, "learning_rate": 1.8342574760115348e-05, "loss": 0.9088, "step": 3602 }, { "epoch": 0.21045560747663553, "grad_norm": 1.3583070039749146, "learning_rate": 1.8341531496377284e-05, "loss": 0.8193, "step": 3603 }, { "epoch": 0.21051401869158878, "grad_norm": 1.1918777227401733, "learning_rate": 1.8340487934090326e-05, "loss": 0.6477, "step": 3604 }, { "epoch": 0.21057242990654207, "grad_norm": 2.189251661300659, "learning_rate": 1.833944407329182e-05, "loss": 0.8587, "step": 3605 }, { "epoch": 0.21063084112149533, "grad_norm": 1.1723434925079346, "learning_rate": 1.8338399914019126e-05, "loss": 0.9505, "step": 3606 }, { "epoch": 0.21068925233644858, "grad_norm": 1.5370293855667114, "learning_rate": 1.8337355456309617e-05, "loss": 0.9278, "step": 3607 }, { "epoch": 0.21074766355140187, "grad_norm": 1.118699312210083, "learning_rate": 1.8336310700200673e-05, "loss": 0.8737, "step": 3608 }, { "epoch": 0.21080607476635513, "grad_norm": 1.428660273551941, "learning_rate": 1.833526564572969e-05, "loss": 0.8906, "step": 3609 }, { "epoch": 0.2108644859813084, "grad_norm": 1.2219226360321045, "learning_rate": 1.8334220292934066e-05, "loss": 0.8888, "step": 3610 }, { "epoch": 0.21092289719626167, "grad_norm": 1.4081978797912598, "learning_rate": 1.833317464185122e-05, "loss": 0.9028, "step": 3611 }, { "epoch": 0.21098130841121496, "grad_norm": 2.2998499870300293, "learning_rate": 1.8332128692518576e-05, "loss": 0.7353, "step": 3612 }, { "epoch": 0.21103971962616822, "grad_norm": 1.7534292936325073, "learning_rate": 1.8331082444973565e-05, "loss": 0.7965, "step": 3613 }, { "epoch": 0.2110981308411215, "grad_norm": 1.9640884399414062, "learning_rate": 1.8330035899253634e-05, "loss": 1.0272, "step": 3614 }, { "epoch": 0.21115654205607476, "grad_norm": 2.349977970123291, "learning_rate": 1.8328989055396246e-05, "loss": 0.9674, "step": 3615 }, { "epoch": 0.21121495327102804, "grad_norm": 2.0642249584198, "learning_rate": 1.832794191343886e-05, "loss": 0.9325, "step": 3616 }, { "epoch": 0.2112733644859813, "grad_norm": 2.441877603530884, "learning_rate": 1.8326894473418958e-05, "loss": 0.8752, "step": 3617 }, { "epoch": 0.2113317757009346, "grad_norm": 1.325338363647461, "learning_rate": 1.8325846735374027e-05, "loss": 0.8812, "step": 3618 }, { "epoch": 0.21139018691588785, "grad_norm": 1.8458186388015747, "learning_rate": 1.832479869934157e-05, "loss": 0.8089, "step": 3619 }, { "epoch": 0.21144859813084113, "grad_norm": 1.9749810695648193, "learning_rate": 1.8323750365359092e-05, "loss": 0.9853, "step": 3620 }, { "epoch": 0.2115070093457944, "grad_norm": 1.9731290340423584, "learning_rate": 1.8322701733464114e-05, "loss": 1.0099, "step": 3621 }, { "epoch": 0.21156542056074767, "grad_norm": 2.8869941234588623, "learning_rate": 1.832165280369417e-05, "loss": 0.7844, "step": 3622 }, { "epoch": 0.21162383177570093, "grad_norm": 4.072784423828125, "learning_rate": 1.83206035760868e-05, "loss": 0.8538, "step": 3623 }, { "epoch": 0.21168224299065422, "grad_norm": 1.6002473831176758, "learning_rate": 1.8319554050679557e-05, "loss": 0.8199, "step": 3624 }, { "epoch": 0.21174065420560748, "grad_norm": 1.7317407131195068, "learning_rate": 1.8318504227510006e-05, "loss": 0.8595, "step": 3625 }, { "epoch": 0.21179906542056076, "grad_norm": 1.7417677640914917, "learning_rate": 1.8317454106615718e-05, "loss": 0.923, "step": 3626 }, { "epoch": 0.21185747663551402, "grad_norm": 1.6626486778259277, "learning_rate": 1.831640368803428e-05, "loss": 0.8391, "step": 3627 }, { "epoch": 0.21191588785046728, "grad_norm": 1.5132896900177002, "learning_rate": 1.8315352971803282e-05, "loss": 0.8302, "step": 3628 }, { "epoch": 0.21197429906542056, "grad_norm": 1.4940619468688965, "learning_rate": 1.8314301957960336e-05, "loss": 1.187, "step": 3629 }, { "epoch": 0.21203271028037382, "grad_norm": 1.5100268125534058, "learning_rate": 1.8313250646543057e-05, "loss": 0.8319, "step": 3630 }, { "epoch": 0.2120911214953271, "grad_norm": 1.4721859693527222, "learning_rate": 1.831219903758907e-05, "loss": 0.8026, "step": 3631 }, { "epoch": 0.21214953271028036, "grad_norm": 1.5908544063568115, "learning_rate": 1.8311147131136015e-05, "loss": 0.7024, "step": 3632 }, { "epoch": 0.21220794392523365, "grad_norm": 1.552046298980713, "learning_rate": 1.831009492722154e-05, "loss": 0.7701, "step": 3633 }, { "epoch": 0.2122663551401869, "grad_norm": 1.8610814809799194, "learning_rate": 1.8309042425883302e-05, "loss": 0.9261, "step": 3634 }, { "epoch": 0.2123247663551402, "grad_norm": 1.2383198738098145, "learning_rate": 1.8307989627158974e-05, "loss": 0.9422, "step": 3635 }, { "epoch": 0.21238317757009345, "grad_norm": 1.5449421405792236, "learning_rate": 1.8306936531086234e-05, "loss": 1.0662, "step": 3636 }, { "epoch": 0.21244158878504674, "grad_norm": 1.2085210084915161, "learning_rate": 1.830588313770277e-05, "loss": 0.8826, "step": 3637 }, { "epoch": 0.2125, "grad_norm": 1.4641751050949097, "learning_rate": 1.8304829447046294e-05, "loss": 0.866, "step": 3638 }, { "epoch": 0.21255841121495328, "grad_norm": 1.5482908487319946, "learning_rate": 1.8303775459154508e-05, "loss": 0.7687, "step": 3639 }, { "epoch": 0.21261682242990654, "grad_norm": 1.303477168083191, "learning_rate": 1.8302721174065136e-05, "loss": 0.8663, "step": 3640 }, { "epoch": 0.21267523364485982, "grad_norm": 1.636293888092041, "learning_rate": 1.8301666591815918e-05, "loss": 0.9055, "step": 3641 }, { "epoch": 0.21273364485981308, "grad_norm": 1.3380041122436523, "learning_rate": 1.8300611712444595e-05, "loss": 0.8209, "step": 3642 }, { "epoch": 0.21279205607476637, "grad_norm": 1.6211283206939697, "learning_rate": 1.8299556535988917e-05, "loss": 0.7898, "step": 3643 }, { "epoch": 0.21285046728971962, "grad_norm": 2.6186447143554688, "learning_rate": 1.8298501062486654e-05, "loss": 0.7137, "step": 3644 }, { "epoch": 0.2129088785046729, "grad_norm": 2.2239067554473877, "learning_rate": 1.8297445291975582e-05, "loss": 1.0301, "step": 3645 }, { "epoch": 0.21296728971962617, "grad_norm": 1.5477402210235596, "learning_rate": 1.829638922449349e-05, "loss": 0.8059, "step": 3646 }, { "epoch": 0.21302570093457943, "grad_norm": 1.6474194526672363, "learning_rate": 1.829533286007817e-05, "loss": 0.8849, "step": 3647 }, { "epoch": 0.2130841121495327, "grad_norm": 2.547515630722046, "learning_rate": 1.8294276198767434e-05, "loss": 1.0168, "step": 3648 }, { "epoch": 0.21314252336448597, "grad_norm": 1.253404140472412, "learning_rate": 1.82932192405991e-05, "loss": 0.7347, "step": 3649 }, { "epoch": 0.21320093457943926, "grad_norm": 2.420363187789917, "learning_rate": 1.8292161985610994e-05, "loss": 0.9471, "step": 3650 }, { "epoch": 0.2132593457943925, "grad_norm": 1.4705604314804077, "learning_rate": 1.829110443384096e-05, "loss": 0.8488, "step": 3651 }, { "epoch": 0.2133177570093458, "grad_norm": 1.4643343687057495, "learning_rate": 1.829004658532685e-05, "loss": 0.7912, "step": 3652 }, { "epoch": 0.21337616822429906, "grad_norm": 1.422391414642334, "learning_rate": 1.8288988440106513e-05, "loss": 0.7385, "step": 3653 }, { "epoch": 0.21343457943925234, "grad_norm": 1.7193251848220825, "learning_rate": 1.8287929998217836e-05, "loss": 0.6801, "step": 3654 }, { "epoch": 0.2134929906542056, "grad_norm": 1.2786962985992432, "learning_rate": 1.8286871259698696e-05, "loss": 0.934, "step": 3655 }, { "epoch": 0.21355140186915889, "grad_norm": 1.4215312004089355, "learning_rate": 1.8285812224586984e-05, "loss": 0.8661, "step": 3656 }, { "epoch": 0.21360981308411214, "grad_norm": 1.2744618654251099, "learning_rate": 1.82847528929206e-05, "loss": 0.6953, "step": 3657 }, { "epoch": 0.21366822429906543, "grad_norm": 1.438755989074707, "learning_rate": 1.8283693264737468e-05, "loss": 0.8851, "step": 3658 }, { "epoch": 0.2137266355140187, "grad_norm": 1.2499467134475708, "learning_rate": 1.8282633340075506e-05, "loss": 0.8861, "step": 3659 }, { "epoch": 0.21378504672897197, "grad_norm": 1.549492359161377, "learning_rate": 1.828157311897265e-05, "loss": 0.945, "step": 3660 }, { "epoch": 0.21384345794392523, "grad_norm": 1.0288233757019043, "learning_rate": 1.8280512601466846e-05, "loss": 0.7022, "step": 3661 }, { "epoch": 0.21390186915887852, "grad_norm": 2.9380319118499756, "learning_rate": 1.8279451787596052e-05, "loss": 0.7444, "step": 3662 }, { "epoch": 0.21396028037383177, "grad_norm": 1.5551611185073853, "learning_rate": 1.8278390677398235e-05, "loss": 0.8775, "step": 3663 }, { "epoch": 0.21401869158878506, "grad_norm": 1.0842458009719849, "learning_rate": 1.8277329270911374e-05, "loss": 0.7694, "step": 3664 }, { "epoch": 0.21407710280373832, "grad_norm": 4.898360729217529, "learning_rate": 1.8276267568173454e-05, "loss": 0.9619, "step": 3665 }, { "epoch": 0.21413551401869158, "grad_norm": 1.6428142786026, "learning_rate": 1.827520556922248e-05, "loss": 0.7719, "step": 3666 }, { "epoch": 0.21419392523364486, "grad_norm": 1.6022261381149292, "learning_rate": 1.8274143274096453e-05, "loss": 0.9769, "step": 3667 }, { "epoch": 0.21425233644859812, "grad_norm": 1.3343614339828491, "learning_rate": 1.8273080682833396e-05, "loss": 0.8491, "step": 3668 }, { "epoch": 0.2143107476635514, "grad_norm": 1.587766170501709, "learning_rate": 1.8272017795471345e-05, "loss": 0.8224, "step": 3669 }, { "epoch": 0.21436915887850466, "grad_norm": 1.2123397588729858, "learning_rate": 1.8270954612048338e-05, "loss": 0.9103, "step": 3670 }, { "epoch": 0.21442757009345795, "grad_norm": 1.6469964981079102, "learning_rate": 1.826989113260243e-05, "loss": 0.693, "step": 3671 }, { "epoch": 0.2144859813084112, "grad_norm": 1.0951699018478394, "learning_rate": 1.8268827357171677e-05, "loss": 0.7029, "step": 3672 }, { "epoch": 0.2145443925233645, "grad_norm": 2.3130276203155518, "learning_rate": 1.8267763285794155e-05, "loss": 1.0189, "step": 3673 }, { "epoch": 0.21460280373831775, "grad_norm": 1.0855454206466675, "learning_rate": 1.8266698918507953e-05, "loss": 0.7977, "step": 3674 }, { "epoch": 0.21466121495327103, "grad_norm": 1.6879549026489258, "learning_rate": 1.826563425535116e-05, "loss": 0.9596, "step": 3675 }, { "epoch": 0.2147196261682243, "grad_norm": 1.2944927215576172, "learning_rate": 1.826456929636188e-05, "loss": 0.7924, "step": 3676 }, { "epoch": 0.21477803738317758, "grad_norm": 1.2947708368301392, "learning_rate": 1.826350404157823e-05, "loss": 0.7875, "step": 3677 }, { "epoch": 0.21483644859813084, "grad_norm": 1.6231284141540527, "learning_rate": 1.8262438491038342e-05, "loss": 0.8885, "step": 3678 }, { "epoch": 0.21489485981308412, "grad_norm": 1.37809157371521, "learning_rate": 1.8261372644780346e-05, "loss": 0.92, "step": 3679 }, { "epoch": 0.21495327102803738, "grad_norm": 1.745905876159668, "learning_rate": 1.8260306502842388e-05, "loss": 0.9588, "step": 3680 }, { "epoch": 0.21501168224299066, "grad_norm": 1.2370965480804443, "learning_rate": 1.825924006526263e-05, "loss": 0.7836, "step": 3681 }, { "epoch": 0.21507009345794392, "grad_norm": 1.590940237045288, "learning_rate": 1.825817333207924e-05, "loss": 0.7626, "step": 3682 }, { "epoch": 0.2151285046728972, "grad_norm": 1.2573927640914917, "learning_rate": 1.8257106303330398e-05, "loss": 0.698, "step": 3683 }, { "epoch": 0.21518691588785047, "grad_norm": 1.2441656589508057, "learning_rate": 1.8256038979054287e-05, "loss": 0.7957, "step": 3684 }, { "epoch": 0.21524532710280375, "grad_norm": 1.2644050121307373, "learning_rate": 1.825497135928912e-05, "loss": 0.9359, "step": 3685 }, { "epoch": 0.215303738317757, "grad_norm": 0.9853841066360474, "learning_rate": 1.82539034440731e-05, "loss": 0.6799, "step": 3686 }, { "epoch": 0.21536214953271027, "grad_norm": 1.0761257410049438, "learning_rate": 1.8252835233444443e-05, "loss": 0.9895, "step": 3687 }, { "epoch": 0.21542056074766355, "grad_norm": 1.9099414348602295, "learning_rate": 1.8251766727441393e-05, "loss": 0.855, "step": 3688 }, { "epoch": 0.2154789719626168, "grad_norm": 1.1675934791564941, "learning_rate": 1.8250697926102182e-05, "loss": 0.8823, "step": 3689 }, { "epoch": 0.2155373831775701, "grad_norm": 1.4601759910583496, "learning_rate": 1.8249628829465066e-05, "loss": 0.8426, "step": 3690 }, { "epoch": 0.21559579439252335, "grad_norm": 1.0716001987457275, "learning_rate": 1.824855943756831e-05, "loss": 0.8639, "step": 3691 }, { "epoch": 0.21565420560747664, "grad_norm": 1.6466447114944458, "learning_rate": 1.8247489750450193e-05, "loss": 0.9124, "step": 3692 }, { "epoch": 0.2157126168224299, "grad_norm": 1.2536439895629883, "learning_rate": 1.824641976814899e-05, "loss": 0.7738, "step": 3693 }, { "epoch": 0.21577102803738318, "grad_norm": 1.7067960500717163, "learning_rate": 1.8245349490703005e-05, "loss": 0.8401, "step": 3694 }, { "epoch": 0.21582943925233644, "grad_norm": 1.4360696077346802, "learning_rate": 1.824427891815054e-05, "loss": 0.8322, "step": 3695 }, { "epoch": 0.21588785046728973, "grad_norm": 1.3695071935653687, "learning_rate": 1.8243208050529907e-05, "loss": 0.9905, "step": 3696 }, { "epoch": 0.21594626168224298, "grad_norm": 3.792065143585205, "learning_rate": 1.8242136887879442e-05, "loss": 0.9615, "step": 3697 }, { "epoch": 0.21600467289719627, "grad_norm": 1.3844319581985474, "learning_rate": 1.8241065430237478e-05, "loss": 0.7452, "step": 3698 }, { "epoch": 0.21606308411214953, "grad_norm": 1.724884033203125, "learning_rate": 1.8239993677642362e-05, "loss": 0.7604, "step": 3699 }, { "epoch": 0.2161214953271028, "grad_norm": 1.325579285621643, "learning_rate": 1.8238921630132458e-05, "loss": 0.8671, "step": 3700 }, { "epoch": 0.21617990654205607, "grad_norm": 1.534001111984253, "learning_rate": 1.823784928774613e-05, "loss": 0.888, "step": 3701 }, { "epoch": 0.21623831775700936, "grad_norm": 2.0909223556518555, "learning_rate": 1.8236776650521756e-05, "loss": 1.011, "step": 3702 }, { "epoch": 0.21629672897196262, "grad_norm": 1.7241864204406738, "learning_rate": 1.8235703718497734e-05, "loss": 0.9441, "step": 3703 }, { "epoch": 0.2163551401869159, "grad_norm": 2.3529701232910156, "learning_rate": 1.823463049171246e-05, "loss": 1.0995, "step": 3704 }, { "epoch": 0.21641355140186916, "grad_norm": 1.8567997217178345, "learning_rate": 1.8233556970204346e-05, "loss": 1.0342, "step": 3705 }, { "epoch": 0.21647196261682242, "grad_norm": 1.8865264654159546, "learning_rate": 1.8232483154011815e-05, "loss": 1.0375, "step": 3706 }, { "epoch": 0.2165303738317757, "grad_norm": 1.2205793857574463, "learning_rate": 1.82314090431733e-05, "loss": 0.8216, "step": 3707 }, { "epoch": 0.21658878504672896, "grad_norm": 2.628530502319336, "learning_rate": 1.823033463772724e-05, "loss": 0.9968, "step": 3708 }, { "epoch": 0.21664719626168225, "grad_norm": 1.0458345413208008, "learning_rate": 1.8229259937712093e-05, "loss": 0.7939, "step": 3709 }, { "epoch": 0.2167056074766355, "grad_norm": 1.932813048362732, "learning_rate": 1.8228184943166324e-05, "loss": 0.802, "step": 3710 }, { "epoch": 0.2167640186915888, "grad_norm": 1.6331835985183716, "learning_rate": 1.8227109654128402e-05, "loss": 1.0241, "step": 3711 }, { "epoch": 0.21682242990654205, "grad_norm": 2.068729877471924, "learning_rate": 1.822603407063682e-05, "loss": 0.8335, "step": 3712 }, { "epoch": 0.21688084112149533, "grad_norm": 1.1740508079528809, "learning_rate": 1.8224958192730066e-05, "loss": 0.7053, "step": 3713 }, { "epoch": 0.2169392523364486, "grad_norm": 1.9261000156402588, "learning_rate": 1.822388202044665e-05, "loss": 0.984, "step": 3714 }, { "epoch": 0.21699766355140188, "grad_norm": 1.5628117322921753, "learning_rate": 1.8222805553825094e-05, "loss": 0.7447, "step": 3715 }, { "epoch": 0.21705607476635513, "grad_norm": 1.5246200561523438, "learning_rate": 1.822172879290392e-05, "loss": 0.6208, "step": 3716 }, { "epoch": 0.21711448598130842, "grad_norm": 1.3305890560150146, "learning_rate": 1.8220651737721664e-05, "loss": 0.7147, "step": 3717 }, { "epoch": 0.21717289719626168, "grad_norm": 1.6294654607772827, "learning_rate": 1.8219574388316877e-05, "loss": 0.806, "step": 3718 }, { "epoch": 0.21723130841121496, "grad_norm": 1.2206389904022217, "learning_rate": 1.821849674472812e-05, "loss": 0.7958, "step": 3719 }, { "epoch": 0.21728971962616822, "grad_norm": 1.2310298681259155, "learning_rate": 1.821741880699396e-05, "loss": 0.8787, "step": 3720 }, { "epoch": 0.2173481308411215, "grad_norm": 1.92970871925354, "learning_rate": 1.8216340575152976e-05, "loss": 0.8358, "step": 3721 }, { "epoch": 0.21740654205607476, "grad_norm": 1.1849515438079834, "learning_rate": 1.8215262049243762e-05, "loss": 0.8049, "step": 3722 }, { "epoch": 0.21746495327102805, "grad_norm": 1.3861024379730225, "learning_rate": 1.8214183229304917e-05, "loss": 0.7616, "step": 3723 }, { "epoch": 0.2175233644859813, "grad_norm": 1.5060944557189941, "learning_rate": 1.8213104115375057e-05, "loss": 0.9607, "step": 3724 }, { "epoch": 0.2175817757009346, "grad_norm": 1.2128725051879883, "learning_rate": 1.8212024707492794e-05, "loss": 0.8427, "step": 3725 }, { "epoch": 0.21764018691588785, "grad_norm": 1.4679263830184937, "learning_rate": 1.8210945005696773e-05, "loss": 0.9809, "step": 3726 }, { "epoch": 0.2176985981308411, "grad_norm": 1.4793184995651245, "learning_rate": 1.820986501002563e-05, "loss": 0.8426, "step": 3727 }, { "epoch": 0.2177570093457944, "grad_norm": 1.8030916452407837, "learning_rate": 1.820878472051802e-05, "loss": 0.947, "step": 3728 }, { "epoch": 0.21781542056074765, "grad_norm": 1.815320611000061, "learning_rate": 1.8207704137212605e-05, "loss": 0.9792, "step": 3729 }, { "epoch": 0.21787383177570094, "grad_norm": 1.675586223602295, "learning_rate": 1.8206623260148063e-05, "loss": 0.7389, "step": 3730 }, { "epoch": 0.2179322429906542, "grad_norm": 1.4841006994247437, "learning_rate": 1.820554208936308e-05, "loss": 0.9204, "step": 3731 }, { "epoch": 0.21799065420560748, "grad_norm": 1.6923390626907349, "learning_rate": 1.820446062489635e-05, "loss": 0.8189, "step": 3732 }, { "epoch": 0.21804906542056074, "grad_norm": 1.465726375579834, "learning_rate": 1.8203378866786578e-05, "loss": 1.0231, "step": 3733 }, { "epoch": 0.21810747663551402, "grad_norm": 1.0179802179336548, "learning_rate": 1.8202296815072486e-05, "loss": 0.6824, "step": 3734 }, { "epoch": 0.21816588785046728, "grad_norm": 1.724619746208191, "learning_rate": 1.8201214469792793e-05, "loss": 0.9177, "step": 3735 }, { "epoch": 0.21822429906542057, "grad_norm": 1.064394235610962, "learning_rate": 1.8200131830986247e-05, "loss": 0.8539, "step": 3736 }, { "epoch": 0.21828271028037383, "grad_norm": 2.354377269744873, "learning_rate": 1.8199048898691587e-05, "loss": 0.9869, "step": 3737 }, { "epoch": 0.2183411214953271, "grad_norm": 1.8847317695617676, "learning_rate": 1.8197965672947577e-05, "loss": 0.9636, "step": 3738 }, { "epoch": 0.21839953271028037, "grad_norm": 1.649509072303772, "learning_rate": 1.8196882153792986e-05, "loss": 0.8272, "step": 3739 }, { "epoch": 0.21845794392523366, "grad_norm": 1.4649264812469482, "learning_rate": 1.8195798341266594e-05, "loss": 0.6825, "step": 3740 }, { "epoch": 0.2185163551401869, "grad_norm": 2.0828664302825928, "learning_rate": 1.8194714235407192e-05, "loss": 0.8303, "step": 3741 }, { "epoch": 0.2185747663551402, "grad_norm": 1.3786146640777588, "learning_rate": 1.8193629836253576e-05, "loss": 0.8806, "step": 3742 }, { "epoch": 0.21863317757009346, "grad_norm": 2.3934152126312256, "learning_rate": 1.819254514384456e-05, "loss": 1.0016, "step": 3743 }, { "epoch": 0.21869158878504674, "grad_norm": 1.2063428163528442, "learning_rate": 1.819146015821897e-05, "loss": 0.8158, "step": 3744 }, { "epoch": 0.21875, "grad_norm": 1.6360461711883545, "learning_rate": 1.8190374879415634e-05, "loss": 0.7254, "step": 3745 }, { "epoch": 0.21880841121495326, "grad_norm": 1.4823569059371948, "learning_rate": 1.8189289307473396e-05, "loss": 0.8018, "step": 3746 }, { "epoch": 0.21886682242990654, "grad_norm": 1.9709851741790771, "learning_rate": 1.8188203442431107e-05, "loss": 0.9305, "step": 3747 }, { "epoch": 0.2189252336448598, "grad_norm": 1.7172255516052246, "learning_rate": 1.8187117284327636e-05, "loss": 0.871, "step": 3748 }, { "epoch": 0.2189836448598131, "grad_norm": 2.2780423164367676, "learning_rate": 1.8186030833201852e-05, "loss": 0.9429, "step": 3749 }, { "epoch": 0.21904205607476634, "grad_norm": 1.367849349975586, "learning_rate": 1.8184944089092643e-05, "loss": 0.7007, "step": 3750 }, { "epoch": 0.21910046728971963, "grad_norm": 1.9434090852737427, "learning_rate": 1.8183857052038902e-05, "loss": 1.0239, "step": 3751 }, { "epoch": 0.2191588785046729, "grad_norm": 1.9017218351364136, "learning_rate": 1.8182769722079538e-05, "loss": 0.9799, "step": 3752 }, { "epoch": 0.21921728971962617, "grad_norm": 1.4640278816223145, "learning_rate": 1.818168209925346e-05, "loss": 0.8517, "step": 3753 }, { "epoch": 0.21927570093457943, "grad_norm": 1.539737343788147, "learning_rate": 1.8180594183599606e-05, "loss": 0.7558, "step": 3754 }, { "epoch": 0.21933411214953272, "grad_norm": 1.4697128534317017, "learning_rate": 1.8179505975156907e-05, "loss": 0.9101, "step": 3755 }, { "epoch": 0.21939252336448598, "grad_norm": 1.1680446863174438, "learning_rate": 1.8178417473964308e-05, "loss": 0.8444, "step": 3756 }, { "epoch": 0.21945093457943926, "grad_norm": 1.477705478668213, "learning_rate": 1.8177328680060774e-05, "loss": 0.924, "step": 3757 }, { "epoch": 0.21950934579439252, "grad_norm": 1.5812221765518188, "learning_rate": 1.8176239593485267e-05, "loss": 0.9416, "step": 3758 }, { "epoch": 0.2195677570093458, "grad_norm": 1.9871543645858765, "learning_rate": 1.817515021427677e-05, "loss": 0.8952, "step": 3759 }, { "epoch": 0.21962616822429906, "grad_norm": 1.400436520576477, "learning_rate": 1.8174060542474272e-05, "loss": 0.7563, "step": 3760 }, { "epoch": 0.21968457943925235, "grad_norm": 1.270986557006836, "learning_rate": 1.8172970578116773e-05, "loss": 1.053, "step": 3761 }, { "epoch": 0.2197429906542056, "grad_norm": 1.5010533332824707, "learning_rate": 1.817188032124328e-05, "loss": 0.7091, "step": 3762 }, { "epoch": 0.2198014018691589, "grad_norm": 1.5315437316894531, "learning_rate": 1.817078977189282e-05, "loss": 0.9103, "step": 3763 }, { "epoch": 0.21985981308411215, "grad_norm": 1.6562800407409668, "learning_rate": 1.816969893010442e-05, "loss": 0.926, "step": 3764 }, { "epoch": 0.2199182242990654, "grad_norm": 1.4998023509979248, "learning_rate": 1.8168607795917128e-05, "loss": 0.9353, "step": 3765 }, { "epoch": 0.2199766355140187, "grad_norm": 1.4323744773864746, "learning_rate": 1.816751636936999e-05, "loss": 0.9035, "step": 3766 }, { "epoch": 0.22003504672897195, "grad_norm": 1.5232857465744019, "learning_rate": 1.8166424650502067e-05, "loss": 1.0501, "step": 3767 }, { "epoch": 0.22009345794392524, "grad_norm": 1.316493272781372, "learning_rate": 1.8165332639352437e-05, "loss": 0.8213, "step": 3768 }, { "epoch": 0.2201518691588785, "grad_norm": 1.2592123746871948, "learning_rate": 1.8164240335960186e-05, "loss": 0.9726, "step": 3769 }, { "epoch": 0.22021028037383178, "grad_norm": 1.7642414569854736, "learning_rate": 1.8163147740364405e-05, "loss": 0.8253, "step": 3770 }, { "epoch": 0.22026869158878504, "grad_norm": 1.5153595209121704, "learning_rate": 1.8162054852604196e-05, "loss": 0.905, "step": 3771 }, { "epoch": 0.22032710280373832, "grad_norm": 1.2984910011291504, "learning_rate": 1.816096167271868e-05, "loss": 0.9689, "step": 3772 }, { "epoch": 0.22038551401869158, "grad_norm": 1.4805145263671875, "learning_rate": 1.8159868200746983e-05, "loss": 1.0083, "step": 3773 }, { "epoch": 0.22044392523364487, "grad_norm": 2.0292773246765137, "learning_rate": 1.815877443672823e-05, "loss": 0.9883, "step": 3774 }, { "epoch": 0.22050233644859812, "grad_norm": 1.561828851699829, "learning_rate": 1.815768038070158e-05, "loss": 0.7565, "step": 3775 }, { "epoch": 0.2205607476635514, "grad_norm": 1.0552695989608765, "learning_rate": 1.8156586032706185e-05, "loss": 0.9253, "step": 3776 }, { "epoch": 0.22061915887850467, "grad_norm": 1.4709917306900024, "learning_rate": 1.8155491392781214e-05, "loss": 0.7618, "step": 3777 }, { "epoch": 0.22067757009345795, "grad_norm": 1.4930452108383179, "learning_rate": 1.8154396460965843e-05, "loss": 0.9271, "step": 3778 }, { "epoch": 0.2207359813084112, "grad_norm": 1.4129128456115723, "learning_rate": 1.815330123729926e-05, "loss": 0.8582, "step": 3779 }, { "epoch": 0.2207943925233645, "grad_norm": 1.7195541858673096, "learning_rate": 1.8152205721820663e-05, "loss": 0.7325, "step": 3780 }, { "epoch": 0.22085280373831775, "grad_norm": 1.690092921257019, "learning_rate": 1.8151109914569267e-05, "loss": 0.8523, "step": 3781 }, { "epoch": 0.22091121495327104, "grad_norm": 1.891892671585083, "learning_rate": 1.8150013815584287e-05, "loss": 0.8576, "step": 3782 }, { "epoch": 0.2209696261682243, "grad_norm": 1.5611928701400757, "learning_rate": 1.8148917424904952e-05, "loss": 0.7427, "step": 3783 }, { "epoch": 0.22102803738317758, "grad_norm": 2.110342502593994, "learning_rate": 1.8147820742570506e-05, "loss": 0.9113, "step": 3784 }, { "epoch": 0.22108644859813084, "grad_norm": 1.846060872077942, "learning_rate": 1.8146723768620197e-05, "loss": 0.8749, "step": 3785 }, { "epoch": 0.2211448598130841, "grad_norm": 1.8824124336242676, "learning_rate": 1.8145626503093287e-05, "loss": 0.672, "step": 3786 }, { "epoch": 0.22120327102803738, "grad_norm": 1.6806719303131104, "learning_rate": 1.814452894602905e-05, "loss": 0.9621, "step": 3787 }, { "epoch": 0.22126168224299064, "grad_norm": 1.958319067955017, "learning_rate": 1.8143431097466765e-05, "loss": 0.9235, "step": 3788 }, { "epoch": 0.22132009345794393, "grad_norm": 0.885739266872406, "learning_rate": 1.814233295744573e-05, "loss": 0.622, "step": 3789 }, { "epoch": 0.2213785046728972, "grad_norm": 1.3991111516952515, "learning_rate": 1.8141234526005242e-05, "loss": 0.8262, "step": 3790 }, { "epoch": 0.22143691588785047, "grad_norm": 1.4907749891281128, "learning_rate": 1.8140135803184618e-05, "loss": 0.8719, "step": 3791 }, { "epoch": 0.22149532710280373, "grad_norm": 1.2663850784301758, "learning_rate": 1.8139036789023183e-05, "loss": 0.7569, "step": 3792 }, { "epoch": 0.22155373831775702, "grad_norm": 1.9428765773773193, "learning_rate": 1.8137937483560267e-05, "loss": 0.8885, "step": 3793 }, { "epoch": 0.22161214953271027, "grad_norm": 1.7519043684005737, "learning_rate": 1.8136837886835222e-05, "loss": 0.8164, "step": 3794 }, { "epoch": 0.22167056074766356, "grad_norm": 1.5022801160812378, "learning_rate": 1.8135737998887396e-05, "loss": 0.8512, "step": 3795 }, { "epoch": 0.22172897196261682, "grad_norm": 1.3566371202468872, "learning_rate": 1.8134637819756154e-05, "loss": 0.908, "step": 3796 }, { "epoch": 0.2217873831775701, "grad_norm": 1.6724507808685303, "learning_rate": 1.813353734948088e-05, "loss": 0.7826, "step": 3797 }, { "epoch": 0.22184579439252336, "grad_norm": 1.2908517122268677, "learning_rate": 1.813243658810096e-05, "loss": 0.9046, "step": 3798 }, { "epoch": 0.22190420560747665, "grad_norm": 2.2720139026641846, "learning_rate": 1.813133553565578e-05, "loss": 0.9181, "step": 3799 }, { "epoch": 0.2219626168224299, "grad_norm": 1.267689824104309, "learning_rate": 1.813023419218476e-05, "loss": 0.8479, "step": 3800 }, { "epoch": 0.2220210280373832, "grad_norm": 2.478743314743042, "learning_rate": 1.8129132557727312e-05, "loss": 1.0779, "step": 3801 }, { "epoch": 0.22207943925233645, "grad_norm": 1.4572290182113647, "learning_rate": 1.812803063232286e-05, "loss": 1.0295, "step": 3802 }, { "epoch": 0.22213785046728973, "grad_norm": 1.683297038078308, "learning_rate": 1.812692841601085e-05, "loss": 0.7325, "step": 3803 }, { "epoch": 0.222196261682243, "grad_norm": 1.1282548904418945, "learning_rate": 1.8125825908830733e-05, "loss": 0.747, "step": 3804 }, { "epoch": 0.22225467289719625, "grad_norm": 1.619830846786499, "learning_rate": 1.8124723110821958e-05, "loss": 0.7783, "step": 3805 }, { "epoch": 0.22231308411214953, "grad_norm": 1.1291215419769287, "learning_rate": 1.8123620022024004e-05, "loss": 0.7441, "step": 3806 }, { "epoch": 0.2223714953271028, "grad_norm": 1.6596626043319702, "learning_rate": 1.8122516642476346e-05, "loss": 0.9413, "step": 3807 }, { "epoch": 0.22242990654205608, "grad_norm": 1.392484188079834, "learning_rate": 1.8121412972218476e-05, "loss": 0.9297, "step": 3808 }, { "epoch": 0.22248831775700934, "grad_norm": 2.001882314682007, "learning_rate": 1.8120309011289897e-05, "loss": 0.9618, "step": 3809 }, { "epoch": 0.22254672897196262, "grad_norm": 1.3406301736831665, "learning_rate": 1.811920475973012e-05, "loss": 0.7994, "step": 3810 }, { "epoch": 0.22260514018691588, "grad_norm": 1.4343708753585815, "learning_rate": 1.8118100217578666e-05, "loss": 0.8353, "step": 3811 }, { "epoch": 0.22266355140186916, "grad_norm": 1.510138750076294, "learning_rate": 1.8116995384875067e-05, "loss": 0.9479, "step": 3812 }, { "epoch": 0.22272196261682242, "grad_norm": 1.5045315027236938, "learning_rate": 1.811589026165887e-05, "loss": 0.918, "step": 3813 }, { "epoch": 0.2227803738317757, "grad_norm": 1.413304328918457, "learning_rate": 1.8114784847969618e-05, "loss": 0.8076, "step": 3814 }, { "epoch": 0.22283878504672897, "grad_norm": 1.5085285902023315, "learning_rate": 1.8113679143846884e-05, "loss": 0.7649, "step": 3815 }, { "epoch": 0.22289719626168225, "grad_norm": 1.3365752696990967, "learning_rate": 1.8112573149330238e-05, "loss": 0.6771, "step": 3816 }, { "epoch": 0.2229556074766355, "grad_norm": 1.996303677558899, "learning_rate": 1.8111466864459262e-05, "loss": 0.8925, "step": 3817 }, { "epoch": 0.2230140186915888, "grad_norm": 1.903282642364502, "learning_rate": 1.8110360289273558e-05, "loss": 0.9066, "step": 3818 }, { "epoch": 0.22307242990654205, "grad_norm": 1.8145153522491455, "learning_rate": 1.8109253423812726e-05, "loss": 0.8399, "step": 3819 }, { "epoch": 0.22313084112149534, "grad_norm": 1.7807892560958862, "learning_rate": 1.810814626811638e-05, "loss": 0.7471, "step": 3820 }, { "epoch": 0.2231892523364486, "grad_norm": 2.176593780517578, "learning_rate": 1.810703882222415e-05, "loss": 0.6844, "step": 3821 }, { "epoch": 0.22324766355140188, "grad_norm": 1.7381647825241089, "learning_rate": 1.810593108617567e-05, "loss": 0.7991, "step": 3822 }, { "epoch": 0.22330607476635514, "grad_norm": 2.0022377967834473, "learning_rate": 1.8104823060010583e-05, "loss": 0.7416, "step": 3823 }, { "epoch": 0.22336448598130842, "grad_norm": 1.987228274345398, "learning_rate": 1.810371474376855e-05, "loss": 0.8329, "step": 3824 }, { "epoch": 0.22342289719626168, "grad_norm": 2.2820169925689697, "learning_rate": 1.810260613748924e-05, "loss": 0.9373, "step": 3825 }, { "epoch": 0.22348130841121494, "grad_norm": 1.520156979560852, "learning_rate": 1.810149724121233e-05, "loss": 0.9231, "step": 3826 }, { "epoch": 0.22353971962616823, "grad_norm": 1.4484199285507202, "learning_rate": 1.8100388054977508e-05, "loss": 0.9903, "step": 3827 }, { "epoch": 0.22359813084112148, "grad_norm": 1.21247136592865, "learning_rate": 1.809927857882447e-05, "loss": 0.6767, "step": 3828 }, { "epoch": 0.22365654205607477, "grad_norm": 1.5954110622406006, "learning_rate": 1.8098168812792926e-05, "loss": 0.9065, "step": 3829 }, { "epoch": 0.22371495327102803, "grad_norm": 1.2794904708862305, "learning_rate": 1.8097058756922596e-05, "loss": 0.8633, "step": 3830 }, { "epoch": 0.2237733644859813, "grad_norm": 1.8251442909240723, "learning_rate": 1.8095948411253207e-05, "loss": 0.931, "step": 3831 }, { "epoch": 0.22383177570093457, "grad_norm": 1.2578065395355225, "learning_rate": 1.80948377758245e-05, "loss": 0.7798, "step": 3832 }, { "epoch": 0.22389018691588786, "grad_norm": 1.7997664213180542, "learning_rate": 1.809372685067623e-05, "loss": 1.0222, "step": 3833 }, { "epoch": 0.22394859813084111, "grad_norm": 1.063572883605957, "learning_rate": 1.8092615635848153e-05, "loss": 0.8223, "step": 3834 }, { "epoch": 0.2240070093457944, "grad_norm": 1.7063714265823364, "learning_rate": 1.8091504131380044e-05, "loss": 0.86, "step": 3835 }, { "epoch": 0.22406542056074766, "grad_norm": 1.1117854118347168, "learning_rate": 1.8090392337311678e-05, "loss": 0.7689, "step": 3836 }, { "epoch": 0.22412383177570094, "grad_norm": 1.2440739870071411, "learning_rate": 1.8089280253682853e-05, "loss": 0.8695, "step": 3837 }, { "epoch": 0.2241822429906542, "grad_norm": 1.4431211948394775, "learning_rate": 1.808816788053337e-05, "loss": 0.918, "step": 3838 }, { "epoch": 0.2242406542056075, "grad_norm": 1.4201463460922241, "learning_rate": 1.8087055217903036e-05, "loss": 1.0773, "step": 3839 }, { "epoch": 0.22429906542056074, "grad_norm": 1.6350265741348267, "learning_rate": 1.8085942265831682e-05, "loss": 0.9012, "step": 3840 }, { "epoch": 0.22435747663551403, "grad_norm": 1.101607084274292, "learning_rate": 1.8084829024359135e-05, "loss": 0.7175, "step": 3841 }, { "epoch": 0.2244158878504673, "grad_norm": 1.5016087293624878, "learning_rate": 1.8083715493525243e-05, "loss": 0.8153, "step": 3842 }, { "epoch": 0.22447429906542057, "grad_norm": 1.4560964107513428, "learning_rate": 1.808260167336986e-05, "loss": 0.9313, "step": 3843 }, { "epoch": 0.22453271028037383, "grad_norm": 1.3076484203338623, "learning_rate": 1.8081487563932846e-05, "loss": 0.8798, "step": 3844 }, { "epoch": 0.2245911214953271, "grad_norm": 1.1114057302474976, "learning_rate": 1.8080373165254078e-05, "loss": 0.6835, "step": 3845 }, { "epoch": 0.22464953271028038, "grad_norm": 1.4395191669464111, "learning_rate": 1.8079258477373444e-05, "loss": 0.8774, "step": 3846 }, { "epoch": 0.22470794392523363, "grad_norm": 1.5263386964797974, "learning_rate": 1.8078143500330835e-05, "loss": 0.85, "step": 3847 }, { "epoch": 0.22476635514018692, "grad_norm": 2.2451894283294678, "learning_rate": 1.807702823416616e-05, "loss": 0.9651, "step": 3848 }, { "epoch": 0.22482476635514018, "grad_norm": 1.1275290250778198, "learning_rate": 1.8075912678919337e-05, "loss": 0.7321, "step": 3849 }, { "epoch": 0.22488317757009346, "grad_norm": 2.157855987548828, "learning_rate": 1.8074796834630285e-05, "loss": 0.8364, "step": 3850 }, { "epoch": 0.22494158878504672, "grad_norm": 1.2402451038360596, "learning_rate": 1.807368070133894e-05, "loss": 0.6991, "step": 3851 }, { "epoch": 0.225, "grad_norm": 1.9220527410507202, "learning_rate": 1.8072564279085262e-05, "loss": 0.8408, "step": 3852 }, { "epoch": 0.22505841121495326, "grad_norm": 1.130741834640503, "learning_rate": 1.80714475679092e-05, "loss": 0.906, "step": 3853 }, { "epoch": 0.22511682242990655, "grad_norm": 1.5834267139434814, "learning_rate": 1.807033056785072e-05, "loss": 0.8888, "step": 3854 }, { "epoch": 0.2251752336448598, "grad_norm": 1.3486289978027344, "learning_rate": 1.80692132789498e-05, "loss": 0.9205, "step": 3855 }, { "epoch": 0.2252336448598131, "grad_norm": 1.201651930809021, "learning_rate": 1.8068095701246438e-05, "loss": 0.7343, "step": 3856 }, { "epoch": 0.22529205607476635, "grad_norm": 1.8117215633392334, "learning_rate": 1.8066977834780625e-05, "loss": 0.952, "step": 3857 }, { "epoch": 0.22535046728971964, "grad_norm": 1.1573644876480103, "learning_rate": 1.8065859679592366e-05, "loss": 0.7799, "step": 3858 }, { "epoch": 0.2254088785046729, "grad_norm": 1.347595453262329, "learning_rate": 1.806474123572169e-05, "loss": 0.9327, "step": 3859 }, { "epoch": 0.22546728971962618, "grad_norm": 2.037909984588623, "learning_rate": 1.806362250320862e-05, "loss": 0.9095, "step": 3860 }, { "epoch": 0.22552570093457944, "grad_norm": 1.0521018505096436, "learning_rate": 1.8062503482093196e-05, "loss": 0.7303, "step": 3861 }, { "epoch": 0.22558411214953272, "grad_norm": 1.9847577810287476, "learning_rate": 1.8061384172415477e-05, "loss": 0.8053, "step": 3862 }, { "epoch": 0.22564252336448598, "grad_norm": 1.7529376745224, "learning_rate": 1.8060264574215516e-05, "loss": 0.7851, "step": 3863 }, { "epoch": 0.22570093457943924, "grad_norm": 1.3611057996749878, "learning_rate": 1.8059144687533386e-05, "loss": 0.7185, "step": 3864 }, { "epoch": 0.22575934579439252, "grad_norm": 1.3868669271469116, "learning_rate": 1.8058024512409167e-05, "loss": 0.8751, "step": 3865 }, { "epoch": 0.22581775700934578, "grad_norm": 1.4074386358261108, "learning_rate": 1.8056904048882957e-05, "loss": 0.9327, "step": 3866 }, { "epoch": 0.22587616822429907, "grad_norm": 1.4155093431472778, "learning_rate": 1.8055783296994848e-05, "loss": 0.8231, "step": 3867 }, { "epoch": 0.22593457943925233, "grad_norm": 1.7975575923919678, "learning_rate": 1.805466225678496e-05, "loss": 0.7565, "step": 3868 }, { "epoch": 0.2259929906542056, "grad_norm": 1.881483793258667, "learning_rate": 1.8053540928293418e-05, "loss": 0.9828, "step": 3869 }, { "epoch": 0.22605140186915887, "grad_norm": 1.7584292888641357, "learning_rate": 1.8052419311560343e-05, "loss": 0.79, "step": 3870 }, { "epoch": 0.22610981308411215, "grad_norm": 1.556365728378296, "learning_rate": 1.805129740662589e-05, "loss": 0.9687, "step": 3871 }, { "epoch": 0.2261682242990654, "grad_norm": 1.9773619174957275, "learning_rate": 1.8050175213530213e-05, "loss": 0.8155, "step": 3872 }, { "epoch": 0.2262266355140187, "grad_norm": 2.2035696506500244, "learning_rate": 1.8049052732313466e-05, "loss": 1.0548, "step": 3873 }, { "epoch": 0.22628504672897196, "grad_norm": 1.379366159439087, "learning_rate": 1.8047929963015834e-05, "loss": 0.8275, "step": 3874 }, { "epoch": 0.22634345794392524, "grad_norm": 1.5631484985351562, "learning_rate": 1.804680690567749e-05, "loss": 0.8399, "step": 3875 }, { "epoch": 0.2264018691588785, "grad_norm": 1.301284909248352, "learning_rate": 1.8045683560338643e-05, "loss": 0.7177, "step": 3876 }, { "epoch": 0.22646028037383178, "grad_norm": 1.4546127319335938, "learning_rate": 1.804455992703949e-05, "loss": 0.8979, "step": 3877 }, { "epoch": 0.22651869158878504, "grad_norm": 1.3490897417068481, "learning_rate": 1.8043436005820247e-05, "loss": 0.8313, "step": 3878 }, { "epoch": 0.22657710280373833, "grad_norm": 1.259905219078064, "learning_rate": 1.804231179672114e-05, "loss": 0.995, "step": 3879 }, { "epoch": 0.2266355140186916, "grad_norm": 1.127285122871399, "learning_rate": 1.8041187299782406e-05, "loss": 0.6331, "step": 3880 }, { "epoch": 0.22669392523364487, "grad_norm": 1.251664161682129, "learning_rate": 1.8040062515044292e-05, "loss": 0.7914, "step": 3881 }, { "epoch": 0.22675233644859813, "grad_norm": 0.9423952102661133, "learning_rate": 1.8038937442547057e-05, "loss": 0.6422, "step": 3882 }, { "epoch": 0.22681074766355142, "grad_norm": 1.1022876501083374, "learning_rate": 1.803781208233096e-05, "loss": 0.7812, "step": 3883 }, { "epoch": 0.22686915887850467, "grad_norm": 1.5114943981170654, "learning_rate": 1.8036686434436285e-05, "loss": 0.872, "step": 3884 }, { "epoch": 0.22692757009345793, "grad_norm": 1.3589484691619873, "learning_rate": 1.803556049890332e-05, "loss": 0.8328, "step": 3885 }, { "epoch": 0.22698598130841122, "grad_norm": 1.795180082321167, "learning_rate": 1.803443427577236e-05, "loss": 0.709, "step": 3886 }, { "epoch": 0.22704439252336447, "grad_norm": 3.5931477546691895, "learning_rate": 1.8033307765083714e-05, "loss": 1.065, "step": 3887 }, { "epoch": 0.22710280373831776, "grad_norm": 1.63896644115448, "learning_rate": 1.8032180966877703e-05, "loss": 0.8493, "step": 3888 }, { "epoch": 0.22716121495327102, "grad_norm": 2.33740234375, "learning_rate": 1.8031053881194652e-05, "loss": 0.9099, "step": 3889 }, { "epoch": 0.2272196261682243, "grad_norm": 1.9019449949264526, "learning_rate": 1.80299265080749e-05, "loss": 0.781, "step": 3890 }, { "epoch": 0.22727803738317756, "grad_norm": 1.7996306419372559, "learning_rate": 1.8028798847558803e-05, "loss": 0.8022, "step": 3891 }, { "epoch": 0.22733644859813085, "grad_norm": 2.47843074798584, "learning_rate": 1.8027670899686716e-05, "loss": 1.0236, "step": 3892 }, { "epoch": 0.2273948598130841, "grad_norm": 1.2525203227996826, "learning_rate": 1.802654266449901e-05, "loss": 0.7789, "step": 3893 }, { "epoch": 0.2274532710280374, "grad_norm": 1.4264098405838013, "learning_rate": 1.8025414142036058e-05, "loss": 0.7261, "step": 3894 }, { "epoch": 0.22751168224299065, "grad_norm": 1.494202971458435, "learning_rate": 1.8024285332338264e-05, "loss": 0.8598, "step": 3895 }, { "epoch": 0.22757009345794393, "grad_norm": 1.2198235988616943, "learning_rate": 1.802315623544602e-05, "loss": 0.6797, "step": 3896 }, { "epoch": 0.2276285046728972, "grad_norm": 1.79105544090271, "learning_rate": 1.8022026851399737e-05, "loss": 0.8428, "step": 3897 }, { "epoch": 0.22768691588785048, "grad_norm": 1.4998196363449097, "learning_rate": 1.802089718023984e-05, "loss": 0.9459, "step": 3898 }, { "epoch": 0.22774532710280374, "grad_norm": 1.3364930152893066, "learning_rate": 1.8019767222006756e-05, "loss": 0.6952, "step": 3899 }, { "epoch": 0.22780373831775702, "grad_norm": 1.7577773332595825, "learning_rate": 1.8018636976740934e-05, "loss": 0.9465, "step": 3900 }, { "epoch": 0.22786214953271028, "grad_norm": 1.7730281352996826, "learning_rate": 1.801750644448282e-05, "loss": 0.7409, "step": 3901 }, { "epoch": 0.22792056074766356, "grad_norm": 1.8323732614517212, "learning_rate": 1.801637562527288e-05, "loss": 0.6518, "step": 3902 }, { "epoch": 0.22797897196261682, "grad_norm": 1.387216567993164, "learning_rate": 1.8015244519151586e-05, "loss": 0.832, "step": 3903 }, { "epoch": 0.22803738317757008, "grad_norm": 1.324317455291748, "learning_rate": 1.801411312615942e-05, "loss": 0.7759, "step": 3904 }, { "epoch": 0.22809579439252337, "grad_norm": 2.123110771179199, "learning_rate": 1.8012981446336876e-05, "loss": 0.9127, "step": 3905 }, { "epoch": 0.22815420560747662, "grad_norm": 1.2443008422851562, "learning_rate": 1.801184947972446e-05, "loss": 0.7513, "step": 3906 }, { "epoch": 0.2282126168224299, "grad_norm": 1.5845894813537598, "learning_rate": 1.8010717226362677e-05, "loss": 0.889, "step": 3907 }, { "epoch": 0.22827102803738317, "grad_norm": 2.2042834758758545, "learning_rate": 1.8009584686292058e-05, "loss": 0.9584, "step": 3908 }, { "epoch": 0.22832943925233645, "grad_norm": 2.577134847640991, "learning_rate": 1.8008451859553143e-05, "loss": 0.9424, "step": 3909 }, { "epoch": 0.2283878504672897, "grad_norm": 1.7564305067062378, "learning_rate": 1.8007318746186464e-05, "loss": 0.6959, "step": 3910 }, { "epoch": 0.228446261682243, "grad_norm": 1.6187676191329956, "learning_rate": 1.8006185346232584e-05, "loss": 0.9963, "step": 3911 }, { "epoch": 0.22850467289719625, "grad_norm": 1.873719573020935, "learning_rate": 1.800505165973207e-05, "loss": 0.8458, "step": 3912 }, { "epoch": 0.22856308411214954, "grad_norm": 1.798729658126831, "learning_rate": 1.8003917686725486e-05, "loss": 0.874, "step": 3913 }, { "epoch": 0.2286214953271028, "grad_norm": 1.2239059209823608, "learning_rate": 1.8002783427253434e-05, "loss": 0.7114, "step": 3914 }, { "epoch": 0.22867990654205608, "grad_norm": 2.706392526626587, "learning_rate": 1.8001648881356496e-05, "loss": 1.1602, "step": 3915 }, { "epoch": 0.22873831775700934, "grad_norm": 1.5126479864120483, "learning_rate": 1.8000514049075283e-05, "loss": 0.9652, "step": 3916 }, { "epoch": 0.22879672897196263, "grad_norm": 1.9095978736877441, "learning_rate": 1.7999378930450414e-05, "loss": 0.7925, "step": 3917 }, { "epoch": 0.22885514018691588, "grad_norm": 1.7051154375076294, "learning_rate": 1.799824352552251e-05, "loss": 1.0129, "step": 3918 }, { "epoch": 0.22891355140186917, "grad_norm": 1.6432898044586182, "learning_rate": 1.7997107834332217e-05, "loss": 1.0201, "step": 3919 }, { "epoch": 0.22897196261682243, "grad_norm": 1.265046238899231, "learning_rate": 1.7995971856920172e-05, "loss": 0.795, "step": 3920 }, { "epoch": 0.2290303738317757, "grad_norm": 1.5258430242538452, "learning_rate": 1.7994835593327042e-05, "loss": 0.8658, "step": 3921 }, { "epoch": 0.22908878504672897, "grad_norm": 1.840064287185669, "learning_rate": 1.7993699043593483e-05, "loss": 1.0531, "step": 3922 }, { "epoch": 0.22914719626168226, "grad_norm": 1.330040693283081, "learning_rate": 1.799256220776018e-05, "loss": 0.9784, "step": 3923 }, { "epoch": 0.22920560747663551, "grad_norm": 2.2869060039520264, "learning_rate": 1.7991425085867823e-05, "loss": 1.0146, "step": 3924 }, { "epoch": 0.22926401869158877, "grad_norm": 1.510877251625061, "learning_rate": 1.7990287677957108e-05, "loss": 0.9486, "step": 3925 }, { "epoch": 0.22932242990654206, "grad_norm": 1.8620975017547607, "learning_rate": 1.798914998406874e-05, "loss": 0.8354, "step": 3926 }, { "epoch": 0.22938084112149532, "grad_norm": 1.2792811393737793, "learning_rate": 1.7988012004243446e-05, "loss": 0.6928, "step": 3927 }, { "epoch": 0.2294392523364486, "grad_norm": 1.3155885934829712, "learning_rate": 1.7986873738521947e-05, "loss": 0.8734, "step": 3928 }, { "epoch": 0.22949766355140186, "grad_norm": 1.374000072479248, "learning_rate": 1.7985735186944985e-05, "loss": 0.9481, "step": 3929 }, { "epoch": 0.22955607476635514, "grad_norm": 1.5831142663955688, "learning_rate": 1.798459634955331e-05, "loss": 0.8809, "step": 3930 }, { "epoch": 0.2296144859813084, "grad_norm": 1.402212142944336, "learning_rate": 1.7983457226387682e-05, "loss": 0.9573, "step": 3931 }, { "epoch": 0.2296728971962617, "grad_norm": 1.2006534337997437, "learning_rate": 1.7982317817488874e-05, "loss": 0.7625, "step": 3932 }, { "epoch": 0.22973130841121495, "grad_norm": 1.84760320186615, "learning_rate": 1.7981178122897657e-05, "loss": 0.9116, "step": 3933 }, { "epoch": 0.22978971962616823, "grad_norm": 1.3563446998596191, "learning_rate": 1.798003814265483e-05, "loss": 0.7804, "step": 3934 }, { "epoch": 0.2298481308411215, "grad_norm": 1.3207861185073853, "learning_rate": 1.7978897876801192e-05, "loss": 0.6967, "step": 3935 }, { "epoch": 0.22990654205607478, "grad_norm": 1.587273120880127, "learning_rate": 1.797775732537755e-05, "loss": 0.7163, "step": 3936 }, { "epoch": 0.22996495327102803, "grad_norm": 1.869821310043335, "learning_rate": 1.797661648842473e-05, "loss": 0.8318, "step": 3937 }, { "epoch": 0.23002336448598132, "grad_norm": 1.1704940795898438, "learning_rate": 1.7975475365983562e-05, "loss": 0.714, "step": 3938 }, { "epoch": 0.23008177570093458, "grad_norm": 1.5083911418914795, "learning_rate": 1.7974333958094886e-05, "loss": 0.7051, "step": 3939 }, { "epoch": 0.23014018691588786, "grad_norm": 1.1088589429855347, "learning_rate": 1.7973192264799553e-05, "loss": 0.8069, "step": 3940 }, { "epoch": 0.23019859813084112, "grad_norm": 1.2135353088378906, "learning_rate": 1.797205028613843e-05, "loss": 0.9996, "step": 3941 }, { "epoch": 0.2302570093457944, "grad_norm": 1.42680823802948, "learning_rate": 1.797090802215238e-05, "loss": 0.7034, "step": 3942 }, { "epoch": 0.23031542056074766, "grad_norm": 1.0606234073638916, "learning_rate": 1.7969765472882295e-05, "loss": 0.6979, "step": 3943 }, { "epoch": 0.23037383177570092, "grad_norm": 2.369450330734253, "learning_rate": 1.7968622638369064e-05, "loss": 0.7559, "step": 3944 }, { "epoch": 0.2304322429906542, "grad_norm": 1.443243384361267, "learning_rate": 1.7967479518653584e-05, "loss": 0.796, "step": 3945 }, { "epoch": 0.23049065420560746, "grad_norm": 2.119457483291626, "learning_rate": 1.796633611377678e-05, "loss": 0.8623, "step": 3946 }, { "epoch": 0.23054906542056075, "grad_norm": 0.9629507064819336, "learning_rate": 1.7965192423779566e-05, "loss": 0.8295, "step": 3947 }, { "epoch": 0.230607476635514, "grad_norm": 1.343808650970459, "learning_rate": 1.7964048448702877e-05, "loss": 0.7177, "step": 3948 }, { "epoch": 0.2306658878504673, "grad_norm": 1.1237033605575562, "learning_rate": 1.7962904188587655e-05, "loss": 0.7427, "step": 3949 }, { "epoch": 0.23072429906542055, "grad_norm": 1.1291792392730713, "learning_rate": 1.796175964347486e-05, "loss": 0.7442, "step": 3950 }, { "epoch": 0.23078271028037384, "grad_norm": 1.2811297178268433, "learning_rate": 1.796061481340545e-05, "loss": 0.8445, "step": 3951 }, { "epoch": 0.2308411214953271, "grad_norm": 1.5696476697921753, "learning_rate": 1.7959469698420405e-05, "loss": 0.9955, "step": 3952 }, { "epoch": 0.23089953271028038, "grad_norm": 1.4708422422409058, "learning_rate": 1.7958324298560702e-05, "loss": 1.131, "step": 3953 }, { "epoch": 0.23095794392523364, "grad_norm": 1.8654773235321045, "learning_rate": 1.7957178613867343e-05, "loss": 0.9212, "step": 3954 }, { "epoch": 0.23101635514018692, "grad_norm": 1.5461291074752808, "learning_rate": 1.795603264438133e-05, "loss": 0.7827, "step": 3955 }, { "epoch": 0.23107476635514018, "grad_norm": 1.8669003248214722, "learning_rate": 1.7954886390143675e-05, "loss": 0.8897, "step": 3956 }, { "epoch": 0.23113317757009347, "grad_norm": 2.1004817485809326, "learning_rate": 1.7953739851195407e-05, "loss": 1.083, "step": 3957 }, { "epoch": 0.23119158878504673, "grad_norm": 2.622119188308716, "learning_rate": 1.7952593027577562e-05, "loss": 0.9924, "step": 3958 }, { "epoch": 0.23125, "grad_norm": 2.145869493484497, "learning_rate": 1.795144591933118e-05, "loss": 0.9004, "step": 3959 }, { "epoch": 0.23130841121495327, "grad_norm": 1.652204990386963, "learning_rate": 1.7950298526497317e-05, "loss": 1.0712, "step": 3960 }, { "epoch": 0.23136682242990655, "grad_norm": 1.3706272840499878, "learning_rate": 1.794915084911705e-05, "loss": 0.8661, "step": 3961 }, { "epoch": 0.2314252336448598, "grad_norm": 1.7685467004776, "learning_rate": 1.7948002887231447e-05, "loss": 0.8964, "step": 3962 }, { "epoch": 0.23148364485981307, "grad_norm": 1.625362515449524, "learning_rate": 1.794685464088159e-05, "loss": 0.8796, "step": 3963 }, { "epoch": 0.23154205607476636, "grad_norm": 1.9056347608566284, "learning_rate": 1.7945706110108584e-05, "loss": 0.8206, "step": 3964 }, { "epoch": 0.2316004672897196, "grad_norm": 1.4759095907211304, "learning_rate": 1.7944557294953528e-05, "loss": 0.9088, "step": 3965 }, { "epoch": 0.2316588785046729, "grad_norm": 2.6139984130859375, "learning_rate": 1.7943408195457545e-05, "loss": 0.7743, "step": 3966 }, { "epoch": 0.23171728971962616, "grad_norm": 2.728895902633667, "learning_rate": 1.794225881166176e-05, "loss": 1.0363, "step": 3967 }, { "epoch": 0.23177570093457944, "grad_norm": 1.8434206247329712, "learning_rate": 1.794110914360731e-05, "loss": 0.8088, "step": 3968 }, { "epoch": 0.2318341121495327, "grad_norm": 1.2987984418869019, "learning_rate": 1.793995919133534e-05, "loss": 0.8577, "step": 3969 }, { "epoch": 0.231892523364486, "grad_norm": 1.4111984968185425, "learning_rate": 1.793880895488701e-05, "loss": 0.9175, "step": 3970 }, { "epoch": 0.23195093457943924, "grad_norm": 1.6692850589752197, "learning_rate": 1.7937658434303494e-05, "loss": 0.8356, "step": 3971 }, { "epoch": 0.23200934579439253, "grad_norm": 1.399569034576416, "learning_rate": 1.793650762962596e-05, "loss": 0.8402, "step": 3972 }, { "epoch": 0.2320677570093458, "grad_norm": 1.5714898109436035, "learning_rate": 1.79353565408956e-05, "loss": 0.7865, "step": 3973 }, { "epoch": 0.23212616822429907, "grad_norm": 2.145941734313965, "learning_rate": 1.7934205168153606e-05, "loss": 0.9249, "step": 3974 }, { "epoch": 0.23218457943925233, "grad_norm": 3.0127978324890137, "learning_rate": 1.7933053511441198e-05, "loss": 1.0396, "step": 3975 }, { "epoch": 0.23224299065420562, "grad_norm": 1.1255699396133423, "learning_rate": 1.793190157079959e-05, "loss": 0.9202, "step": 3976 }, { "epoch": 0.23230140186915887, "grad_norm": 1.6243677139282227, "learning_rate": 1.7930749346270008e-05, "loss": 0.7947, "step": 3977 }, { "epoch": 0.23235981308411216, "grad_norm": 1.1166244745254517, "learning_rate": 1.792959683789369e-05, "loss": 0.7468, "step": 3978 }, { "epoch": 0.23241822429906542, "grad_norm": 2.492842435836792, "learning_rate": 1.7928444045711888e-05, "loss": 0.9514, "step": 3979 }, { "epoch": 0.2324766355140187, "grad_norm": 1.8258088827133179, "learning_rate": 1.792729096976586e-05, "loss": 0.8973, "step": 3980 }, { "epoch": 0.23253504672897196, "grad_norm": 1.6445828676223755, "learning_rate": 1.7926137610096875e-05, "loss": 0.8607, "step": 3981 }, { "epoch": 0.23259345794392525, "grad_norm": 1.310559868812561, "learning_rate": 1.792498396674622e-05, "loss": 0.9943, "step": 3982 }, { "epoch": 0.2326518691588785, "grad_norm": 1.481035590171814, "learning_rate": 1.792383003975517e-05, "loss": 0.7748, "step": 3983 }, { "epoch": 0.23271028037383176, "grad_norm": 1.453161597251892, "learning_rate": 1.792267582916504e-05, "loss": 0.8857, "step": 3984 }, { "epoch": 0.23276869158878505, "grad_norm": 1.5751196146011353, "learning_rate": 1.7921521335017128e-05, "loss": 0.8934, "step": 3985 }, { "epoch": 0.2328271028037383, "grad_norm": 1.2962275743484497, "learning_rate": 1.792036655735276e-05, "loss": 1.018, "step": 3986 }, { "epoch": 0.2328855140186916, "grad_norm": 1.2921041250228882, "learning_rate": 1.7919211496213266e-05, "loss": 1.0342, "step": 3987 }, { "epoch": 0.23294392523364485, "grad_norm": 1.3268524408340454, "learning_rate": 1.7918056151639985e-05, "loss": 0.7253, "step": 3988 }, { "epoch": 0.23300233644859814, "grad_norm": 1.8280142545700073, "learning_rate": 1.7916900523674265e-05, "loss": 0.8036, "step": 3989 }, { "epoch": 0.2330607476635514, "grad_norm": 1.4171401262283325, "learning_rate": 1.7915744612357474e-05, "loss": 0.8727, "step": 3990 }, { "epoch": 0.23311915887850468, "grad_norm": 1.6813515424728394, "learning_rate": 1.7914588417730978e-05, "loss": 0.8326, "step": 3991 }, { "epoch": 0.23317757009345794, "grad_norm": 1.069815754890442, "learning_rate": 1.791343193983616e-05, "loss": 0.793, "step": 3992 }, { "epoch": 0.23323598130841122, "grad_norm": 1.65056574344635, "learning_rate": 1.7912275178714407e-05, "loss": 0.921, "step": 3993 }, { "epoch": 0.23329439252336448, "grad_norm": 1.1659907102584839, "learning_rate": 1.791111813440712e-05, "loss": 0.8244, "step": 3994 }, { "epoch": 0.23335280373831777, "grad_norm": 1.882121205329895, "learning_rate": 1.790996080695572e-05, "loss": 1.0062, "step": 3995 }, { "epoch": 0.23341121495327102, "grad_norm": 1.5657787322998047, "learning_rate": 1.7908803196401616e-05, "loss": 0.9623, "step": 3996 }, { "epoch": 0.2334696261682243, "grad_norm": 1.248297095298767, "learning_rate": 1.790764530278625e-05, "loss": 0.7356, "step": 3997 }, { "epoch": 0.23352803738317757, "grad_norm": 1.311752200126648, "learning_rate": 1.7906487126151056e-05, "loss": 0.8205, "step": 3998 }, { "epoch": 0.23358644859813085, "grad_norm": 1.0049846172332764, "learning_rate": 1.7905328666537493e-05, "loss": 0.7135, "step": 3999 }, { "epoch": 0.2336448598130841, "grad_norm": 1.3898015022277832, "learning_rate": 1.7904169923987014e-05, "loss": 0.9692, "step": 4000 }, { "epoch": 0.2337032710280374, "grad_norm": 1.3108456134796143, "learning_rate": 1.79030108985411e-05, "loss": 1.0135, "step": 4001 }, { "epoch": 0.23376168224299065, "grad_norm": 1.490686297416687, "learning_rate": 1.790185159024123e-05, "loss": 0.8448, "step": 4002 }, { "epoch": 0.2338200934579439, "grad_norm": 1.4234788417816162, "learning_rate": 1.7900691999128895e-05, "loss": 0.8667, "step": 4003 }, { "epoch": 0.2338785046728972, "grad_norm": 1.950960397720337, "learning_rate": 1.7899532125245596e-05, "loss": 0.9318, "step": 4004 }, { "epoch": 0.23393691588785046, "grad_norm": 1.2501163482666016, "learning_rate": 1.7898371968632853e-05, "loss": 0.7876, "step": 4005 }, { "epoch": 0.23399532710280374, "grad_norm": 2.722893714904785, "learning_rate": 1.7897211529332182e-05, "loss": 0.8958, "step": 4006 }, { "epoch": 0.234053738317757, "grad_norm": 1.2010372877120972, "learning_rate": 1.7896050807385113e-05, "loss": 0.7481, "step": 4007 }, { "epoch": 0.23411214953271028, "grad_norm": 1.6591955423355103, "learning_rate": 1.7894889802833203e-05, "loss": 0.7574, "step": 4008 }, { "epoch": 0.23417056074766354, "grad_norm": 2.3293635845184326, "learning_rate": 1.789372851571799e-05, "loss": 0.7414, "step": 4009 }, { "epoch": 0.23422897196261683, "grad_norm": 1.8624203205108643, "learning_rate": 1.7892566946081046e-05, "loss": 0.8801, "step": 4010 }, { "epoch": 0.23428738317757009, "grad_norm": 2.292151927947998, "learning_rate": 1.789140509396394e-05, "loss": 0.8499, "step": 4011 }, { "epoch": 0.23434579439252337, "grad_norm": 1.3855243921279907, "learning_rate": 1.7890242959408255e-05, "loss": 0.9319, "step": 4012 }, { "epoch": 0.23440420560747663, "grad_norm": 1.9719139337539673, "learning_rate": 1.788908054245559e-05, "loss": 0.9048, "step": 4013 }, { "epoch": 0.23446261682242991, "grad_norm": 1.3281302452087402, "learning_rate": 1.788791784314754e-05, "loss": 0.7728, "step": 4014 }, { "epoch": 0.23452102803738317, "grad_norm": 1.4547282457351685, "learning_rate": 1.788675486152573e-05, "loss": 0.8373, "step": 4015 }, { "epoch": 0.23457943925233646, "grad_norm": 1.4001063108444214, "learning_rate": 1.7885591597631776e-05, "loss": 0.9263, "step": 4016 }, { "epoch": 0.23463785046728972, "grad_norm": 1.557289481163025, "learning_rate": 1.7884428051507312e-05, "loss": 0.8954, "step": 4017 }, { "epoch": 0.234696261682243, "grad_norm": 1.6650086641311646, "learning_rate": 1.7883264223193985e-05, "loss": 0.8198, "step": 4018 }, { "epoch": 0.23475467289719626, "grad_norm": 1.1204979419708252, "learning_rate": 1.788210011273345e-05, "loss": 0.9388, "step": 4019 }, { "epoch": 0.23481308411214954, "grad_norm": 1.5939302444458008, "learning_rate": 1.7880935720167367e-05, "loss": 0.752, "step": 4020 }, { "epoch": 0.2348714953271028, "grad_norm": 1.6370790004730225, "learning_rate": 1.787977104553741e-05, "loss": 1.0247, "step": 4021 }, { "epoch": 0.2349299065420561, "grad_norm": 1.292567491531372, "learning_rate": 1.787860608888527e-05, "loss": 0.751, "step": 4022 }, { "epoch": 0.23498831775700935, "grad_norm": 2.239086866378784, "learning_rate": 1.787744085025264e-05, "loss": 0.9015, "step": 4023 }, { "epoch": 0.2350467289719626, "grad_norm": 2.284914016723633, "learning_rate": 1.7876275329681217e-05, "loss": 0.8156, "step": 4024 }, { "epoch": 0.2351051401869159, "grad_norm": 1.2901355028152466, "learning_rate": 1.7875109527212726e-05, "loss": 0.7222, "step": 4025 }, { "epoch": 0.23516355140186915, "grad_norm": 1.9173766374588013, "learning_rate": 1.7873943442888886e-05, "loss": 0.9618, "step": 4026 }, { "epoch": 0.23522196261682243, "grad_norm": 2.023578405380249, "learning_rate": 1.787277707675143e-05, "loss": 0.7722, "step": 4027 }, { "epoch": 0.2352803738317757, "grad_norm": 1.1595985889434814, "learning_rate": 1.787161042884211e-05, "loss": 0.7128, "step": 4028 }, { "epoch": 0.23533878504672898, "grad_norm": 2.9799063205718994, "learning_rate": 1.7870443499202674e-05, "loss": 0.9207, "step": 4029 }, { "epoch": 0.23539719626168223, "grad_norm": 1.8868464231491089, "learning_rate": 1.7869276287874894e-05, "loss": 0.9118, "step": 4030 }, { "epoch": 0.23545560747663552, "grad_norm": 2.7773077487945557, "learning_rate": 1.7868108794900537e-05, "loss": 0.8883, "step": 4031 }, { "epoch": 0.23551401869158878, "grad_norm": 1.5225372314453125, "learning_rate": 1.7866941020321397e-05, "loss": 0.8411, "step": 4032 }, { "epoch": 0.23557242990654206, "grad_norm": 1.42632257938385, "learning_rate": 1.786577296417926e-05, "loss": 0.669, "step": 4033 }, { "epoch": 0.23563084112149532, "grad_norm": 2.709944486618042, "learning_rate": 1.786460462651594e-05, "loss": 0.7287, "step": 4034 }, { "epoch": 0.2356892523364486, "grad_norm": 1.1662921905517578, "learning_rate": 1.786343600737325e-05, "loss": 0.8419, "step": 4035 }, { "epoch": 0.23574766355140186, "grad_norm": 2.943493604660034, "learning_rate": 1.7862267106793016e-05, "loss": 0.7621, "step": 4036 }, { "epoch": 0.23580607476635515, "grad_norm": 1.1565451622009277, "learning_rate": 1.7861097924817066e-05, "loss": 0.7254, "step": 4037 }, { "epoch": 0.2358644859813084, "grad_norm": 2.7267088890075684, "learning_rate": 1.785992846148726e-05, "loss": 1.0089, "step": 4038 }, { "epoch": 0.2359228971962617, "grad_norm": 1.838881492614746, "learning_rate": 1.7858758716845445e-05, "loss": 0.9735, "step": 4039 }, { "epoch": 0.23598130841121495, "grad_norm": 1.7850675582885742, "learning_rate": 1.7857588690933486e-05, "loss": 0.7729, "step": 4040 }, { "epoch": 0.23603971962616824, "grad_norm": 2.469865560531616, "learning_rate": 1.785641838379326e-05, "loss": 0.9128, "step": 4041 }, { "epoch": 0.2360981308411215, "grad_norm": 2.0734660625457764, "learning_rate": 1.7855247795466655e-05, "loss": 0.8218, "step": 4042 }, { "epoch": 0.23615654205607475, "grad_norm": 1.503912329673767, "learning_rate": 1.785407692599557e-05, "loss": 0.8463, "step": 4043 }, { "epoch": 0.23621495327102804, "grad_norm": 2.0059092044830322, "learning_rate": 1.7852905775421906e-05, "loss": 0.9346, "step": 4044 }, { "epoch": 0.2362733644859813, "grad_norm": 1.8904567956924438, "learning_rate": 1.7851734343787583e-05, "loss": 1.0107, "step": 4045 }, { "epoch": 0.23633177570093458, "grad_norm": 1.2985161542892456, "learning_rate": 1.7850562631134523e-05, "loss": 0.8713, "step": 4046 }, { "epoch": 0.23639018691588784, "grad_norm": 1.4932483434677124, "learning_rate": 1.7849390637504665e-05, "loss": 0.7649, "step": 4047 }, { "epoch": 0.23644859813084113, "grad_norm": 3.1218807697296143, "learning_rate": 1.7848218362939952e-05, "loss": 1.0436, "step": 4048 }, { "epoch": 0.23650700934579438, "grad_norm": 2.599426746368408, "learning_rate": 1.7847045807482347e-05, "loss": 0.8965, "step": 4049 }, { "epoch": 0.23656542056074767, "grad_norm": 2.736175537109375, "learning_rate": 1.7845872971173813e-05, "loss": 0.9368, "step": 4050 }, { "epoch": 0.23662383177570093, "grad_norm": 1.3631013631820679, "learning_rate": 1.7844699854056324e-05, "loss": 0.6918, "step": 4051 }, { "epoch": 0.2366822429906542, "grad_norm": 2.808457136154175, "learning_rate": 1.784352645617187e-05, "loss": 0.8881, "step": 4052 }, { "epoch": 0.23674065420560747, "grad_norm": 1.5476998090744019, "learning_rate": 1.784235277756245e-05, "loss": 0.8062, "step": 4053 }, { "epoch": 0.23679906542056076, "grad_norm": 1.534865379333496, "learning_rate": 1.7841178818270064e-05, "loss": 0.7868, "step": 4054 }, { "epoch": 0.236857476635514, "grad_norm": 2.52128267288208, "learning_rate": 1.7840004578336735e-05, "loss": 1.0182, "step": 4055 }, { "epoch": 0.2369158878504673, "grad_norm": 1.8844438791275024, "learning_rate": 1.7838830057804488e-05, "loss": 0.9368, "step": 4056 }, { "epoch": 0.23697429906542056, "grad_norm": 1.9660099744796753, "learning_rate": 1.7837655256715355e-05, "loss": 0.8824, "step": 4057 }, { "epoch": 0.23703271028037384, "grad_norm": 1.7321866750717163, "learning_rate": 1.7836480175111387e-05, "loss": 1.0102, "step": 4058 }, { "epoch": 0.2370911214953271, "grad_norm": 1.7566179037094116, "learning_rate": 1.7835304813034647e-05, "loss": 0.7041, "step": 4059 }, { "epoch": 0.2371495327102804, "grad_norm": 1.6038423776626587, "learning_rate": 1.783412917052719e-05, "loss": 0.8363, "step": 4060 }, { "epoch": 0.23720794392523364, "grad_norm": 1.9228968620300293, "learning_rate": 1.78329532476311e-05, "loss": 0.9469, "step": 4061 }, { "epoch": 0.23726635514018693, "grad_norm": 1.5616626739501953, "learning_rate": 1.783177704438846e-05, "loss": 0.8537, "step": 4062 }, { "epoch": 0.2373247663551402, "grad_norm": 1.9584821462631226, "learning_rate": 1.7830600560841377e-05, "loss": 0.8094, "step": 4063 }, { "epoch": 0.23738317757009345, "grad_norm": 1.4332098960876465, "learning_rate": 1.782942379703195e-05, "loss": 0.912, "step": 4064 }, { "epoch": 0.23744158878504673, "grad_norm": 1.4577926397323608, "learning_rate": 1.7828246753002294e-05, "loss": 0.8073, "step": 4065 }, { "epoch": 0.2375, "grad_norm": 2.649060010910034, "learning_rate": 1.7827069428794542e-05, "loss": 0.9091, "step": 4066 }, { "epoch": 0.23755841121495327, "grad_norm": 1.252150297164917, "learning_rate": 1.782589182445083e-05, "loss": 0.751, "step": 4067 }, { "epoch": 0.23761682242990653, "grad_norm": 1.2219884395599365, "learning_rate": 1.78247139400133e-05, "loss": 0.6902, "step": 4068 }, { "epoch": 0.23767523364485982, "grad_norm": 2.125955820083618, "learning_rate": 1.7823535775524114e-05, "loss": 0.7543, "step": 4069 }, { "epoch": 0.23773364485981308, "grad_norm": 2.568448066711426, "learning_rate": 1.7822357331025442e-05, "loss": 0.8554, "step": 4070 }, { "epoch": 0.23779205607476636, "grad_norm": 1.717914342880249, "learning_rate": 1.7821178606559455e-05, "loss": 0.7107, "step": 4071 }, { "epoch": 0.23785046728971962, "grad_norm": 4.612213611602783, "learning_rate": 1.7819999602168342e-05, "loss": 1.0374, "step": 4072 }, { "epoch": 0.2379088785046729, "grad_norm": 1.2593700885772705, "learning_rate": 1.7818820317894302e-05, "loss": 0.7865, "step": 4073 }, { "epoch": 0.23796728971962616, "grad_norm": 2.8800652027130127, "learning_rate": 1.7817640753779546e-05, "loss": 0.9533, "step": 4074 }, { "epoch": 0.23802570093457945, "grad_norm": 2.023111343383789, "learning_rate": 1.7816460909866283e-05, "loss": 0.8683, "step": 4075 }, { "epoch": 0.2380841121495327, "grad_norm": 2.2084317207336426, "learning_rate": 1.7815280786196748e-05, "loss": 0.9977, "step": 4076 }, { "epoch": 0.238142523364486, "grad_norm": 1.8511934280395508, "learning_rate": 1.7814100382813172e-05, "loss": 0.7979, "step": 4077 }, { "epoch": 0.23820093457943925, "grad_norm": 1.6957545280456543, "learning_rate": 1.7812919699757806e-05, "loss": 0.9509, "step": 4078 }, { "epoch": 0.23825934579439254, "grad_norm": 1.1322728395462036, "learning_rate": 1.7811738737072907e-05, "loss": 0.7131, "step": 4079 }, { "epoch": 0.2383177570093458, "grad_norm": 1.5753147602081299, "learning_rate": 1.781055749480074e-05, "loss": 0.7959, "step": 4080 }, { "epoch": 0.23837616822429908, "grad_norm": 2.115478277206421, "learning_rate": 1.780937597298359e-05, "loss": 0.9857, "step": 4081 }, { "epoch": 0.23843457943925234, "grad_norm": 1.5140172243118286, "learning_rate": 1.7808194171663736e-05, "loss": 0.9076, "step": 4082 }, { "epoch": 0.2384929906542056, "grad_norm": 1.4087153673171997, "learning_rate": 1.7807012090883478e-05, "loss": 0.8136, "step": 4083 }, { "epoch": 0.23855140186915888, "grad_norm": 1.5252623558044434, "learning_rate": 1.7805829730685126e-05, "loss": 0.9548, "step": 4084 }, { "epoch": 0.23860981308411214, "grad_norm": 1.3052979707717896, "learning_rate": 1.7804647091110995e-05, "loss": 0.9829, "step": 4085 }, { "epoch": 0.23866822429906542, "grad_norm": 1.5244327783584595, "learning_rate": 1.7803464172203412e-05, "loss": 0.6009, "step": 4086 }, { "epoch": 0.23872663551401868, "grad_norm": 1.4996685981750488, "learning_rate": 1.7802280974004717e-05, "loss": 0.7818, "step": 4087 }, { "epoch": 0.23878504672897197, "grad_norm": 1.3885968923568726, "learning_rate": 1.7801097496557253e-05, "loss": 0.7176, "step": 4088 }, { "epoch": 0.23884345794392522, "grad_norm": 2.183584451675415, "learning_rate": 1.7799913739903382e-05, "loss": 0.9494, "step": 4089 }, { "epoch": 0.2389018691588785, "grad_norm": 1.2163411378860474, "learning_rate": 1.7798729704085467e-05, "loss": 0.8489, "step": 4090 }, { "epoch": 0.23896028037383177, "grad_norm": 2.0905938148498535, "learning_rate": 1.7797545389145893e-05, "loss": 0.802, "step": 4091 }, { "epoch": 0.23901869158878505, "grad_norm": 1.2196621894836426, "learning_rate": 1.779636079512704e-05, "loss": 1.0306, "step": 4092 }, { "epoch": 0.2390771028037383, "grad_norm": 1.5647120475769043, "learning_rate": 1.779517592207131e-05, "loss": 0.8233, "step": 4093 }, { "epoch": 0.2391355140186916, "grad_norm": 1.594677209854126, "learning_rate": 1.7793990770021103e-05, "loss": 0.8495, "step": 4094 }, { "epoch": 0.23919392523364486, "grad_norm": 2.1248574256896973, "learning_rate": 1.7792805339018846e-05, "loss": 0.7751, "step": 4095 }, { "epoch": 0.23925233644859814, "grad_norm": 1.4542592763900757, "learning_rate": 1.779161962910696e-05, "loss": 0.7668, "step": 4096 }, { "epoch": 0.2393107476635514, "grad_norm": 1.498320460319519, "learning_rate": 1.7790433640327887e-05, "loss": 0.9513, "step": 4097 }, { "epoch": 0.23936915887850468, "grad_norm": 1.3778889179229736, "learning_rate": 1.7789247372724073e-05, "loss": 0.9936, "step": 4098 }, { "epoch": 0.23942757009345794, "grad_norm": 1.1428537368774414, "learning_rate": 1.7788060826337968e-05, "loss": 0.747, "step": 4099 }, { "epoch": 0.23948598130841123, "grad_norm": 1.4396241903305054, "learning_rate": 1.778687400121205e-05, "loss": 0.7661, "step": 4100 }, { "epoch": 0.23954439252336449, "grad_norm": 1.360059380531311, "learning_rate": 1.7785686897388788e-05, "loss": 0.678, "step": 4101 }, { "epoch": 0.23960280373831774, "grad_norm": 1.2809919118881226, "learning_rate": 1.7784499514910674e-05, "loss": 0.7982, "step": 4102 }, { "epoch": 0.23966121495327103, "grad_norm": 1.518586277961731, "learning_rate": 1.7783311853820205e-05, "loss": 0.8526, "step": 4103 }, { "epoch": 0.2397196261682243, "grad_norm": 1.3904377222061157, "learning_rate": 1.778212391415989e-05, "loss": 0.787, "step": 4104 }, { "epoch": 0.23977803738317757, "grad_norm": 1.2547868490219116, "learning_rate": 1.7780935695972238e-05, "loss": 0.8134, "step": 4105 }, { "epoch": 0.23983644859813083, "grad_norm": 1.443833351135254, "learning_rate": 1.7779747199299785e-05, "loss": 0.8829, "step": 4106 }, { "epoch": 0.23989485981308412, "grad_norm": 1.3541814088821411, "learning_rate": 1.7778558424185065e-05, "loss": 0.9512, "step": 4107 }, { "epoch": 0.23995327102803737, "grad_norm": 1.233974814414978, "learning_rate": 1.7777369370670622e-05, "loss": 0.9252, "step": 4108 }, { "epoch": 0.24001168224299066, "grad_norm": 1.6076133251190186, "learning_rate": 1.7776180038799015e-05, "loss": 0.9344, "step": 4109 }, { "epoch": 0.24007009345794392, "grad_norm": 1.9750398397445679, "learning_rate": 1.7774990428612814e-05, "loss": 0.7595, "step": 4110 }, { "epoch": 0.2401285046728972, "grad_norm": 1.9269987344741821, "learning_rate": 1.777380054015459e-05, "loss": 1.0051, "step": 4111 }, { "epoch": 0.24018691588785046, "grad_norm": 1.4126777648925781, "learning_rate": 1.7772610373466937e-05, "loss": 0.8031, "step": 4112 }, { "epoch": 0.24024532710280375, "grad_norm": 1.1841881275177002, "learning_rate": 1.7771419928592445e-05, "loss": 0.8432, "step": 4113 }, { "epoch": 0.240303738317757, "grad_norm": 1.7263988256454468, "learning_rate": 1.7770229205573725e-05, "loss": 1.0079, "step": 4114 }, { "epoch": 0.2403621495327103, "grad_norm": 1.1743417978286743, "learning_rate": 1.7769038204453394e-05, "loss": 0.8274, "step": 4115 }, { "epoch": 0.24042056074766355, "grad_norm": 1.4807167053222656, "learning_rate": 1.7767846925274077e-05, "loss": 1.1218, "step": 4116 }, { "epoch": 0.24047897196261683, "grad_norm": 1.6947628259658813, "learning_rate": 1.776665536807841e-05, "loss": 0.7943, "step": 4117 }, { "epoch": 0.2405373831775701, "grad_norm": 1.652409553527832, "learning_rate": 1.776546353290904e-05, "loss": 0.9379, "step": 4118 }, { "epoch": 0.24059579439252338, "grad_norm": 1.5310391187667847, "learning_rate": 1.7764271419808627e-05, "loss": 0.7491, "step": 4119 }, { "epoch": 0.24065420560747663, "grad_norm": 1.5880143642425537, "learning_rate": 1.776307902881983e-05, "loss": 0.8245, "step": 4120 }, { "epoch": 0.24071261682242992, "grad_norm": 1.4887595176696777, "learning_rate": 1.7761886359985335e-05, "loss": 0.6982, "step": 4121 }, { "epoch": 0.24077102803738318, "grad_norm": 1.2982285022735596, "learning_rate": 1.7760693413347825e-05, "loss": 0.8634, "step": 4122 }, { "epoch": 0.24082943925233644, "grad_norm": 1.375204086303711, "learning_rate": 1.775950018894999e-05, "loss": 0.7266, "step": 4123 }, { "epoch": 0.24088785046728972, "grad_norm": 1.2544560432434082, "learning_rate": 1.7758306686834543e-05, "loss": 0.7947, "step": 4124 }, { "epoch": 0.24094626168224298, "grad_norm": 1.5299665927886963, "learning_rate": 1.77571129070442e-05, "loss": 0.8168, "step": 4125 }, { "epoch": 0.24100467289719626, "grad_norm": 1.5927997827529907, "learning_rate": 1.7755918849621686e-05, "loss": 0.9903, "step": 4126 }, { "epoch": 0.24106308411214952, "grad_norm": 1.7301135063171387, "learning_rate": 1.7754724514609734e-05, "loss": 1.0301, "step": 4127 }, { "epoch": 0.2411214953271028, "grad_norm": 1.4636234045028687, "learning_rate": 1.7753529902051093e-05, "loss": 0.8312, "step": 4128 }, { "epoch": 0.24117990654205607, "grad_norm": 1.786618709564209, "learning_rate": 1.775233501198852e-05, "loss": 0.7924, "step": 4129 }, { "epoch": 0.24123831775700935, "grad_norm": 1.4538257122039795, "learning_rate": 1.775113984446478e-05, "loss": 1.0277, "step": 4130 }, { "epoch": 0.2412967289719626, "grad_norm": 1.719277024269104, "learning_rate": 1.7749944399522647e-05, "loss": 0.9393, "step": 4131 }, { "epoch": 0.2413551401869159, "grad_norm": 1.6715244054794312, "learning_rate": 1.774874867720491e-05, "loss": 0.8344, "step": 4132 }, { "epoch": 0.24141355140186915, "grad_norm": 1.325025200843811, "learning_rate": 1.774755267755436e-05, "loss": 0.7948, "step": 4133 }, { "epoch": 0.24147196261682244, "grad_norm": 1.3968490362167358, "learning_rate": 1.774635640061381e-05, "loss": 0.9631, "step": 4134 }, { "epoch": 0.2415303738317757, "grad_norm": 1.4592965841293335, "learning_rate": 1.7745159846426067e-05, "loss": 0.9654, "step": 4135 }, { "epoch": 0.24158878504672898, "grad_norm": 1.5581556558609009, "learning_rate": 1.7743963015033964e-05, "loss": 0.8111, "step": 4136 }, { "epoch": 0.24164719626168224, "grad_norm": 1.610106348991394, "learning_rate": 1.774276590648033e-05, "loss": 0.9482, "step": 4137 }, { "epoch": 0.24170560747663553, "grad_norm": 1.1070083379745483, "learning_rate": 1.774156852080802e-05, "loss": 0.6851, "step": 4138 }, { "epoch": 0.24176401869158878, "grad_norm": 1.3366810083389282, "learning_rate": 1.774037085805987e-05, "loss": 0.8199, "step": 4139 }, { "epoch": 0.24182242990654207, "grad_norm": 1.3254609107971191, "learning_rate": 1.773917291827877e-05, "loss": 0.9634, "step": 4140 }, { "epoch": 0.24188084112149533, "grad_norm": 1.251358985900879, "learning_rate": 1.7737974701507575e-05, "loss": 0.777, "step": 4141 }, { "epoch": 0.24193925233644858, "grad_norm": 1.359427571296692, "learning_rate": 1.773677620778918e-05, "loss": 0.8538, "step": 4142 }, { "epoch": 0.24199766355140187, "grad_norm": 1.128998875617981, "learning_rate": 1.7735577437166478e-05, "loss": 0.8672, "step": 4143 }, { "epoch": 0.24205607476635513, "grad_norm": 1.2887911796569824, "learning_rate": 1.7734378389682373e-05, "loss": 0.7116, "step": 4144 }, { "epoch": 0.2421144859813084, "grad_norm": 3.1309292316436768, "learning_rate": 1.773317906537978e-05, "loss": 0.808, "step": 4145 }, { "epoch": 0.24217289719626167, "grad_norm": 1.584686279296875, "learning_rate": 1.773197946430162e-05, "loss": 0.8448, "step": 4146 }, { "epoch": 0.24223130841121496, "grad_norm": 3.146674394607544, "learning_rate": 1.7730779586490836e-05, "loss": 0.8606, "step": 4147 }, { "epoch": 0.24228971962616822, "grad_norm": 1.1761720180511475, "learning_rate": 1.7729579431990367e-05, "loss": 0.6553, "step": 4148 }, { "epoch": 0.2423481308411215, "grad_norm": 2.4091203212738037, "learning_rate": 1.7728379000843164e-05, "loss": 0.8578, "step": 4149 }, { "epoch": 0.24240654205607476, "grad_norm": 1.682990550994873, "learning_rate": 1.7727178293092202e-05, "loss": 0.8219, "step": 4150 }, { "epoch": 0.24246495327102804, "grad_norm": 1.6695019006729126, "learning_rate": 1.7725977308780443e-05, "loss": 0.8232, "step": 4151 }, { "epoch": 0.2425233644859813, "grad_norm": 2.0410213470458984, "learning_rate": 1.772477604795088e-05, "loss": 0.8817, "step": 4152 }, { "epoch": 0.2425817757009346, "grad_norm": 1.5819627046585083, "learning_rate": 1.7723574510646497e-05, "loss": 0.8287, "step": 4153 }, { "epoch": 0.24264018691588785, "grad_norm": 1.6994959115982056, "learning_rate": 1.7722372696910305e-05, "loss": 0.8454, "step": 4154 }, { "epoch": 0.24269859813084113, "grad_norm": 2.706117868423462, "learning_rate": 1.772117060678532e-05, "loss": 0.8626, "step": 4155 }, { "epoch": 0.2427570093457944, "grad_norm": 2.5443646907806396, "learning_rate": 1.7719968240314562e-05, "loss": 1.0158, "step": 4156 }, { "epoch": 0.24281542056074767, "grad_norm": 2.333179473876953, "learning_rate": 1.7718765597541064e-05, "loss": 0.8207, "step": 4157 }, { "epoch": 0.24287383177570093, "grad_norm": 1.2761240005493164, "learning_rate": 1.771756267850787e-05, "loss": 0.9757, "step": 4158 }, { "epoch": 0.24293224299065422, "grad_norm": 2.1033294200897217, "learning_rate": 1.7716359483258032e-05, "loss": 0.7433, "step": 4159 }, { "epoch": 0.24299065420560748, "grad_norm": 1.4736117124557495, "learning_rate": 1.7715156011834615e-05, "loss": 1.0149, "step": 4160 }, { "epoch": 0.24304906542056076, "grad_norm": 1.4910950660705566, "learning_rate": 1.7713952264280695e-05, "loss": 0.8159, "step": 4161 }, { "epoch": 0.24310747663551402, "grad_norm": 1.8341660499572754, "learning_rate": 1.7712748240639345e-05, "loss": 0.8759, "step": 4162 }, { "epoch": 0.24316588785046728, "grad_norm": 1.35612952709198, "learning_rate": 1.7711543940953667e-05, "loss": 0.8702, "step": 4163 }, { "epoch": 0.24322429906542056, "grad_norm": 1.962931513786316, "learning_rate": 1.7710339365266765e-05, "loss": 0.9196, "step": 4164 }, { "epoch": 0.24328271028037382, "grad_norm": 1.4158592224121094, "learning_rate": 1.770913451362174e-05, "loss": 1.0409, "step": 4165 }, { "epoch": 0.2433411214953271, "grad_norm": 1.603528618812561, "learning_rate": 1.770792938606173e-05, "loss": 0.7877, "step": 4166 }, { "epoch": 0.24339953271028036, "grad_norm": 1.783137321472168, "learning_rate": 1.7706723982629855e-05, "loss": 0.8318, "step": 4167 }, { "epoch": 0.24345794392523365, "grad_norm": 1.4759843349456787, "learning_rate": 1.7705518303369262e-05, "loss": 0.9826, "step": 4168 }, { "epoch": 0.2435163551401869, "grad_norm": 1.4362173080444336, "learning_rate": 1.77043123483231e-05, "loss": 0.7156, "step": 4169 }, { "epoch": 0.2435747663551402, "grad_norm": 2.0281782150268555, "learning_rate": 1.7703106117534535e-05, "loss": 0.9374, "step": 4170 }, { "epoch": 0.24363317757009345, "grad_norm": 1.4130873680114746, "learning_rate": 1.770189961104674e-05, "loss": 0.8581, "step": 4171 }, { "epoch": 0.24369158878504674, "grad_norm": 1.8077163696289062, "learning_rate": 1.770069282890289e-05, "loss": 0.7098, "step": 4172 }, { "epoch": 0.24375, "grad_norm": 2.2305245399475098, "learning_rate": 1.7699485771146182e-05, "loss": 0.8456, "step": 4173 }, { "epoch": 0.24380841121495328, "grad_norm": 0.9659311771392822, "learning_rate": 1.7698278437819817e-05, "loss": 0.665, "step": 4174 }, { "epoch": 0.24386682242990654, "grad_norm": 2.65138840675354, "learning_rate": 1.7697070828967003e-05, "loss": 0.9116, "step": 4175 }, { "epoch": 0.24392523364485982, "grad_norm": 2.304431915283203, "learning_rate": 1.7695862944630967e-05, "loss": 0.9273, "step": 4176 }, { "epoch": 0.24398364485981308, "grad_norm": 2.160722017288208, "learning_rate": 1.769465478485493e-05, "loss": 0.9681, "step": 4177 }, { "epoch": 0.24404205607476637, "grad_norm": 2.3067307472229004, "learning_rate": 1.769344634968214e-05, "loss": 0.8259, "step": 4178 }, { "epoch": 0.24410046728971962, "grad_norm": 1.4915943145751953, "learning_rate": 1.769223763915585e-05, "loss": 0.7731, "step": 4179 }, { "epoch": 0.2441588785046729, "grad_norm": 1.386739730834961, "learning_rate": 1.7691028653319315e-05, "loss": 0.7094, "step": 4180 }, { "epoch": 0.24421728971962617, "grad_norm": 1.4127442836761475, "learning_rate": 1.7689819392215808e-05, "loss": 0.7602, "step": 4181 }, { "epoch": 0.24427570093457943, "grad_norm": 1.5766870975494385, "learning_rate": 1.768860985588861e-05, "loss": 0.9048, "step": 4182 }, { "epoch": 0.2443341121495327, "grad_norm": 1.53361177444458, "learning_rate": 1.768740004438101e-05, "loss": 0.7457, "step": 4183 }, { "epoch": 0.24439252336448597, "grad_norm": 2.6559388637542725, "learning_rate": 1.7686189957736305e-05, "loss": 0.7748, "step": 4184 }, { "epoch": 0.24445093457943926, "grad_norm": 1.2112427949905396, "learning_rate": 1.768497959599781e-05, "loss": 0.9454, "step": 4185 }, { "epoch": 0.2445093457943925, "grad_norm": 1.7319154739379883, "learning_rate": 1.7683768959208838e-05, "loss": 0.7448, "step": 4186 }, { "epoch": 0.2445677570093458, "grad_norm": 1.7728166580200195, "learning_rate": 1.7682558047412728e-05, "loss": 0.7394, "step": 4187 }, { "epoch": 0.24462616822429906, "grad_norm": 1.2164305448532104, "learning_rate": 1.7681346860652812e-05, "loss": 0.7632, "step": 4188 }, { "epoch": 0.24468457943925234, "grad_norm": 1.8174420595169067, "learning_rate": 1.7680135398972443e-05, "loss": 0.9696, "step": 4189 }, { "epoch": 0.2447429906542056, "grad_norm": 2.110413074493408, "learning_rate": 1.7678923662414975e-05, "loss": 0.695, "step": 4190 }, { "epoch": 0.24480140186915889, "grad_norm": 2.6482577323913574, "learning_rate": 1.7677711651023782e-05, "loss": 0.9859, "step": 4191 }, { "epoch": 0.24485981308411214, "grad_norm": 1.403978943824768, "learning_rate": 1.767649936484224e-05, "loss": 0.9163, "step": 4192 }, { "epoch": 0.24491822429906543, "grad_norm": 2.5382189750671387, "learning_rate": 1.767528680391374e-05, "loss": 0.9487, "step": 4193 }, { "epoch": 0.2449766355140187, "grad_norm": 1.38845694065094, "learning_rate": 1.767407396828168e-05, "loss": 0.888, "step": 4194 }, { "epoch": 0.24503504672897197, "grad_norm": 1.6353354454040527, "learning_rate": 1.7672860857989463e-05, "loss": 0.75, "step": 4195 }, { "epoch": 0.24509345794392523, "grad_norm": 1.163806676864624, "learning_rate": 1.7671647473080512e-05, "loss": 0.7704, "step": 4196 }, { "epoch": 0.24515186915887852, "grad_norm": 1.654999017715454, "learning_rate": 1.7670433813598256e-05, "loss": 1.0841, "step": 4197 }, { "epoch": 0.24521028037383177, "grad_norm": 1.5436253547668457, "learning_rate": 1.7669219879586126e-05, "loss": 0.7512, "step": 4198 }, { "epoch": 0.24526869158878506, "grad_norm": 1.9763691425323486, "learning_rate": 1.7668005671087576e-05, "loss": 0.8597, "step": 4199 }, { "epoch": 0.24532710280373832, "grad_norm": 1.6269512176513672, "learning_rate": 1.7666791188146066e-05, "loss": 0.8929, "step": 4200 }, { "epoch": 0.24538551401869158, "grad_norm": 1.5540958642959595, "learning_rate": 1.7665576430805053e-05, "loss": 0.8126, "step": 4201 }, { "epoch": 0.24544392523364486, "grad_norm": 1.199355125427246, "learning_rate": 1.766436139910802e-05, "loss": 0.6824, "step": 4202 }, { "epoch": 0.24550233644859812, "grad_norm": 1.6631860733032227, "learning_rate": 1.7663146093098455e-05, "loss": 0.8706, "step": 4203 }, { "epoch": 0.2455607476635514, "grad_norm": 1.1029735803604126, "learning_rate": 1.7661930512819848e-05, "loss": 0.7552, "step": 4204 }, { "epoch": 0.24561915887850466, "grad_norm": 1.6565488576889038, "learning_rate": 1.7660714658315718e-05, "loss": 0.9275, "step": 4205 }, { "epoch": 0.24567757009345795, "grad_norm": 1.969421625137329, "learning_rate": 1.765949852962957e-05, "loss": 0.8653, "step": 4206 }, { "epoch": 0.2457359813084112, "grad_norm": 1.2198662757873535, "learning_rate": 1.765828212680493e-05, "loss": 0.7864, "step": 4207 }, { "epoch": 0.2457943925233645, "grad_norm": 1.8622353076934814, "learning_rate": 1.765706544988534e-05, "loss": 0.878, "step": 4208 }, { "epoch": 0.24585280373831775, "grad_norm": 1.330214262008667, "learning_rate": 1.765584849891434e-05, "loss": 0.8251, "step": 4209 }, { "epoch": 0.24591121495327103, "grad_norm": 1.277708888053894, "learning_rate": 1.7654631273935493e-05, "loss": 0.8718, "step": 4210 }, { "epoch": 0.2459696261682243, "grad_norm": 2.2003321647644043, "learning_rate": 1.765341377499236e-05, "loss": 1.0289, "step": 4211 }, { "epoch": 0.24602803738317758, "grad_norm": 1.680095911026001, "learning_rate": 1.7652196002128508e-05, "loss": 0.7204, "step": 4212 }, { "epoch": 0.24608644859813084, "grad_norm": 2.1896090507507324, "learning_rate": 1.7650977955387538e-05, "loss": 1.0101, "step": 4213 }, { "epoch": 0.24614485981308412, "grad_norm": 1.4467071294784546, "learning_rate": 1.7649759634813033e-05, "loss": 0.8567, "step": 4214 }, { "epoch": 0.24620327102803738, "grad_norm": 2.2323355674743652, "learning_rate": 1.7648541040448603e-05, "loss": 0.7909, "step": 4215 }, { "epoch": 0.24626168224299066, "grad_norm": 1.2071423530578613, "learning_rate": 1.764732217233786e-05, "loss": 0.9297, "step": 4216 }, { "epoch": 0.24632009345794392, "grad_norm": 2.600080966949463, "learning_rate": 1.7646103030524423e-05, "loss": 1.0267, "step": 4217 }, { "epoch": 0.2463785046728972, "grad_norm": 1.4055012464523315, "learning_rate": 1.7644883615051936e-05, "loss": 0.7456, "step": 4218 }, { "epoch": 0.24643691588785047, "grad_norm": 1.9932663440704346, "learning_rate": 1.7643663925964035e-05, "loss": 0.9155, "step": 4219 }, { "epoch": 0.24649532710280375, "grad_norm": 1.537703514099121, "learning_rate": 1.7642443963304377e-05, "loss": 1.0714, "step": 4220 }, { "epoch": 0.246553738317757, "grad_norm": 1.788356900215149, "learning_rate": 1.764122372711663e-05, "loss": 1.0246, "step": 4221 }, { "epoch": 0.24661214953271027, "grad_norm": 1.2538788318634033, "learning_rate": 1.7640003217444452e-05, "loss": 0.7401, "step": 4222 }, { "epoch": 0.24667056074766355, "grad_norm": 1.381060004234314, "learning_rate": 1.763878243433154e-05, "loss": 0.8368, "step": 4223 }, { "epoch": 0.2467289719626168, "grad_norm": 1.2549331188201904, "learning_rate": 1.7637561377821586e-05, "loss": 0.706, "step": 4224 }, { "epoch": 0.2467873831775701, "grad_norm": 1.0669025182724, "learning_rate": 1.7636340047958286e-05, "loss": 0.7434, "step": 4225 }, { "epoch": 0.24684579439252335, "grad_norm": 1.7404422760009766, "learning_rate": 1.763511844478535e-05, "loss": 0.8751, "step": 4226 }, { "epoch": 0.24690420560747664, "grad_norm": 1.4416704177856445, "learning_rate": 1.763389656834651e-05, "loss": 0.7554, "step": 4227 }, { "epoch": 0.2469626168224299, "grad_norm": 1.6023699045181274, "learning_rate": 1.763267441868549e-05, "loss": 0.961, "step": 4228 }, { "epoch": 0.24702102803738318, "grad_norm": 1.599575161933899, "learning_rate": 1.7631451995846036e-05, "loss": 1.086, "step": 4229 }, { "epoch": 0.24707943925233644, "grad_norm": 1.2290825843811035, "learning_rate": 1.7630229299871895e-05, "loss": 0.7862, "step": 4230 }, { "epoch": 0.24713785046728973, "grad_norm": 1.6515192985534668, "learning_rate": 1.7629006330806834e-05, "loss": 0.8684, "step": 4231 }, { "epoch": 0.24719626168224298, "grad_norm": 1.3240400552749634, "learning_rate": 1.7627783088694617e-05, "loss": 0.7949, "step": 4232 }, { "epoch": 0.24725467289719627, "grad_norm": 1.1578718423843384, "learning_rate": 1.762655957357903e-05, "loss": 0.864, "step": 4233 }, { "epoch": 0.24731308411214953, "grad_norm": 2.2896435260772705, "learning_rate": 1.762533578550386e-05, "loss": 1.0184, "step": 4234 }, { "epoch": 0.2473714953271028, "grad_norm": 1.7611702680587769, "learning_rate": 1.7624111724512904e-05, "loss": 0.9271, "step": 4235 }, { "epoch": 0.24742990654205607, "grad_norm": 1.0805392265319824, "learning_rate": 1.7622887390649984e-05, "loss": 0.7771, "step": 4236 }, { "epoch": 0.24748831775700936, "grad_norm": 1.6456334590911865, "learning_rate": 1.7621662783958907e-05, "loss": 0.9321, "step": 4237 }, { "epoch": 0.24754672897196262, "grad_norm": 1.296358585357666, "learning_rate": 1.7620437904483512e-05, "loss": 0.8969, "step": 4238 }, { "epoch": 0.2476051401869159, "grad_norm": 1.25215482711792, "learning_rate": 1.7619212752267628e-05, "loss": 0.5278, "step": 4239 }, { "epoch": 0.24766355140186916, "grad_norm": 1.5425528287887573, "learning_rate": 1.7617987327355114e-05, "loss": 0.8668, "step": 4240 }, { "epoch": 0.24772196261682242, "grad_norm": 1.452989101409912, "learning_rate": 1.7616761629789824e-05, "loss": 0.8801, "step": 4241 }, { "epoch": 0.2477803738317757, "grad_norm": 1.771457314491272, "learning_rate": 1.761553565961563e-05, "loss": 0.9572, "step": 4242 }, { "epoch": 0.24783878504672896, "grad_norm": 1.3768471479415894, "learning_rate": 1.7614309416876402e-05, "loss": 0.6866, "step": 4243 }, { "epoch": 0.24789719626168225, "grad_norm": 1.7523553371429443, "learning_rate": 1.7613082901616035e-05, "loss": 0.85, "step": 4244 }, { "epoch": 0.2479556074766355, "grad_norm": 1.1930609941482544, "learning_rate": 1.761185611387843e-05, "loss": 0.871, "step": 4245 }, { "epoch": 0.2480140186915888, "grad_norm": 1.329492211341858, "learning_rate": 1.7610629053707486e-05, "loss": 0.781, "step": 4246 }, { "epoch": 0.24807242990654205, "grad_norm": 1.4240928888320923, "learning_rate": 1.760940172114712e-05, "loss": 0.772, "step": 4247 }, { "epoch": 0.24813084112149533, "grad_norm": 1.4990650415420532, "learning_rate": 1.760817411624127e-05, "loss": 0.8113, "step": 4248 }, { "epoch": 0.2481892523364486, "grad_norm": 1.4246257543563843, "learning_rate": 1.7606946239033865e-05, "loss": 0.7783, "step": 4249 }, { "epoch": 0.24824766355140188, "grad_norm": 1.321437120437622, "learning_rate": 1.7605718089568848e-05, "loss": 0.6748, "step": 4250 }, { "epoch": 0.24830607476635513, "grad_norm": 2.276313304901123, "learning_rate": 1.7604489667890182e-05, "loss": 0.7384, "step": 4251 }, { "epoch": 0.24836448598130842, "grad_norm": 1.5980178117752075, "learning_rate": 1.7603260974041833e-05, "loss": 0.9125, "step": 4252 }, { "epoch": 0.24842289719626168, "grad_norm": 2.3669731616973877, "learning_rate": 1.7602032008067775e-05, "loss": 0.7285, "step": 4253 }, { "epoch": 0.24848130841121496, "grad_norm": 2.4884281158447266, "learning_rate": 1.7600802770011985e-05, "loss": 1.1335, "step": 4254 }, { "epoch": 0.24853971962616822, "grad_norm": 1.577496886253357, "learning_rate": 1.7599573259918473e-05, "loss": 0.7792, "step": 4255 }, { "epoch": 0.2485981308411215, "grad_norm": 3.708017110824585, "learning_rate": 1.7598343477831236e-05, "loss": 0.9298, "step": 4256 }, { "epoch": 0.24865654205607476, "grad_norm": 1.5803805589675903, "learning_rate": 1.759711342379429e-05, "loss": 0.8467, "step": 4257 }, { "epoch": 0.24871495327102805, "grad_norm": 2.969589948654175, "learning_rate": 1.759588309785166e-05, "loss": 0.8476, "step": 4258 }, { "epoch": 0.2487733644859813, "grad_norm": 3.644172191619873, "learning_rate": 1.759465250004738e-05, "loss": 0.9373, "step": 4259 }, { "epoch": 0.2488317757009346, "grad_norm": 1.9475737810134888, "learning_rate": 1.759342163042549e-05, "loss": 0.9471, "step": 4260 }, { "epoch": 0.24889018691588785, "grad_norm": 2.4003589153289795, "learning_rate": 1.759219048903005e-05, "loss": 0.9426, "step": 4261 }, { "epoch": 0.2489485981308411, "grad_norm": 2.32728910446167, "learning_rate": 1.7590959075905122e-05, "loss": 0.9003, "step": 4262 }, { "epoch": 0.2490070093457944, "grad_norm": 1.6664472818374634, "learning_rate": 1.7589727391094772e-05, "loss": 0.8868, "step": 4263 }, { "epoch": 0.24906542056074765, "grad_norm": 2.6481173038482666, "learning_rate": 1.7588495434643094e-05, "loss": 0.9678, "step": 4264 }, { "epoch": 0.24912383177570094, "grad_norm": 1.901961326599121, "learning_rate": 1.758726320659417e-05, "loss": 0.8311, "step": 4265 }, { "epoch": 0.2491822429906542, "grad_norm": 1.2302719354629517, "learning_rate": 1.758603070699211e-05, "loss": 0.8977, "step": 4266 }, { "epoch": 0.24924065420560748, "grad_norm": 2.384772539138794, "learning_rate": 1.7584797935881025e-05, "loss": 0.87, "step": 4267 }, { "epoch": 0.24929906542056074, "grad_norm": 1.859615445137024, "learning_rate": 1.7583564893305033e-05, "loss": 0.9555, "step": 4268 }, { "epoch": 0.24935747663551402, "grad_norm": 1.7088230848312378, "learning_rate": 1.7582331579308266e-05, "loss": 0.8595, "step": 4269 }, { "epoch": 0.24941588785046728, "grad_norm": 1.6782256364822388, "learning_rate": 1.7581097993934866e-05, "loss": 0.8076, "step": 4270 }, { "epoch": 0.24947429906542057, "grad_norm": 1.9180902242660522, "learning_rate": 1.7579864137228986e-05, "loss": 0.7982, "step": 4271 }, { "epoch": 0.24953271028037383, "grad_norm": 1.4376919269561768, "learning_rate": 1.7578630009234784e-05, "loss": 0.8786, "step": 4272 }, { "epoch": 0.2495911214953271, "grad_norm": 1.9098461866378784, "learning_rate": 1.7577395609996427e-05, "loss": 0.8083, "step": 4273 }, { "epoch": 0.24964953271028037, "grad_norm": 2.2084672451019287, "learning_rate": 1.7576160939558103e-05, "loss": 0.9354, "step": 4274 }, { "epoch": 0.24970794392523366, "grad_norm": 1.4996917247772217, "learning_rate": 1.7574925997963998e-05, "loss": 0.7811, "step": 4275 }, { "epoch": 0.2497663551401869, "grad_norm": 1.9670242071151733, "learning_rate": 1.757369078525831e-05, "loss": 0.8377, "step": 4276 }, { "epoch": 0.2498247663551402, "grad_norm": 1.4187402725219727, "learning_rate": 1.757245530148525e-05, "loss": 0.8926, "step": 4277 }, { "epoch": 0.24988317757009346, "grad_norm": 2.1163642406463623, "learning_rate": 1.7571219546689034e-05, "loss": 0.9022, "step": 4278 }, { "epoch": 0.24994158878504674, "grad_norm": 1.949758768081665, "learning_rate": 1.7569983520913895e-05, "loss": 0.9591, "step": 4279 }, { "epoch": 0.25, "grad_norm": 1.2565323114395142, "learning_rate": 1.7568747224204067e-05, "loss": 0.7262, "step": 4280 }, { "epoch": 0.25005841121495326, "grad_norm": 2.8514914512634277, "learning_rate": 1.7567510656603798e-05, "loss": 0.9002, "step": 4281 }, { "epoch": 0.2501168224299065, "grad_norm": 1.5365941524505615, "learning_rate": 1.7566273818157348e-05, "loss": 1.1257, "step": 4282 }, { "epoch": 0.25017523364485983, "grad_norm": 2.840517044067383, "learning_rate": 1.756503670890898e-05, "loss": 0.9298, "step": 4283 }, { "epoch": 0.2502336448598131, "grad_norm": 1.240410327911377, "learning_rate": 1.7563799328902978e-05, "loss": 0.6818, "step": 4284 }, { "epoch": 0.25029205607476634, "grad_norm": 2.9528274536132812, "learning_rate": 1.7562561678183624e-05, "loss": 0.7609, "step": 4285 }, { "epoch": 0.2503504672897196, "grad_norm": 1.587003469467163, "learning_rate": 1.7561323756795214e-05, "loss": 0.8637, "step": 4286 }, { "epoch": 0.2504088785046729, "grad_norm": 1.7923500537872314, "learning_rate": 1.7560085564782057e-05, "loss": 0.6661, "step": 4287 }, { "epoch": 0.2504672897196262, "grad_norm": 1.4341468811035156, "learning_rate": 1.7558847102188464e-05, "loss": 0.8707, "step": 4288 }, { "epoch": 0.25052570093457943, "grad_norm": 1.331661581993103, "learning_rate": 1.755760836905877e-05, "loss": 0.7596, "step": 4289 }, { "epoch": 0.2505841121495327, "grad_norm": 1.1395916938781738, "learning_rate": 1.7556369365437293e-05, "loss": 0.708, "step": 4290 }, { "epoch": 0.250642523364486, "grad_norm": 1.3979294300079346, "learning_rate": 1.7555130091368396e-05, "loss": 0.8406, "step": 4291 }, { "epoch": 0.25070093457943926, "grad_norm": 1.6512377262115479, "learning_rate": 1.755389054689642e-05, "loss": 1.0891, "step": 4292 }, { "epoch": 0.2507593457943925, "grad_norm": 1.5540937185287476, "learning_rate": 1.7552650732065737e-05, "loss": 1.011, "step": 4293 }, { "epoch": 0.2508177570093458, "grad_norm": 1.442472219467163, "learning_rate": 1.755141064692072e-05, "loss": 0.8096, "step": 4294 }, { "epoch": 0.2508761682242991, "grad_norm": 2.534322500228882, "learning_rate": 1.7550170291505746e-05, "loss": 0.8328, "step": 4295 }, { "epoch": 0.25093457943925235, "grad_norm": 2.445997476577759, "learning_rate": 1.7548929665865217e-05, "loss": 0.9572, "step": 4296 }, { "epoch": 0.2509929906542056, "grad_norm": 1.2427587509155273, "learning_rate": 1.7547688770043533e-05, "loss": 0.7552, "step": 4297 }, { "epoch": 0.25105140186915886, "grad_norm": 2.1245977878570557, "learning_rate": 1.75464476040851e-05, "loss": 0.807, "step": 4298 }, { "epoch": 0.2511098130841122, "grad_norm": 1.6205453872680664, "learning_rate": 1.754520616803435e-05, "loss": 0.9503, "step": 4299 }, { "epoch": 0.25116822429906543, "grad_norm": 2.316624641418457, "learning_rate": 1.7543964461935708e-05, "loss": 0.7994, "step": 4300 }, { "epoch": 0.2512266355140187, "grad_norm": 1.5977929830551147, "learning_rate": 1.754272248583362e-05, "loss": 0.994, "step": 4301 }, { "epoch": 0.25128504672897195, "grad_norm": 2.311417579650879, "learning_rate": 1.754148023977253e-05, "loss": 0.9, "step": 4302 }, { "epoch": 0.2513434579439252, "grad_norm": 1.3758829832077026, "learning_rate": 1.7540237723796907e-05, "loss": 0.899, "step": 4303 }, { "epoch": 0.2514018691588785, "grad_norm": 1.9721405506134033, "learning_rate": 1.753899493795122e-05, "loss": 1.0041, "step": 4304 }, { "epoch": 0.2514602803738318, "grad_norm": 1.053052544593811, "learning_rate": 1.7537751882279942e-05, "loss": 0.8392, "step": 4305 }, { "epoch": 0.25151869158878504, "grad_norm": 1.966935396194458, "learning_rate": 1.7536508556827573e-05, "loss": 0.8484, "step": 4306 }, { "epoch": 0.2515771028037383, "grad_norm": 1.2443745136260986, "learning_rate": 1.7535264961638602e-05, "loss": 0.9231, "step": 4307 }, { "epoch": 0.2516355140186916, "grad_norm": 1.1504138708114624, "learning_rate": 1.753402109675755e-05, "loss": 0.7225, "step": 4308 }, { "epoch": 0.25169392523364487, "grad_norm": 2.7831368446350098, "learning_rate": 1.7532776962228924e-05, "loss": 0.9109, "step": 4309 }, { "epoch": 0.2517523364485981, "grad_norm": 1.576688528060913, "learning_rate": 1.753153255809726e-05, "loss": 0.7868, "step": 4310 }, { "epoch": 0.2518107476635514, "grad_norm": 1.736160397529602, "learning_rate": 1.7530287884407092e-05, "loss": 0.7506, "step": 4311 }, { "epoch": 0.2518691588785047, "grad_norm": 1.7260435819625854, "learning_rate": 1.7529042941202973e-05, "loss": 0.925, "step": 4312 }, { "epoch": 0.25192757009345795, "grad_norm": 1.698580026626587, "learning_rate": 1.7527797728529454e-05, "loss": 0.8858, "step": 4313 }, { "epoch": 0.2519859813084112, "grad_norm": 1.959253191947937, "learning_rate": 1.7526552246431105e-05, "loss": 0.675, "step": 4314 }, { "epoch": 0.25204439252336447, "grad_norm": 1.2513357400894165, "learning_rate": 1.7525306494952498e-05, "loss": 0.7917, "step": 4315 }, { "epoch": 0.2521028037383178, "grad_norm": 1.3293222188949585, "learning_rate": 1.752406047413823e-05, "loss": 0.7169, "step": 4316 }, { "epoch": 0.25216121495327104, "grad_norm": 1.485503911972046, "learning_rate": 1.7522814184032886e-05, "loss": 0.8503, "step": 4317 }, { "epoch": 0.2522196261682243, "grad_norm": 1.4255242347717285, "learning_rate": 1.752156762468108e-05, "loss": 0.7411, "step": 4318 }, { "epoch": 0.25227803738317756, "grad_norm": 1.612488865852356, "learning_rate": 1.7520320796127423e-05, "loss": 0.8707, "step": 4319 }, { "epoch": 0.2523364485981308, "grad_norm": 1.5834770202636719, "learning_rate": 1.7519073698416537e-05, "loss": 0.9321, "step": 4320 }, { "epoch": 0.2523948598130841, "grad_norm": 1.715219497680664, "learning_rate": 1.751782633159306e-05, "loss": 0.9826, "step": 4321 }, { "epoch": 0.2524532710280374, "grad_norm": 2.080122709274292, "learning_rate": 1.751657869570164e-05, "loss": 1.0799, "step": 4322 }, { "epoch": 0.25251168224299064, "grad_norm": 1.1132277250289917, "learning_rate": 1.751533079078692e-05, "loss": 0.5487, "step": 4323 }, { "epoch": 0.2525700934579439, "grad_norm": 2.104531764984131, "learning_rate": 1.751408261689357e-05, "loss": 0.9394, "step": 4324 }, { "epoch": 0.2526285046728972, "grad_norm": 1.6899287700653076, "learning_rate": 1.7512834174066266e-05, "loss": 0.8882, "step": 4325 }, { "epoch": 0.25268691588785047, "grad_norm": 1.801041841506958, "learning_rate": 1.7511585462349688e-05, "loss": 0.8721, "step": 4326 }, { "epoch": 0.25274532710280373, "grad_norm": 1.945582389831543, "learning_rate": 1.7510336481788525e-05, "loss": 0.8266, "step": 4327 }, { "epoch": 0.252803738317757, "grad_norm": 1.6456419229507446, "learning_rate": 1.750908723242748e-05, "loss": 0.9707, "step": 4328 }, { "epoch": 0.2528621495327103, "grad_norm": 1.481223225593567, "learning_rate": 1.7507837714311267e-05, "loss": 0.7381, "step": 4329 }, { "epoch": 0.25292056074766356, "grad_norm": 1.0101252794265747, "learning_rate": 1.7506587927484605e-05, "loss": 0.6498, "step": 4330 }, { "epoch": 0.2529789719626168, "grad_norm": 1.9575332403182983, "learning_rate": 1.7505337871992228e-05, "loss": 0.7928, "step": 4331 }, { "epoch": 0.2530373831775701, "grad_norm": 1.2641617059707642, "learning_rate": 1.7504087547878873e-05, "loss": 1.0467, "step": 4332 }, { "epoch": 0.2530957943925234, "grad_norm": 1.306683897972107, "learning_rate": 1.750283695518929e-05, "loss": 0.8885, "step": 4333 }, { "epoch": 0.25315420560747665, "grad_norm": 1.445953369140625, "learning_rate": 1.7501586093968236e-05, "loss": 0.7847, "step": 4334 }, { "epoch": 0.2532126168224299, "grad_norm": 1.3086107969284058, "learning_rate": 1.7500334964260487e-05, "loss": 0.8616, "step": 4335 }, { "epoch": 0.25327102803738316, "grad_norm": 1.7207030057907104, "learning_rate": 1.7499083566110815e-05, "loss": 0.9478, "step": 4336 }, { "epoch": 0.2533294392523365, "grad_norm": 1.4288910627365112, "learning_rate": 1.749783189956401e-05, "loss": 0.9078, "step": 4337 }, { "epoch": 0.25338785046728973, "grad_norm": 1.2254483699798584, "learning_rate": 1.749657996466488e-05, "loss": 0.8589, "step": 4338 }, { "epoch": 0.253446261682243, "grad_norm": 1.4199302196502686, "learning_rate": 1.7495327761458217e-05, "loss": 0.8121, "step": 4339 }, { "epoch": 0.25350467289719625, "grad_norm": 1.3325912952423096, "learning_rate": 1.7494075289988845e-05, "loss": 0.9682, "step": 4340 }, { "epoch": 0.2535630841121495, "grad_norm": 1.235170841217041, "learning_rate": 1.7492822550301595e-05, "loss": 0.8181, "step": 4341 }, { "epoch": 0.2536214953271028, "grad_norm": 1.591398000717163, "learning_rate": 1.7491569542441298e-05, "loss": 0.8605, "step": 4342 }, { "epoch": 0.2536799065420561, "grad_norm": 1.383178472518921, "learning_rate": 1.74903162664528e-05, "loss": 0.847, "step": 4343 }, { "epoch": 0.25373831775700934, "grad_norm": 1.2864216566085815, "learning_rate": 1.7489062722380957e-05, "loss": 0.7364, "step": 4344 }, { "epoch": 0.2537967289719626, "grad_norm": 1.557493805885315, "learning_rate": 1.7487808910270636e-05, "loss": 0.8941, "step": 4345 }, { "epoch": 0.2538551401869159, "grad_norm": 1.4527002573013306, "learning_rate": 1.7486554830166712e-05, "loss": 1.0676, "step": 4346 }, { "epoch": 0.25391355140186916, "grad_norm": 1.2189130783081055, "learning_rate": 1.7485300482114067e-05, "loss": 0.8385, "step": 4347 }, { "epoch": 0.2539719626168224, "grad_norm": 1.2458031177520752, "learning_rate": 1.7484045866157596e-05, "loss": 0.7456, "step": 4348 }, { "epoch": 0.2540303738317757, "grad_norm": 1.2596328258514404, "learning_rate": 1.7482790982342202e-05, "loss": 0.6982, "step": 4349 }, { "epoch": 0.254088785046729, "grad_norm": 1.3778808116912842, "learning_rate": 1.74815358307128e-05, "loss": 0.7162, "step": 4350 }, { "epoch": 0.25414719626168225, "grad_norm": 1.6427485942840576, "learning_rate": 1.748028041131431e-05, "loss": 0.8343, "step": 4351 }, { "epoch": 0.2542056074766355, "grad_norm": 1.0745244026184082, "learning_rate": 1.7479024724191668e-05, "loss": 0.6417, "step": 4352 }, { "epoch": 0.25426401869158877, "grad_norm": 1.3363276720046997, "learning_rate": 1.747776876938981e-05, "loss": 0.8693, "step": 4353 }, { "epoch": 0.2543224299065421, "grad_norm": 1.4058964252471924, "learning_rate": 1.7476512546953695e-05, "loss": 0.8181, "step": 4354 }, { "epoch": 0.25438084112149534, "grad_norm": 2.3689727783203125, "learning_rate": 1.747525605692828e-05, "loss": 0.8009, "step": 4355 }, { "epoch": 0.2544392523364486, "grad_norm": 1.1157797574996948, "learning_rate": 1.747399929935853e-05, "loss": 0.9023, "step": 4356 }, { "epoch": 0.25449766355140185, "grad_norm": 1.4037424325942993, "learning_rate": 1.7472742274289436e-05, "loss": 0.6814, "step": 4357 }, { "epoch": 0.25455607476635517, "grad_norm": 1.528555154800415, "learning_rate": 1.7471484981765982e-05, "loss": 0.8345, "step": 4358 }, { "epoch": 0.2546144859813084, "grad_norm": 1.6826107501983643, "learning_rate": 1.7470227421833166e-05, "loss": 0.9312, "step": 4359 }, { "epoch": 0.2546728971962617, "grad_norm": 2.051069974899292, "learning_rate": 1.7468969594536e-05, "loss": 0.9092, "step": 4360 }, { "epoch": 0.25473130841121494, "grad_norm": 1.4715944528579712, "learning_rate": 1.74677114999195e-05, "loss": 0.8426, "step": 4361 }, { "epoch": 0.2547897196261682, "grad_norm": 1.4972707033157349, "learning_rate": 1.7466453138028702e-05, "loss": 0.8512, "step": 4362 }, { "epoch": 0.2548481308411215, "grad_norm": 1.5086396932601929, "learning_rate": 1.7465194508908627e-05, "loss": 0.8594, "step": 4363 }, { "epoch": 0.25490654205607477, "grad_norm": 1.3461635112762451, "learning_rate": 1.7463935612604337e-05, "loss": 0.8965, "step": 4364 }, { "epoch": 0.254964953271028, "grad_norm": 1.6827178001403809, "learning_rate": 1.7462676449160883e-05, "loss": 0.9135, "step": 4365 }, { "epoch": 0.2550233644859813, "grad_norm": 1.2343552112579346, "learning_rate": 1.7461417018623336e-05, "loss": 0.8728, "step": 4366 }, { "epoch": 0.2550817757009346, "grad_norm": 1.2487332820892334, "learning_rate": 1.746015732103676e-05, "loss": 0.8619, "step": 4367 }, { "epoch": 0.25514018691588786, "grad_norm": 2.1494460105895996, "learning_rate": 1.7458897356446255e-05, "loss": 0.7151, "step": 4368 }, { "epoch": 0.2551985981308411, "grad_norm": 1.3120737075805664, "learning_rate": 1.7457637124896907e-05, "loss": 0.8485, "step": 4369 }, { "epoch": 0.2552570093457944, "grad_norm": 1.5621827840805054, "learning_rate": 1.7456376626433823e-05, "loss": 0.7918, "step": 4370 }, { "epoch": 0.2553154205607477, "grad_norm": 1.3899482488632202, "learning_rate": 1.7455115861102116e-05, "loss": 0.7948, "step": 4371 }, { "epoch": 0.25537383177570094, "grad_norm": 2.2829973697662354, "learning_rate": 1.7453854828946913e-05, "loss": 1.0879, "step": 4372 }, { "epoch": 0.2554322429906542, "grad_norm": 1.1852331161499023, "learning_rate": 1.745259353001334e-05, "loss": 0.9049, "step": 4373 }, { "epoch": 0.25549065420560746, "grad_norm": 1.5502643585205078, "learning_rate": 1.7451331964346548e-05, "loss": 0.8324, "step": 4374 }, { "epoch": 0.2555490654205608, "grad_norm": 1.4339995384216309, "learning_rate": 1.7450070131991683e-05, "loss": 0.8907, "step": 4375 }, { "epoch": 0.25560747663551403, "grad_norm": 1.5127424001693726, "learning_rate": 1.7448808032993912e-05, "loss": 0.8537, "step": 4376 }, { "epoch": 0.2556658878504673, "grad_norm": 1.3834714889526367, "learning_rate": 1.7447545667398406e-05, "loss": 0.7971, "step": 4377 }, { "epoch": 0.25572429906542055, "grad_norm": 1.0594052076339722, "learning_rate": 1.7446283035250336e-05, "loss": 0.7941, "step": 4378 }, { "epoch": 0.25578271028037386, "grad_norm": 1.7280389070510864, "learning_rate": 1.744502013659491e-05, "loss": 0.707, "step": 4379 }, { "epoch": 0.2558411214953271, "grad_norm": 1.2980223894119263, "learning_rate": 1.744375697147731e-05, "loss": 1.1666, "step": 4380 }, { "epoch": 0.2558995327102804, "grad_norm": 1.7643448114395142, "learning_rate": 1.7442493539942757e-05, "loss": 0.7735, "step": 4381 }, { "epoch": 0.25595794392523363, "grad_norm": 1.1989216804504395, "learning_rate": 1.7441229842036467e-05, "loss": 0.9142, "step": 4382 }, { "epoch": 0.2560163551401869, "grad_norm": 1.3064911365509033, "learning_rate": 1.743996587780367e-05, "loss": 0.9184, "step": 4383 }, { "epoch": 0.2560747663551402, "grad_norm": 1.4785159826278687, "learning_rate": 1.7438701647289597e-05, "loss": 0.8963, "step": 4384 }, { "epoch": 0.25613317757009346, "grad_norm": 1.925986647605896, "learning_rate": 1.7437437150539504e-05, "loss": 0.9484, "step": 4385 }, { "epoch": 0.2561915887850467, "grad_norm": 1.4636785984039307, "learning_rate": 1.7436172387598646e-05, "loss": 1.0112, "step": 4386 }, { "epoch": 0.25625, "grad_norm": 1.3800063133239746, "learning_rate": 1.7434907358512286e-05, "loss": 0.9301, "step": 4387 }, { "epoch": 0.2563084112149533, "grad_norm": 1.7896366119384766, "learning_rate": 1.7433642063325708e-05, "loss": 0.8452, "step": 4388 }, { "epoch": 0.25636682242990655, "grad_norm": 1.900508165359497, "learning_rate": 1.743237650208419e-05, "loss": 0.9002, "step": 4389 }, { "epoch": 0.2564252336448598, "grad_norm": 2.0529749393463135, "learning_rate": 1.743111067483303e-05, "loss": 0.9177, "step": 4390 }, { "epoch": 0.25648364485981306, "grad_norm": 1.2239737510681152, "learning_rate": 1.7429844581617532e-05, "loss": 0.8685, "step": 4391 }, { "epoch": 0.2565420560747664, "grad_norm": 1.4567921161651611, "learning_rate": 1.742857822248301e-05, "loss": 0.9188, "step": 4392 }, { "epoch": 0.25660046728971964, "grad_norm": 2.0204644203186035, "learning_rate": 1.7427311597474793e-05, "loss": 0.7109, "step": 4393 }, { "epoch": 0.2566588785046729, "grad_norm": 1.6224309206008911, "learning_rate": 1.742604470663821e-05, "loss": 0.8025, "step": 4394 }, { "epoch": 0.25671728971962615, "grad_norm": 2.849740505218506, "learning_rate": 1.7424777550018605e-05, "loss": 1.1061, "step": 4395 }, { "epoch": 0.25677570093457946, "grad_norm": 1.0391151905059814, "learning_rate": 1.7423510127661324e-05, "loss": 0.7546, "step": 4396 }, { "epoch": 0.2568341121495327, "grad_norm": 3.7871978282928467, "learning_rate": 1.742224243961174e-05, "loss": 0.9282, "step": 4397 }, { "epoch": 0.256892523364486, "grad_norm": 2.097907304763794, "learning_rate": 1.7420974485915216e-05, "loss": 0.9002, "step": 4398 }, { "epoch": 0.25695093457943924, "grad_norm": 2.5068819522857666, "learning_rate": 1.7419706266617137e-05, "loss": 0.9397, "step": 4399 }, { "epoch": 0.2570093457943925, "grad_norm": 2.358572244644165, "learning_rate": 1.7418437781762893e-05, "loss": 0.8566, "step": 4400 }, { "epoch": 0.2570677570093458, "grad_norm": 1.465844988822937, "learning_rate": 1.7417169031397877e-05, "loss": 0.8031, "step": 4401 }, { "epoch": 0.25712616822429907, "grad_norm": 2.6425421237945557, "learning_rate": 1.741590001556751e-05, "loss": 0.8709, "step": 4402 }, { "epoch": 0.2571845794392523, "grad_norm": 1.4845269918441772, "learning_rate": 1.7414630734317205e-05, "loss": 0.7749, "step": 4403 }, { "epoch": 0.2572429906542056, "grad_norm": 1.496203899383545, "learning_rate": 1.741336118769239e-05, "loss": 0.7947, "step": 4404 }, { "epoch": 0.2573014018691589, "grad_norm": 1.929979681968689, "learning_rate": 1.7412091375738507e-05, "loss": 1.0271, "step": 4405 }, { "epoch": 0.25735981308411215, "grad_norm": 0.8925808668136597, "learning_rate": 1.7410821298500994e-05, "loss": 0.7014, "step": 4406 }, { "epoch": 0.2574182242990654, "grad_norm": 1.5614187717437744, "learning_rate": 1.740955095602532e-05, "loss": 0.823, "step": 4407 }, { "epoch": 0.25747663551401867, "grad_norm": 0.9618955254554749, "learning_rate": 1.7408280348356942e-05, "loss": 0.7021, "step": 4408 }, { "epoch": 0.257535046728972, "grad_norm": 1.2783229351043701, "learning_rate": 1.7407009475541338e-05, "loss": 0.7332, "step": 4409 }, { "epoch": 0.25759345794392524, "grad_norm": 1.4544265270233154, "learning_rate": 1.7405738337623998e-05, "loss": 0.9098, "step": 4410 }, { "epoch": 0.2576518691588785, "grad_norm": 1.135457992553711, "learning_rate": 1.740446693465041e-05, "loss": 0.7741, "step": 4411 }, { "epoch": 0.25771028037383176, "grad_norm": 1.265114426612854, "learning_rate": 1.7403195266666086e-05, "loss": 1.0566, "step": 4412 }, { "epoch": 0.25776869158878507, "grad_norm": 1.2624664306640625, "learning_rate": 1.7401923333716534e-05, "loss": 0.6837, "step": 4413 }, { "epoch": 0.25782710280373833, "grad_norm": 1.1648640632629395, "learning_rate": 1.740065113584728e-05, "loss": 0.8562, "step": 4414 }, { "epoch": 0.2578855140186916, "grad_norm": 1.5700461864471436, "learning_rate": 1.7399378673103854e-05, "loss": 0.7787, "step": 4415 }, { "epoch": 0.25794392523364484, "grad_norm": 1.2807748317718506, "learning_rate": 1.73981059455318e-05, "loss": 0.7309, "step": 4416 }, { "epoch": 0.25800233644859816, "grad_norm": 1.3018414974212646, "learning_rate": 1.7396832953176672e-05, "loss": 0.7984, "step": 4417 }, { "epoch": 0.2580607476635514, "grad_norm": 1.9772839546203613, "learning_rate": 1.7395559696084027e-05, "loss": 1.0003, "step": 4418 }, { "epoch": 0.2581191588785047, "grad_norm": 1.0528137683868408, "learning_rate": 1.7394286174299437e-05, "loss": 0.8335, "step": 4419 }, { "epoch": 0.25817757009345793, "grad_norm": 1.4886040687561035, "learning_rate": 1.7393012387868483e-05, "loss": 0.8787, "step": 4420 }, { "epoch": 0.2582359813084112, "grad_norm": 1.1174938678741455, "learning_rate": 1.7391738336836755e-05, "loss": 0.7702, "step": 4421 }, { "epoch": 0.2582943925233645, "grad_norm": 1.2546335458755493, "learning_rate": 1.7390464021249855e-05, "loss": 0.7541, "step": 4422 }, { "epoch": 0.25835280373831776, "grad_norm": 1.1243650913238525, "learning_rate": 1.738918944115339e-05, "loss": 0.8876, "step": 4423 }, { "epoch": 0.258411214953271, "grad_norm": 1.3730055093765259, "learning_rate": 1.738791459659297e-05, "loss": 0.7728, "step": 4424 }, { "epoch": 0.2584696261682243, "grad_norm": 1.2998182773590088, "learning_rate": 1.7386639487614232e-05, "loss": 0.8763, "step": 4425 }, { "epoch": 0.2585280373831776, "grad_norm": 1.5384929180145264, "learning_rate": 1.738536411426281e-05, "loss": 0.9733, "step": 4426 }, { "epoch": 0.25858644859813085, "grad_norm": 1.1641212701797485, "learning_rate": 1.7384088476584347e-05, "loss": 0.841, "step": 4427 }, { "epoch": 0.2586448598130841, "grad_norm": 1.191151738166809, "learning_rate": 1.7382812574624507e-05, "loss": 0.8757, "step": 4428 }, { "epoch": 0.25870327102803736, "grad_norm": 1.3104276657104492, "learning_rate": 1.7381536408428948e-05, "loss": 0.9303, "step": 4429 }, { "epoch": 0.2587616822429907, "grad_norm": 1.1567192077636719, "learning_rate": 1.738025997804335e-05, "loss": 0.9358, "step": 4430 }, { "epoch": 0.25882009345794393, "grad_norm": 1.4357249736785889, "learning_rate": 1.737898328351339e-05, "loss": 0.9842, "step": 4431 }, { "epoch": 0.2588785046728972, "grad_norm": 1.1411546468734741, "learning_rate": 1.737770632488477e-05, "loss": 0.8423, "step": 4432 }, { "epoch": 0.25893691588785045, "grad_norm": 1.210915446281433, "learning_rate": 1.737642910220319e-05, "loss": 0.8965, "step": 4433 }, { "epoch": 0.25899532710280376, "grad_norm": 1.1554478406906128, "learning_rate": 1.7375151615514365e-05, "loss": 0.7753, "step": 4434 }, { "epoch": 0.259053738317757, "grad_norm": 1.4302380084991455, "learning_rate": 1.7373873864864006e-05, "loss": 0.7893, "step": 4435 }, { "epoch": 0.2591121495327103, "grad_norm": 1.4010776281356812, "learning_rate": 1.737259585029786e-05, "loss": 0.8951, "step": 4436 }, { "epoch": 0.25917056074766354, "grad_norm": 1.575037956237793, "learning_rate": 1.737131757186166e-05, "loss": 1.0556, "step": 4437 }, { "epoch": 0.25922897196261685, "grad_norm": 1.6155341863632202, "learning_rate": 1.7370039029601157e-05, "loss": 0.7818, "step": 4438 }, { "epoch": 0.2592873831775701, "grad_norm": 4.432505130767822, "learning_rate": 1.7368760223562108e-05, "loss": 0.9763, "step": 4439 }, { "epoch": 0.25934579439252337, "grad_norm": 1.644836664199829, "learning_rate": 1.736748115379029e-05, "loss": 0.8417, "step": 4440 }, { "epoch": 0.2594042056074766, "grad_norm": 2.7123727798461914, "learning_rate": 1.7366201820331476e-05, "loss": 1.0107, "step": 4441 }, { "epoch": 0.2594626168224299, "grad_norm": 2.814399480819702, "learning_rate": 1.7364922223231455e-05, "loss": 0.9247, "step": 4442 }, { "epoch": 0.2595210280373832, "grad_norm": 1.5992419719696045, "learning_rate": 1.7363642362536023e-05, "loss": 0.8529, "step": 4443 }, { "epoch": 0.25957943925233645, "grad_norm": 2.897857427597046, "learning_rate": 1.7362362238290993e-05, "loss": 0.7784, "step": 4444 }, { "epoch": 0.2596378504672897, "grad_norm": 2.3985888957977295, "learning_rate": 1.7361081850542178e-05, "loss": 0.7999, "step": 4445 }, { "epoch": 0.25969626168224297, "grad_norm": 1.9876166582107544, "learning_rate": 1.7359801199335396e-05, "loss": 1.1197, "step": 4446 }, { "epoch": 0.2597546728971963, "grad_norm": 1.6056170463562012, "learning_rate": 1.73585202847165e-05, "loss": 0.791, "step": 4447 }, { "epoch": 0.25981308411214954, "grad_norm": 1.5070011615753174, "learning_rate": 1.735723910673132e-05, "loss": 0.7779, "step": 4448 }, { "epoch": 0.2598714953271028, "grad_norm": 1.9010744094848633, "learning_rate": 1.7355957665425712e-05, "loss": 1.0055, "step": 4449 }, { "epoch": 0.25992990654205606, "grad_norm": 1.543009638786316, "learning_rate": 1.7354675960845546e-05, "loss": 0.9178, "step": 4450 }, { "epoch": 0.25998831775700937, "grad_norm": 1.551310658454895, "learning_rate": 1.735339399303669e-05, "loss": 0.8484, "step": 4451 }, { "epoch": 0.2600467289719626, "grad_norm": 1.4700149297714233, "learning_rate": 1.735211176204503e-05, "loss": 0.9445, "step": 4452 }, { "epoch": 0.2601051401869159, "grad_norm": 1.5204676389694214, "learning_rate": 1.7350829267916456e-05, "loss": 0.946, "step": 4453 }, { "epoch": 0.26016355140186914, "grad_norm": 1.1356561183929443, "learning_rate": 1.734954651069687e-05, "loss": 0.7046, "step": 4454 }, { "epoch": 0.26022196261682246, "grad_norm": 1.4153565168380737, "learning_rate": 1.7348263490432175e-05, "loss": 0.8232, "step": 4455 }, { "epoch": 0.2602803738317757, "grad_norm": 1.0576757192611694, "learning_rate": 1.7346980207168305e-05, "loss": 0.9372, "step": 4456 }, { "epoch": 0.26033878504672897, "grad_norm": 1.1433755159378052, "learning_rate": 1.734569666095118e-05, "loss": 0.6006, "step": 4457 }, { "epoch": 0.26039719626168223, "grad_norm": 1.8308717012405396, "learning_rate": 1.7344412851826743e-05, "loss": 0.9692, "step": 4458 }, { "epoch": 0.2604556074766355, "grad_norm": 1.872585415840149, "learning_rate": 1.734312877984094e-05, "loss": 0.7874, "step": 4459 }, { "epoch": 0.2605140186915888, "grad_norm": 2.571072578430176, "learning_rate": 1.7341844445039734e-05, "loss": 0.9964, "step": 4460 }, { "epoch": 0.26057242990654206, "grad_norm": 1.510489821434021, "learning_rate": 1.7340559847469084e-05, "loss": 0.8833, "step": 4461 }, { "epoch": 0.2606308411214953, "grad_norm": 2.0310354232788086, "learning_rate": 1.733927498717497e-05, "loss": 0.9943, "step": 4462 }, { "epoch": 0.2606892523364486, "grad_norm": 1.2084722518920898, "learning_rate": 1.7337989864203378e-05, "loss": 0.7462, "step": 4463 }, { "epoch": 0.2607476635514019, "grad_norm": 1.4754887819290161, "learning_rate": 1.7336704478600307e-05, "loss": 0.7671, "step": 4464 }, { "epoch": 0.26080607476635514, "grad_norm": 1.3632855415344238, "learning_rate": 1.7335418830411755e-05, "loss": 0.9127, "step": 4465 }, { "epoch": 0.2608644859813084, "grad_norm": 1.147194743156433, "learning_rate": 1.733413291968374e-05, "loss": 0.6894, "step": 4466 }, { "epoch": 0.26092289719626166, "grad_norm": 1.1927554607391357, "learning_rate": 1.733284674646229e-05, "loss": 0.8795, "step": 4467 }, { "epoch": 0.260981308411215, "grad_norm": 1.3009803295135498, "learning_rate": 1.733156031079343e-05, "loss": 0.7551, "step": 4468 }, { "epoch": 0.26103971962616823, "grad_norm": 1.4626731872558594, "learning_rate": 1.7330273612723206e-05, "loss": 0.9209, "step": 4469 }, { "epoch": 0.2610981308411215, "grad_norm": 1.4665393829345703, "learning_rate": 1.7328986652297672e-05, "loss": 0.832, "step": 4470 }, { "epoch": 0.26115654205607475, "grad_norm": 1.4252609014511108, "learning_rate": 1.7327699429562887e-05, "loss": 0.8709, "step": 4471 }, { "epoch": 0.26121495327102806, "grad_norm": 1.1809054613113403, "learning_rate": 1.7326411944564916e-05, "loss": 0.734, "step": 4472 }, { "epoch": 0.2612733644859813, "grad_norm": 1.8953700065612793, "learning_rate": 1.732512419734985e-05, "loss": 0.8364, "step": 4473 }, { "epoch": 0.2613317757009346, "grad_norm": 1.2014250755310059, "learning_rate": 1.732383618796377e-05, "loss": 0.9342, "step": 4474 }, { "epoch": 0.26139018691588783, "grad_norm": 1.2793428897857666, "learning_rate": 1.7322547916452777e-05, "loss": 0.8288, "step": 4475 }, { "epoch": 0.26144859813084115, "grad_norm": 1.1641409397125244, "learning_rate": 1.732125938286298e-05, "loss": 0.861, "step": 4476 }, { "epoch": 0.2615070093457944, "grad_norm": 1.3233996629714966, "learning_rate": 1.7319970587240497e-05, "loss": 0.7947, "step": 4477 }, { "epoch": 0.26156542056074766, "grad_norm": 0.8365027904510498, "learning_rate": 1.7318681529631452e-05, "loss": 0.7761, "step": 4478 }, { "epoch": 0.2616238317757009, "grad_norm": 1.2595728635787964, "learning_rate": 1.731739221008198e-05, "loss": 0.9057, "step": 4479 }, { "epoch": 0.2616822429906542, "grad_norm": 1.038280725479126, "learning_rate": 1.7316102628638235e-05, "loss": 0.6484, "step": 4480 }, { "epoch": 0.2617406542056075, "grad_norm": 1.3424686193466187, "learning_rate": 1.7314812785346365e-05, "loss": 0.8462, "step": 4481 }, { "epoch": 0.26179906542056075, "grad_norm": 1.0495190620422363, "learning_rate": 1.731352268025254e-05, "loss": 0.7672, "step": 4482 }, { "epoch": 0.261857476635514, "grad_norm": 1.611250877380371, "learning_rate": 1.7312232313402923e-05, "loss": 0.919, "step": 4483 }, { "epoch": 0.26191588785046727, "grad_norm": 1.0105141401290894, "learning_rate": 1.7310941684843705e-05, "loss": 0.8913, "step": 4484 }, { "epoch": 0.2619742990654206, "grad_norm": 1.1067065000534058, "learning_rate": 1.7309650794621077e-05, "loss": 0.751, "step": 4485 }, { "epoch": 0.26203271028037384, "grad_norm": 1.2715847492218018, "learning_rate": 1.730835964278124e-05, "loss": 0.8272, "step": 4486 }, { "epoch": 0.2620911214953271, "grad_norm": 1.291973352432251, "learning_rate": 1.7307068229370408e-05, "loss": 0.8419, "step": 4487 }, { "epoch": 0.26214953271028035, "grad_norm": 1.677229404449463, "learning_rate": 1.73057765544348e-05, "loss": 0.8786, "step": 4488 }, { "epoch": 0.26220794392523367, "grad_norm": 1.1519432067871094, "learning_rate": 1.7304484618020646e-05, "loss": 0.8301, "step": 4489 }, { "epoch": 0.2622663551401869, "grad_norm": 1.6156164407730103, "learning_rate": 1.7303192420174185e-05, "loss": 0.8713, "step": 4490 }, { "epoch": 0.2623247663551402, "grad_norm": 1.5990082025527954, "learning_rate": 1.7301899960941662e-05, "loss": 0.721, "step": 4491 }, { "epoch": 0.26238317757009344, "grad_norm": 1.2838518619537354, "learning_rate": 1.730060724036934e-05, "loss": 0.7791, "step": 4492 }, { "epoch": 0.26244158878504675, "grad_norm": 2.1646225452423096, "learning_rate": 1.7299314258503485e-05, "loss": 1.012, "step": 4493 }, { "epoch": 0.2625, "grad_norm": 1.4227895736694336, "learning_rate": 1.7298021015390375e-05, "loss": 0.8786, "step": 4494 }, { "epoch": 0.26255841121495327, "grad_norm": 1.4085832834243774, "learning_rate": 1.729672751107629e-05, "loss": 0.7136, "step": 4495 }, { "epoch": 0.2626168224299065, "grad_norm": 1.798667550086975, "learning_rate": 1.7295433745607532e-05, "loss": 0.8643, "step": 4496 }, { "epoch": 0.26267523364485984, "grad_norm": 1.3397340774536133, "learning_rate": 1.7294139719030403e-05, "loss": 0.9193, "step": 4497 }, { "epoch": 0.2627336448598131, "grad_norm": 2.027465343475342, "learning_rate": 1.7292845431391218e-05, "loss": 0.8053, "step": 4498 }, { "epoch": 0.26279205607476636, "grad_norm": 2.053009510040283, "learning_rate": 1.72915508827363e-05, "loss": 0.8095, "step": 4499 }, { "epoch": 0.2628504672897196, "grad_norm": 1.4267442226409912, "learning_rate": 1.7290256073111983e-05, "loss": 0.8791, "step": 4500 }, { "epoch": 0.26290887850467287, "grad_norm": 1.8666776418685913, "learning_rate": 1.7288961002564606e-05, "loss": 0.9909, "step": 4501 }, { "epoch": 0.2629672897196262, "grad_norm": 1.4081225395202637, "learning_rate": 1.728766567114052e-05, "loss": 0.6131, "step": 4502 }, { "epoch": 0.26302570093457944, "grad_norm": 1.4663031101226807, "learning_rate": 1.728637007888609e-05, "loss": 0.9098, "step": 4503 }, { "epoch": 0.2630841121495327, "grad_norm": 2.466500997543335, "learning_rate": 1.7285074225847685e-05, "loss": 0.8844, "step": 4504 }, { "epoch": 0.26314252336448596, "grad_norm": 1.3674476146697998, "learning_rate": 1.7283778112071683e-05, "loss": 0.8557, "step": 4505 }, { "epoch": 0.26320093457943927, "grad_norm": 2.5122387409210205, "learning_rate": 1.7282481737604473e-05, "loss": 1.0573, "step": 4506 }, { "epoch": 0.26325934579439253, "grad_norm": 1.4281342029571533, "learning_rate": 1.7281185102492456e-05, "loss": 0.8778, "step": 4507 }, { "epoch": 0.2633177570093458, "grad_norm": 1.6042686700820923, "learning_rate": 1.727988820678203e-05, "loss": 0.9667, "step": 4508 }, { "epoch": 0.26337616822429905, "grad_norm": 1.6028257608413696, "learning_rate": 1.7278591050519623e-05, "loss": 0.7118, "step": 4509 }, { "epoch": 0.26343457943925236, "grad_norm": 1.773690938949585, "learning_rate": 1.7277293633751656e-05, "loss": 0.9019, "step": 4510 }, { "epoch": 0.2634929906542056, "grad_norm": 1.9903775453567505, "learning_rate": 1.7275995956524565e-05, "loss": 0.8251, "step": 4511 }, { "epoch": 0.2635514018691589, "grad_norm": 1.3262861967086792, "learning_rate": 1.7274698018884793e-05, "loss": 0.5962, "step": 4512 }, { "epoch": 0.26360981308411213, "grad_norm": 2.196054458618164, "learning_rate": 1.72733998208788e-05, "loss": 0.8459, "step": 4513 }, { "epoch": 0.26366822429906545, "grad_norm": 2.195756673812866, "learning_rate": 1.727210136255304e-05, "loss": 0.9736, "step": 4514 }, { "epoch": 0.2637266355140187, "grad_norm": 2.819162130355835, "learning_rate": 1.7270802643953996e-05, "loss": 0.8904, "step": 4515 }, { "epoch": 0.26378504672897196, "grad_norm": 1.2414710521697998, "learning_rate": 1.726950366512814e-05, "loss": 0.7436, "step": 4516 }, { "epoch": 0.2638434579439252, "grad_norm": 3.0869016647338867, "learning_rate": 1.7268204426121967e-05, "loss": 0.9007, "step": 4517 }, { "epoch": 0.2639018691588785, "grad_norm": 2.4045403003692627, "learning_rate": 1.7266904926981985e-05, "loss": 0.7923, "step": 4518 }, { "epoch": 0.2639602803738318, "grad_norm": 1.2487614154815674, "learning_rate": 1.7265605167754692e-05, "loss": 0.8, "step": 4519 }, { "epoch": 0.26401869158878505, "grad_norm": 1.8212177753448486, "learning_rate": 1.7264305148486614e-05, "loss": 0.9014, "step": 4520 }, { "epoch": 0.2640771028037383, "grad_norm": 1.86962890625, "learning_rate": 1.726300486922428e-05, "loss": 1.0101, "step": 4521 }, { "epoch": 0.26413551401869156, "grad_norm": 1.9397146701812744, "learning_rate": 1.7261704330014226e-05, "loss": 0.777, "step": 4522 }, { "epoch": 0.2641939252336449, "grad_norm": 1.5688068866729736, "learning_rate": 1.7260403530903e-05, "loss": 0.857, "step": 4523 }, { "epoch": 0.26425233644859814, "grad_norm": 1.6418296098709106, "learning_rate": 1.7259102471937154e-05, "loss": 1.121, "step": 4524 }, { "epoch": 0.2643107476635514, "grad_norm": 2.2144644260406494, "learning_rate": 1.7257801153163258e-05, "loss": 1.0208, "step": 4525 }, { "epoch": 0.26436915887850465, "grad_norm": 1.1805896759033203, "learning_rate": 1.725649957462789e-05, "loss": 0.9577, "step": 4526 }, { "epoch": 0.26442757009345796, "grad_norm": 1.0532957315444946, "learning_rate": 1.7255197736377633e-05, "loss": 0.7476, "step": 4527 }, { "epoch": 0.2644859813084112, "grad_norm": 1.2070547342300415, "learning_rate": 1.7253895638459074e-05, "loss": 0.7157, "step": 4528 }, { "epoch": 0.2645443925233645, "grad_norm": 1.2951061725616455, "learning_rate": 1.725259328091882e-05, "loss": 0.859, "step": 4529 }, { "epoch": 0.26460280373831774, "grad_norm": 1.2053744792938232, "learning_rate": 1.7251290663803483e-05, "loss": 0.6752, "step": 4530 }, { "epoch": 0.26466121495327105, "grad_norm": 1.5118268728256226, "learning_rate": 1.724998778715969e-05, "loss": 0.9032, "step": 4531 }, { "epoch": 0.2647196261682243, "grad_norm": 1.572216272354126, "learning_rate": 1.7248684651034066e-05, "loss": 0.816, "step": 4532 }, { "epoch": 0.26477803738317757, "grad_norm": 1.2055916786193848, "learning_rate": 1.724738125547325e-05, "loss": 0.8369, "step": 4533 }, { "epoch": 0.2648364485981308, "grad_norm": 1.3258782625198364, "learning_rate": 1.7246077600523897e-05, "loss": 1.1057, "step": 4534 }, { "epoch": 0.26489485981308414, "grad_norm": 1.3268955945968628, "learning_rate": 1.724477368623266e-05, "loss": 0.7476, "step": 4535 }, { "epoch": 0.2649532710280374, "grad_norm": 1.487126350402832, "learning_rate": 1.724346951264621e-05, "loss": 0.7133, "step": 4536 }, { "epoch": 0.26501168224299065, "grad_norm": 2.699965715408325, "learning_rate": 1.7242165079811222e-05, "loss": 0.8848, "step": 4537 }, { "epoch": 0.2650700934579439, "grad_norm": 1.1971585750579834, "learning_rate": 1.7240860387774384e-05, "loss": 0.8359, "step": 4538 }, { "epoch": 0.26512850467289717, "grad_norm": 1.9726142883300781, "learning_rate": 1.723955543658239e-05, "loss": 0.8924, "step": 4539 }, { "epoch": 0.2651869158878505, "grad_norm": 1.9970507621765137, "learning_rate": 1.7238250226281952e-05, "loss": 1.1337, "step": 4540 }, { "epoch": 0.26524532710280374, "grad_norm": 1.0675498247146606, "learning_rate": 1.7236944756919776e-05, "loss": 0.7394, "step": 4541 }, { "epoch": 0.265303738317757, "grad_norm": 1.8896511793136597, "learning_rate": 1.723563902854259e-05, "loss": 1.0532, "step": 4542 }, { "epoch": 0.26536214953271026, "grad_norm": 1.1413075923919678, "learning_rate": 1.7234333041197127e-05, "loss": 0.8033, "step": 4543 }, { "epoch": 0.26542056074766357, "grad_norm": 1.0549700260162354, "learning_rate": 1.7233026794930125e-05, "loss": 0.8292, "step": 4544 }, { "epoch": 0.2654789719626168, "grad_norm": 1.3722245693206787, "learning_rate": 1.723172028978834e-05, "loss": 0.7643, "step": 4545 }, { "epoch": 0.2655373831775701, "grad_norm": 1.1683897972106934, "learning_rate": 1.723041352581853e-05, "loss": 0.8956, "step": 4546 }, { "epoch": 0.26559579439252334, "grad_norm": 1.6160260438919067, "learning_rate": 1.7229106503067464e-05, "loss": 0.808, "step": 4547 }, { "epoch": 0.26565420560747666, "grad_norm": 1.92608642578125, "learning_rate": 1.7227799221581927e-05, "loss": 0.7219, "step": 4548 }, { "epoch": 0.2657126168224299, "grad_norm": 1.7557967901229858, "learning_rate": 1.72264916814087e-05, "loss": 0.7985, "step": 4549 }, { "epoch": 0.2657710280373832, "grad_norm": 2.0486063957214355, "learning_rate": 1.7225183882594585e-05, "loss": 0.9264, "step": 4550 }, { "epoch": 0.26582943925233643, "grad_norm": 1.4261727333068848, "learning_rate": 1.722387582518639e-05, "loss": 0.9178, "step": 4551 }, { "epoch": 0.26588785046728974, "grad_norm": 1.8941681385040283, "learning_rate": 1.722256750923093e-05, "loss": 0.7135, "step": 4552 }, { "epoch": 0.265946261682243, "grad_norm": 2.3729350566864014, "learning_rate": 1.7221258934775026e-05, "loss": 0.7941, "step": 4553 }, { "epoch": 0.26600467289719626, "grad_norm": 1.578395962715149, "learning_rate": 1.7219950101865518e-05, "loss": 0.7587, "step": 4554 }, { "epoch": 0.2660630841121495, "grad_norm": 1.6889588832855225, "learning_rate": 1.721864101054925e-05, "loss": 1.0233, "step": 4555 }, { "epoch": 0.26612149532710283, "grad_norm": 2.039019823074341, "learning_rate": 1.7217331660873073e-05, "loss": 0.8598, "step": 4556 }, { "epoch": 0.2661799065420561, "grad_norm": 1.8029662370681763, "learning_rate": 1.721602205288385e-05, "loss": 0.9788, "step": 4557 }, { "epoch": 0.26623831775700935, "grad_norm": 1.542663812637329, "learning_rate": 1.7214712186628456e-05, "loss": 0.875, "step": 4558 }, { "epoch": 0.2662967289719626, "grad_norm": 1.4174917936325073, "learning_rate": 1.7213402062153762e-05, "loss": 0.7261, "step": 4559 }, { "epoch": 0.26635514018691586, "grad_norm": 1.4506149291992188, "learning_rate": 1.7212091679506672e-05, "loss": 0.809, "step": 4560 }, { "epoch": 0.2664135514018692, "grad_norm": 1.6808054447174072, "learning_rate": 1.7210781038734077e-05, "loss": 0.893, "step": 4561 }, { "epoch": 0.26647196261682243, "grad_norm": 1.0815333127975464, "learning_rate": 1.7209470139882887e-05, "loss": 0.6159, "step": 4562 }, { "epoch": 0.2665303738317757, "grad_norm": 2.1257426738739014, "learning_rate": 1.7208158983000022e-05, "loss": 0.9174, "step": 4563 }, { "epoch": 0.26658878504672895, "grad_norm": 1.2872148752212524, "learning_rate": 1.7206847568132406e-05, "loss": 0.8664, "step": 4564 }, { "epoch": 0.26664719626168226, "grad_norm": 2.402013063430786, "learning_rate": 1.7205535895326977e-05, "loss": 1.0118, "step": 4565 }, { "epoch": 0.2667056074766355, "grad_norm": 1.2012513875961304, "learning_rate": 1.720422396463068e-05, "loss": 0.7542, "step": 4566 }, { "epoch": 0.2667640186915888, "grad_norm": 2.8931543827056885, "learning_rate": 1.7202911776090473e-05, "loss": 0.9235, "step": 4567 }, { "epoch": 0.26682242990654204, "grad_norm": 1.7310259342193604, "learning_rate": 1.7201599329753313e-05, "loss": 0.9228, "step": 4568 }, { "epoch": 0.26688084112149535, "grad_norm": 2.380711555480957, "learning_rate": 1.7200286625666182e-05, "loss": 0.8603, "step": 4569 }, { "epoch": 0.2669392523364486, "grad_norm": 1.2236897945404053, "learning_rate": 1.7198973663876057e-05, "loss": 0.7207, "step": 4570 }, { "epoch": 0.26699766355140186, "grad_norm": 1.7741963863372803, "learning_rate": 1.7197660444429927e-05, "loss": 0.777, "step": 4571 }, { "epoch": 0.2670560747663551, "grad_norm": 1.3560428619384766, "learning_rate": 1.7196346967374803e-05, "loss": 0.8851, "step": 4572 }, { "epoch": 0.26711448598130844, "grad_norm": 1.1855672597885132, "learning_rate": 1.719503323275769e-05, "loss": 0.9461, "step": 4573 }, { "epoch": 0.2671728971962617, "grad_norm": 1.6067918539047241, "learning_rate": 1.71937192406256e-05, "loss": 0.784, "step": 4574 }, { "epoch": 0.26723130841121495, "grad_norm": 1.2664129734039307, "learning_rate": 1.7192404991025576e-05, "loss": 0.9132, "step": 4575 }, { "epoch": 0.2672897196261682, "grad_norm": 1.96442711353302, "learning_rate": 1.7191090484004646e-05, "loss": 0.9107, "step": 4576 }, { "epoch": 0.2673481308411215, "grad_norm": 2.221210479736328, "learning_rate": 1.7189775719609855e-05, "loss": 0.9184, "step": 4577 }, { "epoch": 0.2674065420560748, "grad_norm": 1.574271321296692, "learning_rate": 1.718846069788827e-05, "loss": 0.876, "step": 4578 }, { "epoch": 0.26746495327102804, "grad_norm": 1.657844066619873, "learning_rate": 1.7187145418886947e-05, "loss": 0.8651, "step": 4579 }, { "epoch": 0.2675233644859813, "grad_norm": 1.2414543628692627, "learning_rate": 1.7185829882652963e-05, "loss": 0.7372, "step": 4580 }, { "epoch": 0.26758177570093455, "grad_norm": 1.4519544839859009, "learning_rate": 1.7184514089233403e-05, "loss": 0.7313, "step": 4581 }, { "epoch": 0.26764018691588787, "grad_norm": 1.4712330102920532, "learning_rate": 1.7183198038675358e-05, "loss": 1.1185, "step": 4582 }, { "epoch": 0.2676985981308411, "grad_norm": 1.1316092014312744, "learning_rate": 1.7181881731025938e-05, "loss": 0.7906, "step": 4583 }, { "epoch": 0.2677570093457944, "grad_norm": 1.2384567260742188, "learning_rate": 1.7180565166332246e-05, "loss": 0.8362, "step": 4584 }, { "epoch": 0.26781542056074764, "grad_norm": 1.3681799173355103, "learning_rate": 1.71792483446414e-05, "loss": 0.8511, "step": 4585 }, { "epoch": 0.26787383177570095, "grad_norm": 1.647451639175415, "learning_rate": 1.717793126600054e-05, "loss": 0.7499, "step": 4586 }, { "epoch": 0.2679322429906542, "grad_norm": 0.8968048691749573, "learning_rate": 1.7176613930456802e-05, "loss": 0.7571, "step": 4587 }, { "epoch": 0.26799065420560747, "grad_norm": 1.6148693561553955, "learning_rate": 1.717529633805733e-05, "loss": 1.034, "step": 4588 }, { "epoch": 0.26804906542056073, "grad_norm": 1.20424485206604, "learning_rate": 1.717397848884929e-05, "loss": 0.7072, "step": 4589 }, { "epoch": 0.26810747663551404, "grad_norm": 1.3232016563415527, "learning_rate": 1.7172660382879834e-05, "loss": 0.9618, "step": 4590 }, { "epoch": 0.2681658878504673, "grad_norm": 1.247696042060852, "learning_rate": 1.7171342020196153e-05, "loss": 0.8111, "step": 4591 }, { "epoch": 0.26822429906542056, "grad_norm": 1.3705623149871826, "learning_rate": 1.7170023400845423e-05, "loss": 0.8515, "step": 4592 }, { "epoch": 0.2682827102803738, "grad_norm": 1.2277535200119019, "learning_rate": 1.7168704524874843e-05, "loss": 0.8428, "step": 4593 }, { "epoch": 0.26834112149532713, "grad_norm": 1.4465975761413574, "learning_rate": 1.7167385392331614e-05, "loss": 1.0261, "step": 4594 }, { "epoch": 0.2683995327102804, "grad_norm": 1.6010380983352661, "learning_rate": 1.7166066003262946e-05, "loss": 0.75, "step": 4595 }, { "epoch": 0.26845794392523364, "grad_norm": 1.3931180238723755, "learning_rate": 1.716474635771607e-05, "loss": 0.8688, "step": 4596 }, { "epoch": 0.2685163551401869, "grad_norm": 1.4240354299545288, "learning_rate": 1.7163426455738207e-05, "loss": 0.7726, "step": 4597 }, { "epoch": 0.26857476635514016, "grad_norm": 1.5183130502700806, "learning_rate": 1.71621062973766e-05, "loss": 0.6734, "step": 4598 }, { "epoch": 0.2686331775700935, "grad_norm": 1.4216063022613525, "learning_rate": 1.71607858826785e-05, "loss": 0.7762, "step": 4599 }, { "epoch": 0.26869158878504673, "grad_norm": 1.6903125047683716, "learning_rate": 1.7159465211691167e-05, "loss": 0.9442, "step": 4600 }, { "epoch": 0.26875, "grad_norm": 1.5595203638076782, "learning_rate": 1.7158144284461868e-05, "loss": 0.9477, "step": 4601 }, { "epoch": 0.26880841121495325, "grad_norm": 1.1783450841903687, "learning_rate": 1.7156823101037872e-05, "loss": 0.783, "step": 4602 }, { "epoch": 0.26886682242990656, "grad_norm": 1.0618873834609985, "learning_rate": 1.7155501661466478e-05, "loss": 0.7978, "step": 4603 }, { "epoch": 0.2689252336448598, "grad_norm": 1.164709210395813, "learning_rate": 1.715417996579497e-05, "loss": 0.9324, "step": 4604 }, { "epoch": 0.2689836448598131, "grad_norm": 1.3789209127426147, "learning_rate": 1.7152858014070662e-05, "loss": 0.9428, "step": 4605 }, { "epoch": 0.26904205607476633, "grad_norm": 1.567551612854004, "learning_rate": 1.715153580634086e-05, "loss": 0.8466, "step": 4606 }, { "epoch": 0.26910046728971965, "grad_norm": 1.5049060583114624, "learning_rate": 1.7150213342652887e-05, "loss": 0.7355, "step": 4607 }, { "epoch": 0.2691588785046729, "grad_norm": 1.6466008424758911, "learning_rate": 1.714889062305408e-05, "loss": 0.8629, "step": 4608 }, { "epoch": 0.26921728971962616, "grad_norm": 1.3155804872512817, "learning_rate": 1.7147567647591777e-05, "loss": 0.937, "step": 4609 }, { "epoch": 0.2692757009345794, "grad_norm": 1.5018084049224854, "learning_rate": 1.7146244416313328e-05, "loss": 0.8674, "step": 4610 }, { "epoch": 0.26933411214953273, "grad_norm": 2.193037509918213, "learning_rate": 1.714492092926609e-05, "loss": 0.8019, "step": 4611 }, { "epoch": 0.269392523364486, "grad_norm": 2.8942463397979736, "learning_rate": 1.714359718649744e-05, "loss": 0.9626, "step": 4612 }, { "epoch": 0.26945093457943925, "grad_norm": 1.2774180173873901, "learning_rate": 1.7142273188054744e-05, "loss": 0.8811, "step": 4613 }, { "epoch": 0.2695093457943925, "grad_norm": 2.1630947589874268, "learning_rate": 1.7140948933985397e-05, "loss": 0.9518, "step": 4614 }, { "epoch": 0.2695677570093458, "grad_norm": 1.6040288209915161, "learning_rate": 1.713962442433679e-05, "loss": 0.9279, "step": 4615 }, { "epoch": 0.2696261682242991, "grad_norm": 1.845716118812561, "learning_rate": 1.7138299659156336e-05, "loss": 0.7336, "step": 4616 }, { "epoch": 0.26968457943925234, "grad_norm": 1.8262231349945068, "learning_rate": 1.7136974638491438e-05, "loss": 0.8088, "step": 4617 }, { "epoch": 0.2697429906542056, "grad_norm": 1.1859849691390991, "learning_rate": 1.7135649362389528e-05, "loss": 0.762, "step": 4618 }, { "epoch": 0.26980140186915885, "grad_norm": 2.224240303039551, "learning_rate": 1.7134323830898036e-05, "loss": 1.0095, "step": 4619 }, { "epoch": 0.26985981308411217, "grad_norm": 1.1929243803024292, "learning_rate": 1.71329980440644e-05, "loss": 0.743, "step": 4620 }, { "epoch": 0.2699182242990654, "grad_norm": 2.4762094020843506, "learning_rate": 1.7131672001936077e-05, "loss": 0.8883, "step": 4621 }, { "epoch": 0.2699766355140187, "grad_norm": 1.0259852409362793, "learning_rate": 1.7130345704560522e-05, "loss": 0.8802, "step": 4622 }, { "epoch": 0.27003504672897194, "grad_norm": 2.3493645191192627, "learning_rate": 1.7129019151985206e-05, "loss": 0.8569, "step": 4623 }, { "epoch": 0.27009345794392525, "grad_norm": 1.6699795722961426, "learning_rate": 1.712769234425761e-05, "loss": 0.9371, "step": 4624 }, { "epoch": 0.2701518691588785, "grad_norm": 1.8776143789291382, "learning_rate": 1.7126365281425216e-05, "loss": 0.7913, "step": 4625 }, { "epoch": 0.27021028037383177, "grad_norm": 1.5310183763504028, "learning_rate": 1.7125037963535523e-05, "loss": 0.8849, "step": 4626 }, { "epoch": 0.270268691588785, "grad_norm": 1.6809214353561401, "learning_rate": 1.7123710390636038e-05, "loss": 0.8071, "step": 4627 }, { "epoch": 0.27032710280373834, "grad_norm": 2.11877179145813, "learning_rate": 1.7122382562774272e-05, "loss": 0.8663, "step": 4628 }, { "epoch": 0.2703855140186916, "grad_norm": 2.204784393310547, "learning_rate": 1.712105447999775e-05, "loss": 0.9228, "step": 4629 }, { "epoch": 0.27044392523364486, "grad_norm": 1.7639532089233398, "learning_rate": 1.7119726142354006e-05, "loss": 0.9335, "step": 4630 }, { "epoch": 0.2705023364485981, "grad_norm": 2.4653937816619873, "learning_rate": 1.7118397549890588e-05, "loss": 0.8985, "step": 4631 }, { "epoch": 0.2705607476635514, "grad_norm": 0.9717714190483093, "learning_rate": 1.7117068702655034e-05, "loss": 0.6411, "step": 4632 }, { "epoch": 0.2706191588785047, "grad_norm": 1.7267528772354126, "learning_rate": 1.7115739600694915e-05, "loss": 0.9428, "step": 4633 }, { "epoch": 0.27067757009345794, "grad_norm": 1.6054468154907227, "learning_rate": 1.7114410244057796e-05, "loss": 0.7748, "step": 4634 }, { "epoch": 0.2707359813084112, "grad_norm": 1.3112070560455322, "learning_rate": 1.711308063279126e-05, "loss": 0.798, "step": 4635 }, { "epoch": 0.2707943925233645, "grad_norm": 1.8425313234329224, "learning_rate": 1.7111750766942886e-05, "loss": 0.796, "step": 4636 }, { "epoch": 0.27085280373831777, "grad_norm": 1.1546024084091187, "learning_rate": 1.711042064656028e-05, "loss": 0.6852, "step": 4637 }, { "epoch": 0.27091121495327103, "grad_norm": 1.3334263563156128, "learning_rate": 1.7109090271691044e-05, "loss": 1.0037, "step": 4638 }, { "epoch": 0.2709696261682243, "grad_norm": 2.2919788360595703, "learning_rate": 1.710775964238279e-05, "loss": 0.9445, "step": 4639 }, { "epoch": 0.27102803738317754, "grad_norm": 1.8022491931915283, "learning_rate": 1.7106428758683145e-05, "loss": 0.8438, "step": 4640 }, { "epoch": 0.27108644859813086, "grad_norm": 3.0887184143066406, "learning_rate": 1.7105097620639745e-05, "loss": 0.9509, "step": 4641 }, { "epoch": 0.2711448598130841, "grad_norm": 1.436803936958313, "learning_rate": 1.7103766228300225e-05, "loss": 0.7308, "step": 4642 }, { "epoch": 0.2712032710280374, "grad_norm": 1.2093030214309692, "learning_rate": 1.7102434581712244e-05, "loss": 0.8249, "step": 4643 }, { "epoch": 0.27126168224299063, "grad_norm": 1.862243413925171, "learning_rate": 1.710110268092346e-05, "loss": 0.8609, "step": 4644 }, { "epoch": 0.27132009345794394, "grad_norm": 1.1923154592514038, "learning_rate": 1.709977052598154e-05, "loss": 0.8057, "step": 4645 }, { "epoch": 0.2713785046728972, "grad_norm": 1.7834564447402954, "learning_rate": 1.709843811693417e-05, "loss": 0.7357, "step": 4646 }, { "epoch": 0.27143691588785046, "grad_norm": 1.9556776285171509, "learning_rate": 1.7097105453829025e-05, "loss": 0.8051, "step": 4647 }, { "epoch": 0.2714953271028037, "grad_norm": 1.3292878866195679, "learning_rate": 1.7095772536713814e-05, "loss": 0.7614, "step": 4648 }, { "epoch": 0.27155373831775703, "grad_norm": 3.522662878036499, "learning_rate": 1.7094439365636236e-05, "loss": 0.8434, "step": 4649 }, { "epoch": 0.2716121495327103, "grad_norm": 1.9744712114334106, "learning_rate": 1.7093105940644007e-05, "loss": 1.0916, "step": 4650 }, { "epoch": 0.27167056074766355, "grad_norm": 2.5713231563568115, "learning_rate": 1.7091772261784854e-05, "loss": 0.9106, "step": 4651 }, { "epoch": 0.2717289719626168, "grad_norm": 1.4898120164871216, "learning_rate": 1.7090438329106512e-05, "loss": 0.9044, "step": 4652 }, { "epoch": 0.2717873831775701, "grad_norm": 1.6676326990127563, "learning_rate": 1.7089104142656716e-05, "loss": 0.7926, "step": 4653 }, { "epoch": 0.2718457943925234, "grad_norm": 1.4046907424926758, "learning_rate": 1.7087769702483225e-05, "loss": 0.8828, "step": 4654 }, { "epoch": 0.27190420560747663, "grad_norm": 1.3118678331375122, "learning_rate": 1.7086435008633792e-05, "loss": 0.9184, "step": 4655 }, { "epoch": 0.2719626168224299, "grad_norm": 1.2760546207427979, "learning_rate": 1.7085100061156196e-05, "loss": 0.7633, "step": 4656 }, { "epoch": 0.27202102803738315, "grad_norm": 1.8808194398880005, "learning_rate": 1.7083764860098206e-05, "loss": 0.9403, "step": 4657 }, { "epoch": 0.27207943925233646, "grad_norm": 1.352187991142273, "learning_rate": 1.708242940550762e-05, "loss": 1.0033, "step": 4658 }, { "epoch": 0.2721378504672897, "grad_norm": 2.314199209213257, "learning_rate": 1.708109369743222e-05, "loss": 0.7287, "step": 4659 }, { "epoch": 0.272196261682243, "grad_norm": 1.3430707454681396, "learning_rate": 1.7079757735919824e-05, "loss": 0.7257, "step": 4660 }, { "epoch": 0.27225467289719624, "grad_norm": 1.1589666604995728, "learning_rate": 1.7078421521018246e-05, "loss": 0.5983, "step": 4661 }, { "epoch": 0.27231308411214955, "grad_norm": 1.9392482042312622, "learning_rate": 1.7077085052775304e-05, "loss": 0.8331, "step": 4662 }, { "epoch": 0.2723714953271028, "grad_norm": 1.1590827703475952, "learning_rate": 1.707574833123884e-05, "loss": 0.8311, "step": 4663 }, { "epoch": 0.27242990654205607, "grad_norm": 1.3569345474243164, "learning_rate": 1.7074411356456683e-05, "loss": 0.8461, "step": 4664 }, { "epoch": 0.2724883177570093, "grad_norm": 1.2058247327804565, "learning_rate": 1.7073074128476697e-05, "loss": 0.8494, "step": 4665 }, { "epoch": 0.27254672897196264, "grad_norm": 1.5365403890609741, "learning_rate": 1.707173664734674e-05, "loss": 0.7545, "step": 4666 }, { "epoch": 0.2726051401869159, "grad_norm": 1.3597688674926758, "learning_rate": 1.7070398913114673e-05, "loss": 0.9043, "step": 4667 }, { "epoch": 0.27266355140186915, "grad_norm": 2.290611505508423, "learning_rate": 1.7069060925828383e-05, "loss": 0.7382, "step": 4668 }, { "epoch": 0.2727219626168224, "grad_norm": 1.172067403793335, "learning_rate": 1.7067722685535754e-05, "loss": 0.8005, "step": 4669 }, { "epoch": 0.2727803738317757, "grad_norm": 0.9544867873191833, "learning_rate": 1.7066384192284684e-05, "loss": 0.8141, "step": 4670 }, { "epoch": 0.272838785046729, "grad_norm": 1.748843789100647, "learning_rate": 1.7065045446123075e-05, "loss": 0.9548, "step": 4671 }, { "epoch": 0.27289719626168224, "grad_norm": 1.1070584058761597, "learning_rate": 1.7063706447098847e-05, "loss": 0.8075, "step": 4672 }, { "epoch": 0.2729556074766355, "grad_norm": 1.2513054609298706, "learning_rate": 1.706236719525992e-05, "loss": 0.8393, "step": 4673 }, { "epoch": 0.2730140186915888, "grad_norm": 1.3606653213500977, "learning_rate": 1.7061027690654225e-05, "loss": 0.8503, "step": 4674 }, { "epoch": 0.27307242990654207, "grad_norm": 1.6312838792800903, "learning_rate": 1.705968793332971e-05, "loss": 0.8478, "step": 4675 }, { "epoch": 0.2731308411214953, "grad_norm": 1.5177258253097534, "learning_rate": 1.7058347923334316e-05, "loss": 0.934, "step": 4676 }, { "epoch": 0.2731892523364486, "grad_norm": 1.349940299987793, "learning_rate": 1.7057007660716018e-05, "loss": 0.9346, "step": 4677 }, { "epoch": 0.27324766355140184, "grad_norm": 1.4003206491470337, "learning_rate": 1.7055667145522767e-05, "loss": 0.7833, "step": 4678 }, { "epoch": 0.27330607476635516, "grad_norm": 1.7646273374557495, "learning_rate": 1.7054326377802554e-05, "loss": 0.704, "step": 4679 }, { "epoch": 0.2733644859813084, "grad_norm": 1.8467580080032349, "learning_rate": 1.705298535760336e-05, "loss": 1.0432, "step": 4680 }, { "epoch": 0.27342289719626167, "grad_norm": 1.6964530944824219, "learning_rate": 1.7051644084973188e-05, "loss": 0.7284, "step": 4681 }, { "epoch": 0.27348130841121493, "grad_norm": 1.5565301179885864, "learning_rate": 1.705030255996003e-05, "loss": 0.7852, "step": 4682 }, { "epoch": 0.27353971962616824, "grad_norm": 1.348807454109192, "learning_rate": 1.7048960782611914e-05, "loss": 0.7993, "step": 4683 }, { "epoch": 0.2735981308411215, "grad_norm": 1.6150670051574707, "learning_rate": 1.7047618752976852e-05, "loss": 0.8291, "step": 4684 }, { "epoch": 0.27365654205607476, "grad_norm": 1.2890334129333496, "learning_rate": 1.704627647110288e-05, "loss": 1.0446, "step": 4685 }, { "epoch": 0.273714953271028, "grad_norm": 1.715275764465332, "learning_rate": 1.7044933937038045e-05, "loss": 0.7987, "step": 4686 }, { "epoch": 0.27377336448598133, "grad_norm": 1.6043305397033691, "learning_rate": 1.704359115083039e-05, "loss": 1.0886, "step": 4687 }, { "epoch": 0.2738317757009346, "grad_norm": 1.360634207725525, "learning_rate": 1.7042248112527974e-05, "loss": 0.9511, "step": 4688 }, { "epoch": 0.27389018691588785, "grad_norm": 1.2557035684585571, "learning_rate": 1.7040904822178872e-05, "loss": 0.9263, "step": 4689 }, { "epoch": 0.2739485981308411, "grad_norm": 1.781351089477539, "learning_rate": 1.7039561279831156e-05, "loss": 1.0561, "step": 4690 }, { "epoch": 0.2740070093457944, "grad_norm": 1.574337124824524, "learning_rate": 1.703821748553291e-05, "loss": 0.8949, "step": 4691 }, { "epoch": 0.2740654205607477, "grad_norm": 1.5191285610198975, "learning_rate": 1.7036873439332238e-05, "loss": 0.9831, "step": 4692 }, { "epoch": 0.27412383177570093, "grad_norm": 1.5722277164459229, "learning_rate": 1.7035529141277238e-05, "loss": 0.7492, "step": 4693 }, { "epoch": 0.2741822429906542, "grad_norm": 2.1357340812683105, "learning_rate": 1.703418459141602e-05, "loss": 0.8374, "step": 4694 }, { "epoch": 0.2742406542056075, "grad_norm": 1.3229193687438965, "learning_rate": 1.7032839789796712e-05, "loss": 0.7562, "step": 4695 }, { "epoch": 0.27429906542056076, "grad_norm": 1.6604681015014648, "learning_rate": 1.703149473646744e-05, "loss": 0.8865, "step": 4696 }, { "epoch": 0.274357476635514, "grad_norm": 1.0345704555511475, "learning_rate": 1.7030149431476353e-05, "loss": 0.7396, "step": 4697 }, { "epoch": 0.2744158878504673, "grad_norm": 1.47861909866333, "learning_rate": 1.7028803874871593e-05, "loss": 0.866, "step": 4698 }, { "epoch": 0.27447429906542054, "grad_norm": 1.2986087799072266, "learning_rate": 1.7027458066701325e-05, "loss": 0.9423, "step": 4699 }, { "epoch": 0.27453271028037385, "grad_norm": 1.3843516111373901, "learning_rate": 1.702611200701371e-05, "loss": 0.9697, "step": 4700 }, { "epoch": 0.2745911214953271, "grad_norm": 1.4039424657821655, "learning_rate": 1.7024765695856924e-05, "loss": 0.8791, "step": 4701 }, { "epoch": 0.27464953271028036, "grad_norm": 1.5249658823013306, "learning_rate": 1.7023419133279156e-05, "loss": 0.7407, "step": 4702 }, { "epoch": 0.2747079439252336, "grad_norm": 1.484573245048523, "learning_rate": 1.7022072319328603e-05, "loss": 0.8124, "step": 4703 }, { "epoch": 0.27476635514018694, "grad_norm": 1.4202134609222412, "learning_rate": 1.7020725254053458e-05, "loss": 0.8569, "step": 4704 }, { "epoch": 0.2748247663551402, "grad_norm": 1.2104542255401611, "learning_rate": 1.7019377937501943e-05, "loss": 0.7408, "step": 4705 }, { "epoch": 0.27488317757009345, "grad_norm": 1.0855047702789307, "learning_rate": 1.701803036972228e-05, "loss": 0.7197, "step": 4706 }, { "epoch": 0.2749415887850467, "grad_norm": 2.4608101844787598, "learning_rate": 1.701668255076269e-05, "loss": 0.9619, "step": 4707 }, { "epoch": 0.275, "grad_norm": 2.0935475826263428, "learning_rate": 1.701533448067142e-05, "loss": 0.6606, "step": 4708 }, { "epoch": 0.2750584112149533, "grad_norm": 1.7388947010040283, "learning_rate": 1.7013986159496716e-05, "loss": 0.8434, "step": 4709 }, { "epoch": 0.27511682242990654, "grad_norm": 1.3124871253967285, "learning_rate": 1.701263758728684e-05, "loss": 0.7808, "step": 4710 }, { "epoch": 0.2751752336448598, "grad_norm": 1.9600516557693481, "learning_rate": 1.701128876409005e-05, "loss": 0.9905, "step": 4711 }, { "epoch": 0.2752336448598131, "grad_norm": 1.2325448989868164, "learning_rate": 1.7009939689954622e-05, "loss": 0.8191, "step": 4712 }, { "epoch": 0.27529205607476637, "grad_norm": 2.751882791519165, "learning_rate": 1.700859036492885e-05, "loss": 0.9746, "step": 4713 }, { "epoch": 0.2753504672897196, "grad_norm": 1.4326086044311523, "learning_rate": 1.7007240789061014e-05, "loss": 0.7768, "step": 4714 }, { "epoch": 0.2754088785046729, "grad_norm": 1.932991862297058, "learning_rate": 1.7005890962399426e-05, "loss": 0.9637, "step": 4715 }, { "epoch": 0.27546728971962614, "grad_norm": 1.4305273294448853, "learning_rate": 1.7004540884992392e-05, "loss": 0.9307, "step": 4716 }, { "epoch": 0.27552570093457945, "grad_norm": 1.2580698728561401, "learning_rate": 1.7003190556888238e-05, "loss": 0.9168, "step": 4717 }, { "epoch": 0.2755841121495327, "grad_norm": 2.7943317890167236, "learning_rate": 1.7001839978135288e-05, "loss": 1.0661, "step": 4718 }, { "epoch": 0.27564252336448597, "grad_norm": 1.5361483097076416, "learning_rate": 1.700048914878188e-05, "loss": 0.7346, "step": 4719 }, { "epoch": 0.2757009345794392, "grad_norm": 1.474595069885254, "learning_rate": 1.6999138068876364e-05, "loss": 0.6742, "step": 4720 }, { "epoch": 0.27575934579439254, "grad_norm": 2.887228012084961, "learning_rate": 1.699778673846709e-05, "loss": 0.9349, "step": 4721 }, { "epoch": 0.2758177570093458, "grad_norm": 1.8732609748840332, "learning_rate": 1.6996435157602434e-05, "loss": 0.9424, "step": 4722 }, { "epoch": 0.27587616822429906, "grad_norm": 2.3850855827331543, "learning_rate": 1.6995083326330762e-05, "loss": 0.7501, "step": 4723 }, { "epoch": 0.2759345794392523, "grad_norm": 1.302160382270813, "learning_rate": 1.6993731244700454e-05, "loss": 0.7811, "step": 4724 }, { "epoch": 0.2759929906542056, "grad_norm": 1.7790430784225464, "learning_rate": 1.699237891275991e-05, "loss": 0.8324, "step": 4725 }, { "epoch": 0.2760514018691589, "grad_norm": 1.3004953861236572, "learning_rate": 1.6991026330557526e-05, "loss": 0.8151, "step": 4726 }, { "epoch": 0.27610981308411214, "grad_norm": 1.5302232503890991, "learning_rate": 1.6989673498141713e-05, "loss": 0.8843, "step": 4727 }, { "epoch": 0.2761682242990654, "grad_norm": 1.5626568794250488, "learning_rate": 1.6988320415560892e-05, "loss": 0.8814, "step": 4728 }, { "epoch": 0.2762266355140187, "grad_norm": 1.7444381713867188, "learning_rate": 1.6986967082863487e-05, "loss": 0.7381, "step": 4729 }, { "epoch": 0.276285046728972, "grad_norm": 1.8383204936981201, "learning_rate": 1.6985613500097936e-05, "loss": 0.8667, "step": 4730 }, { "epoch": 0.27634345794392523, "grad_norm": 1.3504409790039062, "learning_rate": 1.6984259667312685e-05, "loss": 0.9063, "step": 4731 }, { "epoch": 0.2764018691588785, "grad_norm": 1.689443588256836, "learning_rate": 1.6982905584556187e-05, "loss": 0.8545, "step": 4732 }, { "epoch": 0.2764602803738318, "grad_norm": 2.3582072257995605, "learning_rate": 1.6981551251876905e-05, "loss": 0.9316, "step": 4733 }, { "epoch": 0.27651869158878506, "grad_norm": 1.0993279218673706, "learning_rate": 1.6980196669323317e-05, "loss": 0.8385, "step": 4734 }, { "epoch": 0.2765771028037383, "grad_norm": 3.3346307277679443, "learning_rate": 1.6978841836943897e-05, "loss": 0.9925, "step": 4735 }, { "epoch": 0.2766355140186916, "grad_norm": 1.4374300241470337, "learning_rate": 1.6977486754787142e-05, "loss": 0.9227, "step": 4736 }, { "epoch": 0.27669392523364483, "grad_norm": 2.2062294483184814, "learning_rate": 1.6976131422901548e-05, "loss": 0.9429, "step": 4737 }, { "epoch": 0.27675233644859815, "grad_norm": 2.8630452156066895, "learning_rate": 1.697477584133562e-05, "loss": 0.9566, "step": 4738 }, { "epoch": 0.2768107476635514, "grad_norm": 1.4983025789260864, "learning_rate": 1.6973420010137887e-05, "loss": 0.9983, "step": 4739 }, { "epoch": 0.27686915887850466, "grad_norm": 2.5239484310150146, "learning_rate": 1.697206392935686e-05, "loss": 0.8494, "step": 4740 }, { "epoch": 0.2769275700934579, "grad_norm": 1.3600739240646362, "learning_rate": 1.697070759904108e-05, "loss": 0.9761, "step": 4741 }, { "epoch": 0.27698598130841123, "grad_norm": 1.4403311014175415, "learning_rate": 1.6969351019239093e-05, "loss": 0.8434, "step": 4742 }, { "epoch": 0.2770443925233645, "grad_norm": 1.4536515474319458, "learning_rate": 1.6967994189999452e-05, "loss": 0.7081, "step": 4743 }, { "epoch": 0.27710280373831775, "grad_norm": 1.5322610139846802, "learning_rate": 1.696663711137072e-05, "loss": 0.8544, "step": 4744 }, { "epoch": 0.277161214953271, "grad_norm": 0.9525161981582642, "learning_rate": 1.696527978340146e-05, "loss": 0.5964, "step": 4745 }, { "epoch": 0.2772196261682243, "grad_norm": 1.629380464553833, "learning_rate": 1.696392220614026e-05, "loss": 0.7032, "step": 4746 }, { "epoch": 0.2772780373831776, "grad_norm": 1.509831428527832, "learning_rate": 1.6962564379635702e-05, "loss": 0.8773, "step": 4747 }, { "epoch": 0.27733644859813084, "grad_norm": 1.6049244403839111, "learning_rate": 1.696120630393639e-05, "loss": 0.8058, "step": 4748 }, { "epoch": 0.2773948598130841, "grad_norm": 1.780192494392395, "learning_rate": 1.6959847979090925e-05, "loss": 0.86, "step": 4749 }, { "epoch": 0.2774532710280374, "grad_norm": 2.214557647705078, "learning_rate": 1.6958489405147927e-05, "loss": 0.9861, "step": 4750 }, { "epoch": 0.27751168224299066, "grad_norm": 1.6293656826019287, "learning_rate": 1.6957130582156013e-05, "loss": 0.7685, "step": 4751 }, { "epoch": 0.2775700934579439, "grad_norm": 1.6924240589141846, "learning_rate": 1.6955771510163826e-05, "loss": 0.6996, "step": 4752 }, { "epoch": 0.2776285046728972, "grad_norm": 2.1696810722351074, "learning_rate": 1.6954412189220002e-05, "loss": 0.9604, "step": 4753 }, { "epoch": 0.2776869158878505, "grad_norm": 1.8262395858764648, "learning_rate": 1.6953052619373192e-05, "loss": 0.8522, "step": 4754 }, { "epoch": 0.27774532710280375, "grad_norm": 1.3367236852645874, "learning_rate": 1.695169280067206e-05, "loss": 0.7517, "step": 4755 }, { "epoch": 0.277803738317757, "grad_norm": 1.200305461883545, "learning_rate": 1.6950332733165268e-05, "loss": 0.8354, "step": 4756 }, { "epoch": 0.27786214953271027, "grad_norm": 1.684165358543396, "learning_rate": 1.69489724169015e-05, "loss": 0.7363, "step": 4757 }, { "epoch": 0.2779205607476635, "grad_norm": 1.6568660736083984, "learning_rate": 1.6947611851929438e-05, "loss": 0.8792, "step": 4758 }, { "epoch": 0.27797897196261684, "grad_norm": 1.331797480583191, "learning_rate": 1.6946251038297785e-05, "loss": 0.846, "step": 4759 }, { "epoch": 0.2780373831775701, "grad_norm": 1.4468737840652466, "learning_rate": 1.6944889976055233e-05, "loss": 0.7772, "step": 4760 }, { "epoch": 0.27809579439252335, "grad_norm": 1.1394944190979004, "learning_rate": 1.694352866525051e-05, "loss": 0.847, "step": 4761 }, { "epoch": 0.2781542056074766, "grad_norm": 1.0342782735824585, "learning_rate": 1.6942167105932324e-05, "loss": 0.8164, "step": 4762 }, { "epoch": 0.2782126168224299, "grad_norm": 2.6090376377105713, "learning_rate": 1.6940805298149413e-05, "loss": 0.9341, "step": 4763 }, { "epoch": 0.2782710280373832, "grad_norm": 1.4086849689483643, "learning_rate": 1.6939443241950523e-05, "loss": 0.9544, "step": 4764 }, { "epoch": 0.27832943925233644, "grad_norm": 1.1797068119049072, "learning_rate": 1.693808093738439e-05, "loss": 0.6973, "step": 4765 }, { "epoch": 0.2783878504672897, "grad_norm": 1.1848217248916626, "learning_rate": 1.693671838449978e-05, "loss": 0.7096, "step": 4766 }, { "epoch": 0.278446261682243, "grad_norm": 1.6000982522964478, "learning_rate": 1.6935355583345462e-05, "loss": 0.6838, "step": 4767 }, { "epoch": 0.27850467289719627, "grad_norm": 1.4642739295959473, "learning_rate": 1.6933992533970202e-05, "loss": 1.0882, "step": 4768 }, { "epoch": 0.27856308411214953, "grad_norm": 1.2311851978302002, "learning_rate": 1.6932629236422797e-05, "loss": 0.8222, "step": 4769 }, { "epoch": 0.2786214953271028, "grad_norm": 1.634713888168335, "learning_rate": 1.6931265690752027e-05, "loss": 0.7747, "step": 4770 }, { "epoch": 0.2786799065420561, "grad_norm": 0.977988600730896, "learning_rate": 1.69299018970067e-05, "loss": 0.7841, "step": 4771 }, { "epoch": 0.27873831775700936, "grad_norm": 1.3569848537445068, "learning_rate": 1.692853785523563e-05, "loss": 0.8659, "step": 4772 }, { "epoch": 0.2787967289719626, "grad_norm": 1.5676668882369995, "learning_rate": 1.6927173565487634e-05, "loss": 0.9167, "step": 4773 }, { "epoch": 0.2788551401869159, "grad_norm": 1.3127093315124512, "learning_rate": 1.6925809027811545e-05, "loss": 0.9095, "step": 4774 }, { "epoch": 0.2789135514018692, "grad_norm": 1.2263092994689941, "learning_rate": 1.6924444242256194e-05, "loss": 0.5855, "step": 4775 }, { "epoch": 0.27897196261682244, "grad_norm": 1.5410298109054565, "learning_rate": 1.6923079208870427e-05, "loss": 0.9799, "step": 4776 }, { "epoch": 0.2790303738317757, "grad_norm": 1.3348891735076904, "learning_rate": 1.6921713927703108e-05, "loss": 0.7683, "step": 4777 }, { "epoch": 0.27908878504672896, "grad_norm": 1.27681565284729, "learning_rate": 1.6920348398803094e-05, "loss": 0.7956, "step": 4778 }, { "epoch": 0.2791471962616822, "grad_norm": 1.7851738929748535, "learning_rate": 1.6918982622219262e-05, "loss": 0.903, "step": 4779 }, { "epoch": 0.27920560747663553, "grad_norm": 1.559754490852356, "learning_rate": 1.6917616598000496e-05, "loss": 0.8311, "step": 4780 }, { "epoch": 0.2792640186915888, "grad_norm": 1.0243980884552002, "learning_rate": 1.6916250326195677e-05, "loss": 0.6301, "step": 4781 }, { "epoch": 0.27932242990654205, "grad_norm": 1.184282660484314, "learning_rate": 1.6914883806853716e-05, "loss": 0.746, "step": 4782 }, { "epoch": 0.2793808411214953, "grad_norm": 1.3683491945266724, "learning_rate": 1.6913517040023513e-05, "loss": 0.9705, "step": 4783 }, { "epoch": 0.2794392523364486, "grad_norm": 1.5876538753509521, "learning_rate": 1.6912150025753993e-05, "loss": 0.9089, "step": 4784 }, { "epoch": 0.2794976635514019, "grad_norm": 1.4129283428192139, "learning_rate": 1.6910782764094075e-05, "loss": 0.8544, "step": 4785 }, { "epoch": 0.27955607476635513, "grad_norm": 1.7962994575500488, "learning_rate": 1.6909415255092702e-05, "loss": 0.7693, "step": 4786 }, { "epoch": 0.2796144859813084, "grad_norm": 1.0920130014419556, "learning_rate": 1.690804749879881e-05, "loss": 0.6714, "step": 4787 }, { "epoch": 0.2796728971962617, "grad_norm": 2.097776174545288, "learning_rate": 1.690667949526136e-05, "loss": 1.0176, "step": 4788 }, { "epoch": 0.27973130841121496, "grad_norm": 1.245025873184204, "learning_rate": 1.6905311244529307e-05, "loss": 0.8144, "step": 4789 }, { "epoch": 0.2797897196261682, "grad_norm": 2.311117649078369, "learning_rate": 1.6903942746651626e-05, "loss": 0.9617, "step": 4790 }, { "epoch": 0.2798481308411215, "grad_norm": 0.9907870888710022, "learning_rate": 1.6902574001677293e-05, "loss": 0.7506, "step": 4791 }, { "epoch": 0.2799065420560748, "grad_norm": 1.7198354005813599, "learning_rate": 1.69012050096553e-05, "loss": 0.8579, "step": 4792 }, { "epoch": 0.27996495327102805, "grad_norm": 1.3057230710983276, "learning_rate": 1.689983577063464e-05, "loss": 0.8436, "step": 4793 }, { "epoch": 0.2800233644859813, "grad_norm": 1.3376539945602417, "learning_rate": 1.6898466284664322e-05, "loss": 0.8384, "step": 4794 }, { "epoch": 0.28008177570093457, "grad_norm": 1.152620553970337, "learning_rate": 1.689709655179336e-05, "loss": 0.8288, "step": 4795 }, { "epoch": 0.2801401869158878, "grad_norm": 1.4430360794067383, "learning_rate": 1.6895726572070775e-05, "loss": 0.9146, "step": 4796 }, { "epoch": 0.28019859813084114, "grad_norm": 1.7281312942504883, "learning_rate": 1.6894356345545605e-05, "loss": 0.9384, "step": 4797 }, { "epoch": 0.2802570093457944, "grad_norm": 0.9793370962142944, "learning_rate": 1.6892985872266887e-05, "loss": 0.743, "step": 4798 }, { "epoch": 0.28031542056074765, "grad_norm": 1.7135076522827148, "learning_rate": 1.689161515228367e-05, "loss": 0.9033, "step": 4799 }, { "epoch": 0.2803738317757009, "grad_norm": 1.2356537580490112, "learning_rate": 1.689024418564502e-05, "loss": 0.8783, "step": 4800 }, { "epoch": 0.2804322429906542, "grad_norm": 1.4815969467163086, "learning_rate": 1.6888872972399997e-05, "loss": 0.8006, "step": 4801 }, { "epoch": 0.2804906542056075, "grad_norm": 1.4433549642562866, "learning_rate": 1.6887501512597685e-05, "loss": 0.7512, "step": 4802 }, { "epoch": 0.28054906542056074, "grad_norm": 1.175824761390686, "learning_rate": 1.6886129806287163e-05, "loss": 0.8612, "step": 4803 }, { "epoch": 0.280607476635514, "grad_norm": 1.4325519800186157, "learning_rate": 1.6884757853517524e-05, "loss": 0.8378, "step": 4804 }, { "epoch": 0.2806658878504673, "grad_norm": 1.638449788093567, "learning_rate": 1.688338565433788e-05, "loss": 0.9738, "step": 4805 }, { "epoch": 0.28072429906542057, "grad_norm": 1.3254667520523071, "learning_rate": 1.6882013208797332e-05, "loss": 0.8413, "step": 4806 }, { "epoch": 0.2807827102803738, "grad_norm": 1.6666052341461182, "learning_rate": 1.688064051694501e-05, "loss": 0.8651, "step": 4807 }, { "epoch": 0.2808411214953271, "grad_norm": 1.6442034244537354, "learning_rate": 1.687926757883004e-05, "loss": 0.8403, "step": 4808 }, { "epoch": 0.2808995327102804, "grad_norm": 2.483811616897583, "learning_rate": 1.687789439450156e-05, "loss": 1.0675, "step": 4809 }, { "epoch": 0.28095794392523366, "grad_norm": 1.0845463275909424, "learning_rate": 1.6876520964008714e-05, "loss": 0.8663, "step": 4810 }, { "epoch": 0.2810163551401869, "grad_norm": 2.208681106567383, "learning_rate": 1.6875147287400663e-05, "loss": 0.8708, "step": 4811 }, { "epoch": 0.28107476635514017, "grad_norm": 1.2653374671936035, "learning_rate": 1.687377336472657e-05, "loss": 0.7408, "step": 4812 }, { "epoch": 0.2811331775700935, "grad_norm": 1.3249655961990356, "learning_rate": 1.6872399196035613e-05, "loss": 0.7093, "step": 4813 }, { "epoch": 0.28119158878504674, "grad_norm": 1.180401086807251, "learning_rate": 1.6871024781376964e-05, "loss": 0.7166, "step": 4814 }, { "epoch": 0.28125, "grad_norm": 1.0957354307174683, "learning_rate": 1.6869650120799823e-05, "loss": 0.8048, "step": 4815 }, { "epoch": 0.28130841121495326, "grad_norm": 1.7001584768295288, "learning_rate": 1.6868275214353387e-05, "loss": 0.7883, "step": 4816 }, { "epoch": 0.2813668224299065, "grad_norm": 1.7474350929260254, "learning_rate": 1.6866900062086867e-05, "loss": 0.963, "step": 4817 }, { "epoch": 0.28142523364485983, "grad_norm": 1.5486421585083008, "learning_rate": 1.6865524664049475e-05, "loss": 0.833, "step": 4818 }, { "epoch": 0.2814836448598131, "grad_norm": 1.849302053451538, "learning_rate": 1.686414902029044e-05, "loss": 0.8161, "step": 4819 }, { "epoch": 0.28154205607476634, "grad_norm": 1.8247028589248657, "learning_rate": 1.6862773130859004e-05, "loss": 0.9776, "step": 4820 }, { "epoch": 0.2816004672897196, "grad_norm": 1.6440463066101074, "learning_rate": 1.68613969958044e-05, "loss": 0.9057, "step": 4821 }, { "epoch": 0.2816588785046729, "grad_norm": 1.4015834331512451, "learning_rate": 1.6860020615175892e-05, "loss": 0.8447, "step": 4822 }, { "epoch": 0.2817172897196262, "grad_norm": 1.452325463294983, "learning_rate": 1.6858643989022733e-05, "loss": 0.854, "step": 4823 }, { "epoch": 0.28177570093457943, "grad_norm": 1.8389348983764648, "learning_rate": 1.6857267117394194e-05, "loss": 1.0107, "step": 4824 }, { "epoch": 0.2818341121495327, "grad_norm": 1.190222144126892, "learning_rate": 1.685589000033956e-05, "loss": 0.9349, "step": 4825 }, { "epoch": 0.281892523364486, "grad_norm": 1.538338303565979, "learning_rate": 1.685451263790811e-05, "loss": 0.9686, "step": 4826 }, { "epoch": 0.28195093457943926, "grad_norm": 1.7307047843933105, "learning_rate": 1.685313503014915e-05, "loss": 0.9193, "step": 4827 }, { "epoch": 0.2820093457943925, "grad_norm": 1.5785056352615356, "learning_rate": 1.685175717711198e-05, "loss": 0.8318, "step": 4828 }, { "epoch": 0.2820677570093458, "grad_norm": 1.8002227544784546, "learning_rate": 1.6850379078845913e-05, "loss": 0.7205, "step": 4829 }, { "epoch": 0.2821261682242991, "grad_norm": 1.317025065422058, "learning_rate": 1.6849000735400277e-05, "loss": 0.7903, "step": 4830 }, { "epoch": 0.28218457943925235, "grad_norm": 1.888529896736145, "learning_rate": 1.68476221468244e-05, "loss": 0.8796, "step": 4831 }, { "epoch": 0.2822429906542056, "grad_norm": 1.2540720701217651, "learning_rate": 1.6846243313167626e-05, "loss": 0.8904, "step": 4832 }, { "epoch": 0.28230140186915886, "grad_norm": 1.232817530632019, "learning_rate": 1.68448642344793e-05, "loss": 0.7063, "step": 4833 }, { "epoch": 0.2823598130841122, "grad_norm": 1.8974792957305908, "learning_rate": 1.6843484910808784e-05, "loss": 0.9066, "step": 4834 }, { "epoch": 0.28241822429906543, "grad_norm": 1.3292561769485474, "learning_rate": 1.684210534220544e-05, "loss": 0.8235, "step": 4835 }, { "epoch": 0.2824766355140187, "grad_norm": 1.2617899179458618, "learning_rate": 1.6840725528718655e-05, "loss": 0.7429, "step": 4836 }, { "epoch": 0.28253504672897195, "grad_norm": 2.051201105117798, "learning_rate": 1.68393454703978e-05, "loss": 0.947, "step": 4837 }, { "epoch": 0.2825934579439252, "grad_norm": 0.9700924158096313, "learning_rate": 1.683796516729227e-05, "loss": 0.8033, "step": 4838 }, { "epoch": 0.2826518691588785, "grad_norm": 2.543386697769165, "learning_rate": 1.6836584619451478e-05, "loss": 0.7465, "step": 4839 }, { "epoch": 0.2827102803738318, "grad_norm": 1.6766949892044067, "learning_rate": 1.6835203826924825e-05, "loss": 0.8822, "step": 4840 }, { "epoch": 0.28276869158878504, "grad_norm": 1.2543365955352783, "learning_rate": 1.683382278976173e-05, "loss": 0.829, "step": 4841 }, { "epoch": 0.2828271028037383, "grad_norm": 2.242811918258667, "learning_rate": 1.6832441508011626e-05, "loss": 0.7736, "step": 4842 }, { "epoch": 0.2828855140186916, "grad_norm": 1.568315029144287, "learning_rate": 1.683105998172395e-05, "loss": 0.8974, "step": 4843 }, { "epoch": 0.28294392523364487, "grad_norm": 1.2590223550796509, "learning_rate": 1.682967821094814e-05, "loss": 0.6443, "step": 4844 }, { "epoch": 0.2830023364485981, "grad_norm": 2.096317768096924, "learning_rate": 1.6828296195733663e-05, "loss": 0.9593, "step": 4845 }, { "epoch": 0.2830607476635514, "grad_norm": 1.7264773845672607, "learning_rate": 1.682691393612997e-05, "loss": 0.8572, "step": 4846 }, { "epoch": 0.2831191588785047, "grad_norm": 1.42117178440094, "learning_rate": 1.6825531432186545e-05, "loss": 0.8215, "step": 4847 }, { "epoch": 0.28317757009345795, "grad_norm": 1.7401962280273438, "learning_rate": 1.6824148683952855e-05, "loss": 0.8796, "step": 4848 }, { "epoch": 0.2832359813084112, "grad_norm": 1.229693055152893, "learning_rate": 1.68227656914784e-05, "loss": 0.8907, "step": 4849 }, { "epoch": 0.28329439252336447, "grad_norm": 2.80942964553833, "learning_rate": 1.6821382454812673e-05, "loss": 0.9011, "step": 4850 }, { "epoch": 0.2833528037383178, "grad_norm": 1.4611284732818604, "learning_rate": 1.6819998974005188e-05, "loss": 0.8515, "step": 4851 }, { "epoch": 0.28341121495327104, "grad_norm": 2.823106050491333, "learning_rate": 1.681861524910545e-05, "loss": 0.8364, "step": 4852 }, { "epoch": 0.2834696261682243, "grad_norm": 1.4234743118286133, "learning_rate": 1.6817231280162988e-05, "loss": 0.8067, "step": 4853 }, { "epoch": 0.28352803738317756, "grad_norm": 1.290510892868042, "learning_rate": 1.681584706722734e-05, "loss": 0.7067, "step": 4854 }, { "epoch": 0.2835864485981308, "grad_norm": 2.9115750789642334, "learning_rate": 1.6814462610348044e-05, "loss": 0.9614, "step": 4855 }, { "epoch": 0.2836448598130841, "grad_norm": 1.2964344024658203, "learning_rate": 1.681307790957465e-05, "loss": 0.8758, "step": 4856 }, { "epoch": 0.2837032710280374, "grad_norm": 1.7560064792633057, "learning_rate": 1.6811692964956717e-05, "loss": 0.9575, "step": 4857 }, { "epoch": 0.28376168224299064, "grad_norm": 2.3891100883483887, "learning_rate": 1.6810307776543814e-05, "loss": 0.7665, "step": 4858 }, { "epoch": 0.2838200934579439, "grad_norm": 1.720684289932251, "learning_rate": 1.680892234438552e-05, "loss": 0.9215, "step": 4859 }, { "epoch": 0.2838785046728972, "grad_norm": 2.2813050746917725, "learning_rate": 1.6807536668531416e-05, "loss": 0.8608, "step": 4860 }, { "epoch": 0.28393691588785047, "grad_norm": 1.1676560640335083, "learning_rate": 1.6806150749031095e-05, "loss": 0.8163, "step": 4861 }, { "epoch": 0.28399532710280373, "grad_norm": 2.0792088508605957, "learning_rate": 1.6804764585934167e-05, "loss": 0.9707, "step": 4862 }, { "epoch": 0.284053738317757, "grad_norm": 1.4730713367462158, "learning_rate": 1.6803378179290243e-05, "loss": 0.7616, "step": 4863 }, { "epoch": 0.2841121495327103, "grad_norm": 1.071399450302124, "learning_rate": 1.6801991529148938e-05, "loss": 0.7405, "step": 4864 }, { "epoch": 0.28417056074766356, "grad_norm": 2.036585807800293, "learning_rate": 1.6800604635559887e-05, "loss": 0.9871, "step": 4865 }, { "epoch": 0.2842289719626168, "grad_norm": 0.9429989457130432, "learning_rate": 1.679921749857272e-05, "loss": 0.7088, "step": 4866 }, { "epoch": 0.2842873831775701, "grad_norm": 1.3263874053955078, "learning_rate": 1.6797830118237088e-05, "loss": 0.8674, "step": 4867 }, { "epoch": 0.2843457943925234, "grad_norm": 1.7523317337036133, "learning_rate": 1.679644249460265e-05, "loss": 0.8488, "step": 4868 }, { "epoch": 0.28440420560747665, "grad_norm": 1.3575972318649292, "learning_rate": 1.6795054627719067e-05, "loss": 0.7485, "step": 4869 }, { "epoch": 0.2844626168224299, "grad_norm": 1.7231743335723877, "learning_rate": 1.679366651763601e-05, "loss": 0.821, "step": 4870 }, { "epoch": 0.28452102803738316, "grad_norm": 1.1147888898849487, "learning_rate": 1.6792278164403157e-05, "loss": 0.9356, "step": 4871 }, { "epoch": 0.2845794392523365, "grad_norm": 2.1197049617767334, "learning_rate": 1.6790889568070207e-05, "loss": 0.8957, "step": 4872 }, { "epoch": 0.28463785046728973, "grad_norm": 1.2306716442108154, "learning_rate": 1.6789500728686848e-05, "loss": 0.7839, "step": 4873 }, { "epoch": 0.284696261682243, "grad_norm": 1.4657032489776611, "learning_rate": 1.67881116463028e-05, "loss": 0.8499, "step": 4874 }, { "epoch": 0.28475467289719625, "grad_norm": 1.4194231033325195, "learning_rate": 1.6786722320967773e-05, "loss": 0.7895, "step": 4875 }, { "epoch": 0.2848130841121495, "grad_norm": 1.4157649278640747, "learning_rate": 1.6785332752731493e-05, "loss": 0.9342, "step": 4876 }, { "epoch": 0.2848714953271028, "grad_norm": 1.3179564476013184, "learning_rate": 1.6783942941643687e-05, "loss": 0.8848, "step": 4877 }, { "epoch": 0.2849299065420561, "grad_norm": 1.7154346704483032, "learning_rate": 1.6782552887754103e-05, "loss": 0.8428, "step": 4878 }, { "epoch": 0.28498831775700934, "grad_norm": 1.3896985054016113, "learning_rate": 1.6781162591112497e-05, "loss": 1.1407, "step": 4879 }, { "epoch": 0.2850467289719626, "grad_norm": 1.3329499959945679, "learning_rate": 1.6779772051768622e-05, "loss": 0.9171, "step": 4880 }, { "epoch": 0.2851051401869159, "grad_norm": 1.3443609476089478, "learning_rate": 1.6778381269772245e-05, "loss": 0.896, "step": 4881 }, { "epoch": 0.28516355140186916, "grad_norm": 1.9389383792877197, "learning_rate": 1.6776990245173146e-05, "loss": 0.8541, "step": 4882 }, { "epoch": 0.2852219626168224, "grad_norm": 1.9633715152740479, "learning_rate": 1.6775598978021107e-05, "loss": 0.9099, "step": 4883 }, { "epoch": 0.2852803738317757, "grad_norm": 1.618727207183838, "learning_rate": 1.677420746836593e-05, "loss": 0.9112, "step": 4884 }, { "epoch": 0.285338785046729, "grad_norm": 1.6149592399597168, "learning_rate": 1.6772815716257414e-05, "loss": 0.8704, "step": 4885 }, { "epoch": 0.28539719626168225, "grad_norm": 1.4247691631317139, "learning_rate": 1.6771423721745366e-05, "loss": 0.7404, "step": 4886 }, { "epoch": 0.2854556074766355, "grad_norm": 1.2913271188735962, "learning_rate": 1.6770031484879615e-05, "loss": 0.9265, "step": 4887 }, { "epoch": 0.28551401869158877, "grad_norm": 1.4860981702804565, "learning_rate": 1.6768639005709982e-05, "loss": 0.8219, "step": 4888 }, { "epoch": 0.2855724299065421, "grad_norm": 1.5258969068527222, "learning_rate": 1.676724628428631e-05, "loss": 0.6913, "step": 4889 }, { "epoch": 0.28563084112149534, "grad_norm": 1.1804065704345703, "learning_rate": 1.6765853320658444e-05, "loss": 0.6954, "step": 4890 }, { "epoch": 0.2856892523364486, "grad_norm": 1.0645514726638794, "learning_rate": 1.676446011487624e-05, "loss": 0.7523, "step": 4891 }, { "epoch": 0.28574766355140185, "grad_norm": 1.6018027067184448, "learning_rate": 1.676306666698956e-05, "loss": 0.8866, "step": 4892 }, { "epoch": 0.28580607476635517, "grad_norm": 1.4111131429672241, "learning_rate": 1.676167297704828e-05, "loss": 0.836, "step": 4893 }, { "epoch": 0.2858644859813084, "grad_norm": 1.3367565870285034, "learning_rate": 1.6760279045102277e-05, "loss": 0.9625, "step": 4894 }, { "epoch": 0.2859228971962617, "grad_norm": 1.0047175884246826, "learning_rate": 1.675888487120144e-05, "loss": 0.792, "step": 4895 }, { "epoch": 0.28598130841121494, "grad_norm": 1.7774758338928223, "learning_rate": 1.675749045539567e-05, "loss": 0.9446, "step": 4896 }, { "epoch": 0.2860397196261682, "grad_norm": 1.5941253900527954, "learning_rate": 1.6756095797734874e-05, "loss": 0.7816, "step": 4897 }, { "epoch": 0.2860981308411215, "grad_norm": 1.9725764989852905, "learning_rate": 1.6754700898268965e-05, "loss": 0.8823, "step": 4898 }, { "epoch": 0.28615654205607477, "grad_norm": 1.5456503629684448, "learning_rate": 1.675330575704787e-05, "loss": 0.7888, "step": 4899 }, { "epoch": 0.286214953271028, "grad_norm": 1.427470088005066, "learning_rate": 1.6751910374121526e-05, "loss": 0.7532, "step": 4900 }, { "epoch": 0.2862733644859813, "grad_norm": 1.593376874923706, "learning_rate": 1.6750514749539865e-05, "loss": 0.8122, "step": 4901 }, { "epoch": 0.2863317757009346, "grad_norm": 1.242783546447754, "learning_rate": 1.6749118883352844e-05, "loss": 0.8306, "step": 4902 }, { "epoch": 0.28639018691588786, "grad_norm": 1.2668941020965576, "learning_rate": 1.6747722775610424e-05, "loss": 0.6787, "step": 4903 }, { "epoch": 0.2864485981308411, "grad_norm": 2.1129395961761475, "learning_rate": 1.6746326426362566e-05, "loss": 0.8558, "step": 4904 }, { "epoch": 0.2865070093457944, "grad_norm": 1.6923022270202637, "learning_rate": 1.674492983565925e-05, "loss": 0.7239, "step": 4905 }, { "epoch": 0.2865654205607477, "grad_norm": 2.03912353515625, "learning_rate": 1.6743533003550457e-05, "loss": 0.8457, "step": 4906 }, { "epoch": 0.28662383177570094, "grad_norm": 1.558739185333252, "learning_rate": 1.6742135930086187e-05, "loss": 0.7484, "step": 4907 }, { "epoch": 0.2866822429906542, "grad_norm": 2.041468858718872, "learning_rate": 1.674073861531644e-05, "loss": 0.9581, "step": 4908 }, { "epoch": 0.28674065420560746, "grad_norm": 1.4724807739257812, "learning_rate": 1.6739341059291225e-05, "loss": 0.8089, "step": 4909 }, { "epoch": 0.2867990654205608, "grad_norm": 1.3511631488800049, "learning_rate": 1.673794326206056e-05, "loss": 0.8935, "step": 4910 }, { "epoch": 0.28685747663551403, "grad_norm": 2.4614291191101074, "learning_rate": 1.673654522367448e-05, "loss": 0.9456, "step": 4911 }, { "epoch": 0.2869158878504673, "grad_norm": 1.3440436124801636, "learning_rate": 1.6735146944183013e-05, "loss": 0.6862, "step": 4912 }, { "epoch": 0.28697429906542055, "grad_norm": 2.5852162837982178, "learning_rate": 1.673374842363621e-05, "loss": 0.9778, "step": 4913 }, { "epoch": 0.28703271028037386, "grad_norm": 1.1830766201019287, "learning_rate": 1.6732349662084123e-05, "loss": 0.6743, "step": 4914 }, { "epoch": 0.2870911214953271, "grad_norm": 2.466679573059082, "learning_rate": 1.6730950659576817e-05, "loss": 0.8774, "step": 4915 }, { "epoch": 0.2871495327102804, "grad_norm": 1.6961506605148315, "learning_rate": 1.672955141616436e-05, "loss": 0.8757, "step": 4916 }, { "epoch": 0.28720794392523363, "grad_norm": 1.437044620513916, "learning_rate": 1.6728151931896832e-05, "loss": 0.6846, "step": 4917 }, { "epoch": 0.2872663551401869, "grad_norm": 2.5033040046691895, "learning_rate": 1.6726752206824323e-05, "loss": 0.8337, "step": 4918 }, { "epoch": 0.2873247663551402, "grad_norm": 1.4016746282577515, "learning_rate": 1.672535224099693e-05, "loss": 0.8742, "step": 4919 }, { "epoch": 0.28738317757009346, "grad_norm": 1.6393777132034302, "learning_rate": 1.6723952034464757e-05, "loss": 0.757, "step": 4920 }, { "epoch": 0.2874415887850467, "grad_norm": 1.770155906677246, "learning_rate": 1.672255158727792e-05, "loss": 0.8765, "step": 4921 }, { "epoch": 0.2875, "grad_norm": 1.5078036785125732, "learning_rate": 1.672115089948654e-05, "loss": 0.9128, "step": 4922 }, { "epoch": 0.2875584112149533, "grad_norm": 2.7220096588134766, "learning_rate": 1.6719749971140756e-05, "loss": 0.9439, "step": 4923 }, { "epoch": 0.28761682242990655, "grad_norm": 1.3372167348861694, "learning_rate": 1.67183488022907e-05, "loss": 1.0356, "step": 4924 }, { "epoch": 0.2876752336448598, "grad_norm": 2.4480183124542236, "learning_rate": 1.671694739298652e-05, "loss": 0.7639, "step": 4925 }, { "epoch": 0.28773364485981306, "grad_norm": 2.132948160171509, "learning_rate": 1.671554574327838e-05, "loss": 1.0359, "step": 4926 }, { "epoch": 0.2877920560747664, "grad_norm": 1.804886817932129, "learning_rate": 1.6714143853216434e-05, "loss": 0.6898, "step": 4927 }, { "epoch": 0.28785046728971964, "grad_norm": 3.131714105606079, "learning_rate": 1.6712741722850876e-05, "loss": 0.8373, "step": 4928 }, { "epoch": 0.2879088785046729, "grad_norm": 1.346427321434021, "learning_rate": 1.6711339352231872e-05, "loss": 0.7181, "step": 4929 }, { "epoch": 0.28796728971962615, "grad_norm": 2.7156004905700684, "learning_rate": 1.6709936741409622e-05, "loss": 0.9119, "step": 4930 }, { "epoch": 0.28802570093457946, "grad_norm": 1.9801948070526123, "learning_rate": 1.670853389043432e-05, "loss": 0.7863, "step": 4931 }, { "epoch": 0.2880841121495327, "grad_norm": 1.9488776922225952, "learning_rate": 1.670713079935618e-05, "loss": 0.872, "step": 4932 }, { "epoch": 0.288142523364486, "grad_norm": 1.6858564615249634, "learning_rate": 1.6705727468225423e-05, "loss": 0.7209, "step": 4933 }, { "epoch": 0.28820093457943924, "grad_norm": 1.664269208908081, "learning_rate": 1.6704323897092267e-05, "loss": 1.0063, "step": 4934 }, { "epoch": 0.2882593457943925, "grad_norm": 1.1338019371032715, "learning_rate": 1.6702920086006953e-05, "loss": 0.7654, "step": 4935 }, { "epoch": 0.2883177570093458, "grad_norm": 1.9954144954681396, "learning_rate": 1.670151603501972e-05, "loss": 0.7911, "step": 4936 }, { "epoch": 0.28837616822429907, "grad_norm": 1.1853606700897217, "learning_rate": 1.6700111744180826e-05, "loss": 0.8109, "step": 4937 }, { "epoch": 0.2884345794392523, "grad_norm": 1.5405272245407104, "learning_rate": 1.6698707213540522e-05, "loss": 0.8758, "step": 4938 }, { "epoch": 0.2884929906542056, "grad_norm": 1.5102193355560303, "learning_rate": 1.6697302443149084e-05, "loss": 0.8818, "step": 4939 }, { "epoch": 0.2885514018691589, "grad_norm": 1.7702213525772095, "learning_rate": 1.6695897433056788e-05, "loss": 0.868, "step": 4940 }, { "epoch": 0.28860981308411215, "grad_norm": 1.3283040523529053, "learning_rate": 1.669449218331392e-05, "loss": 0.9223, "step": 4941 }, { "epoch": 0.2886682242990654, "grad_norm": 1.0745738744735718, "learning_rate": 1.6693086693970776e-05, "loss": 0.6908, "step": 4942 }, { "epoch": 0.28872663551401867, "grad_norm": 1.6995042562484741, "learning_rate": 1.6691680965077658e-05, "loss": 0.8425, "step": 4943 }, { "epoch": 0.288785046728972, "grad_norm": 1.0126961469650269, "learning_rate": 1.669027499668488e-05, "loss": 0.6215, "step": 4944 }, { "epoch": 0.28884345794392524, "grad_norm": 1.2199674844741821, "learning_rate": 1.6688868788842757e-05, "loss": 0.7522, "step": 4945 }, { "epoch": 0.2889018691588785, "grad_norm": 1.8967511653900146, "learning_rate": 1.6687462341601627e-05, "loss": 0.8447, "step": 4946 }, { "epoch": 0.28896028037383176, "grad_norm": 1.3762630224227905, "learning_rate": 1.6686055655011818e-05, "loss": 0.9699, "step": 4947 }, { "epoch": 0.28901869158878507, "grad_norm": 2.0449225902557373, "learning_rate": 1.668464872912368e-05, "loss": 1.0161, "step": 4948 }, { "epoch": 0.28907710280373833, "grad_norm": 1.6842856407165527, "learning_rate": 1.6683241563987573e-05, "loss": 0.9047, "step": 4949 }, { "epoch": 0.2891355140186916, "grad_norm": 1.3210985660552979, "learning_rate": 1.6681834159653855e-05, "loss": 0.8759, "step": 4950 }, { "epoch": 0.28919392523364484, "grad_norm": 1.9898709058761597, "learning_rate": 1.6680426516172898e-05, "loss": 0.8026, "step": 4951 }, { "epoch": 0.28925233644859816, "grad_norm": 1.6023284196853638, "learning_rate": 1.6679018633595085e-05, "loss": 0.7233, "step": 4952 }, { "epoch": 0.2893107476635514, "grad_norm": 4.271425724029541, "learning_rate": 1.6677610511970805e-05, "loss": 0.9662, "step": 4953 }, { "epoch": 0.2893691588785047, "grad_norm": 2.0823707580566406, "learning_rate": 1.6676202151350453e-05, "loss": 0.696, "step": 4954 }, { "epoch": 0.28942757009345793, "grad_norm": 4.1301398277282715, "learning_rate": 1.6674793551784434e-05, "loss": 0.892, "step": 4955 }, { "epoch": 0.2894859813084112, "grad_norm": 1.2761691808700562, "learning_rate": 1.6673384713323164e-05, "loss": 0.8141, "step": 4956 }, { "epoch": 0.2895443925233645, "grad_norm": 1.9498858451843262, "learning_rate": 1.667197563601707e-05, "loss": 0.8183, "step": 4957 }, { "epoch": 0.28960280373831776, "grad_norm": 2.308016777038574, "learning_rate": 1.6670566319916585e-05, "loss": 0.8985, "step": 4958 }, { "epoch": 0.289661214953271, "grad_norm": 1.436853051185608, "learning_rate": 1.6669156765072138e-05, "loss": 0.837, "step": 4959 }, { "epoch": 0.2897196261682243, "grad_norm": 1.4825254678726196, "learning_rate": 1.666774697153419e-05, "loss": 0.8443, "step": 4960 }, { "epoch": 0.2897780373831776, "grad_norm": 2.860792398452759, "learning_rate": 1.666633693935319e-05, "loss": 0.9052, "step": 4961 }, { "epoch": 0.28983644859813085, "grad_norm": 1.1371246576309204, "learning_rate": 1.666492666857961e-05, "loss": 0.9094, "step": 4962 }, { "epoch": 0.2898948598130841, "grad_norm": 0.9697433710098267, "learning_rate": 1.6663516159263923e-05, "loss": 0.6389, "step": 4963 }, { "epoch": 0.28995327102803736, "grad_norm": 1.3267639875411987, "learning_rate": 1.666210541145661e-05, "loss": 0.6717, "step": 4964 }, { "epoch": 0.2900116822429907, "grad_norm": 1.7458490133285522, "learning_rate": 1.6660694425208163e-05, "loss": 0.9206, "step": 4965 }, { "epoch": 0.29007009345794393, "grad_norm": 1.3493843078613281, "learning_rate": 1.6659283200569086e-05, "loss": 0.7976, "step": 4966 }, { "epoch": 0.2901285046728972, "grad_norm": 1.2475441694259644, "learning_rate": 1.6657871737589883e-05, "loss": 0.807, "step": 4967 }, { "epoch": 0.29018691588785045, "grad_norm": 1.4633479118347168, "learning_rate": 1.6656460036321074e-05, "loss": 0.7525, "step": 4968 }, { "epoch": 0.29024532710280376, "grad_norm": 1.9616714715957642, "learning_rate": 1.6655048096813183e-05, "loss": 1.0046, "step": 4969 }, { "epoch": 0.290303738317757, "grad_norm": 2.4083797931671143, "learning_rate": 1.665363591911674e-05, "loss": 0.8405, "step": 4970 }, { "epoch": 0.2903621495327103, "grad_norm": 2.111173391342163, "learning_rate": 1.66522235032823e-05, "loss": 0.8462, "step": 4971 }, { "epoch": 0.29042056074766354, "grad_norm": 1.7234433889389038, "learning_rate": 1.6650810849360405e-05, "loss": 0.7978, "step": 4972 }, { "epoch": 0.29047897196261685, "grad_norm": 1.3972630500793457, "learning_rate": 1.6649397957401613e-05, "loss": 0.9109, "step": 4973 }, { "epoch": 0.2905373831775701, "grad_norm": 2.540032386779785, "learning_rate": 1.66479848274565e-05, "loss": 0.9871, "step": 4974 }, { "epoch": 0.29059579439252337, "grad_norm": 1.1458604335784912, "learning_rate": 1.6646571459575637e-05, "loss": 1.0105, "step": 4975 }, { "epoch": 0.2906542056074766, "grad_norm": 2.250426769256592, "learning_rate": 1.6645157853809614e-05, "loss": 0.9091, "step": 4976 }, { "epoch": 0.2907126168224299, "grad_norm": 1.0021281242370605, "learning_rate": 1.664374401020902e-05, "loss": 0.7195, "step": 4977 }, { "epoch": 0.2907710280373832, "grad_norm": 1.8300939798355103, "learning_rate": 1.664232992882446e-05, "loss": 0.8598, "step": 4978 }, { "epoch": 0.29082943925233645, "grad_norm": 1.3215380907058716, "learning_rate": 1.6640915609706543e-05, "loss": 0.8089, "step": 4979 }, { "epoch": 0.2908878504672897, "grad_norm": 1.4292386770248413, "learning_rate": 1.663950105290589e-05, "loss": 0.8417, "step": 4980 }, { "epoch": 0.29094626168224297, "grad_norm": 1.1469509601593018, "learning_rate": 1.663808625847313e-05, "loss": 0.8675, "step": 4981 }, { "epoch": 0.2910046728971963, "grad_norm": 2.7515039443969727, "learning_rate": 1.6636671226458897e-05, "loss": 0.7859, "step": 4982 }, { "epoch": 0.29106308411214954, "grad_norm": 1.3974347114562988, "learning_rate": 1.663525595691384e-05, "loss": 0.729, "step": 4983 }, { "epoch": 0.2911214953271028, "grad_norm": 2.2996208667755127, "learning_rate": 1.6633840449888607e-05, "loss": 0.9266, "step": 4984 }, { "epoch": 0.29117990654205606, "grad_norm": 1.4555827379226685, "learning_rate": 1.663242470543386e-05, "loss": 0.9131, "step": 4985 }, { "epoch": 0.29123831775700937, "grad_norm": 1.6127859354019165, "learning_rate": 1.6631008723600276e-05, "loss": 0.7613, "step": 4986 }, { "epoch": 0.2912967289719626, "grad_norm": 1.4802809953689575, "learning_rate": 1.662959250443853e-05, "loss": 0.8428, "step": 4987 }, { "epoch": 0.2913551401869159, "grad_norm": 1.4918071031570435, "learning_rate": 1.6628176047999306e-05, "loss": 0.7, "step": 4988 }, { "epoch": 0.29141355140186914, "grad_norm": 1.9305802583694458, "learning_rate": 1.6626759354333305e-05, "loss": 0.8165, "step": 4989 }, { "epoch": 0.29147196261682246, "grad_norm": 1.0507957935333252, "learning_rate": 1.6625342423491232e-05, "loss": 0.6655, "step": 4990 }, { "epoch": 0.2915303738317757, "grad_norm": 1.5630468130111694, "learning_rate": 1.6623925255523792e-05, "loss": 0.8848, "step": 4991 }, { "epoch": 0.29158878504672897, "grad_norm": 1.879351258277893, "learning_rate": 1.6622507850481718e-05, "loss": 0.8562, "step": 4992 }, { "epoch": 0.29164719626168223, "grad_norm": 2.6706647872924805, "learning_rate": 1.6621090208415728e-05, "loss": 0.6891, "step": 4993 }, { "epoch": 0.2917056074766355, "grad_norm": 1.6892354488372803, "learning_rate": 1.6619672329376567e-05, "loss": 0.9611, "step": 4994 }, { "epoch": 0.2917640186915888, "grad_norm": 1.6421083211898804, "learning_rate": 1.6618254213414983e-05, "loss": 0.9017, "step": 4995 }, { "epoch": 0.29182242990654206, "grad_norm": 1.8117539882659912, "learning_rate": 1.661683586058173e-05, "loss": 0.891, "step": 4996 }, { "epoch": 0.2918808411214953, "grad_norm": 1.1317334175109863, "learning_rate": 1.6615417270927568e-05, "loss": 0.7019, "step": 4997 }, { "epoch": 0.2919392523364486, "grad_norm": 1.3081728219985962, "learning_rate": 1.6613998444503275e-05, "loss": 0.8349, "step": 4998 }, { "epoch": 0.2919976635514019, "grad_norm": 3.0943565368652344, "learning_rate": 1.6612579381359624e-05, "loss": 0.7619, "step": 4999 }, { "epoch": 0.29205607476635514, "grad_norm": 1.1934740543365479, "learning_rate": 1.6611160081547414e-05, "loss": 0.6913, "step": 5000 }, { "epoch": 0.2921144859813084, "grad_norm": 1.2622839212417603, "learning_rate": 1.6609740545117436e-05, "loss": 0.7102, "step": 5001 }, { "epoch": 0.29217289719626166, "grad_norm": 2.1709671020507812, "learning_rate": 1.66083207721205e-05, "loss": 0.9356, "step": 5002 }, { "epoch": 0.292231308411215, "grad_norm": 1.201892614364624, "learning_rate": 1.6606900762607413e-05, "loss": 0.8025, "step": 5003 }, { "epoch": 0.29228971962616823, "grad_norm": 1.1364749670028687, "learning_rate": 1.6605480516629007e-05, "loss": 1.0229, "step": 5004 }, { "epoch": 0.2923481308411215, "grad_norm": 1.4130535125732422, "learning_rate": 1.660406003423611e-05, "loss": 0.9917, "step": 5005 }, { "epoch": 0.29240654205607475, "grad_norm": 1.1281846761703491, "learning_rate": 1.6602639315479562e-05, "loss": 0.8104, "step": 5006 }, { "epoch": 0.29246495327102806, "grad_norm": 4.039470195770264, "learning_rate": 1.660121836041021e-05, "loss": 1.0367, "step": 5007 }, { "epoch": 0.2925233644859813, "grad_norm": 1.7181905508041382, "learning_rate": 1.6599797169078918e-05, "loss": 0.9825, "step": 5008 }, { "epoch": 0.2925817757009346, "grad_norm": 1.4457722902297974, "learning_rate": 1.659837574153654e-05, "loss": 0.9722, "step": 5009 }, { "epoch": 0.29264018691588783, "grad_norm": 1.682869553565979, "learning_rate": 1.659695407783396e-05, "loss": 0.8281, "step": 5010 }, { "epoch": 0.29269859813084115, "grad_norm": 1.3544446229934692, "learning_rate": 1.659553217802205e-05, "loss": 0.8585, "step": 5011 }, { "epoch": 0.2927570093457944, "grad_norm": 1.126697063446045, "learning_rate": 1.6594110042151715e-05, "loss": 0.7162, "step": 5012 }, { "epoch": 0.29281542056074766, "grad_norm": 1.483545184135437, "learning_rate": 1.659268767027384e-05, "loss": 0.8903, "step": 5013 }, { "epoch": 0.2928738317757009, "grad_norm": 1.3826589584350586, "learning_rate": 1.6591265062439338e-05, "loss": 0.9156, "step": 5014 }, { "epoch": 0.2929322429906542, "grad_norm": 1.3987070322036743, "learning_rate": 1.658984221869913e-05, "loss": 0.8773, "step": 5015 }, { "epoch": 0.2929906542056075, "grad_norm": 1.1664857864379883, "learning_rate": 1.6588419139104132e-05, "loss": 0.8672, "step": 5016 }, { "epoch": 0.29304906542056075, "grad_norm": 1.4476286172866821, "learning_rate": 1.6586995823705282e-05, "loss": 0.9607, "step": 5017 }, { "epoch": 0.293107476635514, "grad_norm": 1.7379546165466309, "learning_rate": 1.658557227255352e-05, "loss": 0.9286, "step": 5018 }, { "epoch": 0.29316588785046727, "grad_norm": 1.3218748569488525, "learning_rate": 1.65841484856998e-05, "loss": 0.8363, "step": 5019 }, { "epoch": 0.2932242990654206, "grad_norm": 1.8201203346252441, "learning_rate": 1.6582724463195073e-05, "loss": 0.9238, "step": 5020 }, { "epoch": 0.29328271028037384, "grad_norm": 1.1371030807495117, "learning_rate": 1.658130020509031e-05, "loss": 0.8051, "step": 5021 }, { "epoch": 0.2933411214953271, "grad_norm": 2.0350308418273926, "learning_rate": 1.6579875711436486e-05, "loss": 1.0919, "step": 5022 }, { "epoch": 0.29339953271028035, "grad_norm": 0.9180075526237488, "learning_rate": 1.6578450982284584e-05, "loss": 0.7963, "step": 5023 }, { "epoch": 0.29345794392523367, "grad_norm": 2.03344464302063, "learning_rate": 1.6577026017685596e-05, "loss": 0.77, "step": 5024 }, { "epoch": 0.2935163551401869, "grad_norm": 1.1643146276474, "learning_rate": 1.6575600817690524e-05, "loss": 0.868, "step": 5025 }, { "epoch": 0.2935747663551402, "grad_norm": 2.607543706893921, "learning_rate": 1.6574175382350367e-05, "loss": 0.9549, "step": 5026 }, { "epoch": 0.29363317757009344, "grad_norm": 1.8673412799835205, "learning_rate": 1.657274971171616e-05, "loss": 0.6647, "step": 5027 }, { "epoch": 0.29369158878504675, "grad_norm": 2.0566322803497314, "learning_rate": 1.6571323805838914e-05, "loss": 0.8239, "step": 5028 }, { "epoch": 0.29375, "grad_norm": 1.7278519868850708, "learning_rate": 1.6569897664769672e-05, "loss": 0.8119, "step": 5029 }, { "epoch": 0.29380841121495327, "grad_norm": 1.5161205530166626, "learning_rate": 1.656847128855947e-05, "loss": 0.6921, "step": 5030 }, { "epoch": 0.2938668224299065, "grad_norm": 2.016585111618042, "learning_rate": 1.656704467725936e-05, "loss": 0.8271, "step": 5031 }, { "epoch": 0.29392523364485984, "grad_norm": 1.7187461853027344, "learning_rate": 1.6565617830920408e-05, "loss": 0.7926, "step": 5032 }, { "epoch": 0.2939836448598131, "grad_norm": 1.9445911645889282, "learning_rate": 1.656419074959367e-05, "loss": 1.1474, "step": 5033 }, { "epoch": 0.29404205607476636, "grad_norm": 1.3532943725585938, "learning_rate": 1.6562763433330237e-05, "loss": 0.8507, "step": 5034 }, { "epoch": 0.2941004672897196, "grad_norm": 1.9160449504852295, "learning_rate": 1.656133588218118e-05, "loss": 0.6432, "step": 5035 }, { "epoch": 0.29415887850467287, "grad_norm": 1.77240788936615, "learning_rate": 1.65599080961976e-05, "loss": 0.7364, "step": 5036 }, { "epoch": 0.2942172897196262, "grad_norm": 0.9711828827857971, "learning_rate": 1.6558480075430594e-05, "loss": 0.7123, "step": 5037 }, { "epoch": 0.29427570093457944, "grad_norm": 1.5439958572387695, "learning_rate": 1.6557051819931275e-05, "loss": 0.835, "step": 5038 }, { "epoch": 0.2943341121495327, "grad_norm": 2.4206137657165527, "learning_rate": 1.6555623329750764e-05, "loss": 0.7995, "step": 5039 }, { "epoch": 0.29439252336448596, "grad_norm": 1.1077121496200562, "learning_rate": 1.655419460494018e-05, "loss": 0.8518, "step": 5040 }, { "epoch": 0.29445093457943927, "grad_norm": 2.2107741832733154, "learning_rate": 1.655276564555066e-05, "loss": 0.9974, "step": 5041 }, { "epoch": 0.29450934579439253, "grad_norm": 1.1075749397277832, "learning_rate": 1.655133645163335e-05, "loss": 0.8855, "step": 5042 }, { "epoch": 0.2945677570093458, "grad_norm": 1.8684707880020142, "learning_rate": 1.65499070232394e-05, "loss": 0.959, "step": 5043 }, { "epoch": 0.29462616822429905, "grad_norm": 1.5779496431350708, "learning_rate": 1.6548477360419976e-05, "loss": 0.851, "step": 5044 }, { "epoch": 0.29468457943925236, "grad_norm": 1.3174740076065063, "learning_rate": 1.6547047463226237e-05, "loss": 0.796, "step": 5045 }, { "epoch": 0.2947429906542056, "grad_norm": 1.262326955795288, "learning_rate": 1.6545617331709364e-05, "loss": 0.6669, "step": 5046 }, { "epoch": 0.2948014018691589, "grad_norm": 1.9317744970321655, "learning_rate": 1.6544186965920542e-05, "loss": 0.9652, "step": 5047 }, { "epoch": 0.29485981308411213, "grad_norm": 1.1382641792297363, "learning_rate": 1.654275636591097e-05, "loss": 0.7637, "step": 5048 }, { "epoch": 0.29491822429906545, "grad_norm": 1.3495242595672607, "learning_rate": 1.6541325531731843e-05, "loss": 0.763, "step": 5049 }, { "epoch": 0.2949766355140187, "grad_norm": 1.0676509141921997, "learning_rate": 1.6539894463434376e-05, "loss": 0.6566, "step": 5050 }, { "epoch": 0.29503504672897196, "grad_norm": 1.491498589515686, "learning_rate": 1.6538463161069786e-05, "loss": 0.7441, "step": 5051 }, { "epoch": 0.2950934579439252, "grad_norm": 1.7201412916183472, "learning_rate": 1.6537031624689298e-05, "loss": 0.8706, "step": 5052 }, { "epoch": 0.2951518691588785, "grad_norm": 1.620262622833252, "learning_rate": 1.653559985434415e-05, "loss": 0.9108, "step": 5053 }, { "epoch": 0.2952102803738318, "grad_norm": 1.51264488697052, "learning_rate": 1.653416785008559e-05, "loss": 0.9672, "step": 5054 }, { "epoch": 0.29526869158878505, "grad_norm": 1.3452454805374146, "learning_rate": 1.6532735611964863e-05, "loss": 1.0656, "step": 5055 }, { "epoch": 0.2953271028037383, "grad_norm": 1.7089557647705078, "learning_rate": 1.6531303140033235e-05, "loss": 0.7735, "step": 5056 }, { "epoch": 0.29538551401869156, "grad_norm": 1.4566389322280884, "learning_rate": 1.652987043434197e-05, "loss": 0.9504, "step": 5057 }, { "epoch": 0.2954439252336449, "grad_norm": 1.6869373321533203, "learning_rate": 1.652843749494235e-05, "loss": 0.9554, "step": 5058 }, { "epoch": 0.29550233644859814, "grad_norm": 1.0639557838439941, "learning_rate": 1.652700432188566e-05, "loss": 0.8148, "step": 5059 }, { "epoch": 0.2955607476635514, "grad_norm": 1.5152809619903564, "learning_rate": 1.6525570915223193e-05, "loss": 0.8977, "step": 5060 }, { "epoch": 0.29561915887850465, "grad_norm": 2.181830883026123, "learning_rate": 1.6524137275006252e-05, "loss": 0.7535, "step": 5061 }, { "epoch": 0.29567757009345796, "grad_norm": 1.326676607131958, "learning_rate": 1.652270340128615e-05, "loss": 0.7591, "step": 5062 }, { "epoch": 0.2957359813084112, "grad_norm": 2.7081358432769775, "learning_rate": 1.6521269294114206e-05, "loss": 0.9666, "step": 5063 }, { "epoch": 0.2957943925233645, "grad_norm": 1.6440106630325317, "learning_rate": 1.6519834953541743e-05, "loss": 0.748, "step": 5064 }, { "epoch": 0.29585280373831774, "grad_norm": 2.0155951976776123, "learning_rate": 1.65184003796201e-05, "loss": 0.8496, "step": 5065 }, { "epoch": 0.29591121495327105, "grad_norm": 1.234120488166809, "learning_rate": 1.6516965572400626e-05, "loss": 0.9259, "step": 5066 }, { "epoch": 0.2959696261682243, "grad_norm": 2.375478744506836, "learning_rate": 1.6515530531934665e-05, "loss": 0.8024, "step": 5067 }, { "epoch": 0.29602803738317757, "grad_norm": 1.4665145874023438, "learning_rate": 1.6514095258273584e-05, "loss": 0.8379, "step": 5068 }, { "epoch": 0.2960864485981308, "grad_norm": 1.799182653427124, "learning_rate": 1.651265975146875e-05, "loss": 0.6506, "step": 5069 }, { "epoch": 0.29614485981308414, "grad_norm": 2.3496475219726562, "learning_rate": 1.651122401157154e-05, "loss": 0.8312, "step": 5070 }, { "epoch": 0.2962032710280374, "grad_norm": 1.3996680974960327, "learning_rate": 1.650978803863334e-05, "loss": 0.8196, "step": 5071 }, { "epoch": 0.29626168224299065, "grad_norm": 1.6125503778457642, "learning_rate": 1.650835183270555e-05, "loss": 0.7823, "step": 5072 }, { "epoch": 0.2963200934579439, "grad_norm": 2.181100368499756, "learning_rate": 1.6506915393839567e-05, "loss": 0.9014, "step": 5073 }, { "epoch": 0.29637850467289717, "grad_norm": 1.5445524454116821, "learning_rate": 1.6505478722086802e-05, "loss": 0.8848, "step": 5074 }, { "epoch": 0.2964369158878505, "grad_norm": 3.0347115993499756, "learning_rate": 1.6504041817498676e-05, "loss": 0.8922, "step": 5075 }, { "epoch": 0.29649532710280374, "grad_norm": 1.1311700344085693, "learning_rate": 1.650260468012662e-05, "loss": 0.7921, "step": 5076 }, { "epoch": 0.296553738317757, "grad_norm": 1.6349130868911743, "learning_rate": 1.6501167310022065e-05, "loss": 0.8782, "step": 5077 }, { "epoch": 0.29661214953271026, "grad_norm": 2.0158703327178955, "learning_rate": 1.649972970723646e-05, "loss": 0.9044, "step": 5078 }, { "epoch": 0.29667056074766357, "grad_norm": 1.0613868236541748, "learning_rate": 1.6498291871821254e-05, "loss": 0.8941, "step": 5079 }, { "epoch": 0.2967289719626168, "grad_norm": 2.6127543449401855, "learning_rate": 1.6496853803827907e-05, "loss": 0.7214, "step": 5080 }, { "epoch": 0.2967873831775701, "grad_norm": 2.380500555038452, "learning_rate": 1.649541550330789e-05, "loss": 0.9754, "step": 5081 }, { "epoch": 0.29684579439252334, "grad_norm": 1.8551230430603027, "learning_rate": 1.6493976970312683e-05, "loss": 0.8805, "step": 5082 }, { "epoch": 0.29690420560747666, "grad_norm": 2.4809458255767822, "learning_rate": 1.6492538204893772e-05, "loss": 0.9521, "step": 5083 }, { "epoch": 0.2969626168224299, "grad_norm": 1.1311769485473633, "learning_rate": 1.6491099207102648e-05, "loss": 0.6389, "step": 5084 }, { "epoch": 0.2970210280373832, "grad_norm": 2.2610816955566406, "learning_rate": 1.6489659976990814e-05, "loss": 0.8411, "step": 5085 }, { "epoch": 0.29707943925233643, "grad_norm": 2.069645643234253, "learning_rate": 1.6488220514609782e-05, "loss": 0.9917, "step": 5086 }, { "epoch": 0.29713785046728974, "grad_norm": 1.1933001279830933, "learning_rate": 1.6486780820011076e-05, "loss": 0.8881, "step": 5087 }, { "epoch": 0.297196261682243, "grad_norm": 1.807507872581482, "learning_rate": 1.6485340893246217e-05, "loss": 0.7906, "step": 5088 }, { "epoch": 0.29725467289719626, "grad_norm": 2.3824386596679688, "learning_rate": 1.6483900734366743e-05, "loss": 0.9145, "step": 5089 }, { "epoch": 0.2973130841121495, "grad_norm": 1.1383129358291626, "learning_rate": 1.6482460343424197e-05, "loss": 0.8908, "step": 5090 }, { "epoch": 0.29737149532710283, "grad_norm": 2.3315865993499756, "learning_rate": 1.6481019720470134e-05, "loss": 1.0003, "step": 5091 }, { "epoch": 0.2974299065420561, "grad_norm": 1.2129547595977783, "learning_rate": 1.6479578865556115e-05, "loss": 0.9011, "step": 5092 }, { "epoch": 0.29748831775700935, "grad_norm": 1.4292254447937012, "learning_rate": 1.6478137778733708e-05, "loss": 0.7932, "step": 5093 }, { "epoch": 0.2975467289719626, "grad_norm": 2.480196475982666, "learning_rate": 1.647669646005449e-05, "loss": 0.9658, "step": 5094 }, { "epoch": 0.29760514018691586, "grad_norm": 1.4757369756698608, "learning_rate": 1.647525490957005e-05, "loss": 0.9182, "step": 5095 }, { "epoch": 0.2976635514018692, "grad_norm": 1.8367244005203247, "learning_rate": 1.6473813127331973e-05, "loss": 0.8837, "step": 5096 }, { "epoch": 0.29772196261682243, "grad_norm": 1.1597779989242554, "learning_rate": 1.6472371113391873e-05, "loss": 0.8126, "step": 5097 }, { "epoch": 0.2977803738317757, "grad_norm": 1.4587713479995728, "learning_rate": 1.6470928867801353e-05, "loss": 0.7708, "step": 5098 }, { "epoch": 0.29783878504672895, "grad_norm": 1.5161209106445312, "learning_rate": 1.6469486390612033e-05, "loss": 0.9332, "step": 5099 }, { "epoch": 0.29789719626168226, "grad_norm": 2.0072038173675537, "learning_rate": 1.6468043681875542e-05, "loss": 0.919, "step": 5100 }, { "epoch": 0.2979556074766355, "grad_norm": 1.446960687637329, "learning_rate": 1.6466600741643515e-05, "loss": 0.9125, "step": 5101 }, { "epoch": 0.2980140186915888, "grad_norm": 0.9727597236633301, "learning_rate": 1.6465157569967595e-05, "loss": 0.8678, "step": 5102 }, { "epoch": 0.29807242990654204, "grad_norm": 1.2194796800613403, "learning_rate": 1.6463714166899438e-05, "loss": 0.7647, "step": 5103 }, { "epoch": 0.29813084112149535, "grad_norm": 1.3506758213043213, "learning_rate": 1.64622705324907e-05, "loss": 0.8601, "step": 5104 }, { "epoch": 0.2981892523364486, "grad_norm": 1.502672791481018, "learning_rate": 1.6460826666793045e-05, "loss": 0.8773, "step": 5105 }, { "epoch": 0.29824766355140186, "grad_norm": 1.2331687211990356, "learning_rate": 1.645938256985816e-05, "loss": 0.7599, "step": 5106 }, { "epoch": 0.2983060747663551, "grad_norm": 1.348124384880066, "learning_rate": 1.645793824173773e-05, "loss": 0.7464, "step": 5107 }, { "epoch": 0.29836448598130844, "grad_norm": 1.181345820426941, "learning_rate": 1.6456493682483436e-05, "loss": 0.9411, "step": 5108 }, { "epoch": 0.2984228971962617, "grad_norm": 1.001910924911499, "learning_rate": 1.645504889214699e-05, "loss": 0.7565, "step": 5109 }, { "epoch": 0.29848130841121495, "grad_norm": 1.2910064458847046, "learning_rate": 1.6453603870780105e-05, "loss": 0.8667, "step": 5110 }, { "epoch": 0.2985397196261682, "grad_norm": 1.3480252027511597, "learning_rate": 1.645215861843449e-05, "loss": 0.8979, "step": 5111 }, { "epoch": 0.2985981308411215, "grad_norm": 0.9928154945373535, "learning_rate": 1.6450713135161875e-05, "loss": 0.769, "step": 5112 }, { "epoch": 0.2986565420560748, "grad_norm": 1.7133058309555054, "learning_rate": 1.6449267421013994e-05, "loss": 0.9957, "step": 5113 }, { "epoch": 0.29871495327102804, "grad_norm": 1.1962008476257324, "learning_rate": 1.6447821476042592e-05, "loss": 0.7727, "step": 5114 }, { "epoch": 0.2987733644859813, "grad_norm": 1.681854248046875, "learning_rate": 1.6446375300299425e-05, "loss": 0.9188, "step": 5115 }, { "epoch": 0.29883177570093455, "grad_norm": 1.360185980796814, "learning_rate": 1.6444928893836246e-05, "loss": 0.7818, "step": 5116 }, { "epoch": 0.29889018691588787, "grad_norm": 1.3680388927459717, "learning_rate": 1.644348225670482e-05, "loss": 0.7456, "step": 5117 }, { "epoch": 0.2989485981308411, "grad_norm": 2.4521491527557373, "learning_rate": 1.644203538895693e-05, "loss": 0.8542, "step": 5118 }, { "epoch": 0.2990070093457944, "grad_norm": 1.9298850297927856, "learning_rate": 1.6440588290644357e-05, "loss": 0.903, "step": 5119 }, { "epoch": 0.29906542056074764, "grad_norm": 1.6718199253082275, "learning_rate": 1.6439140961818894e-05, "loss": 0.7782, "step": 5120 }, { "epoch": 0.29912383177570095, "grad_norm": 1.1642571687698364, "learning_rate": 1.6437693402532345e-05, "loss": 0.8147, "step": 5121 }, { "epoch": 0.2991822429906542, "grad_norm": 1.6700295209884644, "learning_rate": 1.6436245612836516e-05, "loss": 0.748, "step": 5122 }, { "epoch": 0.29924065420560747, "grad_norm": 1.4770735502243042, "learning_rate": 1.6434797592783224e-05, "loss": 0.9445, "step": 5123 }, { "epoch": 0.29929906542056073, "grad_norm": 1.6326720714569092, "learning_rate": 1.6433349342424292e-05, "loss": 0.8362, "step": 5124 }, { "epoch": 0.29935747663551404, "grad_norm": 1.53464937210083, "learning_rate": 1.643190086181156e-05, "loss": 0.8742, "step": 5125 }, { "epoch": 0.2994158878504673, "grad_norm": 1.289630651473999, "learning_rate": 1.6430452150996864e-05, "loss": 0.8777, "step": 5126 }, { "epoch": 0.29947429906542056, "grad_norm": 2.0402748584747314, "learning_rate": 1.642900321003206e-05, "loss": 0.9292, "step": 5127 }, { "epoch": 0.2995327102803738, "grad_norm": 1.6436214447021484, "learning_rate": 1.6427554038969004e-05, "loss": 0.9195, "step": 5128 }, { "epoch": 0.29959112149532713, "grad_norm": 1.3209803104400635, "learning_rate": 1.6426104637859563e-05, "loss": 0.8717, "step": 5129 }, { "epoch": 0.2996495327102804, "grad_norm": 1.9285237789154053, "learning_rate": 1.642465500675561e-05, "loss": 1.0447, "step": 5130 }, { "epoch": 0.29970794392523364, "grad_norm": 1.6055253744125366, "learning_rate": 1.6423205145709033e-05, "loss": 0.8986, "step": 5131 }, { "epoch": 0.2997663551401869, "grad_norm": 1.5571255683898926, "learning_rate": 1.6421755054771718e-05, "loss": 0.9014, "step": 5132 }, { "epoch": 0.29982476635514016, "grad_norm": 1.202172040939331, "learning_rate": 1.6420304733995567e-05, "loss": 0.8301, "step": 5133 }, { "epoch": 0.2998831775700935, "grad_norm": 1.4531166553497314, "learning_rate": 1.641885418343249e-05, "loss": 0.9099, "step": 5134 }, { "epoch": 0.29994158878504673, "grad_norm": 1.0955194234848022, "learning_rate": 1.64174034031344e-05, "loss": 0.6643, "step": 5135 }, { "epoch": 0.3, "grad_norm": 2.138828992843628, "learning_rate": 1.641595239315322e-05, "loss": 0.799, "step": 5136 }, { "epoch": 0.30005841121495325, "grad_norm": 1.6751753091812134, "learning_rate": 1.6414501153540893e-05, "loss": 0.7536, "step": 5137 }, { "epoch": 0.30011682242990656, "grad_norm": 2.3374428749084473, "learning_rate": 1.6413049684349344e-05, "loss": 1.0091, "step": 5138 }, { "epoch": 0.3001752336448598, "grad_norm": 2.219719886779785, "learning_rate": 1.6411597985630535e-05, "loss": 0.6558, "step": 5139 }, { "epoch": 0.3002336448598131, "grad_norm": 1.7026581764221191, "learning_rate": 1.641014605743642e-05, "loss": 0.7462, "step": 5140 }, { "epoch": 0.30029205607476633, "grad_norm": 1.3066540956497192, "learning_rate": 1.6408693899818958e-05, "loss": 0.8115, "step": 5141 }, { "epoch": 0.30035046728971965, "grad_norm": 1.98723304271698, "learning_rate": 1.6407241512830128e-05, "loss": 0.9054, "step": 5142 }, { "epoch": 0.3004088785046729, "grad_norm": 1.2775205373764038, "learning_rate": 1.6405788896521913e-05, "loss": 0.9059, "step": 5143 }, { "epoch": 0.30046728971962616, "grad_norm": 1.3988925218582153, "learning_rate": 1.6404336050946297e-05, "loss": 0.8503, "step": 5144 }, { "epoch": 0.3005257009345794, "grad_norm": 1.73186457157135, "learning_rate": 1.6402882976155293e-05, "loss": 1.0155, "step": 5145 }, { "epoch": 0.30058411214953273, "grad_norm": 1.0756086111068726, "learning_rate": 1.640142967220089e-05, "loss": 0.7357, "step": 5146 }, { "epoch": 0.300642523364486, "grad_norm": 1.7878798246383667, "learning_rate": 1.639997613913511e-05, "loss": 0.6711, "step": 5147 }, { "epoch": 0.30070093457943925, "grad_norm": 1.3645941019058228, "learning_rate": 1.6398522377009976e-05, "loss": 0.8597, "step": 5148 }, { "epoch": 0.3007593457943925, "grad_norm": 2.0033926963806152, "learning_rate": 1.6397068385877523e-05, "loss": 0.8442, "step": 5149 }, { "epoch": 0.3008177570093458, "grad_norm": 1.354583740234375, "learning_rate": 1.639561416578978e-05, "loss": 0.8274, "step": 5150 }, { "epoch": 0.3008761682242991, "grad_norm": 1.2776304483413696, "learning_rate": 1.6394159716798807e-05, "loss": 0.8002, "step": 5151 }, { "epoch": 0.30093457943925234, "grad_norm": 1.5366222858428955, "learning_rate": 1.639270503895665e-05, "loss": 0.7519, "step": 5152 }, { "epoch": 0.3009929906542056, "grad_norm": 1.2656902074813843, "learning_rate": 1.6391250132315376e-05, "loss": 0.8386, "step": 5153 }, { "epoch": 0.30105140186915885, "grad_norm": 1.631341576576233, "learning_rate": 1.638979499692706e-05, "loss": 0.7596, "step": 5154 }, { "epoch": 0.30110981308411217, "grad_norm": 1.238165259361267, "learning_rate": 1.638833963284378e-05, "loss": 0.8775, "step": 5155 }, { "epoch": 0.3011682242990654, "grad_norm": 1.296280860900879, "learning_rate": 1.6386884040117622e-05, "loss": 0.7585, "step": 5156 }, { "epoch": 0.3012266355140187, "grad_norm": 2.0245022773742676, "learning_rate": 1.6385428218800683e-05, "loss": 1.0499, "step": 5157 }, { "epoch": 0.30128504672897194, "grad_norm": 1.7038259506225586, "learning_rate": 1.6383972168945073e-05, "loss": 0.9516, "step": 5158 }, { "epoch": 0.30134345794392525, "grad_norm": 1.621075987815857, "learning_rate": 1.6382515890602898e-05, "loss": 0.7499, "step": 5159 }, { "epoch": 0.3014018691588785, "grad_norm": 1.3739532232284546, "learning_rate": 1.6381059383826288e-05, "loss": 0.7833, "step": 5160 }, { "epoch": 0.30146028037383177, "grad_norm": 1.3987360000610352, "learning_rate": 1.6379602648667362e-05, "loss": 0.6755, "step": 5161 }, { "epoch": 0.301518691588785, "grad_norm": 1.7362391948699951, "learning_rate": 1.6378145685178264e-05, "loss": 0.7806, "step": 5162 }, { "epoch": 0.30157710280373834, "grad_norm": 2.2770936489105225, "learning_rate": 1.6376688493411138e-05, "loss": 0.8077, "step": 5163 }, { "epoch": 0.3016355140186916, "grad_norm": 5.652088165283203, "learning_rate": 1.637523107341814e-05, "loss": 0.6825, "step": 5164 }, { "epoch": 0.30169392523364486, "grad_norm": 1.2320903539657593, "learning_rate": 1.637377342525143e-05, "loss": 0.8107, "step": 5165 }, { "epoch": 0.3017523364485981, "grad_norm": 1.2910314798355103, "learning_rate": 1.6372315548963178e-05, "loss": 0.9132, "step": 5166 }, { "epoch": 0.3018107476635514, "grad_norm": 1.2805149555206299, "learning_rate": 1.637085744460556e-05, "loss": 0.7373, "step": 5167 }, { "epoch": 0.3018691588785047, "grad_norm": 1.7145742177963257, "learning_rate": 1.6369399112230764e-05, "loss": 0.8032, "step": 5168 }, { "epoch": 0.30192757009345794, "grad_norm": 1.1997696161270142, "learning_rate": 1.6367940551890994e-05, "loss": 0.8611, "step": 5169 }, { "epoch": 0.3019859813084112, "grad_norm": 2.9315085411071777, "learning_rate": 1.636648176363844e-05, "loss": 0.9033, "step": 5170 }, { "epoch": 0.3020443925233645, "grad_norm": 1.483402967453003, "learning_rate": 1.6365022747525316e-05, "loss": 0.908, "step": 5171 }, { "epoch": 0.30210280373831777, "grad_norm": 2.1811556816101074, "learning_rate": 1.6363563503603844e-05, "loss": 0.9006, "step": 5172 }, { "epoch": 0.30216121495327103, "grad_norm": 1.682178258895874, "learning_rate": 1.636210403192625e-05, "loss": 0.9899, "step": 5173 }, { "epoch": 0.3022196261682243, "grad_norm": 1.4985207319259644, "learning_rate": 1.6360644332544767e-05, "loss": 0.8444, "step": 5174 }, { "epoch": 0.30227803738317754, "grad_norm": 2.424938917160034, "learning_rate": 1.6359184405511644e-05, "loss": 1.0515, "step": 5175 }, { "epoch": 0.30233644859813086, "grad_norm": 1.246954083442688, "learning_rate": 1.635772425087913e-05, "loss": 0.7155, "step": 5176 }, { "epoch": 0.3023948598130841, "grad_norm": 1.659804344177246, "learning_rate": 1.6356263868699484e-05, "loss": 0.6801, "step": 5177 }, { "epoch": 0.3024532710280374, "grad_norm": 2.652906656265259, "learning_rate": 1.6354803259024975e-05, "loss": 0.8009, "step": 5178 }, { "epoch": 0.30251168224299063, "grad_norm": 1.170605182647705, "learning_rate": 1.635334242190788e-05, "loss": 0.6776, "step": 5179 }, { "epoch": 0.30257009345794394, "grad_norm": 2.9985251426696777, "learning_rate": 1.635188135740048e-05, "loss": 0.8597, "step": 5180 }, { "epoch": 0.3026285046728972, "grad_norm": 1.0671498775482178, "learning_rate": 1.635042006555507e-05, "loss": 0.809, "step": 5181 }, { "epoch": 0.30268691588785046, "grad_norm": 2.4909961223602295, "learning_rate": 1.6348958546423953e-05, "loss": 0.7562, "step": 5182 }, { "epoch": 0.3027453271028037, "grad_norm": 1.6432993412017822, "learning_rate": 1.6347496800059435e-05, "loss": 0.6659, "step": 5183 }, { "epoch": 0.30280373831775703, "grad_norm": 1.0610175132751465, "learning_rate": 1.6346034826513834e-05, "loss": 0.8512, "step": 5184 }, { "epoch": 0.3028621495327103, "grad_norm": 1.9658931493759155, "learning_rate": 1.6344572625839468e-05, "loss": 1.104, "step": 5185 }, { "epoch": 0.30292056074766355, "grad_norm": 1.1379508972167969, "learning_rate": 1.6343110198088677e-05, "loss": 0.6966, "step": 5186 }, { "epoch": 0.3029789719626168, "grad_norm": 1.5912489891052246, "learning_rate": 1.634164754331381e-05, "loss": 0.8063, "step": 5187 }, { "epoch": 0.3030373831775701, "grad_norm": 1.1446672677993774, "learning_rate": 1.63401846615672e-05, "loss": 0.8875, "step": 5188 }, { "epoch": 0.3030957943925234, "grad_norm": 1.261488437652588, "learning_rate": 1.633872155290121e-05, "loss": 0.9426, "step": 5189 }, { "epoch": 0.30315420560747663, "grad_norm": 1.9684029817581177, "learning_rate": 1.6337258217368216e-05, "loss": 1.0192, "step": 5190 }, { "epoch": 0.3032126168224299, "grad_norm": 1.161950945854187, "learning_rate": 1.6335794655020577e-05, "loss": 0.7681, "step": 5191 }, { "epoch": 0.30327102803738315, "grad_norm": 1.6207997798919678, "learning_rate": 1.6334330865910685e-05, "loss": 0.8994, "step": 5192 }, { "epoch": 0.30332943925233646, "grad_norm": 1.3273534774780273, "learning_rate": 1.6332866850090924e-05, "loss": 0.7956, "step": 5193 }, { "epoch": 0.3033878504672897, "grad_norm": 1.535760760307312, "learning_rate": 1.6331402607613697e-05, "loss": 0.7251, "step": 5194 }, { "epoch": 0.303446261682243, "grad_norm": 2.1799707412719727, "learning_rate": 1.6329938138531403e-05, "loss": 1.0409, "step": 5195 }, { "epoch": 0.30350467289719624, "grad_norm": 1.4092626571655273, "learning_rate": 1.6328473442896466e-05, "loss": 0.6557, "step": 5196 }, { "epoch": 0.30356308411214955, "grad_norm": 2.3668100833892822, "learning_rate": 1.63270085207613e-05, "loss": 0.7933, "step": 5197 }, { "epoch": 0.3036214953271028, "grad_norm": 1.9408844709396362, "learning_rate": 1.632554337217834e-05, "loss": 0.8229, "step": 5198 }, { "epoch": 0.30367990654205607, "grad_norm": 1.3876429796218872, "learning_rate": 1.6324077997200026e-05, "loss": 1.0235, "step": 5199 }, { "epoch": 0.3037383177570093, "grad_norm": 1.6246330738067627, "learning_rate": 1.63226123958788e-05, "loss": 0.7606, "step": 5200 }, { "epoch": 0.30379672897196264, "grad_norm": 1.5685425996780396, "learning_rate": 1.632114656826712e-05, "loss": 0.99, "step": 5201 }, { "epoch": 0.3038551401869159, "grad_norm": 1.5682371854782104, "learning_rate": 1.631968051441745e-05, "loss": 0.8041, "step": 5202 }, { "epoch": 0.30391355140186915, "grad_norm": 1.1600899696350098, "learning_rate": 1.6318214234382254e-05, "loss": 1.0183, "step": 5203 }, { "epoch": 0.3039719626168224, "grad_norm": 1.719893455505371, "learning_rate": 1.631674772821402e-05, "loss": 0.7918, "step": 5204 }, { "epoch": 0.3040303738317757, "grad_norm": 1.5142439603805542, "learning_rate": 1.631528099596523e-05, "loss": 0.8397, "step": 5205 }, { "epoch": 0.304088785046729, "grad_norm": 1.361607313156128, "learning_rate": 1.6313814037688383e-05, "loss": 0.8909, "step": 5206 }, { "epoch": 0.30414719626168224, "grad_norm": 1.325974941253662, "learning_rate": 1.6312346853435976e-05, "loss": 0.8146, "step": 5207 }, { "epoch": 0.3042056074766355, "grad_norm": 1.5376551151275635, "learning_rate": 1.631087944326053e-05, "loss": 0.8021, "step": 5208 }, { "epoch": 0.3042640186915888, "grad_norm": 0.9750140309333801, "learning_rate": 1.6309411807214555e-05, "loss": 0.7186, "step": 5209 }, { "epoch": 0.30432242990654207, "grad_norm": 1.7789794206619263, "learning_rate": 1.6307943945350583e-05, "loss": 0.9756, "step": 5210 }, { "epoch": 0.3043808411214953, "grad_norm": 1.2175116539001465, "learning_rate": 1.630647585772115e-05, "loss": 0.7594, "step": 5211 }, { "epoch": 0.3044392523364486, "grad_norm": 1.3901889324188232, "learning_rate": 1.6305007544378805e-05, "loss": 0.7717, "step": 5212 }, { "epoch": 0.30449766355140184, "grad_norm": 1.867985725402832, "learning_rate": 1.630353900537609e-05, "loss": 1.0603, "step": 5213 }, { "epoch": 0.30455607476635516, "grad_norm": 1.4501272439956665, "learning_rate": 1.6302070240765567e-05, "loss": 0.7858, "step": 5214 }, { "epoch": 0.3046144859813084, "grad_norm": 1.5528578758239746, "learning_rate": 1.630060125059981e-05, "loss": 0.8558, "step": 5215 }, { "epoch": 0.30467289719626167, "grad_norm": 1.1772725582122803, "learning_rate": 1.629913203493139e-05, "loss": 0.761, "step": 5216 }, { "epoch": 0.30473130841121493, "grad_norm": 1.4773454666137695, "learning_rate": 1.6297662593812892e-05, "loss": 0.9339, "step": 5217 }, { "epoch": 0.30478971962616824, "grad_norm": 1.8104392290115356, "learning_rate": 1.629619292729691e-05, "loss": 0.9837, "step": 5218 }, { "epoch": 0.3048481308411215, "grad_norm": 1.2152888774871826, "learning_rate": 1.6294723035436045e-05, "loss": 0.9745, "step": 5219 }, { "epoch": 0.30490654205607476, "grad_norm": 1.4232689142227173, "learning_rate": 1.62932529182829e-05, "loss": 0.9014, "step": 5220 }, { "epoch": 0.304964953271028, "grad_norm": 1.9303737878799438, "learning_rate": 1.6291782575890097e-05, "loss": 0.8621, "step": 5221 }, { "epoch": 0.30502336448598133, "grad_norm": 1.381489872932434, "learning_rate": 1.6290312008310262e-05, "loss": 0.7436, "step": 5222 }, { "epoch": 0.3050817757009346, "grad_norm": 2.1267385482788086, "learning_rate": 1.628884121559602e-05, "loss": 0.8658, "step": 5223 }, { "epoch": 0.30514018691588785, "grad_norm": 0.9598006010055542, "learning_rate": 1.6287370197800015e-05, "loss": 0.7081, "step": 5224 }, { "epoch": 0.3051985981308411, "grad_norm": 2.1819498538970947, "learning_rate": 1.62858989549749e-05, "loss": 0.8164, "step": 5225 }, { "epoch": 0.3052570093457944, "grad_norm": 1.6014716625213623, "learning_rate": 1.6284427487173324e-05, "loss": 0.8917, "step": 5226 }, { "epoch": 0.3053154205607477, "grad_norm": 2.1769042015075684, "learning_rate": 1.628295579444796e-05, "loss": 0.8469, "step": 5227 }, { "epoch": 0.30537383177570093, "grad_norm": 1.3217034339904785, "learning_rate": 1.6281483876851475e-05, "loss": 0.7387, "step": 5228 }, { "epoch": 0.3054322429906542, "grad_norm": 2.106966018676758, "learning_rate": 1.6280011734436553e-05, "loss": 0.8732, "step": 5229 }, { "epoch": 0.3054906542056075, "grad_norm": 7.935534954071045, "learning_rate": 1.6278539367255885e-05, "loss": 0.9377, "step": 5230 }, { "epoch": 0.30554906542056076, "grad_norm": 1.271905779838562, "learning_rate": 1.6277066775362156e-05, "loss": 0.8215, "step": 5231 }, { "epoch": 0.305607476635514, "grad_norm": 2.058849334716797, "learning_rate": 1.627559395880809e-05, "loss": 0.738, "step": 5232 }, { "epoch": 0.3056658878504673, "grad_norm": 1.3083447217941284, "learning_rate": 1.6274120917646383e-05, "loss": 0.8253, "step": 5233 }, { "epoch": 0.30572429906542054, "grad_norm": 1.9987149238586426, "learning_rate": 1.6272647651929766e-05, "loss": 0.8376, "step": 5234 }, { "epoch": 0.30578271028037385, "grad_norm": 1.4258882999420166, "learning_rate": 1.6271174161710966e-05, "loss": 0.7799, "step": 5235 }, { "epoch": 0.3058411214953271, "grad_norm": 1.8286950588226318, "learning_rate": 1.6269700447042717e-05, "loss": 0.7392, "step": 5236 }, { "epoch": 0.30589953271028036, "grad_norm": 2.328155517578125, "learning_rate": 1.6268226507977767e-05, "loss": 0.7697, "step": 5237 }, { "epoch": 0.3059579439252336, "grad_norm": 1.2727409601211548, "learning_rate": 1.626675234456887e-05, "loss": 0.9415, "step": 5238 }, { "epoch": 0.30601635514018694, "grad_norm": 2.731794834136963, "learning_rate": 1.6265277956868782e-05, "loss": 0.8638, "step": 5239 }, { "epoch": 0.3060747663551402, "grad_norm": 1.0891848802566528, "learning_rate": 1.626380334493028e-05, "loss": 0.7638, "step": 5240 }, { "epoch": 0.30613317757009345, "grad_norm": 1.8157235383987427, "learning_rate": 1.626232850880614e-05, "loss": 0.8614, "step": 5241 }, { "epoch": 0.3061915887850467, "grad_norm": 1.647463321685791, "learning_rate": 1.6260853448549143e-05, "loss": 0.8676, "step": 5242 }, { "epoch": 0.30625, "grad_norm": 1.7265362739562988, "learning_rate": 1.6259378164212084e-05, "loss": 0.9422, "step": 5243 }, { "epoch": 0.3063084112149533, "grad_norm": 1.4603546857833862, "learning_rate": 1.6257902655847763e-05, "loss": 0.7701, "step": 5244 }, { "epoch": 0.30636682242990654, "grad_norm": 1.2594983577728271, "learning_rate": 1.6256426923508994e-05, "loss": 0.7969, "step": 5245 }, { "epoch": 0.3064252336448598, "grad_norm": 1.7944608926773071, "learning_rate": 1.6254950967248592e-05, "loss": 0.9054, "step": 5246 }, { "epoch": 0.3064836448598131, "grad_norm": 1.1493350267410278, "learning_rate": 1.625347478711938e-05, "loss": 0.705, "step": 5247 }, { "epoch": 0.30654205607476637, "grad_norm": 1.243338942527771, "learning_rate": 1.6251998383174196e-05, "loss": 0.9102, "step": 5248 }, { "epoch": 0.3066004672897196, "grad_norm": 1.416648507118225, "learning_rate": 1.6250521755465877e-05, "loss": 0.8721, "step": 5249 }, { "epoch": 0.3066588785046729, "grad_norm": 1.3737448453903198, "learning_rate": 1.6249044904047274e-05, "loss": 0.7964, "step": 5250 }, { "epoch": 0.30671728971962614, "grad_norm": 1.6152074337005615, "learning_rate": 1.624756782897125e-05, "loss": 0.8048, "step": 5251 }, { "epoch": 0.30677570093457945, "grad_norm": 1.557385802268982, "learning_rate": 1.624609053029066e-05, "loss": 0.8595, "step": 5252 }, { "epoch": 0.3068341121495327, "grad_norm": 0.9879224896430969, "learning_rate": 1.6244613008058386e-05, "loss": 0.7709, "step": 5253 }, { "epoch": 0.30689252336448597, "grad_norm": 1.237291693687439, "learning_rate": 1.6243135262327306e-05, "loss": 0.8804, "step": 5254 }, { "epoch": 0.3069509345794392, "grad_norm": 1.20970618724823, "learning_rate": 1.6241657293150307e-05, "loss": 0.7712, "step": 5255 }, { "epoch": 0.30700934579439254, "grad_norm": 1.3040578365325928, "learning_rate": 1.6240179100580297e-05, "loss": 0.9126, "step": 5256 }, { "epoch": 0.3070677570093458, "grad_norm": 1.4323251247406006, "learning_rate": 1.6238700684670166e-05, "loss": 0.904, "step": 5257 }, { "epoch": 0.30712616822429906, "grad_norm": 1.0959123373031616, "learning_rate": 1.623722204547284e-05, "loss": 0.8134, "step": 5258 }, { "epoch": 0.3071845794392523, "grad_norm": 1.7493619918823242, "learning_rate": 1.6235743183041233e-05, "loss": 0.8384, "step": 5259 }, { "epoch": 0.3072429906542056, "grad_norm": 1.6515417098999023, "learning_rate": 1.623426409742828e-05, "loss": 0.7799, "step": 5260 }, { "epoch": 0.3073014018691589, "grad_norm": 1.499568223953247, "learning_rate": 1.6232784788686913e-05, "loss": 0.9045, "step": 5261 }, { "epoch": 0.30735981308411214, "grad_norm": 1.0795336961746216, "learning_rate": 1.6231305256870085e-05, "loss": 0.7974, "step": 5262 }, { "epoch": 0.3074182242990654, "grad_norm": 1.6928017139434814, "learning_rate": 1.6229825502030743e-05, "loss": 0.7463, "step": 5263 }, { "epoch": 0.3074766355140187, "grad_norm": 1.2563838958740234, "learning_rate": 1.6228345524221845e-05, "loss": 0.7473, "step": 5264 }, { "epoch": 0.307535046728972, "grad_norm": 1.4542213678359985, "learning_rate": 1.6226865323496373e-05, "loss": 0.8444, "step": 5265 }, { "epoch": 0.30759345794392523, "grad_norm": 1.577325701713562, "learning_rate": 1.6225384899907293e-05, "loss": 0.9015, "step": 5266 }, { "epoch": 0.3076518691588785, "grad_norm": 1.4826858043670654, "learning_rate": 1.6223904253507593e-05, "loss": 0.9376, "step": 5267 }, { "epoch": 0.3077102803738318, "grad_norm": 1.369586706161499, "learning_rate": 1.622242338435027e-05, "loss": 0.787, "step": 5268 }, { "epoch": 0.30776869158878506, "grad_norm": 1.5112372636795044, "learning_rate": 1.622094229248832e-05, "loss": 0.909, "step": 5269 }, { "epoch": 0.3078271028037383, "grad_norm": 1.8410108089447021, "learning_rate": 1.6219460977974758e-05, "loss": 0.7868, "step": 5270 }, { "epoch": 0.3078855140186916, "grad_norm": 1.795806884765625, "learning_rate": 1.62179794408626e-05, "loss": 0.8537, "step": 5271 }, { "epoch": 0.30794392523364483, "grad_norm": 1.0610122680664062, "learning_rate": 1.6216497681204863e-05, "loss": 0.7304, "step": 5272 }, { "epoch": 0.30800233644859815, "grad_norm": 1.2598567008972168, "learning_rate": 1.6215015699054588e-05, "loss": 0.7155, "step": 5273 }, { "epoch": 0.3080607476635514, "grad_norm": 1.1190590858459473, "learning_rate": 1.6213533494464817e-05, "loss": 1.0125, "step": 5274 }, { "epoch": 0.30811915887850466, "grad_norm": 1.0861278772354126, "learning_rate": 1.6212051067488596e-05, "loss": 0.9333, "step": 5275 }, { "epoch": 0.3081775700934579, "grad_norm": 1.600223183631897, "learning_rate": 1.6210568418178983e-05, "loss": 0.7806, "step": 5276 }, { "epoch": 0.30823598130841123, "grad_norm": 1.1956048011779785, "learning_rate": 1.6209085546589042e-05, "loss": 0.8113, "step": 5277 }, { "epoch": 0.3082943925233645, "grad_norm": 0.9265108108520508, "learning_rate": 1.6207602452771852e-05, "loss": 0.6363, "step": 5278 }, { "epoch": 0.30835280373831775, "grad_norm": 1.246535062789917, "learning_rate": 1.6206119136780482e-05, "loss": 0.8655, "step": 5279 }, { "epoch": 0.308411214953271, "grad_norm": 1.8092701435089111, "learning_rate": 1.620463559866803e-05, "loss": 1.0814, "step": 5280 }, { "epoch": 0.3084696261682243, "grad_norm": 1.0298984050750732, "learning_rate": 1.620315183848759e-05, "loss": 0.6871, "step": 5281 }, { "epoch": 0.3085280373831776, "grad_norm": 1.2647234201431274, "learning_rate": 1.620166785629227e-05, "loss": 0.8478, "step": 5282 }, { "epoch": 0.30858644859813084, "grad_norm": 1.2483763694763184, "learning_rate": 1.6200183652135174e-05, "loss": 0.8678, "step": 5283 }, { "epoch": 0.3086448598130841, "grad_norm": 1.4492719173431396, "learning_rate": 1.619869922606943e-05, "loss": 0.8074, "step": 5284 }, { "epoch": 0.3087032710280374, "grad_norm": 1.677880048751831, "learning_rate": 1.6197214578148165e-05, "loss": 0.9663, "step": 5285 }, { "epoch": 0.30876168224299066, "grad_norm": 1.084017038345337, "learning_rate": 1.619572970842452e-05, "loss": 0.6565, "step": 5286 }, { "epoch": 0.3088200934579439, "grad_norm": 1.940606951713562, "learning_rate": 1.619424461695163e-05, "loss": 1.0126, "step": 5287 }, { "epoch": 0.3088785046728972, "grad_norm": 1.1686996221542358, "learning_rate": 1.6192759303782654e-05, "loss": 0.7704, "step": 5288 }, { "epoch": 0.3089369158878505, "grad_norm": 2.190880060195923, "learning_rate": 1.619127376897075e-05, "loss": 0.9851, "step": 5289 }, { "epoch": 0.30899532710280375, "grad_norm": 1.233198642730713, "learning_rate": 1.618978801256909e-05, "loss": 0.7603, "step": 5290 }, { "epoch": 0.309053738317757, "grad_norm": 1.6703205108642578, "learning_rate": 1.618830203463084e-05, "loss": 0.8986, "step": 5291 }, { "epoch": 0.30911214953271027, "grad_norm": 2.7897119522094727, "learning_rate": 1.61868158352092e-05, "loss": 0.9171, "step": 5292 }, { "epoch": 0.3091705607476635, "grad_norm": 2.430429220199585, "learning_rate": 1.618532941435735e-05, "loss": 0.8824, "step": 5293 }, { "epoch": 0.30922897196261684, "grad_norm": 2.4406614303588867, "learning_rate": 1.618384277212849e-05, "loss": 0.7704, "step": 5294 }, { "epoch": 0.3092873831775701, "grad_norm": 1.985358476638794, "learning_rate": 1.6182355908575837e-05, "loss": 0.8323, "step": 5295 }, { "epoch": 0.30934579439252335, "grad_norm": 1.0862385034561157, "learning_rate": 1.6180868823752598e-05, "loss": 0.6167, "step": 5296 }, { "epoch": 0.3094042056074766, "grad_norm": 4.3055901527404785, "learning_rate": 1.6179381517712e-05, "loss": 0.9272, "step": 5297 }, { "epoch": 0.3094626168224299, "grad_norm": 1.2504314184188843, "learning_rate": 1.6177893990507275e-05, "loss": 0.686, "step": 5298 }, { "epoch": 0.3095210280373832, "grad_norm": 1.384885311126709, "learning_rate": 1.617640624219166e-05, "loss": 0.5345, "step": 5299 }, { "epoch": 0.30957943925233644, "grad_norm": 3.890984058380127, "learning_rate": 1.617491827281841e-05, "loss": 0.8753, "step": 5300 }, { "epoch": 0.3096378504672897, "grad_norm": 1.3518433570861816, "learning_rate": 1.6173430082440767e-05, "loss": 0.8706, "step": 5301 }, { "epoch": 0.309696261682243, "grad_norm": 3.0970346927642822, "learning_rate": 1.6171941671112006e-05, "loss": 0.95, "step": 5302 }, { "epoch": 0.30975467289719627, "grad_norm": 1.9000269174575806, "learning_rate": 1.6170453038885394e-05, "loss": 0.8598, "step": 5303 }, { "epoch": 0.30981308411214953, "grad_norm": 1.0808634757995605, "learning_rate": 1.6168964185814213e-05, "loss": 0.7894, "step": 5304 }, { "epoch": 0.3098714953271028, "grad_norm": 1.8423186540603638, "learning_rate": 1.6167475111951744e-05, "loss": 0.7792, "step": 5305 }, { "epoch": 0.3099299065420561, "grad_norm": 2.2318665981292725, "learning_rate": 1.616598581735129e-05, "loss": 0.9643, "step": 5306 }, { "epoch": 0.30998831775700936, "grad_norm": 1.388122320175171, "learning_rate": 1.6164496302066145e-05, "loss": 1.0596, "step": 5307 }, { "epoch": 0.3100467289719626, "grad_norm": 3.796233654022217, "learning_rate": 1.6163006566149623e-05, "loss": 0.8766, "step": 5308 }, { "epoch": 0.3101051401869159, "grad_norm": 1.9464679956436157, "learning_rate": 1.6161516609655052e-05, "loss": 0.8914, "step": 5309 }, { "epoch": 0.3101635514018692, "grad_norm": 1.4654607772827148, "learning_rate": 1.616002643263574e-05, "loss": 0.8426, "step": 5310 }, { "epoch": 0.31022196261682244, "grad_norm": 1.9558680057525635, "learning_rate": 1.6158536035145037e-05, "loss": 0.6869, "step": 5311 }, { "epoch": 0.3102803738317757, "grad_norm": 1.1584607362747192, "learning_rate": 1.6157045417236278e-05, "loss": 0.8017, "step": 5312 }, { "epoch": 0.31033878504672896, "grad_norm": 1.4732547998428345, "learning_rate": 1.615555457896282e-05, "loss": 0.7706, "step": 5313 }, { "epoch": 0.3103971962616822, "grad_norm": 1.519139051437378, "learning_rate": 1.6154063520378015e-05, "loss": 0.765, "step": 5314 }, { "epoch": 0.31045560747663553, "grad_norm": 1.1063708066940308, "learning_rate": 1.6152572241535228e-05, "loss": 0.7009, "step": 5315 }, { "epoch": 0.3105140186915888, "grad_norm": 2.2257463932037354, "learning_rate": 1.6151080742487832e-05, "loss": 0.7844, "step": 5316 }, { "epoch": 0.31057242990654205, "grad_norm": 1.4512593746185303, "learning_rate": 1.6149589023289217e-05, "loss": 0.8353, "step": 5317 }, { "epoch": 0.3106308411214953, "grad_norm": 1.9601489305496216, "learning_rate": 1.6148097083992763e-05, "loss": 0.8588, "step": 5318 }, { "epoch": 0.3106892523364486, "grad_norm": 1.8261462450027466, "learning_rate": 1.6146604924651875e-05, "loss": 0.9998, "step": 5319 }, { "epoch": 0.3107476635514019, "grad_norm": 1.4712162017822266, "learning_rate": 1.6145112545319956e-05, "loss": 0.7231, "step": 5320 }, { "epoch": 0.31080607476635513, "grad_norm": 1.5990464687347412, "learning_rate": 1.6143619946050415e-05, "loss": 0.9778, "step": 5321 }, { "epoch": 0.3108644859813084, "grad_norm": 1.5902020931243896, "learning_rate": 1.6142127126896682e-05, "loss": 0.8298, "step": 5322 }, { "epoch": 0.3109228971962617, "grad_norm": 1.9065828323364258, "learning_rate": 1.6140634087912176e-05, "loss": 0.9637, "step": 5323 }, { "epoch": 0.31098130841121496, "grad_norm": 1.5033129453659058, "learning_rate": 1.613914082915034e-05, "loss": 0.8765, "step": 5324 }, { "epoch": 0.3110397196261682, "grad_norm": 1.4350401163101196, "learning_rate": 1.6137647350664615e-05, "loss": 0.8939, "step": 5325 }, { "epoch": 0.3110981308411215, "grad_norm": 1.407354474067688, "learning_rate": 1.613615365250846e-05, "loss": 0.8235, "step": 5326 }, { "epoch": 0.3111565420560748, "grad_norm": 1.4003818035125732, "learning_rate": 1.6134659734735326e-05, "loss": 1.0514, "step": 5327 }, { "epoch": 0.31121495327102805, "grad_norm": 1.013875126838684, "learning_rate": 1.613316559739869e-05, "loss": 1.0134, "step": 5328 }, { "epoch": 0.3112733644859813, "grad_norm": 0.9234548211097717, "learning_rate": 1.6131671240552025e-05, "loss": 0.719, "step": 5329 }, { "epoch": 0.31133177570093457, "grad_norm": 1.3782414197921753, "learning_rate": 1.6130176664248812e-05, "loss": 0.801, "step": 5330 }, { "epoch": 0.3113901869158878, "grad_norm": 1.0765056610107422, "learning_rate": 1.6128681868542548e-05, "loss": 0.771, "step": 5331 }, { "epoch": 0.31144859813084114, "grad_norm": 1.1753416061401367, "learning_rate": 1.612718685348673e-05, "loss": 0.7376, "step": 5332 }, { "epoch": 0.3115070093457944, "grad_norm": 2.0058465003967285, "learning_rate": 1.6125691619134866e-05, "loss": 0.882, "step": 5333 }, { "epoch": 0.31156542056074765, "grad_norm": 1.1101009845733643, "learning_rate": 1.612419616554047e-05, "loss": 0.6319, "step": 5334 }, { "epoch": 0.3116238317757009, "grad_norm": 1.7068935632705688, "learning_rate": 1.6122700492757067e-05, "loss": 0.8915, "step": 5335 }, { "epoch": 0.3116822429906542, "grad_norm": 1.4904946088790894, "learning_rate": 1.6121204600838188e-05, "loss": 0.917, "step": 5336 }, { "epoch": 0.3117406542056075, "grad_norm": 1.5295110940933228, "learning_rate": 1.611970848983737e-05, "loss": 0.9554, "step": 5337 }, { "epoch": 0.31179906542056074, "grad_norm": 1.060495376586914, "learning_rate": 1.6118212159808165e-05, "loss": 0.8963, "step": 5338 }, { "epoch": 0.311857476635514, "grad_norm": 1.0756853818893433, "learning_rate": 1.611671561080412e-05, "loss": 0.7268, "step": 5339 }, { "epoch": 0.3119158878504673, "grad_norm": 1.5918548107147217, "learning_rate": 1.61152188428788e-05, "loss": 0.7546, "step": 5340 }, { "epoch": 0.31197429906542057, "grad_norm": 1.164541482925415, "learning_rate": 1.6113721856085783e-05, "loss": 0.6897, "step": 5341 }, { "epoch": 0.3120327102803738, "grad_norm": 1.5773390531539917, "learning_rate": 1.6112224650478637e-05, "loss": 0.9218, "step": 5342 }, { "epoch": 0.3120911214953271, "grad_norm": 1.8423755168914795, "learning_rate": 1.611072722611095e-05, "loss": 0.8403, "step": 5343 }, { "epoch": 0.3121495327102804, "grad_norm": 1.1626932621002197, "learning_rate": 1.6109229583036323e-05, "loss": 0.6934, "step": 5344 }, { "epoch": 0.31220794392523366, "grad_norm": 1.91323983669281, "learning_rate": 1.610773172130835e-05, "loss": 0.8842, "step": 5345 }, { "epoch": 0.3122663551401869, "grad_norm": 1.5351072549819946, "learning_rate": 1.610623364098064e-05, "loss": 0.8692, "step": 5346 }, { "epoch": 0.31232476635514017, "grad_norm": 1.636104941368103, "learning_rate": 1.6104735342106817e-05, "loss": 0.961, "step": 5347 }, { "epoch": 0.3123831775700935, "grad_norm": 1.7116869688034058, "learning_rate": 1.61032368247405e-05, "loss": 0.8188, "step": 5348 }, { "epoch": 0.31244158878504674, "grad_norm": 1.0516196489334106, "learning_rate": 1.6101738088935325e-05, "loss": 0.8134, "step": 5349 }, { "epoch": 0.3125, "grad_norm": 2.0496912002563477, "learning_rate": 1.610023913474493e-05, "loss": 0.854, "step": 5350 }, { "epoch": 0.31255841121495326, "grad_norm": 1.1558408737182617, "learning_rate": 1.609873996222297e-05, "loss": 0.914, "step": 5351 }, { "epoch": 0.3126168224299065, "grad_norm": 1.3747800588607788, "learning_rate": 1.6097240571423092e-05, "loss": 0.8855, "step": 5352 }, { "epoch": 0.31267523364485983, "grad_norm": 1.1923857927322388, "learning_rate": 1.609574096239897e-05, "loss": 0.8699, "step": 5353 }, { "epoch": 0.3127336448598131, "grad_norm": 1.5420888662338257, "learning_rate": 1.6094241135204264e-05, "loss": 0.8336, "step": 5354 }, { "epoch": 0.31279205607476634, "grad_norm": 1.230438232421875, "learning_rate": 1.6092741089892664e-05, "loss": 0.8285, "step": 5355 }, { "epoch": 0.3128504672897196, "grad_norm": 1.1613318920135498, "learning_rate": 1.6091240826517855e-05, "loss": 0.7766, "step": 5356 }, { "epoch": 0.3129088785046729, "grad_norm": 1.334412693977356, "learning_rate": 1.608974034513353e-05, "loss": 0.6396, "step": 5357 }, { "epoch": 0.3129672897196262, "grad_norm": 1.2005431652069092, "learning_rate": 1.60882396457934e-05, "loss": 0.8264, "step": 5358 }, { "epoch": 0.31302570093457943, "grad_norm": 1.0205386877059937, "learning_rate": 1.6086738728551165e-05, "loss": 0.6815, "step": 5359 }, { "epoch": 0.3130841121495327, "grad_norm": 1.1590023040771484, "learning_rate": 1.6085237593460544e-05, "loss": 0.9779, "step": 5360 }, { "epoch": 0.313142523364486, "grad_norm": 1.310137152671814, "learning_rate": 1.6083736240575275e-05, "loss": 0.9039, "step": 5361 }, { "epoch": 0.31320093457943926, "grad_norm": 1.5105066299438477, "learning_rate": 1.6082234669949085e-05, "loss": 0.978, "step": 5362 }, { "epoch": 0.3132593457943925, "grad_norm": 2.3262760639190674, "learning_rate": 1.6080732881635718e-05, "loss": 0.7626, "step": 5363 }, { "epoch": 0.3133177570093458, "grad_norm": 1.1182644367218018, "learning_rate": 1.6079230875688918e-05, "loss": 0.7659, "step": 5364 }, { "epoch": 0.3133761682242991, "grad_norm": 1.4240111112594604, "learning_rate": 1.6077728652162454e-05, "loss": 0.8167, "step": 5365 }, { "epoch": 0.31343457943925235, "grad_norm": 1.9419625997543335, "learning_rate": 1.6076226211110082e-05, "loss": 0.8178, "step": 5366 }, { "epoch": 0.3134929906542056, "grad_norm": 3.075143814086914, "learning_rate": 1.607472355258558e-05, "loss": 1.0427, "step": 5367 }, { "epoch": 0.31355140186915886, "grad_norm": 1.2176666259765625, "learning_rate": 1.6073220676642724e-05, "loss": 0.7194, "step": 5368 }, { "epoch": 0.3136098130841122, "grad_norm": 1.386294960975647, "learning_rate": 1.6071717583335315e-05, "loss": 0.7024, "step": 5369 }, { "epoch": 0.31366822429906543, "grad_norm": 2.3888020515441895, "learning_rate": 1.6070214272717134e-05, "loss": 0.8939, "step": 5370 }, { "epoch": 0.3137266355140187, "grad_norm": 1.1338402032852173, "learning_rate": 1.6068710744841995e-05, "loss": 0.8836, "step": 5371 }, { "epoch": 0.31378504672897195, "grad_norm": 1.4970606565475464, "learning_rate": 1.606720699976371e-05, "loss": 0.726, "step": 5372 }, { "epoch": 0.3138434579439252, "grad_norm": 1.6283382177352905, "learning_rate": 1.6065703037536095e-05, "loss": 0.9983, "step": 5373 }, { "epoch": 0.3139018691588785, "grad_norm": 1.6775436401367188, "learning_rate": 1.6064198858212978e-05, "loss": 0.8938, "step": 5374 }, { "epoch": 0.3139602803738318, "grad_norm": 1.3800113201141357, "learning_rate": 1.60626944618482e-05, "loss": 0.8181, "step": 5375 }, { "epoch": 0.31401869158878504, "grad_norm": 1.3075724840164185, "learning_rate": 1.6061189848495598e-05, "loss": 0.8554, "step": 5376 }, { "epoch": 0.3140771028037383, "grad_norm": 1.753824234008789, "learning_rate": 1.605968501820903e-05, "loss": 0.8201, "step": 5377 }, { "epoch": 0.3141355140186916, "grad_norm": 1.2147393226623535, "learning_rate": 1.605817997104235e-05, "loss": 0.6758, "step": 5378 }, { "epoch": 0.31419392523364487, "grad_norm": 1.8362380266189575, "learning_rate": 1.6056674707049423e-05, "loss": 0.8908, "step": 5379 }, { "epoch": 0.3142523364485981, "grad_norm": 1.607314944267273, "learning_rate": 1.6055169226284127e-05, "loss": 0.8229, "step": 5380 }, { "epoch": 0.3143107476635514, "grad_norm": 1.7435626983642578, "learning_rate": 1.6053663528800342e-05, "loss": 0.8759, "step": 5381 }, { "epoch": 0.3143691588785047, "grad_norm": 1.0616459846496582, "learning_rate": 1.6052157614651963e-05, "loss": 0.7711, "step": 5382 }, { "epoch": 0.31442757009345795, "grad_norm": 1.50250244140625, "learning_rate": 1.605065148389288e-05, "loss": 0.745, "step": 5383 }, { "epoch": 0.3144859813084112, "grad_norm": 1.1427699327468872, "learning_rate": 1.6049145136577004e-05, "loss": 0.6515, "step": 5384 }, { "epoch": 0.31454439252336447, "grad_norm": 1.268442153930664, "learning_rate": 1.6047638572758244e-05, "loss": 0.729, "step": 5385 }, { "epoch": 0.3146028037383178, "grad_norm": 1.4731550216674805, "learning_rate": 1.6046131792490524e-05, "loss": 0.8711, "step": 5386 }, { "epoch": 0.31466121495327104, "grad_norm": 1.14811110496521, "learning_rate": 1.6044624795827774e-05, "loss": 0.9991, "step": 5387 }, { "epoch": 0.3147196261682243, "grad_norm": 1.1389036178588867, "learning_rate": 1.6043117582823925e-05, "loss": 0.8833, "step": 5388 }, { "epoch": 0.31477803738317756, "grad_norm": 1.7629570960998535, "learning_rate": 1.6041610153532924e-05, "loss": 0.9085, "step": 5389 }, { "epoch": 0.3148364485981308, "grad_norm": 1.329829454421997, "learning_rate": 1.6040102508008726e-05, "loss": 0.7684, "step": 5390 }, { "epoch": 0.3148948598130841, "grad_norm": 1.1196916103363037, "learning_rate": 1.6038594646305285e-05, "loss": 0.8866, "step": 5391 }, { "epoch": 0.3149532710280374, "grad_norm": 1.4719561338424683, "learning_rate": 1.6037086568476575e-05, "loss": 1.0831, "step": 5392 }, { "epoch": 0.31501168224299064, "grad_norm": 1.3668429851531982, "learning_rate": 1.603557827457656e-05, "loss": 1.0039, "step": 5393 }, { "epoch": 0.3150700934579439, "grad_norm": 1.473771095275879, "learning_rate": 1.603406976465924e-05, "loss": 0.8724, "step": 5394 }, { "epoch": 0.3151285046728972, "grad_norm": 1.5427424907684326, "learning_rate": 1.6032561038778588e-05, "loss": 0.8973, "step": 5395 }, { "epoch": 0.31518691588785047, "grad_norm": 1.535618782043457, "learning_rate": 1.603105209698861e-05, "loss": 0.8164, "step": 5396 }, { "epoch": 0.31524532710280373, "grad_norm": 1.1336063146591187, "learning_rate": 1.6029542939343317e-05, "loss": 0.8415, "step": 5397 }, { "epoch": 0.315303738317757, "grad_norm": 1.1065641641616821, "learning_rate": 1.6028033565896715e-05, "loss": 0.8635, "step": 5398 }, { "epoch": 0.3153621495327103, "grad_norm": 1.5426400899887085, "learning_rate": 1.602652397670283e-05, "loss": 0.9217, "step": 5399 }, { "epoch": 0.31542056074766356, "grad_norm": 1.2092676162719727, "learning_rate": 1.6025014171815685e-05, "loss": 0.8294, "step": 5400 }, { "epoch": 0.3154789719626168, "grad_norm": 1.603253960609436, "learning_rate": 1.6023504151289325e-05, "loss": 0.7802, "step": 5401 }, { "epoch": 0.3155373831775701, "grad_norm": 1.897518515586853, "learning_rate": 1.602199391517779e-05, "loss": 0.7804, "step": 5402 }, { "epoch": 0.3155957943925234, "grad_norm": 1.3804978132247925, "learning_rate": 1.6020483463535132e-05, "loss": 0.9804, "step": 5403 }, { "epoch": 0.31565420560747665, "grad_norm": 1.1062949895858765, "learning_rate": 1.6018972796415414e-05, "loss": 0.5881, "step": 5404 }, { "epoch": 0.3157126168224299, "grad_norm": 1.2956804037094116, "learning_rate": 1.60174619138727e-05, "loss": 0.985, "step": 5405 }, { "epoch": 0.31577102803738316, "grad_norm": 1.1951918601989746, "learning_rate": 1.601595081596107e-05, "loss": 0.8275, "step": 5406 }, { "epoch": 0.3158294392523365, "grad_norm": 1.5037723779678345, "learning_rate": 1.6014439502734604e-05, "loss": 0.9277, "step": 5407 }, { "epoch": 0.31588785046728973, "grad_norm": 0.9697794914245605, "learning_rate": 1.6012927974247393e-05, "loss": 0.7524, "step": 5408 }, { "epoch": 0.315946261682243, "grad_norm": 1.5013341903686523, "learning_rate": 1.6011416230553536e-05, "loss": 0.8196, "step": 5409 }, { "epoch": 0.31600467289719625, "grad_norm": 1.3357436656951904, "learning_rate": 1.600990427170714e-05, "loss": 0.8608, "step": 5410 }, { "epoch": 0.3160630841121495, "grad_norm": 1.2043397426605225, "learning_rate": 1.600839209776232e-05, "loss": 0.8594, "step": 5411 }, { "epoch": 0.3161214953271028, "grad_norm": 1.7289164066314697, "learning_rate": 1.6006879708773193e-05, "loss": 0.9319, "step": 5412 }, { "epoch": 0.3161799065420561, "grad_norm": 1.6580047607421875, "learning_rate": 1.6005367104793894e-05, "loss": 0.8222, "step": 5413 }, { "epoch": 0.31623831775700934, "grad_norm": 1.3777885437011719, "learning_rate": 1.6003854285878558e-05, "loss": 0.8218, "step": 5414 }, { "epoch": 0.3162967289719626, "grad_norm": 1.6137996912002563, "learning_rate": 1.6002341252081328e-05, "loss": 0.7636, "step": 5415 }, { "epoch": 0.3163551401869159, "grad_norm": 2.092421770095825, "learning_rate": 1.6000828003456356e-05, "loss": 0.757, "step": 5416 }, { "epoch": 0.31641355140186916, "grad_norm": 1.2995491027832031, "learning_rate": 1.599931454005781e-05, "loss": 0.9414, "step": 5417 }, { "epoch": 0.3164719626168224, "grad_norm": 1.5250866413116455, "learning_rate": 1.5997800861939847e-05, "loss": 0.7774, "step": 5418 }, { "epoch": 0.3165303738317757, "grad_norm": 1.4168542623519897, "learning_rate": 1.599628696915665e-05, "loss": 0.827, "step": 5419 }, { "epoch": 0.316588785046729, "grad_norm": 1.8926961421966553, "learning_rate": 1.59947728617624e-05, "loss": 0.8416, "step": 5420 }, { "epoch": 0.31664719626168225, "grad_norm": 1.9466928243637085, "learning_rate": 1.5993258539811285e-05, "loss": 0.9921, "step": 5421 }, { "epoch": 0.3167056074766355, "grad_norm": 2.095400810241699, "learning_rate": 1.5991744003357508e-05, "loss": 0.9238, "step": 5422 }, { "epoch": 0.31676401869158877, "grad_norm": 1.8012231588363647, "learning_rate": 1.5990229252455274e-05, "loss": 0.7747, "step": 5423 }, { "epoch": 0.3168224299065421, "grad_norm": 1.586301326751709, "learning_rate": 1.5988714287158796e-05, "loss": 0.7774, "step": 5424 }, { "epoch": 0.31688084112149534, "grad_norm": 2.225520610809326, "learning_rate": 1.5987199107522297e-05, "loss": 0.9118, "step": 5425 }, { "epoch": 0.3169392523364486, "grad_norm": 2.570521593093872, "learning_rate": 1.59856837136e-05, "loss": 0.8989, "step": 5426 }, { "epoch": 0.31699766355140185, "grad_norm": 1.9931269884109497, "learning_rate": 1.5984168105446153e-05, "loss": 0.8336, "step": 5427 }, { "epoch": 0.31705607476635517, "grad_norm": 1.1492798328399658, "learning_rate": 1.5982652283114993e-05, "loss": 0.7984, "step": 5428 }, { "epoch": 0.3171144859813084, "grad_norm": 1.8661746978759766, "learning_rate": 1.5981136246660772e-05, "loss": 0.6881, "step": 5429 }, { "epoch": 0.3171728971962617, "grad_norm": 1.4884040355682373, "learning_rate": 1.5979619996137757e-05, "loss": 0.6869, "step": 5430 }, { "epoch": 0.31723130841121494, "grad_norm": 1.8969043493270874, "learning_rate": 1.597810353160021e-05, "loss": 0.8359, "step": 5431 }, { "epoch": 0.3172897196261682, "grad_norm": 1.6706753969192505, "learning_rate": 1.5976586853102403e-05, "loss": 0.8077, "step": 5432 }, { "epoch": 0.3173481308411215, "grad_norm": 1.0056241750717163, "learning_rate": 1.5975069960698623e-05, "loss": 0.7575, "step": 5433 }, { "epoch": 0.31740654205607477, "grad_norm": 1.429147720336914, "learning_rate": 1.5973552854443162e-05, "loss": 0.8464, "step": 5434 }, { "epoch": 0.317464953271028, "grad_norm": 1.6092445850372314, "learning_rate": 1.597203553439032e-05, "loss": 0.7032, "step": 5435 }, { "epoch": 0.3175233644859813, "grad_norm": 1.3008320331573486, "learning_rate": 1.5970518000594392e-05, "loss": 0.7645, "step": 5436 }, { "epoch": 0.3175817757009346, "grad_norm": 1.25498366355896, "learning_rate": 1.5969000253109707e-05, "loss": 0.7316, "step": 5437 }, { "epoch": 0.31764018691588786, "grad_norm": 1.3644644021987915, "learning_rate": 1.5967482291990573e-05, "loss": 0.5921, "step": 5438 }, { "epoch": 0.3176985981308411, "grad_norm": 1.5534272193908691, "learning_rate": 1.5965964117291326e-05, "loss": 0.946, "step": 5439 }, { "epoch": 0.3177570093457944, "grad_norm": 1.7917250394821167, "learning_rate": 1.59644457290663e-05, "loss": 0.7868, "step": 5440 }, { "epoch": 0.3178154205607477, "grad_norm": 1.5181114673614502, "learning_rate": 1.5962927127369838e-05, "loss": 0.7821, "step": 5441 }, { "epoch": 0.31787383177570094, "grad_norm": 1.1829402446746826, "learning_rate": 1.59614083122563e-05, "loss": 0.8684, "step": 5442 }, { "epoch": 0.3179322429906542, "grad_norm": 1.132317066192627, "learning_rate": 1.595988928378003e-05, "loss": 0.8053, "step": 5443 }, { "epoch": 0.31799065420560746, "grad_norm": 1.8963253498077393, "learning_rate": 1.5958370041995406e-05, "loss": 0.9815, "step": 5444 }, { "epoch": 0.3180490654205608, "grad_norm": 1.4164316654205322, "learning_rate": 1.5956850586956803e-05, "loss": 0.7821, "step": 5445 }, { "epoch": 0.31810747663551403, "grad_norm": 1.483526587486267, "learning_rate": 1.59553309187186e-05, "loss": 0.8247, "step": 5446 }, { "epoch": 0.3181658878504673, "grad_norm": 1.203002691268921, "learning_rate": 1.595381103733519e-05, "loss": 0.6779, "step": 5447 }, { "epoch": 0.31822429906542055, "grad_norm": 1.6388866901397705, "learning_rate": 1.5952290942860965e-05, "loss": 0.9576, "step": 5448 }, { "epoch": 0.31828271028037386, "grad_norm": 1.176716685295105, "learning_rate": 1.5950770635350338e-05, "loss": 0.9152, "step": 5449 }, { "epoch": 0.3183411214953271, "grad_norm": 1.6226260662078857, "learning_rate": 1.594925011485771e-05, "loss": 0.9424, "step": 5450 }, { "epoch": 0.3183995327102804, "grad_norm": 1.1976113319396973, "learning_rate": 1.5947729381437512e-05, "loss": 0.8657, "step": 5451 }, { "epoch": 0.31845794392523363, "grad_norm": 1.2859708070755005, "learning_rate": 1.594620843514417e-05, "loss": 1.0091, "step": 5452 }, { "epoch": 0.3185163551401869, "grad_norm": 1.4570425748825073, "learning_rate": 1.5944687276032118e-05, "loss": 1.051, "step": 5453 }, { "epoch": 0.3185747663551402, "grad_norm": 1.327363133430481, "learning_rate": 1.5943165904155803e-05, "loss": 0.8935, "step": 5454 }, { "epoch": 0.31863317757009346, "grad_norm": 1.8207756280899048, "learning_rate": 1.5941644319569665e-05, "loss": 0.9105, "step": 5455 }, { "epoch": 0.3186915887850467, "grad_norm": 1.0479695796966553, "learning_rate": 1.5940122522328176e-05, "loss": 0.8179, "step": 5456 }, { "epoch": 0.31875, "grad_norm": 1.9800364971160889, "learning_rate": 1.5938600512485792e-05, "loss": 0.9817, "step": 5457 }, { "epoch": 0.3188084112149533, "grad_norm": 1.8400225639343262, "learning_rate": 1.5937078290096994e-05, "loss": 1.0592, "step": 5458 }, { "epoch": 0.31886682242990655, "grad_norm": 1.5391223430633545, "learning_rate": 1.5935555855216262e-05, "loss": 0.8478, "step": 5459 }, { "epoch": 0.3189252336448598, "grad_norm": 1.0672171115875244, "learning_rate": 1.593403320789808e-05, "loss": 0.7772, "step": 5460 }, { "epoch": 0.31898364485981306, "grad_norm": 1.4608789682388306, "learning_rate": 1.5932510348196946e-05, "loss": 0.8874, "step": 5461 }, { "epoch": 0.3190420560747664, "grad_norm": 1.1496161222457886, "learning_rate": 1.593098727616737e-05, "loss": 1.0227, "step": 5462 }, { "epoch": 0.31910046728971964, "grad_norm": 1.0920804738998413, "learning_rate": 1.5929463991863858e-05, "loss": 0.8471, "step": 5463 }, { "epoch": 0.3191588785046729, "grad_norm": 1.5265908241271973, "learning_rate": 1.5927940495340934e-05, "loss": 0.8446, "step": 5464 }, { "epoch": 0.31921728971962615, "grad_norm": 1.2075221538543701, "learning_rate": 1.5926416786653116e-05, "loss": 0.8344, "step": 5465 }, { "epoch": 0.31927570093457946, "grad_norm": 1.3574137687683105, "learning_rate": 1.5924892865854946e-05, "loss": 0.8263, "step": 5466 }, { "epoch": 0.3193341121495327, "grad_norm": 1.4055891036987305, "learning_rate": 1.5923368733000967e-05, "loss": 0.7337, "step": 5467 }, { "epoch": 0.319392523364486, "grad_norm": 1.1806451082229614, "learning_rate": 1.5921844388145727e-05, "loss": 0.9645, "step": 5468 }, { "epoch": 0.31945093457943924, "grad_norm": 1.4411327838897705, "learning_rate": 1.592031983134378e-05, "loss": 0.7069, "step": 5469 }, { "epoch": 0.3195093457943925, "grad_norm": 1.3930861949920654, "learning_rate": 1.5918795062649698e-05, "loss": 0.7206, "step": 5470 }, { "epoch": 0.3195677570093458, "grad_norm": 1.492822527885437, "learning_rate": 1.5917270082118044e-05, "loss": 0.9019, "step": 5471 }, { "epoch": 0.31962616822429907, "grad_norm": 1.238291621208191, "learning_rate": 1.5915744889803403e-05, "loss": 0.7482, "step": 5472 }, { "epoch": 0.3196845794392523, "grad_norm": 0.8695330619812012, "learning_rate": 1.5914219485760364e-05, "loss": 0.6511, "step": 5473 }, { "epoch": 0.3197429906542056, "grad_norm": 1.0572607517242432, "learning_rate": 1.5912693870043524e-05, "loss": 0.5977, "step": 5474 }, { "epoch": 0.3198014018691589, "grad_norm": 1.2589645385742188, "learning_rate": 1.591116804270748e-05, "loss": 0.7603, "step": 5475 }, { "epoch": 0.31985981308411215, "grad_norm": 1.382456660270691, "learning_rate": 1.5909642003806846e-05, "loss": 0.808, "step": 5476 }, { "epoch": 0.3199182242990654, "grad_norm": 1.579732894897461, "learning_rate": 1.5908115753396235e-05, "loss": 0.8631, "step": 5477 }, { "epoch": 0.31997663551401867, "grad_norm": 1.315369725227356, "learning_rate": 1.5906589291530283e-05, "loss": 0.6911, "step": 5478 }, { "epoch": 0.320035046728972, "grad_norm": 1.0918986797332764, "learning_rate": 1.5905062618263613e-05, "loss": 0.6169, "step": 5479 }, { "epoch": 0.32009345794392524, "grad_norm": 1.3303712606430054, "learning_rate": 1.590353573365087e-05, "loss": 0.9852, "step": 5480 }, { "epoch": 0.3201518691588785, "grad_norm": 1.3900961875915527, "learning_rate": 1.59020086377467e-05, "loss": 0.8977, "step": 5481 }, { "epoch": 0.32021028037383176, "grad_norm": 0.9736801981925964, "learning_rate": 1.5900481330605764e-05, "loss": 0.8149, "step": 5482 }, { "epoch": 0.32026869158878507, "grad_norm": 1.884910225868225, "learning_rate": 1.589895381228272e-05, "loss": 0.7565, "step": 5483 }, { "epoch": 0.32032710280373833, "grad_norm": 1.277385950088501, "learning_rate": 1.5897426082832235e-05, "loss": 0.8523, "step": 5484 }, { "epoch": 0.3203855140186916, "grad_norm": 1.2683032751083374, "learning_rate": 1.5895898142309e-05, "loss": 0.7522, "step": 5485 }, { "epoch": 0.32044392523364484, "grad_norm": 1.6710152626037598, "learning_rate": 1.589436999076769e-05, "loss": 0.8938, "step": 5486 }, { "epoch": 0.32050233644859816, "grad_norm": 3.544240713119507, "learning_rate": 1.5892841628263002e-05, "loss": 0.764, "step": 5487 }, { "epoch": 0.3205607476635514, "grad_norm": 1.4624725580215454, "learning_rate": 1.5891313054849643e-05, "loss": 0.6867, "step": 5488 }, { "epoch": 0.3206191588785047, "grad_norm": 1.6783607006072998, "learning_rate": 1.588978427058231e-05, "loss": 0.9107, "step": 5489 }, { "epoch": 0.32067757009345793, "grad_norm": 1.4775437116622925, "learning_rate": 1.5888255275515727e-05, "loss": 0.8022, "step": 5490 }, { "epoch": 0.3207359813084112, "grad_norm": 1.7841894626617432, "learning_rate": 1.5886726069704617e-05, "loss": 0.8315, "step": 5491 }, { "epoch": 0.3207943925233645, "grad_norm": 1.6077404022216797, "learning_rate": 1.5885196653203712e-05, "loss": 0.8781, "step": 5492 }, { "epoch": 0.32085280373831776, "grad_norm": 2.252760171890259, "learning_rate": 1.5883667026067745e-05, "loss": 0.9672, "step": 5493 }, { "epoch": 0.320911214953271, "grad_norm": 1.5642982721328735, "learning_rate": 1.588213718835147e-05, "loss": 0.9362, "step": 5494 }, { "epoch": 0.3209696261682243, "grad_norm": 3.8366942405700684, "learning_rate": 1.5880607140109635e-05, "loss": 0.9872, "step": 5495 }, { "epoch": 0.3210280373831776, "grad_norm": 1.520806908607483, "learning_rate": 1.5879076881397006e-05, "loss": 0.8678, "step": 5496 }, { "epoch": 0.32108644859813085, "grad_norm": 1.4436315298080444, "learning_rate": 1.5877546412268348e-05, "loss": 0.9024, "step": 5497 }, { "epoch": 0.3211448598130841, "grad_norm": 1.6651898622512817, "learning_rate": 1.587601573277844e-05, "loss": 0.884, "step": 5498 }, { "epoch": 0.32120327102803736, "grad_norm": 1.5073322057724, "learning_rate": 1.5874484842982068e-05, "loss": 0.6155, "step": 5499 }, { "epoch": 0.3212616822429907, "grad_norm": 1.4284191131591797, "learning_rate": 1.5872953742934018e-05, "loss": 0.7968, "step": 5500 }, { "epoch": 0.32132009345794393, "grad_norm": 1.366506576538086, "learning_rate": 1.587142243268909e-05, "loss": 0.8827, "step": 5501 }, { "epoch": 0.3213785046728972, "grad_norm": 0.9061498641967773, "learning_rate": 1.5869890912302096e-05, "loss": 0.8193, "step": 5502 }, { "epoch": 0.32143691588785045, "grad_norm": 1.176295280456543, "learning_rate": 1.5868359181827846e-05, "loss": 0.9309, "step": 5503 }, { "epoch": 0.32149532710280376, "grad_norm": 1.348198652267456, "learning_rate": 1.5866827241321163e-05, "loss": 0.7911, "step": 5504 }, { "epoch": 0.321553738317757, "grad_norm": 1.3205684423446655, "learning_rate": 1.5865295090836875e-05, "loss": 0.7168, "step": 5505 }, { "epoch": 0.3216121495327103, "grad_norm": 1.4132320880889893, "learning_rate": 1.5863762730429817e-05, "loss": 0.8742, "step": 5506 }, { "epoch": 0.32167056074766354, "grad_norm": 1.1251424551010132, "learning_rate": 1.586223016015484e-05, "loss": 0.9495, "step": 5507 }, { "epoch": 0.32172897196261685, "grad_norm": 0.856122612953186, "learning_rate": 1.5860697380066788e-05, "loss": 0.6927, "step": 5508 }, { "epoch": 0.3217873831775701, "grad_norm": 1.317954659461975, "learning_rate": 1.5859164390220524e-05, "loss": 0.8255, "step": 5509 }, { "epoch": 0.32184579439252337, "grad_norm": 1.1920292377471924, "learning_rate": 1.585763119067091e-05, "loss": 0.773, "step": 5510 }, { "epoch": 0.3219042056074766, "grad_norm": 1.326413869857788, "learning_rate": 1.585609778147283e-05, "loss": 0.8873, "step": 5511 }, { "epoch": 0.3219626168224299, "grad_norm": 1.1427581310272217, "learning_rate": 1.585456416268116e-05, "loss": 0.6808, "step": 5512 }, { "epoch": 0.3220210280373832, "grad_norm": 1.73739492893219, "learning_rate": 1.5853030334350787e-05, "loss": 0.8344, "step": 5513 }, { "epoch": 0.32207943925233645, "grad_norm": 1.4587452411651611, "learning_rate": 1.5851496296536607e-05, "loss": 1.0327, "step": 5514 }, { "epoch": 0.3221378504672897, "grad_norm": 1.51870858669281, "learning_rate": 1.584996204929353e-05, "loss": 0.7661, "step": 5515 }, { "epoch": 0.32219626168224297, "grad_norm": 1.329746127128601, "learning_rate": 1.5848427592676464e-05, "loss": 0.7309, "step": 5516 }, { "epoch": 0.3222546728971963, "grad_norm": 1.6494683027267456, "learning_rate": 1.584689292674033e-05, "loss": 0.8277, "step": 5517 }, { "epoch": 0.32231308411214954, "grad_norm": 1.3989149332046509, "learning_rate": 1.5845358051540055e-05, "loss": 0.8517, "step": 5518 }, { "epoch": 0.3223714953271028, "grad_norm": 1.3210660219192505, "learning_rate": 1.584382296713057e-05, "loss": 0.9666, "step": 5519 }, { "epoch": 0.32242990654205606, "grad_norm": 1.2552520036697388, "learning_rate": 1.5842287673566817e-05, "loss": 0.8787, "step": 5520 }, { "epoch": 0.32248831775700937, "grad_norm": 1.463607907295227, "learning_rate": 1.5840752170903752e-05, "loss": 0.8714, "step": 5521 }, { "epoch": 0.3225467289719626, "grad_norm": 1.4994152784347534, "learning_rate": 1.5839216459196323e-05, "loss": 0.9196, "step": 5522 }, { "epoch": 0.3226051401869159, "grad_norm": 2.4258792400360107, "learning_rate": 1.5837680538499497e-05, "loss": 0.8384, "step": 5523 }, { "epoch": 0.32266355140186914, "grad_norm": 1.3322969675064087, "learning_rate": 1.5836144408868248e-05, "loss": 0.822, "step": 5524 }, { "epoch": 0.32272196261682246, "grad_norm": 1.428139328956604, "learning_rate": 1.5834608070357553e-05, "loss": 0.8356, "step": 5525 }, { "epoch": 0.3227803738317757, "grad_norm": 2.1907389163970947, "learning_rate": 1.5833071523022397e-05, "loss": 0.8546, "step": 5526 }, { "epoch": 0.32283878504672897, "grad_norm": 1.324329137802124, "learning_rate": 1.583153476691778e-05, "loss": 0.8637, "step": 5527 }, { "epoch": 0.32289719626168223, "grad_norm": 1.3752425909042358, "learning_rate": 1.5829997802098694e-05, "loss": 0.7721, "step": 5528 }, { "epoch": 0.3229556074766355, "grad_norm": 1.4925113916397095, "learning_rate": 1.582846062862016e-05, "loss": 0.7764, "step": 5529 }, { "epoch": 0.3230140186915888, "grad_norm": 1.8383159637451172, "learning_rate": 1.582692324653718e-05, "loss": 0.9795, "step": 5530 }, { "epoch": 0.32307242990654206, "grad_norm": 1.747615098953247, "learning_rate": 1.582538565590479e-05, "loss": 0.9293, "step": 5531 }, { "epoch": 0.3231308411214953, "grad_norm": 1.2839034795761108, "learning_rate": 1.5823847856778015e-05, "loss": 0.6911, "step": 5532 }, { "epoch": 0.3231892523364486, "grad_norm": 1.3658815622329712, "learning_rate": 1.58223098492119e-05, "loss": 1.0187, "step": 5533 }, { "epoch": 0.3232476635514019, "grad_norm": 1.3621832132339478, "learning_rate": 1.5820771633261483e-05, "loss": 0.783, "step": 5534 }, { "epoch": 0.32330607476635514, "grad_norm": 1.2581121921539307, "learning_rate": 1.5819233208981825e-05, "loss": 0.8518, "step": 5535 }, { "epoch": 0.3233644859813084, "grad_norm": 0.9507858753204346, "learning_rate": 1.5817694576427984e-05, "loss": 0.8341, "step": 5536 }, { "epoch": 0.32342289719626166, "grad_norm": 1.2913422584533691, "learning_rate": 1.5816155735655026e-05, "loss": 0.7277, "step": 5537 }, { "epoch": 0.323481308411215, "grad_norm": 1.2084136009216309, "learning_rate": 1.5814616686718033e-05, "loss": 0.8635, "step": 5538 }, { "epoch": 0.32353971962616823, "grad_norm": 1.299179196357727, "learning_rate": 1.5813077429672082e-05, "loss": 0.6971, "step": 5539 }, { "epoch": 0.3235981308411215, "grad_norm": 1.5699663162231445, "learning_rate": 1.581153796457227e-05, "loss": 0.7477, "step": 5540 }, { "epoch": 0.32365654205607475, "grad_norm": 1.3745914697647095, "learning_rate": 1.5809998291473694e-05, "loss": 0.8348, "step": 5541 }, { "epoch": 0.32371495327102806, "grad_norm": 1.418288230895996, "learning_rate": 1.580845841043146e-05, "loss": 0.919, "step": 5542 }, { "epoch": 0.3237733644859813, "grad_norm": 1.2636445760726929, "learning_rate": 1.5806918321500678e-05, "loss": 0.8658, "step": 5543 }, { "epoch": 0.3238317757009346, "grad_norm": 1.6091030836105347, "learning_rate": 1.580537802473647e-05, "loss": 0.67, "step": 5544 }, { "epoch": 0.32389018691588783, "grad_norm": 1.2218654155731201, "learning_rate": 1.580383752019397e-05, "loss": 0.8756, "step": 5545 }, { "epoch": 0.32394859813084115, "grad_norm": 1.2445954084396362, "learning_rate": 1.5802296807928304e-05, "loss": 0.9063, "step": 5546 }, { "epoch": 0.3240070093457944, "grad_norm": 1.35776686668396, "learning_rate": 1.5800755887994624e-05, "loss": 0.9028, "step": 5547 }, { "epoch": 0.32406542056074766, "grad_norm": 1.4168708324432373, "learning_rate": 1.5799214760448075e-05, "loss": 0.8444, "step": 5548 }, { "epoch": 0.3241238317757009, "grad_norm": 1.4514226913452148, "learning_rate": 1.5797673425343814e-05, "loss": 0.7592, "step": 5549 }, { "epoch": 0.3241822429906542, "grad_norm": 1.1743417978286743, "learning_rate": 1.5796131882737013e-05, "loss": 0.7462, "step": 5550 }, { "epoch": 0.3242406542056075, "grad_norm": 2.033432960510254, "learning_rate": 1.5794590132682838e-05, "loss": 0.7811, "step": 5551 }, { "epoch": 0.32429906542056075, "grad_norm": 0.9536598324775696, "learning_rate": 1.5793048175236477e-05, "loss": 0.7372, "step": 5552 }, { "epoch": 0.324357476635514, "grad_norm": 2.0302627086639404, "learning_rate": 1.5791506010453107e-05, "loss": 0.8559, "step": 5553 }, { "epoch": 0.32441588785046727, "grad_norm": 1.9856408834457397, "learning_rate": 1.578996363838793e-05, "loss": 0.8506, "step": 5554 }, { "epoch": 0.3244742990654206, "grad_norm": 2.276047468185425, "learning_rate": 1.578842105909615e-05, "loss": 0.9611, "step": 5555 }, { "epoch": 0.32453271028037384, "grad_norm": 1.209254503250122, "learning_rate": 1.5786878272632976e-05, "loss": 0.8722, "step": 5556 }, { "epoch": 0.3245911214953271, "grad_norm": 1.7294076681137085, "learning_rate": 1.578533527905362e-05, "loss": 1.1498, "step": 5557 }, { "epoch": 0.32464953271028035, "grad_norm": 1.254178524017334, "learning_rate": 1.578379207841331e-05, "loss": 0.7726, "step": 5558 }, { "epoch": 0.32470794392523367, "grad_norm": 1.6485716104507446, "learning_rate": 1.578224867076728e-05, "loss": 0.9813, "step": 5559 }, { "epoch": 0.3247663551401869, "grad_norm": 1.2409510612487793, "learning_rate": 1.5780705056170766e-05, "loss": 1.0506, "step": 5560 }, { "epoch": 0.3248247663551402, "grad_norm": 1.529165267944336, "learning_rate": 1.5779161234679023e-05, "loss": 0.8234, "step": 5561 }, { "epoch": 0.32488317757009344, "grad_norm": 2.249023675918579, "learning_rate": 1.5777617206347295e-05, "loss": 0.9131, "step": 5562 }, { "epoch": 0.32494158878504675, "grad_norm": 1.5860211849212646, "learning_rate": 1.577607297123085e-05, "loss": 0.7586, "step": 5563 }, { "epoch": 0.325, "grad_norm": 2.7870755195617676, "learning_rate": 1.5774528529384953e-05, "loss": 0.7723, "step": 5564 }, { "epoch": 0.32505841121495327, "grad_norm": 1.405536413192749, "learning_rate": 1.5772983880864886e-05, "loss": 0.8569, "step": 5565 }, { "epoch": 0.3251168224299065, "grad_norm": 1.995897889137268, "learning_rate": 1.5771439025725928e-05, "loss": 0.8186, "step": 5566 }, { "epoch": 0.32517523364485984, "grad_norm": 1.730050802230835, "learning_rate": 1.5769893964023373e-05, "loss": 0.7841, "step": 5567 }, { "epoch": 0.3252336448598131, "grad_norm": 1.8944584131240845, "learning_rate": 1.576834869581252e-05, "loss": 0.9664, "step": 5568 }, { "epoch": 0.32529205607476636, "grad_norm": 1.9765485525131226, "learning_rate": 1.5766803221148676e-05, "loss": 0.8039, "step": 5569 }, { "epoch": 0.3253504672897196, "grad_norm": 1.304598093032837, "learning_rate": 1.576525754008715e-05, "loss": 0.9249, "step": 5570 }, { "epoch": 0.32540887850467287, "grad_norm": 1.5851699113845825, "learning_rate": 1.5763711652683263e-05, "loss": 0.9123, "step": 5571 }, { "epoch": 0.3254672897196262, "grad_norm": 1.6178717613220215, "learning_rate": 1.5762165558992354e-05, "loss": 0.8512, "step": 5572 }, { "epoch": 0.32552570093457944, "grad_norm": 1.506073236465454, "learning_rate": 1.5760619259069745e-05, "loss": 0.8227, "step": 5573 }, { "epoch": 0.3255841121495327, "grad_norm": 1.9087066650390625, "learning_rate": 1.5759072752970785e-05, "loss": 0.9563, "step": 5574 }, { "epoch": 0.32564252336448596, "grad_norm": 1.6489436626434326, "learning_rate": 1.575752604075083e-05, "loss": 0.7945, "step": 5575 }, { "epoch": 0.32570093457943927, "grad_norm": 1.1822131872177124, "learning_rate": 1.5755979122465225e-05, "loss": 0.8264, "step": 5576 }, { "epoch": 0.32575934579439253, "grad_norm": 1.4920443296432495, "learning_rate": 1.575443199816935e-05, "loss": 0.903, "step": 5577 }, { "epoch": 0.3258177570093458, "grad_norm": 1.796227216720581, "learning_rate": 1.5752884667918563e-05, "loss": 0.8193, "step": 5578 }, { "epoch": 0.32587616822429905, "grad_norm": 1.6562753915786743, "learning_rate": 1.5751337131768258e-05, "loss": 1.0748, "step": 5579 }, { "epoch": 0.32593457943925236, "grad_norm": 1.0631020069122314, "learning_rate": 1.574978938977381e-05, "loss": 0.7518, "step": 5580 }, { "epoch": 0.3259929906542056, "grad_norm": 1.198557734489441, "learning_rate": 1.5748241441990623e-05, "loss": 0.7247, "step": 5581 }, { "epoch": 0.3260514018691589, "grad_norm": 1.3294751644134521, "learning_rate": 1.5746693288474093e-05, "loss": 0.7132, "step": 5582 }, { "epoch": 0.32610981308411213, "grad_norm": 1.198456883430481, "learning_rate": 1.5745144929279633e-05, "loss": 0.7585, "step": 5583 }, { "epoch": 0.32616822429906545, "grad_norm": 1.4224056005477905, "learning_rate": 1.574359636446266e-05, "loss": 0.6561, "step": 5584 }, { "epoch": 0.3262266355140187, "grad_norm": 1.2373571395874023, "learning_rate": 1.5742047594078594e-05, "loss": 0.7008, "step": 5585 }, { "epoch": 0.32628504672897196, "grad_norm": 1.8516491651535034, "learning_rate": 1.5740498618182867e-05, "loss": 0.9969, "step": 5586 }, { "epoch": 0.3263434579439252, "grad_norm": 1.1823832988739014, "learning_rate": 1.5738949436830924e-05, "loss": 0.8275, "step": 5587 }, { "epoch": 0.3264018691588785, "grad_norm": 1.6036806106567383, "learning_rate": 1.5737400050078203e-05, "loss": 0.9942, "step": 5588 }, { "epoch": 0.3264602803738318, "grad_norm": 1.016100525856018, "learning_rate": 1.5735850457980167e-05, "loss": 0.6956, "step": 5589 }, { "epoch": 0.32651869158878505, "grad_norm": 1.6168817281723022, "learning_rate": 1.573430066059227e-05, "loss": 0.8784, "step": 5590 }, { "epoch": 0.3265771028037383, "grad_norm": 1.5666650533676147, "learning_rate": 1.573275065796998e-05, "loss": 0.8536, "step": 5591 }, { "epoch": 0.32663551401869156, "grad_norm": 1.2182562351226807, "learning_rate": 1.5731200450168778e-05, "loss": 0.7729, "step": 5592 }, { "epoch": 0.3266939252336449, "grad_norm": 1.915880560874939, "learning_rate": 1.572965003724414e-05, "loss": 0.8071, "step": 5593 }, { "epoch": 0.32675233644859814, "grad_norm": 1.9251164197921753, "learning_rate": 1.572809941925156e-05, "loss": 0.9408, "step": 5594 }, { "epoch": 0.3268107476635514, "grad_norm": 1.869274377822876, "learning_rate": 1.572654859624654e-05, "loss": 0.8488, "step": 5595 }, { "epoch": 0.32686915887850465, "grad_norm": 1.7381136417388916, "learning_rate": 1.5724997568284573e-05, "loss": 0.7233, "step": 5596 }, { "epoch": 0.32692757009345796, "grad_norm": 1.3573943376541138, "learning_rate": 1.5723446335421186e-05, "loss": 0.735, "step": 5597 }, { "epoch": 0.3269859813084112, "grad_norm": 2.0610973834991455, "learning_rate": 1.572189489771189e-05, "loss": 0.8721, "step": 5598 }, { "epoch": 0.3270443925233645, "grad_norm": 1.188180685043335, "learning_rate": 1.5720343255212213e-05, "loss": 0.6947, "step": 5599 }, { "epoch": 0.32710280373831774, "grad_norm": 1.8774183988571167, "learning_rate": 1.5718791407977686e-05, "loss": 0.8913, "step": 5600 }, { "epoch": 0.32716121495327105, "grad_norm": 1.8762288093566895, "learning_rate": 1.5717239356063855e-05, "loss": 0.7911, "step": 5601 }, { "epoch": 0.3272196261682243, "grad_norm": 1.4229258298873901, "learning_rate": 1.571568709952627e-05, "loss": 0.6452, "step": 5602 }, { "epoch": 0.32727803738317757, "grad_norm": 2.1614325046539307, "learning_rate": 1.5714134638420485e-05, "loss": 0.8812, "step": 5603 }, { "epoch": 0.3273364485981308, "grad_norm": 1.3254512548446655, "learning_rate": 1.5712581972802067e-05, "loss": 0.9273, "step": 5604 }, { "epoch": 0.32739485981308414, "grad_norm": 1.388238787651062, "learning_rate": 1.571102910272658e-05, "loss": 0.7546, "step": 5605 }, { "epoch": 0.3274532710280374, "grad_norm": 3.7207467555999756, "learning_rate": 1.570947602824961e-05, "loss": 0.876, "step": 5606 }, { "epoch": 0.32751168224299065, "grad_norm": 1.1457701921463013, "learning_rate": 1.5707922749426735e-05, "loss": 0.7118, "step": 5607 }, { "epoch": 0.3275700934579439, "grad_norm": 3.7647812366485596, "learning_rate": 1.5706369266313557e-05, "loss": 0.8583, "step": 5608 }, { "epoch": 0.32762850467289717, "grad_norm": 1.1583834886550903, "learning_rate": 1.5704815578965668e-05, "loss": 0.6408, "step": 5609 }, { "epoch": 0.3276869158878505, "grad_norm": 1.3700482845306396, "learning_rate": 1.570326168743868e-05, "loss": 0.7621, "step": 5610 }, { "epoch": 0.32774532710280374, "grad_norm": 1.7887006998062134, "learning_rate": 1.5701707591788203e-05, "loss": 0.8214, "step": 5611 }, { "epoch": 0.327803738317757, "grad_norm": 2.0936203002929688, "learning_rate": 1.5700153292069863e-05, "loss": 0.8187, "step": 5612 }, { "epoch": 0.32786214953271026, "grad_norm": 1.5517297983169556, "learning_rate": 1.569859878833929e-05, "loss": 0.8426, "step": 5613 }, { "epoch": 0.32792056074766357, "grad_norm": 1.6134610176086426, "learning_rate": 1.5697044080652122e-05, "loss": 0.8082, "step": 5614 }, { "epoch": 0.3279789719626168, "grad_norm": 2.3488271236419678, "learning_rate": 1.5695489169063994e-05, "loss": 0.864, "step": 5615 }, { "epoch": 0.3280373831775701, "grad_norm": 1.8171954154968262, "learning_rate": 1.5693934053630567e-05, "loss": 0.9415, "step": 5616 }, { "epoch": 0.32809579439252334, "grad_norm": 1.9768050909042358, "learning_rate": 1.5692378734407498e-05, "loss": 0.9079, "step": 5617 }, { "epoch": 0.32815420560747666, "grad_norm": 1.3941574096679688, "learning_rate": 1.569082321145045e-05, "loss": 0.8288, "step": 5618 }, { "epoch": 0.3282126168224299, "grad_norm": 1.240588903427124, "learning_rate": 1.5689267484815098e-05, "loss": 0.6537, "step": 5619 }, { "epoch": 0.3282710280373832, "grad_norm": 2.236706256866455, "learning_rate": 1.5687711554557125e-05, "loss": 0.8691, "step": 5620 }, { "epoch": 0.32832943925233643, "grad_norm": 1.5440188646316528, "learning_rate": 1.568615542073221e-05, "loss": 0.7255, "step": 5621 }, { "epoch": 0.32838785046728974, "grad_norm": 1.2476558685302734, "learning_rate": 1.5684599083396055e-05, "loss": 0.8273, "step": 5622 }, { "epoch": 0.328446261682243, "grad_norm": 2.400614023208618, "learning_rate": 1.5683042542604363e-05, "loss": 0.8829, "step": 5623 }, { "epoch": 0.32850467289719626, "grad_norm": 1.8472089767456055, "learning_rate": 1.568148579841284e-05, "loss": 0.8151, "step": 5624 }, { "epoch": 0.3285630841121495, "grad_norm": 1.3853567838668823, "learning_rate": 1.5679928850877205e-05, "loss": 0.8944, "step": 5625 }, { "epoch": 0.32862149532710283, "grad_norm": 1.3079336881637573, "learning_rate": 1.5678371700053184e-05, "loss": 0.5529, "step": 5626 }, { "epoch": 0.3286799065420561, "grad_norm": 1.972366213798523, "learning_rate": 1.5676814345996507e-05, "loss": 0.8498, "step": 5627 }, { "epoch": 0.32873831775700935, "grad_norm": 1.1300711631774902, "learning_rate": 1.5675256788762907e-05, "loss": 0.8527, "step": 5628 }, { "epoch": 0.3287967289719626, "grad_norm": 1.3737081289291382, "learning_rate": 1.5673699028408136e-05, "loss": 0.635, "step": 5629 }, { "epoch": 0.32885514018691586, "grad_norm": 2.10697603225708, "learning_rate": 1.5672141064987946e-05, "loss": 0.8569, "step": 5630 }, { "epoch": 0.3289135514018692, "grad_norm": 1.311779499053955, "learning_rate": 1.5670582898558103e-05, "loss": 0.8619, "step": 5631 }, { "epoch": 0.32897196261682243, "grad_norm": 1.8225808143615723, "learning_rate": 1.5669024529174365e-05, "loss": 1.0001, "step": 5632 }, { "epoch": 0.3290303738317757, "grad_norm": 1.2413426637649536, "learning_rate": 1.5667465956892514e-05, "loss": 0.8332, "step": 5633 }, { "epoch": 0.32908878504672895, "grad_norm": 1.4955753087997437, "learning_rate": 1.5665907181768328e-05, "loss": 0.8206, "step": 5634 }, { "epoch": 0.32914719626168226, "grad_norm": 1.2392067909240723, "learning_rate": 1.56643482038576e-05, "loss": 0.8463, "step": 5635 }, { "epoch": 0.3292056074766355, "grad_norm": 1.7269022464752197, "learning_rate": 1.566278902321612e-05, "loss": 0.6375, "step": 5636 }, { "epoch": 0.3292640186915888, "grad_norm": 1.6726831197738647, "learning_rate": 1.5661229639899708e-05, "loss": 0.7338, "step": 5637 }, { "epoch": 0.32932242990654204, "grad_norm": 1.65423583984375, "learning_rate": 1.5659670053964157e-05, "loss": 0.8442, "step": 5638 }, { "epoch": 0.32938084112149535, "grad_norm": 1.7743011713027954, "learning_rate": 1.5658110265465295e-05, "loss": 0.8496, "step": 5639 }, { "epoch": 0.3294392523364486, "grad_norm": 1.1745219230651855, "learning_rate": 1.5656550274458944e-05, "loss": 0.6568, "step": 5640 }, { "epoch": 0.32949766355140186, "grad_norm": 1.4148401021957397, "learning_rate": 1.5654990081000945e-05, "loss": 0.7006, "step": 5641 }, { "epoch": 0.3295560747663551, "grad_norm": 1.5364618301391602, "learning_rate": 1.565342968514713e-05, "loss": 0.9848, "step": 5642 }, { "epoch": 0.32961448598130844, "grad_norm": 2.2106540203094482, "learning_rate": 1.565186908695335e-05, "loss": 0.9243, "step": 5643 }, { "epoch": 0.3296728971962617, "grad_norm": 1.313896894454956, "learning_rate": 1.565030828647546e-05, "loss": 0.908, "step": 5644 }, { "epoch": 0.32973130841121495, "grad_norm": 1.7021853923797607, "learning_rate": 1.564874728376932e-05, "loss": 0.7569, "step": 5645 }, { "epoch": 0.3297897196261682, "grad_norm": 1.092145323753357, "learning_rate": 1.56471860788908e-05, "loss": 0.6583, "step": 5646 }, { "epoch": 0.3298481308411215, "grad_norm": 1.3334983587265015, "learning_rate": 1.5645624671895777e-05, "loss": 0.7696, "step": 5647 }, { "epoch": 0.3299065420560748, "grad_norm": 1.377086877822876, "learning_rate": 1.5644063062840135e-05, "loss": 0.6869, "step": 5648 }, { "epoch": 0.32996495327102804, "grad_norm": 1.9835869073867798, "learning_rate": 1.5642501251779765e-05, "loss": 0.8278, "step": 5649 }, { "epoch": 0.3300233644859813, "grad_norm": 1.993971586227417, "learning_rate": 1.5640939238770566e-05, "loss": 0.8347, "step": 5650 }, { "epoch": 0.33008177570093455, "grad_norm": 1.555946707725525, "learning_rate": 1.563937702386844e-05, "loss": 0.8733, "step": 5651 }, { "epoch": 0.33014018691588787, "grad_norm": 1.6794508695602417, "learning_rate": 1.5637814607129306e-05, "loss": 0.8613, "step": 5652 }, { "epoch": 0.3301985981308411, "grad_norm": 1.6248431205749512, "learning_rate": 1.563625198860908e-05, "loss": 0.927, "step": 5653 }, { "epoch": 0.3302570093457944, "grad_norm": 1.9413126707077026, "learning_rate": 1.563468916836369e-05, "loss": 0.9308, "step": 5654 }, { "epoch": 0.33031542056074764, "grad_norm": 1.297542929649353, "learning_rate": 1.5633126146449068e-05, "loss": 0.69, "step": 5655 }, { "epoch": 0.33037383177570095, "grad_norm": 1.6649446487426758, "learning_rate": 1.5631562922921157e-05, "loss": 0.9657, "step": 5656 }, { "epoch": 0.3304322429906542, "grad_norm": 1.5454233884811401, "learning_rate": 1.5629999497835905e-05, "loss": 0.9434, "step": 5657 }, { "epoch": 0.33049065420560747, "grad_norm": 2.440173387527466, "learning_rate": 1.5628435871249274e-05, "loss": 0.8228, "step": 5658 }, { "epoch": 0.33054906542056073, "grad_norm": 1.466469168663025, "learning_rate": 1.5626872043217218e-05, "loss": 0.7299, "step": 5659 }, { "epoch": 0.33060747663551404, "grad_norm": 1.2339597940444946, "learning_rate": 1.5625308013795713e-05, "loss": 0.879, "step": 5660 }, { "epoch": 0.3306658878504673, "grad_norm": 2.474140167236328, "learning_rate": 1.5623743783040735e-05, "loss": 1.0752, "step": 5661 }, { "epoch": 0.33072429906542056, "grad_norm": 1.3895829916000366, "learning_rate": 1.562217935100827e-05, "loss": 1.0596, "step": 5662 }, { "epoch": 0.3307827102803738, "grad_norm": 1.4249283075332642, "learning_rate": 1.562061471775431e-05, "loss": 0.7039, "step": 5663 }, { "epoch": 0.33084112149532713, "grad_norm": 2.178347587585449, "learning_rate": 1.5619049883334853e-05, "loss": 0.8404, "step": 5664 }, { "epoch": 0.3308995327102804, "grad_norm": 2.095602512359619, "learning_rate": 1.5617484847805906e-05, "loss": 0.8995, "step": 5665 }, { "epoch": 0.33095794392523364, "grad_norm": 2.3186497688293457, "learning_rate": 1.561591961122348e-05, "loss": 0.8804, "step": 5666 }, { "epoch": 0.3310163551401869, "grad_norm": 1.019161581993103, "learning_rate": 1.5614354173643606e-05, "loss": 0.7388, "step": 5667 }, { "epoch": 0.33107476635514016, "grad_norm": 1.990597128868103, "learning_rate": 1.5612788535122295e-05, "loss": 0.7853, "step": 5668 }, { "epoch": 0.3311331775700935, "grad_norm": 2.163358688354492, "learning_rate": 1.56112226957156e-05, "loss": 1.0137, "step": 5669 }, { "epoch": 0.33119158878504673, "grad_norm": 1.3182964324951172, "learning_rate": 1.560965665547955e-05, "loss": 0.6826, "step": 5670 }, { "epoch": 0.33125, "grad_norm": 3.1380884647369385, "learning_rate": 1.5608090414470202e-05, "loss": 0.9316, "step": 5671 }, { "epoch": 0.33130841121495325, "grad_norm": 1.793736457824707, "learning_rate": 1.560652397274361e-05, "loss": 0.7746, "step": 5672 }, { "epoch": 0.33136682242990656, "grad_norm": 2.4819819927215576, "learning_rate": 1.560495733035584e-05, "loss": 0.8685, "step": 5673 }, { "epoch": 0.3314252336448598, "grad_norm": 1.1441890001296997, "learning_rate": 1.560339048736296e-05, "loss": 0.6919, "step": 5674 }, { "epoch": 0.3314836448598131, "grad_norm": 1.9059654474258423, "learning_rate": 1.5601823443821053e-05, "loss": 0.7415, "step": 5675 }, { "epoch": 0.33154205607476633, "grad_norm": 1.7421284914016724, "learning_rate": 1.5600256199786202e-05, "loss": 0.8509, "step": 5676 }, { "epoch": 0.33160046728971965, "grad_norm": 1.9770781993865967, "learning_rate": 1.5598688755314496e-05, "loss": 0.8956, "step": 5677 }, { "epoch": 0.3316588785046729, "grad_norm": 1.5434801578521729, "learning_rate": 1.5597121110462035e-05, "loss": 0.8195, "step": 5678 }, { "epoch": 0.33171728971962616, "grad_norm": 1.662399411201477, "learning_rate": 1.5595553265284937e-05, "loss": 0.9912, "step": 5679 }, { "epoch": 0.3317757009345794, "grad_norm": 1.3321104049682617, "learning_rate": 1.5593985219839303e-05, "loss": 0.9282, "step": 5680 }, { "epoch": 0.33183411214953273, "grad_norm": 1.341302752494812, "learning_rate": 1.5592416974181267e-05, "loss": 0.7692, "step": 5681 }, { "epoch": 0.331892523364486, "grad_norm": 1.7431610822677612, "learning_rate": 1.5590848528366943e-05, "loss": 0.9461, "step": 5682 }, { "epoch": 0.33195093457943925, "grad_norm": 1.243466854095459, "learning_rate": 1.5589279882452476e-05, "loss": 0.8743, "step": 5683 }, { "epoch": 0.3320093457943925, "grad_norm": 1.1938321590423584, "learning_rate": 1.5587711036494008e-05, "loss": 0.8094, "step": 5684 }, { "epoch": 0.3320677570093458, "grad_norm": 1.348180890083313, "learning_rate": 1.5586141990547686e-05, "loss": 0.8094, "step": 5685 }, { "epoch": 0.3321261682242991, "grad_norm": 1.0927568674087524, "learning_rate": 1.5584572744669673e-05, "loss": 0.6945, "step": 5686 }, { "epoch": 0.33218457943925234, "grad_norm": 2.044713020324707, "learning_rate": 1.558300329891613e-05, "loss": 0.6355, "step": 5687 }, { "epoch": 0.3322429906542056, "grad_norm": 1.2622666358947754, "learning_rate": 1.5581433653343224e-05, "loss": 0.8909, "step": 5688 }, { "epoch": 0.33230140186915885, "grad_norm": 3.2837412357330322, "learning_rate": 1.557986380800714e-05, "loss": 0.85, "step": 5689 }, { "epoch": 0.33235981308411217, "grad_norm": 1.2820805311203003, "learning_rate": 1.5578293762964057e-05, "loss": 0.9237, "step": 5690 }, { "epoch": 0.3324182242990654, "grad_norm": 2.2667548656463623, "learning_rate": 1.5576723518270176e-05, "loss": 0.8394, "step": 5691 }, { "epoch": 0.3324766355140187, "grad_norm": 1.071562647819519, "learning_rate": 1.557515307398169e-05, "loss": 0.8098, "step": 5692 }, { "epoch": 0.33253504672897194, "grad_norm": 1.6424601078033447, "learning_rate": 1.557358243015482e-05, "loss": 0.9154, "step": 5693 }, { "epoch": 0.33259345794392525, "grad_norm": 1.2126356363296509, "learning_rate": 1.557201158684576e-05, "loss": 0.8486, "step": 5694 }, { "epoch": 0.3326518691588785, "grad_norm": 1.7574554681777954, "learning_rate": 1.557044054411074e-05, "loss": 0.8387, "step": 5695 }, { "epoch": 0.33271028037383177, "grad_norm": 1.2440279722213745, "learning_rate": 1.5568869302006004e-05, "loss": 0.9827, "step": 5696 }, { "epoch": 0.332768691588785, "grad_norm": 2.359257459640503, "learning_rate": 1.5567297860587762e-05, "loss": 0.9156, "step": 5697 }, { "epoch": 0.33282710280373834, "grad_norm": 2.005373239517212, "learning_rate": 1.556572621991227e-05, "loss": 0.9397, "step": 5698 }, { "epoch": 0.3328855140186916, "grad_norm": 1.1659897565841675, "learning_rate": 1.5564154380035782e-05, "loss": 0.6521, "step": 5699 }, { "epoch": 0.33294392523364486, "grad_norm": 1.6644905805587769, "learning_rate": 1.5562582341014546e-05, "loss": 0.8701, "step": 5700 }, { "epoch": 0.3330023364485981, "grad_norm": 2.1065726280212402, "learning_rate": 1.5561010102904833e-05, "loss": 0.8778, "step": 5701 }, { "epoch": 0.3330607476635514, "grad_norm": 1.0875463485717773, "learning_rate": 1.5559437665762913e-05, "loss": 0.8706, "step": 5702 }, { "epoch": 0.3331191588785047, "grad_norm": 2.4231789112091064, "learning_rate": 1.5557865029645062e-05, "loss": 0.9306, "step": 5703 }, { "epoch": 0.33317757009345794, "grad_norm": 1.151712417602539, "learning_rate": 1.5556292194607565e-05, "loss": 0.6491, "step": 5704 }, { "epoch": 0.3332359813084112, "grad_norm": 2.3527963161468506, "learning_rate": 1.555471916070672e-05, "loss": 1.0778, "step": 5705 }, { "epoch": 0.3332943925233645, "grad_norm": 2.560051679611206, "learning_rate": 1.5553145927998823e-05, "loss": 0.9284, "step": 5706 }, { "epoch": 0.33335280373831777, "grad_norm": 1.385398507118225, "learning_rate": 1.5551572496540182e-05, "loss": 0.8524, "step": 5707 }, { "epoch": 0.33341121495327103, "grad_norm": 1.262820839881897, "learning_rate": 1.554999886638711e-05, "loss": 0.7887, "step": 5708 }, { "epoch": 0.3334696261682243, "grad_norm": 1.9514063596725464, "learning_rate": 1.554842503759593e-05, "loss": 0.9555, "step": 5709 }, { "epoch": 0.33352803738317754, "grad_norm": 1.7269095182418823, "learning_rate": 1.554685101022297e-05, "loss": 0.9242, "step": 5710 }, { "epoch": 0.33358644859813086, "grad_norm": 1.4894026517868042, "learning_rate": 1.5545276784324567e-05, "loss": 0.7517, "step": 5711 }, { "epoch": 0.3336448598130841, "grad_norm": 1.589292287826538, "learning_rate": 1.554370235995706e-05, "loss": 1.0929, "step": 5712 }, { "epoch": 0.3337032710280374, "grad_norm": 1.656268835067749, "learning_rate": 1.55421277371768e-05, "loss": 0.7697, "step": 5713 }, { "epoch": 0.33376168224299063, "grad_norm": 1.2278468608856201, "learning_rate": 1.5540552916040142e-05, "loss": 0.757, "step": 5714 }, { "epoch": 0.33382009345794394, "grad_norm": 1.8276652097702026, "learning_rate": 1.553897789660346e-05, "loss": 0.797, "step": 5715 }, { "epoch": 0.3338785046728972, "grad_norm": 1.458977460861206, "learning_rate": 1.553740267892311e-05, "loss": 0.8808, "step": 5716 }, { "epoch": 0.33393691588785046, "grad_norm": 2.0680696964263916, "learning_rate": 1.553582726305548e-05, "loss": 0.8824, "step": 5717 }, { "epoch": 0.3339953271028037, "grad_norm": 1.246644377708435, "learning_rate": 1.5534251649056954e-05, "loss": 0.7574, "step": 5718 }, { "epoch": 0.33405373831775703, "grad_norm": 1.7626625299453735, "learning_rate": 1.5532675836983917e-05, "loss": 0.7011, "step": 5719 }, { "epoch": 0.3341121495327103, "grad_norm": 2.7931559085845947, "learning_rate": 1.553109982689278e-05, "loss": 0.8346, "step": 5720 }, { "epoch": 0.33417056074766355, "grad_norm": 1.4792695045471191, "learning_rate": 1.5529523618839937e-05, "loss": 0.8809, "step": 5721 }, { "epoch": 0.3342289719626168, "grad_norm": 1.5762337446212769, "learning_rate": 1.5527947212881812e-05, "loss": 0.7118, "step": 5722 }, { "epoch": 0.3342873831775701, "grad_norm": 1.1781128644943237, "learning_rate": 1.5526370609074825e-05, "loss": 0.7768, "step": 5723 }, { "epoch": 0.3343457943925234, "grad_norm": 1.838503360748291, "learning_rate": 1.5524793807475392e-05, "loss": 0.6532, "step": 5724 }, { "epoch": 0.33440420560747663, "grad_norm": 1.8188257217407227, "learning_rate": 1.5523216808139964e-05, "loss": 0.7022, "step": 5725 }, { "epoch": 0.3344626168224299, "grad_norm": 1.383638858795166, "learning_rate": 1.552163961112497e-05, "loss": 1.0124, "step": 5726 }, { "epoch": 0.33452102803738315, "grad_norm": 1.6451960802078247, "learning_rate": 1.5520062216486866e-05, "loss": 0.8341, "step": 5727 }, { "epoch": 0.33457943925233646, "grad_norm": 2.3365557193756104, "learning_rate": 1.5518484624282103e-05, "loss": 0.8504, "step": 5728 }, { "epoch": 0.3346378504672897, "grad_norm": 1.771451473236084, "learning_rate": 1.551690683456715e-05, "loss": 0.8594, "step": 5729 }, { "epoch": 0.334696261682243, "grad_norm": 1.476723313331604, "learning_rate": 1.5515328847398473e-05, "loss": 0.8012, "step": 5730 }, { "epoch": 0.33475467289719624, "grad_norm": 1.9542227983474731, "learning_rate": 1.551375066283255e-05, "loss": 0.8488, "step": 5731 }, { "epoch": 0.33481308411214955, "grad_norm": 0.9993115067481995, "learning_rate": 1.5512172280925867e-05, "loss": 0.6448, "step": 5732 }, { "epoch": 0.3348714953271028, "grad_norm": 2.5936501026153564, "learning_rate": 1.5510593701734912e-05, "loss": 0.8017, "step": 5733 }, { "epoch": 0.33492990654205607, "grad_norm": 1.2149157524108887, "learning_rate": 1.5509014925316185e-05, "loss": 0.8522, "step": 5734 }, { "epoch": 0.3349883177570093, "grad_norm": 2.5876731872558594, "learning_rate": 1.550743595172619e-05, "loss": 1.0644, "step": 5735 }, { "epoch": 0.33504672897196264, "grad_norm": 1.6560845375061035, "learning_rate": 1.5505856781021443e-05, "loss": 0.8348, "step": 5736 }, { "epoch": 0.3351051401869159, "grad_norm": 2.0159382820129395, "learning_rate": 1.550427741325846e-05, "loss": 0.9777, "step": 5737 }, { "epoch": 0.33516355140186915, "grad_norm": 1.6765387058258057, "learning_rate": 1.5502697848493772e-05, "loss": 0.807, "step": 5738 }, { "epoch": 0.3352219626168224, "grad_norm": 1.180038571357727, "learning_rate": 1.5501118086783908e-05, "loss": 0.8063, "step": 5739 }, { "epoch": 0.3352803738317757, "grad_norm": 1.6414018869400024, "learning_rate": 1.5499538128185413e-05, "loss": 0.8418, "step": 5740 }, { "epoch": 0.335338785046729, "grad_norm": 1.3725154399871826, "learning_rate": 1.549795797275483e-05, "loss": 0.7404, "step": 5741 }, { "epoch": 0.33539719626168224, "grad_norm": 1.4569602012634277, "learning_rate": 1.5496377620548717e-05, "loss": 0.9679, "step": 5742 }, { "epoch": 0.3354556074766355, "grad_norm": 2.441312789916992, "learning_rate": 1.5494797071623633e-05, "loss": 1.1054, "step": 5743 }, { "epoch": 0.3355140186915888, "grad_norm": 1.628702163696289, "learning_rate": 1.5493216326036154e-05, "loss": 0.7747, "step": 5744 }, { "epoch": 0.33557242990654207, "grad_norm": 1.8078068494796753, "learning_rate": 1.5491635383842848e-05, "loss": 0.7412, "step": 5745 }, { "epoch": 0.3356308411214953, "grad_norm": 1.2637972831726074, "learning_rate": 1.5490054245100296e-05, "loss": 0.7889, "step": 5746 }, { "epoch": 0.3356892523364486, "grad_norm": 1.366558313369751, "learning_rate": 1.54884729098651e-05, "loss": 0.9087, "step": 5747 }, { "epoch": 0.33574766355140184, "grad_norm": 1.931311845779419, "learning_rate": 1.5486891378193846e-05, "loss": 0.7969, "step": 5748 }, { "epoch": 0.33580607476635516, "grad_norm": 1.1578590869903564, "learning_rate": 1.5485309650143144e-05, "loss": 0.7515, "step": 5749 }, { "epoch": 0.3358644859813084, "grad_norm": 1.4011902809143066, "learning_rate": 1.5483727725769602e-05, "loss": 0.753, "step": 5750 }, { "epoch": 0.33592289719626167, "grad_norm": 1.524571418762207, "learning_rate": 1.548214560512984e-05, "loss": 0.6719, "step": 5751 }, { "epoch": 0.33598130841121493, "grad_norm": 1.888608694076538, "learning_rate": 1.548056328828048e-05, "loss": 0.8008, "step": 5752 }, { "epoch": 0.33603971962616824, "grad_norm": 1.568566083908081, "learning_rate": 1.5478980775278154e-05, "loss": 0.6968, "step": 5753 }, { "epoch": 0.3360981308411215, "grad_norm": 2.01391339302063, "learning_rate": 1.547739806617951e-05, "loss": 0.8898, "step": 5754 }, { "epoch": 0.33615654205607476, "grad_norm": 1.2523292303085327, "learning_rate": 1.5475815161041183e-05, "loss": 0.7904, "step": 5755 }, { "epoch": 0.336214953271028, "grad_norm": 3.50240421295166, "learning_rate": 1.5474232059919835e-05, "loss": 0.8604, "step": 5756 }, { "epoch": 0.33627336448598133, "grad_norm": 2.6416518688201904, "learning_rate": 1.547264876287212e-05, "loss": 0.9337, "step": 5757 }, { "epoch": 0.3363317757009346, "grad_norm": 1.338491439819336, "learning_rate": 1.5471065269954705e-05, "loss": 0.9173, "step": 5758 }, { "epoch": 0.33639018691588785, "grad_norm": 1.6573936939239502, "learning_rate": 1.5469481581224274e-05, "loss": 0.7441, "step": 5759 }, { "epoch": 0.3364485981308411, "grad_norm": 1.9986189603805542, "learning_rate": 1.546789769673749e-05, "loss": 0.7775, "step": 5760 }, { "epoch": 0.3365070093457944, "grad_norm": 1.3375107049942017, "learning_rate": 1.546631361655106e-05, "loss": 0.9322, "step": 5761 }, { "epoch": 0.3365654205607477, "grad_norm": 1.1742916107177734, "learning_rate": 1.546472934072167e-05, "loss": 0.727, "step": 5762 }, { "epoch": 0.33662383177570093, "grad_norm": 2.513037919998169, "learning_rate": 1.5463144869306022e-05, "loss": 0.8793, "step": 5763 }, { "epoch": 0.3366822429906542, "grad_norm": 1.300155758857727, "learning_rate": 1.546156020236083e-05, "loss": 0.9092, "step": 5764 }, { "epoch": 0.3367406542056075, "grad_norm": 1.495845079421997, "learning_rate": 1.545997533994281e-05, "loss": 0.8765, "step": 5765 }, { "epoch": 0.33679906542056076, "grad_norm": 1.4065866470336914, "learning_rate": 1.5458390282108674e-05, "loss": 0.7136, "step": 5766 }, { "epoch": 0.336857476635514, "grad_norm": 1.2635540962219238, "learning_rate": 1.5456805028915165e-05, "loss": 0.8969, "step": 5767 }, { "epoch": 0.3369158878504673, "grad_norm": 1.8274329900741577, "learning_rate": 1.545521958041902e-05, "loss": 0.8449, "step": 5768 }, { "epoch": 0.33697429906542054, "grad_norm": 1.1021629571914673, "learning_rate": 1.5453633936676972e-05, "loss": 0.8758, "step": 5769 }, { "epoch": 0.33703271028037385, "grad_norm": 1.6310514211654663, "learning_rate": 1.5452048097745784e-05, "loss": 0.9443, "step": 5770 }, { "epoch": 0.3370911214953271, "grad_norm": 1.1639639139175415, "learning_rate": 1.545046206368221e-05, "loss": 0.7167, "step": 5771 }, { "epoch": 0.33714953271028036, "grad_norm": 0.9584943652153015, "learning_rate": 1.5448875834543015e-05, "loss": 0.9299, "step": 5772 }, { "epoch": 0.3372079439252336, "grad_norm": 1.501929521560669, "learning_rate": 1.544728941038497e-05, "loss": 0.8198, "step": 5773 }, { "epoch": 0.33726635514018694, "grad_norm": 1.2350339889526367, "learning_rate": 1.5445702791264853e-05, "loss": 0.8354, "step": 5774 }, { "epoch": 0.3373247663551402, "grad_norm": 1.062900424003601, "learning_rate": 1.5444115977239456e-05, "loss": 0.8589, "step": 5775 }, { "epoch": 0.33738317757009345, "grad_norm": 1.1941057443618774, "learning_rate": 1.544252896836557e-05, "loss": 0.8861, "step": 5776 }, { "epoch": 0.3374415887850467, "grad_norm": 2.3343963623046875, "learning_rate": 1.5440941764699988e-05, "loss": 0.8972, "step": 5777 }, { "epoch": 0.3375, "grad_norm": 1.4601960182189941, "learning_rate": 1.5439354366299528e-05, "loss": 0.8564, "step": 5778 }, { "epoch": 0.3375584112149533, "grad_norm": 1.6334599256515503, "learning_rate": 1.5437766773220995e-05, "loss": 0.883, "step": 5779 }, { "epoch": 0.33761682242990654, "grad_norm": 1.345591425895691, "learning_rate": 1.5436178985521218e-05, "loss": 0.7469, "step": 5780 }, { "epoch": 0.3376752336448598, "grad_norm": 1.427453637123108, "learning_rate": 1.5434591003257016e-05, "loss": 0.8608, "step": 5781 }, { "epoch": 0.3377336448598131, "grad_norm": 1.1669509410858154, "learning_rate": 1.5433002826485234e-05, "loss": 0.8606, "step": 5782 }, { "epoch": 0.33779205607476637, "grad_norm": 1.8335365056991577, "learning_rate": 1.5431414455262707e-05, "loss": 0.8499, "step": 5783 }, { "epoch": 0.3378504672897196, "grad_norm": 1.1388285160064697, "learning_rate": 1.542982588964628e-05, "loss": 0.72, "step": 5784 }, { "epoch": 0.3379088785046729, "grad_norm": 1.6735258102416992, "learning_rate": 1.5428237129692816e-05, "loss": 0.8654, "step": 5785 }, { "epoch": 0.33796728971962614, "grad_norm": 1.2051451206207275, "learning_rate": 1.542664817545918e-05, "loss": 0.834, "step": 5786 }, { "epoch": 0.33802570093457945, "grad_norm": 1.3822673559188843, "learning_rate": 1.542505902700224e-05, "loss": 0.9992, "step": 5787 }, { "epoch": 0.3380841121495327, "grad_norm": 1.1342449188232422, "learning_rate": 1.5423469684378865e-05, "loss": 0.725, "step": 5788 }, { "epoch": 0.33814252336448597, "grad_norm": 1.297448992729187, "learning_rate": 1.5421880147645945e-05, "loss": 0.7291, "step": 5789 }, { "epoch": 0.3382009345794392, "grad_norm": 1.5162369012832642, "learning_rate": 1.5420290416860368e-05, "loss": 0.8444, "step": 5790 }, { "epoch": 0.33825934579439254, "grad_norm": 2.109363079071045, "learning_rate": 1.5418700492079036e-05, "loss": 0.9994, "step": 5791 }, { "epoch": 0.3383177570093458, "grad_norm": 1.086641788482666, "learning_rate": 1.541711037335885e-05, "loss": 0.6157, "step": 5792 }, { "epoch": 0.33837616822429906, "grad_norm": 1.6525843143463135, "learning_rate": 1.541552006075672e-05, "loss": 0.6992, "step": 5793 }, { "epoch": 0.3384345794392523, "grad_norm": 1.0794000625610352, "learning_rate": 1.541392955432957e-05, "loss": 0.8075, "step": 5794 }, { "epoch": 0.3384929906542056, "grad_norm": 1.3778883218765259, "learning_rate": 1.5412338854134318e-05, "loss": 0.7971, "step": 5795 }, { "epoch": 0.3385514018691589, "grad_norm": 1.0920151472091675, "learning_rate": 1.54107479602279e-05, "loss": 0.8415, "step": 5796 }, { "epoch": 0.33860981308411214, "grad_norm": 3.1209399700164795, "learning_rate": 1.540915687266726e-05, "loss": 1.0338, "step": 5797 }, { "epoch": 0.3386682242990654, "grad_norm": 1.7439253330230713, "learning_rate": 1.5407565591509334e-05, "loss": 0.8096, "step": 5798 }, { "epoch": 0.3387266355140187, "grad_norm": 1.11403489112854, "learning_rate": 1.540597411681108e-05, "loss": 0.8009, "step": 5799 }, { "epoch": 0.338785046728972, "grad_norm": 1.2408909797668457, "learning_rate": 1.5404382448629457e-05, "loss": 0.7846, "step": 5800 }, { "epoch": 0.33884345794392523, "grad_norm": 1.6487575769424438, "learning_rate": 1.5402790587021436e-05, "loss": 0.7429, "step": 5801 }, { "epoch": 0.3389018691588785, "grad_norm": 1.7822872400283813, "learning_rate": 1.5401198532043985e-05, "loss": 0.9412, "step": 5802 }, { "epoch": 0.3389602803738318, "grad_norm": 1.1788016557693481, "learning_rate": 1.5399606283754086e-05, "loss": 0.8715, "step": 5803 }, { "epoch": 0.33901869158878506, "grad_norm": 1.2074369192123413, "learning_rate": 1.539801384220873e-05, "loss": 0.8212, "step": 5804 }, { "epoch": 0.3390771028037383, "grad_norm": 8.420697212219238, "learning_rate": 1.539642120746491e-05, "loss": 0.9186, "step": 5805 }, { "epoch": 0.3391355140186916, "grad_norm": 3.6663265228271484, "learning_rate": 1.5394828379579625e-05, "loss": 1.0028, "step": 5806 }, { "epoch": 0.33919392523364483, "grad_norm": 2.1764309406280518, "learning_rate": 1.5393235358609887e-05, "loss": 0.9803, "step": 5807 }, { "epoch": 0.33925233644859815, "grad_norm": 2.159722089767456, "learning_rate": 1.5391642144612707e-05, "loss": 0.9508, "step": 5808 }, { "epoch": 0.3393107476635514, "grad_norm": 1.5003488063812256, "learning_rate": 1.5390048737645115e-05, "loss": 0.9813, "step": 5809 }, { "epoch": 0.33936915887850466, "grad_norm": 1.676707148551941, "learning_rate": 1.538845513776413e-05, "loss": 1.0768, "step": 5810 }, { "epoch": 0.3394275700934579, "grad_norm": 1.180515170097351, "learning_rate": 1.5386861345026792e-05, "loss": 0.7989, "step": 5811 }, { "epoch": 0.33948598130841123, "grad_norm": 1.4446675777435303, "learning_rate": 1.5385267359490147e-05, "loss": 0.8453, "step": 5812 }, { "epoch": 0.3395443925233645, "grad_norm": 1.5799040794372559, "learning_rate": 1.538367318121124e-05, "loss": 0.7742, "step": 5813 }, { "epoch": 0.33960280373831775, "grad_norm": 1.3774938583374023, "learning_rate": 1.538207881024713e-05, "loss": 0.8296, "step": 5814 }, { "epoch": 0.339661214953271, "grad_norm": 1.4712698459625244, "learning_rate": 1.5380484246654882e-05, "loss": 0.7813, "step": 5815 }, { "epoch": 0.3397196261682243, "grad_norm": 2.117964506149292, "learning_rate": 1.5378889490491565e-05, "loss": 0.9818, "step": 5816 }, { "epoch": 0.3397780373831776, "grad_norm": 1.7987384796142578, "learning_rate": 1.5377294541814257e-05, "loss": 0.8891, "step": 5817 }, { "epoch": 0.33983644859813084, "grad_norm": 1.5035145282745361, "learning_rate": 1.5375699400680038e-05, "loss": 0.9467, "step": 5818 }, { "epoch": 0.3398948598130841, "grad_norm": 1.0932811498641968, "learning_rate": 1.5374104067146006e-05, "loss": 0.7841, "step": 5819 }, { "epoch": 0.3399532710280374, "grad_norm": 2.6576924324035645, "learning_rate": 1.5372508541269257e-05, "loss": 0.9689, "step": 5820 }, { "epoch": 0.34001168224299066, "grad_norm": 1.3831754922866821, "learning_rate": 1.5370912823106894e-05, "loss": 0.9204, "step": 5821 }, { "epoch": 0.3400700934579439, "grad_norm": 1.3569507598876953, "learning_rate": 1.5369316912716028e-05, "loss": 0.8213, "step": 5822 }, { "epoch": 0.3401285046728972, "grad_norm": 1.4926702976226807, "learning_rate": 1.536772081015378e-05, "loss": 0.7731, "step": 5823 }, { "epoch": 0.3401869158878505, "grad_norm": 2.5355467796325684, "learning_rate": 1.5366124515477276e-05, "loss": 1.1061, "step": 5824 }, { "epoch": 0.34024532710280375, "grad_norm": 2.359382390975952, "learning_rate": 1.5364528028743645e-05, "loss": 0.9016, "step": 5825 }, { "epoch": 0.340303738317757, "grad_norm": 1.3936712741851807, "learning_rate": 1.5362931350010033e-05, "loss": 0.8721, "step": 5826 }, { "epoch": 0.34036214953271027, "grad_norm": 1.7715848684310913, "learning_rate": 1.5361334479333578e-05, "loss": 0.8235, "step": 5827 }, { "epoch": 0.3404205607476635, "grad_norm": 1.2947614192962646, "learning_rate": 1.5359737416771438e-05, "loss": 0.8382, "step": 5828 }, { "epoch": 0.34047897196261684, "grad_norm": 1.2655519247055054, "learning_rate": 1.535814016238077e-05, "loss": 0.8818, "step": 5829 }, { "epoch": 0.3405373831775701, "grad_norm": 2.173485040664673, "learning_rate": 1.5356542716218747e-05, "loss": 0.849, "step": 5830 }, { "epoch": 0.34059579439252335, "grad_norm": 1.1199736595153809, "learning_rate": 1.5354945078342532e-05, "loss": 0.6349, "step": 5831 }, { "epoch": 0.3406542056074766, "grad_norm": 1.2663897275924683, "learning_rate": 1.5353347248809317e-05, "loss": 0.8162, "step": 5832 }, { "epoch": 0.3407126168224299, "grad_norm": 1.806101679801941, "learning_rate": 1.535174922767628e-05, "loss": 0.7456, "step": 5833 }, { "epoch": 0.3407710280373832, "grad_norm": 1.6956325769424438, "learning_rate": 1.535015101500062e-05, "loss": 0.7677, "step": 5834 }, { "epoch": 0.34082943925233644, "grad_norm": 1.4686959981918335, "learning_rate": 1.534855261083954e-05, "loss": 0.8117, "step": 5835 }, { "epoch": 0.3408878504672897, "grad_norm": 1.8869529962539673, "learning_rate": 1.5346954015250247e-05, "loss": 0.888, "step": 5836 }, { "epoch": 0.340946261682243, "grad_norm": 1.104250431060791, "learning_rate": 1.5345355228289952e-05, "loss": 0.8139, "step": 5837 }, { "epoch": 0.34100467289719627, "grad_norm": 2.369628667831421, "learning_rate": 1.5343756250015876e-05, "loss": 0.9536, "step": 5838 }, { "epoch": 0.34106308411214953, "grad_norm": 1.159409761428833, "learning_rate": 1.5342157080485253e-05, "loss": 0.8055, "step": 5839 }, { "epoch": 0.3411214953271028, "grad_norm": 2.2449090480804443, "learning_rate": 1.5340557719755313e-05, "loss": 0.8815, "step": 5840 }, { "epoch": 0.3411799065420561, "grad_norm": 1.403009057044983, "learning_rate": 1.53389581678833e-05, "loss": 0.7968, "step": 5841 }, { "epoch": 0.34123831775700936, "grad_norm": 1.7385576963424683, "learning_rate": 1.533735842492647e-05, "loss": 0.816, "step": 5842 }, { "epoch": 0.3412967289719626, "grad_norm": 1.3855589628219604, "learning_rate": 1.533575849094207e-05, "loss": 0.6815, "step": 5843 }, { "epoch": 0.3413551401869159, "grad_norm": 1.2357114553451538, "learning_rate": 1.533415836598736e-05, "loss": 0.7147, "step": 5844 }, { "epoch": 0.3414135514018692, "grad_norm": 1.3273839950561523, "learning_rate": 1.5332558050119622e-05, "loss": 0.8124, "step": 5845 }, { "epoch": 0.34147196261682244, "grad_norm": 1.5484594106674194, "learning_rate": 1.533095754339612e-05, "loss": 0.8382, "step": 5846 }, { "epoch": 0.3415303738317757, "grad_norm": 0.9259416460990906, "learning_rate": 1.5329356845874148e-05, "loss": 0.7064, "step": 5847 }, { "epoch": 0.34158878504672896, "grad_norm": 1.8767883777618408, "learning_rate": 1.5327755957610984e-05, "loss": 0.9546, "step": 5848 }, { "epoch": 0.3416471962616822, "grad_norm": 1.459657907485962, "learning_rate": 1.5326154878663932e-05, "loss": 0.9198, "step": 5849 }, { "epoch": 0.34170560747663553, "grad_norm": 1.1199387311935425, "learning_rate": 1.53245536090903e-05, "loss": 0.8737, "step": 5850 }, { "epoch": 0.3417640186915888, "grad_norm": 2.2580599784851074, "learning_rate": 1.532295214894739e-05, "loss": 0.9525, "step": 5851 }, { "epoch": 0.34182242990654205, "grad_norm": 1.6921837329864502, "learning_rate": 1.532135049829252e-05, "loss": 0.8783, "step": 5852 }, { "epoch": 0.3418808411214953, "grad_norm": 1.8700097799301147, "learning_rate": 1.531974865718302e-05, "loss": 0.8532, "step": 5853 }, { "epoch": 0.3419392523364486, "grad_norm": 1.1909725666046143, "learning_rate": 1.531814662567622e-05, "loss": 1.0017, "step": 5854 }, { "epoch": 0.3419976635514019, "grad_norm": 1.3797054290771484, "learning_rate": 1.531654440382945e-05, "loss": 0.9179, "step": 5855 }, { "epoch": 0.34205607476635513, "grad_norm": 1.6421451568603516, "learning_rate": 1.5314941991700066e-05, "loss": 0.7409, "step": 5856 }, { "epoch": 0.3421144859813084, "grad_norm": 2.554635524749756, "learning_rate": 1.5313339389345407e-05, "loss": 0.8105, "step": 5857 }, { "epoch": 0.3421728971962617, "grad_norm": 1.8395966291427612, "learning_rate": 1.5311736596822843e-05, "loss": 0.9107, "step": 5858 }, { "epoch": 0.34223130841121496, "grad_norm": 1.2106058597564697, "learning_rate": 1.5310133614189734e-05, "loss": 0.7764, "step": 5859 }, { "epoch": 0.3422897196261682, "grad_norm": 1.0205901861190796, "learning_rate": 1.5308530441503448e-05, "loss": 0.7419, "step": 5860 }, { "epoch": 0.3423481308411215, "grad_norm": 1.5032408237457275, "learning_rate": 1.5306927078821367e-05, "loss": 1.0114, "step": 5861 }, { "epoch": 0.3424065420560748, "grad_norm": 1.2463748455047607, "learning_rate": 1.530532352620088e-05, "loss": 0.8489, "step": 5862 }, { "epoch": 0.34246495327102805, "grad_norm": 1.6025571823120117, "learning_rate": 1.5303719783699368e-05, "loss": 0.8385, "step": 5863 }, { "epoch": 0.3425233644859813, "grad_norm": 1.1387455463409424, "learning_rate": 1.5302115851374247e-05, "loss": 0.7305, "step": 5864 }, { "epoch": 0.34258177570093457, "grad_norm": 1.8209482431411743, "learning_rate": 1.5300511729282906e-05, "loss": 0.8631, "step": 5865 }, { "epoch": 0.3426401869158878, "grad_norm": 1.1160680055618286, "learning_rate": 1.5298907417482773e-05, "loss": 0.7966, "step": 5866 }, { "epoch": 0.34269859813084114, "grad_norm": 1.2461235523223877, "learning_rate": 1.5297302916031257e-05, "loss": 0.735, "step": 5867 }, { "epoch": 0.3427570093457944, "grad_norm": 1.7702152729034424, "learning_rate": 1.5295698224985782e-05, "loss": 0.8955, "step": 5868 }, { "epoch": 0.34281542056074765, "grad_norm": 1.3529292345046997, "learning_rate": 1.529409334440379e-05, "loss": 0.7358, "step": 5869 }, { "epoch": 0.3428738317757009, "grad_norm": 1.3235043287277222, "learning_rate": 1.5292488274342713e-05, "loss": 0.9489, "step": 5870 }, { "epoch": 0.3429322429906542, "grad_norm": 1.1307904720306396, "learning_rate": 1.529088301486e-05, "loss": 0.6078, "step": 5871 }, { "epoch": 0.3429906542056075, "grad_norm": 1.050926923751831, "learning_rate": 1.528927756601311e-05, "loss": 0.8779, "step": 5872 }, { "epoch": 0.34304906542056074, "grad_norm": 1.8453737497329712, "learning_rate": 1.5287671927859494e-05, "loss": 0.8217, "step": 5873 }, { "epoch": 0.343107476635514, "grad_norm": 1.3142653703689575, "learning_rate": 1.5286066100456623e-05, "loss": 0.9855, "step": 5874 }, { "epoch": 0.3431658878504673, "grad_norm": 1.1795753240585327, "learning_rate": 1.5284460083861974e-05, "loss": 0.8435, "step": 5875 }, { "epoch": 0.34322429906542057, "grad_norm": 2.1698997020721436, "learning_rate": 1.5282853878133023e-05, "loss": 0.8831, "step": 5876 }, { "epoch": 0.3432827102803738, "grad_norm": 1.1858786344528198, "learning_rate": 1.5281247483327256e-05, "loss": 0.7715, "step": 5877 }, { "epoch": 0.3433411214953271, "grad_norm": 1.7313522100448608, "learning_rate": 1.527964089950217e-05, "loss": 0.8664, "step": 5878 }, { "epoch": 0.3433995327102804, "grad_norm": 1.4549822807312012, "learning_rate": 1.5278034126715266e-05, "loss": 0.8761, "step": 5879 }, { "epoch": 0.34345794392523366, "grad_norm": 2.308230400085449, "learning_rate": 1.527642716502405e-05, "loss": 0.8905, "step": 5880 }, { "epoch": 0.3435163551401869, "grad_norm": 1.3635929822921753, "learning_rate": 1.5274820014486035e-05, "loss": 0.9609, "step": 5881 }, { "epoch": 0.34357476635514017, "grad_norm": 1.5378241539001465, "learning_rate": 1.5273212675158745e-05, "loss": 0.8251, "step": 5882 }, { "epoch": 0.3436331775700935, "grad_norm": 0.9447709321975708, "learning_rate": 1.5271605147099707e-05, "loss": 0.9476, "step": 5883 }, { "epoch": 0.34369158878504674, "grad_norm": 1.1699182987213135, "learning_rate": 1.5269997430366452e-05, "loss": 0.6412, "step": 5884 }, { "epoch": 0.34375, "grad_norm": 1.8596086502075195, "learning_rate": 1.5268389525016524e-05, "loss": 1.0128, "step": 5885 }, { "epoch": 0.34380841121495326, "grad_norm": 1.077975869178772, "learning_rate": 1.5266781431107473e-05, "loss": 0.8099, "step": 5886 }, { "epoch": 0.3438668224299065, "grad_norm": 1.2534499168395996, "learning_rate": 1.526517314869685e-05, "loss": 0.8344, "step": 5887 }, { "epoch": 0.34392523364485983, "grad_norm": 1.4702932834625244, "learning_rate": 1.5263564677842215e-05, "loss": 0.813, "step": 5888 }, { "epoch": 0.3439836448598131, "grad_norm": 1.0257059335708618, "learning_rate": 1.526195601860115e-05, "loss": 0.7163, "step": 5889 }, { "epoch": 0.34404205607476634, "grad_norm": 1.2832634449005127, "learning_rate": 1.5260347171031208e-05, "loss": 0.9696, "step": 5890 }, { "epoch": 0.3441004672897196, "grad_norm": 1.1727484464645386, "learning_rate": 1.5258738135189986e-05, "loss": 0.9374, "step": 5891 }, { "epoch": 0.3441588785046729, "grad_norm": 1.1609363555908203, "learning_rate": 1.5257128911135069e-05, "loss": 0.8629, "step": 5892 }, { "epoch": 0.3442172897196262, "grad_norm": 1.3802835941314697, "learning_rate": 1.525551949892405e-05, "loss": 0.8966, "step": 5893 }, { "epoch": 0.34427570093457943, "grad_norm": 1.2366371154785156, "learning_rate": 1.5253909898614536e-05, "loss": 0.8711, "step": 5894 }, { "epoch": 0.3443341121495327, "grad_norm": 0.9316235184669495, "learning_rate": 1.5252300110264128e-05, "loss": 0.6884, "step": 5895 }, { "epoch": 0.344392523364486, "grad_norm": 1.3265817165374756, "learning_rate": 1.5250690133930448e-05, "loss": 0.7834, "step": 5896 }, { "epoch": 0.34445093457943926, "grad_norm": 1.3124892711639404, "learning_rate": 1.5249079969671114e-05, "loss": 0.9536, "step": 5897 }, { "epoch": 0.3445093457943925, "grad_norm": 1.4429985284805298, "learning_rate": 1.5247469617543757e-05, "loss": 1.0194, "step": 5898 }, { "epoch": 0.3445677570093458, "grad_norm": 2.018406867980957, "learning_rate": 1.5245859077606016e-05, "loss": 0.9029, "step": 5899 }, { "epoch": 0.3446261682242991, "grad_norm": 1.495670199394226, "learning_rate": 1.5244248349915526e-05, "loss": 1.0056, "step": 5900 }, { "epoch": 0.34468457943925235, "grad_norm": 1.2141376733779907, "learning_rate": 1.5242637434529938e-05, "loss": 0.7261, "step": 5901 }, { "epoch": 0.3447429906542056, "grad_norm": 1.6061581373214722, "learning_rate": 1.5241026331506911e-05, "loss": 0.8477, "step": 5902 }, { "epoch": 0.34480140186915886, "grad_norm": 1.2255266904830933, "learning_rate": 1.5239415040904107e-05, "loss": 0.9708, "step": 5903 }, { "epoch": 0.3448598130841122, "grad_norm": 1.1377990245819092, "learning_rate": 1.5237803562779192e-05, "loss": 0.8847, "step": 5904 }, { "epoch": 0.34491822429906543, "grad_norm": 0.8412197232246399, "learning_rate": 1.5236191897189843e-05, "loss": 0.771, "step": 5905 }, { "epoch": 0.3449766355140187, "grad_norm": 1.1092811822891235, "learning_rate": 1.5234580044193746e-05, "loss": 0.725, "step": 5906 }, { "epoch": 0.34503504672897195, "grad_norm": 1.8998031616210938, "learning_rate": 1.5232968003848583e-05, "loss": 0.8358, "step": 5907 }, { "epoch": 0.3450934579439252, "grad_norm": 1.8050745725631714, "learning_rate": 1.5231355776212058e-05, "loss": 0.7944, "step": 5908 }, { "epoch": 0.3451518691588785, "grad_norm": 1.3656296730041504, "learning_rate": 1.5229743361341869e-05, "loss": 0.7471, "step": 5909 }, { "epoch": 0.3452102803738318, "grad_norm": 1.4436310529708862, "learning_rate": 1.5228130759295722e-05, "loss": 0.7552, "step": 5910 }, { "epoch": 0.34526869158878504, "grad_norm": 1.8468835353851318, "learning_rate": 1.5226517970131345e-05, "loss": 1.1382, "step": 5911 }, { "epoch": 0.3453271028037383, "grad_norm": 1.30514657497406, "learning_rate": 1.522490499390645e-05, "loss": 0.7123, "step": 5912 }, { "epoch": 0.3453855140186916, "grad_norm": 1.514039397239685, "learning_rate": 1.522329183067877e-05, "loss": 0.775, "step": 5913 }, { "epoch": 0.34544392523364487, "grad_norm": 1.496768832206726, "learning_rate": 1.5221678480506041e-05, "loss": 0.8056, "step": 5914 }, { "epoch": 0.3455023364485981, "grad_norm": 1.0471489429473877, "learning_rate": 1.5220064943446005e-05, "loss": 0.6774, "step": 5915 }, { "epoch": 0.3455607476635514, "grad_norm": 1.1793211698532104, "learning_rate": 1.5218451219556411e-05, "loss": 0.6696, "step": 5916 }, { "epoch": 0.3456191588785047, "grad_norm": 1.5989773273468018, "learning_rate": 1.521683730889502e-05, "loss": 0.8248, "step": 5917 }, { "epoch": 0.34567757009345795, "grad_norm": 1.4476851224899292, "learning_rate": 1.5215223211519591e-05, "loss": 0.9371, "step": 5918 }, { "epoch": 0.3457359813084112, "grad_norm": 1.724138855934143, "learning_rate": 1.5213608927487895e-05, "loss": 0.9559, "step": 5919 }, { "epoch": 0.34579439252336447, "grad_norm": 1.7099775075912476, "learning_rate": 1.5211994456857706e-05, "loss": 0.8324, "step": 5920 }, { "epoch": 0.3458528037383178, "grad_norm": 1.5523096323013306, "learning_rate": 1.5210379799686808e-05, "loss": 0.8047, "step": 5921 }, { "epoch": 0.34591121495327104, "grad_norm": 1.375762939453125, "learning_rate": 1.5208764956032991e-05, "loss": 0.7604, "step": 5922 }, { "epoch": 0.3459696261682243, "grad_norm": 1.5884126424789429, "learning_rate": 1.5207149925954052e-05, "loss": 0.7102, "step": 5923 }, { "epoch": 0.34602803738317756, "grad_norm": 1.6684337854385376, "learning_rate": 1.5205534709507794e-05, "loss": 0.9593, "step": 5924 }, { "epoch": 0.3460864485981308, "grad_norm": 1.5408439636230469, "learning_rate": 1.5203919306752024e-05, "loss": 1.113, "step": 5925 }, { "epoch": 0.3461448598130841, "grad_norm": 1.641586184501648, "learning_rate": 1.5202303717744562e-05, "loss": 0.6539, "step": 5926 }, { "epoch": 0.3462032710280374, "grad_norm": 1.5215178728103638, "learning_rate": 1.5200687942543228e-05, "loss": 0.8177, "step": 5927 }, { "epoch": 0.34626168224299064, "grad_norm": 1.710064172744751, "learning_rate": 1.5199071981205857e-05, "loss": 0.9127, "step": 5928 }, { "epoch": 0.3463200934579439, "grad_norm": 1.1162549257278442, "learning_rate": 1.5197455833790278e-05, "loss": 0.7123, "step": 5929 }, { "epoch": 0.3463785046728972, "grad_norm": 1.8298299312591553, "learning_rate": 1.5195839500354337e-05, "loss": 0.8237, "step": 5930 }, { "epoch": 0.34643691588785047, "grad_norm": 1.1787528991699219, "learning_rate": 1.5194222980955884e-05, "loss": 0.8305, "step": 5931 }, { "epoch": 0.34649532710280373, "grad_norm": 1.5070257186889648, "learning_rate": 1.5192606275652777e-05, "loss": 0.8037, "step": 5932 }, { "epoch": 0.346553738317757, "grad_norm": 1.7876298427581787, "learning_rate": 1.5190989384502877e-05, "loss": 0.9038, "step": 5933 }, { "epoch": 0.3466121495327103, "grad_norm": 1.1899068355560303, "learning_rate": 1.5189372307564052e-05, "loss": 0.8395, "step": 5934 }, { "epoch": 0.34667056074766356, "grad_norm": 2.4754419326782227, "learning_rate": 1.5187755044894182e-05, "loss": 0.7775, "step": 5935 }, { "epoch": 0.3467289719626168, "grad_norm": 1.7166657447814941, "learning_rate": 1.5186137596551147e-05, "loss": 0.8227, "step": 5936 }, { "epoch": 0.3467873831775701, "grad_norm": 2.0719332695007324, "learning_rate": 1.5184519962592836e-05, "loss": 0.8247, "step": 5937 }, { "epoch": 0.3468457943925234, "grad_norm": 1.5251967906951904, "learning_rate": 1.518290214307715e-05, "loss": 0.8759, "step": 5938 }, { "epoch": 0.34690420560747665, "grad_norm": 1.7307711839675903, "learning_rate": 1.5181284138061987e-05, "loss": 0.922, "step": 5939 }, { "epoch": 0.3469626168224299, "grad_norm": 1.9552634954452515, "learning_rate": 1.5179665947605252e-05, "loss": 1.1686, "step": 5940 }, { "epoch": 0.34702102803738316, "grad_norm": 1.7779426574707031, "learning_rate": 1.5178047571764876e-05, "loss": 0.8144, "step": 5941 }, { "epoch": 0.3470794392523365, "grad_norm": 1.539062738418579, "learning_rate": 1.517642901059877e-05, "loss": 0.8348, "step": 5942 }, { "epoch": 0.34713785046728973, "grad_norm": 1.3532460927963257, "learning_rate": 1.5174810264164865e-05, "loss": 0.715, "step": 5943 }, { "epoch": 0.347196261682243, "grad_norm": 1.331691026687622, "learning_rate": 1.51731913325211e-05, "loss": 0.8679, "step": 5944 }, { "epoch": 0.34725467289719625, "grad_norm": 1.3090589046478271, "learning_rate": 1.5171572215725415e-05, "loss": 0.7525, "step": 5945 }, { "epoch": 0.3473130841121495, "grad_norm": 1.3590645790100098, "learning_rate": 1.5169952913835757e-05, "loss": 0.8822, "step": 5946 }, { "epoch": 0.3473714953271028, "grad_norm": 1.3989737033843994, "learning_rate": 1.516833342691009e-05, "loss": 1.0024, "step": 5947 }, { "epoch": 0.3474299065420561, "grad_norm": 1.5013142824172974, "learning_rate": 1.5166713755006365e-05, "loss": 0.7308, "step": 5948 }, { "epoch": 0.34748831775700934, "grad_norm": 1.2192859649658203, "learning_rate": 1.516509389818256e-05, "loss": 0.9114, "step": 5949 }, { "epoch": 0.3475467289719626, "grad_norm": 1.5347399711608887, "learning_rate": 1.5163473856496652e-05, "loss": 0.7264, "step": 5950 }, { "epoch": 0.3476051401869159, "grad_norm": 2.4661645889282227, "learning_rate": 1.5161853630006616e-05, "loss": 0.7344, "step": 5951 }, { "epoch": 0.34766355140186916, "grad_norm": 2.6341512203216553, "learning_rate": 1.5160233218770448e-05, "loss": 0.9041, "step": 5952 }, { "epoch": 0.3477219626168224, "grad_norm": 1.0097712278366089, "learning_rate": 1.5158612622846139e-05, "loss": 0.6983, "step": 5953 }, { "epoch": 0.3477803738317757, "grad_norm": 1.250151515007019, "learning_rate": 1.5156991842291688e-05, "loss": 0.8309, "step": 5954 }, { "epoch": 0.347838785046729, "grad_norm": 1.1800967454910278, "learning_rate": 1.5155370877165111e-05, "loss": 0.7431, "step": 5955 }, { "epoch": 0.34789719626168225, "grad_norm": 1.2155309915542603, "learning_rate": 1.5153749727524423e-05, "loss": 0.6175, "step": 5956 }, { "epoch": 0.3479556074766355, "grad_norm": 1.3967928886413574, "learning_rate": 1.515212839342764e-05, "loss": 0.9501, "step": 5957 }, { "epoch": 0.34801401869158877, "grad_norm": 1.5589392185211182, "learning_rate": 1.5150506874932798e-05, "loss": 0.854, "step": 5958 }, { "epoch": 0.3480724299065421, "grad_norm": 1.958314299583435, "learning_rate": 1.5148885172097925e-05, "loss": 0.7976, "step": 5959 }, { "epoch": 0.34813084112149534, "grad_norm": 1.1196023225784302, "learning_rate": 1.5147263284981066e-05, "loss": 0.852, "step": 5960 }, { "epoch": 0.3481892523364486, "grad_norm": 1.7448036670684814, "learning_rate": 1.5145641213640275e-05, "loss": 0.9844, "step": 5961 }, { "epoch": 0.34824766355140185, "grad_norm": 1.7180901765823364, "learning_rate": 1.5144018958133595e-05, "loss": 0.9176, "step": 5962 }, { "epoch": 0.34830607476635517, "grad_norm": 1.616437315940857, "learning_rate": 1.5142396518519098e-05, "loss": 0.9774, "step": 5963 }, { "epoch": 0.3483644859813084, "grad_norm": 1.2576088905334473, "learning_rate": 1.5140773894854847e-05, "loss": 0.7843, "step": 5964 }, { "epoch": 0.3484228971962617, "grad_norm": 1.4213042259216309, "learning_rate": 1.5139151087198918e-05, "loss": 0.7185, "step": 5965 }, { "epoch": 0.34848130841121494, "grad_norm": 1.3814164400100708, "learning_rate": 1.5137528095609395e-05, "loss": 0.8312, "step": 5966 }, { "epoch": 0.3485397196261682, "grad_norm": 1.8403282165527344, "learning_rate": 1.5135904920144357e-05, "loss": 0.8918, "step": 5967 }, { "epoch": 0.3485981308411215, "grad_norm": 1.7928330898284912, "learning_rate": 1.5134281560861912e-05, "loss": 0.8633, "step": 5968 }, { "epoch": 0.34865654205607477, "grad_norm": 1.766255259513855, "learning_rate": 1.5132658017820152e-05, "loss": 0.9168, "step": 5969 }, { "epoch": 0.348714953271028, "grad_norm": 2.2896955013275146, "learning_rate": 1.5131034291077186e-05, "loss": 0.9985, "step": 5970 }, { "epoch": 0.3487733644859813, "grad_norm": 1.583457350730896, "learning_rate": 1.512941038069113e-05, "loss": 0.7194, "step": 5971 }, { "epoch": 0.3488317757009346, "grad_norm": 2.6254396438598633, "learning_rate": 1.5127786286720105e-05, "loss": 1.0033, "step": 5972 }, { "epoch": 0.34889018691588786, "grad_norm": 1.3377512693405151, "learning_rate": 1.5126162009222234e-05, "loss": 1.0136, "step": 5973 }, { "epoch": 0.3489485981308411, "grad_norm": 3.210160493850708, "learning_rate": 1.5124537548255655e-05, "loss": 0.8857, "step": 5974 }, { "epoch": 0.3490070093457944, "grad_norm": 1.6850353479385376, "learning_rate": 1.5122912903878509e-05, "loss": 0.9116, "step": 5975 }, { "epoch": 0.3490654205607477, "grad_norm": 1.5650047063827515, "learning_rate": 1.5121288076148939e-05, "loss": 0.9844, "step": 5976 }, { "epoch": 0.34912383177570094, "grad_norm": 2.095480442047119, "learning_rate": 1.5119663065125105e-05, "loss": 0.9084, "step": 5977 }, { "epoch": 0.3491822429906542, "grad_norm": 1.1735378503799438, "learning_rate": 1.5118037870865164e-05, "loss": 0.6682, "step": 5978 }, { "epoch": 0.34924065420560746, "grad_norm": 1.6136870384216309, "learning_rate": 1.5116412493427279e-05, "loss": 0.8887, "step": 5979 }, { "epoch": 0.3492990654205608, "grad_norm": 1.039270281791687, "learning_rate": 1.5114786932869628e-05, "loss": 0.7672, "step": 5980 }, { "epoch": 0.34935747663551403, "grad_norm": 1.073197364807129, "learning_rate": 1.5113161189250389e-05, "loss": 0.691, "step": 5981 }, { "epoch": 0.3494158878504673, "grad_norm": 1.0337153673171997, "learning_rate": 1.511153526262775e-05, "loss": 0.6853, "step": 5982 }, { "epoch": 0.34947429906542055, "grad_norm": 1.1515812873840332, "learning_rate": 1.5109909153059904e-05, "loss": 0.8137, "step": 5983 }, { "epoch": 0.34953271028037386, "grad_norm": 1.430700659751892, "learning_rate": 1.5108282860605047e-05, "loss": 0.9722, "step": 5984 }, { "epoch": 0.3495911214953271, "grad_norm": 2.4037139415740967, "learning_rate": 1.510665638532139e-05, "loss": 0.9773, "step": 5985 }, { "epoch": 0.3496495327102804, "grad_norm": 1.3161197900772095, "learning_rate": 1.5105029727267147e-05, "loss": 0.6367, "step": 5986 }, { "epoch": 0.34970794392523363, "grad_norm": 1.0871587991714478, "learning_rate": 1.5103402886500526e-05, "loss": 0.6143, "step": 5987 }, { "epoch": 0.3497663551401869, "grad_norm": 2.1535849571228027, "learning_rate": 1.5101775863079761e-05, "loss": 0.8042, "step": 5988 }, { "epoch": 0.3498247663551402, "grad_norm": 1.3871896266937256, "learning_rate": 1.5100148657063089e-05, "loss": 0.7698, "step": 5989 }, { "epoch": 0.34988317757009346, "grad_norm": 1.391149640083313, "learning_rate": 1.5098521268508738e-05, "loss": 0.7781, "step": 5990 }, { "epoch": 0.3499415887850467, "grad_norm": 1.8412610292434692, "learning_rate": 1.509689369747496e-05, "loss": 1.0424, "step": 5991 }, { "epoch": 0.35, "grad_norm": 1.6731243133544922, "learning_rate": 1.5095265944020005e-05, "loss": 0.8099, "step": 5992 }, { "epoch": 0.3500584112149533, "grad_norm": 1.5479274988174438, "learning_rate": 1.5093638008202135e-05, "loss": 0.9701, "step": 5993 }, { "epoch": 0.35011682242990655, "grad_norm": 1.5992037057876587, "learning_rate": 1.5092009890079609e-05, "loss": 0.6804, "step": 5994 }, { "epoch": 0.3501752336448598, "grad_norm": 1.3545200824737549, "learning_rate": 1.50903815897107e-05, "loss": 0.8109, "step": 5995 }, { "epoch": 0.35023364485981306, "grad_norm": 1.1668314933776855, "learning_rate": 1.5088753107153686e-05, "loss": 0.7481, "step": 5996 }, { "epoch": 0.3502920560747664, "grad_norm": 1.3216179609298706, "learning_rate": 1.5087124442466854e-05, "loss": 0.9267, "step": 5997 }, { "epoch": 0.35035046728971964, "grad_norm": 1.536741018295288, "learning_rate": 1.5085495595708493e-05, "loss": 0.7729, "step": 5998 }, { "epoch": 0.3504088785046729, "grad_norm": 1.1276289224624634, "learning_rate": 1.50838665669369e-05, "loss": 1.0576, "step": 5999 }, { "epoch": 0.35046728971962615, "grad_norm": 2.231794595718384, "learning_rate": 1.5082237356210382e-05, "loss": 1.1145, "step": 6000 }, { "epoch": 0.35052570093457946, "grad_norm": 1.1530137062072754, "learning_rate": 1.5080607963587247e-05, "loss": 0.8106, "step": 6001 }, { "epoch": 0.3505841121495327, "grad_norm": 1.1106369495391846, "learning_rate": 1.5078978389125812e-05, "loss": 0.7142, "step": 6002 }, { "epoch": 0.350642523364486, "grad_norm": 1.3850513696670532, "learning_rate": 1.50773486328844e-05, "loss": 0.7874, "step": 6003 }, { "epoch": 0.35070093457943924, "grad_norm": 1.5387781858444214, "learning_rate": 1.5075718694921344e-05, "loss": 0.93, "step": 6004 }, { "epoch": 0.3507593457943925, "grad_norm": 1.3039301633834839, "learning_rate": 1.5074088575294978e-05, "loss": 0.7476, "step": 6005 }, { "epoch": 0.3508177570093458, "grad_norm": 1.811845064163208, "learning_rate": 1.5072458274063645e-05, "loss": 0.8964, "step": 6006 }, { "epoch": 0.35087616822429907, "grad_norm": 1.4671924114227295, "learning_rate": 1.5070827791285694e-05, "loss": 0.8084, "step": 6007 }, { "epoch": 0.3509345794392523, "grad_norm": 1.3203926086425781, "learning_rate": 1.5069197127019483e-05, "loss": 0.6315, "step": 6008 }, { "epoch": 0.3509929906542056, "grad_norm": 1.9969127178192139, "learning_rate": 1.5067566281323374e-05, "loss": 0.8423, "step": 6009 }, { "epoch": 0.3510514018691589, "grad_norm": 2.3730947971343994, "learning_rate": 1.506593525425574e-05, "loss": 0.8388, "step": 6010 }, { "epoch": 0.35110981308411215, "grad_norm": 1.3538684844970703, "learning_rate": 1.5064304045874947e-05, "loss": 0.9323, "step": 6011 }, { "epoch": 0.3511682242990654, "grad_norm": 1.5412824153900146, "learning_rate": 1.5062672656239381e-05, "loss": 0.8088, "step": 6012 }, { "epoch": 0.35122663551401867, "grad_norm": 1.7780535221099854, "learning_rate": 1.5061041085407436e-05, "loss": 1.0322, "step": 6013 }, { "epoch": 0.351285046728972, "grad_norm": 1.0625832080841064, "learning_rate": 1.5059409333437501e-05, "loss": 0.68, "step": 6014 }, { "epoch": 0.35134345794392524, "grad_norm": 1.5201342105865479, "learning_rate": 1.505777740038798e-05, "loss": 0.7149, "step": 6015 }, { "epoch": 0.3514018691588785, "grad_norm": 1.529176115989685, "learning_rate": 1.5056145286317278e-05, "loss": 0.8243, "step": 6016 }, { "epoch": 0.35146028037383176, "grad_norm": 2.611173152923584, "learning_rate": 1.5054512991283814e-05, "loss": 0.821, "step": 6017 }, { "epoch": 0.35151869158878507, "grad_norm": 1.083050012588501, "learning_rate": 1.5052880515346007e-05, "loss": 0.8158, "step": 6018 }, { "epoch": 0.35157710280373833, "grad_norm": 1.4917948246002197, "learning_rate": 1.5051247858562286e-05, "loss": 0.6942, "step": 6019 }, { "epoch": 0.3516355140186916, "grad_norm": 1.780456304550171, "learning_rate": 1.5049615020991077e-05, "loss": 0.8951, "step": 6020 }, { "epoch": 0.35169392523364484, "grad_norm": 1.3471144437789917, "learning_rate": 1.504798200269083e-05, "loss": 0.8886, "step": 6021 }, { "epoch": 0.35175233644859816, "grad_norm": 2.138436794281006, "learning_rate": 1.5046348803719989e-05, "loss": 0.8377, "step": 6022 }, { "epoch": 0.3518107476635514, "grad_norm": 1.9378929138183594, "learning_rate": 1.5044715424137003e-05, "loss": 0.8349, "step": 6023 }, { "epoch": 0.3518691588785047, "grad_norm": 1.3549485206604004, "learning_rate": 1.5043081864000337e-05, "loss": 0.8595, "step": 6024 }, { "epoch": 0.35192757009345793, "grad_norm": 2.7818832397460938, "learning_rate": 1.5041448123368454e-05, "loss": 0.8046, "step": 6025 }, { "epoch": 0.3519859813084112, "grad_norm": 1.3364967107772827, "learning_rate": 1.503981420229983e-05, "loss": 0.7853, "step": 6026 }, { "epoch": 0.3520443925233645, "grad_norm": 1.8190758228302002, "learning_rate": 1.503818010085294e-05, "loss": 0.8363, "step": 6027 }, { "epoch": 0.35210280373831776, "grad_norm": 1.0862805843353271, "learning_rate": 1.5036545819086273e-05, "loss": 0.7428, "step": 6028 }, { "epoch": 0.352161214953271, "grad_norm": 1.4658578634262085, "learning_rate": 1.503491135705832e-05, "loss": 0.8534, "step": 6029 }, { "epoch": 0.3522196261682243, "grad_norm": 2.0126047134399414, "learning_rate": 1.5033276714827575e-05, "loss": 0.8505, "step": 6030 }, { "epoch": 0.3522780373831776, "grad_norm": 2.673180103302002, "learning_rate": 1.503164189245255e-05, "loss": 0.6942, "step": 6031 }, { "epoch": 0.35233644859813085, "grad_norm": 2.059511184692383, "learning_rate": 1.5030006889991753e-05, "loss": 0.9474, "step": 6032 }, { "epoch": 0.3523948598130841, "grad_norm": 1.1596925258636475, "learning_rate": 1.5028371707503704e-05, "loss": 0.8281, "step": 6033 }, { "epoch": 0.35245327102803736, "grad_norm": 0.9989475607872009, "learning_rate": 1.5026736345046921e-05, "loss": 0.6741, "step": 6034 }, { "epoch": 0.3525116822429907, "grad_norm": 2.573136568069458, "learning_rate": 1.5025100802679944e-05, "loss": 0.8422, "step": 6035 }, { "epoch": 0.35257009345794393, "grad_norm": 1.5665981769561768, "learning_rate": 1.5023465080461303e-05, "loss": 0.913, "step": 6036 }, { "epoch": 0.3526285046728972, "grad_norm": 1.7637943029403687, "learning_rate": 1.5021829178449544e-05, "loss": 0.8236, "step": 6037 }, { "epoch": 0.35268691588785045, "grad_norm": 2.0626347064971924, "learning_rate": 1.5020193096703212e-05, "loss": 0.8853, "step": 6038 }, { "epoch": 0.35274532710280376, "grad_norm": 1.5351635217666626, "learning_rate": 1.5018556835280875e-05, "loss": 0.8564, "step": 6039 }, { "epoch": 0.352803738317757, "grad_norm": 2.710651159286499, "learning_rate": 1.5016920394241089e-05, "loss": 0.9111, "step": 6040 }, { "epoch": 0.3528621495327103, "grad_norm": 1.1102235317230225, "learning_rate": 1.501528377364242e-05, "loss": 0.8686, "step": 6041 }, { "epoch": 0.35292056074766354, "grad_norm": 3.212465763092041, "learning_rate": 1.5013646973543448e-05, "loss": 0.9127, "step": 6042 }, { "epoch": 0.35297897196261685, "grad_norm": 1.128391981124878, "learning_rate": 1.5012009994002755e-05, "loss": 0.7337, "step": 6043 }, { "epoch": 0.3530373831775701, "grad_norm": 1.8085830211639404, "learning_rate": 1.501037283507893e-05, "loss": 0.8635, "step": 6044 }, { "epoch": 0.35309579439252337, "grad_norm": 2.26346755027771, "learning_rate": 1.5008735496830562e-05, "loss": 0.8197, "step": 6045 }, { "epoch": 0.3531542056074766, "grad_norm": 1.1979869604110718, "learning_rate": 1.500709797931626e-05, "loss": 0.9029, "step": 6046 }, { "epoch": 0.3532126168224299, "grad_norm": 2.74731707572937, "learning_rate": 1.5005460282594631e-05, "loss": 0.8973, "step": 6047 }, { "epoch": 0.3532710280373832, "grad_norm": 1.745827555656433, "learning_rate": 1.5003822406724285e-05, "loss": 0.9602, "step": 6048 }, { "epoch": 0.35332943925233645, "grad_norm": 3.023080587387085, "learning_rate": 1.5002184351763846e-05, "loss": 0.7758, "step": 6049 }, { "epoch": 0.3533878504672897, "grad_norm": 2.2098591327667236, "learning_rate": 1.500054611777194e-05, "loss": 0.7008, "step": 6050 }, { "epoch": 0.35344626168224297, "grad_norm": 2.2193210124969482, "learning_rate": 1.49989077048072e-05, "loss": 0.9924, "step": 6051 }, { "epoch": 0.3535046728971963, "grad_norm": 1.6937077045440674, "learning_rate": 1.4997269112928267e-05, "loss": 0.7862, "step": 6052 }, { "epoch": 0.35356308411214954, "grad_norm": 2.3974769115448, "learning_rate": 1.4995630342193787e-05, "loss": 0.9092, "step": 6053 }, { "epoch": 0.3536214953271028, "grad_norm": 1.3925247192382812, "learning_rate": 1.4993991392662412e-05, "loss": 0.8204, "step": 6054 }, { "epoch": 0.35367990654205606, "grad_norm": 2.370361804962158, "learning_rate": 1.4992352264392803e-05, "loss": 1.0055, "step": 6055 }, { "epoch": 0.35373831775700937, "grad_norm": 1.519659399986267, "learning_rate": 1.4990712957443619e-05, "loss": 0.9846, "step": 6056 }, { "epoch": 0.3537967289719626, "grad_norm": 1.3510537147521973, "learning_rate": 1.498907347187354e-05, "loss": 0.9034, "step": 6057 }, { "epoch": 0.3538551401869159, "grad_norm": 1.367706537246704, "learning_rate": 1.4987433807741242e-05, "loss": 0.7041, "step": 6058 }, { "epoch": 0.35391355140186914, "grad_norm": 1.6537432670593262, "learning_rate": 1.4985793965105409e-05, "loss": 0.6955, "step": 6059 }, { "epoch": 0.35397196261682246, "grad_norm": 1.0576032400131226, "learning_rate": 1.4984153944024731e-05, "loss": 0.8927, "step": 6060 }, { "epoch": 0.3540303738317757, "grad_norm": 2.298311471939087, "learning_rate": 1.4982513744557905e-05, "loss": 0.8327, "step": 6061 }, { "epoch": 0.35408878504672897, "grad_norm": 1.2108176946640015, "learning_rate": 1.4980873366763635e-05, "loss": 0.698, "step": 6062 }, { "epoch": 0.35414719626168223, "grad_norm": 1.6882247924804688, "learning_rate": 1.4979232810700638e-05, "loss": 0.9909, "step": 6063 }, { "epoch": 0.3542056074766355, "grad_norm": 2.123756170272827, "learning_rate": 1.4977592076427619e-05, "loss": 0.8534, "step": 6064 }, { "epoch": 0.3542640186915888, "grad_norm": 1.6555490493774414, "learning_rate": 1.4975951164003308e-05, "loss": 0.8808, "step": 6065 }, { "epoch": 0.35432242990654206, "grad_norm": 1.8482822179794312, "learning_rate": 1.4974310073486433e-05, "loss": 0.8992, "step": 6066 }, { "epoch": 0.3543808411214953, "grad_norm": 2.65264892578125, "learning_rate": 1.497266880493573e-05, "loss": 0.9419, "step": 6067 }, { "epoch": 0.3544392523364486, "grad_norm": 1.3537558317184448, "learning_rate": 1.4971027358409943e-05, "loss": 0.939, "step": 6068 }, { "epoch": 0.3544976635514019, "grad_norm": 1.4145818948745728, "learning_rate": 1.4969385733967816e-05, "loss": 0.8034, "step": 6069 }, { "epoch": 0.35455607476635514, "grad_norm": 1.5775353908538818, "learning_rate": 1.4967743931668107e-05, "loss": 0.9685, "step": 6070 }, { "epoch": 0.3546144859813084, "grad_norm": 1.6597049236297607, "learning_rate": 1.4966101951569576e-05, "loss": 0.8732, "step": 6071 }, { "epoch": 0.35467289719626166, "grad_norm": 1.3499128818511963, "learning_rate": 1.4964459793730992e-05, "loss": 0.7118, "step": 6072 }, { "epoch": 0.354731308411215, "grad_norm": 1.5532042980194092, "learning_rate": 1.4962817458211124e-05, "loss": 0.8874, "step": 6073 }, { "epoch": 0.35478971962616823, "grad_norm": 1.2074140310287476, "learning_rate": 1.4961174945068761e-05, "loss": 0.9802, "step": 6074 }, { "epoch": 0.3548481308411215, "grad_norm": 1.3015798330307007, "learning_rate": 1.495953225436268e-05, "loss": 0.9019, "step": 6075 }, { "epoch": 0.35490654205607475, "grad_norm": 1.265791416168213, "learning_rate": 1.4957889386151683e-05, "loss": 0.8625, "step": 6076 }, { "epoch": 0.35496495327102806, "grad_norm": 1.5390198230743408, "learning_rate": 1.4956246340494565e-05, "loss": 0.9133, "step": 6077 }, { "epoch": 0.3550233644859813, "grad_norm": 1.8049691915512085, "learning_rate": 1.4954603117450128e-05, "loss": 0.8115, "step": 6078 }, { "epoch": 0.3550817757009346, "grad_norm": 1.4243855476379395, "learning_rate": 1.4952959717077189e-05, "loss": 0.9822, "step": 6079 }, { "epoch": 0.35514018691588783, "grad_norm": 1.4746241569519043, "learning_rate": 1.4951316139434567e-05, "loss": 0.9012, "step": 6080 }, { "epoch": 0.35519859813084115, "grad_norm": 1.5084631443023682, "learning_rate": 1.4949672384581082e-05, "loss": 0.7331, "step": 6081 }, { "epoch": 0.3552570093457944, "grad_norm": 2.1572341918945312, "learning_rate": 1.4948028452575572e-05, "loss": 0.9985, "step": 6082 }, { "epoch": 0.35531542056074766, "grad_norm": 1.1249147653579712, "learning_rate": 1.4946384343476865e-05, "loss": 0.7362, "step": 6083 }, { "epoch": 0.3553738317757009, "grad_norm": 1.3848956823349, "learning_rate": 1.4944740057343814e-05, "loss": 0.7787, "step": 6084 }, { "epoch": 0.3554322429906542, "grad_norm": 1.3571304082870483, "learning_rate": 1.4943095594235263e-05, "loss": 0.9742, "step": 6085 }, { "epoch": 0.3554906542056075, "grad_norm": 1.122994065284729, "learning_rate": 1.494145095421007e-05, "loss": 0.9777, "step": 6086 }, { "epoch": 0.35554906542056075, "grad_norm": 1.2692245244979858, "learning_rate": 1.4939806137327102e-05, "loss": 0.7993, "step": 6087 }, { "epoch": 0.355607476635514, "grad_norm": 1.3260761499404907, "learning_rate": 1.4938161143645223e-05, "loss": 0.8167, "step": 6088 }, { "epoch": 0.35566588785046727, "grad_norm": 1.7774426937103271, "learning_rate": 1.4936515973223307e-05, "loss": 0.9186, "step": 6089 }, { "epoch": 0.3557242990654206, "grad_norm": 1.6834660768508911, "learning_rate": 1.4934870626120242e-05, "loss": 0.6495, "step": 6090 }, { "epoch": 0.35578271028037384, "grad_norm": 1.1507326364517212, "learning_rate": 1.4933225102394909e-05, "loss": 0.7707, "step": 6091 }, { "epoch": 0.3558411214953271, "grad_norm": 1.936310052871704, "learning_rate": 1.4931579402106209e-05, "loss": 0.856, "step": 6092 }, { "epoch": 0.35589953271028035, "grad_norm": 0.9878029227256775, "learning_rate": 1.4929933525313038e-05, "loss": 0.7161, "step": 6093 }, { "epoch": 0.35595794392523367, "grad_norm": 1.3224108219146729, "learning_rate": 1.4928287472074306e-05, "loss": 0.7471, "step": 6094 }, { "epoch": 0.3560163551401869, "grad_norm": 1.5073833465576172, "learning_rate": 1.4926641242448923e-05, "loss": 0.862, "step": 6095 }, { "epoch": 0.3560747663551402, "grad_norm": 0.9641665816307068, "learning_rate": 1.492499483649581e-05, "loss": 0.763, "step": 6096 }, { "epoch": 0.35613317757009344, "grad_norm": 1.763733983039856, "learning_rate": 1.4923348254273896e-05, "loss": 0.8199, "step": 6097 }, { "epoch": 0.35619158878504675, "grad_norm": 1.2752174139022827, "learning_rate": 1.492170149584211e-05, "loss": 0.8626, "step": 6098 }, { "epoch": 0.35625, "grad_norm": 1.7728581428527832, "learning_rate": 1.4920054561259391e-05, "loss": 0.7632, "step": 6099 }, { "epoch": 0.35630841121495327, "grad_norm": 1.10450279712677, "learning_rate": 1.4918407450584684e-05, "loss": 0.8579, "step": 6100 }, { "epoch": 0.3563668224299065, "grad_norm": 1.3081777095794678, "learning_rate": 1.491676016387694e-05, "loss": 0.6846, "step": 6101 }, { "epoch": 0.35642523364485984, "grad_norm": 1.4306941032409668, "learning_rate": 1.4915112701195122e-05, "loss": 0.9464, "step": 6102 }, { "epoch": 0.3564836448598131, "grad_norm": 1.3353914022445679, "learning_rate": 1.4913465062598182e-05, "loss": 0.7769, "step": 6103 }, { "epoch": 0.35654205607476636, "grad_norm": 1.8234585523605347, "learning_rate": 1.49118172481451e-05, "loss": 0.8179, "step": 6104 }, { "epoch": 0.3566004672897196, "grad_norm": 1.2379801273345947, "learning_rate": 1.491016925789485e-05, "loss": 0.7377, "step": 6105 }, { "epoch": 0.35665887850467287, "grad_norm": 1.6216355562210083, "learning_rate": 1.490852109190641e-05, "loss": 0.8508, "step": 6106 }, { "epoch": 0.3567172897196262, "grad_norm": 1.1704356670379639, "learning_rate": 1.4906872750238777e-05, "loss": 0.9225, "step": 6107 }, { "epoch": 0.35677570093457944, "grad_norm": 1.967308521270752, "learning_rate": 1.4905224232950937e-05, "loss": 0.8135, "step": 6108 }, { "epoch": 0.3568341121495327, "grad_norm": 1.1428700685501099, "learning_rate": 1.49035755401019e-05, "loss": 0.8117, "step": 6109 }, { "epoch": 0.35689252336448596, "grad_norm": 1.036210536956787, "learning_rate": 1.4901926671750668e-05, "loss": 0.9213, "step": 6110 }, { "epoch": 0.35695093457943927, "grad_norm": 1.5490504503250122, "learning_rate": 1.4900277627956262e-05, "loss": 0.7638, "step": 6111 }, { "epoch": 0.35700934579439253, "grad_norm": 1.422957420349121, "learning_rate": 1.4898628408777694e-05, "loss": 1.0041, "step": 6112 }, { "epoch": 0.3570677570093458, "grad_norm": 1.8514721393585205, "learning_rate": 1.4896979014273995e-05, "loss": 0.8165, "step": 6113 }, { "epoch": 0.35712616822429905, "grad_norm": 0.9789102077484131, "learning_rate": 1.4895329444504194e-05, "loss": 0.7041, "step": 6114 }, { "epoch": 0.35718457943925236, "grad_norm": 2.3663649559020996, "learning_rate": 1.4893679699527339e-05, "loss": 0.9046, "step": 6115 }, { "epoch": 0.3572429906542056, "grad_norm": 1.2355211973190308, "learning_rate": 1.4892029779402469e-05, "loss": 0.8552, "step": 6116 }, { "epoch": 0.3573014018691589, "grad_norm": 2.7414050102233887, "learning_rate": 1.4890379684188634e-05, "loss": 0.758, "step": 6117 }, { "epoch": 0.35735981308411213, "grad_norm": 0.9693808555603027, "learning_rate": 1.4888729413944896e-05, "loss": 0.6042, "step": 6118 }, { "epoch": 0.35741822429906545, "grad_norm": 1.2585233449935913, "learning_rate": 1.4887078968730314e-05, "loss": 0.7636, "step": 6119 }, { "epoch": 0.3574766355140187, "grad_norm": 1.3953725099563599, "learning_rate": 1.4885428348603968e-05, "loss": 0.903, "step": 6120 }, { "epoch": 0.35753504672897196, "grad_norm": 1.6055067777633667, "learning_rate": 1.4883777553624929e-05, "loss": 0.7222, "step": 6121 }, { "epoch": 0.3575934579439252, "grad_norm": 1.745919942855835, "learning_rate": 1.4882126583852276e-05, "loss": 0.9007, "step": 6122 }, { "epoch": 0.3576518691588785, "grad_norm": 1.621069312095642, "learning_rate": 1.4880475439345106e-05, "loss": 0.8993, "step": 6123 }, { "epoch": 0.3577102803738318, "grad_norm": 1.505040168762207, "learning_rate": 1.487882412016251e-05, "loss": 0.867, "step": 6124 }, { "epoch": 0.35776869158878505, "grad_norm": 1.8845736980438232, "learning_rate": 1.4877172626363589e-05, "loss": 0.9422, "step": 6125 }, { "epoch": 0.3578271028037383, "grad_norm": 1.5918012857437134, "learning_rate": 1.4875520958007457e-05, "loss": 0.9601, "step": 6126 }, { "epoch": 0.35788551401869156, "grad_norm": 1.4911104440689087, "learning_rate": 1.4873869115153223e-05, "loss": 0.657, "step": 6127 }, { "epoch": 0.3579439252336449, "grad_norm": 1.2040661573410034, "learning_rate": 1.4872217097860006e-05, "loss": 0.8562, "step": 6128 }, { "epoch": 0.35800233644859814, "grad_norm": 1.3778356313705444, "learning_rate": 1.4870564906186938e-05, "loss": 0.7703, "step": 6129 }, { "epoch": 0.3580607476635514, "grad_norm": 1.421692967414856, "learning_rate": 1.4868912540193148e-05, "loss": 0.8264, "step": 6130 }, { "epoch": 0.35811915887850465, "grad_norm": 1.368129849433899, "learning_rate": 1.4867259999937778e-05, "loss": 0.7374, "step": 6131 }, { "epoch": 0.35817757009345796, "grad_norm": 1.343214750289917, "learning_rate": 1.4865607285479973e-05, "loss": 0.9386, "step": 6132 }, { "epoch": 0.3582359813084112, "grad_norm": 2.013751983642578, "learning_rate": 1.486395439687888e-05, "loss": 0.7462, "step": 6133 }, { "epoch": 0.3582943925233645, "grad_norm": 1.2350176572799683, "learning_rate": 1.4862301334193666e-05, "loss": 0.893, "step": 6134 }, { "epoch": 0.35835280373831774, "grad_norm": 1.5113344192504883, "learning_rate": 1.4860648097483488e-05, "loss": 0.9135, "step": 6135 }, { "epoch": 0.35841121495327105, "grad_norm": 1.2370582818984985, "learning_rate": 1.4858994686807517e-05, "loss": 0.6737, "step": 6136 }, { "epoch": 0.3584696261682243, "grad_norm": 1.5420737266540527, "learning_rate": 1.4857341102224933e-05, "loss": 0.9982, "step": 6137 }, { "epoch": 0.35852803738317757, "grad_norm": 1.1625635623931885, "learning_rate": 1.4855687343794919e-05, "loss": 0.7701, "step": 6138 }, { "epoch": 0.3585864485981308, "grad_norm": 0.9075958728790283, "learning_rate": 1.4854033411576659e-05, "loss": 0.644, "step": 6139 }, { "epoch": 0.35864485981308414, "grad_norm": 1.356268048286438, "learning_rate": 1.4852379305629355e-05, "loss": 0.7946, "step": 6140 }, { "epoch": 0.3587032710280374, "grad_norm": 1.3966565132141113, "learning_rate": 1.4850725026012202e-05, "loss": 0.8226, "step": 6141 }, { "epoch": 0.35876168224299065, "grad_norm": 1.3708546161651611, "learning_rate": 1.4849070572784412e-05, "loss": 0.7309, "step": 6142 }, { "epoch": 0.3588200934579439, "grad_norm": 1.2790744304656982, "learning_rate": 1.4847415946005199e-05, "loss": 0.7245, "step": 6143 }, { "epoch": 0.35887850467289717, "grad_norm": 1.478148102760315, "learning_rate": 1.484576114573378e-05, "loss": 0.8344, "step": 6144 }, { "epoch": 0.3589369158878505, "grad_norm": 1.4284682273864746, "learning_rate": 1.4844106172029387e-05, "loss": 0.7236, "step": 6145 }, { "epoch": 0.35899532710280374, "grad_norm": 1.228766918182373, "learning_rate": 1.4842451024951246e-05, "loss": 0.7866, "step": 6146 }, { "epoch": 0.359053738317757, "grad_norm": 1.3390235900878906, "learning_rate": 1.4840795704558599e-05, "loss": 0.8133, "step": 6147 }, { "epoch": 0.35911214953271026, "grad_norm": 1.6607812643051147, "learning_rate": 1.483914021091069e-05, "loss": 0.8272, "step": 6148 }, { "epoch": 0.35917056074766357, "grad_norm": 1.707533597946167, "learning_rate": 1.4837484544066773e-05, "loss": 0.8252, "step": 6149 }, { "epoch": 0.3592289719626168, "grad_norm": 1.4081734418869019, "learning_rate": 1.4835828704086105e-05, "loss": 0.8724, "step": 6150 }, { "epoch": 0.3592873831775701, "grad_norm": 1.3027396202087402, "learning_rate": 1.4834172691027947e-05, "loss": 0.8825, "step": 6151 }, { "epoch": 0.35934579439252334, "grad_norm": 1.5196313858032227, "learning_rate": 1.4832516504951566e-05, "loss": 0.7959, "step": 6152 }, { "epoch": 0.35940420560747666, "grad_norm": 1.373347282409668, "learning_rate": 1.4830860145916244e-05, "loss": 0.8829, "step": 6153 }, { "epoch": 0.3594626168224299, "grad_norm": 1.3932896852493286, "learning_rate": 1.4829203613981263e-05, "loss": 0.8091, "step": 6154 }, { "epoch": 0.3595210280373832, "grad_norm": 1.2937719821929932, "learning_rate": 1.4827546909205908e-05, "loss": 0.8782, "step": 6155 }, { "epoch": 0.35957943925233643, "grad_norm": 1.6670395135879517, "learning_rate": 1.4825890031649475e-05, "loss": 0.9135, "step": 6156 }, { "epoch": 0.35963785046728974, "grad_norm": 1.562244176864624, "learning_rate": 1.4824232981371265e-05, "loss": 0.8349, "step": 6157 }, { "epoch": 0.359696261682243, "grad_norm": 2.3165032863616943, "learning_rate": 1.4822575758430581e-05, "loss": 0.8686, "step": 6158 }, { "epoch": 0.35975467289719626, "grad_norm": 1.4446004629135132, "learning_rate": 1.4820918362886745e-05, "loss": 0.741, "step": 6159 }, { "epoch": 0.3598130841121495, "grad_norm": 1.6352874040603638, "learning_rate": 1.4819260794799071e-05, "loss": 0.8978, "step": 6160 }, { "epoch": 0.35987149532710283, "grad_norm": 1.1073966026306152, "learning_rate": 1.4817603054226882e-05, "loss": 0.7421, "step": 6161 }, { "epoch": 0.3599299065420561, "grad_norm": 1.879271149635315, "learning_rate": 1.4815945141229511e-05, "loss": 0.8781, "step": 6162 }, { "epoch": 0.35998831775700935, "grad_norm": 1.7439955472946167, "learning_rate": 1.48142870558663e-05, "loss": 0.8438, "step": 6163 }, { "epoch": 0.3600467289719626, "grad_norm": 1.430033564567566, "learning_rate": 1.4812628798196586e-05, "loss": 0.8026, "step": 6164 }, { "epoch": 0.36010514018691586, "grad_norm": 2.331807851791382, "learning_rate": 1.4810970368279726e-05, "loss": 1.0298, "step": 6165 }, { "epoch": 0.3601635514018692, "grad_norm": 1.4262323379516602, "learning_rate": 1.4809311766175071e-05, "loss": 0.7358, "step": 6166 }, { "epoch": 0.36022196261682243, "grad_norm": 2.2520627975463867, "learning_rate": 1.4807652991941988e-05, "loss": 0.7379, "step": 6167 }, { "epoch": 0.3602803738317757, "grad_norm": 1.3283578157424927, "learning_rate": 1.4805994045639842e-05, "loss": 0.7734, "step": 6168 }, { "epoch": 0.36033878504672895, "grad_norm": 1.2629196643829346, "learning_rate": 1.480433492732801e-05, "loss": 0.6034, "step": 6169 }, { "epoch": 0.36039719626168226, "grad_norm": 3.3804008960723877, "learning_rate": 1.4802675637065871e-05, "loss": 0.9918, "step": 6170 }, { "epoch": 0.3604556074766355, "grad_norm": 1.1851190328598022, "learning_rate": 1.4801016174912815e-05, "loss": 0.8252, "step": 6171 }, { "epoch": 0.3605140186915888, "grad_norm": 3.317741870880127, "learning_rate": 1.4799356540928229e-05, "loss": 1.0638, "step": 6172 }, { "epoch": 0.36057242990654204, "grad_norm": 2.1444005966186523, "learning_rate": 1.4797696735171521e-05, "loss": 0.781, "step": 6173 }, { "epoch": 0.36063084112149535, "grad_norm": 2.344280242919922, "learning_rate": 1.479603675770209e-05, "loss": 1.1191, "step": 6174 }, { "epoch": 0.3606892523364486, "grad_norm": 1.4881080389022827, "learning_rate": 1.4794376608579352e-05, "loss": 0.641, "step": 6175 }, { "epoch": 0.36074766355140186, "grad_norm": 1.4181214570999146, "learning_rate": 1.4792716287862723e-05, "loss": 0.8265, "step": 6176 }, { "epoch": 0.3608060747663551, "grad_norm": 1.0808285474777222, "learning_rate": 1.4791055795611623e-05, "loss": 0.634, "step": 6177 }, { "epoch": 0.36086448598130844, "grad_norm": 1.3694076538085938, "learning_rate": 1.4789395131885489e-05, "loss": 0.9061, "step": 6178 }, { "epoch": 0.3609228971962617, "grad_norm": 1.33843994140625, "learning_rate": 1.4787734296743757e-05, "loss": 0.8558, "step": 6179 }, { "epoch": 0.36098130841121495, "grad_norm": 1.9353058338165283, "learning_rate": 1.4786073290245862e-05, "loss": 0.7089, "step": 6180 }, { "epoch": 0.3610397196261682, "grad_norm": 1.2695413827896118, "learning_rate": 1.4784412112451257e-05, "loss": 0.8863, "step": 6181 }, { "epoch": 0.3610981308411215, "grad_norm": 1.4754056930541992, "learning_rate": 1.4782750763419398e-05, "loss": 0.6459, "step": 6182 }, { "epoch": 0.3611565420560748, "grad_norm": 0.9023260474205017, "learning_rate": 1.4781089243209744e-05, "loss": 0.7924, "step": 6183 }, { "epoch": 0.36121495327102804, "grad_norm": 2.2652902603149414, "learning_rate": 1.4779427551881764e-05, "loss": 0.8901, "step": 6184 }, { "epoch": 0.3612733644859813, "grad_norm": 1.2385401725769043, "learning_rate": 1.4777765689494928e-05, "loss": 0.6845, "step": 6185 }, { "epoch": 0.36133177570093455, "grad_norm": 1.277161955833435, "learning_rate": 1.4776103656108716e-05, "loss": 0.7351, "step": 6186 }, { "epoch": 0.36139018691588787, "grad_norm": 1.9937400817871094, "learning_rate": 1.4774441451782613e-05, "loss": 0.9456, "step": 6187 }, { "epoch": 0.3614485981308411, "grad_norm": 1.2612786293029785, "learning_rate": 1.4772779076576113e-05, "loss": 0.8407, "step": 6188 }, { "epoch": 0.3615070093457944, "grad_norm": 3.106670379638672, "learning_rate": 1.4771116530548713e-05, "loss": 0.9644, "step": 6189 }, { "epoch": 0.36156542056074764, "grad_norm": 1.4969812631607056, "learning_rate": 1.4769453813759914e-05, "loss": 0.7985, "step": 6190 }, { "epoch": 0.36162383177570095, "grad_norm": 1.358338713645935, "learning_rate": 1.4767790926269222e-05, "loss": 0.9699, "step": 6191 }, { "epoch": 0.3616822429906542, "grad_norm": 1.0406771898269653, "learning_rate": 1.4766127868136165e-05, "loss": 0.7224, "step": 6192 }, { "epoch": 0.36174065420560747, "grad_norm": 1.9368988275527954, "learning_rate": 1.4764464639420258e-05, "loss": 0.8777, "step": 6193 }, { "epoch": 0.36179906542056073, "grad_norm": 1.5135765075683594, "learning_rate": 1.4762801240181023e-05, "loss": 0.8413, "step": 6194 }, { "epoch": 0.36185747663551404, "grad_norm": 1.7165069580078125, "learning_rate": 1.4761137670478006e-05, "loss": 0.9637, "step": 6195 }, { "epoch": 0.3619158878504673, "grad_norm": 0.8856866359710693, "learning_rate": 1.4759473930370738e-05, "loss": 0.7489, "step": 6196 }, { "epoch": 0.36197429906542056, "grad_norm": 1.9161853790283203, "learning_rate": 1.4757810019918766e-05, "loss": 0.9725, "step": 6197 }, { "epoch": 0.3620327102803738, "grad_norm": 1.7305020093917847, "learning_rate": 1.4756145939181652e-05, "loss": 0.9356, "step": 6198 }, { "epoch": 0.36209112149532713, "grad_norm": 1.3390377759933472, "learning_rate": 1.475448168821894e-05, "loss": 0.7437, "step": 6199 }, { "epoch": 0.3621495327102804, "grad_norm": 2.296884775161743, "learning_rate": 1.4752817267090207e-05, "loss": 0.7617, "step": 6200 }, { "epoch": 0.36220794392523364, "grad_norm": 1.2698488235473633, "learning_rate": 1.4751152675855018e-05, "loss": 0.9734, "step": 6201 }, { "epoch": 0.3622663551401869, "grad_norm": 1.6359881162643433, "learning_rate": 1.474948791457295e-05, "loss": 0.9326, "step": 6202 }, { "epoch": 0.36232476635514016, "grad_norm": 1.5701266527175903, "learning_rate": 1.474782298330359e-05, "loss": 0.9959, "step": 6203 }, { "epoch": 0.3623831775700935, "grad_norm": 1.6570007801055908, "learning_rate": 1.474615788210652e-05, "loss": 0.8609, "step": 6204 }, { "epoch": 0.36244158878504673, "grad_norm": 2.6084327697753906, "learning_rate": 1.4744492611041339e-05, "loss": 0.8372, "step": 6205 }, { "epoch": 0.3625, "grad_norm": 1.0823386907577515, "learning_rate": 1.4742827170167648e-05, "loss": 0.8034, "step": 6206 }, { "epoch": 0.36255841121495325, "grad_norm": 3.5782315731048584, "learning_rate": 1.4741161559545056e-05, "loss": 0.9065, "step": 6207 }, { "epoch": 0.36261682242990656, "grad_norm": 1.1276757717132568, "learning_rate": 1.4739495779233176e-05, "loss": 0.6997, "step": 6208 }, { "epoch": 0.3626752336448598, "grad_norm": 2.580622434616089, "learning_rate": 1.4737829829291621e-05, "loss": 0.7877, "step": 6209 }, { "epoch": 0.3627336448598131, "grad_norm": 2.0546207427978516, "learning_rate": 1.4736163709780023e-05, "loss": 0.8865, "step": 6210 }, { "epoch": 0.36279205607476633, "grad_norm": 1.7863067388534546, "learning_rate": 1.4734497420758012e-05, "loss": 0.8426, "step": 6211 }, { "epoch": 0.36285046728971965, "grad_norm": 1.9059655666351318, "learning_rate": 1.4732830962285225e-05, "loss": 0.845, "step": 6212 }, { "epoch": 0.3629088785046729, "grad_norm": 1.022812008857727, "learning_rate": 1.4731164334421307e-05, "loss": 0.6034, "step": 6213 }, { "epoch": 0.36296728971962616, "grad_norm": 1.935492992401123, "learning_rate": 1.4729497537225905e-05, "loss": 0.8263, "step": 6214 }, { "epoch": 0.3630257009345794, "grad_norm": 1.1010535955429077, "learning_rate": 1.472783057075868e-05, "loss": 0.897, "step": 6215 }, { "epoch": 0.36308411214953273, "grad_norm": 1.1892808675765991, "learning_rate": 1.4726163435079283e-05, "loss": 0.8061, "step": 6216 }, { "epoch": 0.363142523364486, "grad_norm": 1.3848965167999268, "learning_rate": 1.4724496130247396e-05, "loss": 0.7923, "step": 6217 }, { "epoch": 0.36320093457943925, "grad_norm": 1.3134040832519531, "learning_rate": 1.4722828656322684e-05, "loss": 1.0713, "step": 6218 }, { "epoch": 0.3632593457943925, "grad_norm": 1.9400242567062378, "learning_rate": 1.4721161013364829e-05, "loss": 0.7118, "step": 6219 }, { "epoch": 0.3633177570093458, "grad_norm": 1.2836003303527832, "learning_rate": 1.4719493201433516e-05, "loss": 0.9014, "step": 6220 }, { "epoch": 0.3633761682242991, "grad_norm": 1.718618631362915, "learning_rate": 1.471782522058844e-05, "loss": 0.9728, "step": 6221 }, { "epoch": 0.36343457943925234, "grad_norm": 1.5744364261627197, "learning_rate": 1.4716157070889296e-05, "loss": 0.7933, "step": 6222 }, { "epoch": 0.3634929906542056, "grad_norm": 1.765028715133667, "learning_rate": 1.4714488752395792e-05, "loss": 0.809, "step": 6223 }, { "epoch": 0.36355140186915885, "grad_norm": 2.5471177101135254, "learning_rate": 1.471282026516763e-05, "loss": 0.8956, "step": 6224 }, { "epoch": 0.36360981308411217, "grad_norm": 1.1683839559555054, "learning_rate": 1.4711151609264538e-05, "loss": 0.7105, "step": 6225 }, { "epoch": 0.3636682242990654, "grad_norm": 1.4875532388687134, "learning_rate": 1.470948278474623e-05, "loss": 0.7928, "step": 6226 }, { "epoch": 0.3637266355140187, "grad_norm": 1.2475216388702393, "learning_rate": 1.4707813791672438e-05, "loss": 0.8919, "step": 6227 }, { "epoch": 0.36378504672897194, "grad_norm": 1.0727487802505493, "learning_rate": 1.4706144630102892e-05, "loss": 0.9808, "step": 6228 }, { "epoch": 0.36384345794392525, "grad_norm": 1.1517120599746704, "learning_rate": 1.4704475300097339e-05, "loss": 0.7307, "step": 6229 }, { "epoch": 0.3639018691588785, "grad_norm": 1.1493209600448608, "learning_rate": 1.4702805801715519e-05, "loss": 0.8944, "step": 6230 }, { "epoch": 0.36396028037383177, "grad_norm": 1.7085391283035278, "learning_rate": 1.4701136135017186e-05, "loss": 0.8788, "step": 6231 }, { "epoch": 0.364018691588785, "grad_norm": 1.818114995956421, "learning_rate": 1.4699466300062102e-05, "loss": 0.8642, "step": 6232 }, { "epoch": 0.36407710280373834, "grad_norm": 1.5577473640441895, "learning_rate": 1.469779629691003e-05, "loss": 0.8383, "step": 6233 }, { "epoch": 0.3641355140186916, "grad_norm": 1.5754703283309937, "learning_rate": 1.4696126125620738e-05, "loss": 0.664, "step": 6234 }, { "epoch": 0.36419392523364486, "grad_norm": 1.9719074964523315, "learning_rate": 1.4694455786254003e-05, "loss": 0.8502, "step": 6235 }, { "epoch": 0.3642523364485981, "grad_norm": 1.2961608171463013, "learning_rate": 1.4692785278869611e-05, "loss": 0.9236, "step": 6236 }, { "epoch": 0.3643107476635514, "grad_norm": 2.2522671222686768, "learning_rate": 1.469111460352735e-05, "loss": 0.9896, "step": 6237 }, { "epoch": 0.3643691588785047, "grad_norm": 1.2210865020751953, "learning_rate": 1.4689443760287008e-05, "loss": 0.8696, "step": 6238 }, { "epoch": 0.36442757009345794, "grad_norm": 2.0595030784606934, "learning_rate": 1.4687772749208392e-05, "loss": 0.8202, "step": 6239 }, { "epoch": 0.3644859813084112, "grad_norm": 1.441346287727356, "learning_rate": 1.468610157035131e-05, "loss": 0.6622, "step": 6240 }, { "epoch": 0.3645443925233645, "grad_norm": 1.9402023553848267, "learning_rate": 1.4684430223775568e-05, "loss": 0.8637, "step": 6241 }, { "epoch": 0.36460280373831777, "grad_norm": 2.3536531925201416, "learning_rate": 1.4682758709540992e-05, "loss": 0.8763, "step": 6242 }, { "epoch": 0.36466121495327103, "grad_norm": 1.4165785312652588, "learning_rate": 1.46810870277074e-05, "loss": 0.7731, "step": 6243 }, { "epoch": 0.3647196261682243, "grad_norm": 2.0457327365875244, "learning_rate": 1.4679415178334627e-05, "loss": 0.8599, "step": 6244 }, { "epoch": 0.36477803738317754, "grad_norm": 1.4140307903289795, "learning_rate": 1.4677743161482506e-05, "loss": 0.9333, "step": 6245 }, { "epoch": 0.36483644859813086, "grad_norm": 1.437935709953308, "learning_rate": 1.4676070977210884e-05, "loss": 0.7999, "step": 6246 }, { "epoch": 0.3648948598130841, "grad_norm": 1.9605622291564941, "learning_rate": 1.4674398625579604e-05, "loss": 0.8227, "step": 6247 }, { "epoch": 0.3649532710280374, "grad_norm": 1.4730733633041382, "learning_rate": 1.4672726106648526e-05, "loss": 0.5708, "step": 6248 }, { "epoch": 0.36501168224299063, "grad_norm": 2.546762466430664, "learning_rate": 1.4671053420477506e-05, "loss": 0.8731, "step": 6249 }, { "epoch": 0.36507009345794394, "grad_norm": 1.306107997894287, "learning_rate": 1.4669380567126415e-05, "loss": 0.9146, "step": 6250 }, { "epoch": 0.3651285046728972, "grad_norm": 3.3600914478302, "learning_rate": 1.4667707546655123e-05, "loss": 1.0334, "step": 6251 }, { "epoch": 0.36518691588785046, "grad_norm": 1.4124171733856201, "learning_rate": 1.4666034359123509e-05, "loss": 0.7234, "step": 6252 }, { "epoch": 0.3652453271028037, "grad_norm": 1.138493299484253, "learning_rate": 1.4664361004591459e-05, "loss": 0.8556, "step": 6253 }, { "epoch": 0.36530373831775703, "grad_norm": 1.8140945434570312, "learning_rate": 1.4662687483118859e-05, "loss": 0.7893, "step": 6254 }, { "epoch": 0.3653621495327103, "grad_norm": 1.334076166152954, "learning_rate": 1.4661013794765607e-05, "loss": 0.7144, "step": 6255 }, { "epoch": 0.36542056074766355, "grad_norm": 1.320191740989685, "learning_rate": 1.465933993959161e-05, "loss": 0.7872, "step": 6256 }, { "epoch": 0.3654789719626168, "grad_norm": 2.163038730621338, "learning_rate": 1.4657665917656772e-05, "loss": 0.9668, "step": 6257 }, { "epoch": 0.3655373831775701, "grad_norm": 1.2074594497680664, "learning_rate": 1.4655991729021005e-05, "loss": 0.7038, "step": 6258 }, { "epoch": 0.3655957943925234, "grad_norm": 1.5162339210510254, "learning_rate": 1.4654317373744238e-05, "loss": 0.8049, "step": 6259 }, { "epoch": 0.36565420560747663, "grad_norm": 1.5521875619888306, "learning_rate": 1.4652642851886388e-05, "loss": 0.701, "step": 6260 }, { "epoch": 0.3657126168224299, "grad_norm": 1.6343330144882202, "learning_rate": 1.4650968163507395e-05, "loss": 0.8707, "step": 6261 }, { "epoch": 0.36577102803738315, "grad_norm": 1.1230140924453735, "learning_rate": 1.4649293308667191e-05, "loss": 0.6109, "step": 6262 }, { "epoch": 0.36582943925233646, "grad_norm": 3.0621097087860107, "learning_rate": 1.464761828742572e-05, "loss": 0.891, "step": 6263 }, { "epoch": 0.3658878504672897, "grad_norm": 1.1952961683273315, "learning_rate": 1.4645943099842939e-05, "loss": 0.806, "step": 6264 }, { "epoch": 0.365946261682243, "grad_norm": 1.9940022230148315, "learning_rate": 1.4644267745978797e-05, "loss": 0.7546, "step": 6265 }, { "epoch": 0.36600467289719624, "grad_norm": 1.6372911930084229, "learning_rate": 1.464259222589326e-05, "loss": 0.7912, "step": 6266 }, { "epoch": 0.36606308411214955, "grad_norm": 1.360054850578308, "learning_rate": 1.4640916539646294e-05, "loss": 0.8993, "step": 6267 }, { "epoch": 0.3661214953271028, "grad_norm": 1.3076791763305664, "learning_rate": 1.4639240687297873e-05, "loss": 0.9132, "step": 6268 }, { "epoch": 0.36617990654205607, "grad_norm": 1.5386590957641602, "learning_rate": 1.4637564668907978e-05, "loss": 0.7918, "step": 6269 }, { "epoch": 0.3662383177570093, "grad_norm": 0.9610258340835571, "learning_rate": 1.4635888484536595e-05, "loss": 0.7066, "step": 6270 }, { "epoch": 0.36629672897196264, "grad_norm": 1.3399714231491089, "learning_rate": 1.4634212134243715e-05, "loss": 0.9939, "step": 6271 }, { "epoch": 0.3663551401869159, "grad_norm": 1.9834893941879272, "learning_rate": 1.4632535618089334e-05, "loss": 0.7782, "step": 6272 }, { "epoch": 0.36641355140186915, "grad_norm": 1.2192968130111694, "learning_rate": 1.463085893613346e-05, "loss": 0.8031, "step": 6273 }, { "epoch": 0.3664719626168224, "grad_norm": 2.2705204486846924, "learning_rate": 1.4629182088436096e-05, "loss": 0.8174, "step": 6274 }, { "epoch": 0.3665303738317757, "grad_norm": 1.4126336574554443, "learning_rate": 1.4627505075057267e-05, "loss": 0.8879, "step": 6275 }, { "epoch": 0.366588785046729, "grad_norm": 1.8387084007263184, "learning_rate": 1.4625827896056982e-05, "loss": 0.7944, "step": 6276 }, { "epoch": 0.36664719626168224, "grad_norm": 1.5045171976089478, "learning_rate": 1.462415055149528e-05, "loss": 0.8669, "step": 6277 }, { "epoch": 0.3667056074766355, "grad_norm": 3.7396819591522217, "learning_rate": 1.4622473041432189e-05, "loss": 0.7996, "step": 6278 }, { "epoch": 0.3667640186915888, "grad_norm": 1.3762288093566895, "learning_rate": 1.4620795365927744e-05, "loss": 0.9214, "step": 6279 }, { "epoch": 0.36682242990654207, "grad_norm": 1.9874415397644043, "learning_rate": 1.4619117525041999e-05, "loss": 1.0425, "step": 6280 }, { "epoch": 0.3668808411214953, "grad_norm": 1.8321479558944702, "learning_rate": 1.4617439518834999e-05, "loss": 0.8854, "step": 6281 }, { "epoch": 0.3669392523364486, "grad_norm": 1.989620327949524, "learning_rate": 1.4615761347366802e-05, "loss": 0.9152, "step": 6282 }, { "epoch": 0.36699766355140184, "grad_norm": 1.5456666946411133, "learning_rate": 1.4614083010697474e-05, "loss": 0.7768, "step": 6283 }, { "epoch": 0.36705607476635516, "grad_norm": 1.339311957359314, "learning_rate": 1.461240450888708e-05, "loss": 0.8442, "step": 6284 }, { "epoch": 0.3671144859813084, "grad_norm": 2.197094202041626, "learning_rate": 1.4610725841995694e-05, "loss": 0.8148, "step": 6285 }, { "epoch": 0.36717289719626167, "grad_norm": 1.3461833000183105, "learning_rate": 1.4609047010083401e-05, "loss": 0.882, "step": 6286 }, { "epoch": 0.36723130841121493, "grad_norm": 1.151607871055603, "learning_rate": 1.4607368013210286e-05, "loss": 0.7158, "step": 6287 }, { "epoch": 0.36728971962616824, "grad_norm": 3.0203428268432617, "learning_rate": 1.4605688851436436e-05, "loss": 0.9595, "step": 6288 }, { "epoch": 0.3673481308411215, "grad_norm": 1.2108798027038574, "learning_rate": 1.4604009524821955e-05, "loss": 0.8415, "step": 6289 }, { "epoch": 0.36740654205607476, "grad_norm": 2.0682320594787598, "learning_rate": 1.4602330033426949e-05, "loss": 0.742, "step": 6290 }, { "epoch": 0.367464953271028, "grad_norm": 2.357485771179199, "learning_rate": 1.4600650377311523e-05, "loss": 0.9115, "step": 6291 }, { "epoch": 0.36752336448598133, "grad_norm": 1.3336420059204102, "learning_rate": 1.4598970556535795e-05, "loss": 0.7098, "step": 6292 }, { "epoch": 0.3675817757009346, "grad_norm": 2.030919313430786, "learning_rate": 1.4597290571159886e-05, "loss": 0.8019, "step": 6293 }, { "epoch": 0.36764018691588785, "grad_norm": 1.7381715774536133, "learning_rate": 1.4595610421243927e-05, "loss": 0.7514, "step": 6294 }, { "epoch": 0.3676985981308411, "grad_norm": 1.3090167045593262, "learning_rate": 1.459393010684805e-05, "loss": 0.7472, "step": 6295 }, { "epoch": 0.3677570093457944, "grad_norm": 2.1249148845672607, "learning_rate": 1.4592249628032389e-05, "loss": 0.8158, "step": 6296 }, { "epoch": 0.3678154205607477, "grad_norm": 1.6175421476364136, "learning_rate": 1.4590568984857098e-05, "loss": 0.6705, "step": 6297 }, { "epoch": 0.36787383177570093, "grad_norm": 1.2910150289535522, "learning_rate": 1.4588888177382324e-05, "loss": 0.9158, "step": 6298 }, { "epoch": 0.3679322429906542, "grad_norm": 1.5802549123764038, "learning_rate": 1.4587207205668223e-05, "loss": 0.7937, "step": 6299 }, { "epoch": 0.3679906542056075, "grad_norm": 1.7385114431381226, "learning_rate": 1.4585526069774965e-05, "loss": 0.8976, "step": 6300 }, { "epoch": 0.36804906542056076, "grad_norm": 1.2255858182907104, "learning_rate": 1.458384476976271e-05, "loss": 0.7308, "step": 6301 }, { "epoch": 0.368107476635514, "grad_norm": 1.5057218074798584, "learning_rate": 1.4582163305691637e-05, "loss": 0.7791, "step": 6302 }, { "epoch": 0.3681658878504673, "grad_norm": 1.9023714065551758, "learning_rate": 1.4580481677621928e-05, "loss": 0.8931, "step": 6303 }, { "epoch": 0.36822429906542054, "grad_norm": 1.5485179424285889, "learning_rate": 1.4578799885613766e-05, "loss": 0.8095, "step": 6304 }, { "epoch": 0.36828271028037385, "grad_norm": 1.3302466869354248, "learning_rate": 1.4577117929727347e-05, "loss": 0.9226, "step": 6305 }, { "epoch": 0.3683411214953271, "grad_norm": 1.440955638885498, "learning_rate": 1.4575435810022866e-05, "loss": 0.9623, "step": 6306 }, { "epoch": 0.36839953271028036, "grad_norm": 1.7741761207580566, "learning_rate": 1.457375352656053e-05, "loss": 0.8512, "step": 6307 }, { "epoch": 0.3684579439252336, "grad_norm": 1.4388906955718994, "learning_rate": 1.457207107940055e-05, "loss": 1.0009, "step": 6308 }, { "epoch": 0.36851635514018694, "grad_norm": 0.9716395139694214, "learning_rate": 1.4570388468603139e-05, "loss": 0.6448, "step": 6309 }, { "epoch": 0.3685747663551402, "grad_norm": 1.701663613319397, "learning_rate": 1.4568705694228517e-05, "loss": 0.9845, "step": 6310 }, { "epoch": 0.36863317757009345, "grad_norm": 0.8390812873840332, "learning_rate": 1.4567022756336916e-05, "loss": 0.6103, "step": 6311 }, { "epoch": 0.3686915887850467, "grad_norm": 1.786211609840393, "learning_rate": 1.4565339654988568e-05, "loss": 0.78, "step": 6312 }, { "epoch": 0.36875, "grad_norm": 1.238321304321289, "learning_rate": 1.456365639024371e-05, "loss": 0.8276, "step": 6313 }, { "epoch": 0.3688084112149533, "grad_norm": 1.4523485898971558, "learning_rate": 1.4561972962162594e-05, "loss": 0.9619, "step": 6314 }, { "epoch": 0.36886682242990654, "grad_norm": 1.1638468503952026, "learning_rate": 1.4560289370805461e-05, "loss": 0.9035, "step": 6315 }, { "epoch": 0.3689252336448598, "grad_norm": 1.7187182903289795, "learning_rate": 1.4558605616232575e-05, "loss": 0.7181, "step": 6316 }, { "epoch": 0.3689836448598131, "grad_norm": 1.5297011137008667, "learning_rate": 1.4556921698504196e-05, "loss": 0.7542, "step": 6317 }, { "epoch": 0.36904205607476637, "grad_norm": 0.9306455254554749, "learning_rate": 1.4555237617680593e-05, "loss": 0.7666, "step": 6318 }, { "epoch": 0.3691004672897196, "grad_norm": 1.8257851600646973, "learning_rate": 1.4553553373822042e-05, "loss": 1.0156, "step": 6319 }, { "epoch": 0.3691588785046729, "grad_norm": 1.3608320951461792, "learning_rate": 1.4551868966988823e-05, "loss": 0.913, "step": 6320 }, { "epoch": 0.36921728971962614, "grad_norm": 1.4529443979263306, "learning_rate": 1.4550184397241216e-05, "loss": 0.8627, "step": 6321 }, { "epoch": 0.36927570093457945, "grad_norm": 1.415515661239624, "learning_rate": 1.4548499664639519e-05, "loss": 0.9553, "step": 6322 }, { "epoch": 0.3693341121495327, "grad_norm": 1.0008028745651245, "learning_rate": 1.4546814769244031e-05, "loss": 0.772, "step": 6323 }, { "epoch": 0.36939252336448597, "grad_norm": 1.0851085186004639, "learning_rate": 1.454512971111505e-05, "loss": 0.7394, "step": 6324 }, { "epoch": 0.3694509345794392, "grad_norm": 1.3539131879806519, "learning_rate": 1.4543444490312893e-05, "loss": 0.801, "step": 6325 }, { "epoch": 0.36950934579439254, "grad_norm": 1.1894865036010742, "learning_rate": 1.4541759106897863e-05, "loss": 0.855, "step": 6326 }, { "epoch": 0.3695677570093458, "grad_norm": 1.0739564895629883, "learning_rate": 1.4540073560930293e-05, "loss": 0.7552, "step": 6327 }, { "epoch": 0.36962616822429906, "grad_norm": 1.0984241962432861, "learning_rate": 1.4538387852470506e-05, "loss": 0.795, "step": 6328 }, { "epoch": 0.3696845794392523, "grad_norm": 1.3578639030456543, "learning_rate": 1.453670198157883e-05, "loss": 0.918, "step": 6329 }, { "epoch": 0.3697429906542056, "grad_norm": 1.086082935333252, "learning_rate": 1.4535015948315613e-05, "loss": 0.7979, "step": 6330 }, { "epoch": 0.3698014018691589, "grad_norm": 1.5408004522323608, "learning_rate": 1.4533329752741188e-05, "loss": 0.8101, "step": 6331 }, { "epoch": 0.36985981308411214, "grad_norm": 0.944651186466217, "learning_rate": 1.453164339491591e-05, "loss": 0.8282, "step": 6332 }, { "epoch": 0.3699182242990654, "grad_norm": 1.2009979486465454, "learning_rate": 1.452995687490014e-05, "loss": 0.862, "step": 6333 }, { "epoch": 0.3699766355140187, "grad_norm": 1.1725661754608154, "learning_rate": 1.452827019275423e-05, "loss": 0.7292, "step": 6334 }, { "epoch": 0.370035046728972, "grad_norm": 1.0686852931976318, "learning_rate": 1.4526583348538555e-05, "loss": 0.6954, "step": 6335 }, { "epoch": 0.37009345794392523, "grad_norm": 1.052696704864502, "learning_rate": 1.4524896342313486e-05, "loss": 0.8309, "step": 6336 }, { "epoch": 0.3701518691588785, "grad_norm": 1.5585228204727173, "learning_rate": 1.45232091741394e-05, "loss": 0.798, "step": 6337 }, { "epoch": 0.3702102803738318, "grad_norm": 1.4504574537277222, "learning_rate": 1.4521521844076684e-05, "loss": 0.8861, "step": 6338 }, { "epoch": 0.37026869158878506, "grad_norm": 1.5319132804870605, "learning_rate": 1.4519834352185731e-05, "loss": 0.7479, "step": 6339 }, { "epoch": 0.3703271028037383, "grad_norm": 0.994793713092804, "learning_rate": 1.4518146698526931e-05, "loss": 0.7235, "step": 6340 }, { "epoch": 0.3703855140186916, "grad_norm": 1.648687720298767, "learning_rate": 1.451645888316069e-05, "loss": 0.8096, "step": 6341 }, { "epoch": 0.37044392523364483, "grad_norm": 2.069974660873413, "learning_rate": 1.4514770906147417e-05, "loss": 0.7728, "step": 6342 }, { "epoch": 0.37050233644859815, "grad_norm": 1.7421945333480835, "learning_rate": 1.4513082767547525e-05, "loss": 0.8197, "step": 6343 }, { "epoch": 0.3705607476635514, "grad_norm": 1.2317821979522705, "learning_rate": 1.4511394467421435e-05, "loss": 1.0482, "step": 6344 }, { "epoch": 0.37061915887850466, "grad_norm": 2.2970664501190186, "learning_rate": 1.4509706005829571e-05, "loss": 0.8006, "step": 6345 }, { "epoch": 0.3706775700934579, "grad_norm": 1.4065207242965698, "learning_rate": 1.450801738283236e-05, "loss": 0.8775, "step": 6346 }, { "epoch": 0.37073598130841123, "grad_norm": 2.265338182449341, "learning_rate": 1.4506328598490245e-05, "loss": 0.8794, "step": 6347 }, { "epoch": 0.3707943925233645, "grad_norm": 1.1278876066207886, "learning_rate": 1.4504639652863666e-05, "loss": 0.8069, "step": 6348 }, { "epoch": 0.37085280373831775, "grad_norm": 1.2933217287063599, "learning_rate": 1.4502950546013072e-05, "loss": 0.7795, "step": 6349 }, { "epoch": 0.370911214953271, "grad_norm": 1.5265576839447021, "learning_rate": 1.450126127799892e-05, "loss": 0.8009, "step": 6350 }, { "epoch": 0.3709696261682243, "grad_norm": 1.343530535697937, "learning_rate": 1.4499571848881661e-05, "loss": 0.9452, "step": 6351 }, { "epoch": 0.3710280373831776, "grad_norm": 1.458267092704773, "learning_rate": 1.4497882258721772e-05, "loss": 0.9227, "step": 6352 }, { "epoch": 0.37108644859813084, "grad_norm": 1.0713753700256348, "learning_rate": 1.449619250757972e-05, "loss": 0.8805, "step": 6353 }, { "epoch": 0.3711448598130841, "grad_norm": 1.3340728282928467, "learning_rate": 1.4494502595515979e-05, "loss": 0.7618, "step": 6354 }, { "epoch": 0.3712032710280374, "grad_norm": 1.2763378620147705, "learning_rate": 1.4492812522591035e-05, "loss": 1.0014, "step": 6355 }, { "epoch": 0.37126168224299066, "grad_norm": 1.1697388887405396, "learning_rate": 1.4491122288865378e-05, "loss": 0.8767, "step": 6356 }, { "epoch": 0.3713200934579439, "grad_norm": 1.2426024675369263, "learning_rate": 1.44894318943995e-05, "loss": 0.8777, "step": 6357 }, { "epoch": 0.3713785046728972, "grad_norm": 1.529891848564148, "learning_rate": 1.4487741339253906e-05, "loss": 0.9334, "step": 6358 }, { "epoch": 0.3714369158878505, "grad_norm": 1.0763211250305176, "learning_rate": 1.4486050623489094e-05, "loss": 0.7486, "step": 6359 }, { "epoch": 0.37149532710280375, "grad_norm": 1.7631406784057617, "learning_rate": 1.4484359747165583e-05, "loss": 0.7786, "step": 6360 }, { "epoch": 0.371553738317757, "grad_norm": 1.0562310218811035, "learning_rate": 1.448266871034389e-05, "loss": 0.7097, "step": 6361 }, { "epoch": 0.37161214953271027, "grad_norm": 1.0796431303024292, "learning_rate": 1.4480977513084536e-05, "loss": 0.5929, "step": 6362 }, { "epoch": 0.3716705607476635, "grad_norm": 1.676328420639038, "learning_rate": 1.4479286155448046e-05, "loss": 0.6163, "step": 6363 }, { "epoch": 0.37172897196261684, "grad_norm": 1.4675625562667847, "learning_rate": 1.4477594637494965e-05, "loss": 0.8534, "step": 6364 }, { "epoch": 0.3717873831775701, "grad_norm": 2.2906076908111572, "learning_rate": 1.4475902959285823e-05, "loss": 0.9388, "step": 6365 }, { "epoch": 0.37184579439252335, "grad_norm": 0.8830505013465881, "learning_rate": 1.4474211120881174e-05, "loss": 0.7039, "step": 6366 }, { "epoch": 0.3719042056074766, "grad_norm": 1.9567111730575562, "learning_rate": 1.4472519122341566e-05, "loss": 0.8263, "step": 6367 }, { "epoch": 0.3719626168224299, "grad_norm": 1.2904640436172485, "learning_rate": 1.447082696372756e-05, "loss": 0.7776, "step": 6368 }, { "epoch": 0.3720210280373832, "grad_norm": 1.2072255611419678, "learning_rate": 1.4469134645099715e-05, "loss": 0.7755, "step": 6369 }, { "epoch": 0.37207943925233644, "grad_norm": 1.3962454795837402, "learning_rate": 1.4467442166518601e-05, "loss": 0.6693, "step": 6370 }, { "epoch": 0.3721378504672897, "grad_norm": 0.9599484205245972, "learning_rate": 1.4465749528044797e-05, "loss": 0.6968, "step": 6371 }, { "epoch": 0.372196261682243, "grad_norm": 1.720015287399292, "learning_rate": 1.4464056729738883e-05, "loss": 0.8777, "step": 6372 }, { "epoch": 0.37225467289719627, "grad_norm": 1.163132905960083, "learning_rate": 1.4462363771661441e-05, "loss": 0.8666, "step": 6373 }, { "epoch": 0.37231308411214953, "grad_norm": 1.1864895820617676, "learning_rate": 1.4460670653873065e-05, "loss": 0.9088, "step": 6374 }, { "epoch": 0.3723714953271028, "grad_norm": 1.0764567852020264, "learning_rate": 1.4458977376434356e-05, "loss": 0.8427, "step": 6375 }, { "epoch": 0.3724299065420561, "grad_norm": 1.053270697593689, "learning_rate": 1.445728393940591e-05, "loss": 0.8066, "step": 6376 }, { "epoch": 0.37248831775700936, "grad_norm": 1.063318133354187, "learning_rate": 1.4455590342848348e-05, "loss": 0.6979, "step": 6377 }, { "epoch": 0.3725467289719626, "grad_norm": 0.9321760535240173, "learning_rate": 1.4453896586822274e-05, "loss": 0.724, "step": 6378 }, { "epoch": 0.3726051401869159, "grad_norm": 1.2286168336868286, "learning_rate": 1.4452202671388312e-05, "loss": 0.962, "step": 6379 }, { "epoch": 0.3726635514018692, "grad_norm": 1.3190698623657227, "learning_rate": 1.4450508596607087e-05, "loss": 0.7049, "step": 6380 }, { "epoch": 0.37272196261682244, "grad_norm": 1.346479892730713, "learning_rate": 1.4448814362539239e-05, "loss": 0.7166, "step": 6381 }, { "epoch": 0.3727803738317757, "grad_norm": 1.0270423889160156, "learning_rate": 1.4447119969245395e-05, "loss": 0.5532, "step": 6382 }, { "epoch": 0.37283878504672896, "grad_norm": 1.6465239524841309, "learning_rate": 1.4445425416786205e-05, "loss": 0.8236, "step": 6383 }, { "epoch": 0.3728971962616822, "grad_norm": 1.033690333366394, "learning_rate": 1.4443730705222314e-05, "loss": 0.8287, "step": 6384 }, { "epoch": 0.37295560747663553, "grad_norm": 1.2686958312988281, "learning_rate": 1.4442035834614383e-05, "loss": 0.7273, "step": 6385 }, { "epoch": 0.3730140186915888, "grad_norm": 1.605037808418274, "learning_rate": 1.4440340805023068e-05, "loss": 0.9841, "step": 6386 }, { "epoch": 0.37307242990654205, "grad_norm": 1.0468584299087524, "learning_rate": 1.4438645616509035e-05, "loss": 0.8356, "step": 6387 }, { "epoch": 0.3731308411214953, "grad_norm": 2.0743753910064697, "learning_rate": 1.4436950269132956e-05, "loss": 0.8949, "step": 6388 }, { "epoch": 0.3731892523364486, "grad_norm": 1.9207040071487427, "learning_rate": 1.4435254762955513e-05, "loss": 0.8419, "step": 6389 }, { "epoch": 0.3732476635514019, "grad_norm": 1.3930329084396362, "learning_rate": 1.4433559098037382e-05, "loss": 0.6336, "step": 6390 }, { "epoch": 0.37330607476635513, "grad_norm": 1.3402577638626099, "learning_rate": 1.443186327443926e-05, "loss": 0.8076, "step": 6391 }, { "epoch": 0.3733644859813084, "grad_norm": 0.9929366111755371, "learning_rate": 1.4430167292221833e-05, "loss": 0.7692, "step": 6392 }, { "epoch": 0.3734228971962617, "grad_norm": 1.8433703184127808, "learning_rate": 1.4428471151445806e-05, "loss": 0.8835, "step": 6393 }, { "epoch": 0.37348130841121496, "grad_norm": 1.363682746887207, "learning_rate": 1.4426774852171887e-05, "loss": 0.8873, "step": 6394 }, { "epoch": 0.3735397196261682, "grad_norm": 1.9815223217010498, "learning_rate": 1.4425078394460785e-05, "loss": 0.829, "step": 6395 }, { "epoch": 0.3735981308411215, "grad_norm": 2.258255958557129, "learning_rate": 1.4423381778373218e-05, "loss": 0.8808, "step": 6396 }, { "epoch": 0.3736565420560748, "grad_norm": 2.207803964614868, "learning_rate": 1.442168500396991e-05, "loss": 0.7905, "step": 6397 }, { "epoch": 0.37371495327102805, "grad_norm": 1.512605905532837, "learning_rate": 1.4419988071311583e-05, "loss": 0.9609, "step": 6398 }, { "epoch": 0.3737733644859813, "grad_norm": 1.538195252418518, "learning_rate": 1.441829098045898e-05, "loss": 0.9552, "step": 6399 }, { "epoch": 0.37383177570093457, "grad_norm": 1.4502129554748535, "learning_rate": 1.441659373147284e-05, "loss": 0.6166, "step": 6400 }, { "epoch": 0.3738901869158878, "grad_norm": 1.3849817514419556, "learning_rate": 1.4414896324413902e-05, "loss": 0.7471, "step": 6401 }, { "epoch": 0.37394859813084114, "grad_norm": 1.0508421659469604, "learning_rate": 1.4413198759342925e-05, "loss": 0.6155, "step": 6402 }, { "epoch": 0.3740070093457944, "grad_norm": 1.8507884740829468, "learning_rate": 1.4411501036320661e-05, "loss": 0.8752, "step": 6403 }, { "epoch": 0.37406542056074765, "grad_norm": 1.989604115486145, "learning_rate": 1.4409803155407876e-05, "loss": 0.8562, "step": 6404 }, { "epoch": 0.3741238317757009, "grad_norm": 2.2266616821289062, "learning_rate": 1.4408105116665336e-05, "loss": 0.7074, "step": 6405 }, { "epoch": 0.3741822429906542, "grad_norm": 1.3854645490646362, "learning_rate": 1.4406406920153815e-05, "loss": 0.6476, "step": 6406 }, { "epoch": 0.3742406542056075, "grad_norm": 3.0501551628112793, "learning_rate": 1.4404708565934091e-05, "loss": 0.9471, "step": 6407 }, { "epoch": 0.37429906542056074, "grad_norm": 2.609835147857666, "learning_rate": 1.4403010054066955e-05, "loss": 0.951, "step": 6408 }, { "epoch": 0.374357476635514, "grad_norm": 2.2320923805236816, "learning_rate": 1.440131138461319e-05, "loss": 0.7989, "step": 6409 }, { "epoch": 0.3744158878504673, "grad_norm": 1.8961687088012695, "learning_rate": 1.43996125576336e-05, "loss": 0.8554, "step": 6410 }, { "epoch": 0.37447429906542057, "grad_norm": 1.728014588356018, "learning_rate": 1.4397913573188986e-05, "loss": 0.7473, "step": 6411 }, { "epoch": 0.3745327102803738, "grad_norm": 1.3133150339126587, "learning_rate": 1.4396214431340147e-05, "loss": 0.7255, "step": 6412 }, { "epoch": 0.3745911214953271, "grad_norm": 1.426256537437439, "learning_rate": 1.4394515132147907e-05, "loss": 0.9078, "step": 6413 }, { "epoch": 0.3746495327102804, "grad_norm": 1.9866715669631958, "learning_rate": 1.4392815675673083e-05, "loss": 0.8897, "step": 6414 }, { "epoch": 0.37470794392523366, "grad_norm": 1.0556790828704834, "learning_rate": 1.4391116061976492e-05, "loss": 0.7107, "step": 6415 }, { "epoch": 0.3747663551401869, "grad_norm": 2.320552110671997, "learning_rate": 1.4389416291118973e-05, "loss": 0.8457, "step": 6416 }, { "epoch": 0.37482476635514017, "grad_norm": 0.9113535284996033, "learning_rate": 1.438771636316136e-05, "loss": 0.716, "step": 6417 }, { "epoch": 0.3748831775700935, "grad_norm": 1.5391968488693237, "learning_rate": 1.438601627816449e-05, "loss": 0.9302, "step": 6418 }, { "epoch": 0.37494158878504674, "grad_norm": 1.3877066373825073, "learning_rate": 1.4384316036189216e-05, "loss": 0.6602, "step": 6419 }, { "epoch": 0.375, "grad_norm": 1.4160575866699219, "learning_rate": 1.438261563729639e-05, "loss": 0.7602, "step": 6420 }, { "epoch": 0.37505841121495326, "grad_norm": 1.8849421739578247, "learning_rate": 1.4380915081546866e-05, "loss": 0.7672, "step": 6421 }, { "epoch": 0.3751168224299065, "grad_norm": 1.4234508275985718, "learning_rate": 1.437921436900151e-05, "loss": 0.8581, "step": 6422 }, { "epoch": 0.37517523364485983, "grad_norm": 1.8776005506515503, "learning_rate": 1.4377513499721193e-05, "loss": 0.7885, "step": 6423 }, { "epoch": 0.3752336448598131, "grad_norm": 1.0249521732330322, "learning_rate": 1.437581247376679e-05, "loss": 0.8121, "step": 6424 }, { "epoch": 0.37529205607476634, "grad_norm": 2.1407411098480225, "learning_rate": 1.4374111291199184e-05, "loss": 0.8383, "step": 6425 }, { "epoch": 0.3753504672897196, "grad_norm": 1.0939877033233643, "learning_rate": 1.4372409952079256e-05, "loss": 0.7996, "step": 6426 }, { "epoch": 0.3754088785046729, "grad_norm": 1.7702724933624268, "learning_rate": 1.4370708456467902e-05, "loss": 0.9077, "step": 6427 }, { "epoch": 0.3754672897196262, "grad_norm": 1.329918622970581, "learning_rate": 1.4369006804426015e-05, "loss": 0.8285, "step": 6428 }, { "epoch": 0.37552570093457943, "grad_norm": 1.1053115129470825, "learning_rate": 1.4367304996014506e-05, "loss": 0.6934, "step": 6429 }, { "epoch": 0.3755841121495327, "grad_norm": 1.238384485244751, "learning_rate": 1.436560303129428e-05, "loss": 0.7409, "step": 6430 }, { "epoch": 0.375642523364486, "grad_norm": 1.343253493309021, "learning_rate": 1.4363900910326249e-05, "loss": 0.8229, "step": 6431 }, { "epoch": 0.37570093457943926, "grad_norm": 2.047135829925537, "learning_rate": 1.4362198633171335e-05, "loss": 0.8977, "step": 6432 }, { "epoch": 0.3757593457943925, "grad_norm": 1.3457835912704468, "learning_rate": 1.4360496199890467e-05, "loss": 0.884, "step": 6433 }, { "epoch": 0.3758177570093458, "grad_norm": 2.1422674655914307, "learning_rate": 1.4358793610544565e-05, "loss": 0.8499, "step": 6434 }, { "epoch": 0.3758761682242991, "grad_norm": 1.3528308868408203, "learning_rate": 1.4357090865194583e-05, "loss": 0.8444, "step": 6435 }, { "epoch": 0.37593457943925235, "grad_norm": 1.268094778060913, "learning_rate": 1.4355387963901448e-05, "loss": 0.8369, "step": 6436 }, { "epoch": 0.3759929906542056, "grad_norm": 1.3014475107192993, "learning_rate": 1.4353684906726118e-05, "loss": 0.9246, "step": 6437 }, { "epoch": 0.37605140186915886, "grad_norm": 1.033918023109436, "learning_rate": 1.435198169372954e-05, "loss": 0.6222, "step": 6438 }, { "epoch": 0.3761098130841122, "grad_norm": 1.2645553350448608, "learning_rate": 1.4350278324972674e-05, "loss": 0.691, "step": 6439 }, { "epoch": 0.37616822429906543, "grad_norm": 1.5789703130722046, "learning_rate": 1.4348574800516492e-05, "loss": 0.8371, "step": 6440 }, { "epoch": 0.3762266355140187, "grad_norm": 1.152607798576355, "learning_rate": 1.4346871120421955e-05, "loss": 0.855, "step": 6441 }, { "epoch": 0.37628504672897195, "grad_norm": 1.5857818126678467, "learning_rate": 1.4345167284750042e-05, "loss": 0.8925, "step": 6442 }, { "epoch": 0.3763434579439252, "grad_norm": 0.9326233267784119, "learning_rate": 1.4343463293561734e-05, "loss": 0.6917, "step": 6443 }, { "epoch": 0.3764018691588785, "grad_norm": 2.249809980392456, "learning_rate": 1.4341759146918024e-05, "loss": 0.8596, "step": 6444 }, { "epoch": 0.3764602803738318, "grad_norm": 1.184779405593872, "learning_rate": 1.4340054844879894e-05, "loss": 0.7536, "step": 6445 }, { "epoch": 0.37651869158878504, "grad_norm": 1.093371868133545, "learning_rate": 1.433835038750835e-05, "loss": 0.6746, "step": 6446 }, { "epoch": 0.3765771028037383, "grad_norm": 1.4321221113204956, "learning_rate": 1.4336645774864392e-05, "loss": 0.8725, "step": 6447 }, { "epoch": 0.3766355140186916, "grad_norm": 2.035250186920166, "learning_rate": 1.433494100700903e-05, "loss": 0.8115, "step": 6448 }, { "epoch": 0.37669392523364487, "grad_norm": 1.1295251846313477, "learning_rate": 1.4333236084003282e-05, "loss": 0.7558, "step": 6449 }, { "epoch": 0.3767523364485981, "grad_norm": 1.75361967086792, "learning_rate": 1.4331531005908161e-05, "loss": 0.8959, "step": 6450 }, { "epoch": 0.3768107476635514, "grad_norm": 1.3303879499435425, "learning_rate": 1.43298257727847e-05, "loss": 0.7863, "step": 6451 }, { "epoch": 0.3768691588785047, "grad_norm": 0.8954792618751526, "learning_rate": 1.4328120384693929e-05, "loss": 0.6927, "step": 6452 }, { "epoch": 0.37692757009345795, "grad_norm": 1.6559697389602661, "learning_rate": 1.4326414841696879e-05, "loss": 0.9875, "step": 6453 }, { "epoch": 0.3769859813084112, "grad_norm": 0.9777923226356506, "learning_rate": 1.4324709143854602e-05, "loss": 0.8155, "step": 6454 }, { "epoch": 0.37704439252336447, "grad_norm": 1.1667766571044922, "learning_rate": 1.4323003291228142e-05, "loss": 0.6899, "step": 6455 }, { "epoch": 0.3771028037383178, "grad_norm": 1.5259941816329956, "learning_rate": 1.4321297283878545e-05, "loss": 0.8726, "step": 6456 }, { "epoch": 0.37716121495327104, "grad_norm": 1.1166528463363647, "learning_rate": 1.4319591121866882e-05, "loss": 0.692, "step": 6457 }, { "epoch": 0.3772196261682243, "grad_norm": 1.4783376455307007, "learning_rate": 1.4317884805254211e-05, "loss": 0.9103, "step": 6458 }, { "epoch": 0.37727803738317756, "grad_norm": 1.3311418294906616, "learning_rate": 1.4316178334101604e-05, "loss": 0.914, "step": 6459 }, { "epoch": 0.3773364485981308, "grad_norm": 1.9451245069503784, "learning_rate": 1.4314471708470138e-05, "loss": 0.8617, "step": 6460 }, { "epoch": 0.3773948598130841, "grad_norm": 1.8870769739151, "learning_rate": 1.431276492842089e-05, "loss": 0.7975, "step": 6461 }, { "epoch": 0.3774532710280374, "grad_norm": 2.0801236629486084, "learning_rate": 1.4311057994014953e-05, "loss": 0.8494, "step": 6462 }, { "epoch": 0.37751168224299064, "grad_norm": 1.6558932065963745, "learning_rate": 1.4309350905313412e-05, "loss": 0.75, "step": 6463 }, { "epoch": 0.3775700934579439, "grad_norm": 1.7909564971923828, "learning_rate": 1.430764366237737e-05, "loss": 0.9716, "step": 6464 }, { "epoch": 0.3776285046728972, "grad_norm": 2.3295211791992188, "learning_rate": 1.430593626526793e-05, "loss": 0.65, "step": 6465 }, { "epoch": 0.37768691588785047, "grad_norm": 1.693827509880066, "learning_rate": 1.43042287140462e-05, "loss": 0.9588, "step": 6466 }, { "epoch": 0.37774532710280373, "grad_norm": 1.5680993795394897, "learning_rate": 1.4302521008773291e-05, "loss": 0.7312, "step": 6467 }, { "epoch": 0.377803738317757, "grad_norm": 1.995910406112671, "learning_rate": 1.430081314951033e-05, "loss": 0.8019, "step": 6468 }, { "epoch": 0.3778621495327103, "grad_norm": 1.1303274631500244, "learning_rate": 1.4299105136318439e-05, "loss": 0.7915, "step": 6469 }, { "epoch": 0.37792056074766356, "grad_norm": 2.100384473800659, "learning_rate": 1.4297396969258745e-05, "loss": 0.8346, "step": 6470 }, { "epoch": 0.3779789719626168, "grad_norm": 1.951054573059082, "learning_rate": 1.4295688648392391e-05, "loss": 0.9684, "step": 6471 }, { "epoch": 0.3780373831775701, "grad_norm": 1.7794150114059448, "learning_rate": 1.4293980173780514e-05, "loss": 0.9127, "step": 6472 }, { "epoch": 0.3780957943925234, "grad_norm": 2.0481748580932617, "learning_rate": 1.4292271545484264e-05, "loss": 0.7303, "step": 6473 }, { "epoch": 0.37815420560747665, "grad_norm": 1.35787832736969, "learning_rate": 1.4290562763564792e-05, "loss": 0.7143, "step": 6474 }, { "epoch": 0.3782126168224299, "grad_norm": 1.689577341079712, "learning_rate": 1.4288853828083258e-05, "loss": 0.7836, "step": 6475 }, { "epoch": 0.37827102803738316, "grad_norm": 1.5333447456359863, "learning_rate": 1.4287144739100827e-05, "loss": 1.0697, "step": 6476 }, { "epoch": 0.3783294392523365, "grad_norm": 1.0587823390960693, "learning_rate": 1.4285435496678663e-05, "loss": 0.7157, "step": 6477 }, { "epoch": 0.37838785046728973, "grad_norm": 1.3436145782470703, "learning_rate": 1.4283726100877951e-05, "loss": 0.7806, "step": 6478 }, { "epoch": 0.378446261682243, "grad_norm": 2.3414342403411865, "learning_rate": 1.428201655175986e-05, "loss": 1.0536, "step": 6479 }, { "epoch": 0.37850467289719625, "grad_norm": 1.8313406705856323, "learning_rate": 1.4280306849385584e-05, "loss": 0.8581, "step": 6480 }, { "epoch": 0.3785630841121495, "grad_norm": 1.7739659547805786, "learning_rate": 1.427859699381631e-05, "loss": 0.7454, "step": 6481 }, { "epoch": 0.3786214953271028, "grad_norm": 1.1516618728637695, "learning_rate": 1.4276886985113237e-05, "loss": 0.713, "step": 6482 }, { "epoch": 0.3786799065420561, "grad_norm": 1.4977130889892578, "learning_rate": 1.4275176823337566e-05, "loss": 0.7005, "step": 6483 }, { "epoch": 0.37873831775700934, "grad_norm": 1.9030530452728271, "learning_rate": 1.4273466508550506e-05, "loss": 0.8675, "step": 6484 }, { "epoch": 0.3787967289719626, "grad_norm": 1.3209419250488281, "learning_rate": 1.4271756040813269e-05, "loss": 0.8929, "step": 6485 }, { "epoch": 0.3788551401869159, "grad_norm": 1.5655841827392578, "learning_rate": 1.4270045420187075e-05, "loss": 0.8094, "step": 6486 }, { "epoch": 0.37891355140186916, "grad_norm": 1.4901657104492188, "learning_rate": 1.4268334646733148e-05, "loss": 0.8103, "step": 6487 }, { "epoch": 0.3789719626168224, "grad_norm": 1.1984198093414307, "learning_rate": 1.426662372051272e-05, "loss": 0.7783, "step": 6488 }, { "epoch": 0.3790303738317757, "grad_norm": 1.5513235330581665, "learning_rate": 1.4264912641587021e-05, "loss": 0.8757, "step": 6489 }, { "epoch": 0.379088785046729, "grad_norm": 1.5011910200119019, "learning_rate": 1.4263201410017296e-05, "loss": 0.9084, "step": 6490 }, { "epoch": 0.37914719626168225, "grad_norm": 1.535157322883606, "learning_rate": 1.4261490025864788e-05, "loss": 0.8602, "step": 6491 }, { "epoch": 0.3792056074766355, "grad_norm": 1.9735326766967773, "learning_rate": 1.4259778489190748e-05, "loss": 0.9706, "step": 6492 }, { "epoch": 0.37926401869158877, "grad_norm": 1.2623305320739746, "learning_rate": 1.4258066800056438e-05, "loss": 0.7153, "step": 6493 }, { "epoch": 0.3793224299065421, "grad_norm": 2.3243486881256104, "learning_rate": 1.4256354958523116e-05, "loss": 0.88, "step": 6494 }, { "epoch": 0.37938084112149534, "grad_norm": 1.4223605394363403, "learning_rate": 1.4254642964652053e-05, "loss": 0.8305, "step": 6495 }, { "epoch": 0.3794392523364486, "grad_norm": 1.5619500875473022, "learning_rate": 1.4252930818504521e-05, "loss": 0.9639, "step": 6496 }, { "epoch": 0.37949766355140185, "grad_norm": 1.7134140729904175, "learning_rate": 1.4251218520141797e-05, "loss": 0.8272, "step": 6497 }, { "epoch": 0.37955607476635517, "grad_norm": 1.2388150691986084, "learning_rate": 1.4249506069625167e-05, "loss": 0.6702, "step": 6498 }, { "epoch": 0.3796144859813084, "grad_norm": 1.4024323225021362, "learning_rate": 1.424779346701592e-05, "loss": 0.7381, "step": 6499 }, { "epoch": 0.3796728971962617, "grad_norm": 2.267669200897217, "learning_rate": 1.4246080712375352e-05, "loss": 1.1414, "step": 6500 }, { "epoch": 0.37973130841121494, "grad_norm": 1.774697184562683, "learning_rate": 1.4244367805764765e-05, "loss": 0.7744, "step": 6501 }, { "epoch": 0.3797897196261682, "grad_norm": 1.8134145736694336, "learning_rate": 1.4242654747245464e-05, "loss": 0.913, "step": 6502 }, { "epoch": 0.3798481308411215, "grad_norm": 1.108622431755066, "learning_rate": 1.4240941536878759e-05, "loss": 0.7286, "step": 6503 }, { "epoch": 0.37990654205607477, "grad_norm": 1.2330186367034912, "learning_rate": 1.4239228174725967e-05, "loss": 0.8126, "step": 6504 }, { "epoch": 0.379964953271028, "grad_norm": 1.6948206424713135, "learning_rate": 1.4237514660848413e-05, "loss": 0.9179, "step": 6505 }, { "epoch": 0.3800233644859813, "grad_norm": 1.2890377044677734, "learning_rate": 1.423580099530742e-05, "loss": 0.8484, "step": 6506 }, { "epoch": 0.3800817757009346, "grad_norm": 1.4891778230667114, "learning_rate": 1.4234087178164328e-05, "loss": 0.8432, "step": 6507 }, { "epoch": 0.38014018691588786, "grad_norm": 1.5284353494644165, "learning_rate": 1.423237320948047e-05, "loss": 0.7539, "step": 6508 }, { "epoch": 0.3801985981308411, "grad_norm": 1.265561580657959, "learning_rate": 1.4230659089317194e-05, "loss": 0.9009, "step": 6509 }, { "epoch": 0.3802570093457944, "grad_norm": 1.2934459447860718, "learning_rate": 1.4228944817735845e-05, "loss": 0.625, "step": 6510 }, { "epoch": 0.3803154205607477, "grad_norm": 2.0207173824310303, "learning_rate": 1.422723039479778e-05, "loss": 0.8444, "step": 6511 }, { "epoch": 0.38037383177570094, "grad_norm": 1.3131787776947021, "learning_rate": 1.4225515820564364e-05, "loss": 0.8335, "step": 6512 }, { "epoch": 0.3804322429906542, "grad_norm": 1.3675025701522827, "learning_rate": 1.4223801095096957e-05, "loss": 0.8603, "step": 6513 }, { "epoch": 0.38049065420560746, "grad_norm": 2.493972063064575, "learning_rate": 1.4222086218456928e-05, "loss": 0.9329, "step": 6514 }, { "epoch": 0.3805490654205608, "grad_norm": 1.373171091079712, "learning_rate": 1.4220371190705657e-05, "loss": 0.7999, "step": 6515 }, { "epoch": 0.38060747663551403, "grad_norm": 3.303788661956787, "learning_rate": 1.4218656011904531e-05, "loss": 0.9035, "step": 6516 }, { "epoch": 0.3806658878504673, "grad_norm": 1.1524317264556885, "learning_rate": 1.4216940682114928e-05, "loss": 0.7185, "step": 6517 }, { "epoch": 0.38072429906542055, "grad_norm": 1.3557212352752686, "learning_rate": 1.4215225201398249e-05, "loss": 0.9667, "step": 6518 }, { "epoch": 0.38078271028037386, "grad_norm": 1.5719817876815796, "learning_rate": 1.4213509569815884e-05, "loss": 0.7665, "step": 6519 }, { "epoch": 0.3808411214953271, "grad_norm": 1.7588655948638916, "learning_rate": 1.4211793787429244e-05, "loss": 0.8611, "step": 6520 }, { "epoch": 0.3808995327102804, "grad_norm": 1.179201364517212, "learning_rate": 1.4210077854299735e-05, "loss": 0.7184, "step": 6521 }, { "epoch": 0.38095794392523363, "grad_norm": 2.371652126312256, "learning_rate": 1.4208361770488773e-05, "loss": 0.7754, "step": 6522 }, { "epoch": 0.3810163551401869, "grad_norm": 1.2612478733062744, "learning_rate": 1.4206645536057772e-05, "loss": 0.8886, "step": 6523 }, { "epoch": 0.3810747663551402, "grad_norm": 1.044656753540039, "learning_rate": 1.4204929151068165e-05, "loss": 0.7435, "step": 6524 }, { "epoch": 0.38113317757009346, "grad_norm": 1.3690838813781738, "learning_rate": 1.4203212615581377e-05, "loss": 0.829, "step": 6525 }, { "epoch": 0.3811915887850467, "grad_norm": 1.2632465362548828, "learning_rate": 1.4201495929658845e-05, "loss": 0.8043, "step": 6526 }, { "epoch": 0.38125, "grad_norm": 1.2598780393600464, "learning_rate": 1.4199779093362015e-05, "loss": 0.9522, "step": 6527 }, { "epoch": 0.3813084112149533, "grad_norm": 1.2175730466842651, "learning_rate": 1.4198062106752326e-05, "loss": 0.8165, "step": 6528 }, { "epoch": 0.38136682242990655, "grad_norm": 2.0206663608551025, "learning_rate": 1.4196344969891236e-05, "loss": 0.8282, "step": 6529 }, { "epoch": 0.3814252336448598, "grad_norm": 1.4080026149749756, "learning_rate": 1.4194627682840201e-05, "loss": 0.7075, "step": 6530 }, { "epoch": 0.38148364485981306, "grad_norm": 1.6505367755889893, "learning_rate": 1.419291024566068e-05, "loss": 1.0395, "step": 6531 }, { "epoch": 0.3815420560747664, "grad_norm": 1.310381293296814, "learning_rate": 1.4191192658414148e-05, "loss": 0.88, "step": 6532 }, { "epoch": 0.38160046728971964, "grad_norm": 1.1001373529434204, "learning_rate": 1.4189474921162072e-05, "loss": 0.6222, "step": 6533 }, { "epoch": 0.3816588785046729, "grad_norm": 1.4805080890655518, "learning_rate": 1.4187757033965934e-05, "loss": 0.7823, "step": 6534 }, { "epoch": 0.38171728971962615, "grad_norm": 0.9912036657333374, "learning_rate": 1.4186038996887221e-05, "loss": 0.7388, "step": 6535 }, { "epoch": 0.38177570093457946, "grad_norm": 1.762373685836792, "learning_rate": 1.4184320809987418e-05, "loss": 0.9206, "step": 6536 }, { "epoch": 0.3818341121495327, "grad_norm": 1.0711833238601685, "learning_rate": 1.4182602473328024e-05, "loss": 0.7718, "step": 6537 }, { "epoch": 0.381892523364486, "grad_norm": 1.974076271057129, "learning_rate": 1.4180883986970536e-05, "loss": 0.7372, "step": 6538 }, { "epoch": 0.38195093457943924, "grad_norm": 1.4302786588668823, "learning_rate": 1.4179165350976457e-05, "loss": 1.0156, "step": 6539 }, { "epoch": 0.3820093457943925, "grad_norm": 1.4461524486541748, "learning_rate": 1.4177446565407306e-05, "loss": 0.9242, "step": 6540 }, { "epoch": 0.3820677570093458, "grad_norm": 2.1726529598236084, "learning_rate": 1.4175727630324598e-05, "loss": 0.9451, "step": 6541 }, { "epoch": 0.38212616822429907, "grad_norm": 2.077763557434082, "learning_rate": 1.417400854578985e-05, "loss": 1.0078, "step": 6542 }, { "epoch": 0.3821845794392523, "grad_norm": 1.389790415763855, "learning_rate": 1.4172289311864593e-05, "loss": 0.8146, "step": 6543 }, { "epoch": 0.3822429906542056, "grad_norm": 1.2443633079528809, "learning_rate": 1.4170569928610353e-05, "loss": 0.822, "step": 6544 }, { "epoch": 0.3823014018691589, "grad_norm": 1.522217035293579, "learning_rate": 1.416885039608868e-05, "loss": 0.7416, "step": 6545 }, { "epoch": 0.38235981308411215, "grad_norm": 2.3293962478637695, "learning_rate": 1.416713071436111e-05, "loss": 1.0721, "step": 6546 }, { "epoch": 0.3824182242990654, "grad_norm": 1.5350641012191772, "learning_rate": 1.4165410883489185e-05, "loss": 0.6, "step": 6547 }, { "epoch": 0.38247663551401867, "grad_norm": 2.087538957595825, "learning_rate": 1.4163690903534472e-05, "loss": 0.7934, "step": 6548 }, { "epoch": 0.382535046728972, "grad_norm": 1.396182656288147, "learning_rate": 1.4161970774558522e-05, "loss": 0.7911, "step": 6549 }, { "epoch": 0.38259345794392524, "grad_norm": 1.8175657987594604, "learning_rate": 1.41602504966229e-05, "loss": 0.7318, "step": 6550 }, { "epoch": 0.3826518691588785, "grad_norm": 1.863308310508728, "learning_rate": 1.415853006978918e-05, "loss": 0.7576, "step": 6551 }, { "epoch": 0.38271028037383176, "grad_norm": 1.2729055881500244, "learning_rate": 1.4156809494118932e-05, "loss": 0.8248, "step": 6552 }, { "epoch": 0.38276869158878507, "grad_norm": 1.8202019929885864, "learning_rate": 1.415508876967374e-05, "loss": 0.8571, "step": 6553 }, { "epoch": 0.38282710280373833, "grad_norm": 2.030083656311035, "learning_rate": 1.415336789651519e-05, "loss": 0.9866, "step": 6554 }, { "epoch": 0.3828855140186916, "grad_norm": 2.7539494037628174, "learning_rate": 1.415164687470487e-05, "loss": 0.9979, "step": 6555 }, { "epoch": 0.38294392523364484, "grad_norm": 1.8609442710876465, "learning_rate": 1.4149925704304382e-05, "loss": 0.7339, "step": 6556 }, { "epoch": 0.38300233644859816, "grad_norm": 1.0506144762039185, "learning_rate": 1.414820438537532e-05, "loss": 0.7104, "step": 6557 }, { "epoch": 0.3830607476635514, "grad_norm": 1.8257147073745728, "learning_rate": 1.4146482917979299e-05, "loss": 0.7647, "step": 6558 }, { "epoch": 0.3831191588785047, "grad_norm": 1.869827389717102, "learning_rate": 1.4144761302177925e-05, "loss": 0.8723, "step": 6559 }, { "epoch": 0.38317757009345793, "grad_norm": 2.0195705890655518, "learning_rate": 1.414303953803282e-05, "loss": 1.0082, "step": 6560 }, { "epoch": 0.3832359813084112, "grad_norm": 1.7486776113510132, "learning_rate": 1.4141317625605609e-05, "loss": 0.8769, "step": 6561 }, { "epoch": 0.3832943925233645, "grad_norm": 1.1964105367660522, "learning_rate": 1.4139595564957915e-05, "loss": 0.7951, "step": 6562 }, { "epoch": 0.38335280373831776, "grad_norm": 2.583585023880005, "learning_rate": 1.4137873356151373e-05, "loss": 0.9133, "step": 6563 }, { "epoch": 0.383411214953271, "grad_norm": 1.0759170055389404, "learning_rate": 1.4136150999247623e-05, "loss": 0.6217, "step": 6564 }, { "epoch": 0.3834696261682243, "grad_norm": 1.960318684577942, "learning_rate": 1.413442849430831e-05, "loss": 0.6687, "step": 6565 }, { "epoch": 0.3835280373831776, "grad_norm": 1.3921390771865845, "learning_rate": 1.413270584139508e-05, "loss": 0.7923, "step": 6566 }, { "epoch": 0.38358644859813085, "grad_norm": 2.0889365673065186, "learning_rate": 1.4130983040569594e-05, "loss": 0.905, "step": 6567 }, { "epoch": 0.3836448598130841, "grad_norm": 1.340280532836914, "learning_rate": 1.412926009189351e-05, "loss": 0.8433, "step": 6568 }, { "epoch": 0.38370327102803736, "grad_norm": 1.4555643796920776, "learning_rate": 1.4127536995428486e-05, "loss": 0.825, "step": 6569 }, { "epoch": 0.3837616822429907, "grad_norm": 0.9456163048744202, "learning_rate": 1.4125813751236206e-05, "loss": 0.6951, "step": 6570 }, { "epoch": 0.38382009345794393, "grad_norm": 1.4657251834869385, "learning_rate": 1.4124090359378334e-05, "loss": 0.9665, "step": 6571 }, { "epoch": 0.3838785046728972, "grad_norm": 0.9108923673629761, "learning_rate": 1.4122366819916557e-05, "loss": 0.7062, "step": 6572 }, { "epoch": 0.38393691588785045, "grad_norm": 2.033308744430542, "learning_rate": 1.4120643132912564e-05, "loss": 0.8128, "step": 6573 }, { "epoch": 0.38399532710280376, "grad_norm": 1.2320466041564941, "learning_rate": 1.4118919298428042e-05, "loss": 0.8034, "step": 6574 }, { "epoch": 0.384053738317757, "grad_norm": 2.9360122680664062, "learning_rate": 1.411719531652469e-05, "loss": 0.8074, "step": 6575 }, { "epoch": 0.3841121495327103, "grad_norm": 0.858199417591095, "learning_rate": 1.4115471187264212e-05, "loss": 0.5981, "step": 6576 }, { "epoch": 0.38417056074766354, "grad_norm": 1.487813949584961, "learning_rate": 1.4113746910708313e-05, "loss": 0.8599, "step": 6577 }, { "epoch": 0.38422897196261685, "grad_norm": 2.367053985595703, "learning_rate": 1.4112022486918706e-05, "loss": 0.668, "step": 6578 }, { "epoch": 0.3842873831775701, "grad_norm": 1.4589401483535767, "learning_rate": 1.4110297915957112e-05, "loss": 0.8767, "step": 6579 }, { "epoch": 0.38434579439252337, "grad_norm": 2.571368455886841, "learning_rate": 1.4108573197885254e-05, "loss": 0.935, "step": 6580 }, { "epoch": 0.3844042056074766, "grad_norm": 1.7885692119598389, "learning_rate": 1.4106848332764857e-05, "loss": 0.942, "step": 6581 }, { "epoch": 0.3844626168224299, "grad_norm": 1.0530757904052734, "learning_rate": 1.410512332065766e-05, "loss": 0.8352, "step": 6582 }, { "epoch": 0.3845210280373832, "grad_norm": 1.4752237796783447, "learning_rate": 1.4103398161625398e-05, "loss": 0.7719, "step": 6583 }, { "epoch": 0.38457943925233645, "grad_norm": 1.964828610420227, "learning_rate": 1.410167285572982e-05, "loss": 0.877, "step": 6584 }, { "epoch": 0.3846378504672897, "grad_norm": 1.3200324773788452, "learning_rate": 1.4099947403032675e-05, "loss": 1.1451, "step": 6585 }, { "epoch": 0.38469626168224297, "grad_norm": 2.739459991455078, "learning_rate": 1.4098221803595714e-05, "loss": 0.9664, "step": 6586 }, { "epoch": 0.3847546728971963, "grad_norm": 1.2711601257324219, "learning_rate": 1.40964960574807e-05, "loss": 0.9903, "step": 6587 }, { "epoch": 0.38481308411214954, "grad_norm": 2.05185604095459, "learning_rate": 1.4094770164749398e-05, "loss": 0.7176, "step": 6588 }, { "epoch": 0.3848714953271028, "grad_norm": 2.4743285179138184, "learning_rate": 1.4093044125463585e-05, "loss": 0.8816, "step": 6589 }, { "epoch": 0.38492990654205606, "grad_norm": 2.271134614944458, "learning_rate": 1.4091317939685026e-05, "loss": 0.7416, "step": 6590 }, { "epoch": 0.38498831775700937, "grad_norm": 2.924187183380127, "learning_rate": 1.4089591607475508e-05, "loss": 0.799, "step": 6591 }, { "epoch": 0.3850467289719626, "grad_norm": 5.624514102935791, "learning_rate": 1.4087865128896819e-05, "loss": 0.8451, "step": 6592 }, { "epoch": 0.3851051401869159, "grad_norm": 2.103266716003418, "learning_rate": 1.408613850401075e-05, "loss": 0.874, "step": 6593 }, { "epoch": 0.38516355140186914, "grad_norm": 1.6366519927978516, "learning_rate": 1.4084411732879095e-05, "loss": 0.8427, "step": 6594 }, { "epoch": 0.38522196261682246, "grad_norm": 1.7158839702606201, "learning_rate": 1.408268481556366e-05, "loss": 0.9662, "step": 6595 }, { "epoch": 0.3852803738317757, "grad_norm": 1.8052337169647217, "learning_rate": 1.4080957752126252e-05, "loss": 0.904, "step": 6596 }, { "epoch": 0.38533878504672897, "grad_norm": 2.3448374271392822, "learning_rate": 1.4079230542628679e-05, "loss": 0.8447, "step": 6597 }, { "epoch": 0.38539719626168223, "grad_norm": 1.7219743728637695, "learning_rate": 1.4077503187132763e-05, "loss": 0.9211, "step": 6598 }, { "epoch": 0.3854556074766355, "grad_norm": 1.862451434135437, "learning_rate": 1.407577568570033e-05, "loss": 0.7261, "step": 6599 }, { "epoch": 0.3855140186915888, "grad_norm": 1.4558168649673462, "learning_rate": 1.4074048038393207e-05, "loss": 0.7662, "step": 6600 }, { "epoch": 0.38557242990654206, "grad_norm": 1.5854419469833374, "learning_rate": 1.407232024527322e-05, "loss": 0.7403, "step": 6601 }, { "epoch": 0.3856308411214953, "grad_norm": 2.030653476715088, "learning_rate": 1.4070592306402217e-05, "loss": 0.9159, "step": 6602 }, { "epoch": 0.3856892523364486, "grad_norm": 1.0192114114761353, "learning_rate": 1.406886422184204e-05, "loss": 0.9026, "step": 6603 }, { "epoch": 0.3857476635514019, "grad_norm": 2.385347843170166, "learning_rate": 1.406713599165454e-05, "loss": 0.845, "step": 6604 }, { "epoch": 0.38580607476635514, "grad_norm": 1.384653091430664, "learning_rate": 1.4065407615901561e-05, "loss": 0.7624, "step": 6605 }, { "epoch": 0.3858644859813084, "grad_norm": 1.0745981931686401, "learning_rate": 1.4063679094644976e-05, "loss": 0.7439, "step": 6606 }, { "epoch": 0.38592289719626166, "grad_norm": 2.4583346843719482, "learning_rate": 1.4061950427946642e-05, "loss": 0.8986, "step": 6607 }, { "epoch": 0.385981308411215, "grad_norm": 1.2100125551223755, "learning_rate": 1.406022161586843e-05, "loss": 0.5619, "step": 6608 }, { "epoch": 0.38603971962616823, "grad_norm": 2.1859843730926514, "learning_rate": 1.405849265847222e-05, "loss": 1.1217, "step": 6609 }, { "epoch": 0.3860981308411215, "grad_norm": 3.802591562271118, "learning_rate": 1.4056763555819887e-05, "loss": 0.8392, "step": 6610 }, { "epoch": 0.38615654205607475, "grad_norm": 1.8080041408538818, "learning_rate": 1.405503430797332e-05, "loss": 0.8449, "step": 6611 }, { "epoch": 0.38621495327102806, "grad_norm": 1.3974782228469849, "learning_rate": 1.405330491499441e-05, "loss": 1.0181, "step": 6612 }, { "epoch": 0.3862733644859813, "grad_norm": 1.2660183906555176, "learning_rate": 1.4051575376945048e-05, "loss": 0.7778, "step": 6613 }, { "epoch": 0.3863317757009346, "grad_norm": 1.4961590766906738, "learning_rate": 1.4049845693887146e-05, "loss": 0.8604, "step": 6614 }, { "epoch": 0.38639018691588783, "grad_norm": 1.1557338237762451, "learning_rate": 1.40481158658826e-05, "loss": 0.9206, "step": 6615 }, { "epoch": 0.38644859813084115, "grad_norm": 2.203403949737549, "learning_rate": 1.4046385892993321e-05, "loss": 0.987, "step": 6616 }, { "epoch": 0.3865070093457944, "grad_norm": 2.1321163177490234, "learning_rate": 1.4044655775281235e-05, "loss": 0.9577, "step": 6617 }, { "epoch": 0.38656542056074766, "grad_norm": 0.9824846386909485, "learning_rate": 1.404292551280826e-05, "loss": 0.7084, "step": 6618 }, { "epoch": 0.3866238317757009, "grad_norm": 2.512728214263916, "learning_rate": 1.4041195105636323e-05, "loss": 0.7302, "step": 6619 }, { "epoch": 0.3866822429906542, "grad_norm": 1.3401645421981812, "learning_rate": 1.4039464553827353e-05, "loss": 0.8763, "step": 6620 }, { "epoch": 0.3867406542056075, "grad_norm": 2.1535353660583496, "learning_rate": 1.4037733857443292e-05, "loss": 0.8803, "step": 6621 }, { "epoch": 0.38679906542056075, "grad_norm": 1.6581213474273682, "learning_rate": 1.403600301654608e-05, "loss": 0.8267, "step": 6622 }, { "epoch": 0.386857476635514, "grad_norm": 1.7558274269104004, "learning_rate": 1.403427203119767e-05, "loss": 0.8519, "step": 6623 }, { "epoch": 0.38691588785046727, "grad_norm": 2.3639678955078125, "learning_rate": 1.403254090146001e-05, "loss": 1.0191, "step": 6624 }, { "epoch": 0.3869742990654206, "grad_norm": 1.1006604433059692, "learning_rate": 1.4030809627395059e-05, "loss": 0.8029, "step": 6625 }, { "epoch": 0.38703271028037384, "grad_norm": 1.419267177581787, "learning_rate": 1.4029078209064781e-05, "loss": 0.9313, "step": 6626 }, { "epoch": 0.3870911214953271, "grad_norm": 1.2277309894561768, "learning_rate": 1.4027346646531144e-05, "loss": 0.5571, "step": 6627 }, { "epoch": 0.38714953271028035, "grad_norm": 1.8582431077957153, "learning_rate": 1.4025614939856125e-05, "loss": 0.953, "step": 6628 }, { "epoch": 0.38720794392523367, "grad_norm": 1.0720608234405518, "learning_rate": 1.40238830891017e-05, "loss": 0.571, "step": 6629 }, { "epoch": 0.3872663551401869, "grad_norm": 2.6397550106048584, "learning_rate": 1.402215109432985e-05, "loss": 0.8699, "step": 6630 }, { "epoch": 0.3873247663551402, "grad_norm": 1.372532844543457, "learning_rate": 1.402041895560257e-05, "loss": 0.9318, "step": 6631 }, { "epoch": 0.38738317757009344, "grad_norm": 1.8463470935821533, "learning_rate": 1.4018686672981851e-05, "loss": 0.8099, "step": 6632 }, { "epoch": 0.38744158878504675, "grad_norm": 3.174978494644165, "learning_rate": 1.4016954246529697e-05, "loss": 0.8603, "step": 6633 }, { "epoch": 0.3875, "grad_norm": 1.1348093748092651, "learning_rate": 1.4015221676308107e-05, "loss": 0.7378, "step": 6634 }, { "epoch": 0.38755841121495327, "grad_norm": 1.9174282550811768, "learning_rate": 1.4013488962379091e-05, "loss": 0.9665, "step": 6635 }, { "epoch": 0.3876168224299065, "grad_norm": 2.2820162773132324, "learning_rate": 1.401175610480467e-05, "loss": 0.9189, "step": 6636 }, { "epoch": 0.38767523364485984, "grad_norm": 1.6147143840789795, "learning_rate": 1.4010023103646857e-05, "loss": 0.8475, "step": 6637 }, { "epoch": 0.3877336448598131, "grad_norm": 3.3975744247436523, "learning_rate": 1.4008289958967685e-05, "loss": 0.9342, "step": 6638 }, { "epoch": 0.38779205607476636, "grad_norm": 1.162998914718628, "learning_rate": 1.4006556670829175e-05, "loss": 0.6651, "step": 6639 }, { "epoch": 0.3878504672897196, "grad_norm": 2.506248950958252, "learning_rate": 1.400482323929337e-05, "loss": 0.7087, "step": 6640 }, { "epoch": 0.38790887850467287, "grad_norm": 2.281162738800049, "learning_rate": 1.4003089664422306e-05, "loss": 0.8114, "step": 6641 }, { "epoch": 0.3879672897196262, "grad_norm": 1.0804147720336914, "learning_rate": 1.4001355946278032e-05, "loss": 0.7807, "step": 6642 }, { "epoch": 0.38802570093457944, "grad_norm": 1.9014118909835815, "learning_rate": 1.3999622084922599e-05, "loss": 0.6818, "step": 6643 }, { "epoch": 0.3880841121495327, "grad_norm": 2.3459651470184326, "learning_rate": 1.3997888080418061e-05, "loss": 0.8842, "step": 6644 }, { "epoch": 0.38814252336448596, "grad_norm": 1.351022481918335, "learning_rate": 1.399615393282648e-05, "loss": 0.9629, "step": 6645 }, { "epoch": 0.38820093457943927, "grad_norm": 1.404110312461853, "learning_rate": 1.399441964220992e-05, "loss": 0.8277, "step": 6646 }, { "epoch": 0.38825934579439253, "grad_norm": 2.8335447311401367, "learning_rate": 1.3992685208630459e-05, "loss": 0.911, "step": 6647 }, { "epoch": 0.3883177570093458, "grad_norm": 2.107149600982666, "learning_rate": 1.3990950632150167e-05, "loss": 0.8305, "step": 6648 }, { "epoch": 0.38837616822429905, "grad_norm": 1.9789834022521973, "learning_rate": 1.3989215912831125e-05, "loss": 0.8551, "step": 6649 }, { "epoch": 0.38843457943925236, "grad_norm": 2.3492512702941895, "learning_rate": 1.3987481050735424e-05, "loss": 0.8378, "step": 6650 }, { "epoch": 0.3884929906542056, "grad_norm": 1.3364009857177734, "learning_rate": 1.3985746045925157e-05, "loss": 0.7414, "step": 6651 }, { "epoch": 0.3885514018691589, "grad_norm": 1.417130947113037, "learning_rate": 1.3984010898462417e-05, "loss": 0.7521, "step": 6652 }, { "epoch": 0.38860981308411213, "grad_norm": 2.22281813621521, "learning_rate": 1.3982275608409305e-05, "loss": 0.992, "step": 6653 }, { "epoch": 0.38866822429906545, "grad_norm": 1.1102526187896729, "learning_rate": 1.3980540175827933e-05, "loss": 0.769, "step": 6654 }, { "epoch": 0.3887266355140187, "grad_norm": 1.6844284534454346, "learning_rate": 1.3978804600780412e-05, "loss": 0.8532, "step": 6655 }, { "epoch": 0.38878504672897196, "grad_norm": 1.6211988925933838, "learning_rate": 1.3977068883328854e-05, "loss": 0.9415, "step": 6656 }, { "epoch": 0.3888434579439252, "grad_norm": 1.3167327642440796, "learning_rate": 1.3975333023535388e-05, "loss": 0.8659, "step": 6657 }, { "epoch": 0.3889018691588785, "grad_norm": 1.9568748474121094, "learning_rate": 1.3973597021462142e-05, "loss": 0.9612, "step": 6658 }, { "epoch": 0.3889602803738318, "grad_norm": 1.246802806854248, "learning_rate": 1.3971860877171243e-05, "loss": 0.921, "step": 6659 }, { "epoch": 0.38901869158878505, "grad_norm": 1.1364390850067139, "learning_rate": 1.3970124590724832e-05, "loss": 0.7969, "step": 6660 }, { "epoch": 0.3890771028037383, "grad_norm": 1.3188090324401855, "learning_rate": 1.3968388162185051e-05, "loss": 1.0378, "step": 6661 }, { "epoch": 0.38913551401869156, "grad_norm": 1.352397084236145, "learning_rate": 1.396665159161405e-05, "loss": 0.9158, "step": 6662 }, { "epoch": 0.3891939252336449, "grad_norm": 1.104246973991394, "learning_rate": 1.3964914879073978e-05, "loss": 0.9834, "step": 6663 }, { "epoch": 0.38925233644859814, "grad_norm": 1.612625241279602, "learning_rate": 1.3963178024626997e-05, "loss": 0.832, "step": 6664 }, { "epoch": 0.3893107476635514, "grad_norm": 0.997369647026062, "learning_rate": 1.3961441028335272e-05, "loss": 0.7271, "step": 6665 }, { "epoch": 0.38936915887850465, "grad_norm": 1.476346731185913, "learning_rate": 1.395970389026096e-05, "loss": 0.8758, "step": 6666 }, { "epoch": 0.38942757009345796, "grad_norm": 0.9112341403961182, "learning_rate": 1.3957966610466252e-05, "loss": 0.7159, "step": 6667 }, { "epoch": 0.3894859813084112, "grad_norm": 1.7309235334396362, "learning_rate": 1.3956229189013308e-05, "loss": 0.849, "step": 6668 }, { "epoch": 0.3895443925233645, "grad_norm": 1.2926621437072754, "learning_rate": 1.3954491625964325e-05, "loss": 0.8675, "step": 6669 }, { "epoch": 0.38960280373831774, "grad_norm": 1.9297972917556763, "learning_rate": 1.3952753921381486e-05, "loss": 0.7914, "step": 6670 }, { "epoch": 0.38966121495327105, "grad_norm": 1.2644795179367065, "learning_rate": 1.395101607532698e-05, "loss": 0.8991, "step": 6671 }, { "epoch": 0.3897196261682243, "grad_norm": 1.65181565284729, "learning_rate": 1.394927808786302e-05, "loss": 0.9786, "step": 6672 }, { "epoch": 0.38977803738317757, "grad_norm": 1.4655941724777222, "learning_rate": 1.3947539959051794e-05, "loss": 0.7323, "step": 6673 }, { "epoch": 0.3898364485981308, "grad_norm": 2.421518325805664, "learning_rate": 1.3945801688955519e-05, "loss": 0.789, "step": 6674 }, { "epoch": 0.38989485981308414, "grad_norm": 1.3477556705474854, "learning_rate": 1.3944063277636405e-05, "loss": 0.6977, "step": 6675 }, { "epoch": 0.3899532710280374, "grad_norm": 2.72721266746521, "learning_rate": 1.3942324725156676e-05, "loss": 0.7364, "step": 6676 }, { "epoch": 0.39001168224299065, "grad_norm": 1.1932883262634277, "learning_rate": 1.3940586031578552e-05, "loss": 0.6287, "step": 6677 }, { "epoch": 0.3900700934579439, "grad_norm": 1.8416776657104492, "learning_rate": 1.3938847196964262e-05, "loss": 0.9103, "step": 6678 }, { "epoch": 0.39012850467289717, "grad_norm": 2.0035147666931152, "learning_rate": 1.3937108221376041e-05, "loss": 0.9514, "step": 6679 }, { "epoch": 0.3901869158878505, "grad_norm": 2.523911952972412, "learning_rate": 1.393536910487613e-05, "loss": 0.8144, "step": 6680 }, { "epoch": 0.39024532710280374, "grad_norm": 2.574256420135498, "learning_rate": 1.393362984752677e-05, "loss": 1.0848, "step": 6681 }, { "epoch": 0.390303738317757, "grad_norm": 1.1579786539077759, "learning_rate": 1.393189044939021e-05, "loss": 0.7209, "step": 6682 }, { "epoch": 0.39036214953271026, "grad_norm": 1.0666579008102417, "learning_rate": 1.3930150910528708e-05, "loss": 0.7931, "step": 6683 }, { "epoch": 0.39042056074766357, "grad_norm": 1.6825495958328247, "learning_rate": 1.3928411231004522e-05, "loss": 0.8613, "step": 6684 }, { "epoch": 0.3904789719626168, "grad_norm": 2.495715379714966, "learning_rate": 1.392667141087991e-05, "loss": 1.0731, "step": 6685 }, { "epoch": 0.3905373831775701, "grad_norm": 2.4534363746643066, "learning_rate": 1.3924931450217152e-05, "loss": 0.8935, "step": 6686 }, { "epoch": 0.39059579439252334, "grad_norm": 1.1079933643341064, "learning_rate": 1.3923191349078513e-05, "loss": 0.7941, "step": 6687 }, { "epoch": 0.39065420560747666, "grad_norm": 1.6010074615478516, "learning_rate": 1.3921451107526275e-05, "loss": 0.8087, "step": 6688 }, { "epoch": 0.3907126168224299, "grad_norm": 1.1062517166137695, "learning_rate": 1.3919710725622726e-05, "loss": 0.6629, "step": 6689 }, { "epoch": 0.3907710280373832, "grad_norm": 1.398009181022644, "learning_rate": 1.3917970203430154e-05, "loss": 0.8529, "step": 6690 }, { "epoch": 0.39082943925233643, "grad_norm": 1.2846473455429077, "learning_rate": 1.391622954101085e-05, "loss": 0.7734, "step": 6691 }, { "epoch": 0.39088785046728974, "grad_norm": 1.7115144729614258, "learning_rate": 1.3914488738427117e-05, "loss": 0.753, "step": 6692 }, { "epoch": 0.390946261682243, "grad_norm": 1.2705857753753662, "learning_rate": 1.3912747795741255e-05, "loss": 0.893, "step": 6693 }, { "epoch": 0.39100467289719626, "grad_norm": 1.5739386081695557, "learning_rate": 1.391100671301558e-05, "loss": 1.0344, "step": 6694 }, { "epoch": 0.3910630841121495, "grad_norm": 1.1606425046920776, "learning_rate": 1.3909265490312404e-05, "loss": 0.7731, "step": 6695 }, { "epoch": 0.39112149532710283, "grad_norm": 1.1729884147644043, "learning_rate": 1.3907524127694045e-05, "loss": 0.763, "step": 6696 }, { "epoch": 0.3911799065420561, "grad_norm": 1.3708930015563965, "learning_rate": 1.3905782625222827e-05, "loss": 0.8936, "step": 6697 }, { "epoch": 0.39123831775700935, "grad_norm": 1.281546950340271, "learning_rate": 1.390404098296108e-05, "loss": 0.9249, "step": 6698 }, { "epoch": 0.3912967289719626, "grad_norm": 1.4707818031311035, "learning_rate": 1.3902299200971138e-05, "loss": 0.8848, "step": 6699 }, { "epoch": 0.39135514018691586, "grad_norm": 1.3991272449493408, "learning_rate": 1.390055727931535e-05, "loss": 0.7856, "step": 6700 }, { "epoch": 0.3914135514018692, "grad_norm": 1.3819688558578491, "learning_rate": 1.3898815218056043e-05, "loss": 0.8916, "step": 6701 }, { "epoch": 0.39147196261682243, "grad_norm": 1.9473466873168945, "learning_rate": 1.389707301725558e-05, "loss": 0.9, "step": 6702 }, { "epoch": 0.3915303738317757, "grad_norm": 1.105241060256958, "learning_rate": 1.389533067697631e-05, "loss": 0.7261, "step": 6703 }, { "epoch": 0.39158878504672895, "grad_norm": 2.109325885772705, "learning_rate": 1.3893588197280595e-05, "loss": 0.9664, "step": 6704 }, { "epoch": 0.39164719626168226, "grad_norm": 1.622120976448059, "learning_rate": 1.38918455782308e-05, "loss": 0.9137, "step": 6705 }, { "epoch": 0.3917056074766355, "grad_norm": 2.3067290782928467, "learning_rate": 1.389010281988929e-05, "loss": 1.0154, "step": 6706 }, { "epoch": 0.3917640186915888, "grad_norm": 1.1282963752746582, "learning_rate": 1.3888359922318442e-05, "loss": 0.8104, "step": 6707 }, { "epoch": 0.39182242990654204, "grad_norm": 1.9111994504928589, "learning_rate": 1.3886616885580636e-05, "loss": 0.8515, "step": 6708 }, { "epoch": 0.39188084112149535, "grad_norm": 1.3009015321731567, "learning_rate": 1.3884873709738259e-05, "loss": 0.8053, "step": 6709 }, { "epoch": 0.3919392523364486, "grad_norm": 1.1095088720321655, "learning_rate": 1.3883130394853695e-05, "loss": 0.8278, "step": 6710 }, { "epoch": 0.39199766355140186, "grad_norm": 1.6017732620239258, "learning_rate": 1.388138694098934e-05, "loss": 0.8469, "step": 6711 }, { "epoch": 0.3920560747663551, "grad_norm": 1.8870015144348145, "learning_rate": 1.3879643348207594e-05, "loss": 0.7778, "step": 6712 }, { "epoch": 0.39211448598130844, "grad_norm": 1.616862416267395, "learning_rate": 1.3877899616570865e-05, "loss": 0.8932, "step": 6713 }, { "epoch": 0.3921728971962617, "grad_norm": 1.3162585496902466, "learning_rate": 1.3876155746141558e-05, "loss": 0.7456, "step": 6714 }, { "epoch": 0.39223130841121495, "grad_norm": 1.568503737449646, "learning_rate": 1.3874411736982087e-05, "loss": 0.8229, "step": 6715 }, { "epoch": 0.3922897196261682, "grad_norm": 1.8304831981658936, "learning_rate": 1.3872667589154873e-05, "loss": 0.8341, "step": 6716 }, { "epoch": 0.3923481308411215, "grad_norm": 1.0583473443984985, "learning_rate": 1.3870923302722341e-05, "loss": 0.6898, "step": 6717 }, { "epoch": 0.3924065420560748, "grad_norm": 1.4255024194717407, "learning_rate": 1.3869178877746917e-05, "loss": 0.9356, "step": 6718 }, { "epoch": 0.39246495327102804, "grad_norm": 1.8861949443817139, "learning_rate": 1.3867434314291036e-05, "loss": 1.0043, "step": 6719 }, { "epoch": 0.3925233644859813, "grad_norm": 1.5184147357940674, "learning_rate": 1.3865689612417138e-05, "loss": 0.8255, "step": 6720 }, { "epoch": 0.39258177570093455, "grad_norm": 1.7600096464157104, "learning_rate": 1.386394477218767e-05, "loss": 0.8002, "step": 6721 }, { "epoch": 0.39264018691588787, "grad_norm": 1.5777348279953003, "learning_rate": 1.3862199793665077e-05, "loss": 0.8257, "step": 6722 }, { "epoch": 0.3926985981308411, "grad_norm": 1.366744041442871, "learning_rate": 1.3860454676911814e-05, "loss": 0.6631, "step": 6723 }, { "epoch": 0.3927570093457944, "grad_norm": 2.0077474117279053, "learning_rate": 1.3858709421990337e-05, "loss": 0.8986, "step": 6724 }, { "epoch": 0.39281542056074764, "grad_norm": 1.0148917436599731, "learning_rate": 1.3856964028963119e-05, "loss": 0.8457, "step": 6725 }, { "epoch": 0.39287383177570095, "grad_norm": 1.6309741735458374, "learning_rate": 1.3855218497892616e-05, "loss": 0.9999, "step": 6726 }, { "epoch": 0.3929322429906542, "grad_norm": 1.339109182357788, "learning_rate": 1.385347282884131e-05, "loss": 1.0683, "step": 6727 }, { "epoch": 0.39299065420560747, "grad_norm": 1.4560832977294922, "learning_rate": 1.3851727021871679e-05, "loss": 0.8883, "step": 6728 }, { "epoch": 0.39304906542056073, "grad_norm": 1.30412757396698, "learning_rate": 1.3849981077046204e-05, "loss": 0.7783, "step": 6729 }, { "epoch": 0.39310747663551404, "grad_norm": 1.3573436737060547, "learning_rate": 1.3848234994427377e-05, "loss": 0.7972, "step": 6730 }, { "epoch": 0.3931658878504673, "grad_norm": 1.1832369565963745, "learning_rate": 1.3846488774077687e-05, "loss": 0.8249, "step": 6731 }, { "epoch": 0.39322429906542056, "grad_norm": 1.6369514465332031, "learning_rate": 1.3844742416059634e-05, "loss": 1.0564, "step": 6732 }, { "epoch": 0.3932827102803738, "grad_norm": 1.166935920715332, "learning_rate": 1.3842995920435722e-05, "loss": 0.9495, "step": 6733 }, { "epoch": 0.39334112149532713, "grad_norm": 1.2332731485366821, "learning_rate": 1.384124928726846e-05, "loss": 0.7622, "step": 6734 }, { "epoch": 0.3933995327102804, "grad_norm": 1.5254437923431396, "learning_rate": 1.3839502516620362e-05, "loss": 0.9484, "step": 6735 }, { "epoch": 0.39345794392523364, "grad_norm": 1.188893437385559, "learning_rate": 1.3837755608553945e-05, "loss": 0.9094, "step": 6736 }, { "epoch": 0.3935163551401869, "grad_norm": 1.0877894163131714, "learning_rate": 1.3836008563131726e-05, "loss": 0.609, "step": 6737 }, { "epoch": 0.39357476635514016, "grad_norm": 1.4763563871383667, "learning_rate": 1.3834261380416243e-05, "loss": 0.8253, "step": 6738 }, { "epoch": 0.3936331775700935, "grad_norm": 1.9393726587295532, "learning_rate": 1.3832514060470026e-05, "loss": 1.0306, "step": 6739 }, { "epoch": 0.39369158878504673, "grad_norm": 1.854153037071228, "learning_rate": 1.3830766603355605e-05, "loss": 0.6987, "step": 6740 }, { "epoch": 0.39375, "grad_norm": 1.6527866125106812, "learning_rate": 1.3829019009135531e-05, "loss": 0.8088, "step": 6741 }, { "epoch": 0.39380841121495325, "grad_norm": 1.4343626499176025, "learning_rate": 1.3827271277872351e-05, "loss": 0.9973, "step": 6742 }, { "epoch": 0.39386682242990656, "grad_norm": 1.2683751583099365, "learning_rate": 1.3825523409628613e-05, "loss": 0.8374, "step": 6743 }, { "epoch": 0.3939252336448598, "grad_norm": 1.961116075515747, "learning_rate": 1.3823775404466878e-05, "loss": 0.6131, "step": 6744 }, { "epoch": 0.3939836448598131, "grad_norm": 1.342303991317749, "learning_rate": 1.3822027262449704e-05, "loss": 0.7839, "step": 6745 }, { "epoch": 0.39404205607476633, "grad_norm": 1.0279486179351807, "learning_rate": 1.3820278983639665e-05, "loss": 0.7207, "step": 6746 }, { "epoch": 0.39410046728971965, "grad_norm": 1.1320103406906128, "learning_rate": 1.3818530568099328e-05, "loss": 0.7382, "step": 6747 }, { "epoch": 0.3941588785046729, "grad_norm": 1.0669207572937012, "learning_rate": 1.3816782015891272e-05, "loss": 0.7965, "step": 6748 }, { "epoch": 0.39421728971962616, "grad_norm": 1.1287680864334106, "learning_rate": 1.381503332707808e-05, "loss": 0.8229, "step": 6749 }, { "epoch": 0.3942757009345794, "grad_norm": 1.1360052824020386, "learning_rate": 1.3813284501722333e-05, "loss": 0.74, "step": 6750 }, { "epoch": 0.39433411214953273, "grad_norm": 1.3980865478515625, "learning_rate": 1.3811535539886628e-05, "loss": 0.9066, "step": 6751 }, { "epoch": 0.394392523364486, "grad_norm": 1.0640908479690552, "learning_rate": 1.380978644163356e-05, "loss": 0.688, "step": 6752 }, { "epoch": 0.39445093457943925, "grad_norm": 0.9892295002937317, "learning_rate": 1.3808037207025728e-05, "loss": 0.7356, "step": 6753 }, { "epoch": 0.3945093457943925, "grad_norm": 1.230116367340088, "learning_rate": 1.3806287836125744e-05, "loss": 0.816, "step": 6754 }, { "epoch": 0.3945677570093458, "grad_norm": 1.2999566793441772, "learning_rate": 1.3804538328996215e-05, "loss": 0.9169, "step": 6755 }, { "epoch": 0.3946261682242991, "grad_norm": 1.311396598815918, "learning_rate": 1.3802788685699757e-05, "loss": 0.8088, "step": 6756 }, { "epoch": 0.39468457943925234, "grad_norm": 1.3846418857574463, "learning_rate": 1.380103890629899e-05, "loss": 0.7491, "step": 6757 }, { "epoch": 0.3947429906542056, "grad_norm": 1.179189682006836, "learning_rate": 1.3799288990856545e-05, "loss": 0.8318, "step": 6758 }, { "epoch": 0.39480140186915885, "grad_norm": 1.4130172729492188, "learning_rate": 1.3797538939435045e-05, "loss": 0.7849, "step": 6759 }, { "epoch": 0.39485981308411217, "grad_norm": 1.406972885131836, "learning_rate": 1.379578875209713e-05, "loss": 0.7144, "step": 6760 }, { "epoch": 0.3949182242990654, "grad_norm": 1.749326467514038, "learning_rate": 1.379403842890544e-05, "loss": 0.8969, "step": 6761 }, { "epoch": 0.3949766355140187, "grad_norm": 1.3201090097427368, "learning_rate": 1.379228796992262e-05, "loss": 0.8493, "step": 6762 }, { "epoch": 0.39503504672897194, "grad_norm": 1.0786585807800293, "learning_rate": 1.3790537375211324e-05, "loss": 0.7287, "step": 6763 }, { "epoch": 0.39509345794392525, "grad_norm": 1.6118189096450806, "learning_rate": 1.37887866448342e-05, "loss": 0.8833, "step": 6764 }, { "epoch": 0.3951518691588785, "grad_norm": 1.402835726737976, "learning_rate": 1.378703577885391e-05, "loss": 0.892, "step": 6765 }, { "epoch": 0.39521028037383177, "grad_norm": 1.3542492389678955, "learning_rate": 1.378528477733312e-05, "loss": 0.9019, "step": 6766 }, { "epoch": 0.395268691588785, "grad_norm": 1.2885433435440063, "learning_rate": 1.3783533640334499e-05, "loss": 0.7085, "step": 6767 }, { "epoch": 0.39532710280373834, "grad_norm": 1.1516978740692139, "learning_rate": 1.3781782367920722e-05, "loss": 0.8293, "step": 6768 }, { "epoch": 0.3953855140186916, "grad_norm": 1.272883653640747, "learning_rate": 1.3780030960154467e-05, "loss": 0.8779, "step": 6769 }, { "epoch": 0.39544392523364486, "grad_norm": 1.4421635866165161, "learning_rate": 1.3778279417098418e-05, "loss": 0.8928, "step": 6770 }, { "epoch": 0.3955023364485981, "grad_norm": 1.4604994058609009, "learning_rate": 1.3776527738815264e-05, "loss": 0.7941, "step": 6771 }, { "epoch": 0.3955607476635514, "grad_norm": 0.9517174959182739, "learning_rate": 1.37747759253677e-05, "loss": 0.8405, "step": 6772 }, { "epoch": 0.3956191588785047, "grad_norm": 1.9870235919952393, "learning_rate": 1.3773023976818425e-05, "loss": 0.8572, "step": 6773 }, { "epoch": 0.39567757009345794, "grad_norm": 1.2324858903884888, "learning_rate": 1.3771271893230138e-05, "loss": 0.8451, "step": 6774 }, { "epoch": 0.3957359813084112, "grad_norm": 1.4537146091461182, "learning_rate": 1.3769519674665552e-05, "loss": 0.9896, "step": 6775 }, { "epoch": 0.3957943925233645, "grad_norm": 1.7601813077926636, "learning_rate": 1.3767767321187377e-05, "loss": 0.7857, "step": 6776 }, { "epoch": 0.39585280373831777, "grad_norm": 1.1994733810424805, "learning_rate": 1.3766014832858334e-05, "loss": 0.6773, "step": 6777 }, { "epoch": 0.39591121495327103, "grad_norm": 1.6518871784210205, "learning_rate": 1.3764262209741144e-05, "loss": 0.7673, "step": 6778 }, { "epoch": 0.3959696261682243, "grad_norm": 1.5308189392089844, "learning_rate": 1.3762509451898534e-05, "loss": 1.0306, "step": 6779 }, { "epoch": 0.39602803738317754, "grad_norm": 1.507237195968628, "learning_rate": 1.3760756559393235e-05, "loss": 0.9829, "step": 6780 }, { "epoch": 0.39608644859813086, "grad_norm": 1.3803675174713135, "learning_rate": 1.3759003532287989e-05, "loss": 0.7619, "step": 6781 }, { "epoch": 0.3961448598130841, "grad_norm": 1.2651011943817139, "learning_rate": 1.3757250370645534e-05, "loss": 0.847, "step": 6782 }, { "epoch": 0.3962032710280374, "grad_norm": 1.4046088457107544, "learning_rate": 1.3755497074528619e-05, "loss": 0.9933, "step": 6783 }, { "epoch": 0.39626168224299063, "grad_norm": 1.4224886894226074, "learning_rate": 1.3753743643999991e-05, "loss": 0.9895, "step": 6784 }, { "epoch": 0.39632009345794394, "grad_norm": 1.4340664148330688, "learning_rate": 1.3751990079122412e-05, "loss": 0.8779, "step": 6785 }, { "epoch": 0.3963785046728972, "grad_norm": 2.2284302711486816, "learning_rate": 1.375023637995864e-05, "loss": 0.7256, "step": 6786 }, { "epoch": 0.39643691588785046, "grad_norm": 1.7352981567382812, "learning_rate": 1.3748482546571445e-05, "loss": 0.8089, "step": 6787 }, { "epoch": 0.3964953271028037, "grad_norm": 1.8333238363265991, "learning_rate": 1.3746728579023591e-05, "loss": 0.8556, "step": 6788 }, { "epoch": 0.39655373831775703, "grad_norm": 1.0459774732589722, "learning_rate": 1.374497447737786e-05, "loss": 0.8802, "step": 6789 }, { "epoch": 0.3966121495327103, "grad_norm": 1.3804097175598145, "learning_rate": 1.3743220241697029e-05, "loss": 0.7175, "step": 6790 }, { "epoch": 0.39667056074766355, "grad_norm": 1.0675915479660034, "learning_rate": 1.3741465872043883e-05, "loss": 0.7402, "step": 6791 }, { "epoch": 0.3967289719626168, "grad_norm": 1.7794582843780518, "learning_rate": 1.373971136848122e-05, "loss": 0.9263, "step": 6792 }, { "epoch": 0.3967873831775701, "grad_norm": 1.163651466369629, "learning_rate": 1.3737956731071822e-05, "loss": 0.8053, "step": 6793 }, { "epoch": 0.3968457943925234, "grad_norm": 2.296485185623169, "learning_rate": 1.3736201959878497e-05, "loss": 0.8595, "step": 6794 }, { "epoch": 0.39690420560747663, "grad_norm": 1.403016209602356, "learning_rate": 1.3734447054964045e-05, "loss": 0.79, "step": 6795 }, { "epoch": 0.3969626168224299, "grad_norm": 1.3119397163391113, "learning_rate": 1.3732692016391278e-05, "loss": 0.8101, "step": 6796 }, { "epoch": 0.39702102803738315, "grad_norm": 1.1470365524291992, "learning_rate": 1.3730936844223015e-05, "loss": 0.7861, "step": 6797 }, { "epoch": 0.39707943925233646, "grad_norm": 1.632616400718689, "learning_rate": 1.3729181538522062e-05, "loss": 0.8968, "step": 6798 }, { "epoch": 0.3971378504672897, "grad_norm": 1.2564808130264282, "learning_rate": 1.3727426099351254e-05, "loss": 0.8098, "step": 6799 }, { "epoch": 0.397196261682243, "grad_norm": 1.4447717666625977, "learning_rate": 1.3725670526773413e-05, "loss": 0.8789, "step": 6800 }, { "epoch": 0.39725467289719624, "grad_norm": 1.3268766403198242, "learning_rate": 1.3723914820851371e-05, "loss": 0.9437, "step": 6801 }, { "epoch": 0.39731308411214955, "grad_norm": 1.6237226724624634, "learning_rate": 1.3722158981647978e-05, "loss": 0.9048, "step": 6802 }, { "epoch": 0.3973714953271028, "grad_norm": 1.1538621187210083, "learning_rate": 1.372040300922606e-05, "loss": 0.7301, "step": 6803 }, { "epoch": 0.39742990654205607, "grad_norm": 1.9889559745788574, "learning_rate": 1.3718646903648476e-05, "loss": 0.6518, "step": 6804 }, { "epoch": 0.3974883177570093, "grad_norm": 1.0057886838912964, "learning_rate": 1.3716890664978072e-05, "loss": 0.7104, "step": 6805 }, { "epoch": 0.39754672897196264, "grad_norm": 1.0524784326553345, "learning_rate": 1.3715134293277706e-05, "loss": 0.7047, "step": 6806 }, { "epoch": 0.3976051401869159, "grad_norm": 1.6016623973846436, "learning_rate": 1.3713377788610244e-05, "loss": 0.8365, "step": 6807 }, { "epoch": 0.39766355140186915, "grad_norm": 1.1568821668624878, "learning_rate": 1.371162115103855e-05, "loss": 0.8795, "step": 6808 }, { "epoch": 0.3977219626168224, "grad_norm": 1.394814133644104, "learning_rate": 1.370986438062549e-05, "loss": 0.793, "step": 6809 }, { "epoch": 0.3977803738317757, "grad_norm": 1.5063717365264893, "learning_rate": 1.370810747743395e-05, "loss": 0.7818, "step": 6810 }, { "epoch": 0.397838785046729, "grad_norm": 0.9900177121162415, "learning_rate": 1.3706350441526801e-05, "loss": 0.732, "step": 6811 }, { "epoch": 0.39789719626168224, "grad_norm": 1.3708313703536987, "learning_rate": 1.3704593272966935e-05, "loss": 0.9481, "step": 6812 }, { "epoch": 0.3979556074766355, "grad_norm": 1.6563241481781006, "learning_rate": 1.3702835971817239e-05, "loss": 0.8693, "step": 6813 }, { "epoch": 0.3980140186915888, "grad_norm": 1.1518698930740356, "learning_rate": 1.370107853814061e-05, "loss": 0.8017, "step": 6814 }, { "epoch": 0.39807242990654207, "grad_norm": 1.4334046840667725, "learning_rate": 1.3699320971999945e-05, "loss": 0.7092, "step": 6815 }, { "epoch": 0.3981308411214953, "grad_norm": 1.234079360961914, "learning_rate": 1.3697563273458153e-05, "loss": 0.7482, "step": 6816 }, { "epoch": 0.3981892523364486, "grad_norm": 1.9115458726882935, "learning_rate": 1.3695805442578136e-05, "loss": 0.9712, "step": 6817 }, { "epoch": 0.39824766355140184, "grad_norm": 1.8689590692520142, "learning_rate": 1.3694047479422815e-05, "loss": 0.7449, "step": 6818 }, { "epoch": 0.39830607476635516, "grad_norm": 1.6297664642333984, "learning_rate": 1.3692289384055104e-05, "loss": 0.8465, "step": 6819 }, { "epoch": 0.3983644859813084, "grad_norm": 1.6331491470336914, "learning_rate": 1.369053115653793e-05, "loss": 0.7497, "step": 6820 }, { "epoch": 0.39842289719626167, "grad_norm": 2.1384565830230713, "learning_rate": 1.368877279693422e-05, "loss": 0.9669, "step": 6821 }, { "epoch": 0.39848130841121493, "grad_norm": 0.9961921572685242, "learning_rate": 1.3687014305306905e-05, "loss": 0.8278, "step": 6822 }, { "epoch": 0.39853971962616824, "grad_norm": 1.050248146057129, "learning_rate": 1.3685255681718922e-05, "loss": 0.8425, "step": 6823 }, { "epoch": 0.3985981308411215, "grad_norm": 1.0493507385253906, "learning_rate": 1.3683496926233217e-05, "loss": 0.7731, "step": 6824 }, { "epoch": 0.39865654205607476, "grad_norm": 1.1766411066055298, "learning_rate": 1.3681738038912735e-05, "loss": 0.6446, "step": 6825 }, { "epoch": 0.398714953271028, "grad_norm": 1.2362933158874512, "learning_rate": 1.3679979019820429e-05, "loss": 0.9224, "step": 6826 }, { "epoch": 0.39877336448598133, "grad_norm": 1.6419317722320557, "learning_rate": 1.3678219869019252e-05, "loss": 0.8528, "step": 6827 }, { "epoch": 0.3988317757009346, "grad_norm": 1.3263297080993652, "learning_rate": 1.3676460586572167e-05, "loss": 0.7503, "step": 6828 }, { "epoch": 0.39889018691588785, "grad_norm": 1.6226218938827515, "learning_rate": 1.3674701172542142e-05, "loss": 0.9796, "step": 6829 }, { "epoch": 0.3989485981308411, "grad_norm": 1.080880880355835, "learning_rate": 1.3672941626992144e-05, "loss": 1.0391, "step": 6830 }, { "epoch": 0.3990070093457944, "grad_norm": 0.9891543984413147, "learning_rate": 1.3671181949985152e-05, "loss": 0.6863, "step": 6831 }, { "epoch": 0.3990654205607477, "grad_norm": 1.2352268695831299, "learning_rate": 1.3669422141584146e-05, "loss": 0.8872, "step": 6832 }, { "epoch": 0.39912383177570093, "grad_norm": 1.1943901777267456, "learning_rate": 1.3667662201852106e-05, "loss": 0.8815, "step": 6833 }, { "epoch": 0.3991822429906542, "grad_norm": 1.0221476554870605, "learning_rate": 1.3665902130852023e-05, "loss": 0.8151, "step": 6834 }, { "epoch": 0.3992406542056075, "grad_norm": 1.7804116010665894, "learning_rate": 1.3664141928646895e-05, "loss": 0.8284, "step": 6835 }, { "epoch": 0.39929906542056076, "grad_norm": 1.1621383428573608, "learning_rate": 1.3662381595299717e-05, "loss": 0.9475, "step": 6836 }, { "epoch": 0.399357476635514, "grad_norm": 1.9621732234954834, "learning_rate": 1.3660621130873492e-05, "loss": 0.8564, "step": 6837 }, { "epoch": 0.3994158878504673, "grad_norm": 1.4122538566589355, "learning_rate": 1.3658860535431235e-05, "loss": 0.7404, "step": 6838 }, { "epoch": 0.39947429906542054, "grad_norm": 1.29094398021698, "learning_rate": 1.3657099809035948e-05, "loss": 0.8304, "step": 6839 }, { "epoch": 0.39953271028037385, "grad_norm": 1.5206363201141357, "learning_rate": 1.3655338951750657e-05, "loss": 0.93, "step": 6840 }, { "epoch": 0.3995911214953271, "grad_norm": 1.245003342628479, "learning_rate": 1.3653577963638384e-05, "loss": 0.932, "step": 6841 }, { "epoch": 0.39964953271028036, "grad_norm": 2.0110180377960205, "learning_rate": 1.3651816844762148e-05, "loss": 0.6929, "step": 6842 }, { "epoch": 0.3997079439252336, "grad_norm": 1.135087013244629, "learning_rate": 1.3650055595184989e-05, "loss": 0.7178, "step": 6843 }, { "epoch": 0.39976635514018694, "grad_norm": 1.3464226722717285, "learning_rate": 1.3648294214969941e-05, "loss": 0.7857, "step": 6844 }, { "epoch": 0.3998247663551402, "grad_norm": 1.1342593431472778, "learning_rate": 1.3646532704180043e-05, "loss": 0.9022, "step": 6845 }, { "epoch": 0.39988317757009345, "grad_norm": 1.095273733139038, "learning_rate": 1.3644771062878341e-05, "loss": 0.8937, "step": 6846 }, { "epoch": 0.3999415887850467, "grad_norm": 1.2302688360214233, "learning_rate": 1.364300929112789e-05, "loss": 0.8798, "step": 6847 }, { "epoch": 0.4, "grad_norm": 1.1721482276916504, "learning_rate": 1.3641247388991734e-05, "loss": 0.8133, "step": 6848 }, { "epoch": 0.4000584112149533, "grad_norm": 1.334267258644104, "learning_rate": 1.3639485356532945e-05, "loss": 0.8441, "step": 6849 }, { "epoch": 0.40011682242990654, "grad_norm": 1.1136903762817383, "learning_rate": 1.3637723193814582e-05, "loss": 0.944, "step": 6850 }, { "epoch": 0.4001752336448598, "grad_norm": 1.6946895122528076, "learning_rate": 1.3635960900899715e-05, "loss": 0.9003, "step": 6851 }, { "epoch": 0.4002336448598131, "grad_norm": 1.097571849822998, "learning_rate": 1.3634198477851415e-05, "loss": 0.7121, "step": 6852 }, { "epoch": 0.40029205607476637, "grad_norm": 1.648793339729309, "learning_rate": 1.363243592473276e-05, "loss": 0.9948, "step": 6853 }, { "epoch": 0.4003504672897196, "grad_norm": 1.3656537532806396, "learning_rate": 1.3630673241606835e-05, "loss": 0.7651, "step": 6854 }, { "epoch": 0.4004088785046729, "grad_norm": 1.3652609586715698, "learning_rate": 1.3628910428536733e-05, "loss": 0.5903, "step": 6855 }, { "epoch": 0.40046728971962614, "grad_norm": 1.518311619758606, "learning_rate": 1.3627147485585534e-05, "loss": 0.8181, "step": 6856 }, { "epoch": 0.40052570093457945, "grad_norm": 1.1218619346618652, "learning_rate": 1.3625384412816346e-05, "loss": 0.9115, "step": 6857 }, { "epoch": 0.4005841121495327, "grad_norm": 1.4666575193405151, "learning_rate": 1.3623621210292264e-05, "loss": 0.7951, "step": 6858 }, { "epoch": 0.40064252336448597, "grad_norm": 1.4273688793182373, "learning_rate": 1.3621857878076396e-05, "loss": 0.8027, "step": 6859 }, { "epoch": 0.4007009345794392, "grad_norm": 1.1548171043395996, "learning_rate": 1.3620094416231857e-05, "loss": 0.8292, "step": 6860 }, { "epoch": 0.40075934579439254, "grad_norm": 2.4014570713043213, "learning_rate": 1.3618330824821753e-05, "loss": 0.937, "step": 6861 }, { "epoch": 0.4008177570093458, "grad_norm": 1.162353754043579, "learning_rate": 1.3616567103909214e-05, "loss": 0.722, "step": 6862 }, { "epoch": 0.40087616822429906, "grad_norm": 1.937622308731079, "learning_rate": 1.3614803253557358e-05, "loss": 0.8182, "step": 6863 }, { "epoch": 0.4009345794392523, "grad_norm": 2.136770009994507, "learning_rate": 1.3613039273829316e-05, "loss": 0.8658, "step": 6864 }, { "epoch": 0.4009929906542056, "grad_norm": 1.6520590782165527, "learning_rate": 1.3611275164788227e-05, "loss": 0.834, "step": 6865 }, { "epoch": 0.4010514018691589, "grad_norm": 2.6463208198547363, "learning_rate": 1.3609510926497223e-05, "loss": 0.7982, "step": 6866 }, { "epoch": 0.40110981308411214, "grad_norm": 1.1843531131744385, "learning_rate": 1.3607746559019446e-05, "loss": 0.7421, "step": 6867 }, { "epoch": 0.4011682242990654, "grad_norm": 2.816248893737793, "learning_rate": 1.3605982062418053e-05, "loss": 0.9683, "step": 6868 }, { "epoch": 0.4012266355140187, "grad_norm": 1.2918598651885986, "learning_rate": 1.3604217436756189e-05, "loss": 0.9748, "step": 6869 }, { "epoch": 0.401285046728972, "grad_norm": 2.4190149307250977, "learning_rate": 1.3602452682097012e-05, "loss": 0.8222, "step": 6870 }, { "epoch": 0.40134345794392523, "grad_norm": 1.836401104927063, "learning_rate": 1.3600687798503687e-05, "loss": 0.7324, "step": 6871 }, { "epoch": 0.4014018691588785, "grad_norm": 1.225666880607605, "learning_rate": 1.3598922786039375e-05, "loss": 0.6295, "step": 6872 }, { "epoch": 0.4014602803738318, "grad_norm": 1.5858886241912842, "learning_rate": 1.3597157644767251e-05, "loss": 0.7255, "step": 6873 }, { "epoch": 0.40151869158878506, "grad_norm": 2.6616389751434326, "learning_rate": 1.3595392374750495e-05, "loss": 1.0395, "step": 6874 }, { "epoch": 0.4015771028037383, "grad_norm": 1.3353190422058105, "learning_rate": 1.3593626976052277e-05, "loss": 0.7786, "step": 6875 }, { "epoch": 0.4016355140186916, "grad_norm": 1.7682033777236938, "learning_rate": 1.3591861448735786e-05, "loss": 0.8788, "step": 6876 }, { "epoch": 0.40169392523364483, "grad_norm": 2.6181583404541016, "learning_rate": 1.3590095792864215e-05, "loss": 0.913, "step": 6877 }, { "epoch": 0.40175233644859815, "grad_norm": 1.5273773670196533, "learning_rate": 1.3588330008500752e-05, "loss": 0.8122, "step": 6878 }, { "epoch": 0.4018107476635514, "grad_norm": 2.8839213848114014, "learning_rate": 1.3586564095708604e-05, "loss": 0.8185, "step": 6879 }, { "epoch": 0.40186915887850466, "grad_norm": 1.475128173828125, "learning_rate": 1.3584798054550963e-05, "loss": 0.7784, "step": 6880 }, { "epoch": 0.4019275700934579, "grad_norm": 1.9714758396148682, "learning_rate": 1.3583031885091042e-05, "loss": 0.9331, "step": 6881 }, { "epoch": 0.40198598130841123, "grad_norm": 1.7370038032531738, "learning_rate": 1.3581265587392059e-05, "loss": 0.7316, "step": 6882 }, { "epoch": 0.4020443925233645, "grad_norm": 1.3093363046646118, "learning_rate": 1.3579499161517223e-05, "loss": 0.8376, "step": 6883 }, { "epoch": 0.40210280373831775, "grad_norm": 1.566522479057312, "learning_rate": 1.357773260752976e-05, "loss": 0.8499, "step": 6884 }, { "epoch": 0.402161214953271, "grad_norm": 1.806718111038208, "learning_rate": 1.3575965925492894e-05, "loss": 0.8045, "step": 6885 }, { "epoch": 0.4022196261682243, "grad_norm": 1.9879218339920044, "learning_rate": 1.3574199115469852e-05, "loss": 0.9356, "step": 6886 }, { "epoch": 0.4022780373831776, "grad_norm": 1.9726225137710571, "learning_rate": 1.3572432177523877e-05, "loss": 0.9988, "step": 6887 }, { "epoch": 0.40233644859813084, "grad_norm": 1.1570613384246826, "learning_rate": 1.3570665111718206e-05, "loss": 0.9288, "step": 6888 }, { "epoch": 0.4023948598130841, "grad_norm": 1.3566070795059204, "learning_rate": 1.3568897918116084e-05, "loss": 0.7746, "step": 6889 }, { "epoch": 0.4024532710280374, "grad_norm": 6.074902057647705, "learning_rate": 1.3567130596780757e-05, "loss": 0.8429, "step": 6890 }, { "epoch": 0.40251168224299066, "grad_norm": 1.4233341217041016, "learning_rate": 1.3565363147775483e-05, "loss": 0.7914, "step": 6891 }, { "epoch": 0.4025700934579439, "grad_norm": 1.8859431743621826, "learning_rate": 1.3563595571163513e-05, "loss": 1.1279, "step": 6892 }, { "epoch": 0.4026285046728972, "grad_norm": 2.9112281799316406, "learning_rate": 1.3561827867008117e-05, "loss": 0.7772, "step": 6893 }, { "epoch": 0.4026869158878505, "grad_norm": 1.931187391281128, "learning_rate": 1.356006003537256e-05, "loss": 0.8815, "step": 6894 }, { "epoch": 0.40274532710280375, "grad_norm": 1.4125083684921265, "learning_rate": 1.3558292076320115e-05, "loss": 0.7925, "step": 6895 }, { "epoch": 0.402803738317757, "grad_norm": 1.1725244522094727, "learning_rate": 1.3556523989914054e-05, "loss": 0.7572, "step": 6896 }, { "epoch": 0.40286214953271027, "grad_norm": 1.3195143938064575, "learning_rate": 1.355475577621766e-05, "loss": 1.0418, "step": 6897 }, { "epoch": 0.4029205607476635, "grad_norm": 2.0805647373199463, "learning_rate": 1.3552987435294223e-05, "loss": 1.0044, "step": 6898 }, { "epoch": 0.40297897196261684, "grad_norm": 1.4546408653259277, "learning_rate": 1.3551218967207032e-05, "loss": 0.8461, "step": 6899 }, { "epoch": 0.4030373831775701, "grad_norm": 2.1775031089782715, "learning_rate": 1.3549450372019372e-05, "loss": 0.9391, "step": 6900 }, { "epoch": 0.40309579439252335, "grad_norm": 1.4211177825927734, "learning_rate": 1.3547681649794553e-05, "loss": 0.7976, "step": 6901 }, { "epoch": 0.4031542056074766, "grad_norm": 1.1744678020477295, "learning_rate": 1.3545912800595875e-05, "loss": 0.7474, "step": 6902 }, { "epoch": 0.4032126168224299, "grad_norm": 1.7947970628738403, "learning_rate": 1.3544143824486647e-05, "loss": 0.758, "step": 6903 }, { "epoch": 0.4032710280373832, "grad_norm": 1.1013399362564087, "learning_rate": 1.3542374721530181e-05, "loss": 0.7306, "step": 6904 }, { "epoch": 0.40332943925233644, "grad_norm": 2.8602230548858643, "learning_rate": 1.3540605491789793e-05, "loss": 0.9975, "step": 6905 }, { "epoch": 0.4033878504672897, "grad_norm": 0.9886209964752197, "learning_rate": 1.3538836135328807e-05, "loss": 0.6768, "step": 6906 }, { "epoch": 0.403446261682243, "grad_norm": 1.742355227470398, "learning_rate": 1.3537066652210551e-05, "loss": 0.8659, "step": 6907 }, { "epoch": 0.40350467289719627, "grad_norm": 1.2000954151153564, "learning_rate": 1.3535297042498353e-05, "loss": 0.7178, "step": 6908 }, { "epoch": 0.40356308411214953, "grad_norm": 0.8335860967636108, "learning_rate": 1.3533527306255547e-05, "loss": 0.7494, "step": 6909 }, { "epoch": 0.4036214953271028, "grad_norm": 1.4769368171691895, "learning_rate": 1.3531757443545476e-05, "loss": 0.7171, "step": 6910 }, { "epoch": 0.4036799065420561, "grad_norm": 1.2109918594360352, "learning_rate": 1.3529987454431486e-05, "loss": 0.8184, "step": 6911 }, { "epoch": 0.40373831775700936, "grad_norm": 1.328275442123413, "learning_rate": 1.3528217338976924e-05, "loss": 0.8207, "step": 6912 }, { "epoch": 0.4037967289719626, "grad_norm": 1.2815375328063965, "learning_rate": 1.3526447097245144e-05, "loss": 1.0706, "step": 6913 }, { "epoch": 0.4038551401869159, "grad_norm": 1.1657623052597046, "learning_rate": 1.35246767292995e-05, "loss": 0.7785, "step": 6914 }, { "epoch": 0.4039135514018692, "grad_norm": 1.6093708276748657, "learning_rate": 1.3522906235203362e-05, "loss": 0.9279, "step": 6915 }, { "epoch": 0.40397196261682244, "grad_norm": 0.9268635511398315, "learning_rate": 1.3521135615020092e-05, "loss": 0.722, "step": 6916 }, { "epoch": 0.4040303738317757, "grad_norm": 1.7550724744796753, "learning_rate": 1.351936486881306e-05, "loss": 0.992, "step": 6917 }, { "epoch": 0.40408878504672896, "grad_norm": 1.1399835348129272, "learning_rate": 1.351759399664565e-05, "loss": 0.7774, "step": 6918 }, { "epoch": 0.4041471962616822, "grad_norm": 1.1871176958084106, "learning_rate": 1.3515822998581237e-05, "loss": 0.8875, "step": 6919 }, { "epoch": 0.40420560747663553, "grad_norm": 1.3405399322509766, "learning_rate": 1.3514051874683207e-05, "loss": 0.6889, "step": 6920 }, { "epoch": 0.4042640186915888, "grad_norm": 1.0633465051651, "learning_rate": 1.3512280625014949e-05, "loss": 0.8403, "step": 6921 }, { "epoch": 0.40432242990654205, "grad_norm": 1.2162188291549683, "learning_rate": 1.3510509249639858e-05, "loss": 0.7034, "step": 6922 }, { "epoch": 0.4043808411214953, "grad_norm": 0.9832929372787476, "learning_rate": 1.3508737748621335e-05, "loss": 0.7836, "step": 6923 }, { "epoch": 0.4044392523364486, "grad_norm": 1.3160873651504517, "learning_rate": 1.350696612202278e-05, "loss": 1.0196, "step": 6924 }, { "epoch": 0.4044976635514019, "grad_norm": 1.1144126653671265, "learning_rate": 1.35051943699076e-05, "loss": 0.8727, "step": 6925 }, { "epoch": 0.40455607476635513, "grad_norm": 1.0171231031417847, "learning_rate": 1.3503422492339209e-05, "loss": 0.8343, "step": 6926 }, { "epoch": 0.4046144859813084, "grad_norm": 1.200504183769226, "learning_rate": 1.3501650489381023e-05, "loss": 0.8869, "step": 6927 }, { "epoch": 0.4046728971962617, "grad_norm": 1.1484131813049316, "learning_rate": 1.3499878361096465e-05, "loss": 0.9068, "step": 6928 }, { "epoch": 0.40473130841121496, "grad_norm": 1.0123521089553833, "learning_rate": 1.3498106107548961e-05, "loss": 0.7243, "step": 6929 }, { "epoch": 0.4047897196261682, "grad_norm": 1.1908164024353027, "learning_rate": 1.3496333728801934e-05, "loss": 0.7455, "step": 6930 }, { "epoch": 0.4048481308411215, "grad_norm": 1.5915136337280273, "learning_rate": 1.349456122491883e-05, "loss": 0.7759, "step": 6931 }, { "epoch": 0.4049065420560748, "grad_norm": 1.0436941385269165, "learning_rate": 1.349278859596308e-05, "loss": 0.7491, "step": 6932 }, { "epoch": 0.40496495327102805, "grad_norm": 1.201785683631897, "learning_rate": 1.3491015841998127e-05, "loss": 0.8081, "step": 6933 }, { "epoch": 0.4050233644859813, "grad_norm": 1.229730486869812, "learning_rate": 1.3489242963087423e-05, "loss": 0.6634, "step": 6934 }, { "epoch": 0.40508177570093457, "grad_norm": 2.479174852371216, "learning_rate": 1.3487469959294421e-05, "loss": 0.673, "step": 6935 }, { "epoch": 0.4051401869158878, "grad_norm": 1.3029006719589233, "learning_rate": 1.3485696830682573e-05, "loss": 0.7795, "step": 6936 }, { "epoch": 0.40519859813084114, "grad_norm": 1.470202088356018, "learning_rate": 1.3483923577315347e-05, "loss": 0.9466, "step": 6937 }, { "epoch": 0.4052570093457944, "grad_norm": 1.0555601119995117, "learning_rate": 1.3482150199256203e-05, "loss": 0.7152, "step": 6938 }, { "epoch": 0.40531542056074765, "grad_norm": 2.949171781539917, "learning_rate": 1.3480376696568615e-05, "loss": 0.8259, "step": 6939 }, { "epoch": 0.4053738317757009, "grad_norm": 1.4698222875595093, "learning_rate": 1.3478603069316057e-05, "loss": 1.0609, "step": 6940 }, { "epoch": 0.4054322429906542, "grad_norm": 1.7462444305419922, "learning_rate": 1.3476829317562009e-05, "loss": 0.9585, "step": 6941 }, { "epoch": 0.4054906542056075, "grad_norm": 0.8435330390930176, "learning_rate": 1.347505544136995e-05, "loss": 0.6104, "step": 6942 }, { "epoch": 0.40554906542056074, "grad_norm": 1.217717170715332, "learning_rate": 1.3473281440803374e-05, "loss": 1.0289, "step": 6943 }, { "epoch": 0.405607476635514, "grad_norm": 1.3794347047805786, "learning_rate": 1.347150731592577e-05, "loss": 0.8796, "step": 6944 }, { "epoch": 0.4056658878504673, "grad_norm": 1.2341727018356323, "learning_rate": 1.346973306680064e-05, "loss": 0.826, "step": 6945 }, { "epoch": 0.40572429906542057, "grad_norm": 1.5386921167373657, "learning_rate": 1.3467958693491479e-05, "loss": 0.7606, "step": 6946 }, { "epoch": 0.4057827102803738, "grad_norm": 2.5199506282806396, "learning_rate": 1.3466184196061796e-05, "loss": 0.8785, "step": 6947 }, { "epoch": 0.4058411214953271, "grad_norm": 1.209825873374939, "learning_rate": 1.3464409574575104e-05, "loss": 0.7845, "step": 6948 }, { "epoch": 0.4058995327102804, "grad_norm": 1.4654728174209595, "learning_rate": 1.3462634829094914e-05, "loss": 0.826, "step": 6949 }, { "epoch": 0.40595794392523366, "grad_norm": 1.575481653213501, "learning_rate": 1.3460859959684744e-05, "loss": 0.9101, "step": 6950 }, { "epoch": 0.4060163551401869, "grad_norm": 1.282598614692688, "learning_rate": 1.3459084966408125e-05, "loss": 0.8297, "step": 6951 }, { "epoch": 0.40607476635514017, "grad_norm": 1.4009710550308228, "learning_rate": 1.345730984932858e-05, "loss": 0.8642, "step": 6952 }, { "epoch": 0.4061331775700935, "grad_norm": 1.2758382558822632, "learning_rate": 1.3455534608509641e-05, "loss": 0.8008, "step": 6953 }, { "epoch": 0.40619158878504674, "grad_norm": 1.1124955415725708, "learning_rate": 1.3453759244014845e-05, "loss": 0.7588, "step": 6954 }, { "epoch": 0.40625, "grad_norm": 1.2811285257339478, "learning_rate": 1.3451983755907736e-05, "loss": 0.7869, "step": 6955 }, { "epoch": 0.40630841121495326, "grad_norm": 1.375985860824585, "learning_rate": 1.3450208144251861e-05, "loss": 0.7101, "step": 6956 }, { "epoch": 0.4063668224299065, "grad_norm": 1.1599897146224976, "learning_rate": 1.3448432409110768e-05, "loss": 0.7755, "step": 6957 }, { "epoch": 0.40642523364485983, "grad_norm": 2.234687328338623, "learning_rate": 1.3446656550548008e-05, "loss": 0.8331, "step": 6958 }, { "epoch": 0.4064836448598131, "grad_norm": 1.2096489667892456, "learning_rate": 1.3444880568627144e-05, "loss": 0.8785, "step": 6959 }, { "epoch": 0.40654205607476634, "grad_norm": 1.2155590057373047, "learning_rate": 1.3443104463411742e-05, "loss": 0.7415, "step": 6960 }, { "epoch": 0.4066004672897196, "grad_norm": 1.484121322631836, "learning_rate": 1.3441328234965365e-05, "loss": 0.7864, "step": 6961 }, { "epoch": 0.4066588785046729, "grad_norm": 1.3203308582305908, "learning_rate": 1.3439551883351589e-05, "loss": 0.7952, "step": 6962 }, { "epoch": 0.4067172897196262, "grad_norm": 1.1818861961364746, "learning_rate": 1.3437775408633988e-05, "loss": 0.8137, "step": 6963 }, { "epoch": 0.40677570093457943, "grad_norm": 1.0718308687210083, "learning_rate": 1.3435998810876147e-05, "loss": 0.9724, "step": 6964 }, { "epoch": 0.4068341121495327, "grad_norm": 1.3575928211212158, "learning_rate": 1.343422209014165e-05, "loss": 0.9822, "step": 6965 }, { "epoch": 0.406892523364486, "grad_norm": 1.3009949922561646, "learning_rate": 1.3432445246494086e-05, "loss": 0.8945, "step": 6966 }, { "epoch": 0.40695093457943926, "grad_norm": 1.4750561714172363, "learning_rate": 1.3430668279997048e-05, "loss": 0.8683, "step": 6967 }, { "epoch": 0.4070093457943925, "grad_norm": 1.2161277532577515, "learning_rate": 1.3428891190714137e-05, "loss": 0.6561, "step": 6968 }, { "epoch": 0.4070677570093458, "grad_norm": 1.0492058992385864, "learning_rate": 1.3427113978708955e-05, "loss": 0.9243, "step": 6969 }, { "epoch": 0.4071261682242991, "grad_norm": 0.9703459739685059, "learning_rate": 1.342533664404511e-05, "loss": 0.6242, "step": 6970 }, { "epoch": 0.40718457943925235, "grad_norm": 1.118920922279358, "learning_rate": 1.3423559186786217e-05, "loss": 0.8452, "step": 6971 }, { "epoch": 0.4072429906542056, "grad_norm": 1.5200327634811401, "learning_rate": 1.342178160699589e-05, "loss": 0.6956, "step": 6972 }, { "epoch": 0.40730140186915886, "grad_norm": 1.372090220451355, "learning_rate": 1.3420003904737748e-05, "loss": 1.0239, "step": 6973 }, { "epoch": 0.4073598130841122, "grad_norm": 1.0229748487472534, "learning_rate": 1.3418226080075416e-05, "loss": 0.7354, "step": 6974 }, { "epoch": 0.40741822429906543, "grad_norm": 1.8867957592010498, "learning_rate": 1.3416448133072525e-05, "loss": 0.7541, "step": 6975 }, { "epoch": 0.4074766355140187, "grad_norm": 1.6046725511550903, "learning_rate": 1.3414670063792711e-05, "loss": 1.0091, "step": 6976 }, { "epoch": 0.40753504672897195, "grad_norm": 1.5582317113876343, "learning_rate": 1.341289187229961e-05, "loss": 0.6957, "step": 6977 }, { "epoch": 0.4075934579439252, "grad_norm": 1.8861489295959473, "learning_rate": 1.3411113558656865e-05, "loss": 1.0721, "step": 6978 }, { "epoch": 0.4076518691588785, "grad_norm": 2.635643482208252, "learning_rate": 1.3409335122928123e-05, "loss": 0.8675, "step": 6979 }, { "epoch": 0.4077102803738318, "grad_norm": 2.1066653728485107, "learning_rate": 1.3407556565177032e-05, "loss": 0.9259, "step": 6980 }, { "epoch": 0.40776869158878504, "grad_norm": 1.595299482345581, "learning_rate": 1.3405777885467255e-05, "loss": 0.8643, "step": 6981 }, { "epoch": 0.4078271028037383, "grad_norm": 2.6347339153289795, "learning_rate": 1.3403999083862446e-05, "loss": 0.8157, "step": 6982 }, { "epoch": 0.4078855140186916, "grad_norm": 1.1641743183135986, "learning_rate": 1.3402220160426272e-05, "loss": 0.8715, "step": 6983 }, { "epoch": 0.40794392523364487, "grad_norm": 1.7129268646240234, "learning_rate": 1.3400441115222402e-05, "loss": 0.8252, "step": 6984 }, { "epoch": 0.4080023364485981, "grad_norm": 1.476583480834961, "learning_rate": 1.3398661948314509e-05, "loss": 0.7271, "step": 6985 }, { "epoch": 0.4080607476635514, "grad_norm": 1.4341875314712524, "learning_rate": 1.3396882659766271e-05, "loss": 0.8047, "step": 6986 }, { "epoch": 0.4081191588785047, "grad_norm": 2.6956939697265625, "learning_rate": 1.3395103249641368e-05, "loss": 0.9413, "step": 6987 }, { "epoch": 0.40817757009345795, "grad_norm": 1.741500735282898, "learning_rate": 1.3393323718003486e-05, "loss": 0.8083, "step": 6988 }, { "epoch": 0.4082359813084112, "grad_norm": 1.269441843032837, "learning_rate": 1.3391544064916318e-05, "loss": 0.9332, "step": 6989 }, { "epoch": 0.40829439252336447, "grad_norm": 1.8384506702423096, "learning_rate": 1.3389764290443559e-05, "loss": 0.8547, "step": 6990 }, { "epoch": 0.4083528037383178, "grad_norm": 1.6573220491409302, "learning_rate": 1.3387984394648905e-05, "loss": 0.7723, "step": 6991 }, { "epoch": 0.40841121495327104, "grad_norm": 1.2989497184753418, "learning_rate": 1.3386204377596063e-05, "loss": 0.8092, "step": 6992 }, { "epoch": 0.4084696261682243, "grad_norm": 1.3372114896774292, "learning_rate": 1.3384424239348742e-05, "loss": 0.6581, "step": 6993 }, { "epoch": 0.40852803738317756, "grad_norm": 1.6396137475967407, "learning_rate": 1.3382643979970649e-05, "loss": 0.8315, "step": 6994 }, { "epoch": 0.4085864485981308, "grad_norm": 1.3515692949295044, "learning_rate": 1.3380863599525507e-05, "loss": 0.7178, "step": 6995 }, { "epoch": 0.4086448598130841, "grad_norm": 1.789974570274353, "learning_rate": 1.3379083098077027e-05, "loss": 0.8114, "step": 6996 }, { "epoch": 0.4087032710280374, "grad_norm": 1.538679599761963, "learning_rate": 1.337730247568895e-05, "loss": 0.9161, "step": 6997 }, { "epoch": 0.40876168224299064, "grad_norm": 1.464099407196045, "learning_rate": 1.3375521732424992e-05, "loss": 0.6977, "step": 6998 }, { "epoch": 0.4088200934579439, "grad_norm": 2.261906147003174, "learning_rate": 1.3373740868348892e-05, "loss": 0.8132, "step": 6999 }, { "epoch": 0.4088785046728972, "grad_norm": 1.2379450798034668, "learning_rate": 1.337195988352439e-05, "loss": 0.775, "step": 7000 }, { "epoch": 0.40893691588785047, "grad_norm": 2.7044830322265625, "learning_rate": 1.3370178778015223e-05, "loss": 0.8089, "step": 7001 }, { "epoch": 0.40899532710280373, "grad_norm": 0.987372100353241, "learning_rate": 1.3368397551885144e-05, "loss": 0.7145, "step": 7002 }, { "epoch": 0.409053738317757, "grad_norm": 1.8784306049346924, "learning_rate": 1.3366616205197903e-05, "loss": 0.9608, "step": 7003 }, { "epoch": 0.4091121495327103, "grad_norm": 1.0591256618499756, "learning_rate": 1.3364834738017251e-05, "loss": 0.8137, "step": 7004 }, { "epoch": 0.40917056074766356, "grad_norm": 1.4293195009231567, "learning_rate": 1.3363053150406955e-05, "loss": 0.786, "step": 7005 }, { "epoch": 0.4092289719626168, "grad_norm": 1.0468159914016724, "learning_rate": 1.3361271442430775e-05, "loss": 0.828, "step": 7006 }, { "epoch": 0.4092873831775701, "grad_norm": 5.885508060455322, "learning_rate": 1.3359489614152476e-05, "loss": 1.0877, "step": 7007 }, { "epoch": 0.4093457943925234, "grad_norm": 1.6419466733932495, "learning_rate": 1.3357707665635837e-05, "loss": 1.0611, "step": 7008 }, { "epoch": 0.40940420560747665, "grad_norm": 1.7165244817733765, "learning_rate": 1.3355925596944634e-05, "loss": 0.7674, "step": 7009 }, { "epoch": 0.4094626168224299, "grad_norm": 1.1866276264190674, "learning_rate": 1.3354143408142648e-05, "loss": 0.7159, "step": 7010 }, { "epoch": 0.40952102803738316, "grad_norm": 1.4357860088348389, "learning_rate": 1.3352361099293662e-05, "loss": 1.0108, "step": 7011 }, { "epoch": 0.4095794392523365, "grad_norm": 1.9725223779678345, "learning_rate": 1.3350578670461469e-05, "loss": 0.8706, "step": 7012 }, { "epoch": 0.40963785046728973, "grad_norm": 1.655189871788025, "learning_rate": 1.3348796121709862e-05, "loss": 0.8062, "step": 7013 }, { "epoch": 0.409696261682243, "grad_norm": 2.002819538116455, "learning_rate": 1.3347013453102642e-05, "loss": 0.7525, "step": 7014 }, { "epoch": 0.40975467289719625, "grad_norm": 3.697563648223877, "learning_rate": 1.3345230664703607e-05, "loss": 0.9662, "step": 7015 }, { "epoch": 0.4098130841121495, "grad_norm": 1.4131548404693604, "learning_rate": 1.3343447756576568e-05, "loss": 0.7448, "step": 7016 }, { "epoch": 0.4098714953271028, "grad_norm": 2.0425148010253906, "learning_rate": 1.3341664728785335e-05, "loss": 1.0284, "step": 7017 }, { "epoch": 0.4099299065420561, "grad_norm": 2.680234432220459, "learning_rate": 1.3339881581393725e-05, "loss": 0.7771, "step": 7018 }, { "epoch": 0.40998831775700934, "grad_norm": 2.0522942543029785, "learning_rate": 1.3338098314465557e-05, "loss": 0.9458, "step": 7019 }, { "epoch": 0.4100467289719626, "grad_norm": 3.2122082710266113, "learning_rate": 1.3336314928064655e-05, "loss": 0.9447, "step": 7020 }, { "epoch": 0.4101051401869159, "grad_norm": 1.113216757774353, "learning_rate": 1.3334531422254847e-05, "loss": 0.8398, "step": 7021 }, { "epoch": 0.41016355140186916, "grad_norm": 1.947019338607788, "learning_rate": 1.333274779709997e-05, "loss": 0.6814, "step": 7022 }, { "epoch": 0.4102219626168224, "grad_norm": 1.73639714717865, "learning_rate": 1.3330964052663857e-05, "loss": 0.8599, "step": 7023 }, { "epoch": 0.4102803738317757, "grad_norm": 1.7111468315124512, "learning_rate": 1.3329180189010348e-05, "loss": 0.7516, "step": 7024 }, { "epoch": 0.410338785046729, "grad_norm": 1.988183617591858, "learning_rate": 1.3327396206203294e-05, "loss": 0.8516, "step": 7025 }, { "epoch": 0.41039719626168225, "grad_norm": 1.8723390102386475, "learning_rate": 1.332561210430654e-05, "loss": 0.8873, "step": 7026 }, { "epoch": 0.4104556074766355, "grad_norm": 1.5464928150177002, "learning_rate": 1.3323827883383942e-05, "loss": 0.8625, "step": 7027 }, { "epoch": 0.41051401869158877, "grad_norm": 1.39186692237854, "learning_rate": 1.3322043543499361e-05, "loss": 0.766, "step": 7028 }, { "epoch": 0.4105724299065421, "grad_norm": 2.024078845977783, "learning_rate": 1.3320259084716654e-05, "loss": 0.8909, "step": 7029 }, { "epoch": 0.41063084112149534, "grad_norm": 1.6263238191604614, "learning_rate": 1.3318474507099695e-05, "loss": 0.96, "step": 7030 }, { "epoch": 0.4106892523364486, "grad_norm": 1.5967196226119995, "learning_rate": 1.331668981071235e-05, "loss": 0.967, "step": 7031 }, { "epoch": 0.41074766355140185, "grad_norm": 1.3757356405258179, "learning_rate": 1.3314904995618494e-05, "loss": 0.7144, "step": 7032 }, { "epoch": 0.41080607476635517, "grad_norm": 2.0007729530334473, "learning_rate": 1.3313120061882007e-05, "loss": 0.736, "step": 7033 }, { "epoch": 0.4108644859813084, "grad_norm": 1.9029581546783447, "learning_rate": 1.3311335009566781e-05, "loss": 0.8398, "step": 7034 }, { "epoch": 0.4109228971962617, "grad_norm": 1.7369178533554077, "learning_rate": 1.3309549838736692e-05, "loss": 0.8436, "step": 7035 }, { "epoch": 0.41098130841121494, "grad_norm": 1.817375898361206, "learning_rate": 1.3307764549455641e-05, "loss": 0.8941, "step": 7036 }, { "epoch": 0.4110397196261682, "grad_norm": 1.1163309812545776, "learning_rate": 1.3305979141787524e-05, "loss": 0.87, "step": 7037 }, { "epoch": 0.4110981308411215, "grad_norm": 1.8068405389785767, "learning_rate": 1.3304193615796232e-05, "loss": 0.9367, "step": 7038 }, { "epoch": 0.41115654205607477, "grad_norm": 1.4216768741607666, "learning_rate": 1.3302407971545688e-05, "loss": 0.9562, "step": 7039 }, { "epoch": 0.411214953271028, "grad_norm": 0.9644507169723511, "learning_rate": 1.3300622209099788e-05, "loss": 0.6857, "step": 7040 }, { "epoch": 0.4112733644859813, "grad_norm": 1.549504041671753, "learning_rate": 1.3298836328522444e-05, "loss": 0.8877, "step": 7041 }, { "epoch": 0.4113317757009346, "grad_norm": 0.9154462814331055, "learning_rate": 1.3297050329877581e-05, "loss": 0.8398, "step": 7042 }, { "epoch": 0.41139018691588786, "grad_norm": 1.066239595413208, "learning_rate": 1.3295264213229123e-05, "loss": 0.7589, "step": 7043 }, { "epoch": 0.4114485981308411, "grad_norm": 0.9066060781478882, "learning_rate": 1.3293477978640987e-05, "loss": 0.6346, "step": 7044 }, { "epoch": 0.4115070093457944, "grad_norm": 1.5822393894195557, "learning_rate": 1.3291691626177113e-05, "loss": 0.8956, "step": 7045 }, { "epoch": 0.4115654205607477, "grad_norm": 1.3359397649765015, "learning_rate": 1.3289905155901427e-05, "loss": 0.7032, "step": 7046 }, { "epoch": 0.41162383177570094, "grad_norm": 1.458519697189331, "learning_rate": 1.3288118567877874e-05, "loss": 0.7546, "step": 7047 }, { "epoch": 0.4116822429906542, "grad_norm": 1.1638152599334717, "learning_rate": 1.3286331862170398e-05, "loss": 0.7912, "step": 7048 }, { "epoch": 0.41174065420560746, "grad_norm": 1.9350500106811523, "learning_rate": 1.328454503884294e-05, "loss": 0.8155, "step": 7049 }, { "epoch": 0.4117990654205608, "grad_norm": 1.7516855001449585, "learning_rate": 1.3282758097959458e-05, "loss": 0.9669, "step": 7050 }, { "epoch": 0.41185747663551403, "grad_norm": 1.134613037109375, "learning_rate": 1.3280971039583906e-05, "loss": 0.7897, "step": 7051 }, { "epoch": 0.4119158878504673, "grad_norm": 1.474884271621704, "learning_rate": 1.3279183863780239e-05, "loss": 0.9324, "step": 7052 }, { "epoch": 0.41197429906542055, "grad_norm": 1.1466063261032104, "learning_rate": 1.327739657061243e-05, "loss": 0.7393, "step": 7053 }, { "epoch": 0.41203271028037386, "grad_norm": 1.468216896057129, "learning_rate": 1.3275609160144438e-05, "loss": 1.0214, "step": 7054 }, { "epoch": 0.4120911214953271, "grad_norm": 1.1333125829696655, "learning_rate": 1.3273821632440244e-05, "loss": 0.6961, "step": 7055 }, { "epoch": 0.4121495327102804, "grad_norm": 1.8806777000427246, "learning_rate": 1.3272033987563822e-05, "loss": 0.9857, "step": 7056 }, { "epoch": 0.41220794392523363, "grad_norm": 1.2207274436950684, "learning_rate": 1.327024622557915e-05, "loss": 0.8174, "step": 7057 }, { "epoch": 0.4122663551401869, "grad_norm": 1.1331173181533813, "learning_rate": 1.3268458346550217e-05, "loss": 0.707, "step": 7058 }, { "epoch": 0.4123247663551402, "grad_norm": 1.4061203002929688, "learning_rate": 1.3266670350541008e-05, "loss": 1.0139, "step": 7059 }, { "epoch": 0.41238317757009346, "grad_norm": 1.161898136138916, "learning_rate": 1.326488223761552e-05, "loss": 0.7459, "step": 7060 }, { "epoch": 0.4124415887850467, "grad_norm": 1.1582205295562744, "learning_rate": 1.3263094007837752e-05, "loss": 0.7558, "step": 7061 }, { "epoch": 0.4125, "grad_norm": 0.8845446109771729, "learning_rate": 1.3261305661271702e-05, "loss": 0.7108, "step": 7062 }, { "epoch": 0.4125584112149533, "grad_norm": 1.275368094444275, "learning_rate": 1.325951719798138e-05, "loss": 0.818, "step": 7063 }, { "epoch": 0.41261682242990655, "grad_norm": 1.124741792678833, "learning_rate": 1.3257728618030793e-05, "loss": 0.6554, "step": 7064 }, { "epoch": 0.4126752336448598, "grad_norm": 1.011977195739746, "learning_rate": 1.3255939921483958e-05, "loss": 0.9145, "step": 7065 }, { "epoch": 0.41273364485981306, "grad_norm": 1.2276805639266968, "learning_rate": 1.325415110840489e-05, "loss": 0.7247, "step": 7066 }, { "epoch": 0.4127920560747664, "grad_norm": 1.1076816320419312, "learning_rate": 1.3252362178857617e-05, "loss": 0.7356, "step": 7067 }, { "epoch": 0.41285046728971964, "grad_norm": 1.4785494804382324, "learning_rate": 1.3250573132906159e-05, "loss": 0.6986, "step": 7068 }, { "epoch": 0.4129088785046729, "grad_norm": 0.9061902761459351, "learning_rate": 1.3248783970614556e-05, "loss": 0.7129, "step": 7069 }, { "epoch": 0.41296728971962615, "grad_norm": 1.870420217514038, "learning_rate": 1.3246994692046837e-05, "loss": 0.8809, "step": 7070 }, { "epoch": 0.41302570093457946, "grad_norm": 1.1567094326019287, "learning_rate": 1.3245205297267041e-05, "loss": 0.8408, "step": 7071 }, { "epoch": 0.4130841121495327, "grad_norm": 1.9473644495010376, "learning_rate": 1.3243415786339218e-05, "loss": 0.8526, "step": 7072 }, { "epoch": 0.413142523364486, "grad_norm": 1.1711344718933105, "learning_rate": 1.3241626159327407e-05, "loss": 0.7908, "step": 7073 }, { "epoch": 0.41320093457943924, "grad_norm": 1.394141435623169, "learning_rate": 1.3239836416295667e-05, "loss": 0.7901, "step": 7074 }, { "epoch": 0.4132593457943925, "grad_norm": 1.6443641185760498, "learning_rate": 1.3238046557308048e-05, "loss": 0.8965, "step": 7075 }, { "epoch": 0.4133177570093458, "grad_norm": 1.3528401851654053, "learning_rate": 1.3236256582428617e-05, "loss": 0.6719, "step": 7076 }, { "epoch": 0.41337616822429907, "grad_norm": 1.4931432008743286, "learning_rate": 1.3234466491721436e-05, "loss": 0.8068, "step": 7077 }, { "epoch": 0.4134345794392523, "grad_norm": 2.1452722549438477, "learning_rate": 1.323267628525057e-05, "loss": 0.7224, "step": 7078 }, { "epoch": 0.4134929906542056, "grad_norm": 1.873668909072876, "learning_rate": 1.3230885963080093e-05, "loss": 0.8072, "step": 7079 }, { "epoch": 0.4135514018691589, "grad_norm": 1.5657025575637817, "learning_rate": 1.3229095525274085e-05, "loss": 0.7301, "step": 7080 }, { "epoch": 0.41360981308411215, "grad_norm": 1.4852427244186401, "learning_rate": 1.3227304971896626e-05, "loss": 1.04, "step": 7081 }, { "epoch": 0.4136682242990654, "grad_norm": 1.225490689277649, "learning_rate": 1.3225514303011799e-05, "loss": 0.7357, "step": 7082 }, { "epoch": 0.41372663551401867, "grad_norm": 2.2041900157928467, "learning_rate": 1.3223723518683695e-05, "loss": 0.8378, "step": 7083 }, { "epoch": 0.413785046728972, "grad_norm": 1.0620427131652832, "learning_rate": 1.3221932618976404e-05, "loss": 0.7374, "step": 7084 }, { "epoch": 0.41384345794392524, "grad_norm": 1.791324257850647, "learning_rate": 1.3220141603954029e-05, "loss": 0.7228, "step": 7085 }, { "epoch": 0.4139018691588785, "grad_norm": 1.1475719213485718, "learning_rate": 1.3218350473680669e-05, "loss": 0.8886, "step": 7086 }, { "epoch": 0.41396028037383176, "grad_norm": 0.9516966342926025, "learning_rate": 1.3216559228220426e-05, "loss": 0.7299, "step": 7087 }, { "epoch": 0.41401869158878507, "grad_norm": 1.2792842388153076, "learning_rate": 1.3214767867637417e-05, "loss": 0.78, "step": 7088 }, { "epoch": 0.41407710280373833, "grad_norm": 1.5985926389694214, "learning_rate": 1.3212976391995752e-05, "loss": 0.8834, "step": 7089 }, { "epoch": 0.4141355140186916, "grad_norm": 1.1499536037445068, "learning_rate": 1.3211184801359544e-05, "loss": 0.7557, "step": 7090 }, { "epoch": 0.41419392523364484, "grad_norm": 1.9097706079483032, "learning_rate": 1.3209393095792926e-05, "loss": 0.732, "step": 7091 }, { "epoch": 0.41425233644859816, "grad_norm": 1.3495712280273438, "learning_rate": 1.320760127536002e-05, "loss": 0.7829, "step": 7092 }, { "epoch": 0.4143107476635514, "grad_norm": 1.7976027727127075, "learning_rate": 1.3205809340124951e-05, "loss": 0.8138, "step": 7093 }, { "epoch": 0.4143691588785047, "grad_norm": 1.5162429809570312, "learning_rate": 1.320401729015186e-05, "loss": 0.8413, "step": 7094 }, { "epoch": 0.41442757009345793, "grad_norm": 1.3618547916412354, "learning_rate": 1.3202225125504884e-05, "loss": 0.8492, "step": 7095 }, { "epoch": 0.4144859813084112, "grad_norm": 1.8391022682189941, "learning_rate": 1.3200432846248163e-05, "loss": 0.8362, "step": 7096 }, { "epoch": 0.4145443925233645, "grad_norm": 1.6467559337615967, "learning_rate": 1.319864045244585e-05, "loss": 0.9186, "step": 7097 }, { "epoch": 0.41460280373831776, "grad_norm": 1.0824869871139526, "learning_rate": 1.319684794416209e-05, "loss": 0.7379, "step": 7098 }, { "epoch": 0.414661214953271, "grad_norm": 2.251190662384033, "learning_rate": 1.3195055321461037e-05, "loss": 0.9601, "step": 7099 }, { "epoch": 0.4147196261682243, "grad_norm": 1.159938097000122, "learning_rate": 1.3193262584406856e-05, "loss": 0.6665, "step": 7100 }, { "epoch": 0.4147780373831776, "grad_norm": 1.9296165704727173, "learning_rate": 1.3191469733063708e-05, "loss": 0.772, "step": 7101 }, { "epoch": 0.41483644859813085, "grad_norm": 2.0046162605285645, "learning_rate": 1.318967676749576e-05, "loss": 0.8423, "step": 7102 }, { "epoch": 0.4148948598130841, "grad_norm": 1.526634693145752, "learning_rate": 1.3187883687767182e-05, "loss": 0.7322, "step": 7103 }, { "epoch": 0.41495327102803736, "grad_norm": 2.6886727809906006, "learning_rate": 1.318609049394215e-05, "loss": 0.8824, "step": 7104 }, { "epoch": 0.4150116822429907, "grad_norm": 1.3946510553359985, "learning_rate": 1.3184297186084846e-05, "loss": 0.9392, "step": 7105 }, { "epoch": 0.41507009345794393, "grad_norm": 2.0025129318237305, "learning_rate": 1.3182503764259456e-05, "loss": 0.8881, "step": 7106 }, { "epoch": 0.4151285046728972, "grad_norm": 1.731435775756836, "learning_rate": 1.3180710228530156e-05, "loss": 0.7705, "step": 7107 }, { "epoch": 0.41518691588785045, "grad_norm": 1.248745083808899, "learning_rate": 1.317891657896115e-05, "loss": 0.7332, "step": 7108 }, { "epoch": 0.41524532710280376, "grad_norm": 2.2188992500305176, "learning_rate": 1.3177122815616627e-05, "loss": 0.8634, "step": 7109 }, { "epoch": 0.415303738317757, "grad_norm": 1.5628477334976196, "learning_rate": 1.317532893856079e-05, "loss": 0.7705, "step": 7110 }, { "epoch": 0.4153621495327103, "grad_norm": 1.548299789428711, "learning_rate": 1.3173534947857847e-05, "loss": 0.7332, "step": 7111 }, { "epoch": 0.41542056074766354, "grad_norm": 1.5710937976837158, "learning_rate": 1.3171740843571993e-05, "loss": 0.7698, "step": 7112 }, { "epoch": 0.41547897196261685, "grad_norm": 1.2997559309005737, "learning_rate": 1.3169946625767455e-05, "loss": 0.7561, "step": 7113 }, { "epoch": 0.4155373831775701, "grad_norm": 2.1065826416015625, "learning_rate": 1.3168152294508442e-05, "loss": 0.858, "step": 7114 }, { "epoch": 0.41559579439252337, "grad_norm": 1.3279939889907837, "learning_rate": 1.3166357849859175e-05, "loss": 0.6691, "step": 7115 }, { "epoch": 0.4156542056074766, "grad_norm": 1.2637863159179688, "learning_rate": 1.3164563291883879e-05, "loss": 0.8575, "step": 7116 }, { "epoch": 0.4157126168224299, "grad_norm": 1.5435734987258911, "learning_rate": 1.3162768620646781e-05, "loss": 0.7732, "step": 7117 }, { "epoch": 0.4157710280373832, "grad_norm": 1.3435062170028687, "learning_rate": 1.3160973836212114e-05, "loss": 0.9764, "step": 7118 }, { "epoch": 0.41582943925233645, "grad_norm": 1.5632411241531372, "learning_rate": 1.3159178938644117e-05, "loss": 0.8109, "step": 7119 }, { "epoch": 0.4158878504672897, "grad_norm": 1.3480390310287476, "learning_rate": 1.3157383928007028e-05, "loss": 0.8268, "step": 7120 }, { "epoch": 0.41594626168224297, "grad_norm": 0.8592516183853149, "learning_rate": 1.3155588804365091e-05, "loss": 0.6334, "step": 7121 }, { "epoch": 0.4160046728971963, "grad_norm": 1.1525485515594482, "learning_rate": 1.3153793567782558e-05, "loss": 0.8342, "step": 7122 }, { "epoch": 0.41606308411214954, "grad_norm": 1.5924428701400757, "learning_rate": 1.3151998218323676e-05, "loss": 0.9217, "step": 7123 }, { "epoch": 0.4161214953271028, "grad_norm": 1.1556977033615112, "learning_rate": 1.3150202756052708e-05, "loss": 0.8471, "step": 7124 }, { "epoch": 0.41617990654205606, "grad_norm": 0.9675741791725159, "learning_rate": 1.3148407181033913e-05, "loss": 0.7742, "step": 7125 }, { "epoch": 0.41623831775700937, "grad_norm": 2.040125608444214, "learning_rate": 1.3146611493331554e-05, "loss": 0.8505, "step": 7126 }, { "epoch": 0.4162967289719626, "grad_norm": 0.9990410208702087, "learning_rate": 1.31448156930099e-05, "loss": 0.6187, "step": 7127 }, { "epoch": 0.4163551401869159, "grad_norm": 2.3286240100860596, "learning_rate": 1.3143019780133224e-05, "loss": 0.846, "step": 7128 }, { "epoch": 0.41641355140186914, "grad_norm": 1.3190302848815918, "learning_rate": 1.3141223754765804e-05, "loss": 1.0407, "step": 7129 }, { "epoch": 0.41647196261682246, "grad_norm": 2.336350202560425, "learning_rate": 1.3139427616971923e-05, "loss": 0.8028, "step": 7130 }, { "epoch": 0.4165303738317757, "grad_norm": 2.552474021911621, "learning_rate": 1.3137631366815862e-05, "loss": 0.8522, "step": 7131 }, { "epoch": 0.41658878504672897, "grad_norm": 2.3699116706848145, "learning_rate": 1.3135835004361908e-05, "loss": 0.9075, "step": 7132 }, { "epoch": 0.41664719626168223, "grad_norm": 1.3800592422485352, "learning_rate": 1.313403852967436e-05, "loss": 0.815, "step": 7133 }, { "epoch": 0.4167056074766355, "grad_norm": 1.670546054840088, "learning_rate": 1.3132241942817511e-05, "loss": 0.8794, "step": 7134 }, { "epoch": 0.4167640186915888, "grad_norm": 1.4078755378723145, "learning_rate": 1.3130445243855665e-05, "loss": 0.7142, "step": 7135 }, { "epoch": 0.41682242990654206, "grad_norm": 1.8648232221603394, "learning_rate": 1.3128648432853126e-05, "loss": 0.852, "step": 7136 }, { "epoch": 0.4168808411214953, "grad_norm": 1.3988336324691772, "learning_rate": 1.31268515098742e-05, "loss": 0.8627, "step": 7137 }, { "epoch": 0.4169392523364486, "grad_norm": 2.24851131439209, "learning_rate": 1.3125054474983203e-05, "loss": 0.7652, "step": 7138 }, { "epoch": 0.4169976635514019, "grad_norm": 1.0543185472488403, "learning_rate": 1.3123257328244455e-05, "loss": 0.754, "step": 7139 }, { "epoch": 0.41705607476635514, "grad_norm": 1.7489434480667114, "learning_rate": 1.3121460069722269e-05, "loss": 0.7186, "step": 7140 }, { "epoch": 0.4171144859813084, "grad_norm": 1.1871641874313354, "learning_rate": 1.3119662699480977e-05, "loss": 0.6266, "step": 7141 }, { "epoch": 0.41717289719626166, "grad_norm": 1.2864326238632202, "learning_rate": 1.3117865217584906e-05, "loss": 0.8341, "step": 7142 }, { "epoch": 0.417231308411215, "grad_norm": 1.753240704536438, "learning_rate": 1.3116067624098388e-05, "loss": 0.9676, "step": 7143 }, { "epoch": 0.41728971962616823, "grad_norm": 2.306734085083008, "learning_rate": 1.3114269919085762e-05, "loss": 0.805, "step": 7144 }, { "epoch": 0.4173481308411215, "grad_norm": 1.9506229162216187, "learning_rate": 1.3112472102611367e-05, "loss": 0.7936, "step": 7145 }, { "epoch": 0.41740654205607475, "grad_norm": 1.4058157205581665, "learning_rate": 1.311067417473955e-05, "loss": 0.7715, "step": 7146 }, { "epoch": 0.41746495327102806, "grad_norm": 0.9834449887275696, "learning_rate": 1.3108876135534659e-05, "loss": 0.8937, "step": 7147 }, { "epoch": 0.4175233644859813, "grad_norm": 1.216390609741211, "learning_rate": 1.3107077985061043e-05, "loss": 0.7553, "step": 7148 }, { "epoch": 0.4175817757009346, "grad_norm": 1.083244800567627, "learning_rate": 1.3105279723383066e-05, "loss": 0.7605, "step": 7149 }, { "epoch": 0.41764018691588783, "grad_norm": 1.4250249862670898, "learning_rate": 1.310348135056509e-05, "loss": 0.8522, "step": 7150 }, { "epoch": 0.41769859813084115, "grad_norm": 1.2004905939102173, "learning_rate": 1.310168286667147e-05, "loss": 0.7656, "step": 7151 }, { "epoch": 0.4177570093457944, "grad_norm": 1.1909253597259521, "learning_rate": 1.3099884271766583e-05, "loss": 0.7561, "step": 7152 }, { "epoch": 0.41781542056074766, "grad_norm": 1.3647925853729248, "learning_rate": 1.3098085565914799e-05, "loss": 0.8695, "step": 7153 }, { "epoch": 0.4178738317757009, "grad_norm": 2.077477216720581, "learning_rate": 1.3096286749180493e-05, "loss": 0.8636, "step": 7154 }, { "epoch": 0.4179322429906542, "grad_norm": 1.3916902542114258, "learning_rate": 1.3094487821628055e-05, "loss": 0.7141, "step": 7155 }, { "epoch": 0.4179906542056075, "grad_norm": 2.8254640102386475, "learning_rate": 1.3092688783321858e-05, "loss": 0.899, "step": 7156 }, { "epoch": 0.41804906542056075, "grad_norm": 1.1150336265563965, "learning_rate": 1.3090889634326298e-05, "loss": 0.852, "step": 7157 }, { "epoch": 0.418107476635514, "grad_norm": 1.9337234497070312, "learning_rate": 1.3089090374705764e-05, "loss": 0.8202, "step": 7158 }, { "epoch": 0.41816588785046727, "grad_norm": 3.319319248199463, "learning_rate": 1.3087291004524656e-05, "loss": 1.0565, "step": 7159 }, { "epoch": 0.4182242990654206, "grad_norm": 1.2912821769714355, "learning_rate": 1.3085491523847373e-05, "loss": 0.7111, "step": 7160 }, { "epoch": 0.41828271028037384, "grad_norm": 3.626185417175293, "learning_rate": 1.3083691932738321e-05, "loss": 0.8832, "step": 7161 }, { "epoch": 0.4183411214953271, "grad_norm": 1.5755815505981445, "learning_rate": 1.3081892231261903e-05, "loss": 0.8466, "step": 7162 }, { "epoch": 0.41839953271028035, "grad_norm": 2.6077826023101807, "learning_rate": 1.308009241948254e-05, "loss": 0.8043, "step": 7163 }, { "epoch": 0.41845794392523367, "grad_norm": 3.156802177429199, "learning_rate": 1.3078292497464643e-05, "loss": 0.9602, "step": 7164 }, { "epoch": 0.4185163551401869, "grad_norm": 1.3737820386886597, "learning_rate": 1.3076492465272632e-05, "loss": 0.8715, "step": 7165 }, { "epoch": 0.4185747663551402, "grad_norm": 1.7637876272201538, "learning_rate": 1.3074692322970934e-05, "loss": 0.8818, "step": 7166 }, { "epoch": 0.41863317757009344, "grad_norm": 2.0736446380615234, "learning_rate": 1.3072892070623975e-05, "loss": 0.8133, "step": 7167 }, { "epoch": 0.41869158878504675, "grad_norm": 1.1296782493591309, "learning_rate": 1.3071091708296187e-05, "loss": 0.8, "step": 7168 }, { "epoch": 0.41875, "grad_norm": 1.5923916101455688, "learning_rate": 1.3069291236052012e-05, "loss": 0.8805, "step": 7169 }, { "epoch": 0.41880841121495327, "grad_norm": 1.9181574583053589, "learning_rate": 1.306749065395588e-05, "loss": 1.1158, "step": 7170 }, { "epoch": 0.4188668224299065, "grad_norm": 0.9228140711784363, "learning_rate": 1.3065689962072245e-05, "loss": 0.666, "step": 7171 }, { "epoch": 0.41892523364485984, "grad_norm": 1.9471426010131836, "learning_rate": 1.3063889160465549e-05, "loss": 0.8594, "step": 7172 }, { "epoch": 0.4189836448598131, "grad_norm": 1.77140474319458, "learning_rate": 1.3062088249200244e-05, "loss": 1.0211, "step": 7173 }, { "epoch": 0.41904205607476636, "grad_norm": 1.3267858028411865, "learning_rate": 1.3060287228340791e-05, "loss": 0.8137, "step": 7174 }, { "epoch": 0.4191004672897196, "grad_norm": 2.1297497749328613, "learning_rate": 1.3058486097951644e-05, "loss": 0.9276, "step": 7175 }, { "epoch": 0.41915887850467287, "grad_norm": 1.1735881567001343, "learning_rate": 1.3056684858097265e-05, "loss": 0.6135, "step": 7176 }, { "epoch": 0.4192172897196262, "grad_norm": 1.461754322052002, "learning_rate": 1.305488350884213e-05, "loss": 0.7529, "step": 7177 }, { "epoch": 0.41927570093457944, "grad_norm": 1.3911799192428589, "learning_rate": 1.3053082050250705e-05, "loss": 0.7212, "step": 7178 }, { "epoch": 0.4193341121495327, "grad_norm": 2.1428494453430176, "learning_rate": 1.3051280482387464e-05, "loss": 0.8553, "step": 7179 }, { "epoch": 0.41939252336448596, "grad_norm": 1.106935739517212, "learning_rate": 1.304947880531689e-05, "loss": 0.8044, "step": 7180 }, { "epoch": 0.41945093457943927, "grad_norm": 1.1326144933700562, "learning_rate": 1.3047677019103462e-05, "loss": 0.6529, "step": 7181 }, { "epoch": 0.41950934579439253, "grad_norm": 1.8609216213226318, "learning_rate": 1.3045875123811671e-05, "loss": 0.7455, "step": 7182 }, { "epoch": 0.4195677570093458, "grad_norm": 1.6191242933273315, "learning_rate": 1.3044073119506009e-05, "loss": 0.8595, "step": 7183 }, { "epoch": 0.41962616822429905, "grad_norm": 1.5069588422775269, "learning_rate": 1.3042271006250965e-05, "loss": 0.824, "step": 7184 }, { "epoch": 0.41968457943925236, "grad_norm": 1.0407958030700684, "learning_rate": 1.3040468784111045e-05, "loss": 0.7458, "step": 7185 }, { "epoch": 0.4197429906542056, "grad_norm": 1.1943809986114502, "learning_rate": 1.3038666453150746e-05, "loss": 1.0258, "step": 7186 }, { "epoch": 0.4198014018691589, "grad_norm": 1.1147887706756592, "learning_rate": 1.3036864013434573e-05, "loss": 0.706, "step": 7187 }, { "epoch": 0.41985981308411213, "grad_norm": 1.2460296154022217, "learning_rate": 1.3035061465027046e-05, "loss": 0.7388, "step": 7188 }, { "epoch": 0.41991822429906545, "grad_norm": 1.1527056694030762, "learning_rate": 1.303325880799267e-05, "loss": 0.806, "step": 7189 }, { "epoch": 0.4199766355140187, "grad_norm": 0.8887636065483093, "learning_rate": 1.303145604239597e-05, "loss": 0.7543, "step": 7190 }, { "epoch": 0.42003504672897196, "grad_norm": 1.3490761518478394, "learning_rate": 1.3029653168301462e-05, "loss": 0.7272, "step": 7191 }, { "epoch": 0.4200934579439252, "grad_norm": 0.8734915852546692, "learning_rate": 1.3027850185773676e-05, "loss": 0.7348, "step": 7192 }, { "epoch": 0.4201518691588785, "grad_norm": 1.0847907066345215, "learning_rate": 1.3026047094877142e-05, "loss": 0.848, "step": 7193 }, { "epoch": 0.4202102803738318, "grad_norm": 0.9947614669799805, "learning_rate": 1.3024243895676392e-05, "loss": 0.7434, "step": 7194 }, { "epoch": 0.42026869158878505, "grad_norm": 1.3540948629379272, "learning_rate": 1.3022440588235963e-05, "loss": 0.9209, "step": 7195 }, { "epoch": 0.4203271028037383, "grad_norm": 1.3250470161437988, "learning_rate": 1.30206371726204e-05, "loss": 0.7182, "step": 7196 }, { "epoch": 0.42038551401869156, "grad_norm": 1.0952274799346924, "learning_rate": 1.3018833648894246e-05, "loss": 0.859, "step": 7197 }, { "epoch": 0.4204439252336449, "grad_norm": 1.3066866397857666, "learning_rate": 1.301703001712205e-05, "loss": 1.0258, "step": 7198 }, { "epoch": 0.42050233644859814, "grad_norm": 1.0827300548553467, "learning_rate": 1.3015226277368367e-05, "loss": 0.7914, "step": 7199 }, { "epoch": 0.4205607476635514, "grad_norm": 0.9472302794456482, "learning_rate": 1.3013422429697756e-05, "loss": 0.7879, "step": 7200 }, { "epoch": 0.42061915887850465, "grad_norm": 1.0813086032867432, "learning_rate": 1.3011618474174768e-05, "loss": 0.7584, "step": 7201 }, { "epoch": 0.42067757009345796, "grad_norm": 1.0911310911178589, "learning_rate": 1.3009814410863979e-05, "loss": 0.8164, "step": 7202 }, { "epoch": 0.4207359813084112, "grad_norm": 1.1923936605453491, "learning_rate": 1.3008010239829951e-05, "loss": 0.8719, "step": 7203 }, { "epoch": 0.4207943925233645, "grad_norm": 1.0504926443099976, "learning_rate": 1.3006205961137262e-05, "loss": 0.8342, "step": 7204 }, { "epoch": 0.42085280373831774, "grad_norm": 1.2008792161941528, "learning_rate": 1.3004401574850483e-05, "loss": 0.9115, "step": 7205 }, { "epoch": 0.42091121495327105, "grad_norm": 1.5385252237319946, "learning_rate": 1.3002597081034197e-05, "loss": 0.8431, "step": 7206 }, { "epoch": 0.4209696261682243, "grad_norm": 1.2658121585845947, "learning_rate": 1.3000792479752986e-05, "loss": 0.8561, "step": 7207 }, { "epoch": 0.42102803738317757, "grad_norm": 1.1862212419509888, "learning_rate": 1.2998987771071442e-05, "loss": 0.8398, "step": 7208 }, { "epoch": 0.4210864485981308, "grad_norm": 1.0291388034820557, "learning_rate": 1.2997182955054148e-05, "loss": 0.8029, "step": 7209 }, { "epoch": 0.42114485981308414, "grad_norm": 1.032088279724121, "learning_rate": 1.2995378031765712e-05, "loss": 0.8644, "step": 7210 }, { "epoch": 0.4212032710280374, "grad_norm": 1.3370119333267212, "learning_rate": 1.2993573001270722e-05, "loss": 0.8253, "step": 7211 }, { "epoch": 0.42126168224299065, "grad_norm": 1.545714020729065, "learning_rate": 1.2991767863633788e-05, "loss": 0.8623, "step": 7212 }, { "epoch": 0.4213200934579439, "grad_norm": 1.071467638015747, "learning_rate": 1.2989962618919516e-05, "loss": 0.7775, "step": 7213 }, { "epoch": 0.42137850467289717, "grad_norm": 1.2252581119537354, "learning_rate": 1.298815726719251e-05, "loss": 0.9401, "step": 7214 }, { "epoch": 0.4214369158878505, "grad_norm": 1.1196597814559937, "learning_rate": 1.29863518085174e-05, "loss": 0.7391, "step": 7215 }, { "epoch": 0.42149532710280374, "grad_norm": 1.3395525217056274, "learning_rate": 1.2984546242958789e-05, "loss": 0.8068, "step": 7216 }, { "epoch": 0.421553738317757, "grad_norm": 1.033729076385498, "learning_rate": 1.2982740570581307e-05, "loss": 0.8489, "step": 7217 }, { "epoch": 0.42161214953271026, "grad_norm": 1.6757187843322754, "learning_rate": 1.2980934791449579e-05, "loss": 0.9894, "step": 7218 }, { "epoch": 0.42167056074766357, "grad_norm": 1.3687188625335693, "learning_rate": 1.2979128905628236e-05, "loss": 0.7768, "step": 7219 }, { "epoch": 0.4217289719626168, "grad_norm": 1.0284717082977295, "learning_rate": 1.2977322913181906e-05, "loss": 0.8478, "step": 7220 }, { "epoch": 0.4217873831775701, "grad_norm": 1.7894014120101929, "learning_rate": 1.2975516814175235e-05, "loss": 0.978, "step": 7221 }, { "epoch": 0.42184579439252334, "grad_norm": 1.2783753871917725, "learning_rate": 1.297371060867286e-05, "loss": 0.8785, "step": 7222 }, { "epoch": 0.42190420560747666, "grad_norm": 1.9040402173995972, "learning_rate": 1.2971904296739429e-05, "loss": 0.8864, "step": 7223 }, { "epoch": 0.4219626168224299, "grad_norm": 1.0847052335739136, "learning_rate": 1.2970097878439587e-05, "loss": 0.7829, "step": 7224 }, { "epoch": 0.4220210280373832, "grad_norm": 1.4328447580337524, "learning_rate": 1.2968291353837991e-05, "loss": 0.8395, "step": 7225 }, { "epoch": 0.42207943925233643, "grad_norm": 1.3537253141403198, "learning_rate": 1.2966484722999294e-05, "loss": 1.0465, "step": 7226 }, { "epoch": 0.42213785046728974, "grad_norm": 1.1570664644241333, "learning_rate": 1.2964677985988159e-05, "loss": 0.8022, "step": 7227 }, { "epoch": 0.422196261682243, "grad_norm": 1.47099769115448, "learning_rate": 1.2962871142869249e-05, "loss": 0.7991, "step": 7228 }, { "epoch": 0.42225467289719626, "grad_norm": 1.208648443222046, "learning_rate": 1.2961064193707233e-05, "loss": 0.858, "step": 7229 }, { "epoch": 0.4223130841121495, "grad_norm": 1.0734474658966064, "learning_rate": 1.2959257138566783e-05, "loss": 0.9257, "step": 7230 }, { "epoch": 0.42237149532710283, "grad_norm": 1.224564790725708, "learning_rate": 1.295744997751257e-05, "loss": 0.8839, "step": 7231 }, { "epoch": 0.4224299065420561, "grad_norm": 1.3705930709838867, "learning_rate": 1.2955642710609287e-05, "loss": 0.8097, "step": 7232 }, { "epoch": 0.42248831775700935, "grad_norm": 1.2837791442871094, "learning_rate": 1.29538353379216e-05, "loss": 0.8437, "step": 7233 }, { "epoch": 0.4225467289719626, "grad_norm": 1.3127070665359497, "learning_rate": 1.2952027859514208e-05, "loss": 1.0281, "step": 7234 }, { "epoch": 0.42260514018691586, "grad_norm": 1.2721593379974365, "learning_rate": 1.2950220275451794e-05, "loss": 0.6649, "step": 7235 }, { "epoch": 0.4226635514018692, "grad_norm": 0.9368929862976074, "learning_rate": 1.294841258579906e-05, "loss": 0.7441, "step": 7236 }, { "epoch": 0.42272196261682243, "grad_norm": 1.6755435466766357, "learning_rate": 1.29466047906207e-05, "loss": 0.9621, "step": 7237 }, { "epoch": 0.4227803738317757, "grad_norm": 1.395822525024414, "learning_rate": 1.2944796889981417e-05, "loss": 1.1541, "step": 7238 }, { "epoch": 0.42283878504672895, "grad_norm": 1.7686327695846558, "learning_rate": 1.2942988883945916e-05, "loss": 0.8369, "step": 7239 }, { "epoch": 0.42289719626168226, "grad_norm": 1.267500877380371, "learning_rate": 1.294118077257891e-05, "loss": 0.6948, "step": 7240 }, { "epoch": 0.4229556074766355, "grad_norm": 2.283534049987793, "learning_rate": 1.2939372555945112e-05, "loss": 0.7804, "step": 7241 }, { "epoch": 0.4230140186915888, "grad_norm": 1.7308998107910156, "learning_rate": 1.2937564234109232e-05, "loss": 0.8853, "step": 7242 }, { "epoch": 0.42307242990654204, "grad_norm": 2.414506435394287, "learning_rate": 1.2935755807136e-05, "loss": 1.0014, "step": 7243 }, { "epoch": 0.42313084112149535, "grad_norm": 2.4534003734588623, "learning_rate": 1.2933947275090137e-05, "loss": 0.8024, "step": 7244 }, { "epoch": 0.4231892523364486, "grad_norm": 1.3571447134017944, "learning_rate": 1.2932138638036368e-05, "loss": 0.7022, "step": 7245 }, { "epoch": 0.42324766355140186, "grad_norm": 1.8969885110855103, "learning_rate": 1.2930329896039438e-05, "loss": 0.8698, "step": 7246 }, { "epoch": 0.4233060747663551, "grad_norm": 1.4941619634628296, "learning_rate": 1.2928521049164066e-05, "loss": 0.8564, "step": 7247 }, { "epoch": 0.42336448598130844, "grad_norm": 1.1419175863265991, "learning_rate": 1.2926712097475002e-05, "loss": 0.7259, "step": 7248 }, { "epoch": 0.4234228971962617, "grad_norm": 2.3595118522644043, "learning_rate": 1.2924903041036992e-05, "loss": 0.8836, "step": 7249 }, { "epoch": 0.42348130841121495, "grad_norm": 1.3141244649887085, "learning_rate": 1.2923093879914777e-05, "loss": 0.8163, "step": 7250 }, { "epoch": 0.4235397196261682, "grad_norm": 1.4856642484664917, "learning_rate": 1.2921284614173108e-05, "loss": 0.678, "step": 7251 }, { "epoch": 0.4235981308411215, "grad_norm": 2.3752100467681885, "learning_rate": 1.2919475243876742e-05, "loss": 0.8455, "step": 7252 }, { "epoch": 0.4236565420560748, "grad_norm": 1.684302568435669, "learning_rate": 1.2917665769090437e-05, "loss": 0.8862, "step": 7253 }, { "epoch": 0.42371495327102804, "grad_norm": 2.004642963409424, "learning_rate": 1.2915856189878956e-05, "loss": 0.9832, "step": 7254 }, { "epoch": 0.4237733644859813, "grad_norm": 2.215517044067383, "learning_rate": 1.2914046506307068e-05, "loss": 0.9414, "step": 7255 }, { "epoch": 0.42383177570093455, "grad_norm": 2.338646650314331, "learning_rate": 1.2912236718439537e-05, "loss": 0.8369, "step": 7256 }, { "epoch": 0.42389018691588787, "grad_norm": 1.5673469305038452, "learning_rate": 1.291042682634114e-05, "loss": 0.645, "step": 7257 }, { "epoch": 0.4239485981308411, "grad_norm": 1.7279750108718872, "learning_rate": 1.2908616830076653e-05, "loss": 0.947, "step": 7258 }, { "epoch": 0.4240070093457944, "grad_norm": 1.9334651231765747, "learning_rate": 1.2906806729710854e-05, "loss": 0.8869, "step": 7259 }, { "epoch": 0.42406542056074764, "grad_norm": 1.0029332637786865, "learning_rate": 1.2904996525308534e-05, "loss": 0.8237, "step": 7260 }, { "epoch": 0.42412383177570095, "grad_norm": 1.385254979133606, "learning_rate": 1.290318621693448e-05, "loss": 0.6883, "step": 7261 }, { "epoch": 0.4241822429906542, "grad_norm": 2.3175454139709473, "learning_rate": 1.290137580465348e-05, "loss": 1.0601, "step": 7262 }, { "epoch": 0.42424065420560747, "grad_norm": 1.0364177227020264, "learning_rate": 1.2899565288530334e-05, "loss": 0.7142, "step": 7263 }, { "epoch": 0.42429906542056073, "grad_norm": 1.3028736114501953, "learning_rate": 1.2897754668629836e-05, "loss": 0.8329, "step": 7264 }, { "epoch": 0.42435747663551404, "grad_norm": 1.33549964427948, "learning_rate": 1.2895943945016796e-05, "loss": 0.7178, "step": 7265 }, { "epoch": 0.4244158878504673, "grad_norm": 1.347437858581543, "learning_rate": 1.289413311775602e-05, "loss": 0.7086, "step": 7266 }, { "epoch": 0.42447429906542056, "grad_norm": 1.3039541244506836, "learning_rate": 1.2892322186912311e-05, "loss": 0.7518, "step": 7267 }, { "epoch": 0.4245327102803738, "grad_norm": 1.2631583213806152, "learning_rate": 1.2890511152550493e-05, "loss": 0.8502, "step": 7268 }, { "epoch": 0.42459112149532713, "grad_norm": 1.1837389469146729, "learning_rate": 1.288870001473538e-05, "loss": 0.7001, "step": 7269 }, { "epoch": 0.4246495327102804, "grad_norm": 1.0908831357955933, "learning_rate": 1.2886888773531796e-05, "loss": 0.8936, "step": 7270 }, { "epoch": 0.42470794392523364, "grad_norm": 1.392350196838379, "learning_rate": 1.2885077429004563e-05, "loss": 0.8361, "step": 7271 }, { "epoch": 0.4247663551401869, "grad_norm": 0.9984793663024902, "learning_rate": 1.288326598121851e-05, "loss": 0.7904, "step": 7272 }, { "epoch": 0.42482476635514016, "grad_norm": 1.0424679517745972, "learning_rate": 1.288145443023847e-05, "loss": 0.8783, "step": 7273 }, { "epoch": 0.4248831775700935, "grad_norm": 1.3819762468338013, "learning_rate": 1.2879642776129289e-05, "loss": 0.9237, "step": 7274 }, { "epoch": 0.42494158878504673, "grad_norm": 1.3770729303359985, "learning_rate": 1.2877831018955793e-05, "loss": 0.8171, "step": 7275 }, { "epoch": 0.425, "grad_norm": 0.8334076404571533, "learning_rate": 1.2876019158782835e-05, "loss": 0.7034, "step": 7276 }, { "epoch": 0.42505841121495325, "grad_norm": 1.3272985219955444, "learning_rate": 1.2874207195675262e-05, "loss": 0.6417, "step": 7277 }, { "epoch": 0.42511682242990656, "grad_norm": 0.9999146461486816, "learning_rate": 1.287239512969792e-05, "loss": 0.8498, "step": 7278 }, { "epoch": 0.4251752336448598, "grad_norm": 1.221760630607605, "learning_rate": 1.2870582960915669e-05, "loss": 0.7685, "step": 7279 }, { "epoch": 0.4252336448598131, "grad_norm": 1.724774718284607, "learning_rate": 1.2868770689393369e-05, "loss": 0.7967, "step": 7280 }, { "epoch": 0.42529205607476633, "grad_norm": 1.142959713935852, "learning_rate": 1.2866958315195877e-05, "loss": 0.6737, "step": 7281 }, { "epoch": 0.42535046728971965, "grad_norm": 1.7718360424041748, "learning_rate": 1.2865145838388063e-05, "loss": 0.7367, "step": 7282 }, { "epoch": 0.4254088785046729, "grad_norm": 1.3151627779006958, "learning_rate": 1.2863333259034794e-05, "loss": 0.7246, "step": 7283 }, { "epoch": 0.42546728971962616, "grad_norm": 1.3043402433395386, "learning_rate": 1.2861520577200946e-05, "loss": 0.7733, "step": 7284 }, { "epoch": 0.4255257009345794, "grad_norm": 1.5347949266433716, "learning_rate": 1.2859707792951397e-05, "loss": 0.7295, "step": 7285 }, { "epoch": 0.42558411214953273, "grad_norm": 1.5230491161346436, "learning_rate": 1.285789490635102e-05, "loss": 0.7737, "step": 7286 }, { "epoch": 0.425642523364486, "grad_norm": 1.1988186836242676, "learning_rate": 1.2856081917464711e-05, "loss": 0.7819, "step": 7287 }, { "epoch": 0.42570093457943925, "grad_norm": 1.3239234685897827, "learning_rate": 1.285426882635735e-05, "loss": 0.7811, "step": 7288 }, { "epoch": 0.4257593457943925, "grad_norm": 1.2747776508331299, "learning_rate": 1.285245563309383e-05, "loss": 0.7127, "step": 7289 }, { "epoch": 0.4258177570093458, "grad_norm": 1.5840624570846558, "learning_rate": 1.285064233773905e-05, "loss": 0.7065, "step": 7290 }, { "epoch": 0.4258761682242991, "grad_norm": 1.0832144021987915, "learning_rate": 1.2848828940357907e-05, "loss": 0.6976, "step": 7291 }, { "epoch": 0.42593457943925234, "grad_norm": 1.1042295694351196, "learning_rate": 1.2847015441015299e-05, "loss": 0.6401, "step": 7292 }, { "epoch": 0.4259929906542056, "grad_norm": 1.6844338178634644, "learning_rate": 1.2845201839776138e-05, "loss": 0.7383, "step": 7293 }, { "epoch": 0.42605140186915885, "grad_norm": 1.4931895732879639, "learning_rate": 1.2843388136705333e-05, "loss": 0.8848, "step": 7294 }, { "epoch": 0.42610981308411217, "grad_norm": 1.1730824708938599, "learning_rate": 1.2841574331867798e-05, "loss": 0.8324, "step": 7295 }, { "epoch": 0.4261682242990654, "grad_norm": 2.021705150604248, "learning_rate": 1.2839760425328449e-05, "loss": 0.747, "step": 7296 }, { "epoch": 0.4262266355140187, "grad_norm": 0.9527627229690552, "learning_rate": 1.2837946417152206e-05, "loss": 0.6688, "step": 7297 }, { "epoch": 0.42628504672897194, "grad_norm": 1.6356443166732788, "learning_rate": 1.2836132307403994e-05, "loss": 0.8757, "step": 7298 }, { "epoch": 0.42634345794392525, "grad_norm": 1.2327029705047607, "learning_rate": 1.2834318096148745e-05, "loss": 0.7054, "step": 7299 }, { "epoch": 0.4264018691588785, "grad_norm": 1.1671491861343384, "learning_rate": 1.2832503783451384e-05, "loss": 1.1057, "step": 7300 }, { "epoch": 0.42646028037383177, "grad_norm": 3.107818126678467, "learning_rate": 1.2830689369376854e-05, "loss": 0.8609, "step": 7301 }, { "epoch": 0.426518691588785, "grad_norm": 1.8118321895599365, "learning_rate": 1.2828874853990087e-05, "loss": 0.8589, "step": 7302 }, { "epoch": 0.42657710280373834, "grad_norm": 2.1763756275177, "learning_rate": 1.2827060237356028e-05, "loss": 0.9148, "step": 7303 }, { "epoch": 0.4266355140186916, "grad_norm": 1.347988486289978, "learning_rate": 1.282524551953963e-05, "loss": 0.7567, "step": 7304 }, { "epoch": 0.42669392523364486, "grad_norm": 1.1331137418746948, "learning_rate": 1.2823430700605832e-05, "loss": 0.742, "step": 7305 }, { "epoch": 0.4267523364485981, "grad_norm": 3.0717217922210693, "learning_rate": 1.2821615780619595e-05, "loss": 0.887, "step": 7306 }, { "epoch": 0.4268107476635514, "grad_norm": 1.4173614978790283, "learning_rate": 1.2819800759645873e-05, "loss": 0.8131, "step": 7307 }, { "epoch": 0.4268691588785047, "grad_norm": 2.629594564437866, "learning_rate": 1.2817985637749626e-05, "loss": 0.9243, "step": 7308 }, { "epoch": 0.42692757009345794, "grad_norm": 1.5124056339263916, "learning_rate": 1.2816170414995826e-05, "loss": 0.8693, "step": 7309 }, { "epoch": 0.4269859813084112, "grad_norm": 1.9537869691848755, "learning_rate": 1.2814355091449433e-05, "loss": 0.6783, "step": 7310 }, { "epoch": 0.4270443925233645, "grad_norm": 1.5064386129379272, "learning_rate": 1.2812539667175416e-05, "loss": 0.6423, "step": 7311 }, { "epoch": 0.42710280373831777, "grad_norm": 1.9331753253936768, "learning_rate": 1.281072414223876e-05, "loss": 0.8579, "step": 7312 }, { "epoch": 0.42716121495327103, "grad_norm": 1.589590311050415, "learning_rate": 1.2808908516704437e-05, "loss": 0.8596, "step": 7313 }, { "epoch": 0.4272196261682243, "grad_norm": 2.3537797927856445, "learning_rate": 1.2807092790637432e-05, "loss": 0.751, "step": 7314 }, { "epoch": 0.42727803738317754, "grad_norm": 1.330036997795105, "learning_rate": 1.2805276964102731e-05, "loss": 1.0265, "step": 7315 }, { "epoch": 0.42733644859813086, "grad_norm": 1.345538854598999, "learning_rate": 1.280346103716532e-05, "loss": 0.9549, "step": 7316 }, { "epoch": 0.4273948598130841, "grad_norm": 2.2430689334869385, "learning_rate": 1.2801645009890195e-05, "loss": 0.7977, "step": 7317 }, { "epoch": 0.4274532710280374, "grad_norm": 1.2751206159591675, "learning_rate": 1.2799828882342355e-05, "loss": 0.8492, "step": 7318 }, { "epoch": 0.42751168224299063, "grad_norm": 1.3296892642974854, "learning_rate": 1.27980126545868e-05, "loss": 0.6857, "step": 7319 }, { "epoch": 0.42757009345794394, "grad_norm": 1.4038491249084473, "learning_rate": 1.2796196326688533e-05, "loss": 0.6649, "step": 7320 }, { "epoch": 0.4276285046728972, "grad_norm": 0.974965512752533, "learning_rate": 1.2794379898712558e-05, "loss": 0.7882, "step": 7321 }, { "epoch": 0.42768691588785046, "grad_norm": 1.5756020545959473, "learning_rate": 1.2792563370723887e-05, "loss": 0.7409, "step": 7322 }, { "epoch": 0.4277453271028037, "grad_norm": 1.5461525917053223, "learning_rate": 1.279074674278754e-05, "loss": 0.9653, "step": 7323 }, { "epoch": 0.42780373831775703, "grad_norm": 0.9854947328567505, "learning_rate": 1.2788930014968535e-05, "loss": 0.7683, "step": 7324 }, { "epoch": 0.4278621495327103, "grad_norm": 1.6942062377929688, "learning_rate": 1.2787113187331886e-05, "loss": 0.9112, "step": 7325 }, { "epoch": 0.42792056074766355, "grad_norm": 1.0487182140350342, "learning_rate": 1.2785296259942626e-05, "loss": 0.7724, "step": 7326 }, { "epoch": 0.4279789719626168, "grad_norm": 1.3739159107208252, "learning_rate": 1.2783479232865781e-05, "loss": 0.9109, "step": 7327 }, { "epoch": 0.4280373831775701, "grad_norm": 0.9708336591720581, "learning_rate": 1.2781662106166384e-05, "loss": 0.6591, "step": 7328 }, { "epoch": 0.4280957943925234, "grad_norm": 1.3200603723526, "learning_rate": 1.277984487990947e-05, "loss": 0.9388, "step": 7329 }, { "epoch": 0.42815420560747663, "grad_norm": 1.1537665128707886, "learning_rate": 1.277802755416008e-05, "loss": 0.7528, "step": 7330 }, { "epoch": 0.4282126168224299, "grad_norm": 1.6921640634536743, "learning_rate": 1.2776210128983257e-05, "loss": 0.7574, "step": 7331 }, { "epoch": 0.42827102803738315, "grad_norm": 0.9300222396850586, "learning_rate": 1.277439260444405e-05, "loss": 0.7089, "step": 7332 }, { "epoch": 0.42832943925233646, "grad_norm": 0.9031180143356323, "learning_rate": 1.2772574980607508e-05, "loss": 0.5969, "step": 7333 }, { "epoch": 0.4283878504672897, "grad_norm": 1.0960859060287476, "learning_rate": 1.2770757257538684e-05, "loss": 0.697, "step": 7334 }, { "epoch": 0.428446261682243, "grad_norm": 1.209161400794983, "learning_rate": 1.2768939435302636e-05, "loss": 0.8005, "step": 7335 }, { "epoch": 0.42850467289719624, "grad_norm": 1.052355170249939, "learning_rate": 1.276712151396442e-05, "loss": 0.8341, "step": 7336 }, { "epoch": 0.42856308411214955, "grad_norm": 1.0269018411636353, "learning_rate": 1.2765303493589112e-05, "loss": 0.6774, "step": 7337 }, { "epoch": 0.4286214953271028, "grad_norm": 0.9540998339653015, "learning_rate": 1.2763485374241772e-05, "loss": 0.8001, "step": 7338 }, { "epoch": 0.42867990654205607, "grad_norm": 1.4063290357589722, "learning_rate": 1.2761667155987473e-05, "loss": 1.0117, "step": 7339 }, { "epoch": 0.4287383177570093, "grad_norm": 1.8542165756225586, "learning_rate": 1.2759848838891291e-05, "loss": 0.8274, "step": 7340 }, { "epoch": 0.42879672897196264, "grad_norm": 1.1366066932678223, "learning_rate": 1.2758030423018302e-05, "loss": 0.8398, "step": 7341 }, { "epoch": 0.4288551401869159, "grad_norm": 1.127223253250122, "learning_rate": 1.2756211908433593e-05, "loss": 0.8112, "step": 7342 }, { "epoch": 0.42891355140186915, "grad_norm": 0.9553771018981934, "learning_rate": 1.275439329520225e-05, "loss": 0.7619, "step": 7343 }, { "epoch": 0.4289719626168224, "grad_norm": 0.9456044435501099, "learning_rate": 1.2752574583389354e-05, "loss": 0.7585, "step": 7344 }, { "epoch": 0.4290303738317757, "grad_norm": 1.3672128915786743, "learning_rate": 1.2750755773060008e-05, "loss": 0.7498, "step": 7345 }, { "epoch": 0.429088785046729, "grad_norm": 1.4275622367858887, "learning_rate": 1.2748936864279305e-05, "loss": 0.8096, "step": 7346 }, { "epoch": 0.42914719626168224, "grad_norm": 1.3616763353347778, "learning_rate": 1.274711785711234e-05, "loss": 0.6863, "step": 7347 }, { "epoch": 0.4292056074766355, "grad_norm": 1.4096120595932007, "learning_rate": 1.2745298751624224e-05, "loss": 0.991, "step": 7348 }, { "epoch": 0.4292640186915888, "grad_norm": 0.9988852739334106, "learning_rate": 1.2743479547880062e-05, "loss": 0.818, "step": 7349 }, { "epoch": 0.42932242990654207, "grad_norm": 3.196597099304199, "learning_rate": 1.2741660245944958e-05, "loss": 0.661, "step": 7350 }, { "epoch": 0.4293808411214953, "grad_norm": 1.0997157096862793, "learning_rate": 1.2739840845884036e-05, "loss": 0.822, "step": 7351 }, { "epoch": 0.4294392523364486, "grad_norm": 1.3302736282348633, "learning_rate": 1.2738021347762404e-05, "loss": 0.8155, "step": 7352 }, { "epoch": 0.42949766355140184, "grad_norm": 1.0774784088134766, "learning_rate": 1.2736201751645192e-05, "loss": 0.5909, "step": 7353 }, { "epoch": 0.42955607476635516, "grad_norm": 1.1073468923568726, "learning_rate": 1.2734382057597519e-05, "loss": 0.641, "step": 7354 }, { "epoch": 0.4296144859813084, "grad_norm": 1.5664525032043457, "learning_rate": 1.2732562265684512e-05, "loss": 0.9082, "step": 7355 }, { "epoch": 0.42967289719626167, "grad_norm": 1.5578382015228271, "learning_rate": 1.2730742375971306e-05, "loss": 0.975, "step": 7356 }, { "epoch": 0.42973130841121493, "grad_norm": 1.9322867393493652, "learning_rate": 1.2728922388523037e-05, "loss": 0.8029, "step": 7357 }, { "epoch": 0.42978971962616824, "grad_norm": 1.3320494890213013, "learning_rate": 1.272710230340484e-05, "loss": 0.8397, "step": 7358 }, { "epoch": 0.4298481308411215, "grad_norm": 1.341773271560669, "learning_rate": 1.2725282120681857e-05, "loss": 0.6801, "step": 7359 }, { "epoch": 0.42990654205607476, "grad_norm": 1.199790358543396, "learning_rate": 1.2723461840419237e-05, "loss": 0.7923, "step": 7360 }, { "epoch": 0.429964953271028, "grad_norm": 1.5190787315368652, "learning_rate": 1.2721641462682124e-05, "loss": 0.7443, "step": 7361 }, { "epoch": 0.43002336448598133, "grad_norm": 1.16517972946167, "learning_rate": 1.2719820987535679e-05, "loss": 0.7205, "step": 7362 }, { "epoch": 0.4300817757009346, "grad_norm": 2.1539132595062256, "learning_rate": 1.2718000415045047e-05, "loss": 0.9577, "step": 7363 }, { "epoch": 0.43014018691588785, "grad_norm": 1.598724603652954, "learning_rate": 1.2716179745275396e-05, "loss": 0.9103, "step": 7364 }, { "epoch": 0.4301985981308411, "grad_norm": 1.3141121864318848, "learning_rate": 1.2714358978291885e-05, "loss": 0.8162, "step": 7365 }, { "epoch": 0.4302570093457944, "grad_norm": 1.4501396417617798, "learning_rate": 1.271253811415968e-05, "loss": 0.9055, "step": 7366 }, { "epoch": 0.4303154205607477, "grad_norm": 1.2683392763137817, "learning_rate": 1.2710717152943957e-05, "loss": 0.7709, "step": 7367 }, { "epoch": 0.43037383177570093, "grad_norm": 1.3280993700027466, "learning_rate": 1.2708896094709881e-05, "loss": 0.8786, "step": 7368 }, { "epoch": 0.4304322429906542, "grad_norm": 1.6020843982696533, "learning_rate": 1.2707074939522633e-05, "loss": 0.8376, "step": 7369 }, { "epoch": 0.4304906542056075, "grad_norm": 1.4022260904312134, "learning_rate": 1.2705253687447395e-05, "loss": 0.8246, "step": 7370 }, { "epoch": 0.43054906542056076, "grad_norm": 1.5604885816574097, "learning_rate": 1.2703432338549347e-05, "loss": 0.8173, "step": 7371 }, { "epoch": 0.430607476635514, "grad_norm": 1.275033712387085, "learning_rate": 1.2701610892893679e-05, "loss": 0.7923, "step": 7372 }, { "epoch": 0.4306658878504673, "grad_norm": 1.0587131977081299, "learning_rate": 1.269978935054558e-05, "loss": 0.9286, "step": 7373 }, { "epoch": 0.43072429906542054, "grad_norm": 1.624031901359558, "learning_rate": 1.2697967711570243e-05, "loss": 0.7545, "step": 7374 }, { "epoch": 0.43078271028037385, "grad_norm": 1.4583431482315063, "learning_rate": 1.269614597603287e-05, "loss": 0.7277, "step": 7375 }, { "epoch": 0.4308411214953271, "grad_norm": 1.1041182279586792, "learning_rate": 1.269432414399866e-05, "loss": 0.7587, "step": 7376 }, { "epoch": 0.43089953271028036, "grad_norm": 1.3128958940505981, "learning_rate": 1.2692502215532819e-05, "loss": 0.6932, "step": 7377 }, { "epoch": 0.4309579439252336, "grad_norm": 1.6593575477600098, "learning_rate": 1.2690680190700551e-05, "loss": 0.9164, "step": 7378 }, { "epoch": 0.43101635514018694, "grad_norm": 1.2767192125320435, "learning_rate": 1.268885806956707e-05, "loss": 0.8405, "step": 7379 }, { "epoch": 0.4310747663551402, "grad_norm": 1.2467948198318481, "learning_rate": 1.268703585219759e-05, "loss": 0.8568, "step": 7380 }, { "epoch": 0.43113317757009345, "grad_norm": 1.2129838466644287, "learning_rate": 1.268521353865733e-05, "loss": 0.6733, "step": 7381 }, { "epoch": 0.4311915887850467, "grad_norm": 1.1319485902786255, "learning_rate": 1.2683391129011515e-05, "loss": 0.7418, "step": 7382 }, { "epoch": 0.43125, "grad_norm": 1.0207072496414185, "learning_rate": 1.2681568623325364e-05, "loss": 0.7286, "step": 7383 }, { "epoch": 0.4313084112149533, "grad_norm": 1.3509247303009033, "learning_rate": 1.267974602166411e-05, "loss": 0.6566, "step": 7384 }, { "epoch": 0.43136682242990654, "grad_norm": 0.9885188341140747, "learning_rate": 1.2677923324092985e-05, "loss": 0.8986, "step": 7385 }, { "epoch": 0.4314252336448598, "grad_norm": 1.510452151298523, "learning_rate": 1.267610053067722e-05, "loss": 0.7639, "step": 7386 }, { "epoch": 0.4314836448598131, "grad_norm": 1.037193775177002, "learning_rate": 1.267427764148206e-05, "loss": 0.7208, "step": 7387 }, { "epoch": 0.43154205607476637, "grad_norm": 1.093684434890747, "learning_rate": 1.2672454656572744e-05, "loss": 0.8021, "step": 7388 }, { "epoch": 0.4316004672897196, "grad_norm": 1.4348512887954712, "learning_rate": 1.2670631576014519e-05, "loss": 0.8022, "step": 7389 }, { "epoch": 0.4316588785046729, "grad_norm": 1.6470474004745483, "learning_rate": 1.2668808399872635e-05, "loss": 0.6984, "step": 7390 }, { "epoch": 0.43171728971962614, "grad_norm": 1.2532979249954224, "learning_rate": 1.2666985128212341e-05, "loss": 0.8178, "step": 7391 }, { "epoch": 0.43177570093457945, "grad_norm": 1.6827566623687744, "learning_rate": 1.2665161761098899e-05, "loss": 0.8525, "step": 7392 }, { "epoch": 0.4318341121495327, "grad_norm": 0.945914089679718, "learning_rate": 1.2663338298597562e-05, "loss": 0.6955, "step": 7393 }, { "epoch": 0.43189252336448597, "grad_norm": 1.1020594835281372, "learning_rate": 1.2661514740773596e-05, "loss": 0.6791, "step": 7394 }, { "epoch": 0.4319509345794392, "grad_norm": 1.2266478538513184, "learning_rate": 1.2659691087692271e-05, "loss": 0.7565, "step": 7395 }, { "epoch": 0.43200934579439254, "grad_norm": 1.0467603206634521, "learning_rate": 1.265786733941885e-05, "loss": 0.7307, "step": 7396 }, { "epoch": 0.4320677570093458, "grad_norm": 1.1896278858184814, "learning_rate": 1.2656043496018611e-05, "loss": 0.855, "step": 7397 }, { "epoch": 0.43212616822429906, "grad_norm": 1.3580102920532227, "learning_rate": 1.265421955755683e-05, "loss": 0.9331, "step": 7398 }, { "epoch": 0.4321845794392523, "grad_norm": 1.2853630781173706, "learning_rate": 1.2652395524098782e-05, "loss": 0.8288, "step": 7399 }, { "epoch": 0.4322429906542056, "grad_norm": 1.3756346702575684, "learning_rate": 1.2650571395709757e-05, "loss": 0.7421, "step": 7400 }, { "epoch": 0.4323014018691589, "grad_norm": 0.9059591889381409, "learning_rate": 1.264874717245504e-05, "loss": 0.6287, "step": 7401 }, { "epoch": 0.43235981308411214, "grad_norm": 3.291522264480591, "learning_rate": 1.2646922854399919e-05, "loss": 0.8944, "step": 7402 }, { "epoch": 0.4324182242990654, "grad_norm": 1.2747231721878052, "learning_rate": 1.2645098441609687e-05, "loss": 0.7173, "step": 7403 }, { "epoch": 0.4324766355140187, "grad_norm": 1.1233681440353394, "learning_rate": 1.2643273934149645e-05, "loss": 0.8228, "step": 7404 }, { "epoch": 0.432535046728972, "grad_norm": 1.5099135637283325, "learning_rate": 1.2641449332085087e-05, "loss": 0.984, "step": 7405 }, { "epoch": 0.43259345794392523, "grad_norm": 1.054072618484497, "learning_rate": 1.2639624635481326e-05, "loss": 0.6941, "step": 7406 }, { "epoch": 0.4326518691588785, "grad_norm": 1.6331124305725098, "learning_rate": 1.263779984440366e-05, "loss": 1.0118, "step": 7407 }, { "epoch": 0.4327102803738318, "grad_norm": 1.029805064201355, "learning_rate": 1.2635974958917405e-05, "loss": 0.9301, "step": 7408 }, { "epoch": 0.43276869158878506, "grad_norm": 1.464151382446289, "learning_rate": 1.2634149979087873e-05, "loss": 1.0213, "step": 7409 }, { "epoch": 0.4328271028037383, "grad_norm": 1.2839893102645874, "learning_rate": 1.263232490498038e-05, "loss": 0.7348, "step": 7410 }, { "epoch": 0.4328855140186916, "grad_norm": 2.566742181777954, "learning_rate": 1.2630499736660249e-05, "loss": 0.9322, "step": 7411 }, { "epoch": 0.43294392523364483, "grad_norm": 1.21678626537323, "learning_rate": 1.2628674474192802e-05, "loss": 0.9304, "step": 7412 }, { "epoch": 0.43300233644859815, "grad_norm": 1.167301893234253, "learning_rate": 1.2626849117643366e-05, "loss": 0.7809, "step": 7413 }, { "epoch": 0.4330607476635514, "grad_norm": 1.2590248584747314, "learning_rate": 1.2625023667077274e-05, "loss": 0.887, "step": 7414 }, { "epoch": 0.43311915887850466, "grad_norm": 0.9351562261581421, "learning_rate": 1.2623198122559863e-05, "loss": 0.8018, "step": 7415 }, { "epoch": 0.4331775700934579, "grad_norm": 1.7204128503799438, "learning_rate": 1.262137248415646e-05, "loss": 0.8068, "step": 7416 }, { "epoch": 0.43323598130841123, "grad_norm": 1.2742843627929688, "learning_rate": 1.2619546751932414e-05, "loss": 0.808, "step": 7417 }, { "epoch": 0.4332943925233645, "grad_norm": 1.0958493947982788, "learning_rate": 1.261772092595307e-05, "loss": 0.681, "step": 7418 }, { "epoch": 0.43335280373831775, "grad_norm": 1.5383952856063843, "learning_rate": 1.261589500628377e-05, "loss": 0.8543, "step": 7419 }, { "epoch": 0.433411214953271, "grad_norm": 1.3299388885498047, "learning_rate": 1.261406899298987e-05, "loss": 0.8596, "step": 7420 }, { "epoch": 0.4334696261682243, "grad_norm": 1.855381727218628, "learning_rate": 1.261224288613672e-05, "loss": 0.9269, "step": 7421 }, { "epoch": 0.4335280373831776, "grad_norm": 1.0948874950408936, "learning_rate": 1.261041668578968e-05, "loss": 0.7246, "step": 7422 }, { "epoch": 0.43358644859813084, "grad_norm": 1.4446368217468262, "learning_rate": 1.2608590392014111e-05, "loss": 0.7892, "step": 7423 }, { "epoch": 0.4336448598130841, "grad_norm": 1.3096448183059692, "learning_rate": 1.2606764004875375e-05, "loss": 0.7827, "step": 7424 }, { "epoch": 0.4337032710280374, "grad_norm": 1.1219899654388428, "learning_rate": 1.2604937524438845e-05, "loss": 0.7585, "step": 7425 }, { "epoch": 0.43376168224299066, "grad_norm": 1.4703015089035034, "learning_rate": 1.2603110950769888e-05, "loss": 0.8729, "step": 7426 }, { "epoch": 0.4338200934579439, "grad_norm": 1.121778964996338, "learning_rate": 1.2601284283933874e-05, "loss": 0.9593, "step": 7427 }, { "epoch": 0.4338785046728972, "grad_norm": 2.236422061920166, "learning_rate": 1.2599457523996188e-05, "loss": 0.8946, "step": 7428 }, { "epoch": 0.4339369158878505, "grad_norm": 1.1041978597640991, "learning_rate": 1.2597630671022208e-05, "loss": 0.6937, "step": 7429 }, { "epoch": 0.43399532710280375, "grad_norm": 2.50173282623291, "learning_rate": 1.2595803725077318e-05, "loss": 0.721, "step": 7430 }, { "epoch": 0.434053738317757, "grad_norm": 1.3097506761550903, "learning_rate": 1.2593976686226906e-05, "loss": 0.8423, "step": 7431 }, { "epoch": 0.43411214953271027, "grad_norm": 1.0639365911483765, "learning_rate": 1.259214955453636e-05, "loss": 0.7534, "step": 7432 }, { "epoch": 0.4341705607476635, "grad_norm": 1.4167203903198242, "learning_rate": 1.2590322330071081e-05, "loss": 0.8754, "step": 7433 }, { "epoch": 0.43422897196261684, "grad_norm": 1.12962007522583, "learning_rate": 1.258849501289646e-05, "loss": 0.8987, "step": 7434 }, { "epoch": 0.4342873831775701, "grad_norm": 1.312851905822754, "learning_rate": 1.2586667603077905e-05, "loss": 0.9268, "step": 7435 }, { "epoch": 0.43434579439252335, "grad_norm": 1.0863806009292603, "learning_rate": 1.258484010068081e-05, "loss": 0.7363, "step": 7436 }, { "epoch": 0.4344042056074766, "grad_norm": 1.0438122749328613, "learning_rate": 1.2583012505770594e-05, "loss": 0.7117, "step": 7437 }, { "epoch": 0.4344626168224299, "grad_norm": 1.286889672279358, "learning_rate": 1.2581184818412655e-05, "loss": 0.9404, "step": 7438 }, { "epoch": 0.4345210280373832, "grad_norm": 1.5603094100952148, "learning_rate": 1.2579357038672422e-05, "loss": 0.87, "step": 7439 }, { "epoch": 0.43457943925233644, "grad_norm": 0.9571154117584229, "learning_rate": 1.25775291666153e-05, "loss": 0.7788, "step": 7440 }, { "epoch": 0.4346378504672897, "grad_norm": 1.326988935470581, "learning_rate": 1.2575701202306715e-05, "loss": 0.8098, "step": 7441 }, { "epoch": 0.434696261682243, "grad_norm": 1.4019054174423218, "learning_rate": 1.257387314581209e-05, "loss": 0.8984, "step": 7442 }, { "epoch": 0.43475467289719627, "grad_norm": 0.9017239809036255, "learning_rate": 1.2572044997196854e-05, "loss": 0.7194, "step": 7443 }, { "epoch": 0.43481308411214953, "grad_norm": 1.3122076988220215, "learning_rate": 1.2570216756526434e-05, "loss": 0.8361, "step": 7444 }, { "epoch": 0.4348714953271028, "grad_norm": 1.3106565475463867, "learning_rate": 1.256838842386627e-05, "loss": 0.7987, "step": 7445 }, { "epoch": 0.4349299065420561, "grad_norm": 1.481842279434204, "learning_rate": 1.256655999928179e-05, "loss": 0.7753, "step": 7446 }, { "epoch": 0.43498831775700936, "grad_norm": 1.4083157777786255, "learning_rate": 1.2564731482838446e-05, "loss": 0.909, "step": 7447 }, { "epoch": 0.4350467289719626, "grad_norm": 1.1712393760681152, "learning_rate": 1.2562902874601673e-05, "loss": 0.6855, "step": 7448 }, { "epoch": 0.4351051401869159, "grad_norm": 1.4469281435012817, "learning_rate": 1.2561074174636923e-05, "loss": 0.9616, "step": 7449 }, { "epoch": 0.4351635514018692, "grad_norm": 1.0387219190597534, "learning_rate": 1.2559245383009642e-05, "loss": 0.9521, "step": 7450 }, { "epoch": 0.43522196261682244, "grad_norm": 1.264289379119873, "learning_rate": 1.2557416499785287e-05, "loss": 0.7721, "step": 7451 }, { "epoch": 0.4352803738317757, "grad_norm": 1.3587594032287598, "learning_rate": 1.2555587525029312e-05, "loss": 0.7121, "step": 7452 }, { "epoch": 0.43533878504672896, "grad_norm": 1.56312894821167, "learning_rate": 1.2553758458807182e-05, "loss": 0.8658, "step": 7453 }, { "epoch": 0.4353971962616822, "grad_norm": 1.6974766254425049, "learning_rate": 1.2551929301184355e-05, "loss": 0.761, "step": 7454 }, { "epoch": 0.43545560747663553, "grad_norm": 1.1624743938446045, "learning_rate": 1.2550100052226304e-05, "loss": 0.9235, "step": 7455 }, { "epoch": 0.4355140186915888, "grad_norm": 2.3404202461242676, "learning_rate": 1.2548270711998493e-05, "loss": 0.7728, "step": 7456 }, { "epoch": 0.43557242990654205, "grad_norm": 1.4796572923660278, "learning_rate": 1.2546441280566395e-05, "loss": 0.8517, "step": 7457 }, { "epoch": 0.4356308411214953, "grad_norm": 1.1164448261260986, "learning_rate": 1.2544611757995494e-05, "loss": 0.9721, "step": 7458 }, { "epoch": 0.4356892523364486, "grad_norm": 0.9053198099136353, "learning_rate": 1.2542782144351267e-05, "loss": 0.6348, "step": 7459 }, { "epoch": 0.4357476635514019, "grad_norm": 1.198959231376648, "learning_rate": 1.2540952439699188e-05, "loss": 0.7447, "step": 7460 }, { "epoch": 0.43580607476635513, "grad_norm": 1.1718461513519287, "learning_rate": 1.2539122644104755e-05, "loss": 0.8404, "step": 7461 }, { "epoch": 0.4358644859813084, "grad_norm": 1.221441388130188, "learning_rate": 1.2537292757633452e-05, "loss": 0.7953, "step": 7462 }, { "epoch": 0.4359228971962617, "grad_norm": 1.6636431217193604, "learning_rate": 1.2535462780350771e-05, "loss": 0.7786, "step": 7463 }, { "epoch": 0.43598130841121496, "grad_norm": 1.3963927030563354, "learning_rate": 1.2533632712322215e-05, "loss": 0.8564, "step": 7464 }, { "epoch": 0.4360397196261682, "grad_norm": 1.3919610977172852, "learning_rate": 1.2531802553613273e-05, "loss": 0.8472, "step": 7465 }, { "epoch": 0.4360981308411215, "grad_norm": 1.6096115112304688, "learning_rate": 1.2529972304289455e-05, "loss": 0.8278, "step": 7466 }, { "epoch": 0.4361565420560748, "grad_norm": 1.9490795135498047, "learning_rate": 1.2528141964416266e-05, "loss": 1.0867, "step": 7467 }, { "epoch": 0.43621495327102805, "grad_norm": 1.3634235858917236, "learning_rate": 1.2526311534059212e-05, "loss": 0.7924, "step": 7468 }, { "epoch": 0.4362733644859813, "grad_norm": 1.100772738456726, "learning_rate": 1.2524481013283809e-05, "loss": 0.933, "step": 7469 }, { "epoch": 0.43633177570093457, "grad_norm": 3.306414842605591, "learning_rate": 1.252265040215557e-05, "loss": 0.8685, "step": 7470 }, { "epoch": 0.4363901869158878, "grad_norm": 1.2671924829483032, "learning_rate": 1.2520819700740012e-05, "loss": 0.9079, "step": 7471 }, { "epoch": 0.43644859813084114, "grad_norm": 1.7079752683639526, "learning_rate": 1.2518988909102663e-05, "loss": 0.7292, "step": 7472 }, { "epoch": 0.4365070093457944, "grad_norm": 1.3721143007278442, "learning_rate": 1.2517158027309041e-05, "loss": 0.8071, "step": 7473 }, { "epoch": 0.43656542056074765, "grad_norm": 1.2803030014038086, "learning_rate": 1.2515327055424682e-05, "loss": 0.7679, "step": 7474 }, { "epoch": 0.4366238317757009, "grad_norm": 1.7496976852416992, "learning_rate": 1.2513495993515113e-05, "loss": 0.8344, "step": 7475 }, { "epoch": 0.4366822429906542, "grad_norm": 1.6638894081115723, "learning_rate": 1.2511664841645868e-05, "loss": 0.8898, "step": 7476 }, { "epoch": 0.4367406542056075, "grad_norm": 2.6812281608581543, "learning_rate": 1.2509833599882486e-05, "loss": 0.892, "step": 7477 }, { "epoch": 0.43679906542056074, "grad_norm": 0.8109844923019409, "learning_rate": 1.2508002268290513e-05, "loss": 0.5978, "step": 7478 }, { "epoch": 0.436857476635514, "grad_norm": 2.171523332595825, "learning_rate": 1.2506170846935486e-05, "loss": 0.8028, "step": 7479 }, { "epoch": 0.4369158878504673, "grad_norm": 3.7309229373931885, "learning_rate": 1.2504339335882958e-05, "loss": 0.9293, "step": 7480 }, { "epoch": 0.43697429906542057, "grad_norm": 1.7015224695205688, "learning_rate": 1.250250773519848e-05, "loss": 0.9889, "step": 7481 }, { "epoch": 0.4370327102803738, "grad_norm": 3.410125255584717, "learning_rate": 1.2500676044947602e-05, "loss": 0.7952, "step": 7482 }, { "epoch": 0.4370911214953271, "grad_norm": 2.914975643157959, "learning_rate": 1.2498844265195887e-05, "loss": 0.8843, "step": 7483 }, { "epoch": 0.4371495327102804, "grad_norm": 2.9647109508514404, "learning_rate": 1.2497012396008893e-05, "loss": 0.8696, "step": 7484 }, { "epoch": 0.43720794392523366, "grad_norm": 3.1030192375183105, "learning_rate": 1.2495180437452179e-05, "loss": 0.8627, "step": 7485 }, { "epoch": 0.4372663551401869, "grad_norm": 2.686476230621338, "learning_rate": 1.249334838959132e-05, "loss": 0.9102, "step": 7486 }, { "epoch": 0.43732476635514017, "grad_norm": 1.8854871988296509, "learning_rate": 1.2491516252491883e-05, "loss": 0.6943, "step": 7487 }, { "epoch": 0.4373831775700935, "grad_norm": 3.2853972911834717, "learning_rate": 1.248968402621944e-05, "loss": 0.849, "step": 7488 }, { "epoch": 0.43744158878504674, "grad_norm": 2.605517625808716, "learning_rate": 1.2487851710839569e-05, "loss": 0.9925, "step": 7489 }, { "epoch": 0.4375, "grad_norm": 1.3369930982589722, "learning_rate": 1.2486019306417847e-05, "loss": 0.6882, "step": 7490 }, { "epoch": 0.43755841121495326, "grad_norm": 3.0775458812713623, "learning_rate": 1.2484186813019863e-05, "loss": 0.7759, "step": 7491 }, { "epoch": 0.4376168224299065, "grad_norm": 1.9101605415344238, "learning_rate": 1.2482354230711197e-05, "loss": 0.8303, "step": 7492 }, { "epoch": 0.43767523364485983, "grad_norm": 1.3211532831192017, "learning_rate": 1.2480521559557444e-05, "loss": 0.8135, "step": 7493 }, { "epoch": 0.4377336448598131, "grad_norm": 0.8874841928482056, "learning_rate": 1.2478688799624193e-05, "loss": 0.6634, "step": 7494 }, { "epoch": 0.43779205607476634, "grad_norm": 2.2474637031555176, "learning_rate": 1.2476855950977039e-05, "loss": 0.8695, "step": 7495 }, { "epoch": 0.4378504672897196, "grad_norm": 1.6198863983154297, "learning_rate": 1.2475023013681579e-05, "loss": 0.7067, "step": 7496 }, { "epoch": 0.4379088785046729, "grad_norm": 1.5421472787857056, "learning_rate": 1.2473189987803422e-05, "loss": 0.8769, "step": 7497 }, { "epoch": 0.4379672897196262, "grad_norm": 1.100337266921997, "learning_rate": 1.2471356873408168e-05, "loss": 0.828, "step": 7498 }, { "epoch": 0.43802570093457943, "grad_norm": 1.953345775604248, "learning_rate": 1.2469523670561425e-05, "loss": 1.0095, "step": 7499 }, { "epoch": 0.4380841121495327, "grad_norm": 1.959349513053894, "learning_rate": 1.246769037932881e-05, "loss": 0.8349, "step": 7500 }, { "epoch": 0.438142523364486, "grad_norm": 1.5436793565750122, "learning_rate": 1.2465856999775929e-05, "loss": 0.9052, "step": 7501 }, { "epoch": 0.43820093457943926, "grad_norm": 1.390255093574524, "learning_rate": 1.2464023531968408e-05, "loss": 1.0509, "step": 7502 }, { "epoch": 0.4382593457943925, "grad_norm": 1.4185377359390259, "learning_rate": 1.2462189975971864e-05, "loss": 0.7616, "step": 7503 }, { "epoch": 0.4383177570093458, "grad_norm": 1.7507802248001099, "learning_rate": 1.246035633185192e-05, "loss": 0.8595, "step": 7504 }, { "epoch": 0.4383761682242991, "grad_norm": 1.298140048980713, "learning_rate": 1.2458522599674208e-05, "loss": 0.8146, "step": 7505 }, { "epoch": 0.43843457943925235, "grad_norm": 1.4998599290847778, "learning_rate": 1.2456688779504353e-05, "loss": 0.9109, "step": 7506 }, { "epoch": 0.4384929906542056, "grad_norm": 1.8919597864151, "learning_rate": 1.2454854871407993e-05, "loss": 0.9485, "step": 7507 }, { "epoch": 0.43855140186915886, "grad_norm": 1.0639021396636963, "learning_rate": 1.2453020875450763e-05, "loss": 0.7278, "step": 7508 }, { "epoch": 0.4386098130841122, "grad_norm": 1.109589695930481, "learning_rate": 1.2451186791698304e-05, "loss": 0.84, "step": 7509 }, { "epoch": 0.43866822429906543, "grad_norm": 1.8191499710083008, "learning_rate": 1.2449352620216254e-05, "loss": 0.8406, "step": 7510 }, { "epoch": 0.4387266355140187, "grad_norm": 1.2610244750976562, "learning_rate": 1.2447518361070265e-05, "loss": 0.8621, "step": 7511 }, { "epoch": 0.43878504672897195, "grad_norm": 1.4411523342132568, "learning_rate": 1.2445684014325986e-05, "loss": 0.769, "step": 7512 }, { "epoch": 0.4388434579439252, "grad_norm": 1.154054045677185, "learning_rate": 1.2443849580049067e-05, "loss": 0.7305, "step": 7513 }, { "epoch": 0.4389018691588785, "grad_norm": 2.283626079559326, "learning_rate": 1.2442015058305167e-05, "loss": 1.0588, "step": 7514 }, { "epoch": 0.4389602803738318, "grad_norm": 1.0895864963531494, "learning_rate": 1.244018044915994e-05, "loss": 0.7292, "step": 7515 }, { "epoch": 0.43901869158878504, "grad_norm": 1.3544049263000488, "learning_rate": 1.2438345752679051e-05, "loss": 0.7875, "step": 7516 }, { "epoch": 0.4390771028037383, "grad_norm": 1.3696374893188477, "learning_rate": 1.2436510968928165e-05, "loss": 0.7137, "step": 7517 }, { "epoch": 0.4391355140186916, "grad_norm": 1.557594895362854, "learning_rate": 1.243467609797295e-05, "loss": 1.0422, "step": 7518 }, { "epoch": 0.43919392523364487, "grad_norm": 1.5803279876708984, "learning_rate": 1.2432841139879073e-05, "loss": 0.7469, "step": 7519 }, { "epoch": 0.4392523364485981, "grad_norm": 1.521587610244751, "learning_rate": 1.2431006094712215e-05, "loss": 0.7231, "step": 7520 }, { "epoch": 0.4393107476635514, "grad_norm": 2.1405816078186035, "learning_rate": 1.2429170962538047e-05, "loss": 0.9417, "step": 7521 }, { "epoch": 0.4393691588785047, "grad_norm": 1.2867473363876343, "learning_rate": 1.2427335743422257e-05, "loss": 0.7933, "step": 7522 }, { "epoch": 0.43942757009345795, "grad_norm": 2.4366931915283203, "learning_rate": 1.2425500437430523e-05, "loss": 0.8971, "step": 7523 }, { "epoch": 0.4394859813084112, "grad_norm": 1.4617804288864136, "learning_rate": 1.2423665044628535e-05, "loss": 0.8684, "step": 7524 }, { "epoch": 0.43954439252336447, "grad_norm": 1.2659937143325806, "learning_rate": 1.2421829565081979e-05, "loss": 0.6534, "step": 7525 }, { "epoch": 0.4396028037383178, "grad_norm": 1.5046048164367676, "learning_rate": 1.2419993998856553e-05, "loss": 0.7416, "step": 7526 }, { "epoch": 0.43966121495327104, "grad_norm": 1.8002660274505615, "learning_rate": 1.241815834601795e-05, "loss": 0.7078, "step": 7527 }, { "epoch": 0.4397196261682243, "grad_norm": 1.7492696046829224, "learning_rate": 1.241632260663187e-05, "loss": 0.8078, "step": 7528 }, { "epoch": 0.43977803738317756, "grad_norm": 1.7097444534301758, "learning_rate": 1.2414486780764013e-05, "loss": 0.7667, "step": 7529 }, { "epoch": 0.4398364485981308, "grad_norm": 1.5886642932891846, "learning_rate": 1.2412650868480088e-05, "loss": 0.8986, "step": 7530 }, { "epoch": 0.4398948598130841, "grad_norm": 1.4190504550933838, "learning_rate": 1.2410814869845803e-05, "loss": 1.0017, "step": 7531 }, { "epoch": 0.4399532710280374, "grad_norm": 1.2181580066680908, "learning_rate": 1.2408978784926866e-05, "loss": 0.6385, "step": 7532 }, { "epoch": 0.44001168224299064, "grad_norm": 1.244179606437683, "learning_rate": 1.2407142613788996e-05, "loss": 0.6183, "step": 7533 }, { "epoch": 0.4400700934579439, "grad_norm": 1.0421791076660156, "learning_rate": 1.240530635649791e-05, "loss": 0.8835, "step": 7534 }, { "epoch": 0.4401285046728972, "grad_norm": 1.2732290029525757, "learning_rate": 1.2403470013119326e-05, "loss": 0.9331, "step": 7535 }, { "epoch": 0.44018691588785047, "grad_norm": 1.32803213596344, "learning_rate": 1.2401633583718973e-05, "loss": 0.767, "step": 7536 }, { "epoch": 0.44024532710280373, "grad_norm": 1.344342827796936, "learning_rate": 1.2399797068362572e-05, "loss": 1.0266, "step": 7537 }, { "epoch": 0.440303738317757, "grad_norm": 1.3550797700881958, "learning_rate": 1.2397960467115858e-05, "loss": 0.7288, "step": 7538 }, { "epoch": 0.4403621495327103, "grad_norm": 1.0932872295379639, "learning_rate": 1.239612378004456e-05, "loss": 0.629, "step": 7539 }, { "epoch": 0.44042056074766356, "grad_norm": 1.21235191822052, "learning_rate": 1.2394287007214415e-05, "loss": 0.6917, "step": 7540 }, { "epoch": 0.4404789719626168, "grad_norm": 1.1243276596069336, "learning_rate": 1.239245014869117e-05, "loss": 0.7238, "step": 7541 }, { "epoch": 0.4405373831775701, "grad_norm": 1.0519654750823975, "learning_rate": 1.2390613204540557e-05, "loss": 0.6857, "step": 7542 }, { "epoch": 0.4405957943925234, "grad_norm": 1.4688005447387695, "learning_rate": 1.2388776174828325e-05, "loss": 0.7362, "step": 7543 }, { "epoch": 0.44065420560747665, "grad_norm": 1.1348791122436523, "learning_rate": 1.2386939059620225e-05, "loss": 0.8338, "step": 7544 }, { "epoch": 0.4407126168224299, "grad_norm": 3.067042589187622, "learning_rate": 1.2385101858982004e-05, "loss": 0.7559, "step": 7545 }, { "epoch": 0.44077102803738316, "grad_norm": 1.541517734527588, "learning_rate": 1.2383264572979424e-05, "loss": 0.7405, "step": 7546 }, { "epoch": 0.4408294392523365, "grad_norm": 1.5245870351791382, "learning_rate": 1.2381427201678233e-05, "loss": 0.8801, "step": 7547 }, { "epoch": 0.44088785046728973, "grad_norm": 1.240593671798706, "learning_rate": 1.2379589745144198e-05, "loss": 0.7482, "step": 7548 }, { "epoch": 0.440946261682243, "grad_norm": 1.137313961982727, "learning_rate": 1.2377752203443083e-05, "loss": 0.8419, "step": 7549 }, { "epoch": 0.44100467289719625, "grad_norm": 1.550986647605896, "learning_rate": 1.2375914576640652e-05, "loss": 0.7036, "step": 7550 }, { "epoch": 0.4410630841121495, "grad_norm": 1.0324125289916992, "learning_rate": 1.2374076864802675e-05, "loss": 0.6194, "step": 7551 }, { "epoch": 0.4411214953271028, "grad_norm": 1.8759655952453613, "learning_rate": 1.237223906799493e-05, "loss": 0.6989, "step": 7552 }, { "epoch": 0.4411799065420561, "grad_norm": 1.4601624011993408, "learning_rate": 1.2370401186283186e-05, "loss": 0.8419, "step": 7553 }, { "epoch": 0.44123831775700934, "grad_norm": 1.4528241157531738, "learning_rate": 1.2368563219733222e-05, "loss": 0.9214, "step": 7554 }, { "epoch": 0.4412967289719626, "grad_norm": 1.2169338464736938, "learning_rate": 1.2366725168410829e-05, "loss": 0.7184, "step": 7555 }, { "epoch": 0.4413551401869159, "grad_norm": 1.1810318231582642, "learning_rate": 1.2364887032381782e-05, "loss": 0.767, "step": 7556 }, { "epoch": 0.44141355140186916, "grad_norm": 1.6249983310699463, "learning_rate": 1.2363048811711875e-05, "loss": 0.9492, "step": 7557 }, { "epoch": 0.4414719626168224, "grad_norm": 0.9361751675605774, "learning_rate": 1.2361210506466897e-05, "loss": 0.894, "step": 7558 }, { "epoch": 0.4415303738317757, "grad_norm": 1.8832955360412598, "learning_rate": 1.235937211671264e-05, "loss": 0.9296, "step": 7559 }, { "epoch": 0.441588785046729, "grad_norm": 1.5445257425308228, "learning_rate": 1.235753364251491e-05, "loss": 0.8637, "step": 7560 }, { "epoch": 0.44164719626168225, "grad_norm": 1.7638696432113647, "learning_rate": 1.2355695083939497e-05, "loss": 0.7567, "step": 7561 }, { "epoch": 0.4417056074766355, "grad_norm": 1.356215000152588, "learning_rate": 1.2353856441052204e-05, "loss": 0.7563, "step": 7562 }, { "epoch": 0.44176401869158877, "grad_norm": 1.1235121488571167, "learning_rate": 1.2352017713918848e-05, "loss": 0.9405, "step": 7563 }, { "epoch": 0.4418224299065421, "grad_norm": 1.3424416780471802, "learning_rate": 1.2350178902605228e-05, "loss": 0.8297, "step": 7564 }, { "epoch": 0.44188084112149534, "grad_norm": 1.7939871549606323, "learning_rate": 1.234834000717716e-05, "loss": 0.9528, "step": 7565 }, { "epoch": 0.4419392523364486, "grad_norm": 2.484501600265503, "learning_rate": 1.234650102770046e-05, "loss": 0.8223, "step": 7566 }, { "epoch": 0.44199766355140185, "grad_norm": 1.8146668672561646, "learning_rate": 1.2344661964240946e-05, "loss": 0.9232, "step": 7567 }, { "epoch": 0.44205607476635517, "grad_norm": 2.8341972827911377, "learning_rate": 1.2342822816864436e-05, "loss": 0.8952, "step": 7568 }, { "epoch": 0.4421144859813084, "grad_norm": 1.2514135837554932, "learning_rate": 1.2340983585636756e-05, "loss": 0.9731, "step": 7569 }, { "epoch": 0.4421728971962617, "grad_norm": 1.535917043685913, "learning_rate": 1.2339144270623737e-05, "loss": 0.9025, "step": 7570 }, { "epoch": 0.44223130841121494, "grad_norm": 1.4129260778427124, "learning_rate": 1.2337304871891207e-05, "loss": 0.9092, "step": 7571 }, { "epoch": 0.4422897196261682, "grad_norm": 1.1960368156433105, "learning_rate": 1.2335465389504999e-05, "loss": 0.6981, "step": 7572 }, { "epoch": 0.4423481308411215, "grad_norm": 1.4889090061187744, "learning_rate": 1.2333625823530946e-05, "loss": 0.9731, "step": 7573 }, { "epoch": 0.44240654205607477, "grad_norm": 2.1319713592529297, "learning_rate": 1.2331786174034892e-05, "loss": 0.8984, "step": 7574 }, { "epoch": 0.442464953271028, "grad_norm": 1.392475962638855, "learning_rate": 1.2329946441082681e-05, "loss": 0.8256, "step": 7575 }, { "epoch": 0.4425233644859813, "grad_norm": 1.4402130842208862, "learning_rate": 1.2328106624740151e-05, "loss": 0.6789, "step": 7576 }, { "epoch": 0.4425817757009346, "grad_norm": 2.1556036472320557, "learning_rate": 1.2326266725073155e-05, "loss": 0.9634, "step": 7577 }, { "epoch": 0.44264018691588786, "grad_norm": 1.1320432424545288, "learning_rate": 1.2324426742147544e-05, "loss": 0.6409, "step": 7578 }, { "epoch": 0.4426985981308411, "grad_norm": 2.7970855236053467, "learning_rate": 1.2322586676029168e-05, "loss": 0.9204, "step": 7579 }, { "epoch": 0.4427570093457944, "grad_norm": 1.1921939849853516, "learning_rate": 1.2320746526783896e-05, "loss": 0.8938, "step": 7580 }, { "epoch": 0.4428154205607477, "grad_norm": 1.3236862421035767, "learning_rate": 1.231890629447757e-05, "loss": 0.8643, "step": 7581 }, { "epoch": 0.44287383177570094, "grad_norm": 2.3922972679138184, "learning_rate": 1.2317065979176069e-05, "loss": 0.9139, "step": 7582 }, { "epoch": 0.4429322429906542, "grad_norm": 1.0604668855667114, "learning_rate": 1.2315225580945252e-05, "loss": 0.7578, "step": 7583 }, { "epoch": 0.44299065420560746, "grad_norm": 2.0719082355499268, "learning_rate": 1.231338509985099e-05, "loss": 0.7707, "step": 7584 }, { "epoch": 0.4430490654205608, "grad_norm": 2.0283286571502686, "learning_rate": 1.2311544535959153e-05, "loss": 0.7611, "step": 7585 }, { "epoch": 0.44310747663551403, "grad_norm": 2.163665294647217, "learning_rate": 1.2309703889335617e-05, "loss": 0.8877, "step": 7586 }, { "epoch": 0.4431658878504673, "grad_norm": 1.80801522731781, "learning_rate": 1.230786316004626e-05, "loss": 0.8172, "step": 7587 }, { "epoch": 0.44322429906542055, "grad_norm": 1.5377683639526367, "learning_rate": 1.2306022348156963e-05, "loss": 0.7465, "step": 7588 }, { "epoch": 0.44328271028037386, "grad_norm": 1.5658334493637085, "learning_rate": 1.2304181453733613e-05, "loss": 0.9468, "step": 7589 }, { "epoch": 0.4433411214953271, "grad_norm": 1.1269651651382446, "learning_rate": 1.230234047684209e-05, "loss": 0.9127, "step": 7590 }, { "epoch": 0.4433995327102804, "grad_norm": 2.0986111164093018, "learning_rate": 1.2300499417548289e-05, "loss": 0.9782, "step": 7591 }, { "epoch": 0.44345794392523363, "grad_norm": 1.2564749717712402, "learning_rate": 1.22986582759181e-05, "loss": 0.9631, "step": 7592 }, { "epoch": 0.4435163551401869, "grad_norm": 1.347561001777649, "learning_rate": 1.229681705201742e-05, "loss": 0.7796, "step": 7593 }, { "epoch": 0.4435747663551402, "grad_norm": 1.3948136568069458, "learning_rate": 1.2294975745912152e-05, "loss": 0.8207, "step": 7594 }, { "epoch": 0.44363317757009346, "grad_norm": 1.20103120803833, "learning_rate": 1.2293134357668185e-05, "loss": 0.7773, "step": 7595 }, { "epoch": 0.4436915887850467, "grad_norm": 1.2362086772918701, "learning_rate": 1.2291292887351438e-05, "loss": 0.9283, "step": 7596 }, { "epoch": 0.44375, "grad_norm": 1.6489049196243286, "learning_rate": 1.2289451335027811e-05, "loss": 0.904, "step": 7597 }, { "epoch": 0.4438084112149533, "grad_norm": 1.1215016841888428, "learning_rate": 1.2287609700763212e-05, "loss": 0.7151, "step": 7598 }, { "epoch": 0.44386682242990655, "grad_norm": 1.9032069444656372, "learning_rate": 1.2285767984623563e-05, "loss": 0.9148, "step": 7599 }, { "epoch": 0.4439252336448598, "grad_norm": 1.1004559993743896, "learning_rate": 1.2283926186674773e-05, "loss": 0.8457, "step": 7600 }, { "epoch": 0.44398364485981306, "grad_norm": 1.0530809164047241, "learning_rate": 1.228208430698276e-05, "loss": 1.0795, "step": 7601 }, { "epoch": 0.4440420560747664, "grad_norm": 2.0106587409973145, "learning_rate": 1.228024234561345e-05, "loss": 0.8034, "step": 7602 }, { "epoch": 0.44410046728971964, "grad_norm": 0.8564778566360474, "learning_rate": 1.2278400302632769e-05, "loss": 0.7453, "step": 7603 }, { "epoch": 0.4441588785046729, "grad_norm": 1.0581541061401367, "learning_rate": 1.2276558178106643e-05, "loss": 0.6954, "step": 7604 }, { "epoch": 0.44421728971962615, "grad_norm": 1.521486759185791, "learning_rate": 1.2274715972101003e-05, "loss": 0.7776, "step": 7605 }, { "epoch": 0.44427570093457946, "grad_norm": 1.2508432865142822, "learning_rate": 1.2272873684681782e-05, "loss": 0.6732, "step": 7606 }, { "epoch": 0.4443341121495327, "grad_norm": 1.2807867527008057, "learning_rate": 1.2271031315914917e-05, "loss": 0.9051, "step": 7607 }, { "epoch": 0.444392523364486, "grad_norm": 1.8848309516906738, "learning_rate": 1.2269188865866349e-05, "loss": 0.8223, "step": 7608 }, { "epoch": 0.44445093457943924, "grad_norm": 1.687212586402893, "learning_rate": 1.226734633460202e-05, "loss": 0.8473, "step": 7609 }, { "epoch": 0.4445093457943925, "grad_norm": 1.654923915863037, "learning_rate": 1.2265503722187875e-05, "loss": 0.8451, "step": 7610 }, { "epoch": 0.4445677570093458, "grad_norm": 1.5941721200942993, "learning_rate": 1.2263661028689859e-05, "loss": 0.8895, "step": 7611 }, { "epoch": 0.44462616822429907, "grad_norm": 1.186187744140625, "learning_rate": 1.2261818254173928e-05, "loss": 0.7032, "step": 7612 }, { "epoch": 0.4446845794392523, "grad_norm": 2.0993618965148926, "learning_rate": 1.2259975398706036e-05, "loss": 1.0545, "step": 7613 }, { "epoch": 0.4447429906542056, "grad_norm": 1.5097401142120361, "learning_rate": 1.2258132462352138e-05, "loss": 0.7554, "step": 7614 }, { "epoch": 0.4448014018691589, "grad_norm": 1.2128559350967407, "learning_rate": 1.2256289445178194e-05, "loss": 0.7021, "step": 7615 }, { "epoch": 0.44485981308411215, "grad_norm": 1.9023090600967407, "learning_rate": 1.2254446347250166e-05, "loss": 1.0475, "step": 7616 }, { "epoch": 0.4449182242990654, "grad_norm": 3.2036807537078857, "learning_rate": 1.2252603168634021e-05, "loss": 0.7274, "step": 7617 }, { "epoch": 0.44497663551401867, "grad_norm": 1.392080307006836, "learning_rate": 1.225075990939573e-05, "loss": 0.8324, "step": 7618 }, { "epoch": 0.445035046728972, "grad_norm": 1.4983941316604614, "learning_rate": 1.2248916569601262e-05, "loss": 0.7414, "step": 7619 }, { "epoch": 0.44509345794392524, "grad_norm": 1.5407953262329102, "learning_rate": 1.2247073149316587e-05, "loss": 0.7744, "step": 7620 }, { "epoch": 0.4451518691588785, "grad_norm": 1.8567017316818237, "learning_rate": 1.224522964860769e-05, "loss": 0.749, "step": 7621 }, { "epoch": 0.44521028037383176, "grad_norm": 1.6907211542129517, "learning_rate": 1.2243386067540548e-05, "loss": 0.8265, "step": 7622 }, { "epoch": 0.44526869158878507, "grad_norm": 1.4969598054885864, "learning_rate": 1.2241542406181141e-05, "loss": 0.784, "step": 7623 }, { "epoch": 0.44532710280373833, "grad_norm": 1.4825608730316162, "learning_rate": 1.2239698664595461e-05, "loss": 0.9204, "step": 7624 }, { "epoch": 0.4453855140186916, "grad_norm": 1.0961296558380127, "learning_rate": 1.2237854842849488e-05, "loss": 0.7374, "step": 7625 }, { "epoch": 0.44544392523364484, "grad_norm": 1.1480273008346558, "learning_rate": 1.2236010941009222e-05, "loss": 0.8216, "step": 7626 }, { "epoch": 0.44550233644859816, "grad_norm": 3.161864995956421, "learning_rate": 1.2234166959140654e-05, "loss": 0.957, "step": 7627 }, { "epoch": 0.4455607476635514, "grad_norm": 1.0792688131332397, "learning_rate": 1.2232322897309784e-05, "loss": 0.5722, "step": 7628 }, { "epoch": 0.4456191588785047, "grad_norm": 1.788050889968872, "learning_rate": 1.2230478755582607e-05, "loss": 0.8447, "step": 7629 }, { "epoch": 0.44567757009345793, "grad_norm": 1.2390334606170654, "learning_rate": 1.2228634534025128e-05, "loss": 0.7332, "step": 7630 }, { "epoch": 0.4457359813084112, "grad_norm": 1.5694152116775513, "learning_rate": 1.2226790232703355e-05, "loss": 0.7932, "step": 7631 }, { "epoch": 0.4457943925233645, "grad_norm": 1.4598296880722046, "learning_rate": 1.2224945851683294e-05, "loss": 0.6378, "step": 7632 }, { "epoch": 0.44585280373831776, "grad_norm": 1.0853118896484375, "learning_rate": 1.222310139103096e-05, "loss": 0.7155, "step": 7633 }, { "epoch": 0.445911214953271, "grad_norm": 4.055160999298096, "learning_rate": 1.2221256850812365e-05, "loss": 0.813, "step": 7634 }, { "epoch": 0.4459696261682243, "grad_norm": 1.328769564628601, "learning_rate": 1.2219412231093525e-05, "loss": 0.6887, "step": 7635 }, { "epoch": 0.4460280373831776, "grad_norm": 1.5169681310653687, "learning_rate": 1.2217567531940465e-05, "loss": 0.8343, "step": 7636 }, { "epoch": 0.44608644859813085, "grad_norm": 1.6375112533569336, "learning_rate": 1.2215722753419202e-05, "loss": 0.7356, "step": 7637 }, { "epoch": 0.4461448598130841, "grad_norm": 1.8415199518203735, "learning_rate": 1.2213877895595769e-05, "loss": 1.0177, "step": 7638 }, { "epoch": 0.44620327102803736, "grad_norm": 0.9603798985481262, "learning_rate": 1.2212032958536183e-05, "loss": 0.6697, "step": 7639 }, { "epoch": 0.4462616822429907, "grad_norm": 2.0146162509918213, "learning_rate": 1.2210187942306491e-05, "loss": 0.8259, "step": 7640 }, { "epoch": 0.44632009345794393, "grad_norm": 1.371583342552185, "learning_rate": 1.2208342846972716e-05, "loss": 0.8119, "step": 7641 }, { "epoch": 0.4463785046728972, "grad_norm": 1.6000862121582031, "learning_rate": 1.2206497672600899e-05, "loss": 0.9262, "step": 7642 }, { "epoch": 0.44643691588785045, "grad_norm": 2.074779987335205, "learning_rate": 1.220465241925708e-05, "loss": 0.8713, "step": 7643 }, { "epoch": 0.44649532710280376, "grad_norm": 1.2061327695846558, "learning_rate": 1.2202807087007301e-05, "loss": 0.8, "step": 7644 }, { "epoch": 0.446553738317757, "grad_norm": 3.2882583141326904, "learning_rate": 1.2200961675917605e-05, "loss": 0.9779, "step": 7645 }, { "epoch": 0.4466121495327103, "grad_norm": 2.01973557472229, "learning_rate": 1.2199116186054045e-05, "loss": 0.9274, "step": 7646 }, { "epoch": 0.44667056074766354, "grad_norm": 3.630223512649536, "learning_rate": 1.219727061748267e-05, "loss": 0.9234, "step": 7647 }, { "epoch": 0.44672897196261685, "grad_norm": 1.691185474395752, "learning_rate": 1.2195424970269538e-05, "loss": 0.9847, "step": 7648 }, { "epoch": 0.4467873831775701, "grad_norm": 3.258314847946167, "learning_rate": 1.2193579244480702e-05, "loss": 0.9026, "step": 7649 }, { "epoch": 0.44684579439252337, "grad_norm": 1.8900394439697266, "learning_rate": 1.2191733440182219e-05, "loss": 0.7396, "step": 7650 }, { "epoch": 0.4469042056074766, "grad_norm": 1.624751329421997, "learning_rate": 1.218988755744016e-05, "loss": 0.959, "step": 7651 }, { "epoch": 0.4469626168224299, "grad_norm": 1.1412733793258667, "learning_rate": 1.2188041596320583e-05, "loss": 0.9125, "step": 7652 }, { "epoch": 0.4470210280373832, "grad_norm": 0.8551326990127563, "learning_rate": 1.2186195556889558e-05, "loss": 0.6404, "step": 7653 }, { "epoch": 0.44707943925233645, "grad_norm": 2.004673719406128, "learning_rate": 1.2184349439213157e-05, "loss": 0.9535, "step": 7654 }, { "epoch": 0.4471378504672897, "grad_norm": 1.5209996700286865, "learning_rate": 1.2182503243357455e-05, "loss": 0.8593, "step": 7655 }, { "epoch": 0.44719626168224297, "grad_norm": 1.4482909440994263, "learning_rate": 1.2180656969388523e-05, "loss": 0.8039, "step": 7656 }, { "epoch": 0.4472546728971963, "grad_norm": 2.0454771518707275, "learning_rate": 1.2178810617372449e-05, "loss": 0.8903, "step": 7657 }, { "epoch": 0.44731308411214954, "grad_norm": 1.4955836534500122, "learning_rate": 1.2176964187375306e-05, "loss": 0.8411, "step": 7658 }, { "epoch": 0.4473714953271028, "grad_norm": 1.746269941329956, "learning_rate": 1.2175117679463187e-05, "loss": 0.7944, "step": 7659 }, { "epoch": 0.44742990654205606, "grad_norm": 1.9974803924560547, "learning_rate": 1.2173271093702174e-05, "loss": 0.8279, "step": 7660 }, { "epoch": 0.44748831775700937, "grad_norm": 1.672743797302246, "learning_rate": 1.2171424430158361e-05, "loss": 0.6637, "step": 7661 }, { "epoch": 0.4475467289719626, "grad_norm": 1.861889362335205, "learning_rate": 1.216957768889784e-05, "loss": 0.988, "step": 7662 }, { "epoch": 0.4476051401869159, "grad_norm": 1.907555341720581, "learning_rate": 1.2167730869986707e-05, "loss": 0.7391, "step": 7663 }, { "epoch": 0.44766355140186914, "grad_norm": 1.9696152210235596, "learning_rate": 1.2165883973491056e-05, "loss": 0.8569, "step": 7664 }, { "epoch": 0.44772196261682246, "grad_norm": 1.9006052017211914, "learning_rate": 1.2164036999477e-05, "loss": 0.818, "step": 7665 }, { "epoch": 0.4477803738317757, "grad_norm": 1.7035237550735474, "learning_rate": 1.2162189948010633e-05, "loss": 0.7052, "step": 7666 }, { "epoch": 0.44783878504672897, "grad_norm": 1.5723696947097778, "learning_rate": 1.2160342819158068e-05, "loss": 0.9193, "step": 7667 }, { "epoch": 0.44789719626168223, "grad_norm": 1.8544881343841553, "learning_rate": 1.2158495612985415e-05, "loss": 0.7257, "step": 7668 }, { "epoch": 0.4479556074766355, "grad_norm": 0.9722537994384766, "learning_rate": 1.2156648329558783e-05, "loss": 0.6802, "step": 7669 }, { "epoch": 0.4480140186915888, "grad_norm": 1.5634466409683228, "learning_rate": 1.2154800968944284e-05, "loss": 0.922, "step": 7670 }, { "epoch": 0.44807242990654206, "grad_norm": 0.9409656524658203, "learning_rate": 1.215295353120805e-05, "loss": 0.6108, "step": 7671 }, { "epoch": 0.4481308411214953, "grad_norm": 1.4353747367858887, "learning_rate": 1.2151106016416187e-05, "loss": 0.9563, "step": 7672 }, { "epoch": 0.4481892523364486, "grad_norm": 1.0914397239685059, "learning_rate": 1.2149258424634829e-05, "loss": 0.8373, "step": 7673 }, { "epoch": 0.4482476635514019, "grad_norm": 1.7562299966812134, "learning_rate": 1.2147410755930097e-05, "loss": 0.8545, "step": 7674 }, { "epoch": 0.44830607476635514, "grad_norm": 1.438489317893982, "learning_rate": 1.2145563010368122e-05, "loss": 1.0799, "step": 7675 }, { "epoch": 0.4483644859813084, "grad_norm": 1.1552603244781494, "learning_rate": 1.2143715188015039e-05, "loss": 0.7745, "step": 7676 }, { "epoch": 0.44842289719626166, "grad_norm": 1.5140392780303955, "learning_rate": 1.214186728893698e-05, "loss": 0.8313, "step": 7677 }, { "epoch": 0.448481308411215, "grad_norm": 1.346234917640686, "learning_rate": 1.2140019313200078e-05, "loss": 0.9744, "step": 7678 }, { "epoch": 0.44853971962616823, "grad_norm": 1.04249107837677, "learning_rate": 1.213817126087048e-05, "loss": 0.7595, "step": 7679 }, { "epoch": 0.4485981308411215, "grad_norm": 1.789021372795105, "learning_rate": 1.2136323132014327e-05, "loss": 0.8671, "step": 7680 }, { "epoch": 0.44865654205607475, "grad_norm": 1.8299202919006348, "learning_rate": 1.2134474926697764e-05, "loss": 0.7245, "step": 7681 }, { "epoch": 0.44871495327102806, "grad_norm": 1.376866340637207, "learning_rate": 1.213262664498694e-05, "loss": 0.921, "step": 7682 }, { "epoch": 0.4487733644859813, "grad_norm": 1.804828405380249, "learning_rate": 1.2130778286948004e-05, "loss": 0.6715, "step": 7683 }, { "epoch": 0.4488317757009346, "grad_norm": 1.439928412437439, "learning_rate": 1.2128929852647115e-05, "loss": 0.8082, "step": 7684 }, { "epoch": 0.44889018691588783, "grad_norm": 1.8086520433425903, "learning_rate": 1.2127081342150427e-05, "loss": 0.8445, "step": 7685 }, { "epoch": 0.44894859813084115, "grad_norm": 1.1653236150741577, "learning_rate": 1.2125232755524098e-05, "loss": 0.8069, "step": 7686 }, { "epoch": 0.4490070093457944, "grad_norm": 1.1248712539672852, "learning_rate": 1.2123384092834292e-05, "loss": 0.7383, "step": 7687 }, { "epoch": 0.44906542056074766, "grad_norm": 0.9876068234443665, "learning_rate": 1.2121535354147174e-05, "loss": 0.6217, "step": 7688 }, { "epoch": 0.4491238317757009, "grad_norm": 1.0334184169769287, "learning_rate": 1.2119686539528908e-05, "loss": 0.727, "step": 7689 }, { "epoch": 0.4491822429906542, "grad_norm": 1.0373139381408691, "learning_rate": 1.2117837649045668e-05, "loss": 0.7799, "step": 7690 }, { "epoch": 0.4492406542056075, "grad_norm": 1.2999340295791626, "learning_rate": 1.2115988682763626e-05, "loss": 0.8078, "step": 7691 }, { "epoch": 0.44929906542056075, "grad_norm": 1.9330755472183228, "learning_rate": 1.2114139640748959e-05, "loss": 0.8454, "step": 7692 }, { "epoch": 0.449357476635514, "grad_norm": 0.9908627271652222, "learning_rate": 1.2112290523067844e-05, "loss": 0.7916, "step": 7693 }, { "epoch": 0.44941588785046727, "grad_norm": 1.6606082916259766, "learning_rate": 1.2110441329786461e-05, "loss": 0.8842, "step": 7694 }, { "epoch": 0.4494742990654206, "grad_norm": 1.6881217956542969, "learning_rate": 1.2108592060970996e-05, "loss": 0.7582, "step": 7695 }, { "epoch": 0.44953271028037384, "grad_norm": 1.545859456062317, "learning_rate": 1.2106742716687637e-05, "loss": 0.7127, "step": 7696 }, { "epoch": 0.4495911214953271, "grad_norm": 1.1529943943023682, "learning_rate": 1.2104893297002566e-05, "loss": 0.8151, "step": 7697 }, { "epoch": 0.44964953271028035, "grad_norm": 1.8377394676208496, "learning_rate": 1.2103043801981982e-05, "loss": 0.7953, "step": 7698 }, { "epoch": 0.44970794392523367, "grad_norm": 1.1982066631317139, "learning_rate": 1.2101194231692079e-05, "loss": 0.7201, "step": 7699 }, { "epoch": 0.4497663551401869, "grad_norm": 1.3231278657913208, "learning_rate": 1.2099344586199053e-05, "loss": 0.8706, "step": 7700 }, { "epoch": 0.4498247663551402, "grad_norm": 2.0221192836761475, "learning_rate": 1.2097494865569104e-05, "loss": 0.9518, "step": 7701 }, { "epoch": 0.44988317757009344, "grad_norm": 1.2724136114120483, "learning_rate": 1.2095645069868434e-05, "loss": 0.7704, "step": 7702 }, { "epoch": 0.44994158878504675, "grad_norm": 1.348541021347046, "learning_rate": 1.2093795199163245e-05, "loss": 0.5781, "step": 7703 }, { "epoch": 0.45, "grad_norm": 2.576589345932007, "learning_rate": 1.2091945253519755e-05, "loss": 0.9206, "step": 7704 }, { "epoch": 0.45005841121495327, "grad_norm": 1.1365910768508911, "learning_rate": 1.2090095233004164e-05, "loss": 0.8284, "step": 7705 }, { "epoch": 0.4501168224299065, "grad_norm": 3.0817320346832275, "learning_rate": 1.2088245137682695e-05, "loss": 0.7289, "step": 7706 }, { "epoch": 0.45017523364485984, "grad_norm": 1.5442339181900024, "learning_rate": 1.2086394967621557e-05, "loss": 0.7153, "step": 7707 }, { "epoch": 0.4502336448598131, "grad_norm": 1.4862985610961914, "learning_rate": 1.208454472288697e-05, "loss": 0.7797, "step": 7708 }, { "epoch": 0.45029205607476636, "grad_norm": 1.7847270965576172, "learning_rate": 1.2082694403545159e-05, "loss": 0.9372, "step": 7709 }, { "epoch": 0.4503504672897196, "grad_norm": 2.462141990661621, "learning_rate": 1.2080844009662347e-05, "loss": 0.9517, "step": 7710 }, { "epoch": 0.45040887850467287, "grad_norm": 1.0451966524124146, "learning_rate": 1.2078993541304758e-05, "loss": 0.737, "step": 7711 }, { "epoch": 0.4504672897196262, "grad_norm": 2.8267781734466553, "learning_rate": 1.2077142998538622e-05, "loss": 0.8009, "step": 7712 }, { "epoch": 0.45052570093457944, "grad_norm": 1.4985374212265015, "learning_rate": 1.2075292381430175e-05, "loss": 1.0148, "step": 7713 }, { "epoch": 0.4505841121495327, "grad_norm": 2.1916847229003906, "learning_rate": 1.2073441690045647e-05, "loss": 0.8514, "step": 7714 }, { "epoch": 0.45064252336448596, "grad_norm": 2.3998055458068848, "learning_rate": 1.207159092445128e-05, "loss": 0.746, "step": 7715 }, { "epoch": 0.45070093457943927, "grad_norm": 1.4071204662322998, "learning_rate": 1.2069740084713307e-05, "loss": 0.8865, "step": 7716 }, { "epoch": 0.45075934579439253, "grad_norm": 1.3358336687088013, "learning_rate": 1.2067889170897979e-05, "loss": 0.664, "step": 7717 }, { "epoch": 0.4508177570093458, "grad_norm": 1.5070551633834839, "learning_rate": 1.2066038183071538e-05, "loss": 0.6752, "step": 7718 }, { "epoch": 0.45087616822429905, "grad_norm": 2.0924317836761475, "learning_rate": 1.2064187121300232e-05, "loss": 0.9597, "step": 7719 }, { "epoch": 0.45093457943925236, "grad_norm": 1.4140771627426147, "learning_rate": 1.2062335985650311e-05, "loss": 0.8254, "step": 7720 }, { "epoch": 0.4509929906542056, "grad_norm": 1.9445879459381104, "learning_rate": 1.2060484776188028e-05, "loss": 0.8247, "step": 7721 }, { "epoch": 0.4510514018691589, "grad_norm": 1.4172824621200562, "learning_rate": 1.2058633492979642e-05, "loss": 0.7347, "step": 7722 }, { "epoch": 0.45110981308411213, "grad_norm": 1.8207145929336548, "learning_rate": 1.2056782136091407e-05, "loss": 0.8021, "step": 7723 }, { "epoch": 0.45116822429906545, "grad_norm": 1.7288973331451416, "learning_rate": 1.205493070558959e-05, "loss": 0.7695, "step": 7724 }, { "epoch": 0.4512266355140187, "grad_norm": 1.5112791061401367, "learning_rate": 1.2053079201540452e-05, "loss": 0.7711, "step": 7725 }, { "epoch": 0.45128504672897196, "grad_norm": 1.5109221935272217, "learning_rate": 1.2051227624010258e-05, "loss": 0.8352, "step": 7726 }, { "epoch": 0.4513434579439252, "grad_norm": 1.241358757019043, "learning_rate": 1.204937597306528e-05, "loss": 0.8698, "step": 7727 }, { "epoch": 0.4514018691588785, "grad_norm": 1.6757701635360718, "learning_rate": 1.2047524248771784e-05, "loss": 0.7671, "step": 7728 }, { "epoch": 0.4514602803738318, "grad_norm": 2.252934694290161, "learning_rate": 1.2045672451196056e-05, "loss": 0.828, "step": 7729 }, { "epoch": 0.45151869158878505, "grad_norm": 1.7069984674453735, "learning_rate": 1.204382058040436e-05, "loss": 0.7536, "step": 7730 }, { "epoch": 0.4515771028037383, "grad_norm": 1.109544038772583, "learning_rate": 1.2041968636462984e-05, "loss": 0.7625, "step": 7731 }, { "epoch": 0.45163551401869156, "grad_norm": 2.1797611713409424, "learning_rate": 1.2040116619438207e-05, "loss": 0.8503, "step": 7732 }, { "epoch": 0.4516939252336449, "grad_norm": 1.011308193206787, "learning_rate": 1.2038264529396315e-05, "loss": 0.671, "step": 7733 }, { "epoch": 0.45175233644859814, "grad_norm": 1.671506643295288, "learning_rate": 1.2036412366403598e-05, "loss": 0.8347, "step": 7734 }, { "epoch": 0.4518107476635514, "grad_norm": 1.7703604698181152, "learning_rate": 1.2034560130526341e-05, "loss": 0.8096, "step": 7735 }, { "epoch": 0.45186915887850465, "grad_norm": 1.0203391313552856, "learning_rate": 1.2032707821830837e-05, "loss": 0.7326, "step": 7736 }, { "epoch": 0.45192757009345796, "grad_norm": 1.2542555332183838, "learning_rate": 1.2030855440383387e-05, "loss": 0.7572, "step": 7737 }, { "epoch": 0.4519859813084112, "grad_norm": 1.6879295110702515, "learning_rate": 1.2029002986250285e-05, "loss": 0.8317, "step": 7738 }, { "epoch": 0.4520443925233645, "grad_norm": 1.4787722826004028, "learning_rate": 1.2027150459497832e-05, "loss": 0.7447, "step": 7739 }, { "epoch": 0.45210280373831774, "grad_norm": 1.3069957494735718, "learning_rate": 1.202529786019233e-05, "loss": 0.8316, "step": 7740 }, { "epoch": 0.45216121495327105, "grad_norm": 1.3555545806884766, "learning_rate": 1.2023445188400084e-05, "loss": 0.8985, "step": 7741 }, { "epoch": 0.4522196261682243, "grad_norm": 1.4550788402557373, "learning_rate": 1.2021592444187406e-05, "loss": 0.8323, "step": 7742 }, { "epoch": 0.45227803738317757, "grad_norm": 1.4142533540725708, "learning_rate": 1.2019739627620608e-05, "loss": 0.8371, "step": 7743 }, { "epoch": 0.4523364485981308, "grad_norm": 1.957518458366394, "learning_rate": 1.2017886738765998e-05, "loss": 0.7965, "step": 7744 }, { "epoch": 0.45239485981308414, "grad_norm": 0.9339454770088196, "learning_rate": 1.2016033777689895e-05, "loss": 0.7525, "step": 7745 }, { "epoch": 0.4524532710280374, "grad_norm": 1.3579035997390747, "learning_rate": 1.2014180744458619e-05, "loss": 0.7051, "step": 7746 }, { "epoch": 0.45251168224299065, "grad_norm": 1.391140341758728, "learning_rate": 1.2012327639138488e-05, "loss": 0.8828, "step": 7747 }, { "epoch": 0.4525700934579439, "grad_norm": 1.1982229948043823, "learning_rate": 1.2010474461795827e-05, "loss": 0.7864, "step": 7748 }, { "epoch": 0.45262850467289717, "grad_norm": 2.7436187267303467, "learning_rate": 1.2008621212496964e-05, "loss": 0.9628, "step": 7749 }, { "epoch": 0.4526869158878505, "grad_norm": 1.413004755973816, "learning_rate": 1.2006767891308232e-05, "loss": 0.865, "step": 7750 }, { "epoch": 0.45274532710280374, "grad_norm": 2.015829086303711, "learning_rate": 1.2004914498295952e-05, "loss": 0.8951, "step": 7751 }, { "epoch": 0.452803738317757, "grad_norm": 1.250786304473877, "learning_rate": 1.2003061033526464e-05, "loss": 0.7496, "step": 7752 }, { "epoch": 0.45286214953271026, "grad_norm": 1.451573133468628, "learning_rate": 1.2001207497066107e-05, "loss": 0.7783, "step": 7753 }, { "epoch": 0.45292056074766357, "grad_norm": 1.6534395217895508, "learning_rate": 1.1999353888981218e-05, "loss": 0.7552, "step": 7754 }, { "epoch": 0.4529789719626168, "grad_norm": 1.4250601530075073, "learning_rate": 1.1997500209338135e-05, "loss": 0.8631, "step": 7755 }, { "epoch": 0.4530373831775701, "grad_norm": 1.1822751760482788, "learning_rate": 1.199564645820321e-05, "loss": 0.8084, "step": 7756 }, { "epoch": 0.45309579439252334, "grad_norm": 1.1157194375991821, "learning_rate": 1.1993792635642782e-05, "loss": 0.7626, "step": 7757 }, { "epoch": 0.45315420560747666, "grad_norm": 1.2312331199645996, "learning_rate": 1.1991938741723208e-05, "loss": 0.78, "step": 7758 }, { "epoch": 0.4532126168224299, "grad_norm": 1.2085223197937012, "learning_rate": 1.1990084776510838e-05, "loss": 0.6738, "step": 7759 }, { "epoch": 0.4532710280373832, "grad_norm": 1.3665820360183716, "learning_rate": 1.1988230740072022e-05, "loss": 0.7377, "step": 7760 }, { "epoch": 0.45332943925233643, "grad_norm": 1.5165103673934937, "learning_rate": 1.198637663247312e-05, "loss": 0.7806, "step": 7761 }, { "epoch": 0.45338785046728974, "grad_norm": 1.6224822998046875, "learning_rate": 1.1984522453780495e-05, "loss": 0.8413, "step": 7762 }, { "epoch": 0.453446261682243, "grad_norm": 1.5620441436767578, "learning_rate": 1.1982668204060505e-05, "loss": 0.9576, "step": 7763 }, { "epoch": 0.45350467289719626, "grad_norm": 2.1024177074432373, "learning_rate": 1.1980813883379518e-05, "loss": 0.8686, "step": 7764 }, { "epoch": 0.4535630841121495, "grad_norm": 1.3445792198181152, "learning_rate": 1.1978959491803898e-05, "loss": 0.7907, "step": 7765 }, { "epoch": 0.45362149532710283, "grad_norm": 1.2354387044906616, "learning_rate": 1.1977105029400015e-05, "loss": 0.8255, "step": 7766 }, { "epoch": 0.4536799065420561, "grad_norm": 1.799311876296997, "learning_rate": 1.1975250496234247e-05, "loss": 0.6789, "step": 7767 }, { "epoch": 0.45373831775700935, "grad_norm": 1.5786356925964355, "learning_rate": 1.1973395892372965e-05, "loss": 0.9213, "step": 7768 }, { "epoch": 0.4537967289719626, "grad_norm": 1.6298410892486572, "learning_rate": 1.1971541217882544e-05, "loss": 0.9038, "step": 7769 }, { "epoch": 0.45385514018691586, "grad_norm": 2.4969124794006348, "learning_rate": 1.1969686472829366e-05, "loss": 0.84, "step": 7770 }, { "epoch": 0.4539135514018692, "grad_norm": 1.1201941967010498, "learning_rate": 1.1967831657279816e-05, "loss": 0.8086, "step": 7771 }, { "epoch": 0.45397196261682243, "grad_norm": 3.398439407348633, "learning_rate": 1.1965976771300273e-05, "loss": 0.8358, "step": 7772 }, { "epoch": 0.4540303738317757, "grad_norm": 1.284101128578186, "learning_rate": 1.1964121814957136e-05, "loss": 0.8366, "step": 7773 }, { "epoch": 0.45408878504672895, "grad_norm": 2.562032461166382, "learning_rate": 1.1962266788316784e-05, "loss": 0.9178, "step": 7774 }, { "epoch": 0.45414719626168226, "grad_norm": 1.0633091926574707, "learning_rate": 1.1960411691445612e-05, "loss": 0.7237, "step": 7775 }, { "epoch": 0.4542056074766355, "grad_norm": 2.3833014965057373, "learning_rate": 1.195855652441002e-05, "loss": 0.8665, "step": 7776 }, { "epoch": 0.4542640186915888, "grad_norm": 1.2466002702713013, "learning_rate": 1.1956701287276397e-05, "loss": 0.6927, "step": 7777 }, { "epoch": 0.45432242990654204, "grad_norm": 2.3543269634246826, "learning_rate": 1.1954845980111153e-05, "loss": 0.7584, "step": 7778 }, { "epoch": 0.45438084112149535, "grad_norm": 1.5213550329208374, "learning_rate": 1.1952990602980685e-05, "loss": 0.799, "step": 7779 }, { "epoch": 0.4544392523364486, "grad_norm": 1.531679391860962, "learning_rate": 1.1951135155951397e-05, "loss": 0.9261, "step": 7780 }, { "epoch": 0.45449766355140186, "grad_norm": 1.9031076431274414, "learning_rate": 1.1949279639089701e-05, "loss": 0.743, "step": 7781 }, { "epoch": 0.4545560747663551, "grad_norm": 1.2161190509796143, "learning_rate": 1.1947424052462005e-05, "loss": 0.8416, "step": 7782 }, { "epoch": 0.45461448598130844, "grad_norm": 0.9041776657104492, "learning_rate": 1.1945568396134721e-05, "loss": 0.7413, "step": 7783 }, { "epoch": 0.4546728971962617, "grad_norm": 1.6305022239685059, "learning_rate": 1.1943712670174265e-05, "loss": 0.7948, "step": 7784 }, { "epoch": 0.45473130841121495, "grad_norm": 1.6009509563446045, "learning_rate": 1.1941856874647058e-05, "loss": 0.9806, "step": 7785 }, { "epoch": 0.4547897196261682, "grad_norm": 1.7736562490463257, "learning_rate": 1.1940001009619511e-05, "loss": 0.8991, "step": 7786 }, { "epoch": 0.4548481308411215, "grad_norm": 1.539228081703186, "learning_rate": 1.1938145075158057e-05, "loss": 1.0113, "step": 7787 }, { "epoch": 0.4549065420560748, "grad_norm": 1.1306376457214355, "learning_rate": 1.193628907132911e-05, "loss": 0.6661, "step": 7788 }, { "epoch": 0.45496495327102804, "grad_norm": 1.2273273468017578, "learning_rate": 1.193443299819911e-05, "loss": 0.7299, "step": 7789 }, { "epoch": 0.4550233644859813, "grad_norm": 1.299748420715332, "learning_rate": 1.193257685583448e-05, "loss": 0.9712, "step": 7790 }, { "epoch": 0.45508177570093455, "grad_norm": 0.8781351447105408, "learning_rate": 1.193072064430165e-05, "loss": 0.6976, "step": 7791 }, { "epoch": 0.45514018691588787, "grad_norm": 2.4343972206115723, "learning_rate": 1.1928864363667064e-05, "loss": 0.7865, "step": 7792 }, { "epoch": 0.4551985981308411, "grad_norm": 1.2043875455856323, "learning_rate": 1.1927008013997153e-05, "loss": 0.8143, "step": 7793 }, { "epoch": 0.4552570093457944, "grad_norm": 1.315030813217163, "learning_rate": 1.1925151595358352e-05, "loss": 0.9008, "step": 7794 }, { "epoch": 0.45531542056074764, "grad_norm": 0.9292242527008057, "learning_rate": 1.1923295107817117e-05, "loss": 0.7084, "step": 7795 }, { "epoch": 0.45537383177570095, "grad_norm": 1.0720036029815674, "learning_rate": 1.1921438551439883e-05, "loss": 0.7484, "step": 7796 }, { "epoch": 0.4554322429906542, "grad_norm": 1.042830467224121, "learning_rate": 1.19195819262931e-05, "loss": 0.8152, "step": 7797 }, { "epoch": 0.45549065420560747, "grad_norm": 1.218522548675537, "learning_rate": 1.1917725232443218e-05, "loss": 0.8061, "step": 7798 }, { "epoch": 0.45554906542056073, "grad_norm": 1.1851615905761719, "learning_rate": 1.1915868469956686e-05, "loss": 0.8246, "step": 7799 }, { "epoch": 0.45560747663551404, "grad_norm": 1.1063755750656128, "learning_rate": 1.1914011638899966e-05, "loss": 0.6192, "step": 7800 }, { "epoch": 0.4556658878504673, "grad_norm": 1.4166842699050903, "learning_rate": 1.1912154739339508e-05, "loss": 0.809, "step": 7801 }, { "epoch": 0.45572429906542056, "grad_norm": 1.5983283519744873, "learning_rate": 1.1910297771341777e-05, "loss": 0.7629, "step": 7802 }, { "epoch": 0.4557827102803738, "grad_norm": 0.9663062691688538, "learning_rate": 1.190844073497323e-05, "loss": 0.7162, "step": 7803 }, { "epoch": 0.45584112149532713, "grad_norm": 1.4677790403366089, "learning_rate": 1.1906583630300337e-05, "loss": 0.8568, "step": 7804 }, { "epoch": 0.4558995327102804, "grad_norm": 1.555975317955017, "learning_rate": 1.190472645738956e-05, "loss": 0.7523, "step": 7805 }, { "epoch": 0.45595794392523364, "grad_norm": 1.132243037223816, "learning_rate": 1.190286921630737e-05, "loss": 0.8579, "step": 7806 }, { "epoch": 0.4560163551401869, "grad_norm": 1.3394006490707397, "learning_rate": 1.1901011907120243e-05, "loss": 0.8204, "step": 7807 }, { "epoch": 0.45607476635514016, "grad_norm": 1.0650893449783325, "learning_rate": 1.1899154529894647e-05, "loss": 0.8033, "step": 7808 }, { "epoch": 0.4561331775700935, "grad_norm": 1.2059129476547241, "learning_rate": 1.1897297084697065e-05, "loss": 0.7987, "step": 7809 }, { "epoch": 0.45619158878504673, "grad_norm": 1.4243431091308594, "learning_rate": 1.1895439571593967e-05, "loss": 0.8773, "step": 7810 }, { "epoch": 0.45625, "grad_norm": 1.130881667137146, "learning_rate": 1.1893581990651848e-05, "loss": 0.7703, "step": 7811 }, { "epoch": 0.45630841121495325, "grad_norm": 1.1700968742370605, "learning_rate": 1.1891724341937181e-05, "loss": 0.6446, "step": 7812 }, { "epoch": 0.45636682242990656, "grad_norm": 1.685482144355774, "learning_rate": 1.1889866625516454e-05, "loss": 0.9037, "step": 7813 }, { "epoch": 0.4564252336448598, "grad_norm": 1.2763632535934448, "learning_rate": 1.188800884145616e-05, "loss": 0.7297, "step": 7814 }, { "epoch": 0.4564836448598131, "grad_norm": 1.897595763206482, "learning_rate": 1.1886150989822786e-05, "loss": 0.691, "step": 7815 }, { "epoch": 0.45654205607476633, "grad_norm": 1.7682921886444092, "learning_rate": 1.1884293070682831e-05, "loss": 0.7585, "step": 7816 }, { "epoch": 0.45660046728971965, "grad_norm": 1.4457982778549194, "learning_rate": 1.1882435084102788e-05, "loss": 0.917, "step": 7817 }, { "epoch": 0.4566588785046729, "grad_norm": 1.4053641557693481, "learning_rate": 1.1880577030149153e-05, "loss": 0.7938, "step": 7818 }, { "epoch": 0.45671728971962616, "grad_norm": 1.8820431232452393, "learning_rate": 1.1878718908888429e-05, "loss": 0.6922, "step": 7819 }, { "epoch": 0.4567757009345794, "grad_norm": 1.7560256719589233, "learning_rate": 1.1876860720387122e-05, "loss": 0.9737, "step": 7820 }, { "epoch": 0.45683411214953273, "grad_norm": 1.3571712970733643, "learning_rate": 1.1875002464711737e-05, "loss": 0.8449, "step": 7821 }, { "epoch": 0.456892523364486, "grad_norm": 1.3896217346191406, "learning_rate": 1.187314414192878e-05, "loss": 0.7105, "step": 7822 }, { "epoch": 0.45695093457943925, "grad_norm": 1.832859992980957, "learning_rate": 1.1871285752104762e-05, "loss": 0.7322, "step": 7823 }, { "epoch": 0.4570093457943925, "grad_norm": 1.500128149986267, "learning_rate": 1.1869427295306195e-05, "loss": 0.8787, "step": 7824 }, { "epoch": 0.4570677570093458, "grad_norm": 1.8966552019119263, "learning_rate": 1.1867568771599599e-05, "loss": 0.9193, "step": 7825 }, { "epoch": 0.4571261682242991, "grad_norm": 0.9997594356536865, "learning_rate": 1.1865710181051488e-05, "loss": 0.6775, "step": 7826 }, { "epoch": 0.45718457943925234, "grad_norm": 1.3786005973815918, "learning_rate": 1.186385152372838e-05, "loss": 0.6874, "step": 7827 }, { "epoch": 0.4572429906542056, "grad_norm": 3.4494853019714355, "learning_rate": 1.1861992799696805e-05, "loss": 0.8642, "step": 7828 }, { "epoch": 0.45730140186915885, "grad_norm": 1.467230200767517, "learning_rate": 1.1860134009023281e-05, "loss": 0.6861, "step": 7829 }, { "epoch": 0.45735981308411217, "grad_norm": 3.3938207626342773, "learning_rate": 1.1858275151774334e-05, "loss": 0.886, "step": 7830 }, { "epoch": 0.4574182242990654, "grad_norm": 1.10456383228302, "learning_rate": 1.1856416228016505e-05, "loss": 0.7317, "step": 7831 }, { "epoch": 0.4574766355140187, "grad_norm": 2.200015068054199, "learning_rate": 1.1854557237816313e-05, "loss": 0.8988, "step": 7832 }, { "epoch": 0.45753504672897194, "grad_norm": 3.351895570755005, "learning_rate": 1.1852698181240299e-05, "loss": 0.9837, "step": 7833 }, { "epoch": 0.45759345794392525, "grad_norm": 2.3482303619384766, "learning_rate": 1.1850839058355002e-05, "loss": 0.7846, "step": 7834 }, { "epoch": 0.4576518691588785, "grad_norm": 2.9611008167266846, "learning_rate": 1.1848979869226952e-05, "loss": 0.7825, "step": 7835 }, { "epoch": 0.45771028037383177, "grad_norm": 1.1628189086914062, "learning_rate": 1.1847120613922704e-05, "loss": 0.7128, "step": 7836 }, { "epoch": 0.457768691588785, "grad_norm": 1.2837755680084229, "learning_rate": 1.1845261292508791e-05, "loss": 0.6903, "step": 7837 }, { "epoch": 0.45782710280373834, "grad_norm": 1.9033123254776, "learning_rate": 1.1843401905051763e-05, "loss": 0.7554, "step": 7838 }, { "epoch": 0.4578855140186916, "grad_norm": 2.4328794479370117, "learning_rate": 1.1841542451618169e-05, "loss": 0.7333, "step": 7839 }, { "epoch": 0.45794392523364486, "grad_norm": 0.9032630920410156, "learning_rate": 1.183968293227456e-05, "loss": 0.8286, "step": 7840 }, { "epoch": 0.4580023364485981, "grad_norm": 2.5622336864471436, "learning_rate": 1.183782334708749e-05, "loss": 0.7514, "step": 7841 }, { "epoch": 0.4580607476635514, "grad_norm": 3.0428943634033203, "learning_rate": 1.1835963696123513e-05, "loss": 0.7536, "step": 7842 }, { "epoch": 0.4581191588785047, "grad_norm": 1.319347858428955, "learning_rate": 1.1834103979449187e-05, "loss": 0.7636, "step": 7843 }, { "epoch": 0.45817757009345794, "grad_norm": 3.09159255027771, "learning_rate": 1.1832244197131076e-05, "loss": 0.7434, "step": 7844 }, { "epoch": 0.4582359813084112, "grad_norm": 1.7676756381988525, "learning_rate": 1.1830384349235742e-05, "loss": 0.7317, "step": 7845 }, { "epoch": 0.4582943925233645, "grad_norm": 0.9604412913322449, "learning_rate": 1.1828524435829745e-05, "loss": 0.8532, "step": 7846 }, { "epoch": 0.45835280373831777, "grad_norm": 3.762899160385132, "learning_rate": 1.1826664456979657e-05, "loss": 0.8363, "step": 7847 }, { "epoch": 0.45841121495327103, "grad_norm": 0.9603025913238525, "learning_rate": 1.1824804412752047e-05, "loss": 0.8853, "step": 7848 }, { "epoch": 0.4584696261682243, "grad_norm": 1.620762586593628, "learning_rate": 1.1822944303213486e-05, "loss": 0.8229, "step": 7849 }, { "epoch": 0.45852803738317754, "grad_norm": 1.6923041343688965, "learning_rate": 1.1821084128430553e-05, "loss": 0.7877, "step": 7850 }, { "epoch": 0.45858644859813086, "grad_norm": 1.213129997253418, "learning_rate": 1.1819223888469823e-05, "loss": 0.752, "step": 7851 }, { "epoch": 0.4586448598130841, "grad_norm": 1.4485493898391724, "learning_rate": 1.1817363583397868e-05, "loss": 1.0171, "step": 7852 }, { "epoch": 0.4587032710280374, "grad_norm": 1.2052007913589478, "learning_rate": 1.1815503213281279e-05, "loss": 0.6453, "step": 7853 }, { "epoch": 0.45876168224299063, "grad_norm": 1.638279676437378, "learning_rate": 1.1813642778186636e-05, "loss": 0.9786, "step": 7854 }, { "epoch": 0.45882009345794394, "grad_norm": 1.2722560167312622, "learning_rate": 1.1811782278180526e-05, "loss": 0.9427, "step": 7855 }, { "epoch": 0.4588785046728972, "grad_norm": 1.492388129234314, "learning_rate": 1.1809921713329534e-05, "loss": 0.842, "step": 7856 }, { "epoch": 0.45893691588785046, "grad_norm": 1.576842188835144, "learning_rate": 1.1808061083700255e-05, "loss": 0.8123, "step": 7857 }, { "epoch": 0.4589953271028037, "grad_norm": 1.326062798500061, "learning_rate": 1.1806200389359281e-05, "loss": 0.7764, "step": 7858 }, { "epoch": 0.45905373831775703, "grad_norm": 1.4084066152572632, "learning_rate": 1.180433963037321e-05, "loss": 0.9368, "step": 7859 }, { "epoch": 0.4591121495327103, "grad_norm": 1.1468091011047363, "learning_rate": 1.1802478806808636e-05, "loss": 0.793, "step": 7860 }, { "epoch": 0.45917056074766355, "grad_norm": 2.0042724609375, "learning_rate": 1.180061791873216e-05, "loss": 0.7549, "step": 7861 }, { "epoch": 0.4592289719626168, "grad_norm": 1.1191834211349487, "learning_rate": 1.1798756966210386e-05, "loss": 0.7283, "step": 7862 }, { "epoch": 0.4592873831775701, "grad_norm": 2.0066730976104736, "learning_rate": 1.1796895949309914e-05, "loss": 0.901, "step": 7863 }, { "epoch": 0.4593457943925234, "grad_norm": 1.2716652154922485, "learning_rate": 1.1795034868097357e-05, "loss": 0.8072, "step": 7864 }, { "epoch": 0.45940420560747663, "grad_norm": 1.3281928300857544, "learning_rate": 1.1793173722639322e-05, "loss": 0.6479, "step": 7865 }, { "epoch": 0.4594626168224299, "grad_norm": 2.0228445529937744, "learning_rate": 1.179131251300242e-05, "loss": 0.8741, "step": 7866 }, { "epoch": 0.45952102803738315, "grad_norm": 1.3456919193267822, "learning_rate": 1.1789451239253267e-05, "loss": 0.7479, "step": 7867 }, { "epoch": 0.45957943925233646, "grad_norm": 1.094649076461792, "learning_rate": 1.1787589901458474e-05, "loss": 0.7781, "step": 7868 }, { "epoch": 0.4596378504672897, "grad_norm": 1.6034198999404907, "learning_rate": 1.1785728499684666e-05, "loss": 0.9075, "step": 7869 }, { "epoch": 0.459696261682243, "grad_norm": 1.114476203918457, "learning_rate": 1.178386703399846e-05, "loss": 0.6671, "step": 7870 }, { "epoch": 0.45975467289719624, "grad_norm": 2.65329647064209, "learning_rate": 1.1782005504466478e-05, "loss": 0.9538, "step": 7871 }, { "epoch": 0.45981308411214955, "grad_norm": 1.5372042655944824, "learning_rate": 1.1780143911155349e-05, "loss": 0.9205, "step": 7872 }, { "epoch": 0.4598714953271028, "grad_norm": 1.9673802852630615, "learning_rate": 1.1778282254131698e-05, "loss": 0.6964, "step": 7873 }, { "epoch": 0.45992990654205607, "grad_norm": 1.2449097633361816, "learning_rate": 1.177642053346216e-05, "loss": 0.737, "step": 7874 }, { "epoch": 0.4599883177570093, "grad_norm": 0.9557665586471558, "learning_rate": 1.1774558749213358e-05, "loss": 0.7767, "step": 7875 }, { "epoch": 0.46004672897196264, "grad_norm": 2.388679265975952, "learning_rate": 1.1772696901451932e-05, "loss": 0.8576, "step": 7876 }, { "epoch": 0.4601051401869159, "grad_norm": 1.1462514400482178, "learning_rate": 1.1770834990244522e-05, "loss": 0.7168, "step": 7877 }, { "epoch": 0.46016355140186915, "grad_norm": 1.5064579248428345, "learning_rate": 1.1768973015657761e-05, "loss": 1.0196, "step": 7878 }, { "epoch": 0.4602219626168224, "grad_norm": 1.961579442024231, "learning_rate": 1.1767110977758293e-05, "loss": 0.9833, "step": 7879 }, { "epoch": 0.4602803738317757, "grad_norm": 1.2098267078399658, "learning_rate": 1.1765248876612761e-05, "loss": 0.8483, "step": 7880 }, { "epoch": 0.460338785046729, "grad_norm": 2.3140158653259277, "learning_rate": 1.1763386712287812e-05, "loss": 0.7987, "step": 7881 }, { "epoch": 0.46039719626168224, "grad_norm": 0.9356619715690613, "learning_rate": 1.1761524484850088e-05, "loss": 0.8369, "step": 7882 }, { "epoch": 0.4604556074766355, "grad_norm": 1.201667070388794, "learning_rate": 1.175966219436625e-05, "loss": 0.7873, "step": 7883 }, { "epoch": 0.4605140186915888, "grad_norm": 1.784391164779663, "learning_rate": 1.1757799840902946e-05, "loss": 0.8301, "step": 7884 }, { "epoch": 0.46057242990654207, "grad_norm": 1.2940727472305298, "learning_rate": 1.1755937424526826e-05, "loss": 0.831, "step": 7885 }, { "epoch": 0.4606308411214953, "grad_norm": 1.5645077228546143, "learning_rate": 1.1754074945304555e-05, "loss": 0.832, "step": 7886 }, { "epoch": 0.4606892523364486, "grad_norm": 1.333086609840393, "learning_rate": 1.1752212403302785e-05, "loss": 0.7413, "step": 7887 }, { "epoch": 0.46074766355140184, "grad_norm": 1.6208816766738892, "learning_rate": 1.1750349798588181e-05, "loss": 0.7205, "step": 7888 }, { "epoch": 0.46080607476635516, "grad_norm": 1.6053836345672607, "learning_rate": 1.1748487131227408e-05, "loss": 0.8151, "step": 7889 }, { "epoch": 0.4608644859813084, "grad_norm": 1.1764975786209106, "learning_rate": 1.174662440128713e-05, "loss": 0.8616, "step": 7890 }, { "epoch": 0.46092289719626167, "grad_norm": 1.2206742763519287, "learning_rate": 1.174476160883402e-05, "loss": 0.6857, "step": 7891 }, { "epoch": 0.46098130841121493, "grad_norm": 1.0395193099975586, "learning_rate": 1.174289875393474e-05, "loss": 0.8416, "step": 7892 }, { "epoch": 0.46103971962616824, "grad_norm": 1.3541486263275146, "learning_rate": 1.1741035836655968e-05, "loss": 0.8525, "step": 7893 }, { "epoch": 0.4610981308411215, "grad_norm": 1.651739478111267, "learning_rate": 1.1739172857064383e-05, "loss": 0.8265, "step": 7894 }, { "epoch": 0.46115654205607476, "grad_norm": 1.1489626169204712, "learning_rate": 1.1737309815226653e-05, "loss": 0.7875, "step": 7895 }, { "epoch": 0.461214953271028, "grad_norm": 1.1935622692108154, "learning_rate": 1.1735446711209465e-05, "loss": 0.8003, "step": 7896 }, { "epoch": 0.46127336448598133, "grad_norm": 0.9978535175323486, "learning_rate": 1.1733583545079497e-05, "loss": 0.7139, "step": 7897 }, { "epoch": 0.4613317757009346, "grad_norm": 1.4551410675048828, "learning_rate": 1.1731720316903435e-05, "loss": 0.8371, "step": 7898 }, { "epoch": 0.46139018691588785, "grad_norm": 1.2324877977371216, "learning_rate": 1.1729857026747964e-05, "loss": 0.6732, "step": 7899 }, { "epoch": 0.4614485981308411, "grad_norm": 1.4246504306793213, "learning_rate": 1.1727993674679773e-05, "loss": 0.864, "step": 7900 }, { "epoch": 0.4615070093457944, "grad_norm": 1.5043939352035522, "learning_rate": 1.1726130260765549e-05, "loss": 0.8349, "step": 7901 }, { "epoch": 0.4615654205607477, "grad_norm": 1.0399692058563232, "learning_rate": 1.1724266785071992e-05, "loss": 0.7678, "step": 7902 }, { "epoch": 0.46162383177570093, "grad_norm": 1.672737717628479, "learning_rate": 1.1722403247665794e-05, "loss": 0.9189, "step": 7903 }, { "epoch": 0.4616822429906542, "grad_norm": 1.247186541557312, "learning_rate": 1.1720539648613647e-05, "loss": 0.7225, "step": 7904 }, { "epoch": 0.4617406542056075, "grad_norm": 1.7357144355773926, "learning_rate": 1.1718675987982257e-05, "loss": 0.9121, "step": 7905 }, { "epoch": 0.46179906542056076, "grad_norm": 1.6209269762039185, "learning_rate": 1.1716812265838325e-05, "loss": 0.9625, "step": 7906 }, { "epoch": 0.461857476635514, "grad_norm": 1.1494659185409546, "learning_rate": 1.1714948482248549e-05, "loss": 0.6752, "step": 7907 }, { "epoch": 0.4619158878504673, "grad_norm": 1.4161243438720703, "learning_rate": 1.1713084637279643e-05, "loss": 0.7553, "step": 7908 }, { "epoch": 0.46197429906542054, "grad_norm": 1.1995222568511963, "learning_rate": 1.1711220730998307e-05, "loss": 0.7861, "step": 7909 }, { "epoch": 0.46203271028037385, "grad_norm": 2.449035167694092, "learning_rate": 1.170935676347126e-05, "loss": 0.8421, "step": 7910 }, { "epoch": 0.4620911214953271, "grad_norm": 1.3378397226333618, "learning_rate": 1.1707492734765209e-05, "loss": 0.7024, "step": 7911 }, { "epoch": 0.46214953271028036, "grad_norm": 2.4040653705596924, "learning_rate": 1.1705628644946871e-05, "loss": 0.9161, "step": 7912 }, { "epoch": 0.4622079439252336, "grad_norm": 1.8441733121871948, "learning_rate": 1.1703764494082962e-05, "loss": 0.8026, "step": 7913 }, { "epoch": 0.46226635514018694, "grad_norm": 1.3714954853057861, "learning_rate": 1.1701900282240205e-05, "loss": 0.9303, "step": 7914 }, { "epoch": 0.4623247663551402, "grad_norm": 1.5226390361785889, "learning_rate": 1.1700036009485309e-05, "loss": 0.8605, "step": 7915 }, { "epoch": 0.46238317757009345, "grad_norm": 1.2878237962722778, "learning_rate": 1.1698171675885012e-05, "loss": 0.8289, "step": 7916 }, { "epoch": 0.4624415887850467, "grad_norm": 2.797250986099243, "learning_rate": 1.1696307281506036e-05, "loss": 0.8755, "step": 7917 }, { "epoch": 0.4625, "grad_norm": 1.4987444877624512, "learning_rate": 1.1694442826415104e-05, "loss": 0.8037, "step": 7918 }, { "epoch": 0.4625584112149533, "grad_norm": 1.8157322406768799, "learning_rate": 1.1692578310678951e-05, "loss": 0.9482, "step": 7919 }, { "epoch": 0.46261682242990654, "grad_norm": 1.0746088027954102, "learning_rate": 1.1690713734364308e-05, "loss": 0.7664, "step": 7920 }, { "epoch": 0.4626752336448598, "grad_norm": 1.2964146137237549, "learning_rate": 1.1688849097537904e-05, "loss": 1.0013, "step": 7921 }, { "epoch": 0.4627336448598131, "grad_norm": 1.3100671768188477, "learning_rate": 1.1686984400266486e-05, "loss": 0.8652, "step": 7922 }, { "epoch": 0.46279205607476637, "grad_norm": 1.2779282331466675, "learning_rate": 1.1685119642616783e-05, "loss": 0.7339, "step": 7923 }, { "epoch": 0.4628504672897196, "grad_norm": 1.2107869386672974, "learning_rate": 1.1683254824655543e-05, "loss": 0.7908, "step": 7924 }, { "epoch": 0.4629088785046729, "grad_norm": 1.2144272327423096, "learning_rate": 1.1681389946449504e-05, "loss": 0.8679, "step": 7925 }, { "epoch": 0.46296728971962614, "grad_norm": 1.3432285785675049, "learning_rate": 1.1679525008065413e-05, "loss": 0.7455, "step": 7926 }, { "epoch": 0.46302570093457945, "grad_norm": 0.8477568030357361, "learning_rate": 1.167766000957002e-05, "loss": 0.6782, "step": 7927 }, { "epoch": 0.4630841121495327, "grad_norm": 1.151510238647461, "learning_rate": 1.1675794951030073e-05, "loss": 0.745, "step": 7928 }, { "epoch": 0.46314252336448597, "grad_norm": 0.8998242020606995, "learning_rate": 1.1673929832512319e-05, "loss": 0.8969, "step": 7929 }, { "epoch": 0.4632009345794392, "grad_norm": 1.144076943397522, "learning_rate": 1.1672064654083517e-05, "loss": 0.8546, "step": 7930 }, { "epoch": 0.46325934579439254, "grad_norm": 0.8959993720054626, "learning_rate": 1.1670199415810421e-05, "loss": 0.7236, "step": 7931 }, { "epoch": 0.4633177570093458, "grad_norm": 1.0453755855560303, "learning_rate": 1.1668334117759792e-05, "loss": 0.814, "step": 7932 }, { "epoch": 0.46337616822429906, "grad_norm": 0.9346754550933838, "learning_rate": 1.1666468759998386e-05, "loss": 0.8408, "step": 7933 }, { "epoch": 0.4634345794392523, "grad_norm": 1.4414706230163574, "learning_rate": 1.1664603342592967e-05, "loss": 0.7466, "step": 7934 }, { "epoch": 0.4634929906542056, "grad_norm": 1.3712680339813232, "learning_rate": 1.1662737865610301e-05, "loss": 0.7172, "step": 7935 }, { "epoch": 0.4635514018691589, "grad_norm": 1.3493651151657104, "learning_rate": 1.1660872329117154e-05, "loss": 0.9718, "step": 7936 }, { "epoch": 0.46360981308411214, "grad_norm": 1.6717305183410645, "learning_rate": 1.1659006733180294e-05, "loss": 0.6706, "step": 7937 }, { "epoch": 0.4636682242990654, "grad_norm": 1.340023159980774, "learning_rate": 1.1657141077866495e-05, "loss": 0.8083, "step": 7938 }, { "epoch": 0.4637266355140187, "grad_norm": 1.4130488634109497, "learning_rate": 1.1655275363242522e-05, "loss": 0.9244, "step": 7939 }, { "epoch": 0.463785046728972, "grad_norm": 1.3346267938613892, "learning_rate": 1.1653409589375156e-05, "loss": 0.8995, "step": 7940 }, { "epoch": 0.46384345794392523, "grad_norm": 1.7607955932617188, "learning_rate": 1.1651543756331176e-05, "loss": 0.6872, "step": 7941 }, { "epoch": 0.4639018691588785, "grad_norm": 1.4084408283233643, "learning_rate": 1.1649677864177358e-05, "loss": 0.674, "step": 7942 }, { "epoch": 0.4639602803738318, "grad_norm": 1.5946836471557617, "learning_rate": 1.1647811912980485e-05, "loss": 0.8867, "step": 7943 }, { "epoch": 0.46401869158878506, "grad_norm": 1.7942118644714355, "learning_rate": 1.164594590280734e-05, "loss": 0.9573, "step": 7944 }, { "epoch": 0.4640771028037383, "grad_norm": 1.4504916667938232, "learning_rate": 1.1644079833724711e-05, "loss": 0.7304, "step": 7945 }, { "epoch": 0.4641355140186916, "grad_norm": 1.2186816930770874, "learning_rate": 1.1642213705799379e-05, "loss": 0.9414, "step": 7946 }, { "epoch": 0.46419392523364483, "grad_norm": 1.422831654548645, "learning_rate": 1.1640347519098143e-05, "loss": 0.766, "step": 7947 }, { "epoch": 0.46425233644859815, "grad_norm": 1.1995720863342285, "learning_rate": 1.1638481273687787e-05, "loss": 0.8083, "step": 7948 }, { "epoch": 0.4643107476635514, "grad_norm": 1.3111242055892944, "learning_rate": 1.1636614969635111e-05, "loss": 0.7649, "step": 7949 }, { "epoch": 0.46436915887850466, "grad_norm": 1.0525847673416138, "learning_rate": 1.1634748607006912e-05, "loss": 0.8519, "step": 7950 }, { "epoch": 0.4644275700934579, "grad_norm": 1.4746888875961304, "learning_rate": 1.1632882185869982e-05, "loss": 0.9871, "step": 7951 }, { "epoch": 0.46448598130841123, "grad_norm": 1.7231873273849487, "learning_rate": 1.1631015706291127e-05, "loss": 0.7445, "step": 7952 }, { "epoch": 0.4645443925233645, "grad_norm": 1.0703840255737305, "learning_rate": 1.1629149168337145e-05, "loss": 0.7471, "step": 7953 }, { "epoch": 0.46460280373831775, "grad_norm": 2.4107813835144043, "learning_rate": 1.1627282572074843e-05, "loss": 0.9185, "step": 7954 }, { "epoch": 0.464661214953271, "grad_norm": 1.4738823175430298, "learning_rate": 1.1625415917571029e-05, "loss": 0.9169, "step": 7955 }, { "epoch": 0.4647196261682243, "grad_norm": 1.897957682609558, "learning_rate": 1.162354920489251e-05, "loss": 0.7689, "step": 7956 }, { "epoch": 0.4647780373831776, "grad_norm": 1.1748926639556885, "learning_rate": 1.1621682434106098e-05, "loss": 0.7618, "step": 7957 }, { "epoch": 0.46483644859813084, "grad_norm": 1.7181528806686401, "learning_rate": 1.1619815605278607e-05, "loss": 0.7318, "step": 7958 }, { "epoch": 0.4648948598130841, "grad_norm": 1.5056248903274536, "learning_rate": 1.1617948718476847e-05, "loss": 0.8737, "step": 7959 }, { "epoch": 0.4649532710280374, "grad_norm": 1.7717593908309937, "learning_rate": 1.161608177376764e-05, "loss": 0.8455, "step": 7960 }, { "epoch": 0.46501168224299066, "grad_norm": 1.910927414894104, "learning_rate": 1.1614214771217806e-05, "loss": 0.7991, "step": 7961 }, { "epoch": 0.4650700934579439, "grad_norm": 1.1524192094802856, "learning_rate": 1.161234771089416e-05, "loss": 0.9083, "step": 7962 }, { "epoch": 0.4651285046728972, "grad_norm": 1.5558699369430542, "learning_rate": 1.161048059286353e-05, "loss": 0.7265, "step": 7963 }, { "epoch": 0.4651869158878505, "grad_norm": 1.43449866771698, "learning_rate": 1.1608613417192744e-05, "loss": 1.0538, "step": 7964 }, { "epoch": 0.46524532710280375, "grad_norm": 1.2481982707977295, "learning_rate": 1.1606746183948623e-05, "loss": 0.855, "step": 7965 }, { "epoch": 0.465303738317757, "grad_norm": 1.4428070783615112, "learning_rate": 1.1604878893198002e-05, "loss": 0.8867, "step": 7966 }, { "epoch": 0.46536214953271027, "grad_norm": 1.3375321626663208, "learning_rate": 1.1603011545007708e-05, "loss": 0.9127, "step": 7967 }, { "epoch": 0.4654205607476635, "grad_norm": 1.234856128692627, "learning_rate": 1.1601144139444578e-05, "loss": 0.7519, "step": 7968 }, { "epoch": 0.46547897196261684, "grad_norm": 1.67133629322052, "learning_rate": 1.1599276676575446e-05, "loss": 0.6856, "step": 7969 }, { "epoch": 0.4655373831775701, "grad_norm": 1.5969429016113281, "learning_rate": 1.159740915646715e-05, "loss": 0.9093, "step": 7970 }, { "epoch": 0.46559579439252335, "grad_norm": 1.136024832725525, "learning_rate": 1.1595541579186531e-05, "loss": 0.7632, "step": 7971 }, { "epoch": 0.4656542056074766, "grad_norm": 2.7406833171844482, "learning_rate": 1.159367394480043e-05, "loss": 0.9393, "step": 7972 }, { "epoch": 0.4657126168224299, "grad_norm": 1.253808617591858, "learning_rate": 1.1591806253375687e-05, "loss": 0.7388, "step": 7973 }, { "epoch": 0.4657710280373832, "grad_norm": 1.8332295417785645, "learning_rate": 1.1589938504979155e-05, "loss": 0.8667, "step": 7974 }, { "epoch": 0.46582943925233644, "grad_norm": 1.5564547777175903, "learning_rate": 1.1588070699677678e-05, "loss": 0.9081, "step": 7975 }, { "epoch": 0.4658878504672897, "grad_norm": 1.3237615823745728, "learning_rate": 1.1586202837538107e-05, "loss": 0.8896, "step": 7976 }, { "epoch": 0.465946261682243, "grad_norm": 2.5012457370758057, "learning_rate": 1.1584334918627294e-05, "loss": 0.8672, "step": 7977 }, { "epoch": 0.46600467289719627, "grad_norm": 1.113303780555725, "learning_rate": 1.1582466943012092e-05, "loss": 0.6982, "step": 7978 }, { "epoch": 0.46606308411214953, "grad_norm": 1.7304761409759521, "learning_rate": 1.1580598910759353e-05, "loss": 0.6733, "step": 7979 }, { "epoch": 0.4661214953271028, "grad_norm": 2.2625021934509277, "learning_rate": 1.1578730821935946e-05, "loss": 0.9534, "step": 7980 }, { "epoch": 0.4661799065420561, "grad_norm": 1.6028724908828735, "learning_rate": 1.1576862676608723e-05, "loss": 0.7535, "step": 7981 }, { "epoch": 0.46623831775700936, "grad_norm": 1.3671520948410034, "learning_rate": 1.1574994474844545e-05, "loss": 0.7659, "step": 7982 }, { "epoch": 0.4662967289719626, "grad_norm": 2.6904873847961426, "learning_rate": 1.1573126216710285e-05, "loss": 0.822, "step": 7983 }, { "epoch": 0.4663551401869159, "grad_norm": 1.7617707252502441, "learning_rate": 1.1571257902272797e-05, "loss": 0.8635, "step": 7984 }, { "epoch": 0.4664135514018692, "grad_norm": 2.0600056648254395, "learning_rate": 1.156938953159896e-05, "loss": 0.742, "step": 7985 }, { "epoch": 0.46647196261682244, "grad_norm": 1.1206858158111572, "learning_rate": 1.1567521104755639e-05, "loss": 0.8443, "step": 7986 }, { "epoch": 0.4665303738317757, "grad_norm": 1.409766674041748, "learning_rate": 1.1565652621809704e-05, "loss": 0.9044, "step": 7987 }, { "epoch": 0.46658878504672896, "grad_norm": 3.752082347869873, "learning_rate": 1.1563784082828035e-05, "loss": 0.8236, "step": 7988 }, { "epoch": 0.4666471962616822, "grad_norm": 2.319718599319458, "learning_rate": 1.1561915487877506e-05, "loss": 0.9335, "step": 7989 }, { "epoch": 0.46670560747663553, "grad_norm": 2.1291801929473877, "learning_rate": 1.1560046837024994e-05, "loss": 0.6934, "step": 7990 }, { "epoch": 0.4667640186915888, "grad_norm": 2.0380306243896484, "learning_rate": 1.1558178130337381e-05, "loss": 0.9216, "step": 7991 }, { "epoch": 0.46682242990654205, "grad_norm": 1.1809290647506714, "learning_rate": 1.1556309367881545e-05, "loss": 0.8855, "step": 7992 }, { "epoch": 0.4668808411214953, "grad_norm": 1.1310734748840332, "learning_rate": 1.1554440549724374e-05, "loss": 0.6931, "step": 7993 }, { "epoch": 0.4669392523364486, "grad_norm": 3.0194523334503174, "learning_rate": 1.1552571675932755e-05, "loss": 0.9036, "step": 7994 }, { "epoch": 0.4669976635514019, "grad_norm": 1.7095732688903809, "learning_rate": 1.1550702746573576e-05, "loss": 1.0203, "step": 7995 }, { "epoch": 0.46705607476635513, "grad_norm": 2.6832799911499023, "learning_rate": 1.1548833761713726e-05, "loss": 0.8869, "step": 7996 }, { "epoch": 0.4671144859813084, "grad_norm": 1.2435566186904907, "learning_rate": 1.1546964721420097e-05, "loss": 0.7846, "step": 7997 }, { "epoch": 0.4671728971962617, "grad_norm": 1.6649149656295776, "learning_rate": 1.1545095625759581e-05, "loss": 0.9442, "step": 7998 }, { "epoch": 0.46723130841121496, "grad_norm": 2.481868028640747, "learning_rate": 1.1543226474799078e-05, "loss": 0.927, "step": 7999 }, { "epoch": 0.4672897196261682, "grad_norm": 1.1759706735610962, "learning_rate": 1.1541357268605486e-05, "loss": 0.7025, "step": 8000 }, { "epoch": 0.4673481308411215, "grad_norm": 2.6633942127227783, "learning_rate": 1.1539488007245704e-05, "loss": 0.7988, "step": 8001 }, { "epoch": 0.4674065420560748, "grad_norm": 1.2337942123413086, "learning_rate": 1.1537618690786631e-05, "loss": 0.8515, "step": 8002 }, { "epoch": 0.46746495327102805, "grad_norm": 1.317962408065796, "learning_rate": 1.1535749319295178e-05, "loss": 1.0694, "step": 8003 }, { "epoch": 0.4675233644859813, "grad_norm": 1.1036118268966675, "learning_rate": 1.1533879892838242e-05, "loss": 0.7472, "step": 8004 }, { "epoch": 0.46758177570093457, "grad_norm": 2.1416428089141846, "learning_rate": 1.1532010411482744e-05, "loss": 0.8798, "step": 8005 }, { "epoch": 0.4676401869158878, "grad_norm": 1.3844976425170898, "learning_rate": 1.153014087529558e-05, "loss": 0.953, "step": 8006 }, { "epoch": 0.46769859813084114, "grad_norm": 3.9491894245147705, "learning_rate": 1.1528271284343668e-05, "loss": 1.0087, "step": 8007 }, { "epoch": 0.4677570093457944, "grad_norm": 1.9495329856872559, "learning_rate": 1.1526401638693923e-05, "loss": 0.7641, "step": 8008 }, { "epoch": 0.46781542056074765, "grad_norm": 2.8485190868377686, "learning_rate": 1.1524531938413261e-05, "loss": 0.9656, "step": 8009 }, { "epoch": 0.4678738317757009, "grad_norm": 1.7533786296844482, "learning_rate": 1.1522662183568598e-05, "loss": 0.7405, "step": 8010 }, { "epoch": 0.4679322429906542, "grad_norm": 1.4561933279037476, "learning_rate": 1.1520792374226855e-05, "loss": 0.9572, "step": 8011 }, { "epoch": 0.4679906542056075, "grad_norm": 2.2384209632873535, "learning_rate": 1.1518922510454949e-05, "loss": 0.8595, "step": 8012 }, { "epoch": 0.46804906542056074, "grad_norm": 2.1887636184692383, "learning_rate": 1.151705259231981e-05, "loss": 0.8847, "step": 8013 }, { "epoch": 0.468107476635514, "grad_norm": 1.2158334255218506, "learning_rate": 1.1515182619888364e-05, "loss": 0.8517, "step": 8014 }, { "epoch": 0.4681658878504673, "grad_norm": 1.4574909210205078, "learning_rate": 1.1513312593227532e-05, "loss": 0.7597, "step": 8015 }, { "epoch": 0.46822429906542057, "grad_norm": 2.2221755981445312, "learning_rate": 1.151144251240425e-05, "loss": 0.6282, "step": 8016 }, { "epoch": 0.4682827102803738, "grad_norm": 1.2017855644226074, "learning_rate": 1.1509572377485443e-05, "loss": 0.8309, "step": 8017 }, { "epoch": 0.4683411214953271, "grad_norm": 1.6620975732803345, "learning_rate": 1.150770218853805e-05, "loss": 0.7572, "step": 8018 }, { "epoch": 0.4683995327102804, "grad_norm": 1.6878831386566162, "learning_rate": 1.1505831945629008e-05, "loss": 0.7464, "step": 8019 }, { "epoch": 0.46845794392523366, "grad_norm": 1.3288328647613525, "learning_rate": 1.1503961648825244e-05, "loss": 0.6506, "step": 8020 }, { "epoch": 0.4685163551401869, "grad_norm": 1.223394751548767, "learning_rate": 1.1502091298193707e-05, "loss": 0.8403, "step": 8021 }, { "epoch": 0.46857476635514017, "grad_norm": 1.9204272031784058, "learning_rate": 1.1500220893801335e-05, "loss": 0.7799, "step": 8022 }, { "epoch": 0.4686331775700935, "grad_norm": 2.3913846015930176, "learning_rate": 1.149835043571507e-05, "loss": 0.8835, "step": 8023 }, { "epoch": 0.46869158878504674, "grad_norm": 1.0171396732330322, "learning_rate": 1.149647992400186e-05, "loss": 0.9804, "step": 8024 }, { "epoch": 0.46875, "grad_norm": 1.6699254512786865, "learning_rate": 1.1494609358728646e-05, "loss": 0.7528, "step": 8025 }, { "epoch": 0.46880841121495326, "grad_norm": 1.532904028892517, "learning_rate": 1.1492738739962384e-05, "loss": 0.7393, "step": 8026 }, { "epoch": 0.4688668224299065, "grad_norm": 0.9098556041717529, "learning_rate": 1.1490868067770018e-05, "loss": 0.6541, "step": 8027 }, { "epoch": 0.46892523364485983, "grad_norm": 1.1385846138000488, "learning_rate": 1.1488997342218504e-05, "loss": 0.6759, "step": 8028 }, { "epoch": 0.4689836448598131, "grad_norm": 1.5728586912155151, "learning_rate": 1.14871265633748e-05, "loss": 0.9586, "step": 8029 }, { "epoch": 0.46904205607476634, "grad_norm": 1.2067850828170776, "learning_rate": 1.1485255731305855e-05, "loss": 0.8114, "step": 8030 }, { "epoch": 0.4691004672897196, "grad_norm": 1.3328102827072144, "learning_rate": 1.148338484607863e-05, "loss": 0.8355, "step": 8031 }, { "epoch": 0.4691588785046729, "grad_norm": 1.9761312007904053, "learning_rate": 1.1481513907760087e-05, "loss": 0.8513, "step": 8032 }, { "epoch": 0.4692172897196262, "grad_norm": 1.4566657543182373, "learning_rate": 1.1479642916417186e-05, "loss": 1.1212, "step": 8033 }, { "epoch": 0.46927570093457943, "grad_norm": 2.216611385345459, "learning_rate": 1.1477771872116894e-05, "loss": 0.8243, "step": 8034 }, { "epoch": 0.4693341121495327, "grad_norm": 1.0218008756637573, "learning_rate": 1.1475900774926176e-05, "loss": 0.7286, "step": 8035 }, { "epoch": 0.469392523364486, "grad_norm": 1.01106858253479, "learning_rate": 1.1474029624911997e-05, "loss": 0.8608, "step": 8036 }, { "epoch": 0.46945093457943926, "grad_norm": 1.1597745418548584, "learning_rate": 1.1472158422141326e-05, "loss": 0.8138, "step": 8037 }, { "epoch": 0.4695093457943925, "grad_norm": 1.6976252794265747, "learning_rate": 1.1470287166681144e-05, "loss": 0.8045, "step": 8038 }, { "epoch": 0.4695677570093458, "grad_norm": 1.7008858919143677, "learning_rate": 1.1468415858598413e-05, "loss": 0.7326, "step": 8039 }, { "epoch": 0.4696261682242991, "grad_norm": 1.8780423402786255, "learning_rate": 1.1466544497960112e-05, "loss": 1.1205, "step": 8040 }, { "epoch": 0.46968457943925235, "grad_norm": 1.1881787776947021, "learning_rate": 1.146467308483322e-05, "loss": 1.0303, "step": 8041 }, { "epoch": 0.4697429906542056, "grad_norm": 1.1216280460357666, "learning_rate": 1.1462801619284716e-05, "loss": 0.7571, "step": 8042 }, { "epoch": 0.46980140186915886, "grad_norm": 1.0795785188674927, "learning_rate": 1.1460930101381583e-05, "loss": 0.8815, "step": 8043 }, { "epoch": 0.4698598130841122, "grad_norm": 0.8822343945503235, "learning_rate": 1.1459058531190797e-05, "loss": 0.5686, "step": 8044 }, { "epoch": 0.46991822429906543, "grad_norm": 0.9267634749412537, "learning_rate": 1.1457186908779345e-05, "loss": 0.6802, "step": 8045 }, { "epoch": 0.4699766355140187, "grad_norm": 1.3127174377441406, "learning_rate": 1.145531523421422e-05, "loss": 0.8795, "step": 8046 }, { "epoch": 0.47003504672897195, "grad_norm": 0.7843573093414307, "learning_rate": 1.1453443507562405e-05, "loss": 0.5476, "step": 8047 }, { "epoch": 0.4700934579439252, "grad_norm": 1.548439860343933, "learning_rate": 1.1451571728890892e-05, "loss": 0.9062, "step": 8048 }, { "epoch": 0.4701518691588785, "grad_norm": 1.0918141603469849, "learning_rate": 1.144969989826667e-05, "loss": 0.7848, "step": 8049 }, { "epoch": 0.4702102803738318, "grad_norm": 1.2219551801681519, "learning_rate": 1.1447828015756735e-05, "loss": 0.8193, "step": 8050 }, { "epoch": 0.47026869158878504, "grad_norm": 1.065940260887146, "learning_rate": 1.1445956081428084e-05, "loss": 0.7169, "step": 8051 }, { "epoch": 0.4703271028037383, "grad_norm": 1.1029467582702637, "learning_rate": 1.1444084095347716e-05, "loss": 0.9679, "step": 8052 }, { "epoch": 0.4703855140186916, "grad_norm": 1.2243963479995728, "learning_rate": 1.1442212057582626e-05, "loss": 0.8105, "step": 8053 }, { "epoch": 0.47044392523364487, "grad_norm": 1.7578213214874268, "learning_rate": 1.144033996819982e-05, "loss": 0.7408, "step": 8054 }, { "epoch": 0.4705023364485981, "grad_norm": 1.2038683891296387, "learning_rate": 1.1438467827266302e-05, "loss": 0.8735, "step": 8055 }, { "epoch": 0.4705607476635514, "grad_norm": 1.419204592704773, "learning_rate": 1.1436595634849067e-05, "loss": 0.8588, "step": 8056 }, { "epoch": 0.4706191588785047, "grad_norm": 1.5876739025115967, "learning_rate": 1.1434723391015137e-05, "loss": 1.0077, "step": 8057 }, { "epoch": 0.47067757009345795, "grad_norm": 1.5851885080337524, "learning_rate": 1.1432851095831511e-05, "loss": 0.7607, "step": 8058 }, { "epoch": 0.4707359813084112, "grad_norm": 1.3333773612976074, "learning_rate": 1.1430978749365203e-05, "loss": 0.6984, "step": 8059 }, { "epoch": 0.47079439252336447, "grad_norm": 1.2299484014511108, "learning_rate": 1.1429106351683223e-05, "loss": 0.8662, "step": 8060 }, { "epoch": 0.4708528037383178, "grad_norm": 1.0834298133850098, "learning_rate": 1.1427233902852586e-05, "loss": 0.7411, "step": 8061 }, { "epoch": 0.47091121495327104, "grad_norm": 1.7843303680419922, "learning_rate": 1.1425361402940311e-05, "loss": 0.7182, "step": 8062 }, { "epoch": 0.4709696261682243, "grad_norm": 1.4945836067199707, "learning_rate": 1.1423488852013418e-05, "loss": 0.9088, "step": 8063 }, { "epoch": 0.47102803738317756, "grad_norm": 1.459718942642212, "learning_rate": 1.1421616250138915e-05, "loss": 0.7391, "step": 8064 }, { "epoch": 0.4710864485981308, "grad_norm": 1.2622137069702148, "learning_rate": 1.141974359738384e-05, "loss": 0.8512, "step": 8065 }, { "epoch": 0.4711448598130841, "grad_norm": 1.7831648588180542, "learning_rate": 1.1417870893815205e-05, "loss": 0.8221, "step": 8066 }, { "epoch": 0.4712032710280374, "grad_norm": 2.1320066452026367, "learning_rate": 1.1415998139500035e-05, "loss": 0.6979, "step": 8067 }, { "epoch": 0.47126168224299064, "grad_norm": 1.387277603149414, "learning_rate": 1.1414125334505364e-05, "loss": 0.7362, "step": 8068 }, { "epoch": 0.4713200934579439, "grad_norm": 1.0500282049179077, "learning_rate": 1.1412252478898216e-05, "loss": 0.9527, "step": 8069 }, { "epoch": 0.4713785046728972, "grad_norm": 1.590188980102539, "learning_rate": 1.1410379572745623e-05, "loss": 0.6294, "step": 8070 }, { "epoch": 0.47143691588785047, "grad_norm": 1.967476487159729, "learning_rate": 1.140850661611462e-05, "loss": 0.7323, "step": 8071 }, { "epoch": 0.47149532710280373, "grad_norm": 1.2032350301742554, "learning_rate": 1.1406633609072238e-05, "loss": 0.8304, "step": 8072 }, { "epoch": 0.471553738317757, "grad_norm": 1.0440611839294434, "learning_rate": 1.1404760551685512e-05, "loss": 0.5796, "step": 8073 }, { "epoch": 0.4716121495327103, "grad_norm": 1.052754282951355, "learning_rate": 1.1402887444021484e-05, "loss": 0.8608, "step": 8074 }, { "epoch": 0.47167056074766356, "grad_norm": 1.133158564567566, "learning_rate": 1.1401014286147192e-05, "loss": 0.766, "step": 8075 }, { "epoch": 0.4717289719626168, "grad_norm": 1.3580424785614014, "learning_rate": 1.1399141078129676e-05, "loss": 0.8631, "step": 8076 }, { "epoch": 0.4717873831775701, "grad_norm": 1.265690565109253, "learning_rate": 1.1397267820035986e-05, "loss": 0.6599, "step": 8077 }, { "epoch": 0.4718457943925234, "grad_norm": 0.980343222618103, "learning_rate": 1.1395394511933157e-05, "loss": 0.7223, "step": 8078 }, { "epoch": 0.47190420560747665, "grad_norm": 1.7681293487548828, "learning_rate": 1.1393521153888242e-05, "loss": 0.8766, "step": 8079 }, { "epoch": 0.4719626168224299, "grad_norm": 1.4371427297592163, "learning_rate": 1.1391647745968291e-05, "loss": 0.6565, "step": 8080 }, { "epoch": 0.47202102803738316, "grad_norm": 1.456728219985962, "learning_rate": 1.1389774288240348e-05, "loss": 0.9669, "step": 8081 }, { "epoch": 0.4720794392523365, "grad_norm": 1.8013454675674438, "learning_rate": 1.1387900780771472e-05, "loss": 0.837, "step": 8082 }, { "epoch": 0.47213785046728973, "grad_norm": 1.4117072820663452, "learning_rate": 1.1386027223628712e-05, "loss": 0.8036, "step": 8083 }, { "epoch": 0.472196261682243, "grad_norm": 1.297059416770935, "learning_rate": 1.138415361687913e-05, "loss": 0.8034, "step": 8084 }, { "epoch": 0.47225467289719625, "grad_norm": 2.1878902912139893, "learning_rate": 1.138227996058978e-05, "loss": 1.0812, "step": 8085 }, { "epoch": 0.4723130841121495, "grad_norm": 1.0357998609542847, "learning_rate": 1.1380406254827716e-05, "loss": 0.6761, "step": 8086 }, { "epoch": 0.4723714953271028, "grad_norm": 2.0897622108459473, "learning_rate": 1.1378532499660011e-05, "loss": 0.8586, "step": 8087 }, { "epoch": 0.4724299065420561, "grad_norm": 0.9780245423316956, "learning_rate": 1.137665869515372e-05, "loss": 0.6884, "step": 8088 }, { "epoch": 0.47248831775700934, "grad_norm": 1.316962480545044, "learning_rate": 1.1374784841375905e-05, "loss": 0.7311, "step": 8089 }, { "epoch": 0.4725467289719626, "grad_norm": 1.3167760372161865, "learning_rate": 1.137291093839364e-05, "loss": 0.7993, "step": 8090 }, { "epoch": 0.4726051401869159, "grad_norm": 1.4015883207321167, "learning_rate": 1.1371036986273988e-05, "loss": 0.7651, "step": 8091 }, { "epoch": 0.47266355140186916, "grad_norm": 2.4208297729492188, "learning_rate": 1.1369162985084024e-05, "loss": 0.8093, "step": 8092 }, { "epoch": 0.4727219626168224, "grad_norm": 1.4944134950637817, "learning_rate": 1.1367288934890814e-05, "loss": 0.907, "step": 8093 }, { "epoch": 0.4727803738317757, "grad_norm": 1.8244678974151611, "learning_rate": 1.1365414835761432e-05, "loss": 0.883, "step": 8094 }, { "epoch": 0.472838785046729, "grad_norm": 1.306287407875061, "learning_rate": 1.136354068776296e-05, "loss": 0.6702, "step": 8095 }, { "epoch": 0.47289719626168225, "grad_norm": 1.7515424489974976, "learning_rate": 1.1361666490962468e-05, "loss": 0.9057, "step": 8096 }, { "epoch": 0.4729556074766355, "grad_norm": 1.6402910947799683, "learning_rate": 1.1359792245427035e-05, "loss": 0.9472, "step": 8097 }, { "epoch": 0.47301401869158877, "grad_norm": 1.1351045370101929, "learning_rate": 1.1357917951223748e-05, "loss": 0.774, "step": 8098 }, { "epoch": 0.4730724299065421, "grad_norm": 1.8467674255371094, "learning_rate": 1.1356043608419682e-05, "loss": 0.9301, "step": 8099 }, { "epoch": 0.47313084112149534, "grad_norm": 1.3877460956573486, "learning_rate": 1.1354169217081921e-05, "loss": 0.803, "step": 8100 }, { "epoch": 0.4731892523364486, "grad_norm": 1.1131527423858643, "learning_rate": 1.135229477727756e-05, "loss": 0.7958, "step": 8101 }, { "epoch": 0.47324766355140185, "grad_norm": 3.0506343841552734, "learning_rate": 1.1350420289073677e-05, "loss": 0.8388, "step": 8102 }, { "epoch": 0.47330607476635517, "grad_norm": 1.7555696964263916, "learning_rate": 1.1348545752537358e-05, "loss": 0.7769, "step": 8103 }, { "epoch": 0.4733644859813084, "grad_norm": 3.7893331050872803, "learning_rate": 1.1346671167735705e-05, "loss": 0.9828, "step": 8104 }, { "epoch": 0.4734228971962617, "grad_norm": 1.6090593338012695, "learning_rate": 1.1344796534735805e-05, "loss": 0.8551, "step": 8105 }, { "epoch": 0.47348130841121494, "grad_norm": 3.0288264751434326, "learning_rate": 1.1342921853604754e-05, "loss": 0.8108, "step": 8106 }, { "epoch": 0.4735397196261682, "grad_norm": 1.2260046005249023, "learning_rate": 1.1341047124409645e-05, "loss": 0.6636, "step": 8107 }, { "epoch": 0.4735981308411215, "grad_norm": 1.068301796913147, "learning_rate": 1.1339172347217577e-05, "loss": 0.6476, "step": 8108 }, { "epoch": 0.47365654205607477, "grad_norm": 2.923888921737671, "learning_rate": 1.1337297522095651e-05, "loss": 0.778, "step": 8109 }, { "epoch": 0.473714953271028, "grad_norm": 1.3474012613296509, "learning_rate": 1.133542264911097e-05, "loss": 0.8892, "step": 8110 }, { "epoch": 0.4737733644859813, "grad_norm": 1.456111192703247, "learning_rate": 1.1333547728330632e-05, "loss": 0.7246, "step": 8111 }, { "epoch": 0.4738317757009346, "grad_norm": 1.871264934539795, "learning_rate": 1.1331672759821744e-05, "loss": 0.6594, "step": 8112 }, { "epoch": 0.47389018691588786, "grad_norm": 1.380853533744812, "learning_rate": 1.1329797743651414e-05, "loss": 0.891, "step": 8113 }, { "epoch": 0.4739485981308411, "grad_norm": 1.3166546821594238, "learning_rate": 1.1327922679886745e-05, "loss": 0.9169, "step": 8114 }, { "epoch": 0.4740070093457944, "grad_norm": 1.4417482614517212, "learning_rate": 1.1326047568594852e-05, "loss": 1.0104, "step": 8115 }, { "epoch": 0.4740654205607477, "grad_norm": 2.2650015354156494, "learning_rate": 1.1324172409842844e-05, "loss": 0.8381, "step": 8116 }, { "epoch": 0.47412383177570094, "grad_norm": 1.3329718112945557, "learning_rate": 1.1322297203697836e-05, "loss": 0.8829, "step": 8117 }, { "epoch": 0.4741822429906542, "grad_norm": 1.2793956995010376, "learning_rate": 1.1320421950226942e-05, "loss": 0.8321, "step": 8118 }, { "epoch": 0.47424065420560746, "grad_norm": 1.343982219696045, "learning_rate": 1.1318546649497276e-05, "loss": 0.8652, "step": 8119 }, { "epoch": 0.4742990654205608, "grad_norm": 0.9737800359725952, "learning_rate": 1.131667130157596e-05, "loss": 0.8324, "step": 8120 }, { "epoch": 0.47435747663551403, "grad_norm": 1.068589448928833, "learning_rate": 1.1314795906530115e-05, "loss": 0.8233, "step": 8121 }, { "epoch": 0.4744158878504673, "grad_norm": 1.2550418376922607, "learning_rate": 1.1312920464426855e-05, "loss": 0.6854, "step": 8122 }, { "epoch": 0.47447429906542055, "grad_norm": 1.1960475444793701, "learning_rate": 1.1311044975333312e-05, "loss": 0.9588, "step": 8123 }, { "epoch": 0.47453271028037386, "grad_norm": 1.3794482946395874, "learning_rate": 1.1309169439316605e-05, "loss": 0.686, "step": 8124 }, { "epoch": 0.4745911214953271, "grad_norm": 1.4274863004684448, "learning_rate": 1.1307293856443865e-05, "loss": 0.9003, "step": 8125 }, { "epoch": 0.4746495327102804, "grad_norm": 1.4612165689468384, "learning_rate": 1.1305418226782217e-05, "loss": 0.8783, "step": 8126 }, { "epoch": 0.47470794392523363, "grad_norm": 1.1648848056793213, "learning_rate": 1.1303542550398791e-05, "loss": 0.6961, "step": 8127 }, { "epoch": 0.4747663551401869, "grad_norm": 1.2863895893096924, "learning_rate": 1.1301666827360721e-05, "loss": 0.9385, "step": 8128 }, { "epoch": 0.4748247663551402, "grad_norm": 1.1684536933898926, "learning_rate": 1.1299791057735141e-05, "loss": 0.8414, "step": 8129 }, { "epoch": 0.47488317757009346, "grad_norm": 1.4948744773864746, "learning_rate": 1.1297915241589184e-05, "loss": 0.7983, "step": 8130 }, { "epoch": 0.4749415887850467, "grad_norm": 1.5341191291809082, "learning_rate": 1.1296039378989986e-05, "loss": 0.906, "step": 8131 }, { "epoch": 0.475, "grad_norm": 1.8813613653182983, "learning_rate": 1.129416347000469e-05, "loss": 0.9144, "step": 8132 }, { "epoch": 0.4750584112149533, "grad_norm": 2.018563747406006, "learning_rate": 1.1292287514700426e-05, "loss": 0.9454, "step": 8133 }, { "epoch": 0.47511682242990655, "grad_norm": 0.9363566040992737, "learning_rate": 1.1290411513144343e-05, "loss": 0.6957, "step": 8134 }, { "epoch": 0.4751752336448598, "grad_norm": 1.1078490018844604, "learning_rate": 1.1288535465403592e-05, "loss": 0.7269, "step": 8135 }, { "epoch": 0.47523364485981306, "grad_norm": 3.7968857288360596, "learning_rate": 1.1286659371545301e-05, "loss": 0.7971, "step": 8136 }, { "epoch": 0.4752920560747664, "grad_norm": 1.1117956638336182, "learning_rate": 1.1284783231636627e-05, "loss": 0.8326, "step": 8137 }, { "epoch": 0.47535046728971964, "grad_norm": 1.2053329944610596, "learning_rate": 1.1282907045744718e-05, "loss": 0.8631, "step": 8138 }, { "epoch": 0.4754088785046729, "grad_norm": 1.3024818897247314, "learning_rate": 1.1281030813936717e-05, "loss": 0.7315, "step": 8139 }, { "epoch": 0.47546728971962615, "grad_norm": 1.162804126739502, "learning_rate": 1.127915453627979e-05, "loss": 0.8282, "step": 8140 }, { "epoch": 0.47552570093457946, "grad_norm": 1.7431418895721436, "learning_rate": 1.1277278212841075e-05, "loss": 0.8819, "step": 8141 }, { "epoch": 0.4755841121495327, "grad_norm": 1.2914721965789795, "learning_rate": 1.1275401843687733e-05, "loss": 0.738, "step": 8142 }, { "epoch": 0.475642523364486, "grad_norm": 0.9377710819244385, "learning_rate": 1.1273525428886921e-05, "loss": 0.7163, "step": 8143 }, { "epoch": 0.47570093457943924, "grad_norm": 1.3649184703826904, "learning_rate": 1.1271648968505797e-05, "loss": 0.9356, "step": 8144 }, { "epoch": 0.4757593457943925, "grad_norm": 2.060861110687256, "learning_rate": 1.1269772462611522e-05, "loss": 0.8165, "step": 8145 }, { "epoch": 0.4758177570093458, "grad_norm": 1.0110257863998413, "learning_rate": 1.1267895911271254e-05, "loss": 0.9429, "step": 8146 }, { "epoch": 0.47587616822429907, "grad_norm": 1.7791383266448975, "learning_rate": 1.1266019314552157e-05, "loss": 0.9425, "step": 8147 }, { "epoch": 0.4759345794392523, "grad_norm": 0.8862088322639465, "learning_rate": 1.1264142672521396e-05, "loss": 0.6819, "step": 8148 }, { "epoch": 0.4759929906542056, "grad_norm": 1.1489177942276, "learning_rate": 1.1262265985246139e-05, "loss": 0.82, "step": 8149 }, { "epoch": 0.4760514018691589, "grad_norm": 1.7276573181152344, "learning_rate": 1.1260389252793554e-05, "loss": 0.8615, "step": 8150 }, { "epoch": 0.47610981308411215, "grad_norm": 1.0464924573898315, "learning_rate": 1.1258512475230807e-05, "loss": 0.7857, "step": 8151 }, { "epoch": 0.4761682242990654, "grad_norm": 1.6846643686294556, "learning_rate": 1.125663565262507e-05, "loss": 0.8903, "step": 8152 }, { "epoch": 0.47622663551401867, "grad_norm": 0.8995001912117004, "learning_rate": 1.1254758785043516e-05, "loss": 0.7367, "step": 8153 }, { "epoch": 0.476285046728972, "grad_norm": 1.2384425401687622, "learning_rate": 1.1252881872553325e-05, "loss": 0.6984, "step": 8154 }, { "epoch": 0.47634345794392524, "grad_norm": 1.1838713884353638, "learning_rate": 1.1251004915221663e-05, "loss": 0.6433, "step": 8155 }, { "epoch": 0.4764018691588785, "grad_norm": 1.2868002653121948, "learning_rate": 1.1249127913115714e-05, "loss": 0.8815, "step": 8156 }, { "epoch": 0.47646028037383176, "grad_norm": 1.4241904020309448, "learning_rate": 1.1247250866302657e-05, "loss": 0.778, "step": 8157 }, { "epoch": 0.47651869158878507, "grad_norm": 1.2292195558547974, "learning_rate": 1.1245373774849669e-05, "loss": 0.7689, "step": 8158 }, { "epoch": 0.47657710280373833, "grad_norm": 1.2760939598083496, "learning_rate": 1.1243496638823938e-05, "loss": 0.8187, "step": 8159 }, { "epoch": 0.4766355140186916, "grad_norm": 0.8686109185218811, "learning_rate": 1.124161945829264e-05, "loss": 0.6791, "step": 8160 }, { "epoch": 0.47669392523364484, "grad_norm": 1.267501950263977, "learning_rate": 1.123974223332297e-05, "loss": 0.7457, "step": 8161 }, { "epoch": 0.47675233644859816, "grad_norm": 1.514755129814148, "learning_rate": 1.1237864963982108e-05, "loss": 0.9301, "step": 8162 }, { "epoch": 0.4768107476635514, "grad_norm": 1.0144155025482178, "learning_rate": 1.1235987650337245e-05, "loss": 0.7329, "step": 8163 }, { "epoch": 0.4768691588785047, "grad_norm": 1.128238320350647, "learning_rate": 1.1234110292455573e-05, "loss": 0.6868, "step": 8164 }, { "epoch": 0.47692757009345793, "grad_norm": 1.1776700019836426, "learning_rate": 1.1232232890404282e-05, "loss": 0.7691, "step": 8165 }, { "epoch": 0.4769859813084112, "grad_norm": 1.5818248987197876, "learning_rate": 1.1230355444250563e-05, "loss": 0.7747, "step": 8166 }, { "epoch": 0.4770443925233645, "grad_norm": 1.031643271446228, "learning_rate": 1.1228477954061614e-05, "loss": 0.734, "step": 8167 }, { "epoch": 0.47710280373831776, "grad_norm": 1.1571756601333618, "learning_rate": 1.1226600419904634e-05, "loss": 0.8271, "step": 8168 }, { "epoch": 0.477161214953271, "grad_norm": 1.467250943183899, "learning_rate": 1.1224722841846815e-05, "loss": 0.9237, "step": 8169 }, { "epoch": 0.4772196261682243, "grad_norm": 1.3182400465011597, "learning_rate": 1.1222845219955364e-05, "loss": 0.6415, "step": 8170 }, { "epoch": 0.4772780373831776, "grad_norm": 1.0274627208709717, "learning_rate": 1.1220967554297478e-05, "loss": 0.65, "step": 8171 }, { "epoch": 0.47733644859813085, "grad_norm": 0.9236146211624146, "learning_rate": 1.1219089844940356e-05, "loss": 0.653, "step": 8172 }, { "epoch": 0.4773948598130841, "grad_norm": 0.9677895903587341, "learning_rate": 1.1217212091951211e-05, "loss": 0.7498, "step": 8173 }, { "epoch": 0.47745327102803736, "grad_norm": 1.300561785697937, "learning_rate": 1.1215334295397244e-05, "loss": 0.9196, "step": 8174 }, { "epoch": 0.4775116822429907, "grad_norm": 1.249969720840454, "learning_rate": 1.1213456455345664e-05, "loss": 0.8686, "step": 8175 }, { "epoch": 0.47757009345794393, "grad_norm": 1.5132062435150146, "learning_rate": 1.1211578571863679e-05, "loss": 0.7723, "step": 8176 }, { "epoch": 0.4776285046728972, "grad_norm": 1.2263469696044922, "learning_rate": 1.12097006450185e-05, "loss": 0.8957, "step": 8177 }, { "epoch": 0.47768691588785045, "grad_norm": 1.3683044910430908, "learning_rate": 1.1207822674877338e-05, "loss": 0.8709, "step": 8178 }, { "epoch": 0.47774532710280376, "grad_norm": 1.0116894245147705, "learning_rate": 1.1205944661507413e-05, "loss": 0.7688, "step": 8179 }, { "epoch": 0.477803738317757, "grad_norm": 1.185796856880188, "learning_rate": 1.1204066604975932e-05, "loss": 0.7047, "step": 8180 }, { "epoch": 0.4778621495327103, "grad_norm": 1.3482515811920166, "learning_rate": 1.1202188505350115e-05, "loss": 0.8022, "step": 8181 }, { "epoch": 0.47792056074766354, "grad_norm": 1.5625789165496826, "learning_rate": 1.1200310362697185e-05, "loss": 0.827, "step": 8182 }, { "epoch": 0.47797897196261685, "grad_norm": 1.1746996641159058, "learning_rate": 1.1198432177084352e-05, "loss": 0.7014, "step": 8183 }, { "epoch": 0.4780373831775701, "grad_norm": 1.4105138778686523, "learning_rate": 1.119655394857885e-05, "loss": 0.6605, "step": 8184 }, { "epoch": 0.47809579439252337, "grad_norm": 1.1436553001403809, "learning_rate": 1.1194675677247888e-05, "loss": 0.7617, "step": 8185 }, { "epoch": 0.4781542056074766, "grad_norm": 1.3134160041809082, "learning_rate": 1.1192797363158702e-05, "loss": 0.8464, "step": 8186 }, { "epoch": 0.4782126168224299, "grad_norm": 1.8595021963119507, "learning_rate": 1.1190919006378516e-05, "loss": 0.9862, "step": 8187 }, { "epoch": 0.4782710280373832, "grad_norm": 1.391549825668335, "learning_rate": 1.1189040606974552e-05, "loss": 0.8955, "step": 8188 }, { "epoch": 0.47832943925233645, "grad_norm": 1.3020095825195312, "learning_rate": 1.1187162165014047e-05, "loss": 0.8333, "step": 8189 }, { "epoch": 0.4783878504672897, "grad_norm": 1.135400414466858, "learning_rate": 1.1185283680564225e-05, "loss": 0.8794, "step": 8190 }, { "epoch": 0.47844626168224297, "grad_norm": 1.4474550485610962, "learning_rate": 1.118340515369232e-05, "loss": 0.6893, "step": 8191 }, { "epoch": 0.4785046728971963, "grad_norm": 1.255622386932373, "learning_rate": 1.1181526584465567e-05, "loss": 0.6471, "step": 8192 }, { "epoch": 0.47856308411214954, "grad_norm": 0.8738980293273926, "learning_rate": 1.1179647972951202e-05, "loss": 0.6053, "step": 8193 }, { "epoch": 0.4786214953271028, "grad_norm": 5.038303375244141, "learning_rate": 1.1177769319216459e-05, "loss": 0.8812, "step": 8194 }, { "epoch": 0.47867990654205606, "grad_norm": 1.0718841552734375, "learning_rate": 1.1175890623328578e-05, "loss": 0.8136, "step": 8195 }, { "epoch": 0.47873831775700937, "grad_norm": 1.3946545124053955, "learning_rate": 1.1174011885354798e-05, "loss": 0.6722, "step": 8196 }, { "epoch": 0.4787967289719626, "grad_norm": 2.542717933654785, "learning_rate": 1.117213310536236e-05, "loss": 1.0057, "step": 8197 }, { "epoch": 0.4788551401869159, "grad_norm": 1.432792067527771, "learning_rate": 1.1170254283418511e-05, "loss": 0.6847, "step": 8198 }, { "epoch": 0.47891355140186914, "grad_norm": 2.782658338546753, "learning_rate": 1.1168375419590489e-05, "loss": 0.8417, "step": 8199 }, { "epoch": 0.47897196261682246, "grad_norm": 1.4169377088546753, "learning_rate": 1.1166496513945541e-05, "loss": 0.7248, "step": 8200 }, { "epoch": 0.4790303738317757, "grad_norm": 2.0551624298095703, "learning_rate": 1.1164617566550919e-05, "loss": 0.6816, "step": 8201 }, { "epoch": 0.47908878504672897, "grad_norm": 1.7728224992752075, "learning_rate": 1.1162738577473866e-05, "loss": 0.794, "step": 8202 }, { "epoch": 0.47914719626168223, "grad_norm": 1.7983160018920898, "learning_rate": 1.116085954678164e-05, "loss": 1.0449, "step": 8203 }, { "epoch": 0.4792056074766355, "grad_norm": 1.5668880939483643, "learning_rate": 1.1158980474541484e-05, "loss": 0.612, "step": 8204 }, { "epoch": 0.4792640186915888, "grad_norm": 2.12135910987854, "learning_rate": 1.115710136082065e-05, "loss": 0.7862, "step": 8205 }, { "epoch": 0.47932242990654206, "grad_norm": 1.2382994890213013, "learning_rate": 1.1155222205686403e-05, "loss": 0.7887, "step": 8206 }, { "epoch": 0.4793808411214953, "grad_norm": 1.590722680091858, "learning_rate": 1.1153343009205993e-05, "loss": 0.7814, "step": 8207 }, { "epoch": 0.4794392523364486, "grad_norm": 1.3874232769012451, "learning_rate": 1.1151463771446678e-05, "loss": 0.7222, "step": 8208 }, { "epoch": 0.4794976635514019, "grad_norm": 1.223403811454773, "learning_rate": 1.1149584492475718e-05, "loss": 0.6553, "step": 8209 }, { "epoch": 0.47955607476635514, "grad_norm": 1.185109257698059, "learning_rate": 1.114770517236037e-05, "loss": 0.6275, "step": 8210 }, { "epoch": 0.4796144859813084, "grad_norm": 2.007439613342285, "learning_rate": 1.1145825811167903e-05, "loss": 0.9005, "step": 8211 }, { "epoch": 0.47967289719626166, "grad_norm": 1.5324971675872803, "learning_rate": 1.1143946408965579e-05, "loss": 0.9905, "step": 8212 }, { "epoch": 0.479731308411215, "grad_norm": 1.452138066291809, "learning_rate": 1.1142066965820655e-05, "loss": 0.862, "step": 8213 }, { "epoch": 0.47978971962616823, "grad_norm": 1.3850023746490479, "learning_rate": 1.1140187481800406e-05, "loss": 0.878, "step": 8214 }, { "epoch": 0.4798481308411215, "grad_norm": 1.543061375617981, "learning_rate": 1.1138307956972097e-05, "loss": 0.8445, "step": 8215 }, { "epoch": 0.47990654205607475, "grad_norm": 1.1442172527313232, "learning_rate": 1.1136428391402995e-05, "loss": 0.7586, "step": 8216 }, { "epoch": 0.47996495327102806, "grad_norm": 1.4244601726531982, "learning_rate": 1.1134548785160382e-05, "loss": 0.7572, "step": 8217 }, { "epoch": 0.4800233644859813, "grad_norm": 1.5059618949890137, "learning_rate": 1.1132669138311513e-05, "loss": 0.8156, "step": 8218 }, { "epoch": 0.4800817757009346, "grad_norm": 1.8389860391616821, "learning_rate": 1.1130789450923677e-05, "loss": 1.018, "step": 8219 }, { "epoch": 0.48014018691588783, "grad_norm": 1.323753833770752, "learning_rate": 1.1128909723064138e-05, "loss": 0.7639, "step": 8220 }, { "epoch": 0.48019859813084115, "grad_norm": 1.5453143119812012, "learning_rate": 1.1127029954800181e-05, "loss": 1.0033, "step": 8221 }, { "epoch": 0.4802570093457944, "grad_norm": 1.5289928913116455, "learning_rate": 1.1125150146199082e-05, "loss": 0.8084, "step": 8222 }, { "epoch": 0.48031542056074766, "grad_norm": 1.30830717086792, "learning_rate": 1.1123270297328118e-05, "loss": 0.903, "step": 8223 }, { "epoch": 0.4803738317757009, "grad_norm": 1.1369297504425049, "learning_rate": 1.1121390408254569e-05, "loss": 0.7697, "step": 8224 }, { "epoch": 0.4804322429906542, "grad_norm": 2.5175163745880127, "learning_rate": 1.111951047904572e-05, "loss": 0.8617, "step": 8225 }, { "epoch": 0.4804906542056075, "grad_norm": 1.0663288831710815, "learning_rate": 1.111763050976886e-05, "loss": 0.7095, "step": 8226 }, { "epoch": 0.48054906542056075, "grad_norm": 1.1239643096923828, "learning_rate": 1.1115750500491265e-05, "loss": 0.7606, "step": 8227 }, { "epoch": 0.480607476635514, "grad_norm": 2.3816986083984375, "learning_rate": 1.1113870451280228e-05, "loss": 0.9418, "step": 8228 }, { "epoch": 0.48066588785046727, "grad_norm": 1.409247875213623, "learning_rate": 1.1111990362203034e-05, "loss": 0.7623, "step": 8229 }, { "epoch": 0.4807242990654206, "grad_norm": 1.7720226049423218, "learning_rate": 1.1110110233326972e-05, "loss": 0.8356, "step": 8230 }, { "epoch": 0.48078271028037384, "grad_norm": 2.429680585861206, "learning_rate": 1.1108230064719336e-05, "loss": 0.7455, "step": 8231 }, { "epoch": 0.4808411214953271, "grad_norm": 1.444208025932312, "learning_rate": 1.110634985644742e-05, "loss": 0.696, "step": 8232 }, { "epoch": 0.48089953271028035, "grad_norm": 2.854828357696533, "learning_rate": 1.1104469608578514e-05, "loss": 0.7927, "step": 8233 }, { "epoch": 0.48095794392523367, "grad_norm": 1.365604281425476, "learning_rate": 1.1102589321179912e-05, "loss": 1.093, "step": 8234 }, { "epoch": 0.4810163551401869, "grad_norm": 2.1085519790649414, "learning_rate": 1.1100708994318916e-05, "loss": 0.7672, "step": 8235 }, { "epoch": 0.4810747663551402, "grad_norm": 2.660736083984375, "learning_rate": 1.109882862806282e-05, "loss": 0.7762, "step": 8236 }, { "epoch": 0.48113317757009344, "grad_norm": 2.9023361206054688, "learning_rate": 1.1096948222478928e-05, "loss": 0.7592, "step": 8237 }, { "epoch": 0.48119158878504675, "grad_norm": 1.8543391227722168, "learning_rate": 1.1095067777634535e-05, "loss": 0.7246, "step": 8238 }, { "epoch": 0.48125, "grad_norm": 2.4455149173736572, "learning_rate": 1.1093187293596946e-05, "loss": 1.0317, "step": 8239 }, { "epoch": 0.48130841121495327, "grad_norm": 1.7023518085479736, "learning_rate": 1.1091306770433466e-05, "loss": 0.8909, "step": 8240 }, { "epoch": 0.4813668224299065, "grad_norm": 1.6903074979782104, "learning_rate": 1.1089426208211399e-05, "loss": 0.8939, "step": 8241 }, { "epoch": 0.48142523364485984, "grad_norm": 1.0873355865478516, "learning_rate": 1.1087545606998049e-05, "loss": 0.8203, "step": 8242 }, { "epoch": 0.4814836448598131, "grad_norm": 1.1359853744506836, "learning_rate": 1.1085664966860728e-05, "loss": 0.7025, "step": 8243 }, { "epoch": 0.48154205607476636, "grad_norm": 1.3991005420684814, "learning_rate": 1.1083784287866746e-05, "loss": 0.6042, "step": 8244 }, { "epoch": 0.4816004672897196, "grad_norm": 1.5581238269805908, "learning_rate": 1.108190357008341e-05, "loss": 0.9001, "step": 8245 }, { "epoch": 0.48165887850467287, "grad_norm": 1.185274600982666, "learning_rate": 1.1080022813578035e-05, "loss": 0.6663, "step": 8246 }, { "epoch": 0.4817172897196262, "grad_norm": 1.6215320825576782, "learning_rate": 1.1078142018417932e-05, "loss": 0.9298, "step": 8247 }, { "epoch": 0.48177570093457944, "grad_norm": 1.156678557395935, "learning_rate": 1.107626118467042e-05, "loss": 0.7571, "step": 8248 }, { "epoch": 0.4818341121495327, "grad_norm": 1.1663274765014648, "learning_rate": 1.1074380312402809e-05, "loss": 0.884, "step": 8249 }, { "epoch": 0.48189252336448596, "grad_norm": 1.261168122291565, "learning_rate": 1.1072499401682422e-05, "loss": 0.8175, "step": 8250 }, { "epoch": 0.48195093457943927, "grad_norm": 1.224462628364563, "learning_rate": 1.1070618452576576e-05, "loss": 0.8562, "step": 8251 }, { "epoch": 0.48200934579439253, "grad_norm": 1.007840871810913, "learning_rate": 1.1068737465152592e-05, "loss": 0.6303, "step": 8252 }, { "epoch": 0.4820677570093458, "grad_norm": 0.9743557572364807, "learning_rate": 1.1066856439477792e-05, "loss": 0.6657, "step": 8253 }, { "epoch": 0.48212616822429905, "grad_norm": 1.6455717086791992, "learning_rate": 1.1064975375619498e-05, "loss": 0.8704, "step": 8254 }, { "epoch": 0.48218457943925236, "grad_norm": 1.1491280794143677, "learning_rate": 1.1063094273645032e-05, "loss": 0.8504, "step": 8255 }, { "epoch": 0.4822429906542056, "grad_norm": 1.3718830347061157, "learning_rate": 1.1061213133621728e-05, "loss": 0.9381, "step": 8256 }, { "epoch": 0.4823014018691589, "grad_norm": 1.8236910104751587, "learning_rate": 1.1059331955616905e-05, "loss": 0.9048, "step": 8257 }, { "epoch": 0.48235981308411213, "grad_norm": 1.3153096437454224, "learning_rate": 1.1057450739697896e-05, "loss": 0.8378, "step": 8258 }, { "epoch": 0.48241822429906545, "grad_norm": 1.2217111587524414, "learning_rate": 1.1055569485932029e-05, "loss": 0.7807, "step": 8259 }, { "epoch": 0.4824766355140187, "grad_norm": 1.5282347202301025, "learning_rate": 1.1053688194386636e-05, "loss": 0.858, "step": 8260 }, { "epoch": 0.48253504672897196, "grad_norm": 1.1340142488479614, "learning_rate": 1.1051806865129052e-05, "loss": 0.8503, "step": 8261 }, { "epoch": 0.4825934579439252, "grad_norm": 1.357850193977356, "learning_rate": 1.1049925498226608e-05, "loss": 0.9002, "step": 8262 }, { "epoch": 0.4826518691588785, "grad_norm": 1.9453190565109253, "learning_rate": 1.1048044093746637e-05, "loss": 0.8215, "step": 8263 }, { "epoch": 0.4827102803738318, "grad_norm": 1.0209249258041382, "learning_rate": 1.104616265175648e-05, "loss": 0.7667, "step": 8264 }, { "epoch": 0.48276869158878505, "grad_norm": 1.3877168893814087, "learning_rate": 1.1044281172323476e-05, "loss": 0.7863, "step": 8265 }, { "epoch": 0.4828271028037383, "grad_norm": 1.4602329730987549, "learning_rate": 1.1042399655514961e-05, "loss": 0.7981, "step": 8266 }, { "epoch": 0.48288551401869156, "grad_norm": 1.1285449266433716, "learning_rate": 1.1040518101398277e-05, "loss": 0.7356, "step": 8267 }, { "epoch": 0.4829439252336449, "grad_norm": 1.4123297929763794, "learning_rate": 1.1038636510040764e-05, "loss": 0.7678, "step": 8268 }, { "epoch": 0.48300233644859814, "grad_norm": 1.2662993669509888, "learning_rate": 1.103675488150977e-05, "loss": 0.62, "step": 8269 }, { "epoch": 0.4830607476635514, "grad_norm": 1.3227360248565674, "learning_rate": 1.103487321587264e-05, "loss": 0.8814, "step": 8270 }, { "epoch": 0.48311915887850465, "grad_norm": 0.8556036949157715, "learning_rate": 1.103299151319671e-05, "loss": 0.5997, "step": 8271 }, { "epoch": 0.48317757009345796, "grad_norm": 1.109300971031189, "learning_rate": 1.1031109773549337e-05, "loss": 0.6161, "step": 8272 }, { "epoch": 0.4832359813084112, "grad_norm": 1.2362983226776123, "learning_rate": 1.1029227996997869e-05, "loss": 0.8964, "step": 8273 }, { "epoch": 0.4832943925233645, "grad_norm": 1.7991005182266235, "learning_rate": 1.1027346183609653e-05, "loss": 0.9747, "step": 8274 }, { "epoch": 0.48335280373831774, "grad_norm": 1.399539828300476, "learning_rate": 1.1025464333452043e-05, "loss": 0.8207, "step": 8275 }, { "epoch": 0.48341121495327105, "grad_norm": 1.123709797859192, "learning_rate": 1.1023582446592388e-05, "loss": 0.8425, "step": 8276 }, { "epoch": 0.4834696261682243, "grad_norm": 1.2299323081970215, "learning_rate": 1.1021700523098046e-05, "loss": 0.8273, "step": 8277 }, { "epoch": 0.48352803738317757, "grad_norm": 1.6205369234085083, "learning_rate": 1.1019818563036371e-05, "loss": 1.0305, "step": 8278 }, { "epoch": 0.4835864485981308, "grad_norm": 1.5318260192871094, "learning_rate": 1.1017936566474717e-05, "loss": 0.7978, "step": 8279 }, { "epoch": 0.48364485981308414, "grad_norm": 1.3795362710952759, "learning_rate": 1.1016054533480448e-05, "loss": 0.9591, "step": 8280 }, { "epoch": 0.4837032710280374, "grad_norm": 1.4061784744262695, "learning_rate": 1.1014172464120914e-05, "loss": 0.9072, "step": 8281 }, { "epoch": 0.48376168224299065, "grad_norm": 1.25641667842865, "learning_rate": 1.1012290358463482e-05, "loss": 0.7405, "step": 8282 }, { "epoch": 0.4838200934579439, "grad_norm": 1.5442231893539429, "learning_rate": 1.1010408216575514e-05, "loss": 0.6934, "step": 8283 }, { "epoch": 0.48387850467289717, "grad_norm": 1.803606390953064, "learning_rate": 1.1008526038524372e-05, "loss": 0.8793, "step": 8284 }, { "epoch": 0.4839369158878505, "grad_norm": 1.5157074928283691, "learning_rate": 1.1006643824377418e-05, "loss": 0.9167, "step": 8285 }, { "epoch": 0.48399532710280374, "grad_norm": 1.77335786819458, "learning_rate": 1.100476157420202e-05, "loss": 0.9074, "step": 8286 }, { "epoch": 0.484053738317757, "grad_norm": 1.233156442642212, "learning_rate": 1.1002879288065546e-05, "loss": 0.8409, "step": 8287 }, { "epoch": 0.48411214953271026, "grad_norm": 1.5208029747009277, "learning_rate": 1.100099696603536e-05, "loss": 0.7586, "step": 8288 }, { "epoch": 0.48417056074766357, "grad_norm": 1.7704863548278809, "learning_rate": 1.0999114608178837e-05, "loss": 0.7617, "step": 8289 }, { "epoch": 0.4842289719626168, "grad_norm": 0.9940364360809326, "learning_rate": 1.0997232214563345e-05, "loss": 0.8386, "step": 8290 }, { "epoch": 0.4842873831775701, "grad_norm": 2.0266191959381104, "learning_rate": 1.0995349785256258e-05, "loss": 0.8405, "step": 8291 }, { "epoch": 0.48434579439252334, "grad_norm": 1.4931440353393555, "learning_rate": 1.0993467320324944e-05, "loss": 0.9595, "step": 8292 }, { "epoch": 0.48440420560747666, "grad_norm": 1.6326684951782227, "learning_rate": 1.0991584819836782e-05, "loss": 0.8, "step": 8293 }, { "epoch": 0.4844626168224299, "grad_norm": 1.1839896440505981, "learning_rate": 1.0989702283859151e-05, "loss": 0.7211, "step": 8294 }, { "epoch": 0.4845210280373832, "grad_norm": 1.085160493850708, "learning_rate": 1.0987819712459423e-05, "loss": 0.7115, "step": 8295 }, { "epoch": 0.48457943925233643, "grad_norm": 1.3837530612945557, "learning_rate": 1.0985937105704976e-05, "loss": 0.7831, "step": 8296 }, { "epoch": 0.48463785046728974, "grad_norm": 1.5989174842834473, "learning_rate": 1.0984054463663192e-05, "loss": 0.7413, "step": 8297 }, { "epoch": 0.484696261682243, "grad_norm": 2.9685347080230713, "learning_rate": 1.0982171786401452e-05, "loss": 0.6996, "step": 8298 }, { "epoch": 0.48475467289719626, "grad_norm": 1.4959617853164673, "learning_rate": 1.0980289073987141e-05, "loss": 0.639, "step": 8299 }, { "epoch": 0.4848130841121495, "grad_norm": 1.0556660890579224, "learning_rate": 1.0978406326487636e-05, "loss": 0.6657, "step": 8300 }, { "epoch": 0.48487149532710283, "grad_norm": 2.3248960971832275, "learning_rate": 1.0976523543970326e-05, "loss": 0.8579, "step": 8301 }, { "epoch": 0.4849299065420561, "grad_norm": 1.0492607355117798, "learning_rate": 1.0974640726502594e-05, "loss": 0.7146, "step": 8302 }, { "epoch": 0.48498831775700935, "grad_norm": 1.1819878816604614, "learning_rate": 1.0972757874151834e-05, "loss": 0.7571, "step": 8303 }, { "epoch": 0.4850467289719626, "grad_norm": 0.9635971784591675, "learning_rate": 1.0970874986985427e-05, "loss": 0.6451, "step": 8304 }, { "epoch": 0.48510514018691586, "grad_norm": 1.3710709810256958, "learning_rate": 1.096899206507077e-05, "loss": 0.6037, "step": 8305 }, { "epoch": 0.4851635514018692, "grad_norm": 1.4173600673675537, "learning_rate": 1.0967109108475244e-05, "loss": 0.8661, "step": 8306 }, { "epoch": 0.48522196261682243, "grad_norm": 2.8306150436401367, "learning_rate": 1.096522611726625e-05, "loss": 0.6532, "step": 8307 }, { "epoch": 0.4852803738317757, "grad_norm": 1.2978571653366089, "learning_rate": 1.0963343091511178e-05, "loss": 0.9035, "step": 8308 }, { "epoch": 0.48533878504672895, "grad_norm": 1.36392080783844, "learning_rate": 1.0961460031277424e-05, "loss": 0.759, "step": 8309 }, { "epoch": 0.48539719626168226, "grad_norm": 1.414556622505188, "learning_rate": 1.0959576936632384e-05, "loss": 0.7488, "step": 8310 }, { "epoch": 0.4854556074766355, "grad_norm": 1.707192301750183, "learning_rate": 1.0957693807643455e-05, "loss": 0.8243, "step": 8311 }, { "epoch": 0.4855140186915888, "grad_norm": 1.7057021856307983, "learning_rate": 1.0955810644378031e-05, "loss": 0.8605, "step": 8312 }, { "epoch": 0.48557242990654204, "grad_norm": 2.1861183643341064, "learning_rate": 1.0953927446903518e-05, "loss": 0.8018, "step": 8313 }, { "epoch": 0.48563084112149535, "grad_norm": 1.14665687084198, "learning_rate": 1.0952044215287318e-05, "loss": 0.6859, "step": 8314 }, { "epoch": 0.4856892523364486, "grad_norm": 1.614440679550171, "learning_rate": 1.0950160949596824e-05, "loss": 1.0519, "step": 8315 }, { "epoch": 0.48574766355140186, "grad_norm": 1.3982418775558472, "learning_rate": 1.0948277649899448e-05, "loss": 0.8674, "step": 8316 }, { "epoch": 0.4858060747663551, "grad_norm": 1.5884084701538086, "learning_rate": 1.0946394316262591e-05, "loss": 1.0574, "step": 8317 }, { "epoch": 0.48586448598130844, "grad_norm": 1.0647684335708618, "learning_rate": 1.0944510948753656e-05, "loss": 0.9796, "step": 8318 }, { "epoch": 0.4859228971962617, "grad_norm": 1.0421050786972046, "learning_rate": 1.0942627547440058e-05, "loss": 0.8332, "step": 8319 }, { "epoch": 0.48598130841121495, "grad_norm": 1.3795182704925537, "learning_rate": 1.0940744112389199e-05, "loss": 0.8041, "step": 8320 }, { "epoch": 0.4860397196261682, "grad_norm": 1.2612638473510742, "learning_rate": 1.0938860643668487e-05, "loss": 0.7841, "step": 8321 }, { "epoch": 0.4860981308411215, "grad_norm": 1.3005449771881104, "learning_rate": 1.0936977141345337e-05, "loss": 0.665, "step": 8322 }, { "epoch": 0.4861565420560748, "grad_norm": 1.342862844467163, "learning_rate": 1.093509360548716e-05, "loss": 0.7309, "step": 8323 }, { "epoch": 0.48621495327102804, "grad_norm": 1.0868120193481445, "learning_rate": 1.0933210036161368e-05, "loss": 0.8041, "step": 8324 }, { "epoch": 0.4862733644859813, "grad_norm": 1.344976544380188, "learning_rate": 1.0931326433435374e-05, "loss": 0.8918, "step": 8325 }, { "epoch": 0.48633177570093455, "grad_norm": 0.9622787237167358, "learning_rate": 1.0929442797376593e-05, "loss": 0.7848, "step": 8326 }, { "epoch": 0.48639018691588787, "grad_norm": 1.0755444765090942, "learning_rate": 1.0927559128052445e-05, "loss": 0.7381, "step": 8327 }, { "epoch": 0.4864485981308411, "grad_norm": 0.9408852458000183, "learning_rate": 1.0925675425530348e-05, "loss": 0.6795, "step": 8328 }, { "epoch": 0.4865070093457944, "grad_norm": 1.460055947303772, "learning_rate": 1.0923791689877716e-05, "loss": 0.9861, "step": 8329 }, { "epoch": 0.48656542056074764, "grad_norm": 1.0432909727096558, "learning_rate": 1.0921907921161975e-05, "loss": 0.7859, "step": 8330 }, { "epoch": 0.48662383177570095, "grad_norm": 1.87828528881073, "learning_rate": 1.0920024119450539e-05, "loss": 0.7746, "step": 8331 }, { "epoch": 0.4866822429906542, "grad_norm": 1.403098225593567, "learning_rate": 1.0918140284810836e-05, "loss": 0.6831, "step": 8332 }, { "epoch": 0.48674065420560747, "grad_norm": 1.8060262203216553, "learning_rate": 1.091625641731029e-05, "loss": 0.8857, "step": 8333 }, { "epoch": 0.48679906542056073, "grad_norm": 1.2390469312667847, "learning_rate": 1.0914372517016323e-05, "loss": 0.7694, "step": 8334 }, { "epoch": 0.48685747663551404, "grad_norm": 1.5144188404083252, "learning_rate": 1.0912488583996364e-05, "loss": 0.7849, "step": 8335 }, { "epoch": 0.4869158878504673, "grad_norm": 1.2528231143951416, "learning_rate": 1.0910604618317839e-05, "loss": 0.5849, "step": 8336 }, { "epoch": 0.48697429906542056, "grad_norm": 1.0429611206054688, "learning_rate": 1.0908720620048173e-05, "loss": 0.8188, "step": 8337 }, { "epoch": 0.4870327102803738, "grad_norm": 0.8799006342887878, "learning_rate": 1.0906836589254803e-05, "loss": 0.8293, "step": 8338 }, { "epoch": 0.48709112149532713, "grad_norm": 1.4960452318191528, "learning_rate": 1.0904952526005153e-05, "loss": 0.8425, "step": 8339 }, { "epoch": 0.4871495327102804, "grad_norm": 1.0037095546722412, "learning_rate": 1.0903068430366654e-05, "loss": 0.8102, "step": 8340 }, { "epoch": 0.48720794392523364, "grad_norm": 1.7748695611953735, "learning_rate": 1.0901184302406747e-05, "loss": 1.0463, "step": 8341 }, { "epoch": 0.4872663551401869, "grad_norm": 1.606176733970642, "learning_rate": 1.0899300142192857e-05, "loss": 0.8472, "step": 8342 }, { "epoch": 0.48732476635514016, "grad_norm": 1.0778439044952393, "learning_rate": 1.0897415949792427e-05, "loss": 0.643, "step": 8343 }, { "epoch": 0.4873831775700935, "grad_norm": 1.1715461015701294, "learning_rate": 1.089553172527289e-05, "loss": 0.6469, "step": 8344 }, { "epoch": 0.48744158878504673, "grad_norm": 1.2624008655548096, "learning_rate": 1.089364746870168e-05, "loss": 0.9408, "step": 8345 }, { "epoch": 0.4875, "grad_norm": 1.250942587852478, "learning_rate": 1.0891763180146242e-05, "loss": 0.8587, "step": 8346 }, { "epoch": 0.48755841121495325, "grad_norm": 1.580391526222229, "learning_rate": 1.0889878859674015e-05, "loss": 0.7436, "step": 8347 }, { "epoch": 0.48761682242990656, "grad_norm": 1.247432827949524, "learning_rate": 1.0887994507352435e-05, "loss": 0.8514, "step": 8348 }, { "epoch": 0.4876752336448598, "grad_norm": 0.9850144386291504, "learning_rate": 1.0886110123248952e-05, "loss": 0.5993, "step": 8349 }, { "epoch": 0.4877336448598131, "grad_norm": 1.3098256587982178, "learning_rate": 1.0884225707431003e-05, "loss": 0.8523, "step": 8350 }, { "epoch": 0.48779205607476633, "grad_norm": 1.304616093635559, "learning_rate": 1.0882341259966032e-05, "loss": 1.0076, "step": 8351 }, { "epoch": 0.48785046728971965, "grad_norm": 1.1694142818450928, "learning_rate": 1.0880456780921492e-05, "loss": 0.6877, "step": 8352 }, { "epoch": 0.4879088785046729, "grad_norm": 1.3504852056503296, "learning_rate": 1.0878572270364822e-05, "loss": 0.7159, "step": 8353 }, { "epoch": 0.48796728971962616, "grad_norm": 1.7157386541366577, "learning_rate": 1.087668772836347e-05, "loss": 0.8894, "step": 8354 }, { "epoch": 0.4880257009345794, "grad_norm": 2.322683334350586, "learning_rate": 1.0874803154984892e-05, "loss": 0.763, "step": 8355 }, { "epoch": 0.48808411214953273, "grad_norm": 0.9903655052185059, "learning_rate": 1.0872918550296535e-05, "loss": 0.6215, "step": 8356 }, { "epoch": 0.488142523364486, "grad_norm": 1.228106141090393, "learning_rate": 1.0871033914365844e-05, "loss": 0.7529, "step": 8357 }, { "epoch": 0.48820093457943925, "grad_norm": 1.4413459300994873, "learning_rate": 1.0869149247260282e-05, "loss": 0.7614, "step": 8358 }, { "epoch": 0.4882593457943925, "grad_norm": 1.5778359174728394, "learning_rate": 1.0867264549047292e-05, "loss": 0.7706, "step": 8359 }, { "epoch": 0.4883177570093458, "grad_norm": 1.8460171222686768, "learning_rate": 1.0865379819794336e-05, "loss": 0.8055, "step": 8360 }, { "epoch": 0.4883761682242991, "grad_norm": 1.539494276046753, "learning_rate": 1.0863495059568868e-05, "loss": 0.9623, "step": 8361 }, { "epoch": 0.48843457943925234, "grad_norm": 1.2928950786590576, "learning_rate": 1.0861610268438343e-05, "loss": 0.7779, "step": 8362 }, { "epoch": 0.4884929906542056, "grad_norm": 2.1858468055725098, "learning_rate": 1.0859725446470222e-05, "loss": 0.7837, "step": 8363 }, { "epoch": 0.48855140186915885, "grad_norm": 1.3475478887557983, "learning_rate": 1.0857840593731958e-05, "loss": 0.6848, "step": 8364 }, { "epoch": 0.48860981308411217, "grad_norm": 1.6058651208877563, "learning_rate": 1.0855955710291017e-05, "loss": 0.6687, "step": 8365 }, { "epoch": 0.4886682242990654, "grad_norm": 1.3301249742507935, "learning_rate": 1.085407079621486e-05, "loss": 0.8508, "step": 8366 }, { "epoch": 0.4887266355140187, "grad_norm": 1.4074463844299316, "learning_rate": 1.0852185851570945e-05, "loss": 0.6817, "step": 8367 }, { "epoch": 0.48878504672897194, "grad_norm": 2.9444775581359863, "learning_rate": 1.085030087642674e-05, "loss": 0.6359, "step": 8368 }, { "epoch": 0.48884345794392525, "grad_norm": 1.4282091856002808, "learning_rate": 1.0848415870849707e-05, "loss": 0.8079, "step": 8369 }, { "epoch": 0.4889018691588785, "grad_norm": 1.7980270385742188, "learning_rate": 1.0846530834907309e-05, "loss": 0.899, "step": 8370 }, { "epoch": 0.48896028037383177, "grad_norm": 1.4139240980148315, "learning_rate": 1.0844645768667018e-05, "loss": 0.8258, "step": 8371 }, { "epoch": 0.489018691588785, "grad_norm": 1.2203325033187866, "learning_rate": 1.0842760672196304e-05, "loss": 0.7196, "step": 8372 }, { "epoch": 0.48907710280373834, "grad_norm": 1.4056260585784912, "learning_rate": 1.0840875545562625e-05, "loss": 0.7795, "step": 8373 }, { "epoch": 0.4891355140186916, "grad_norm": 0.9989223480224609, "learning_rate": 1.0838990388833461e-05, "loss": 0.7548, "step": 8374 }, { "epoch": 0.48919392523364486, "grad_norm": 1.3282994031906128, "learning_rate": 1.0837105202076281e-05, "loss": 0.9009, "step": 8375 }, { "epoch": 0.4892523364485981, "grad_norm": 0.9960129261016846, "learning_rate": 1.083521998535855e-05, "loss": 0.6588, "step": 8376 }, { "epoch": 0.4893107476635514, "grad_norm": 1.1546396017074585, "learning_rate": 1.0833334738747752e-05, "loss": 0.8801, "step": 8377 }, { "epoch": 0.4893691588785047, "grad_norm": 1.35297429561615, "learning_rate": 1.0831449462311352e-05, "loss": 0.8517, "step": 8378 }, { "epoch": 0.48942757009345794, "grad_norm": 0.9250224232673645, "learning_rate": 1.082956415611683e-05, "loss": 0.7415, "step": 8379 }, { "epoch": 0.4894859813084112, "grad_norm": 1.305645227432251, "learning_rate": 1.0827678820231662e-05, "loss": 0.7028, "step": 8380 }, { "epoch": 0.4895443925233645, "grad_norm": 1.0893300771713257, "learning_rate": 1.0825793454723325e-05, "loss": 0.7784, "step": 8381 }, { "epoch": 0.48960280373831777, "grad_norm": 2.1532745361328125, "learning_rate": 1.0823908059659295e-05, "loss": 0.8653, "step": 8382 }, { "epoch": 0.48966121495327103, "grad_norm": 1.158075213432312, "learning_rate": 1.0822022635107058e-05, "loss": 0.7861, "step": 8383 }, { "epoch": 0.4897196261682243, "grad_norm": 1.352211833000183, "learning_rate": 1.0820137181134085e-05, "loss": 0.8302, "step": 8384 }, { "epoch": 0.48977803738317754, "grad_norm": 1.2060002088546753, "learning_rate": 1.0818251697807867e-05, "loss": 0.9149, "step": 8385 }, { "epoch": 0.48983644859813086, "grad_norm": 1.0192749500274658, "learning_rate": 1.0816366185195886e-05, "loss": 0.8807, "step": 8386 }, { "epoch": 0.4898948598130841, "grad_norm": 1.9905641078948975, "learning_rate": 1.0814480643365615e-05, "loss": 0.8143, "step": 8387 }, { "epoch": 0.4899532710280374, "grad_norm": 1.33511221408844, "learning_rate": 1.081259507238455e-05, "loss": 0.8419, "step": 8388 }, { "epoch": 0.49001168224299063, "grad_norm": 1.8312230110168457, "learning_rate": 1.0810709472320174e-05, "loss": 0.8405, "step": 8389 }, { "epoch": 0.49007009345794394, "grad_norm": 1.0858107805252075, "learning_rate": 1.0808823843239968e-05, "loss": 0.6431, "step": 8390 }, { "epoch": 0.4901285046728972, "grad_norm": 1.4424872398376465, "learning_rate": 1.080693818521143e-05, "loss": 0.9225, "step": 8391 }, { "epoch": 0.49018691588785046, "grad_norm": 1.3112026453018188, "learning_rate": 1.080505249830204e-05, "loss": 0.8181, "step": 8392 }, { "epoch": 0.4902453271028037, "grad_norm": 1.2835373878479004, "learning_rate": 1.0803166782579295e-05, "loss": 0.7948, "step": 8393 }, { "epoch": 0.49030373831775703, "grad_norm": 1.212577223777771, "learning_rate": 1.0801281038110683e-05, "loss": 0.8047, "step": 8394 }, { "epoch": 0.4903621495327103, "grad_norm": 1.3716511726379395, "learning_rate": 1.0799395264963693e-05, "loss": 0.768, "step": 8395 }, { "epoch": 0.49042056074766355, "grad_norm": 1.39473557472229, "learning_rate": 1.0797509463205824e-05, "loss": 0.7903, "step": 8396 }, { "epoch": 0.4904789719626168, "grad_norm": 1.4065618515014648, "learning_rate": 1.0795623632904563e-05, "loss": 0.8274, "step": 8397 }, { "epoch": 0.4905373831775701, "grad_norm": 1.3205615282058716, "learning_rate": 1.0793737774127411e-05, "loss": 0.828, "step": 8398 }, { "epoch": 0.4905957943925234, "grad_norm": 1.2577295303344727, "learning_rate": 1.0791851886941862e-05, "loss": 0.9916, "step": 8399 }, { "epoch": 0.49065420560747663, "grad_norm": 0.9879062175750732, "learning_rate": 1.0789965971415415e-05, "loss": 0.7123, "step": 8400 }, { "epoch": 0.4907126168224299, "grad_norm": 2.2096519470214844, "learning_rate": 1.0788080027615566e-05, "loss": 0.6742, "step": 8401 }, { "epoch": 0.49077102803738315, "grad_norm": 1.6493396759033203, "learning_rate": 1.0786194055609814e-05, "loss": 0.8287, "step": 8402 }, { "epoch": 0.49082943925233646, "grad_norm": 1.1711111068725586, "learning_rate": 1.0784308055465658e-05, "loss": 0.8093, "step": 8403 }, { "epoch": 0.4908878504672897, "grad_norm": 1.5836833715438843, "learning_rate": 1.0782422027250604e-05, "loss": 0.8674, "step": 8404 }, { "epoch": 0.490946261682243, "grad_norm": 0.9737565517425537, "learning_rate": 1.0780535971032149e-05, "loss": 0.8071, "step": 8405 }, { "epoch": 0.49100467289719624, "grad_norm": 1.0632432699203491, "learning_rate": 1.0778649886877798e-05, "loss": 0.7138, "step": 8406 }, { "epoch": 0.49106308411214955, "grad_norm": 1.1022529602050781, "learning_rate": 1.0776763774855058e-05, "loss": 0.7225, "step": 8407 }, { "epoch": 0.4911214953271028, "grad_norm": 1.3662887811660767, "learning_rate": 1.077487763503143e-05, "loss": 0.7878, "step": 8408 }, { "epoch": 0.49117990654205607, "grad_norm": 1.783595323562622, "learning_rate": 1.0772991467474421e-05, "loss": 1.0264, "step": 8409 }, { "epoch": 0.4912383177570093, "grad_norm": 1.1630220413208008, "learning_rate": 1.0771105272251542e-05, "loss": 0.7805, "step": 8410 }, { "epoch": 0.49129672897196264, "grad_norm": 1.5873218774795532, "learning_rate": 1.0769219049430297e-05, "loss": 0.8278, "step": 8411 }, { "epoch": 0.4913551401869159, "grad_norm": 1.3507914543151855, "learning_rate": 1.0767332799078196e-05, "loss": 0.6833, "step": 8412 }, { "epoch": 0.49141355140186915, "grad_norm": 1.5627672672271729, "learning_rate": 1.076544652126275e-05, "loss": 0.89, "step": 8413 }, { "epoch": 0.4914719626168224, "grad_norm": 1.2357234954833984, "learning_rate": 1.076356021605147e-05, "loss": 1.0548, "step": 8414 }, { "epoch": 0.4915303738317757, "grad_norm": 1.2658616304397583, "learning_rate": 1.0761673883511868e-05, "loss": 0.867, "step": 8415 }, { "epoch": 0.491588785046729, "grad_norm": 1.3071919679641724, "learning_rate": 1.0759787523711456e-05, "loss": 0.9041, "step": 8416 }, { "epoch": 0.49164719626168224, "grad_norm": 1.345606803894043, "learning_rate": 1.0757901136717748e-05, "loss": 0.8536, "step": 8417 }, { "epoch": 0.4917056074766355, "grad_norm": 1.0617015361785889, "learning_rate": 1.0756014722598263e-05, "loss": 0.7522, "step": 8418 }, { "epoch": 0.4917640186915888, "grad_norm": 1.2033991813659668, "learning_rate": 1.0754128281420511e-05, "loss": 0.6814, "step": 8419 }, { "epoch": 0.49182242990654207, "grad_norm": 1.5747836828231812, "learning_rate": 1.0752241813252014e-05, "loss": 0.8444, "step": 8420 }, { "epoch": 0.4918808411214953, "grad_norm": 1.026147723197937, "learning_rate": 1.0750355318160288e-05, "loss": 0.6777, "step": 8421 }, { "epoch": 0.4919392523364486, "grad_norm": 1.3075939416885376, "learning_rate": 1.0748468796212852e-05, "loss": 0.7161, "step": 8422 }, { "epoch": 0.49199766355140184, "grad_norm": 1.4733611345291138, "learning_rate": 1.0746582247477222e-05, "loss": 0.8289, "step": 8423 }, { "epoch": 0.49205607476635516, "grad_norm": 1.2442595958709717, "learning_rate": 1.0744695672020926e-05, "loss": 0.787, "step": 8424 }, { "epoch": 0.4921144859813084, "grad_norm": 1.2429784536361694, "learning_rate": 1.0742809069911482e-05, "loss": 0.6777, "step": 8425 }, { "epoch": 0.49217289719626167, "grad_norm": 1.142314076423645, "learning_rate": 1.074092244121641e-05, "loss": 0.7715, "step": 8426 }, { "epoch": 0.49223130841121493, "grad_norm": 1.1617423295974731, "learning_rate": 1.073903578600324e-05, "loss": 0.8337, "step": 8427 }, { "epoch": 0.49228971962616824, "grad_norm": 0.9685590267181396, "learning_rate": 1.073714910433949e-05, "loss": 0.6325, "step": 8428 }, { "epoch": 0.4923481308411215, "grad_norm": 1.290269136428833, "learning_rate": 1.0735262396292692e-05, "loss": 0.7465, "step": 8429 }, { "epoch": 0.49240654205607476, "grad_norm": 1.0093568563461304, "learning_rate": 1.0733375661930373e-05, "loss": 0.7737, "step": 8430 }, { "epoch": 0.492464953271028, "grad_norm": 1.1014773845672607, "learning_rate": 1.0731488901320049e-05, "loss": 0.812, "step": 8431 }, { "epoch": 0.49252336448598133, "grad_norm": 0.911355197429657, "learning_rate": 1.0729602114529261e-05, "loss": 0.7494, "step": 8432 }, { "epoch": 0.4925817757009346, "grad_norm": 1.3884737491607666, "learning_rate": 1.0727715301625532e-05, "loss": 0.9167, "step": 8433 }, { "epoch": 0.49264018691588785, "grad_norm": 1.2301111221313477, "learning_rate": 1.0725828462676394e-05, "loss": 0.8288, "step": 8434 }, { "epoch": 0.4926985981308411, "grad_norm": 1.2108131647109985, "learning_rate": 1.0723941597749378e-05, "loss": 0.6924, "step": 8435 }, { "epoch": 0.4927570093457944, "grad_norm": 0.9519122838973999, "learning_rate": 1.0722054706912015e-05, "loss": 0.7438, "step": 8436 }, { "epoch": 0.4928154205607477, "grad_norm": 1.1022634506225586, "learning_rate": 1.0720167790231842e-05, "loss": 0.8278, "step": 8437 }, { "epoch": 0.49287383177570093, "grad_norm": 1.0328106880187988, "learning_rate": 1.0718280847776387e-05, "loss": 0.7567, "step": 8438 }, { "epoch": 0.4929322429906542, "grad_norm": 1.1821796894073486, "learning_rate": 1.0716393879613192e-05, "loss": 0.7205, "step": 8439 }, { "epoch": 0.4929906542056075, "grad_norm": 0.9582909941673279, "learning_rate": 1.0714506885809787e-05, "loss": 0.6228, "step": 8440 }, { "epoch": 0.49304906542056076, "grad_norm": 1.1407629251480103, "learning_rate": 1.0712619866433712e-05, "loss": 0.7104, "step": 8441 }, { "epoch": 0.493107476635514, "grad_norm": 1.309781789779663, "learning_rate": 1.07107328215525e-05, "loss": 0.7103, "step": 8442 }, { "epoch": 0.4931658878504673, "grad_norm": 0.9593786597251892, "learning_rate": 1.0708845751233697e-05, "loss": 0.7604, "step": 8443 }, { "epoch": 0.49322429906542054, "grad_norm": 1.0310816764831543, "learning_rate": 1.0706958655544837e-05, "loss": 0.8167, "step": 8444 }, { "epoch": 0.49328271028037385, "grad_norm": 0.985617995262146, "learning_rate": 1.0705071534553461e-05, "loss": 0.8351, "step": 8445 }, { "epoch": 0.4933411214953271, "grad_norm": 1.25132155418396, "learning_rate": 1.0703184388327112e-05, "loss": 0.9838, "step": 8446 }, { "epoch": 0.49339953271028036, "grad_norm": 1.3405801057815552, "learning_rate": 1.0701297216933332e-05, "loss": 0.7961, "step": 8447 }, { "epoch": 0.4934579439252336, "grad_norm": 1.1855599880218506, "learning_rate": 1.069941002043966e-05, "loss": 1.1296, "step": 8448 }, { "epoch": 0.49351635514018694, "grad_norm": 1.2003613710403442, "learning_rate": 1.0697522798913648e-05, "loss": 0.7054, "step": 8449 }, { "epoch": 0.4935747663551402, "grad_norm": 1.0324938297271729, "learning_rate": 1.0695635552422834e-05, "loss": 0.7463, "step": 8450 }, { "epoch": 0.49363317757009345, "grad_norm": 1.1551882028579712, "learning_rate": 1.0693748281034768e-05, "loss": 0.8237, "step": 8451 }, { "epoch": 0.4936915887850467, "grad_norm": 1.151587963104248, "learning_rate": 1.0691860984816994e-05, "loss": 0.8455, "step": 8452 }, { "epoch": 0.49375, "grad_norm": 1.4434536695480347, "learning_rate": 1.0689973663837058e-05, "loss": 0.7123, "step": 8453 }, { "epoch": 0.4938084112149533, "grad_norm": 1.2036973237991333, "learning_rate": 1.0688086318162516e-05, "loss": 1.0148, "step": 8454 }, { "epoch": 0.49386682242990654, "grad_norm": 1.6328561305999756, "learning_rate": 1.0686198947860909e-05, "loss": 0.8795, "step": 8455 }, { "epoch": 0.4939252336448598, "grad_norm": 1.6177090406417847, "learning_rate": 1.0684311552999788e-05, "loss": 0.7714, "step": 8456 }, { "epoch": 0.4939836448598131, "grad_norm": 1.8074309825897217, "learning_rate": 1.0682424133646712e-05, "loss": 0.8135, "step": 8457 }, { "epoch": 0.49404205607476637, "grad_norm": 1.3953701257705688, "learning_rate": 1.0680536689869224e-05, "loss": 0.9166, "step": 8458 }, { "epoch": 0.4941004672897196, "grad_norm": 2.0033528804779053, "learning_rate": 1.0678649221734883e-05, "loss": 0.828, "step": 8459 }, { "epoch": 0.4941588785046729, "grad_norm": 1.1650304794311523, "learning_rate": 1.0676761729311238e-05, "loss": 0.765, "step": 8460 }, { "epoch": 0.49421728971962614, "grad_norm": 1.7062015533447266, "learning_rate": 1.0674874212665845e-05, "loss": 0.7882, "step": 8461 }, { "epoch": 0.49427570093457945, "grad_norm": 1.3011523485183716, "learning_rate": 1.067298667186626e-05, "loss": 0.7099, "step": 8462 }, { "epoch": 0.4943341121495327, "grad_norm": 0.8808482885360718, "learning_rate": 1.0671099106980045e-05, "loss": 0.6618, "step": 8463 }, { "epoch": 0.49439252336448597, "grad_norm": 1.609508991241455, "learning_rate": 1.0669211518074745e-05, "loss": 0.9036, "step": 8464 }, { "epoch": 0.4944509345794392, "grad_norm": 1.9791405200958252, "learning_rate": 1.0667323905217927e-05, "loss": 0.8534, "step": 8465 }, { "epoch": 0.49450934579439254, "grad_norm": 1.7332189083099365, "learning_rate": 1.066543626847715e-05, "loss": 0.8651, "step": 8466 }, { "epoch": 0.4945677570093458, "grad_norm": 1.4597474336624146, "learning_rate": 1.0663548607919966e-05, "loss": 0.7784, "step": 8467 }, { "epoch": 0.49462616822429906, "grad_norm": 1.403831124305725, "learning_rate": 1.0661660923613949e-05, "loss": 0.8265, "step": 8468 }, { "epoch": 0.4946845794392523, "grad_norm": 1.326066255569458, "learning_rate": 1.0659773215626645e-05, "loss": 0.6958, "step": 8469 }, { "epoch": 0.4947429906542056, "grad_norm": 1.592868447303772, "learning_rate": 1.0657885484025628e-05, "loss": 0.9321, "step": 8470 }, { "epoch": 0.4948014018691589, "grad_norm": 1.1581014394760132, "learning_rate": 1.0655997728878456e-05, "loss": 0.7744, "step": 8471 }, { "epoch": 0.49485981308411214, "grad_norm": 1.2098404169082642, "learning_rate": 1.0654109950252694e-05, "loss": 0.7602, "step": 8472 }, { "epoch": 0.4949182242990654, "grad_norm": 2.720696210861206, "learning_rate": 1.0652222148215905e-05, "loss": 0.905, "step": 8473 }, { "epoch": 0.4949766355140187, "grad_norm": 1.2474775314331055, "learning_rate": 1.0650334322835657e-05, "loss": 0.7435, "step": 8474 }, { "epoch": 0.495035046728972, "grad_norm": 1.5929392576217651, "learning_rate": 1.0648446474179517e-05, "loss": 0.7173, "step": 8475 }, { "epoch": 0.49509345794392523, "grad_norm": 1.7661429643630981, "learning_rate": 1.0646558602315052e-05, "loss": 0.9055, "step": 8476 }, { "epoch": 0.4951518691588785, "grad_norm": 1.038367509841919, "learning_rate": 1.0644670707309827e-05, "loss": 0.7558, "step": 8477 }, { "epoch": 0.4952102803738318, "grad_norm": 1.841027855873108, "learning_rate": 1.0642782789231419e-05, "loss": 0.8403, "step": 8478 }, { "epoch": 0.49526869158878506, "grad_norm": 1.7984166145324707, "learning_rate": 1.0640894848147387e-05, "loss": 0.7538, "step": 8479 }, { "epoch": 0.4953271028037383, "grad_norm": 1.1092475652694702, "learning_rate": 1.0639006884125308e-05, "loss": 0.7179, "step": 8480 }, { "epoch": 0.4953855140186916, "grad_norm": 2.532177209854126, "learning_rate": 1.0637118897232752e-05, "loss": 0.9035, "step": 8481 }, { "epoch": 0.49544392523364483, "grad_norm": 1.25027596950531, "learning_rate": 1.0635230887537294e-05, "loss": 0.8481, "step": 8482 }, { "epoch": 0.49550233644859815, "grad_norm": 1.3578256368637085, "learning_rate": 1.0633342855106503e-05, "loss": 0.9516, "step": 8483 }, { "epoch": 0.4955607476635514, "grad_norm": 1.5441888570785522, "learning_rate": 1.0631454800007957e-05, "loss": 0.6415, "step": 8484 }, { "epoch": 0.49561915887850466, "grad_norm": 1.5186036825180054, "learning_rate": 1.0629566722309226e-05, "loss": 0.7415, "step": 8485 }, { "epoch": 0.4956775700934579, "grad_norm": 1.4230760335922241, "learning_rate": 1.0627678622077888e-05, "loss": 0.7407, "step": 8486 }, { "epoch": 0.49573598130841123, "grad_norm": 1.6323134899139404, "learning_rate": 1.062579049938152e-05, "loss": 0.6806, "step": 8487 }, { "epoch": 0.4957943925233645, "grad_norm": 1.2663735151290894, "learning_rate": 1.0623902354287702e-05, "loss": 0.7682, "step": 8488 }, { "epoch": 0.49585280373831775, "grad_norm": 1.4200352430343628, "learning_rate": 1.0622014186864005e-05, "loss": 0.9707, "step": 8489 }, { "epoch": 0.495911214953271, "grad_norm": 1.3832416534423828, "learning_rate": 1.062012599717801e-05, "loss": 0.6831, "step": 8490 }, { "epoch": 0.4959696261682243, "grad_norm": 2.302687406539917, "learning_rate": 1.06182377852973e-05, "loss": 0.9106, "step": 8491 }, { "epoch": 0.4960280373831776, "grad_norm": 1.1656535863876343, "learning_rate": 1.0616349551289453e-05, "loss": 0.8599, "step": 8492 }, { "epoch": 0.49608644859813084, "grad_norm": 1.5952328443527222, "learning_rate": 1.0614461295222051e-05, "loss": 0.6675, "step": 8493 }, { "epoch": 0.4961448598130841, "grad_norm": 1.0284360647201538, "learning_rate": 1.0612573017162673e-05, "loss": 0.7043, "step": 8494 }, { "epoch": 0.4962032710280374, "grad_norm": 1.2982821464538574, "learning_rate": 1.0610684717178905e-05, "loss": 0.7695, "step": 8495 }, { "epoch": 0.49626168224299066, "grad_norm": 1.4247291088104248, "learning_rate": 1.060879639533833e-05, "loss": 0.8264, "step": 8496 }, { "epoch": 0.4963200934579439, "grad_norm": 0.980518102645874, "learning_rate": 1.0606908051708531e-05, "loss": 0.8313, "step": 8497 }, { "epoch": 0.4963785046728972, "grad_norm": 1.1928435564041138, "learning_rate": 1.0605019686357097e-05, "loss": 0.8923, "step": 8498 }, { "epoch": 0.4964369158878505, "grad_norm": 1.0846693515777588, "learning_rate": 1.0603131299351608e-05, "loss": 0.7572, "step": 8499 }, { "epoch": 0.49649532710280375, "grad_norm": 1.1139631271362305, "learning_rate": 1.060124289075965e-05, "loss": 0.6921, "step": 8500 }, { "epoch": 0.496553738317757, "grad_norm": 0.9802372455596924, "learning_rate": 1.0599354460648817e-05, "loss": 0.7425, "step": 8501 }, { "epoch": 0.49661214953271027, "grad_norm": 1.5662283897399902, "learning_rate": 1.0597466009086695e-05, "loss": 0.9653, "step": 8502 }, { "epoch": 0.4966705607476635, "grad_norm": 1.1618276834487915, "learning_rate": 1.0595577536140869e-05, "loss": 0.7746, "step": 8503 }, { "epoch": 0.49672897196261684, "grad_norm": 1.2602355480194092, "learning_rate": 1.0593689041878932e-05, "loss": 0.6753, "step": 8504 }, { "epoch": 0.4967873831775701, "grad_norm": 1.3170323371887207, "learning_rate": 1.0591800526368477e-05, "loss": 0.7224, "step": 8505 }, { "epoch": 0.49684579439252335, "grad_norm": 1.2371270656585693, "learning_rate": 1.0589911989677087e-05, "loss": 1.0112, "step": 8506 }, { "epoch": 0.4969042056074766, "grad_norm": 1.1535776853561401, "learning_rate": 1.0588023431872363e-05, "loss": 0.7313, "step": 8507 }, { "epoch": 0.4969626168224299, "grad_norm": 1.4669955968856812, "learning_rate": 1.058613485302189e-05, "loss": 0.9009, "step": 8508 }, { "epoch": 0.4970210280373832, "grad_norm": 1.0600413084030151, "learning_rate": 1.058424625319327e-05, "loss": 0.7897, "step": 8509 }, { "epoch": 0.49707943925233644, "grad_norm": 1.5876672267913818, "learning_rate": 1.0582357632454089e-05, "loss": 0.8523, "step": 8510 }, { "epoch": 0.4971378504672897, "grad_norm": 1.2239638566970825, "learning_rate": 1.0580468990871944e-05, "loss": 0.7569, "step": 8511 }, { "epoch": 0.497196261682243, "grad_norm": 2.0041468143463135, "learning_rate": 1.0578580328514437e-05, "loss": 1.0284, "step": 8512 }, { "epoch": 0.49725467289719627, "grad_norm": 1.1626962423324585, "learning_rate": 1.0576691645449157e-05, "loss": 0.8384, "step": 8513 }, { "epoch": 0.49731308411214953, "grad_norm": 2.037468433380127, "learning_rate": 1.0574802941743702e-05, "loss": 0.6985, "step": 8514 }, { "epoch": 0.4973714953271028, "grad_norm": 1.3068885803222656, "learning_rate": 1.0572914217465674e-05, "loss": 0.7266, "step": 8515 }, { "epoch": 0.4974299065420561, "grad_norm": 1.8289146423339844, "learning_rate": 1.0571025472682668e-05, "loss": 0.9571, "step": 8516 }, { "epoch": 0.49748831775700936, "grad_norm": 1.493918538093567, "learning_rate": 1.0569136707462286e-05, "loss": 0.7403, "step": 8517 }, { "epoch": 0.4975467289719626, "grad_norm": 1.1221332550048828, "learning_rate": 1.0567247921872128e-05, "loss": 0.7053, "step": 8518 }, { "epoch": 0.4976051401869159, "grad_norm": 1.2235733270645142, "learning_rate": 1.0565359115979792e-05, "loss": 0.8312, "step": 8519 }, { "epoch": 0.4976635514018692, "grad_norm": 1.2741072177886963, "learning_rate": 1.0563470289852882e-05, "loss": 0.9232, "step": 8520 }, { "epoch": 0.49772196261682244, "grad_norm": 1.4484457969665527, "learning_rate": 1.0561581443559003e-05, "loss": 0.8611, "step": 8521 }, { "epoch": 0.4977803738317757, "grad_norm": 1.2309925556182861, "learning_rate": 1.055969257716575e-05, "loss": 0.8057, "step": 8522 }, { "epoch": 0.49783878504672896, "grad_norm": 1.4812757968902588, "learning_rate": 1.0557803690740734e-05, "loss": 0.8233, "step": 8523 }, { "epoch": 0.4978971962616822, "grad_norm": 1.6422711610794067, "learning_rate": 1.0555914784351557e-05, "loss": 0.9221, "step": 8524 }, { "epoch": 0.49795560747663553, "grad_norm": 1.0456682443618774, "learning_rate": 1.0554025858065822e-05, "loss": 0.6558, "step": 8525 }, { "epoch": 0.4980140186915888, "grad_norm": 1.115608811378479, "learning_rate": 1.0552136911951143e-05, "loss": 0.8038, "step": 8526 }, { "epoch": 0.49807242990654205, "grad_norm": 1.5227320194244385, "learning_rate": 1.0550247946075117e-05, "loss": 0.9547, "step": 8527 }, { "epoch": 0.4981308411214953, "grad_norm": 1.7325801849365234, "learning_rate": 1.0548358960505354e-05, "loss": 0.9153, "step": 8528 }, { "epoch": 0.4981892523364486, "grad_norm": 1.360953450202942, "learning_rate": 1.0546469955309467e-05, "loss": 0.7095, "step": 8529 }, { "epoch": 0.4982476635514019, "grad_norm": 1.7831432819366455, "learning_rate": 1.0544580930555055e-05, "loss": 0.6888, "step": 8530 }, { "epoch": 0.49830607476635513, "grad_norm": 1.2747154235839844, "learning_rate": 1.054269188630974e-05, "loss": 0.7157, "step": 8531 }, { "epoch": 0.4983644859813084, "grad_norm": 1.3179025650024414, "learning_rate": 1.0540802822641124e-05, "loss": 0.9929, "step": 8532 }, { "epoch": 0.4984228971962617, "grad_norm": 1.4340307712554932, "learning_rate": 1.0538913739616817e-05, "loss": 0.7521, "step": 8533 }, { "epoch": 0.49848130841121496, "grad_norm": 3.268897533416748, "learning_rate": 1.0537024637304433e-05, "loss": 0.9097, "step": 8534 }, { "epoch": 0.4985397196261682, "grad_norm": 1.3708540201187134, "learning_rate": 1.0535135515771586e-05, "loss": 0.7186, "step": 8535 }, { "epoch": 0.4985981308411215, "grad_norm": 1.2338007688522339, "learning_rate": 1.0533246375085886e-05, "loss": 0.9384, "step": 8536 }, { "epoch": 0.4986565420560748, "grad_norm": 1.7421637773513794, "learning_rate": 1.0531357215314948e-05, "loss": 0.9559, "step": 8537 }, { "epoch": 0.49871495327102805, "grad_norm": 1.7226227521896362, "learning_rate": 1.0529468036526387e-05, "loss": 0.8625, "step": 8538 }, { "epoch": 0.4987733644859813, "grad_norm": 1.875684142112732, "learning_rate": 1.0527578838787814e-05, "loss": 0.8934, "step": 8539 }, { "epoch": 0.49883177570093457, "grad_norm": 1.0308973789215088, "learning_rate": 1.0525689622166848e-05, "loss": 0.6815, "step": 8540 }, { "epoch": 0.4988901869158878, "grad_norm": 2.2228097915649414, "learning_rate": 1.0523800386731107e-05, "loss": 0.8892, "step": 8541 }, { "epoch": 0.49894859813084114, "grad_norm": 1.50262451171875, "learning_rate": 1.0521911132548207e-05, "loss": 0.9044, "step": 8542 }, { "epoch": 0.4990070093457944, "grad_norm": 1.548587679862976, "learning_rate": 1.0520021859685761e-05, "loss": 0.7597, "step": 8543 }, { "epoch": 0.49906542056074765, "grad_norm": 2.3727309703826904, "learning_rate": 1.051813256821139e-05, "loss": 0.9599, "step": 8544 }, { "epoch": 0.4991238317757009, "grad_norm": 1.7384699583053589, "learning_rate": 1.0516243258192715e-05, "loss": 0.8173, "step": 8545 }, { "epoch": 0.4991822429906542, "grad_norm": 2.246589183807373, "learning_rate": 1.0514353929697358e-05, "loss": 0.9262, "step": 8546 }, { "epoch": 0.4992406542056075, "grad_norm": 1.8895200490951538, "learning_rate": 1.051246458279293e-05, "loss": 0.7778, "step": 8547 }, { "epoch": 0.49929906542056074, "grad_norm": 1.5466030836105347, "learning_rate": 1.051057521754706e-05, "loss": 0.7601, "step": 8548 }, { "epoch": 0.499357476635514, "grad_norm": 1.3799279928207397, "learning_rate": 1.0508685834027368e-05, "loss": 0.7956, "step": 8549 }, { "epoch": 0.4994158878504673, "grad_norm": 1.3163037300109863, "learning_rate": 1.0506796432301476e-05, "loss": 0.7738, "step": 8550 }, { "epoch": 0.49947429906542057, "grad_norm": 1.4168401956558228, "learning_rate": 1.0504907012437004e-05, "loss": 0.9284, "step": 8551 }, { "epoch": 0.4995327102803738, "grad_norm": 1.4582881927490234, "learning_rate": 1.050301757450158e-05, "loss": 0.812, "step": 8552 }, { "epoch": 0.4995911214953271, "grad_norm": 1.8360786437988281, "learning_rate": 1.0501128118562824e-05, "loss": 1.0281, "step": 8553 }, { "epoch": 0.4996495327102804, "grad_norm": 1.1404248476028442, "learning_rate": 1.0499238644688365e-05, "loss": 0.8781, "step": 8554 }, { "epoch": 0.49970794392523366, "grad_norm": 1.9503318071365356, "learning_rate": 1.0497349152945828e-05, "loss": 0.9262, "step": 8555 }, { "epoch": 0.4997663551401869, "grad_norm": 2.0982589721679688, "learning_rate": 1.0495459643402836e-05, "loss": 0.9616, "step": 8556 }, { "epoch": 0.49982476635514017, "grad_norm": 1.6514145135879517, "learning_rate": 1.0493570116127018e-05, "loss": 0.8448, "step": 8557 }, { "epoch": 0.4998831775700935, "grad_norm": 1.539888858795166, "learning_rate": 1.0491680571186e-05, "loss": 0.7556, "step": 8558 }, { "epoch": 0.49994158878504674, "grad_norm": 2.1772847175598145, "learning_rate": 1.0489791008647411e-05, "loss": 0.74, "step": 8559 }, { "epoch": 0.5, "grad_norm": 1.6758649349212646, "learning_rate": 1.0487901428578882e-05, "loss": 0.8653, "step": 8560 }, { "epoch": 0.5000584112149533, "grad_norm": 1.9774589538574219, "learning_rate": 1.0486011831048039e-05, "loss": 0.9418, "step": 8561 }, { "epoch": 0.5001168224299065, "grad_norm": 1.1550345420837402, "learning_rate": 1.0484122216122513e-05, "loss": 0.6533, "step": 8562 }, { "epoch": 0.5001752336448598, "grad_norm": 1.2475956678390503, "learning_rate": 1.0482232583869933e-05, "loss": 0.7597, "step": 8563 }, { "epoch": 0.500233644859813, "grad_norm": 1.7565475702285767, "learning_rate": 1.0480342934357933e-05, "loss": 0.7622, "step": 8564 }, { "epoch": 0.5002920560747663, "grad_norm": 1.1140618324279785, "learning_rate": 1.0478453267654147e-05, "loss": 0.7195, "step": 8565 }, { "epoch": 0.5003504672897197, "grad_norm": 2.225597620010376, "learning_rate": 1.0476563583826198e-05, "loss": 0.7753, "step": 8566 }, { "epoch": 0.5004088785046729, "grad_norm": 1.095345377922058, "learning_rate": 1.0474673882941728e-05, "loss": 0.7083, "step": 8567 }, { "epoch": 0.5004672897196262, "grad_norm": 1.4137048721313477, "learning_rate": 1.0472784165068368e-05, "loss": 0.822, "step": 8568 }, { "epoch": 0.5005257009345795, "grad_norm": 1.4115087985992432, "learning_rate": 1.0470894430273749e-05, "loss": 0.7186, "step": 8569 }, { "epoch": 0.5005841121495327, "grad_norm": 1.4078572988510132, "learning_rate": 1.0469004678625515e-05, "loss": 1.0087, "step": 8570 }, { "epoch": 0.500642523364486, "grad_norm": 1.0177552700042725, "learning_rate": 1.046711491019129e-05, "loss": 0.7794, "step": 8571 }, { "epoch": 0.5007009345794392, "grad_norm": 1.437340497970581, "learning_rate": 1.0465225125038713e-05, "loss": 0.7635, "step": 8572 }, { "epoch": 0.5007593457943925, "grad_norm": 0.9883590936660767, "learning_rate": 1.046333532323543e-05, "loss": 0.6222, "step": 8573 }, { "epoch": 0.5008177570093458, "grad_norm": 2.0634074211120605, "learning_rate": 1.0461445504849066e-05, "loss": 0.8809, "step": 8574 }, { "epoch": 0.500876168224299, "grad_norm": 1.6920568943023682, "learning_rate": 1.0459555669947266e-05, "loss": 0.8746, "step": 8575 }, { "epoch": 0.5009345794392523, "grad_norm": 1.4898953437805176, "learning_rate": 1.0457665818597664e-05, "loss": 0.7047, "step": 8576 }, { "epoch": 0.5009929906542057, "grad_norm": 2.656644582748413, "learning_rate": 1.0455775950867901e-05, "loss": 0.9419, "step": 8577 }, { "epoch": 0.5010514018691589, "grad_norm": 1.2413349151611328, "learning_rate": 1.045388606682562e-05, "loss": 0.9684, "step": 8578 }, { "epoch": 0.5011098130841122, "grad_norm": 2.02714204788208, "learning_rate": 1.0451996166538461e-05, "loss": 0.6878, "step": 8579 }, { "epoch": 0.5011682242990654, "grad_norm": 1.3991553783416748, "learning_rate": 1.0450106250074055e-05, "loss": 0.812, "step": 8580 }, { "epoch": 0.5012266355140187, "grad_norm": 1.4965835809707642, "learning_rate": 1.0448216317500054e-05, "loss": 0.7267, "step": 8581 }, { "epoch": 0.501285046728972, "grad_norm": 2.5658698081970215, "learning_rate": 1.0446326368884097e-05, "loss": 0.8607, "step": 8582 }, { "epoch": 0.5013434579439252, "grad_norm": 1.2056498527526855, "learning_rate": 1.0444436404293823e-05, "loss": 0.7459, "step": 8583 }, { "epoch": 0.5014018691588785, "grad_norm": 1.3286436796188354, "learning_rate": 1.0442546423796882e-05, "loss": 0.8985, "step": 8584 }, { "epoch": 0.5014602803738317, "grad_norm": 1.5384433269500732, "learning_rate": 1.0440656427460909e-05, "loss": 0.6863, "step": 8585 }, { "epoch": 0.501518691588785, "grad_norm": 1.5929739475250244, "learning_rate": 1.0438766415353556e-05, "loss": 0.8194, "step": 8586 }, { "epoch": 0.5015771028037384, "grad_norm": 1.6945066452026367, "learning_rate": 1.0436876387542464e-05, "loss": 0.9442, "step": 8587 }, { "epoch": 0.5016355140186916, "grad_norm": 1.9139913320541382, "learning_rate": 1.0434986344095276e-05, "loss": 0.8222, "step": 8588 }, { "epoch": 0.5016939252336449, "grad_norm": 1.947701096534729, "learning_rate": 1.0433096285079644e-05, "loss": 0.7839, "step": 8589 }, { "epoch": 0.5017523364485982, "grad_norm": 1.4081451892852783, "learning_rate": 1.0431206210563211e-05, "loss": 0.8002, "step": 8590 }, { "epoch": 0.5018107476635514, "grad_norm": 1.4043017625808716, "learning_rate": 1.0429316120613621e-05, "loss": 0.7299, "step": 8591 }, { "epoch": 0.5018691588785047, "grad_norm": 1.42898690700531, "learning_rate": 1.0427426015298527e-05, "loss": 0.8831, "step": 8592 }, { "epoch": 0.5019275700934579, "grad_norm": 1.6606338024139404, "learning_rate": 1.0425535894685577e-05, "loss": 0.8709, "step": 8593 }, { "epoch": 0.5019859813084112, "grad_norm": 1.733809471130371, "learning_rate": 1.0423645758842416e-05, "loss": 0.938, "step": 8594 }, { "epoch": 0.5020443925233645, "grad_norm": 1.1945810317993164, "learning_rate": 1.0421755607836694e-05, "loss": 0.8648, "step": 8595 }, { "epoch": 0.5021028037383177, "grad_norm": 1.4839013814926147, "learning_rate": 1.0419865441736058e-05, "loss": 0.9221, "step": 8596 }, { "epoch": 0.502161214953271, "grad_norm": 1.2612181901931763, "learning_rate": 1.041797526060817e-05, "loss": 0.7991, "step": 8597 }, { "epoch": 0.5022196261682244, "grad_norm": 1.3116546869277954, "learning_rate": 1.0416085064520667e-05, "loss": 0.791, "step": 8598 }, { "epoch": 0.5022780373831776, "grad_norm": 2.20961856842041, "learning_rate": 1.0414194853541206e-05, "loss": 0.7256, "step": 8599 }, { "epoch": 0.5023364485981309, "grad_norm": 1.2178395986557007, "learning_rate": 1.0412304627737441e-05, "loss": 0.7629, "step": 8600 }, { "epoch": 0.5023948598130841, "grad_norm": 3.5423083305358887, "learning_rate": 1.0410414387177022e-05, "loss": 0.8955, "step": 8601 }, { "epoch": 0.5024532710280374, "grad_norm": 0.8031693696975708, "learning_rate": 1.04085241319276e-05, "loss": 0.6272, "step": 8602 }, { "epoch": 0.5025116822429907, "grad_norm": 2.918386459350586, "learning_rate": 1.0406633862056832e-05, "loss": 0.8855, "step": 8603 }, { "epoch": 0.5025700934579439, "grad_norm": 1.7838804721832275, "learning_rate": 1.0404743577632372e-05, "loss": 0.9172, "step": 8604 }, { "epoch": 0.5026285046728972, "grad_norm": 1.6891332864761353, "learning_rate": 1.0402853278721871e-05, "loss": 0.8915, "step": 8605 }, { "epoch": 0.5026869158878504, "grad_norm": 2.3782172203063965, "learning_rate": 1.0400962965392986e-05, "loss": 0.8397, "step": 8606 }, { "epoch": 0.5027453271028037, "grad_norm": 1.8863768577575684, "learning_rate": 1.0399072637713376e-05, "loss": 0.8895, "step": 8607 }, { "epoch": 0.502803738317757, "grad_norm": 1.6450315713882446, "learning_rate": 1.0397182295750691e-05, "loss": 0.9208, "step": 8608 }, { "epoch": 0.5028621495327102, "grad_norm": 2.1516268253326416, "learning_rate": 1.0395291939572593e-05, "loss": 0.7783, "step": 8609 }, { "epoch": 0.5029205607476636, "grad_norm": 1.5917094945907593, "learning_rate": 1.0393401569246733e-05, "loss": 0.8048, "step": 8610 }, { "epoch": 0.5029789719626169, "grad_norm": 2.092546224594116, "learning_rate": 1.0391511184840775e-05, "loss": 0.9711, "step": 8611 }, { "epoch": 0.5030373831775701, "grad_norm": 2.103487253189087, "learning_rate": 1.0389620786422374e-05, "loss": 0.9137, "step": 8612 }, { "epoch": 0.5030957943925234, "grad_norm": 1.4335812330245972, "learning_rate": 1.0387730374059188e-05, "loss": 0.7212, "step": 8613 }, { "epoch": 0.5031542056074766, "grad_norm": 1.4961129426956177, "learning_rate": 1.0385839947818878e-05, "loss": 0.7846, "step": 8614 }, { "epoch": 0.5032126168224299, "grad_norm": 1.1499582529067993, "learning_rate": 1.0383949507769102e-05, "loss": 0.6036, "step": 8615 }, { "epoch": 0.5032710280373832, "grad_norm": 1.0266791582107544, "learning_rate": 1.038205905397752e-05, "loss": 0.6669, "step": 8616 }, { "epoch": 0.5033294392523364, "grad_norm": 1.1628080606460571, "learning_rate": 1.0380168586511795e-05, "loss": 0.8175, "step": 8617 }, { "epoch": 0.5033878504672897, "grad_norm": 1.5895997285842896, "learning_rate": 1.0378278105439585e-05, "loss": 0.9432, "step": 8618 }, { "epoch": 0.503446261682243, "grad_norm": 2.0047318935394287, "learning_rate": 1.0376387610828554e-05, "loss": 0.9596, "step": 8619 }, { "epoch": 0.5035046728971962, "grad_norm": 1.4524495601654053, "learning_rate": 1.037449710274636e-05, "loss": 0.8251, "step": 8620 }, { "epoch": 0.5035630841121496, "grad_norm": 1.3787121772766113, "learning_rate": 1.037260658126067e-05, "loss": 0.7858, "step": 8621 }, { "epoch": 0.5036214953271028, "grad_norm": 1.6281116008758545, "learning_rate": 1.0370716046439146e-05, "loss": 0.9908, "step": 8622 }, { "epoch": 0.5036799065420561, "grad_norm": 1.5498002767562866, "learning_rate": 1.0368825498349456e-05, "loss": 0.8666, "step": 8623 }, { "epoch": 0.5037383177570094, "grad_norm": 1.8150322437286377, "learning_rate": 1.036693493705925e-05, "loss": 0.7838, "step": 8624 }, { "epoch": 0.5037967289719626, "grad_norm": 1.1606723070144653, "learning_rate": 1.0365044362636204e-05, "loss": 0.7569, "step": 8625 }, { "epoch": 0.5038551401869159, "grad_norm": 1.9989815950393677, "learning_rate": 1.0363153775147982e-05, "loss": 1.0071, "step": 8626 }, { "epoch": 0.5039135514018691, "grad_norm": 1.517678141593933, "learning_rate": 1.0361263174662247e-05, "loss": 0.9124, "step": 8627 }, { "epoch": 0.5039719626168224, "grad_norm": 1.1767914295196533, "learning_rate": 1.0359372561246668e-05, "loss": 0.8115, "step": 8628 }, { "epoch": 0.5040303738317757, "grad_norm": 1.5828518867492676, "learning_rate": 1.0357481934968903e-05, "loss": 0.7413, "step": 8629 }, { "epoch": 0.5040887850467289, "grad_norm": 1.6610699892044067, "learning_rate": 1.0355591295896628e-05, "loss": 0.8284, "step": 8630 }, { "epoch": 0.5041471962616823, "grad_norm": 1.6059284210205078, "learning_rate": 1.0353700644097508e-05, "loss": 0.8739, "step": 8631 }, { "epoch": 0.5042056074766356, "grad_norm": 2.0099220275878906, "learning_rate": 1.0351809979639207e-05, "loss": 0.8534, "step": 8632 }, { "epoch": 0.5042640186915888, "grad_norm": 1.4019384384155273, "learning_rate": 1.0349919302589397e-05, "loss": 0.6038, "step": 8633 }, { "epoch": 0.5043224299065421, "grad_norm": 1.4604460000991821, "learning_rate": 1.0348028613015747e-05, "loss": 0.7152, "step": 8634 }, { "epoch": 0.5043808411214953, "grad_norm": 1.603283405303955, "learning_rate": 1.0346137910985919e-05, "loss": 0.9356, "step": 8635 }, { "epoch": 0.5044392523364486, "grad_norm": 1.1539626121520996, "learning_rate": 1.0344247196567589e-05, "loss": 0.6144, "step": 8636 }, { "epoch": 0.5044976635514019, "grad_norm": 1.3327564001083374, "learning_rate": 1.034235646982843e-05, "loss": 0.7715, "step": 8637 }, { "epoch": 0.5045560747663551, "grad_norm": 1.1592153310775757, "learning_rate": 1.0340465730836101e-05, "loss": 0.7796, "step": 8638 }, { "epoch": 0.5046144859813084, "grad_norm": 1.0290025472640991, "learning_rate": 1.0338574979658285e-05, "loss": 0.7182, "step": 8639 }, { "epoch": 0.5046728971962616, "grad_norm": 1.2970551252365112, "learning_rate": 1.0336684216362645e-05, "loss": 0.7667, "step": 8640 }, { "epoch": 0.5047313084112149, "grad_norm": 1.176289439201355, "learning_rate": 1.0334793441016854e-05, "loss": 0.8845, "step": 8641 }, { "epoch": 0.5047897196261683, "grad_norm": 1.8765064477920532, "learning_rate": 1.0332902653688593e-05, "loss": 0.9687, "step": 8642 }, { "epoch": 0.5048481308411215, "grad_norm": 1.0181142091751099, "learning_rate": 1.0331011854445519e-05, "loss": 0.6823, "step": 8643 }, { "epoch": 0.5049065420560748, "grad_norm": 1.3168673515319824, "learning_rate": 1.0329121043355317e-05, "loss": 0.619, "step": 8644 }, { "epoch": 0.5049649532710281, "grad_norm": 1.0553507804870605, "learning_rate": 1.0327230220485656e-05, "loss": 0.6238, "step": 8645 }, { "epoch": 0.5050233644859813, "grad_norm": 1.9030718803405762, "learning_rate": 1.0325339385904207e-05, "loss": 0.9928, "step": 8646 }, { "epoch": 0.5050817757009346, "grad_norm": 1.5278841257095337, "learning_rate": 1.0323448539678653e-05, "loss": 0.853, "step": 8647 }, { "epoch": 0.5051401869158878, "grad_norm": 1.5061005353927612, "learning_rate": 1.0321557681876661e-05, "loss": 0.9128, "step": 8648 }, { "epoch": 0.5051985981308411, "grad_norm": 0.8978981971740723, "learning_rate": 1.0319666812565905e-05, "loss": 0.6304, "step": 8649 }, { "epoch": 0.5052570093457944, "grad_norm": 1.1124012470245361, "learning_rate": 1.0317775931814067e-05, "loss": 0.7631, "step": 8650 }, { "epoch": 0.5053154205607476, "grad_norm": 1.4056962728500366, "learning_rate": 1.031588503968882e-05, "loss": 0.6713, "step": 8651 }, { "epoch": 0.5053738317757009, "grad_norm": 1.4954673051834106, "learning_rate": 1.0313994136257838e-05, "loss": 0.9865, "step": 8652 }, { "epoch": 0.5054322429906543, "grad_norm": 1.555474042892456, "learning_rate": 1.03121032215888e-05, "loss": 0.8765, "step": 8653 }, { "epoch": 0.5054906542056075, "grad_norm": 1.5750986337661743, "learning_rate": 1.031021229574938e-05, "loss": 0.6727, "step": 8654 }, { "epoch": 0.5055490654205608, "grad_norm": 1.5105912685394287, "learning_rate": 1.0308321358807261e-05, "loss": 0.7314, "step": 8655 }, { "epoch": 0.505607476635514, "grad_norm": 2.7204761505126953, "learning_rate": 1.0306430410830118e-05, "loss": 0.9238, "step": 8656 }, { "epoch": 0.5056658878504673, "grad_norm": 1.1044436693191528, "learning_rate": 1.0304539451885629e-05, "loss": 0.7214, "step": 8657 }, { "epoch": 0.5057242990654206, "grad_norm": 1.457259178161621, "learning_rate": 1.0302648482041473e-05, "loss": 0.7132, "step": 8658 }, { "epoch": 0.5057827102803738, "grad_norm": 1.8962417840957642, "learning_rate": 1.0300757501365327e-05, "loss": 0.8358, "step": 8659 }, { "epoch": 0.5058411214953271, "grad_norm": 1.7037161588668823, "learning_rate": 1.0298866509924872e-05, "loss": 0.7837, "step": 8660 }, { "epoch": 0.5058995327102803, "grad_norm": 1.135085940361023, "learning_rate": 1.029697550778779e-05, "loss": 0.6426, "step": 8661 }, { "epoch": 0.5059579439252336, "grad_norm": 3.1595873832702637, "learning_rate": 1.0295084495021759e-05, "loss": 0.7809, "step": 8662 }, { "epoch": 0.506016355140187, "grad_norm": 0.936428964138031, "learning_rate": 1.0293193471694458e-05, "loss": 0.7691, "step": 8663 }, { "epoch": 0.5060747663551401, "grad_norm": 2.423868179321289, "learning_rate": 1.0291302437873572e-05, "loss": 0.895, "step": 8664 }, { "epoch": 0.5061331775700935, "grad_norm": 1.380904197692871, "learning_rate": 1.028941139362678e-05, "loss": 0.735, "step": 8665 }, { "epoch": 0.5061915887850468, "grad_norm": 1.2202156782150269, "learning_rate": 1.0287520339021763e-05, "loss": 0.6408, "step": 8666 }, { "epoch": 0.50625, "grad_norm": 1.6056660413742065, "learning_rate": 1.0285629274126206e-05, "loss": 0.8391, "step": 8667 }, { "epoch": 0.5063084112149533, "grad_norm": 2.5867462158203125, "learning_rate": 1.0283738199007787e-05, "loss": 0.8105, "step": 8668 }, { "epoch": 0.5063668224299065, "grad_norm": 1.490059494972229, "learning_rate": 1.0281847113734191e-05, "loss": 0.7682, "step": 8669 }, { "epoch": 0.5064252336448598, "grad_norm": 2.7285609245300293, "learning_rate": 1.0279956018373103e-05, "loss": 0.838, "step": 8670 }, { "epoch": 0.5064836448598131, "grad_norm": 1.2690064907073975, "learning_rate": 1.0278064912992205e-05, "loss": 0.775, "step": 8671 }, { "epoch": 0.5065420560747663, "grad_norm": 1.8996022939682007, "learning_rate": 1.0276173797659181e-05, "loss": 0.673, "step": 8672 }, { "epoch": 0.5066004672897196, "grad_norm": 1.6853817701339722, "learning_rate": 1.0274282672441715e-05, "loss": 0.8399, "step": 8673 }, { "epoch": 0.506658878504673, "grad_norm": 1.385898232460022, "learning_rate": 1.027239153740749e-05, "loss": 0.6207, "step": 8674 }, { "epoch": 0.5067172897196262, "grad_norm": 1.0627140998840332, "learning_rate": 1.0270500392624197e-05, "loss": 0.7269, "step": 8675 }, { "epoch": 0.5067757009345795, "grad_norm": 1.6484286785125732, "learning_rate": 1.0268609238159513e-05, "loss": 0.9869, "step": 8676 }, { "epoch": 0.5068341121495327, "grad_norm": 1.69534432888031, "learning_rate": 1.026671807408113e-05, "loss": 0.9405, "step": 8677 }, { "epoch": 0.506892523364486, "grad_norm": 1.4705853462219238, "learning_rate": 1.0264826900456733e-05, "loss": 0.7555, "step": 8678 }, { "epoch": 0.5069509345794393, "grad_norm": 1.2778266668319702, "learning_rate": 1.0262935717354e-05, "loss": 0.8949, "step": 8679 }, { "epoch": 0.5070093457943925, "grad_norm": 1.5705304145812988, "learning_rate": 1.0261044524840633e-05, "loss": 0.663, "step": 8680 }, { "epoch": 0.5070677570093458, "grad_norm": 1.2508149147033691, "learning_rate": 1.025915332298431e-05, "loss": 0.7753, "step": 8681 }, { "epoch": 0.507126168224299, "grad_norm": 1.5154589414596558, "learning_rate": 1.0257262111852715e-05, "loss": 0.8944, "step": 8682 }, { "epoch": 0.5071845794392523, "grad_norm": 0.919369101524353, "learning_rate": 1.0255370891513544e-05, "loss": 0.7846, "step": 8683 }, { "epoch": 0.5072429906542056, "grad_norm": 1.8030129671096802, "learning_rate": 1.0253479662034477e-05, "loss": 0.7819, "step": 8684 }, { "epoch": 0.5073014018691588, "grad_norm": 1.1486095190048218, "learning_rate": 1.0251588423483205e-05, "loss": 0.8041, "step": 8685 }, { "epoch": 0.5073598130841122, "grad_norm": 1.4725098609924316, "learning_rate": 1.0249697175927425e-05, "loss": 0.7621, "step": 8686 }, { "epoch": 0.5074182242990655, "grad_norm": 1.4489377737045288, "learning_rate": 1.0247805919434812e-05, "loss": 0.9477, "step": 8687 }, { "epoch": 0.5074766355140187, "grad_norm": 1.2732654809951782, "learning_rate": 1.0245914654073066e-05, "loss": 0.8337, "step": 8688 }, { "epoch": 0.507535046728972, "grad_norm": 1.571071743965149, "learning_rate": 1.024402337990987e-05, "loss": 0.7476, "step": 8689 }, { "epoch": 0.5075934579439252, "grad_norm": 1.813157081604004, "learning_rate": 1.024213209701292e-05, "loss": 1.0313, "step": 8690 }, { "epoch": 0.5076518691588785, "grad_norm": 2.105072498321533, "learning_rate": 1.0240240805449904e-05, "loss": 0.6815, "step": 8691 }, { "epoch": 0.5077102803738318, "grad_norm": 1.6183288097381592, "learning_rate": 1.0238349505288508e-05, "loss": 0.7324, "step": 8692 }, { "epoch": 0.507768691588785, "grad_norm": 1.3835707902908325, "learning_rate": 1.0236458196596426e-05, "loss": 0.7424, "step": 8693 }, { "epoch": 0.5078271028037383, "grad_norm": 1.2778700590133667, "learning_rate": 1.0234566879441352e-05, "loss": 0.8284, "step": 8694 }, { "epoch": 0.5078855140186916, "grad_norm": 1.6216710805892944, "learning_rate": 1.0232675553890975e-05, "loss": 0.9195, "step": 8695 }, { "epoch": 0.5079439252336448, "grad_norm": 1.0490435361862183, "learning_rate": 1.0230784220012986e-05, "loss": 0.7301, "step": 8696 }, { "epoch": 0.5080023364485982, "grad_norm": 1.3330767154693604, "learning_rate": 1.0228892877875078e-05, "loss": 0.8586, "step": 8697 }, { "epoch": 0.5080607476635514, "grad_norm": 1.4444334506988525, "learning_rate": 1.0227001527544947e-05, "loss": 0.7683, "step": 8698 }, { "epoch": 0.5081191588785047, "grad_norm": 1.806036353111267, "learning_rate": 1.0225110169090276e-05, "loss": 0.7854, "step": 8699 }, { "epoch": 0.508177570093458, "grad_norm": 1.9502434730529785, "learning_rate": 1.022321880257877e-05, "loss": 0.9741, "step": 8700 }, { "epoch": 0.5082359813084112, "grad_norm": 1.71083664894104, "learning_rate": 1.0221327428078112e-05, "loss": 0.8772, "step": 8701 }, { "epoch": 0.5082943925233645, "grad_norm": 0.9066480398178101, "learning_rate": 1.0219436045656e-05, "loss": 0.8886, "step": 8702 }, { "epoch": 0.5083528037383177, "grad_norm": 1.1605356931686401, "learning_rate": 1.0217544655380129e-05, "loss": 0.5678, "step": 8703 }, { "epoch": 0.508411214953271, "grad_norm": 1.4467298984527588, "learning_rate": 1.021565325731819e-05, "loss": 0.7341, "step": 8704 }, { "epoch": 0.5084696261682243, "grad_norm": 4.1785969734191895, "learning_rate": 1.0213761851537882e-05, "loss": 0.6168, "step": 8705 }, { "epoch": 0.5085280373831775, "grad_norm": 1.3542331457138062, "learning_rate": 1.0211870438106897e-05, "loss": 0.8073, "step": 8706 }, { "epoch": 0.5085864485981308, "grad_norm": 1.6929198503494263, "learning_rate": 1.0209979017092926e-05, "loss": 0.8261, "step": 8707 }, { "epoch": 0.5086448598130842, "grad_norm": 1.3175568580627441, "learning_rate": 1.0208087588563672e-05, "loss": 0.7768, "step": 8708 }, { "epoch": 0.5087032710280374, "grad_norm": 1.2367126941680908, "learning_rate": 1.0206196152586822e-05, "loss": 0.9234, "step": 8709 }, { "epoch": 0.5087616822429907, "grad_norm": 1.303064227104187, "learning_rate": 1.020430470923008e-05, "loss": 0.8373, "step": 8710 }, { "epoch": 0.5088200934579439, "grad_norm": 1.3209037780761719, "learning_rate": 1.0202413258561137e-05, "loss": 0.6773, "step": 8711 }, { "epoch": 0.5088785046728972, "grad_norm": 1.3516734838485718, "learning_rate": 1.0200521800647689e-05, "loss": 0.9418, "step": 8712 }, { "epoch": 0.5089369158878505, "grad_norm": 1.4657676219940186, "learning_rate": 1.0198630335557433e-05, "loss": 0.9167, "step": 8713 }, { "epoch": 0.5089953271028037, "grad_norm": 1.4312669038772583, "learning_rate": 1.0196738863358072e-05, "loss": 0.7701, "step": 8714 }, { "epoch": 0.509053738317757, "grad_norm": 1.18099045753479, "learning_rate": 1.0194847384117293e-05, "loss": 0.7528, "step": 8715 }, { "epoch": 0.5091121495327103, "grad_norm": 1.4349325895309448, "learning_rate": 1.01929558979028e-05, "loss": 0.878, "step": 8716 }, { "epoch": 0.5091705607476635, "grad_norm": 1.2550885677337646, "learning_rate": 1.0191064404782286e-05, "loss": 0.8883, "step": 8717 }, { "epoch": 0.5092289719626168, "grad_norm": 1.1169885396957397, "learning_rate": 1.0189172904823455e-05, "loss": 0.7676, "step": 8718 }, { "epoch": 0.50928738317757, "grad_norm": 1.7296260595321655, "learning_rate": 1.0187281398094e-05, "loss": 0.8907, "step": 8719 }, { "epoch": 0.5093457943925234, "grad_norm": 0.9688595533370972, "learning_rate": 1.018538988466162e-05, "loss": 0.7334, "step": 8720 }, { "epoch": 0.5094042056074767, "grad_norm": 1.460009217262268, "learning_rate": 1.0183498364594014e-05, "loss": 0.965, "step": 8721 }, { "epoch": 0.5094626168224299, "grad_norm": 1.3782248497009277, "learning_rate": 1.0181606837958882e-05, "loss": 0.8163, "step": 8722 }, { "epoch": 0.5095210280373832, "grad_norm": 1.0298539400100708, "learning_rate": 1.0179715304823921e-05, "loss": 0.7967, "step": 8723 }, { "epoch": 0.5095794392523364, "grad_norm": 1.246126413345337, "learning_rate": 1.0177823765256831e-05, "loss": 0.8274, "step": 8724 }, { "epoch": 0.5096378504672897, "grad_norm": 1.0740694999694824, "learning_rate": 1.0175932219325314e-05, "loss": 0.732, "step": 8725 }, { "epoch": 0.509696261682243, "grad_norm": 1.4771316051483154, "learning_rate": 1.0174040667097061e-05, "loss": 0.9178, "step": 8726 }, { "epoch": 0.5097546728971962, "grad_norm": 1.4864798784255981, "learning_rate": 1.0172149108639781e-05, "loss": 0.7433, "step": 8727 }, { "epoch": 0.5098130841121495, "grad_norm": 1.5258574485778809, "learning_rate": 1.0170257544021173e-05, "loss": 0.869, "step": 8728 }, { "epoch": 0.5098714953271029, "grad_norm": 1.1025702953338623, "learning_rate": 1.0168365973308936e-05, "loss": 0.7006, "step": 8729 }, { "epoch": 0.509929906542056, "grad_norm": 1.2590956687927246, "learning_rate": 1.0166474396570769e-05, "loss": 0.7475, "step": 8730 }, { "epoch": 0.5099883177570094, "grad_norm": 1.6773853302001953, "learning_rate": 1.0164582813874375e-05, "loss": 0.8006, "step": 8731 }, { "epoch": 0.5100467289719626, "grad_norm": 0.8739032745361328, "learning_rate": 1.016269122528745e-05, "loss": 0.7213, "step": 8732 }, { "epoch": 0.5101051401869159, "grad_norm": 1.3983606100082397, "learning_rate": 1.0160799630877703e-05, "loss": 0.9011, "step": 8733 }, { "epoch": 0.5101635514018692, "grad_norm": 1.25416898727417, "learning_rate": 1.015890803071283e-05, "loss": 0.7457, "step": 8734 }, { "epoch": 0.5102219626168224, "grad_norm": 1.4666422605514526, "learning_rate": 1.0157016424860535e-05, "loss": 0.7637, "step": 8735 }, { "epoch": 0.5102803738317757, "grad_norm": 0.9791244268417358, "learning_rate": 1.0155124813388517e-05, "loss": 0.6566, "step": 8736 }, { "epoch": 0.510338785046729, "grad_norm": 1.240062952041626, "learning_rate": 1.015323319636448e-05, "loss": 0.84, "step": 8737 }, { "epoch": 0.5103971962616822, "grad_norm": 1.0279844999313354, "learning_rate": 1.0151341573856129e-05, "loss": 0.7724, "step": 8738 }, { "epoch": 0.5104556074766355, "grad_norm": 1.0967055559158325, "learning_rate": 1.0149449945931163e-05, "loss": 0.6542, "step": 8739 }, { "epoch": 0.5105140186915887, "grad_norm": 1.1036242246627808, "learning_rate": 1.0147558312657282e-05, "loss": 0.8545, "step": 8740 }, { "epoch": 0.5105724299065421, "grad_norm": 1.316125750541687, "learning_rate": 1.0145666674102195e-05, "loss": 0.7497, "step": 8741 }, { "epoch": 0.5106308411214954, "grad_norm": 1.058022379875183, "learning_rate": 1.0143775030333601e-05, "loss": 0.5881, "step": 8742 }, { "epoch": 0.5106892523364486, "grad_norm": 1.0657540559768677, "learning_rate": 1.0141883381419203e-05, "loss": 0.8963, "step": 8743 }, { "epoch": 0.5107476635514019, "grad_norm": 1.722511649131775, "learning_rate": 1.0139991727426708e-05, "loss": 0.791, "step": 8744 }, { "epoch": 0.5108060747663551, "grad_norm": 1.5090616941452026, "learning_rate": 1.0138100068423813e-05, "loss": 0.7568, "step": 8745 }, { "epoch": 0.5108644859813084, "grad_norm": 1.2460882663726807, "learning_rate": 1.0136208404478229e-05, "loss": 0.9175, "step": 8746 }, { "epoch": 0.5109228971962617, "grad_norm": 1.2722272872924805, "learning_rate": 1.0134316735657657e-05, "loss": 0.9725, "step": 8747 }, { "epoch": 0.5109813084112149, "grad_norm": 1.2078478336334229, "learning_rate": 1.01324250620298e-05, "loss": 0.916, "step": 8748 }, { "epoch": 0.5110397196261682, "grad_norm": 1.2987110614776611, "learning_rate": 1.0130533383662361e-05, "loss": 0.7991, "step": 8749 }, { "epoch": 0.5110981308411215, "grad_norm": 1.1787868738174438, "learning_rate": 1.012864170062305e-05, "loss": 0.8469, "step": 8750 }, { "epoch": 0.5111565420560747, "grad_norm": 0.9371494650840759, "learning_rate": 1.0126750012979564e-05, "loss": 0.6133, "step": 8751 }, { "epoch": 0.5112149532710281, "grad_norm": 1.3431477546691895, "learning_rate": 1.0124858320799612e-05, "loss": 0.7001, "step": 8752 }, { "epoch": 0.5112733644859813, "grad_norm": 1.1271194219589233, "learning_rate": 1.0122966624150903e-05, "loss": 0.712, "step": 8753 }, { "epoch": 0.5113317757009346, "grad_norm": 1.3822089433670044, "learning_rate": 1.0121074923101135e-05, "loss": 0.8309, "step": 8754 }, { "epoch": 0.5113901869158879, "grad_norm": 1.727028727531433, "learning_rate": 1.0119183217718016e-05, "loss": 0.926, "step": 8755 }, { "epoch": 0.5114485981308411, "grad_norm": 1.271942377090454, "learning_rate": 1.0117291508069252e-05, "loss": 0.8253, "step": 8756 }, { "epoch": 0.5115070093457944, "grad_norm": 1.2418947219848633, "learning_rate": 1.0115399794222544e-05, "loss": 0.8118, "step": 8757 }, { "epoch": 0.5115654205607477, "grad_norm": 1.4071941375732422, "learning_rate": 1.0113508076245609e-05, "loss": 0.796, "step": 8758 }, { "epoch": 0.5116238317757009, "grad_norm": 1.2570545673370361, "learning_rate": 1.0111616354206138e-05, "loss": 0.8849, "step": 8759 }, { "epoch": 0.5116822429906542, "grad_norm": 1.3948715925216675, "learning_rate": 1.0109724628171846e-05, "loss": 0.844, "step": 8760 }, { "epoch": 0.5117406542056074, "grad_norm": 0.8993479609489441, "learning_rate": 1.0107832898210438e-05, "loss": 0.6775, "step": 8761 }, { "epoch": 0.5117990654205608, "grad_norm": 1.283848762512207, "learning_rate": 1.0105941164389618e-05, "loss": 0.75, "step": 8762 }, { "epoch": 0.5118574766355141, "grad_norm": 1.5814588069915771, "learning_rate": 1.01040494267771e-05, "loss": 0.9654, "step": 8763 }, { "epoch": 0.5119158878504673, "grad_norm": 1.587070345878601, "learning_rate": 1.0102157685440581e-05, "loss": 0.8241, "step": 8764 }, { "epoch": 0.5119742990654206, "grad_norm": 1.166029691696167, "learning_rate": 1.0100265940447769e-05, "loss": 0.8114, "step": 8765 }, { "epoch": 0.5120327102803738, "grad_norm": 1.1769284009933472, "learning_rate": 1.0098374191866376e-05, "loss": 0.8179, "step": 8766 }, { "epoch": 0.5120911214953271, "grad_norm": 1.5647590160369873, "learning_rate": 1.0096482439764105e-05, "loss": 0.8927, "step": 8767 }, { "epoch": 0.5121495327102804, "grad_norm": 0.9874793291091919, "learning_rate": 1.0094590684208665e-05, "loss": 0.7272, "step": 8768 }, { "epoch": 0.5122079439252336, "grad_norm": 1.0737740993499756, "learning_rate": 1.0092698925267762e-05, "loss": 0.6306, "step": 8769 }, { "epoch": 0.5122663551401869, "grad_norm": 1.0763256549835205, "learning_rate": 1.00908071630091e-05, "loss": 0.8325, "step": 8770 }, { "epoch": 0.5123247663551402, "grad_norm": 1.3582684993743896, "learning_rate": 1.0088915397500394e-05, "loss": 0.8792, "step": 8771 }, { "epoch": 0.5123831775700934, "grad_norm": 1.0211058855056763, "learning_rate": 1.0087023628809347e-05, "loss": 0.7039, "step": 8772 }, { "epoch": 0.5124415887850468, "grad_norm": 1.359070062637329, "learning_rate": 1.0085131857003668e-05, "loss": 0.8269, "step": 8773 }, { "epoch": 0.5125, "grad_norm": 1.0054594278335571, "learning_rate": 1.008324008215106e-05, "loss": 0.6143, "step": 8774 }, { "epoch": 0.5125584112149533, "grad_norm": 1.2330663204193115, "learning_rate": 1.0081348304319238e-05, "loss": 0.8082, "step": 8775 }, { "epoch": 0.5126168224299066, "grad_norm": 1.0655370950698853, "learning_rate": 1.0079456523575903e-05, "loss": 0.7063, "step": 8776 }, { "epoch": 0.5126752336448598, "grad_norm": 1.7695738077163696, "learning_rate": 1.0077564739988772e-05, "loss": 0.9588, "step": 8777 }, { "epoch": 0.5127336448598131, "grad_norm": 1.0941979885101318, "learning_rate": 1.0075672953625544e-05, "loss": 0.8863, "step": 8778 }, { "epoch": 0.5127920560747663, "grad_norm": 1.7994333505630493, "learning_rate": 1.0073781164553932e-05, "loss": 0.8335, "step": 8779 }, { "epoch": 0.5128504672897196, "grad_norm": 1.3672266006469727, "learning_rate": 1.0071889372841646e-05, "loss": 0.7456, "step": 8780 }, { "epoch": 0.5129088785046729, "grad_norm": 2.0119221210479736, "learning_rate": 1.0069997578556387e-05, "loss": 0.896, "step": 8781 }, { "epoch": 0.5129672897196261, "grad_norm": 1.1957058906555176, "learning_rate": 1.0068105781765875e-05, "loss": 0.8577, "step": 8782 }, { "epoch": 0.5130257009345794, "grad_norm": 1.068917155265808, "learning_rate": 1.0066213982537811e-05, "loss": 0.6091, "step": 8783 }, { "epoch": 0.5130841121495328, "grad_norm": 1.2334624528884888, "learning_rate": 1.00643221809399e-05, "loss": 0.808, "step": 8784 }, { "epoch": 0.513142523364486, "grad_norm": 1.9363127946853638, "learning_rate": 1.006243037703986e-05, "loss": 0.9165, "step": 8785 }, { "epoch": 0.5132009345794393, "grad_norm": 1.306991457939148, "learning_rate": 1.0060538570905396e-05, "loss": 0.8449, "step": 8786 }, { "epoch": 0.5132593457943925, "grad_norm": 0.952630341053009, "learning_rate": 1.0058646762604216e-05, "loss": 0.6383, "step": 8787 }, { "epoch": 0.5133177570093458, "grad_norm": 3.831784248352051, "learning_rate": 1.0056754952204028e-05, "loss": 0.8778, "step": 8788 }, { "epoch": 0.5133761682242991, "grad_norm": 1.5166858434677124, "learning_rate": 1.0054863139772547e-05, "loss": 0.6784, "step": 8789 }, { "epoch": 0.5134345794392523, "grad_norm": 2.3085122108459473, "learning_rate": 1.0052971325377472e-05, "loss": 0.7591, "step": 8790 }, { "epoch": 0.5134929906542056, "grad_norm": 1.7611058950424194, "learning_rate": 1.0051079509086524e-05, "loss": 0.7087, "step": 8791 }, { "epoch": 0.5135514018691589, "grad_norm": 1.3241487741470337, "learning_rate": 1.0049187690967404e-05, "loss": 0.7167, "step": 8792 }, { "epoch": 0.5136098130841121, "grad_norm": 1.9762994050979614, "learning_rate": 1.0047295871087825e-05, "loss": 0.7568, "step": 8793 }, { "epoch": 0.5136682242990654, "grad_norm": 2.3407418727874756, "learning_rate": 1.0045404049515498e-05, "loss": 0.8816, "step": 8794 }, { "epoch": 0.5137266355140186, "grad_norm": 1.190247893333435, "learning_rate": 1.0043512226318124e-05, "loss": 0.7663, "step": 8795 }, { "epoch": 0.513785046728972, "grad_norm": 1.643476128578186, "learning_rate": 1.0041620401563423e-05, "loss": 0.7636, "step": 8796 }, { "epoch": 0.5138434579439253, "grad_norm": 1.742812156677246, "learning_rate": 1.0039728575319102e-05, "loss": 0.6446, "step": 8797 }, { "epoch": 0.5139018691588785, "grad_norm": 1.9061230421066284, "learning_rate": 1.0037836747652864e-05, "loss": 0.8335, "step": 8798 }, { "epoch": 0.5139602803738318, "grad_norm": 1.4308335781097412, "learning_rate": 1.0035944918632429e-05, "loss": 0.6756, "step": 8799 }, { "epoch": 0.514018691588785, "grad_norm": 1.2399342060089111, "learning_rate": 1.0034053088325501e-05, "loss": 0.6136, "step": 8800 }, { "epoch": 0.5140771028037383, "grad_norm": 3.983670711517334, "learning_rate": 1.0032161256799788e-05, "loss": 1.0674, "step": 8801 }, { "epoch": 0.5141355140186916, "grad_norm": 1.192023754119873, "learning_rate": 1.0030269424123005e-05, "loss": 0.8722, "step": 8802 }, { "epoch": 0.5141939252336448, "grad_norm": 3.209744691848755, "learning_rate": 1.0028377590362856e-05, "loss": 0.815, "step": 8803 }, { "epoch": 0.5142523364485981, "grad_norm": 3.240285634994507, "learning_rate": 1.0026485755587059e-05, "loss": 0.9639, "step": 8804 }, { "epoch": 0.5143107476635514, "grad_norm": 1.350691318511963, "learning_rate": 1.0024593919863317e-05, "loss": 0.7755, "step": 8805 }, { "epoch": 0.5143691588785047, "grad_norm": 4.868653774261475, "learning_rate": 1.0022702083259344e-05, "loss": 0.929, "step": 8806 }, { "epoch": 0.514427570093458, "grad_norm": 1.0384865999221802, "learning_rate": 1.0020810245842847e-05, "loss": 0.7513, "step": 8807 }, { "epoch": 0.5144859813084112, "grad_norm": 2.383192300796509, "learning_rate": 1.0018918407681537e-05, "loss": 0.882, "step": 8808 }, { "epoch": 0.5145443925233645, "grad_norm": 2.8826241493225098, "learning_rate": 1.0017026568843125e-05, "loss": 1.0868, "step": 8809 }, { "epoch": 0.5146028037383178, "grad_norm": 1.3307472467422485, "learning_rate": 1.0015134729395322e-05, "loss": 0.877, "step": 8810 }, { "epoch": 0.514661214953271, "grad_norm": 1.5682470798492432, "learning_rate": 1.0013242889405836e-05, "loss": 0.6668, "step": 8811 }, { "epoch": 0.5147196261682243, "grad_norm": 1.9298418760299683, "learning_rate": 1.001135104894238e-05, "loss": 0.8015, "step": 8812 }, { "epoch": 0.5147780373831776, "grad_norm": 1.8204858303070068, "learning_rate": 1.000945920807266e-05, "loss": 0.8089, "step": 8813 }, { "epoch": 0.5148364485981308, "grad_norm": 1.4970178604125977, "learning_rate": 1.0007567366864388e-05, "loss": 0.8401, "step": 8814 }, { "epoch": 0.5148948598130841, "grad_norm": 1.3958786725997925, "learning_rate": 1.0005675525385277e-05, "loss": 0.7763, "step": 8815 }, { "epoch": 0.5149532710280373, "grad_norm": 3.487241744995117, "learning_rate": 1.0003783683703039e-05, "loss": 1.0981, "step": 8816 }, { "epoch": 0.5150116822429907, "grad_norm": 1.3661943674087524, "learning_rate": 1.0001891841885374e-05, "loss": 0.8391, "step": 8817 }, { "epoch": 0.515070093457944, "grad_norm": 1.5781362056732178, "learning_rate": 1e-05, "loss": 0.6622, "step": 8818 }, { "epoch": 0.5151285046728972, "grad_norm": 1.3967727422714233, "learning_rate": 9.99810815811463e-06, "loss": 0.5538, "step": 8819 }, { "epoch": 0.5151869158878505, "grad_norm": 3.4050703048706055, "learning_rate": 9.996216316296964e-06, "loss": 0.8729, "step": 8820 }, { "epoch": 0.5152453271028037, "grad_norm": 1.2283756732940674, "learning_rate": 9.994324474614725e-06, "loss": 0.7946, "step": 8821 }, { "epoch": 0.515303738317757, "grad_norm": 2.9517736434936523, "learning_rate": 9.992432633135612e-06, "loss": 0.9883, "step": 8822 }, { "epoch": 0.5153621495327103, "grad_norm": 2.9631617069244385, "learning_rate": 9.990540791927343e-06, "loss": 0.7476, "step": 8823 }, { "epoch": 0.5154205607476635, "grad_norm": 0.8196703195571899, "learning_rate": 9.988648951057627e-06, "loss": 0.6474, "step": 8824 }, { "epoch": 0.5154789719626168, "grad_norm": 1.0885381698608398, "learning_rate": 9.986757110594168e-06, "loss": 0.8502, "step": 8825 }, { "epoch": 0.5155373831775701, "grad_norm": 2.554476737976074, "learning_rate": 9.984865270604683e-06, "loss": 0.884, "step": 8826 }, { "epoch": 0.5155957943925233, "grad_norm": 1.9300940036773682, "learning_rate": 9.982973431156877e-06, "loss": 0.9924, "step": 8827 }, { "epoch": 0.5156542056074767, "grad_norm": 1.37371826171875, "learning_rate": 9.981081592318466e-06, "loss": 0.862, "step": 8828 }, { "epoch": 0.5157126168224299, "grad_norm": 2.4248881340026855, "learning_rate": 9.97918975415716e-06, "loss": 0.7536, "step": 8829 }, { "epoch": 0.5157710280373832, "grad_norm": 1.9277650117874146, "learning_rate": 9.97729791674066e-06, "loss": 0.8548, "step": 8830 }, { "epoch": 0.5158294392523365, "grad_norm": 2.074235677719116, "learning_rate": 9.975406080136685e-06, "loss": 0.9006, "step": 8831 }, { "epoch": 0.5158878504672897, "grad_norm": 2.6656172275543213, "learning_rate": 9.973514244412941e-06, "loss": 0.8544, "step": 8832 }, { "epoch": 0.515946261682243, "grad_norm": 1.577407956123352, "learning_rate": 9.971622409637146e-06, "loss": 0.7544, "step": 8833 }, { "epoch": 0.5160046728971963, "grad_norm": 1.4977304935455322, "learning_rate": 9.969730575876999e-06, "loss": 1.0107, "step": 8834 }, { "epoch": 0.5160630841121495, "grad_norm": 1.2713831663131714, "learning_rate": 9.967838743200213e-06, "loss": 0.8016, "step": 8835 }, { "epoch": 0.5161214953271028, "grad_norm": 2.739224433898926, "learning_rate": 9.965946911674502e-06, "loss": 0.7803, "step": 8836 }, { "epoch": 0.516179906542056, "grad_norm": 1.8621525764465332, "learning_rate": 9.96405508136757e-06, "loss": 0.7253, "step": 8837 }, { "epoch": 0.5162383177570093, "grad_norm": 1.6955286264419556, "learning_rate": 9.962163252347137e-06, "loss": 0.8258, "step": 8838 }, { "epoch": 0.5162967289719627, "grad_norm": 2.3015294075012207, "learning_rate": 9.960271424680903e-06, "loss": 0.8132, "step": 8839 }, { "epoch": 0.5163551401869159, "grad_norm": 1.5203945636749268, "learning_rate": 9.958379598436579e-06, "loss": 0.7813, "step": 8840 }, { "epoch": 0.5164135514018692, "grad_norm": 1.3504387140274048, "learning_rate": 9.95648777368188e-06, "loss": 0.9386, "step": 8841 }, { "epoch": 0.5164719626168224, "grad_norm": 1.7022470235824585, "learning_rate": 9.954595950484507e-06, "loss": 0.6817, "step": 8842 }, { "epoch": 0.5165303738317757, "grad_norm": 1.8486344814300537, "learning_rate": 9.952704128912178e-06, "loss": 0.8696, "step": 8843 }, { "epoch": 0.516588785046729, "grad_norm": 1.4868243932724, "learning_rate": 9.950812309032599e-06, "loss": 0.8108, "step": 8844 }, { "epoch": 0.5166471962616822, "grad_norm": 2.079456090927124, "learning_rate": 9.948920490913478e-06, "loss": 0.6831, "step": 8845 }, { "epoch": 0.5167056074766355, "grad_norm": 1.950417399406433, "learning_rate": 9.947028674622531e-06, "loss": 0.8091, "step": 8846 }, { "epoch": 0.5167640186915888, "grad_norm": 1.3537086248397827, "learning_rate": 9.945136860227458e-06, "loss": 0.8946, "step": 8847 }, { "epoch": 0.516822429906542, "grad_norm": 3.048762083053589, "learning_rate": 9.943245047795973e-06, "loss": 0.9834, "step": 8848 }, { "epoch": 0.5168808411214953, "grad_norm": 1.2114958763122559, "learning_rate": 9.94135323739579e-06, "loss": 0.6833, "step": 8849 }, { "epoch": 0.5169392523364486, "grad_norm": 1.7340867519378662, "learning_rate": 9.939461429094608e-06, "loss": 0.9343, "step": 8850 }, { "epoch": 0.5169976635514019, "grad_norm": 2.1767218112945557, "learning_rate": 9.937569622960142e-06, "loss": 0.7675, "step": 8851 }, { "epoch": 0.5170560747663552, "grad_norm": 1.444509744644165, "learning_rate": 9.935677819060102e-06, "loss": 0.6837, "step": 8852 }, { "epoch": 0.5171144859813084, "grad_norm": 1.675580382347107, "learning_rate": 9.933786017462192e-06, "loss": 0.8012, "step": 8853 }, { "epoch": 0.5171728971962617, "grad_norm": 1.3548823595046997, "learning_rate": 9.93189421823413e-06, "loss": 0.8277, "step": 8854 }, { "epoch": 0.517231308411215, "grad_norm": 1.4062308073043823, "learning_rate": 9.930002421443611e-06, "loss": 0.8, "step": 8855 }, { "epoch": 0.5172897196261682, "grad_norm": 1.401039481163025, "learning_rate": 9.928110627158357e-06, "loss": 0.9136, "step": 8856 }, { "epoch": 0.5173481308411215, "grad_norm": 0.9998422265052795, "learning_rate": 9.926218835446073e-06, "loss": 0.7562, "step": 8857 }, { "epoch": 0.5174065420560747, "grad_norm": 1.3541609048843384, "learning_rate": 9.924327046374459e-06, "loss": 0.639, "step": 8858 }, { "epoch": 0.517464953271028, "grad_norm": 1.2305731773376465, "learning_rate": 9.922435260011233e-06, "loss": 0.7751, "step": 8859 }, { "epoch": 0.5175233644859814, "grad_norm": 1.2001370191574097, "learning_rate": 9.920543476424097e-06, "loss": 0.8265, "step": 8860 }, { "epoch": 0.5175817757009346, "grad_norm": 1.5854209661483765, "learning_rate": 9.918651695680765e-06, "loss": 0.8432, "step": 8861 }, { "epoch": 0.5176401869158879, "grad_norm": 1.1582777500152588, "learning_rate": 9.916759917848945e-06, "loss": 0.9433, "step": 8862 }, { "epoch": 0.5176985981308411, "grad_norm": 1.5476160049438477, "learning_rate": 9.914868142996337e-06, "loss": 0.6913, "step": 8863 }, { "epoch": 0.5177570093457944, "grad_norm": 1.522396445274353, "learning_rate": 9.912976371190657e-06, "loss": 0.8451, "step": 8864 }, { "epoch": 0.5178154205607477, "grad_norm": 1.212594985961914, "learning_rate": 9.911084602499606e-06, "loss": 0.5945, "step": 8865 }, { "epoch": 0.5178738317757009, "grad_norm": 1.122289776802063, "learning_rate": 9.909192836990902e-06, "loss": 0.7612, "step": 8866 }, { "epoch": 0.5179322429906542, "grad_norm": 1.0219759941101074, "learning_rate": 9.907301074732243e-06, "loss": 0.6263, "step": 8867 }, { "epoch": 0.5179906542056075, "grad_norm": 1.914457082748413, "learning_rate": 9.905409315791338e-06, "loss": 0.8216, "step": 8868 }, { "epoch": 0.5180490654205607, "grad_norm": 1.1910151243209839, "learning_rate": 9.903517560235896e-06, "loss": 0.773, "step": 8869 }, { "epoch": 0.518107476635514, "grad_norm": 1.2458465099334717, "learning_rate": 9.901625808133625e-06, "loss": 0.8232, "step": 8870 }, { "epoch": 0.5181658878504672, "grad_norm": 1.4091193675994873, "learning_rate": 9.899734059552233e-06, "loss": 0.7792, "step": 8871 }, { "epoch": 0.5182242990654206, "grad_norm": 1.2402018308639526, "learning_rate": 9.897842314559424e-06, "loss": 0.8194, "step": 8872 }, { "epoch": 0.5182827102803739, "grad_norm": 1.3534046411514282, "learning_rate": 9.895950573222903e-06, "loss": 0.7684, "step": 8873 }, { "epoch": 0.5183411214953271, "grad_norm": 0.9886946082115173, "learning_rate": 9.894058835610384e-06, "loss": 0.8182, "step": 8874 }, { "epoch": 0.5183995327102804, "grad_norm": 1.2737826108932495, "learning_rate": 9.892167101789563e-06, "loss": 0.6372, "step": 8875 }, { "epoch": 0.5184579439252337, "grad_norm": 1.8537418842315674, "learning_rate": 9.890275371828156e-06, "loss": 0.617, "step": 8876 }, { "epoch": 0.5185163551401869, "grad_norm": 0.9235401153564453, "learning_rate": 9.888383645793865e-06, "loss": 0.6745, "step": 8877 }, { "epoch": 0.5185747663551402, "grad_norm": 1.9808225631713867, "learning_rate": 9.886491923754396e-06, "loss": 0.8447, "step": 8878 }, { "epoch": 0.5186331775700934, "grad_norm": 1.0025548934936523, "learning_rate": 9.884600205777458e-06, "loss": 0.6521, "step": 8879 }, { "epoch": 0.5186915887850467, "grad_norm": 1.1123167276382446, "learning_rate": 9.882708491930752e-06, "loss": 0.6873, "step": 8880 }, { "epoch": 0.51875, "grad_norm": 1.745197057723999, "learning_rate": 9.880816782281987e-06, "loss": 0.8317, "step": 8881 }, { "epoch": 0.5188084112149532, "grad_norm": 1.0145217180252075, "learning_rate": 9.87892507689887e-06, "loss": 0.6894, "step": 8882 }, { "epoch": 0.5188668224299066, "grad_norm": 1.1665618419647217, "learning_rate": 9.8770333758491e-06, "loss": 0.7227, "step": 8883 }, { "epoch": 0.5189252336448598, "grad_norm": 2.508396625518799, "learning_rate": 9.87514167920039e-06, "loss": 0.8185, "step": 8884 }, { "epoch": 0.5189836448598131, "grad_norm": 1.6372036933898926, "learning_rate": 9.873249987020437e-06, "loss": 0.8651, "step": 8885 }, { "epoch": 0.5190420560747664, "grad_norm": 1.5602457523345947, "learning_rate": 9.871358299376953e-06, "loss": 0.8679, "step": 8886 }, { "epoch": 0.5191004672897196, "grad_norm": 1.5397788286209106, "learning_rate": 9.869466616337642e-06, "loss": 0.924, "step": 8887 }, { "epoch": 0.5191588785046729, "grad_norm": 1.3812026977539062, "learning_rate": 9.867574937970204e-06, "loss": 0.8241, "step": 8888 }, { "epoch": 0.5192172897196262, "grad_norm": 1.3362740278244019, "learning_rate": 9.865683264342347e-06, "loss": 0.6579, "step": 8889 }, { "epoch": 0.5192757009345794, "grad_norm": 1.4695689678192139, "learning_rate": 9.863791595521771e-06, "loss": 0.6751, "step": 8890 }, { "epoch": 0.5193341121495327, "grad_norm": 1.3303231000900269, "learning_rate": 9.861899931576188e-06, "loss": 0.822, "step": 8891 }, { "epoch": 0.5193925233644859, "grad_norm": 1.219150185585022, "learning_rate": 9.860008272573297e-06, "loss": 0.8331, "step": 8892 }, { "epoch": 0.5194509345794392, "grad_norm": 1.0866353511810303, "learning_rate": 9.858116618580799e-06, "loss": 0.8391, "step": 8893 }, { "epoch": 0.5195093457943926, "grad_norm": 2.2310056686401367, "learning_rate": 9.856224969666402e-06, "loss": 0.9352, "step": 8894 }, { "epoch": 0.5195677570093458, "grad_norm": 1.2200138568878174, "learning_rate": 9.854333325897805e-06, "loss": 0.7263, "step": 8895 }, { "epoch": 0.5196261682242991, "grad_norm": 1.387223482131958, "learning_rate": 9.852441687342721e-06, "loss": 0.8407, "step": 8896 }, { "epoch": 0.5196845794392523, "grad_norm": 1.547084927558899, "learning_rate": 9.850550054068842e-06, "loss": 0.7134, "step": 8897 }, { "epoch": 0.5197429906542056, "grad_norm": 1.3451393842697144, "learning_rate": 9.848658426143873e-06, "loss": 0.8095, "step": 8898 }, { "epoch": 0.5198014018691589, "grad_norm": 2.4506568908691406, "learning_rate": 9.846766803635523e-06, "loss": 0.7718, "step": 8899 }, { "epoch": 0.5198598130841121, "grad_norm": 1.0890886783599854, "learning_rate": 9.844875186611482e-06, "loss": 0.6389, "step": 8900 }, { "epoch": 0.5199182242990654, "grad_norm": 1.5777136087417603, "learning_rate": 9.842983575139468e-06, "loss": 0.8093, "step": 8901 }, { "epoch": 0.5199766355140187, "grad_norm": 1.439374327659607, "learning_rate": 9.841091969287173e-06, "loss": 1.0102, "step": 8902 }, { "epoch": 0.5200350467289719, "grad_norm": 1.0344479084014893, "learning_rate": 9.839200369122299e-06, "loss": 0.7421, "step": 8903 }, { "epoch": 0.5200934579439253, "grad_norm": 1.3465977907180786, "learning_rate": 9.837308774712553e-06, "loss": 0.9261, "step": 8904 }, { "epoch": 0.5201518691588785, "grad_norm": 1.5784342288970947, "learning_rate": 9.835417186125631e-06, "loss": 0.7665, "step": 8905 }, { "epoch": 0.5202102803738318, "grad_norm": 1.2651681900024414, "learning_rate": 9.833525603429233e-06, "loss": 0.8453, "step": 8906 }, { "epoch": 0.5202686915887851, "grad_norm": 1.437782883644104, "learning_rate": 9.83163402669107e-06, "loss": 0.8441, "step": 8907 }, { "epoch": 0.5203271028037383, "grad_norm": 1.664136528968811, "learning_rate": 9.829742455978828e-06, "loss": 0.7372, "step": 8908 }, { "epoch": 0.5203855140186916, "grad_norm": 1.0944209098815918, "learning_rate": 9.82785089136022e-06, "loss": 0.7423, "step": 8909 }, { "epoch": 0.5204439252336449, "grad_norm": 0.9501782655715942, "learning_rate": 9.82595933290294e-06, "loss": 0.8326, "step": 8910 }, { "epoch": 0.5205023364485981, "grad_norm": 3.037672758102417, "learning_rate": 9.824067780674691e-06, "loss": 0.8031, "step": 8911 }, { "epoch": 0.5205607476635514, "grad_norm": 0.8803115487098694, "learning_rate": 9.822176234743174e-06, "loss": 0.741, "step": 8912 }, { "epoch": 0.5206191588785046, "grad_norm": 2.126065731048584, "learning_rate": 9.820284695176082e-06, "loss": 0.8913, "step": 8913 }, { "epoch": 0.5206775700934579, "grad_norm": 2.456850290298462, "learning_rate": 9.818393162041123e-06, "loss": 0.8221, "step": 8914 }, { "epoch": 0.5207359813084113, "grad_norm": 1.0122623443603516, "learning_rate": 9.816501635405991e-06, "loss": 0.7192, "step": 8915 }, { "epoch": 0.5207943925233645, "grad_norm": 1.2813594341278076, "learning_rate": 9.814610115338384e-06, "loss": 0.788, "step": 8916 }, { "epoch": 0.5208528037383178, "grad_norm": 2.884104013442993, "learning_rate": 9.812718601906004e-06, "loss": 0.8944, "step": 8917 }, { "epoch": 0.520911214953271, "grad_norm": 1.248413324356079, "learning_rate": 9.810827095176547e-06, "loss": 0.8435, "step": 8918 }, { "epoch": 0.5209696261682243, "grad_norm": 1.7789113521575928, "learning_rate": 9.808935595217715e-06, "loss": 0.9716, "step": 8919 }, { "epoch": 0.5210280373831776, "grad_norm": 2.2315874099731445, "learning_rate": 9.807044102097206e-06, "loss": 0.8933, "step": 8920 }, { "epoch": 0.5210864485981308, "grad_norm": 0.9131799936294556, "learning_rate": 9.805152615882709e-06, "loss": 0.7611, "step": 8921 }, { "epoch": 0.5211448598130841, "grad_norm": 1.2788788080215454, "learning_rate": 9.803261136641934e-06, "loss": 0.8328, "step": 8922 }, { "epoch": 0.5212032710280374, "grad_norm": 1.486191749572754, "learning_rate": 9.801369664442565e-06, "loss": 0.7067, "step": 8923 }, { "epoch": 0.5212616822429906, "grad_norm": 1.3197017908096313, "learning_rate": 9.799478199352314e-06, "loss": 0.7327, "step": 8924 }, { "epoch": 0.521320093457944, "grad_norm": 1.3361564874649048, "learning_rate": 9.797586741438868e-06, "loss": 0.8493, "step": 8925 }, { "epoch": 0.5213785046728971, "grad_norm": 1.4107098579406738, "learning_rate": 9.795695290769924e-06, "loss": 0.8147, "step": 8926 }, { "epoch": 0.5214369158878505, "grad_norm": 1.6472485065460205, "learning_rate": 9.79380384741318e-06, "loss": 0.9894, "step": 8927 }, { "epoch": 0.5214953271028038, "grad_norm": 1.0775169134140015, "learning_rate": 9.79191241143633e-06, "loss": 0.7129, "step": 8928 }, { "epoch": 0.521553738317757, "grad_norm": 1.2799170017242432, "learning_rate": 9.790020982907077e-06, "loss": 0.9269, "step": 8929 }, { "epoch": 0.5216121495327103, "grad_norm": 1.0944501161575317, "learning_rate": 9.788129561893108e-06, "loss": 0.6572, "step": 8930 }, { "epoch": 0.5216705607476636, "grad_norm": 0.8175486326217651, "learning_rate": 9.78623814846212e-06, "loss": 0.5207, "step": 8931 }, { "epoch": 0.5217289719626168, "grad_norm": 1.2947837114334106, "learning_rate": 9.784346742681813e-06, "loss": 0.7661, "step": 8932 }, { "epoch": 0.5217873831775701, "grad_norm": 1.6084469556808472, "learning_rate": 9.782455344619871e-06, "loss": 0.7324, "step": 8933 }, { "epoch": 0.5218457943925233, "grad_norm": 1.0310970544815063, "learning_rate": 9.780563954344002e-06, "loss": 0.7986, "step": 8934 }, { "epoch": 0.5219042056074766, "grad_norm": 1.1516433954238892, "learning_rate": 9.778672571921893e-06, "loss": 0.7531, "step": 8935 }, { "epoch": 0.52196261682243, "grad_norm": 1.193750023841858, "learning_rate": 9.776781197421234e-06, "loss": 0.8121, "step": 8936 }, { "epoch": 0.5220210280373832, "grad_norm": 1.0241612195968628, "learning_rate": 9.774889830909728e-06, "loss": 0.7662, "step": 8937 }, { "epoch": 0.5220794392523365, "grad_norm": 1.6903036832809448, "learning_rate": 9.772998472455058e-06, "loss": 0.7543, "step": 8938 }, { "epoch": 0.5221378504672897, "grad_norm": 2.012855052947998, "learning_rate": 9.771107122124924e-06, "loss": 0.7562, "step": 8939 }, { "epoch": 0.522196261682243, "grad_norm": 1.3098204135894775, "learning_rate": 9.769215779987019e-06, "loss": 0.6402, "step": 8940 }, { "epoch": 0.5222546728971963, "grad_norm": 1.1239686012268066, "learning_rate": 9.767324446109027e-06, "loss": 0.7074, "step": 8941 }, { "epoch": 0.5223130841121495, "grad_norm": 1.2727465629577637, "learning_rate": 9.765433120558652e-06, "loss": 0.8825, "step": 8942 }, { "epoch": 0.5223714953271028, "grad_norm": 3.433446168899536, "learning_rate": 9.763541803403574e-06, "loss": 0.829, "step": 8943 }, { "epoch": 0.5224299065420561, "grad_norm": 1.1789350509643555, "learning_rate": 9.761650494711494e-06, "loss": 0.7531, "step": 8944 }, { "epoch": 0.5224883177570093, "grad_norm": 1.3534742593765259, "learning_rate": 9.759759194550102e-06, "loss": 0.8882, "step": 8945 }, { "epoch": 0.5225467289719626, "grad_norm": 1.4847979545593262, "learning_rate": 9.757867902987083e-06, "loss": 0.7403, "step": 8946 }, { "epoch": 0.5226051401869158, "grad_norm": 1.0125521421432495, "learning_rate": 9.75597662009013e-06, "loss": 0.6901, "step": 8947 }, { "epoch": 0.5226635514018692, "grad_norm": 1.1898305416107178, "learning_rate": 9.754085345926935e-06, "loss": 0.7617, "step": 8948 }, { "epoch": 0.5227219626168225, "grad_norm": 1.4595729112625122, "learning_rate": 9.75219408056519e-06, "loss": 0.8272, "step": 8949 }, { "epoch": 0.5227803738317757, "grad_norm": 1.4104794263839722, "learning_rate": 9.75030282407258e-06, "loss": 0.8286, "step": 8950 }, { "epoch": 0.522838785046729, "grad_norm": 1.1393764019012451, "learning_rate": 9.748411576516794e-06, "loss": 0.7191, "step": 8951 }, { "epoch": 0.5228971962616823, "grad_norm": 1.1646121740341187, "learning_rate": 9.746520337965526e-06, "loss": 0.7931, "step": 8952 }, { "epoch": 0.5229556074766355, "grad_norm": 1.2455464601516724, "learning_rate": 9.744629108486458e-06, "loss": 0.951, "step": 8953 }, { "epoch": 0.5230140186915888, "grad_norm": 0.8597033619880676, "learning_rate": 9.742737888147288e-06, "loss": 0.7372, "step": 8954 }, { "epoch": 0.523072429906542, "grad_norm": 1.028119683265686, "learning_rate": 9.740846677015695e-06, "loss": 0.6952, "step": 8955 }, { "epoch": 0.5231308411214953, "grad_norm": 1.1761747598648071, "learning_rate": 9.738955475159369e-06, "loss": 0.732, "step": 8956 }, { "epoch": 0.5231892523364486, "grad_norm": 5.0911993980407715, "learning_rate": 9.737064282646e-06, "loss": 0.7931, "step": 8957 }, { "epoch": 0.5232476635514018, "grad_norm": 1.0024365186691284, "learning_rate": 9.735173099543269e-06, "loss": 0.4427, "step": 8958 }, { "epoch": 0.5233060747663552, "grad_norm": 1.0437718629837036, "learning_rate": 9.733281925918872e-06, "loss": 0.775, "step": 8959 }, { "epoch": 0.5233644859813084, "grad_norm": 3.149498224258423, "learning_rate": 9.731390761840488e-06, "loss": 0.6891, "step": 8960 }, { "epoch": 0.5234228971962617, "grad_norm": 0.9674168229103088, "learning_rate": 9.729499607375805e-06, "loss": 0.6657, "step": 8961 }, { "epoch": 0.523481308411215, "grad_norm": 1.043115496635437, "learning_rate": 9.72760846259251e-06, "loss": 0.7401, "step": 8962 }, { "epoch": 0.5235397196261682, "grad_norm": 1.3255726099014282, "learning_rate": 9.72571732755829e-06, "loss": 0.7968, "step": 8963 }, { "epoch": 0.5235981308411215, "grad_norm": 1.087714433670044, "learning_rate": 9.72382620234082e-06, "loss": 0.6882, "step": 8964 }, { "epoch": 0.5236565420560748, "grad_norm": 1.0445549488067627, "learning_rate": 9.721935087007799e-06, "loss": 0.7744, "step": 8965 }, { "epoch": 0.523714953271028, "grad_norm": 1.5827062129974365, "learning_rate": 9.720043981626897e-06, "loss": 0.8076, "step": 8966 }, { "epoch": 0.5237733644859813, "grad_norm": 0.9359023571014404, "learning_rate": 9.71815288626581e-06, "loss": 0.708, "step": 8967 }, { "epoch": 0.5238317757009345, "grad_norm": 2.127406597137451, "learning_rate": 9.716261800992218e-06, "loss": 0.7886, "step": 8968 }, { "epoch": 0.5238901869158878, "grad_norm": 1.122846007347107, "learning_rate": 9.714370725873798e-06, "loss": 0.9837, "step": 8969 }, { "epoch": 0.5239485981308412, "grad_norm": 2.1081371307373047, "learning_rate": 9.712479660978242e-06, "loss": 0.9248, "step": 8970 }, { "epoch": 0.5240070093457944, "grad_norm": 1.0299865007400513, "learning_rate": 9.710588606373223e-06, "loss": 0.7256, "step": 8971 }, { "epoch": 0.5240654205607477, "grad_norm": 0.9673563838005066, "learning_rate": 9.70869756212643e-06, "loss": 0.5754, "step": 8972 }, { "epoch": 0.524123831775701, "grad_norm": 1.6067966222763062, "learning_rate": 9.706806528305545e-06, "loss": 0.6951, "step": 8973 }, { "epoch": 0.5241822429906542, "grad_norm": 1.1329838037490845, "learning_rate": 9.704915504978245e-06, "loss": 0.788, "step": 8974 }, { "epoch": 0.5242406542056075, "grad_norm": 1.4023293256759644, "learning_rate": 9.703024492212214e-06, "loss": 0.7607, "step": 8975 }, { "epoch": 0.5242990654205607, "grad_norm": 1.2480511665344238, "learning_rate": 9.701133490075128e-06, "loss": 0.6935, "step": 8976 }, { "epoch": 0.524357476635514, "grad_norm": 1.5114773511886597, "learning_rate": 9.699242498634676e-06, "loss": 0.8423, "step": 8977 }, { "epoch": 0.5244158878504673, "grad_norm": 1.2694240808486938, "learning_rate": 9.697351517958534e-06, "loss": 0.651, "step": 8978 }, { "epoch": 0.5244742990654205, "grad_norm": 1.024849772453308, "learning_rate": 9.695460548114374e-06, "loss": 0.6156, "step": 8979 }, { "epoch": 0.5245327102803738, "grad_norm": 1.046384334564209, "learning_rate": 9.693569589169884e-06, "loss": 0.7742, "step": 8980 }, { "epoch": 0.524591121495327, "grad_norm": 1.5552481412887573, "learning_rate": 9.691678641192739e-06, "loss": 0.9024, "step": 8981 }, { "epoch": 0.5246495327102804, "grad_norm": 1.6841537952423096, "learning_rate": 9.689787704250622e-06, "loss": 0.6951, "step": 8982 }, { "epoch": 0.5247079439252337, "grad_norm": 1.2241591215133667, "learning_rate": 9.687896778411205e-06, "loss": 0.7378, "step": 8983 }, { "epoch": 0.5247663551401869, "grad_norm": 1.202019214630127, "learning_rate": 9.686005863742165e-06, "loss": 0.7186, "step": 8984 }, { "epoch": 0.5248247663551402, "grad_norm": 1.4428433179855347, "learning_rate": 9.684114960311182e-06, "loss": 0.7212, "step": 8985 }, { "epoch": 0.5248831775700935, "grad_norm": 1.1202154159545898, "learning_rate": 9.682224068185933e-06, "loss": 0.9584, "step": 8986 }, { "epoch": 0.5249415887850467, "grad_norm": 1.7434850931167603, "learning_rate": 9.680333187434096e-06, "loss": 0.705, "step": 8987 }, { "epoch": 0.525, "grad_norm": 1.912421464920044, "learning_rate": 9.678442318123344e-06, "loss": 0.9036, "step": 8988 }, { "epoch": 0.5250584112149532, "grad_norm": 1.0546901226043701, "learning_rate": 9.67655146032135e-06, "loss": 0.8069, "step": 8989 }, { "epoch": 0.5251168224299065, "grad_norm": 1.021221399307251, "learning_rate": 9.674660614095795e-06, "loss": 0.5732, "step": 8990 }, { "epoch": 0.5251752336448599, "grad_norm": 1.754904866218567, "learning_rate": 9.672769779514345e-06, "loss": 0.7531, "step": 8991 }, { "epoch": 0.525233644859813, "grad_norm": 1.038620114326477, "learning_rate": 9.670878956644686e-06, "loss": 0.8787, "step": 8992 }, { "epoch": 0.5252920560747664, "grad_norm": 2.151146411895752, "learning_rate": 9.668988145554484e-06, "loss": 0.6753, "step": 8993 }, { "epoch": 0.5253504672897197, "grad_norm": 1.7857598066329956, "learning_rate": 9.667097346311412e-06, "loss": 0.7621, "step": 8994 }, { "epoch": 0.5254088785046729, "grad_norm": 1.6162446737289429, "learning_rate": 9.665206558983147e-06, "loss": 0.776, "step": 8995 }, { "epoch": 0.5254672897196262, "grad_norm": 1.9926971197128296, "learning_rate": 9.663315783637358e-06, "loss": 0.9228, "step": 8996 }, { "epoch": 0.5255257009345794, "grad_norm": 1.1767661571502686, "learning_rate": 9.661425020341719e-06, "loss": 0.7757, "step": 8997 }, { "epoch": 0.5255841121495327, "grad_norm": 2.2611238956451416, "learning_rate": 9.659534269163904e-06, "loss": 0.7204, "step": 8998 }, { "epoch": 0.525642523364486, "grad_norm": 1.5472520589828491, "learning_rate": 9.657643530171574e-06, "loss": 0.9337, "step": 8999 }, { "epoch": 0.5257009345794392, "grad_norm": 1.7988231182098389, "learning_rate": 9.655752803432415e-06, "loss": 0.9153, "step": 9000 }, { "epoch": 0.5257593457943925, "grad_norm": 1.2711127996444702, "learning_rate": 9.653862089014083e-06, "loss": 0.7366, "step": 9001 }, { "epoch": 0.5258177570093457, "grad_norm": 2.68520450592041, "learning_rate": 9.651971386984258e-06, "loss": 0.7957, "step": 9002 }, { "epoch": 0.5258761682242991, "grad_norm": 1.0812126398086548, "learning_rate": 9.650080697410608e-06, "loss": 0.773, "step": 9003 }, { "epoch": 0.5259345794392524, "grad_norm": 2.1383860111236572, "learning_rate": 9.648190020360795e-06, "loss": 0.8308, "step": 9004 }, { "epoch": 0.5259929906542056, "grad_norm": 2.775798797607422, "learning_rate": 9.646299355902496e-06, "loss": 0.9465, "step": 9005 }, { "epoch": 0.5260514018691589, "grad_norm": 1.2580416202545166, "learning_rate": 9.644408704103372e-06, "loss": 0.6843, "step": 9006 }, { "epoch": 0.5261098130841122, "grad_norm": 1.9682339429855347, "learning_rate": 9.642518065031099e-06, "loss": 0.7878, "step": 9007 }, { "epoch": 0.5261682242990654, "grad_norm": 2.5633037090301514, "learning_rate": 9.640627438753337e-06, "loss": 1.0011, "step": 9008 }, { "epoch": 0.5262266355140187, "grad_norm": 1.1596696376800537, "learning_rate": 9.638736825337755e-06, "loss": 0.7004, "step": 9009 }, { "epoch": 0.5262850467289719, "grad_norm": 2.2985081672668457, "learning_rate": 9.636846224852021e-06, "loss": 0.6438, "step": 9010 }, { "epoch": 0.5263434579439252, "grad_norm": 3.072577476501465, "learning_rate": 9.634955637363796e-06, "loss": 0.9179, "step": 9011 }, { "epoch": 0.5264018691588785, "grad_norm": 1.384995937347412, "learning_rate": 9.633065062940754e-06, "loss": 0.9, "step": 9012 }, { "epoch": 0.5264602803738317, "grad_norm": 2.3431315422058105, "learning_rate": 9.631174501650551e-06, "loss": 0.9078, "step": 9013 }, { "epoch": 0.5265186915887851, "grad_norm": 2.5148632526397705, "learning_rate": 9.629283953560854e-06, "loss": 0.9349, "step": 9014 }, { "epoch": 0.5265771028037384, "grad_norm": 1.0315120220184326, "learning_rate": 9.627393418739333e-06, "loss": 0.9396, "step": 9015 }, { "epoch": 0.5266355140186916, "grad_norm": 1.6856577396392822, "learning_rate": 9.62550289725364e-06, "loss": 0.803, "step": 9016 }, { "epoch": 0.5266939252336449, "grad_norm": 1.8798859119415283, "learning_rate": 9.62361238917145e-06, "loss": 0.8086, "step": 9017 }, { "epoch": 0.5267523364485981, "grad_norm": 1.6933413743972778, "learning_rate": 9.621721894560419e-06, "loss": 0.8239, "step": 9018 }, { "epoch": 0.5268107476635514, "grad_norm": 1.1708663702011108, "learning_rate": 9.619831413488207e-06, "loss": 0.764, "step": 9019 }, { "epoch": 0.5268691588785047, "grad_norm": 1.974562644958496, "learning_rate": 9.617940946022482e-06, "loss": 0.8376, "step": 9020 }, { "epoch": 0.5269275700934579, "grad_norm": 0.9804455637931824, "learning_rate": 9.616050492230901e-06, "loss": 0.5277, "step": 9021 }, { "epoch": 0.5269859813084112, "grad_norm": 1.2987111806869507, "learning_rate": 9.614160052181123e-06, "loss": 0.9129, "step": 9022 }, { "epoch": 0.5270443925233644, "grad_norm": 1.5744812488555908, "learning_rate": 9.612269625940815e-06, "loss": 0.8222, "step": 9023 }, { "epoch": 0.5271028037383177, "grad_norm": 1.1146876811981201, "learning_rate": 9.610379213577626e-06, "loss": 0.7104, "step": 9024 }, { "epoch": 0.5271612149532711, "grad_norm": 1.6742373704910278, "learning_rate": 9.608488815159226e-06, "loss": 0.8888, "step": 9025 }, { "epoch": 0.5272196261682243, "grad_norm": 1.4935013055801392, "learning_rate": 9.606598430753269e-06, "loss": 0.7246, "step": 9026 }, { "epoch": 0.5272780373831776, "grad_norm": 1.9790843725204468, "learning_rate": 9.604708060427408e-06, "loss": 0.7616, "step": 9027 }, { "epoch": 0.5273364485981309, "grad_norm": 1.954580307006836, "learning_rate": 9.602817704249312e-06, "loss": 0.7883, "step": 9028 }, { "epoch": 0.5273948598130841, "grad_norm": 1.1816099882125854, "learning_rate": 9.600927362286627e-06, "loss": 0.8812, "step": 9029 }, { "epoch": 0.5274532710280374, "grad_norm": 1.4868007898330688, "learning_rate": 9.599037034607015e-06, "loss": 0.8092, "step": 9030 }, { "epoch": 0.5275116822429906, "grad_norm": 1.6772464513778687, "learning_rate": 9.597146721278134e-06, "loss": 0.7957, "step": 9031 }, { "epoch": 0.5275700934579439, "grad_norm": 1.4258779287338257, "learning_rate": 9.59525642236763e-06, "loss": 0.8599, "step": 9032 }, { "epoch": 0.5276285046728972, "grad_norm": 1.6094081401824951, "learning_rate": 9.593366137943172e-06, "loss": 0.9239, "step": 9033 }, { "epoch": 0.5276869158878504, "grad_norm": 1.3716504573822021, "learning_rate": 9.591475868072402e-06, "loss": 0.6991, "step": 9034 }, { "epoch": 0.5277453271028038, "grad_norm": 2.316542387008667, "learning_rate": 9.589585612822982e-06, "loss": 0.7227, "step": 9035 }, { "epoch": 0.527803738317757, "grad_norm": 1.8538804054260254, "learning_rate": 9.587695372262564e-06, "loss": 0.9918, "step": 9036 }, { "epoch": 0.5278621495327103, "grad_norm": 1.4642506837844849, "learning_rate": 9.585805146458796e-06, "loss": 0.9798, "step": 9037 }, { "epoch": 0.5279205607476636, "grad_norm": 1.1400587558746338, "learning_rate": 9.583914935479336e-06, "loss": 0.782, "step": 9038 }, { "epoch": 0.5279789719626168, "grad_norm": 1.1087384223937988, "learning_rate": 9.582024739391832e-06, "loss": 0.7094, "step": 9039 }, { "epoch": 0.5280373831775701, "grad_norm": 1.3368618488311768, "learning_rate": 9.580134558263943e-06, "loss": 0.7606, "step": 9040 }, { "epoch": 0.5280957943925234, "grad_norm": 1.7445894479751587, "learning_rate": 9.578244392163311e-06, "loss": 0.8682, "step": 9041 }, { "epoch": 0.5281542056074766, "grad_norm": 1.2491108179092407, "learning_rate": 9.576354241157588e-06, "loss": 0.8416, "step": 9042 }, { "epoch": 0.5282126168224299, "grad_norm": 1.6343742609024048, "learning_rate": 9.574464105314426e-06, "loss": 0.758, "step": 9043 }, { "epoch": 0.5282710280373831, "grad_norm": 1.2234578132629395, "learning_rate": 9.572573984701471e-06, "loss": 0.8675, "step": 9044 }, { "epoch": 0.5283294392523364, "grad_norm": 1.3022730350494385, "learning_rate": 9.57068387938638e-06, "loss": 0.7648, "step": 9045 }, { "epoch": 0.5283878504672898, "grad_norm": 1.430323839187622, "learning_rate": 9.568793789436794e-06, "loss": 0.8381, "step": 9046 }, { "epoch": 0.528446261682243, "grad_norm": 1.2808459997177124, "learning_rate": 9.566903714920358e-06, "loss": 0.7933, "step": 9047 }, { "epoch": 0.5285046728971963, "grad_norm": 1.3038917779922485, "learning_rate": 9.565013655904728e-06, "loss": 0.7856, "step": 9048 }, { "epoch": 0.5285630841121496, "grad_norm": 1.0370322465896606, "learning_rate": 9.563123612457538e-06, "loss": 0.7524, "step": 9049 }, { "epoch": 0.5286214953271028, "grad_norm": 1.6916301250457764, "learning_rate": 9.561233584646448e-06, "loss": 0.8503, "step": 9050 }, { "epoch": 0.5286799065420561, "grad_norm": 1.6381562948226929, "learning_rate": 9.559343572539094e-06, "loss": 0.96, "step": 9051 }, { "epoch": 0.5287383177570093, "grad_norm": 1.189204216003418, "learning_rate": 9.55745357620312e-06, "loss": 0.788, "step": 9052 }, { "epoch": 0.5287967289719626, "grad_norm": 1.0431212186813354, "learning_rate": 9.55556359570618e-06, "loss": 0.7853, "step": 9053 }, { "epoch": 0.5288551401869159, "grad_norm": 1.699548363685608, "learning_rate": 9.553673631115907e-06, "loss": 0.8951, "step": 9054 }, { "epoch": 0.5289135514018691, "grad_norm": 1.1765129566192627, "learning_rate": 9.551783682499949e-06, "loss": 0.7676, "step": 9055 }, { "epoch": 0.5289719626168224, "grad_norm": 1.0112214088439941, "learning_rate": 9.549893749925948e-06, "loss": 0.7913, "step": 9056 }, { "epoch": 0.5290303738317756, "grad_norm": 1.3006415367126465, "learning_rate": 9.548003833461544e-06, "loss": 0.9504, "step": 9057 }, { "epoch": 0.529088785046729, "grad_norm": 1.8358575105667114, "learning_rate": 9.546113933174382e-06, "loss": 0.7791, "step": 9058 }, { "epoch": 0.5291471962616823, "grad_norm": 1.2239515781402588, "learning_rate": 9.544224049132099e-06, "loss": 0.7639, "step": 9059 }, { "epoch": 0.5292056074766355, "grad_norm": 1.8196135759353638, "learning_rate": 9.54233418140234e-06, "loss": 0.9658, "step": 9060 }, { "epoch": 0.5292640186915888, "grad_norm": 0.9349765181541443, "learning_rate": 9.54044433005274e-06, "loss": 0.7941, "step": 9061 }, { "epoch": 0.5293224299065421, "grad_norm": 1.5134061574935913, "learning_rate": 9.538554495150937e-06, "loss": 0.7106, "step": 9062 }, { "epoch": 0.5293808411214953, "grad_norm": 1.7175227403640747, "learning_rate": 9.536664676764576e-06, "loss": 0.8027, "step": 9063 }, { "epoch": 0.5294392523364486, "grad_norm": 1.0481555461883545, "learning_rate": 9.534774874961287e-06, "loss": 0.7394, "step": 9064 }, { "epoch": 0.5294976635514018, "grad_norm": 2.0287363529205322, "learning_rate": 9.532885089808713e-06, "loss": 0.867, "step": 9065 }, { "epoch": 0.5295560747663551, "grad_norm": 0.9988622665405273, "learning_rate": 9.530995321374492e-06, "loss": 0.9171, "step": 9066 }, { "epoch": 0.5296144859813084, "grad_norm": 1.9696828126907349, "learning_rate": 9.529105569726251e-06, "loss": 1.0046, "step": 9067 }, { "epoch": 0.5296728971962616, "grad_norm": 1.2593235969543457, "learning_rate": 9.527215834931635e-06, "loss": 0.8488, "step": 9068 }, { "epoch": 0.529731308411215, "grad_norm": 1.6201540231704712, "learning_rate": 9.525326117058272e-06, "loss": 0.718, "step": 9069 }, { "epoch": 0.5297897196261683, "grad_norm": 1.8629220724105835, "learning_rate": 9.523436416173805e-06, "loss": 0.8381, "step": 9070 }, { "epoch": 0.5298481308411215, "grad_norm": 1.1741570234298706, "learning_rate": 9.52154673234586e-06, "loss": 0.7526, "step": 9071 }, { "epoch": 0.5299065420560748, "grad_norm": 3.9852263927459717, "learning_rate": 9.519657065642067e-06, "loss": 0.897, "step": 9072 }, { "epoch": 0.529964953271028, "grad_norm": 1.7938085794448853, "learning_rate": 9.51776741613007e-06, "loss": 0.7158, "step": 9073 }, { "epoch": 0.5300233644859813, "grad_norm": 1.6872464418411255, "learning_rate": 9.515877783877492e-06, "loss": 0.7873, "step": 9074 }, { "epoch": 0.5300817757009346, "grad_norm": 0.9800614714622498, "learning_rate": 9.513988168951964e-06, "loss": 0.6604, "step": 9075 }, { "epoch": 0.5301401869158878, "grad_norm": 1.1477352380752563, "learning_rate": 9.512098571421121e-06, "loss": 0.7518, "step": 9076 }, { "epoch": 0.5301985981308411, "grad_norm": 0.9882923364639282, "learning_rate": 9.510208991352589e-06, "loss": 0.5656, "step": 9077 }, { "epoch": 0.5302570093457943, "grad_norm": 1.136269450187683, "learning_rate": 9.508319428814003e-06, "loss": 0.9323, "step": 9078 }, { "epoch": 0.5303154205607477, "grad_norm": 1.05036461353302, "learning_rate": 9.506429883872985e-06, "loss": 0.8073, "step": 9079 }, { "epoch": 0.530373831775701, "grad_norm": 1.0639218091964722, "learning_rate": 9.504540356597166e-06, "loss": 0.769, "step": 9080 }, { "epoch": 0.5304322429906542, "grad_norm": 1.0423057079315186, "learning_rate": 9.502650847054177e-06, "loss": 0.85, "step": 9081 }, { "epoch": 0.5304906542056075, "grad_norm": 0.8057941198348999, "learning_rate": 9.500761355311635e-06, "loss": 0.6175, "step": 9082 }, { "epoch": 0.5305490654205608, "grad_norm": 1.0871763229370117, "learning_rate": 9.498871881437178e-06, "loss": 0.7557, "step": 9083 }, { "epoch": 0.530607476635514, "grad_norm": 1.7246384620666504, "learning_rate": 9.496982425498424e-06, "loss": 0.7924, "step": 9084 }, { "epoch": 0.5306658878504673, "grad_norm": 1.0874148607254028, "learning_rate": 9.495092987562997e-06, "loss": 0.8064, "step": 9085 }, { "epoch": 0.5307242990654205, "grad_norm": 1.2919360399246216, "learning_rate": 9.49320356769853e-06, "loss": 0.6391, "step": 9086 }, { "epoch": 0.5307827102803738, "grad_norm": 1.3229827880859375, "learning_rate": 9.491314165972635e-06, "loss": 0.89, "step": 9087 }, { "epoch": 0.5308411214953271, "grad_norm": 1.3112964630126953, "learning_rate": 9.489424782452941e-06, "loss": 0.9311, "step": 9088 }, { "epoch": 0.5308995327102803, "grad_norm": 1.2132456302642822, "learning_rate": 9.487535417207074e-06, "loss": 0.8043, "step": 9089 }, { "epoch": 0.5309579439252337, "grad_norm": 1.239626407623291, "learning_rate": 9.485646070302646e-06, "loss": 0.8245, "step": 9090 }, { "epoch": 0.531016355140187, "grad_norm": 1.192966341972351, "learning_rate": 9.483756741807288e-06, "loss": 0.7606, "step": 9091 }, { "epoch": 0.5310747663551402, "grad_norm": 1.2310079336166382, "learning_rate": 9.481867431788612e-06, "loss": 0.8571, "step": 9092 }, { "epoch": 0.5311331775700935, "grad_norm": 1.383040189743042, "learning_rate": 9.479978140314242e-06, "loss": 0.7434, "step": 9093 }, { "epoch": 0.5311915887850467, "grad_norm": 1.398544192314148, "learning_rate": 9.4780888674518e-06, "loss": 0.7894, "step": 9094 }, { "epoch": 0.53125, "grad_norm": 1.214841604232788, "learning_rate": 9.476199613268896e-06, "loss": 0.7101, "step": 9095 }, { "epoch": 0.5313084112149533, "grad_norm": 1.0581343173980713, "learning_rate": 9.474310377833153e-06, "loss": 0.7524, "step": 9096 }, { "epoch": 0.5313668224299065, "grad_norm": 1.5421814918518066, "learning_rate": 9.472421161212188e-06, "loss": 0.9596, "step": 9097 }, { "epoch": 0.5314252336448598, "grad_norm": 1.0763682126998901, "learning_rate": 9.470531963473616e-06, "loss": 0.751, "step": 9098 }, { "epoch": 0.531483644859813, "grad_norm": 1.246592402458191, "learning_rate": 9.468642784685055e-06, "loss": 0.7204, "step": 9099 }, { "epoch": 0.5315420560747663, "grad_norm": 1.0021579265594482, "learning_rate": 9.466753624914117e-06, "loss": 0.6492, "step": 9100 }, { "epoch": 0.5316004672897197, "grad_norm": 1.5764657258987427, "learning_rate": 9.464864484228417e-06, "loss": 1.0009, "step": 9101 }, { "epoch": 0.5316588785046729, "grad_norm": 1.076160192489624, "learning_rate": 9.462975362695568e-06, "loss": 0.6281, "step": 9102 }, { "epoch": 0.5317172897196262, "grad_norm": 2.3351142406463623, "learning_rate": 9.461086260383188e-06, "loss": 0.8356, "step": 9103 }, { "epoch": 0.5317757009345795, "grad_norm": 1.2609649896621704, "learning_rate": 9.459197177358881e-06, "loss": 0.7019, "step": 9104 }, { "epoch": 0.5318341121495327, "grad_norm": 1.6674071550369263, "learning_rate": 9.457308113690262e-06, "loss": 1.0855, "step": 9105 }, { "epoch": 0.531892523364486, "grad_norm": 1.6330307722091675, "learning_rate": 9.455419069444948e-06, "loss": 0.7773, "step": 9106 }, { "epoch": 0.5319509345794392, "grad_norm": 1.2441484928131104, "learning_rate": 9.453530044690535e-06, "loss": 0.8755, "step": 9107 }, { "epoch": 0.5320093457943925, "grad_norm": 1.5132591724395752, "learning_rate": 9.45164103949465e-06, "loss": 0.8492, "step": 9108 }, { "epoch": 0.5320677570093458, "grad_norm": 1.490504503250122, "learning_rate": 9.449752053924888e-06, "loss": 0.7472, "step": 9109 }, { "epoch": 0.532126168224299, "grad_norm": 1.4474278688430786, "learning_rate": 9.44786308804886e-06, "loss": 0.8421, "step": 9110 }, { "epoch": 0.5321845794392523, "grad_norm": 1.0504722595214844, "learning_rate": 9.44597414193418e-06, "loss": 0.9727, "step": 9111 }, { "epoch": 0.5322429906542057, "grad_norm": 1.5610361099243164, "learning_rate": 9.444085215648445e-06, "loss": 0.8955, "step": 9112 }, { "epoch": 0.5323014018691589, "grad_norm": 1.6117240190505981, "learning_rate": 9.442196309259268e-06, "loss": 0.721, "step": 9113 }, { "epoch": 0.5323598130841122, "grad_norm": 1.5189523696899414, "learning_rate": 9.440307422834256e-06, "loss": 0.9565, "step": 9114 }, { "epoch": 0.5324182242990654, "grad_norm": 1.593272089958191, "learning_rate": 9.438418556441e-06, "loss": 0.6725, "step": 9115 }, { "epoch": 0.5324766355140187, "grad_norm": 1.7999300956726074, "learning_rate": 9.436529710147122e-06, "loss": 0.9421, "step": 9116 }, { "epoch": 0.532535046728972, "grad_norm": 1.1515049934387207, "learning_rate": 9.43464088402021e-06, "loss": 0.7602, "step": 9117 }, { "epoch": 0.5325934579439252, "grad_norm": 1.2608646154403687, "learning_rate": 9.432752078127875e-06, "loss": 0.7429, "step": 9118 }, { "epoch": 0.5326518691588785, "grad_norm": 1.4787139892578125, "learning_rate": 9.430863292537718e-06, "loss": 0.8285, "step": 9119 }, { "epoch": 0.5327102803738317, "grad_norm": 1.1396496295928955, "learning_rate": 9.428974527317334e-06, "loss": 0.7578, "step": 9120 }, { "epoch": 0.532768691588785, "grad_norm": 0.8948111534118652, "learning_rate": 9.42708578253433e-06, "loss": 0.7849, "step": 9121 }, { "epoch": 0.5328271028037384, "grad_norm": 1.448848843574524, "learning_rate": 9.4251970582563e-06, "loss": 0.7619, "step": 9122 }, { "epoch": 0.5328855140186916, "grad_norm": 1.2858083248138428, "learning_rate": 9.423308354550846e-06, "loss": 0.846, "step": 9123 }, { "epoch": 0.5329439252336449, "grad_norm": 1.0898125171661377, "learning_rate": 9.421419671485568e-06, "loss": 0.7331, "step": 9124 }, { "epoch": 0.5330023364485982, "grad_norm": 1.4005672931671143, "learning_rate": 9.419531009128057e-06, "loss": 0.7549, "step": 9125 }, { "epoch": 0.5330607476635514, "grad_norm": 1.334145188331604, "learning_rate": 9.417642367545915e-06, "loss": 0.7799, "step": 9126 }, { "epoch": 0.5331191588785047, "grad_norm": 1.0962871313095093, "learning_rate": 9.415753746806732e-06, "loss": 0.7335, "step": 9127 }, { "epoch": 0.5331775700934579, "grad_norm": 1.3432574272155762, "learning_rate": 9.413865146978113e-06, "loss": 0.8645, "step": 9128 }, { "epoch": 0.5332359813084112, "grad_norm": 1.2068878412246704, "learning_rate": 9.411976568127642e-06, "loss": 0.792, "step": 9129 }, { "epoch": 0.5332943925233645, "grad_norm": 1.2171505689620972, "learning_rate": 9.410088010322915e-06, "loss": 0.7583, "step": 9130 }, { "epoch": 0.5333528037383177, "grad_norm": 1.3159570693969727, "learning_rate": 9.408199473631527e-06, "loss": 0.7248, "step": 9131 }, { "epoch": 0.533411214953271, "grad_norm": 1.3578014373779297, "learning_rate": 9.406310958121072e-06, "loss": 0.8116, "step": 9132 }, { "epoch": 0.5334696261682244, "grad_norm": 1.8402047157287598, "learning_rate": 9.404422463859134e-06, "loss": 0.8513, "step": 9133 }, { "epoch": 0.5335280373831776, "grad_norm": 2.072479248046875, "learning_rate": 9.40253399091331e-06, "loss": 0.7713, "step": 9134 }, { "epoch": 0.5335864485981309, "grad_norm": 1.6261605024337769, "learning_rate": 9.400645539351184e-06, "loss": 0.7703, "step": 9135 }, { "epoch": 0.5336448598130841, "grad_norm": 1.163686752319336, "learning_rate": 9.398757109240353e-06, "loss": 0.8802, "step": 9136 }, { "epoch": 0.5337032710280374, "grad_norm": 1.2041130065917969, "learning_rate": 9.396868700648399e-06, "loss": 0.8002, "step": 9137 }, { "epoch": 0.5337616822429907, "grad_norm": 1.2998356819152832, "learning_rate": 9.394980313642908e-06, "loss": 0.7393, "step": 9138 }, { "epoch": 0.5338200934579439, "grad_norm": 1.3116190433502197, "learning_rate": 9.393091948291472e-06, "loss": 0.849, "step": 9139 }, { "epoch": 0.5338785046728972, "grad_norm": 1.0685863494873047, "learning_rate": 9.39120360466167e-06, "loss": 0.8181, "step": 9140 }, { "epoch": 0.5339369158878504, "grad_norm": 1.2946139574050903, "learning_rate": 9.389315282821097e-06, "loss": 0.6681, "step": 9141 }, { "epoch": 0.5339953271028037, "grad_norm": 1.3352789878845215, "learning_rate": 9.38742698283733e-06, "loss": 0.9171, "step": 9142 }, { "epoch": 0.534053738317757, "grad_norm": 1.180828332901001, "learning_rate": 9.38553870477795e-06, "loss": 0.8964, "step": 9143 }, { "epoch": 0.5341121495327102, "grad_norm": 1.2517434358596802, "learning_rate": 9.38365044871055e-06, "loss": 0.7929, "step": 9144 }, { "epoch": 0.5341705607476636, "grad_norm": 1.585709810256958, "learning_rate": 9.381762214702703e-06, "loss": 0.951, "step": 9145 }, { "epoch": 0.5342289719626169, "grad_norm": 1.1936626434326172, "learning_rate": 9.379874002821992e-06, "loss": 0.5739, "step": 9146 }, { "epoch": 0.5342873831775701, "grad_norm": 1.642872929573059, "learning_rate": 9.377985813136001e-06, "loss": 0.7284, "step": 9147 }, { "epoch": 0.5343457943925234, "grad_norm": 1.1646928787231445, "learning_rate": 9.376097645712301e-06, "loss": 0.9286, "step": 9148 }, { "epoch": 0.5344042056074766, "grad_norm": 1.389730453491211, "learning_rate": 9.374209500618482e-06, "loss": 0.8096, "step": 9149 }, { "epoch": 0.5344626168224299, "grad_norm": 1.0454472303390503, "learning_rate": 9.372321377922114e-06, "loss": 0.7316, "step": 9150 }, { "epoch": 0.5345210280373832, "grad_norm": 1.2345349788665771, "learning_rate": 9.370433277690776e-06, "loss": 0.8435, "step": 9151 }, { "epoch": 0.5345794392523364, "grad_norm": 1.6054075956344604, "learning_rate": 9.368545199992048e-06, "loss": 0.7588, "step": 9152 }, { "epoch": 0.5346378504672897, "grad_norm": 1.2915058135986328, "learning_rate": 9.3666571448935e-06, "loss": 0.9243, "step": 9153 }, { "epoch": 0.534696261682243, "grad_norm": 1.1297882795333862, "learning_rate": 9.36476911246271e-06, "loss": 0.6453, "step": 9154 }, { "epoch": 0.5347546728971962, "grad_norm": 1.8059502840042114, "learning_rate": 9.362881102767248e-06, "loss": 0.9614, "step": 9155 }, { "epoch": 0.5348130841121496, "grad_norm": 1.1223783493041992, "learning_rate": 9.360993115874693e-06, "loss": 0.809, "step": 9156 }, { "epoch": 0.5348714953271028, "grad_norm": 1.3554216623306274, "learning_rate": 9.359105151852618e-06, "loss": 0.9386, "step": 9157 }, { "epoch": 0.5349299065420561, "grad_norm": 1.36380934715271, "learning_rate": 9.357217210768586e-06, "loss": 0.9435, "step": 9158 }, { "epoch": 0.5349883177570094, "grad_norm": 1.2582969665527344, "learning_rate": 9.355329292690174e-06, "loss": 0.7788, "step": 9159 }, { "epoch": 0.5350467289719626, "grad_norm": 1.2050803899765015, "learning_rate": 9.353441397684948e-06, "loss": 0.5951, "step": 9160 }, { "epoch": 0.5351051401869159, "grad_norm": 1.4432318210601807, "learning_rate": 9.351553525820486e-06, "loss": 0.6851, "step": 9161 }, { "epoch": 0.5351635514018691, "grad_norm": 1.2646995782852173, "learning_rate": 9.349665677164346e-06, "loss": 1.0184, "step": 9162 }, { "epoch": 0.5352219626168224, "grad_norm": 1.239564299583435, "learning_rate": 9.347777851784097e-06, "loss": 0.8181, "step": 9163 }, { "epoch": 0.5352803738317757, "grad_norm": 0.9728541970252991, "learning_rate": 9.34589004974731e-06, "loss": 0.7316, "step": 9164 }, { "epoch": 0.5353387850467289, "grad_norm": 1.2760769128799438, "learning_rate": 9.344002271121546e-06, "loss": 0.6565, "step": 9165 }, { "epoch": 0.5353971962616823, "grad_norm": 0.9222696423530579, "learning_rate": 9.342114515974377e-06, "loss": 0.8185, "step": 9166 }, { "epoch": 0.5354556074766356, "grad_norm": 1.2460591793060303, "learning_rate": 9.340226784373358e-06, "loss": 0.7062, "step": 9167 }, { "epoch": 0.5355140186915888, "grad_norm": 1.4752684831619263, "learning_rate": 9.338339076386055e-06, "loss": 0.7901, "step": 9168 }, { "epoch": 0.5355724299065421, "grad_norm": 1.3801467418670654, "learning_rate": 9.336451392080035e-06, "loss": 0.7894, "step": 9169 }, { "epoch": 0.5356308411214953, "grad_norm": 1.2133121490478516, "learning_rate": 9.334563731522855e-06, "loss": 0.8891, "step": 9170 }, { "epoch": 0.5356892523364486, "grad_norm": 1.1373449563980103, "learning_rate": 9.332676094782074e-06, "loss": 0.6964, "step": 9171 }, { "epoch": 0.5357476635514019, "grad_norm": 1.3455861806869507, "learning_rate": 9.33078848192526e-06, "loss": 0.7366, "step": 9172 }, { "epoch": 0.5358060747663551, "grad_norm": 1.2490248680114746, "learning_rate": 9.328900893019958e-06, "loss": 0.6808, "step": 9173 }, { "epoch": 0.5358644859813084, "grad_norm": 0.9530498385429382, "learning_rate": 9.327013328133743e-06, "loss": 0.6698, "step": 9174 }, { "epoch": 0.5359228971962616, "grad_norm": 0.9198258519172668, "learning_rate": 9.325125787334157e-06, "loss": 0.6474, "step": 9175 }, { "epoch": 0.5359813084112149, "grad_norm": 1.4554802179336548, "learning_rate": 9.323238270688765e-06, "loss": 0.654, "step": 9176 }, { "epoch": 0.5360397196261683, "grad_norm": 1.6528266668319702, "learning_rate": 9.321350778265124e-06, "loss": 0.989, "step": 9177 }, { "epoch": 0.5360981308411215, "grad_norm": 1.0823382139205933, "learning_rate": 9.319463310130778e-06, "loss": 0.7688, "step": 9178 }, { "epoch": 0.5361565420560748, "grad_norm": 1.8574535846710205, "learning_rate": 9.317575866353293e-06, "loss": 0.9255, "step": 9179 }, { "epoch": 0.5362149532710281, "grad_norm": 3.4228620529174805, "learning_rate": 9.315688447000211e-06, "loss": 0.8387, "step": 9180 }, { "epoch": 0.5362733644859813, "grad_norm": 1.0998722314834595, "learning_rate": 9.313801052139093e-06, "loss": 0.6558, "step": 9181 }, { "epoch": 0.5363317757009346, "grad_norm": 2.0880515575408936, "learning_rate": 9.31191368183749e-06, "loss": 0.9702, "step": 9182 }, { "epoch": 0.5363901869158878, "grad_norm": 1.5736569166183472, "learning_rate": 9.310026336162943e-06, "loss": 0.728, "step": 9183 }, { "epoch": 0.5364485981308411, "grad_norm": 2.4043891429901123, "learning_rate": 9.308139015183008e-06, "loss": 0.9024, "step": 9184 }, { "epoch": 0.5365070093457944, "grad_norm": 1.2006666660308838, "learning_rate": 9.306251718965234e-06, "loss": 0.7504, "step": 9185 }, { "epoch": 0.5365654205607476, "grad_norm": 1.4202616214752197, "learning_rate": 9.30436444757717e-06, "loss": 0.8179, "step": 9186 }, { "epoch": 0.5366238317757009, "grad_norm": 1.6783013343811035, "learning_rate": 9.302477201086355e-06, "loss": 0.7186, "step": 9187 }, { "epoch": 0.5366822429906543, "grad_norm": 0.9848355650901794, "learning_rate": 9.300589979560339e-06, "loss": 0.6031, "step": 9188 }, { "epoch": 0.5367406542056075, "grad_norm": 2.08581805229187, "learning_rate": 9.298702783066671e-06, "loss": 0.9286, "step": 9189 }, { "epoch": 0.5367990654205608, "grad_norm": 1.0386866331100464, "learning_rate": 9.296815611672893e-06, "loss": 0.7625, "step": 9190 }, { "epoch": 0.536857476635514, "grad_norm": 1.1983075141906738, "learning_rate": 9.294928465446542e-06, "loss": 0.753, "step": 9191 }, { "epoch": 0.5369158878504673, "grad_norm": 1.0929118394851685, "learning_rate": 9.293041344455167e-06, "loss": 0.6731, "step": 9192 }, { "epoch": 0.5369742990654206, "grad_norm": 2.061577320098877, "learning_rate": 9.291154248766305e-06, "loss": 0.7268, "step": 9193 }, { "epoch": 0.5370327102803738, "grad_norm": 1.2957173585891724, "learning_rate": 9.289267178447503e-06, "loss": 0.8138, "step": 9194 }, { "epoch": 0.5370911214953271, "grad_norm": 1.1307835578918457, "learning_rate": 9.287380133566293e-06, "loss": 0.7015, "step": 9195 }, { "epoch": 0.5371495327102803, "grad_norm": 1.4503058195114136, "learning_rate": 9.285493114190214e-06, "loss": 0.8415, "step": 9196 }, { "epoch": 0.5372079439252336, "grad_norm": 1.3787903785705566, "learning_rate": 9.28360612038681e-06, "loss": 0.8168, "step": 9197 }, { "epoch": 0.537266355140187, "grad_norm": 0.987311840057373, "learning_rate": 9.281719152223611e-06, "loss": 0.6975, "step": 9198 }, { "epoch": 0.5373247663551401, "grad_norm": 1.3703851699829102, "learning_rate": 9.279832209768161e-06, "loss": 0.7463, "step": 9199 }, { "epoch": 0.5373831775700935, "grad_norm": 1.520495891571045, "learning_rate": 9.277945293087987e-06, "loss": 0.7701, "step": 9200 }, { "epoch": 0.5374415887850468, "grad_norm": 1.5243644714355469, "learning_rate": 9.276058402250623e-06, "loss": 0.8766, "step": 9201 }, { "epoch": 0.5375, "grad_norm": 1.4848405122756958, "learning_rate": 9.274171537323611e-06, "loss": 1.0231, "step": 9202 }, { "epoch": 0.5375584112149533, "grad_norm": 1.439224362373352, "learning_rate": 9.272284698374471e-06, "loss": 0.8839, "step": 9203 }, { "epoch": 0.5376168224299065, "grad_norm": 2.551145553588867, "learning_rate": 9.270397885470744e-06, "loss": 0.9274, "step": 9204 }, { "epoch": 0.5376752336448598, "grad_norm": 1.102676272392273, "learning_rate": 9.268511098679955e-06, "loss": 0.8495, "step": 9205 }, { "epoch": 0.5377336448598131, "grad_norm": 2.002502202987671, "learning_rate": 9.26662433806963e-06, "loss": 0.7297, "step": 9206 }, { "epoch": 0.5377920560747663, "grad_norm": 1.4006001949310303, "learning_rate": 9.26473760370731e-06, "loss": 0.7471, "step": 9207 }, { "epoch": 0.5378504672897196, "grad_norm": 1.70341157913208, "learning_rate": 9.26285089566051e-06, "loss": 0.8092, "step": 9208 }, { "epoch": 0.537908878504673, "grad_norm": 1.890731692314148, "learning_rate": 9.260964213996763e-06, "loss": 0.8375, "step": 9209 }, { "epoch": 0.5379672897196262, "grad_norm": 1.0085769891738892, "learning_rate": 9.259077558783593e-06, "loss": 0.6401, "step": 9210 }, { "epoch": 0.5380257009345795, "grad_norm": 2.063716411590576, "learning_rate": 9.257190930088522e-06, "loss": 0.8841, "step": 9211 }, { "epoch": 0.5380841121495327, "grad_norm": 1.4762903451919556, "learning_rate": 9.255304327979077e-06, "loss": 0.8559, "step": 9212 }, { "epoch": 0.538142523364486, "grad_norm": 2.1050965785980225, "learning_rate": 9.253417752522778e-06, "loss": 0.9607, "step": 9213 }, { "epoch": 0.5382009345794393, "grad_norm": 1.0816795825958252, "learning_rate": 9.251531203787151e-06, "loss": 0.7242, "step": 9214 }, { "epoch": 0.5382593457943925, "grad_norm": 1.4750759601593018, "learning_rate": 9.249644681839717e-06, "loss": 0.6959, "step": 9215 }, { "epoch": 0.5383177570093458, "grad_norm": 1.6760666370391846, "learning_rate": 9.247758186747988e-06, "loss": 0.7767, "step": 9216 }, { "epoch": 0.538376168224299, "grad_norm": 1.0788819789886475, "learning_rate": 9.24587171857949e-06, "loss": 0.8082, "step": 9217 }, { "epoch": 0.5384345794392523, "grad_norm": 1.7764127254486084, "learning_rate": 9.243985277401739e-06, "loss": 0.7378, "step": 9218 }, { "epoch": 0.5384929906542056, "grad_norm": 1.6931488513946533, "learning_rate": 9.242098863282255e-06, "loss": 0.8361, "step": 9219 }, { "epoch": 0.5385514018691588, "grad_norm": 1.1378529071807861, "learning_rate": 9.240212476288549e-06, "loss": 0.8325, "step": 9220 }, { "epoch": 0.5386098130841122, "grad_norm": 1.1511626243591309, "learning_rate": 9.238326116488134e-06, "loss": 0.8659, "step": 9221 }, { "epoch": 0.5386682242990655, "grad_norm": 1.506212592124939, "learning_rate": 9.236439783948532e-06, "loss": 0.7236, "step": 9222 }, { "epoch": 0.5387266355140187, "grad_norm": 3.4506397247314453, "learning_rate": 9.234553478737251e-06, "loss": 0.8383, "step": 9223 }, { "epoch": 0.538785046728972, "grad_norm": 1.1610020399093628, "learning_rate": 9.232667200921806e-06, "loss": 0.7494, "step": 9224 }, { "epoch": 0.5388434579439252, "grad_norm": 1.6683963537216187, "learning_rate": 9.230780950569706e-06, "loss": 0.8484, "step": 9225 }, { "epoch": 0.5389018691588785, "grad_norm": 1.2988899946212769, "learning_rate": 9.22889472774846e-06, "loss": 0.7677, "step": 9226 }, { "epoch": 0.5389602803738318, "grad_norm": 1.3570939302444458, "learning_rate": 9.227008532525582e-06, "loss": 0.7752, "step": 9227 }, { "epoch": 0.539018691588785, "grad_norm": 2.246950149536133, "learning_rate": 9.225122364968573e-06, "loss": 0.7839, "step": 9228 }, { "epoch": 0.5390771028037383, "grad_norm": 1.0646451711654663, "learning_rate": 9.223236225144944e-06, "loss": 0.7027, "step": 9229 }, { "epoch": 0.5391355140186916, "grad_norm": 1.749054193496704, "learning_rate": 9.221350113122203e-06, "loss": 0.8399, "step": 9230 }, { "epoch": 0.5391939252336448, "grad_norm": 1.5230402946472168, "learning_rate": 9.219464028967853e-06, "loss": 0.7557, "step": 9231 }, { "epoch": 0.5392523364485982, "grad_norm": 1.22171151638031, "learning_rate": 9.217577972749401e-06, "loss": 0.816, "step": 9232 }, { "epoch": 0.5393107476635514, "grad_norm": 1.0056511163711548, "learning_rate": 9.215691944534343e-06, "loss": 0.6884, "step": 9233 }, { "epoch": 0.5393691588785047, "grad_norm": 1.3240022659301758, "learning_rate": 9.21380594439019e-06, "loss": 0.8423, "step": 9234 }, { "epoch": 0.539427570093458, "grad_norm": 1.1477748155593872, "learning_rate": 9.21191997238444e-06, "loss": 0.7555, "step": 9235 }, { "epoch": 0.5394859813084112, "grad_norm": 1.399928331375122, "learning_rate": 9.210034028584588e-06, "loss": 0.8332, "step": 9236 }, { "epoch": 0.5395443925233645, "grad_norm": 1.3966392278671265, "learning_rate": 9.20814811305814e-06, "loss": 0.9102, "step": 9237 }, { "epoch": 0.5396028037383177, "grad_norm": 1.374050259590149, "learning_rate": 9.20626222587259e-06, "loss": 0.671, "step": 9238 }, { "epoch": 0.539661214953271, "grad_norm": 1.195705771446228, "learning_rate": 9.204376367095438e-06, "loss": 0.9191, "step": 9239 }, { "epoch": 0.5397196261682243, "grad_norm": 1.3188278675079346, "learning_rate": 9.202490536794182e-06, "loss": 0.8735, "step": 9240 }, { "epoch": 0.5397780373831775, "grad_norm": 1.5979055166244507, "learning_rate": 9.200604735036308e-06, "loss": 0.8911, "step": 9241 }, { "epoch": 0.5398364485981308, "grad_norm": 1.1388314962387085, "learning_rate": 9.198718961889322e-06, "loss": 0.8136, "step": 9242 }, { "epoch": 0.5398948598130842, "grad_norm": 1.0922212600708008, "learning_rate": 9.196833217420705e-06, "loss": 0.7133, "step": 9243 }, { "epoch": 0.5399532710280374, "grad_norm": 1.5760552883148193, "learning_rate": 9.194947501697961e-06, "loss": 0.7326, "step": 9244 }, { "epoch": 0.5400116822429907, "grad_norm": 1.1298457384109497, "learning_rate": 9.193061814788575e-06, "loss": 0.8346, "step": 9245 }, { "epoch": 0.5400700934579439, "grad_norm": 1.673620581626892, "learning_rate": 9.191176156760034e-06, "loss": 0.9624, "step": 9246 }, { "epoch": 0.5401285046728972, "grad_norm": 1.4730080366134644, "learning_rate": 9.18929052767983e-06, "loss": 0.8634, "step": 9247 }, { "epoch": 0.5401869158878505, "grad_norm": 1.6628414392471313, "learning_rate": 9.187404927615456e-06, "loss": 0.8137, "step": 9248 }, { "epoch": 0.5402453271028037, "grad_norm": 0.9694393277168274, "learning_rate": 9.185519356634389e-06, "loss": 0.6004, "step": 9249 }, { "epoch": 0.540303738317757, "grad_norm": 1.2814668416976929, "learning_rate": 9.183633814804121e-06, "loss": 0.8483, "step": 9250 }, { "epoch": 0.5403621495327103, "grad_norm": 1.0906559228897095, "learning_rate": 9.181748302192133e-06, "loss": 0.7201, "step": 9251 }, { "epoch": 0.5404205607476635, "grad_norm": 1.5842688083648682, "learning_rate": 9.179862818865916e-06, "loss": 0.9919, "step": 9252 }, { "epoch": 0.5404789719626168, "grad_norm": 1.0066947937011719, "learning_rate": 9.177977364892947e-06, "loss": 0.7706, "step": 9253 }, { "epoch": 0.54053738317757, "grad_norm": 1.1931161880493164, "learning_rate": 9.176091940340706e-06, "loss": 0.8897, "step": 9254 }, { "epoch": 0.5405957943925234, "grad_norm": 1.5534182786941528, "learning_rate": 9.174206545276678e-06, "loss": 0.6692, "step": 9255 }, { "epoch": 0.5406542056074767, "grad_norm": 1.0544401407241821, "learning_rate": 9.17232117976834e-06, "loss": 0.6792, "step": 9256 }, { "epoch": 0.5407126168224299, "grad_norm": 1.181933879852295, "learning_rate": 9.170435843883172e-06, "loss": 0.727, "step": 9257 }, { "epoch": 0.5407710280373832, "grad_norm": 1.8356400728225708, "learning_rate": 9.168550537688652e-06, "loss": 0.8163, "step": 9258 }, { "epoch": 0.5408294392523364, "grad_norm": 1.3949692249298096, "learning_rate": 9.166665261252251e-06, "loss": 1.0118, "step": 9259 }, { "epoch": 0.5408878504672897, "grad_norm": 2.2799549102783203, "learning_rate": 9.164780014641452e-06, "loss": 0.7514, "step": 9260 }, { "epoch": 0.540946261682243, "grad_norm": 1.0863337516784668, "learning_rate": 9.162894797923722e-06, "loss": 0.7237, "step": 9261 }, { "epoch": 0.5410046728971962, "grad_norm": 1.9818214178085327, "learning_rate": 9.16100961116654e-06, "loss": 0.7246, "step": 9262 }, { "epoch": 0.5410630841121495, "grad_norm": 5.370372772216797, "learning_rate": 9.159124454437377e-06, "loss": 0.712, "step": 9263 }, { "epoch": 0.5411214953271029, "grad_norm": 1.3274387121200562, "learning_rate": 9.157239327803698e-06, "loss": 0.8537, "step": 9264 }, { "epoch": 0.541179906542056, "grad_norm": 1.2794222831726074, "learning_rate": 9.155354231332983e-06, "loss": 0.7406, "step": 9265 }, { "epoch": 0.5412383177570094, "grad_norm": 0.9602473378181458, "learning_rate": 9.153469165092691e-06, "loss": 0.7737, "step": 9266 }, { "epoch": 0.5412967289719626, "grad_norm": 1.1567456722259521, "learning_rate": 9.151584129150297e-06, "loss": 0.7992, "step": 9267 }, { "epoch": 0.5413551401869159, "grad_norm": 1.303306221961975, "learning_rate": 9.149699123573266e-06, "loss": 0.8921, "step": 9268 }, { "epoch": 0.5414135514018692, "grad_norm": 1.4957162141799927, "learning_rate": 9.147814148429057e-06, "loss": 0.6266, "step": 9269 }, { "epoch": 0.5414719626168224, "grad_norm": 1.5030492544174194, "learning_rate": 9.145929203785144e-06, "loss": 0.9203, "step": 9270 }, { "epoch": 0.5415303738317757, "grad_norm": 1.4379351139068604, "learning_rate": 9.144044289708984e-06, "loss": 0.9464, "step": 9271 }, { "epoch": 0.541588785046729, "grad_norm": 1.4127764701843262, "learning_rate": 9.142159406268043e-06, "loss": 0.6814, "step": 9272 }, { "epoch": 0.5416471962616822, "grad_norm": 1.3178216218948364, "learning_rate": 9.140274553529785e-06, "loss": 0.8054, "step": 9273 }, { "epoch": 0.5417056074766355, "grad_norm": 1.1800750494003296, "learning_rate": 9.13838973156166e-06, "loss": 0.7636, "step": 9274 }, { "epoch": 0.5417640186915887, "grad_norm": 1.3515212535858154, "learning_rate": 9.136504940431134e-06, "loss": 0.6923, "step": 9275 }, { "epoch": 0.5418224299065421, "grad_norm": 1.1030263900756836, "learning_rate": 9.134620180205665e-06, "loss": 0.6728, "step": 9276 }, { "epoch": 0.5418808411214954, "grad_norm": 2.2494490146636963, "learning_rate": 9.132735450952712e-06, "loss": 0.8134, "step": 9277 }, { "epoch": 0.5419392523364486, "grad_norm": 1.0075984001159668, "learning_rate": 9.130850752739724e-06, "loss": 0.8395, "step": 9278 }, { "epoch": 0.5419976635514019, "grad_norm": 1.396468997001648, "learning_rate": 9.128966085634157e-06, "loss": 0.8691, "step": 9279 }, { "epoch": 0.5420560747663551, "grad_norm": 1.468185305595398, "learning_rate": 9.127081449703469e-06, "loss": 0.8783, "step": 9280 }, { "epoch": 0.5421144859813084, "grad_norm": 1.6242730617523193, "learning_rate": 9.125196845015109e-06, "loss": 0.9618, "step": 9281 }, { "epoch": 0.5421728971962617, "grad_norm": 1.2831484079360962, "learning_rate": 9.123312271636531e-06, "loss": 0.9011, "step": 9282 }, { "epoch": 0.5422313084112149, "grad_norm": 1.6063710451126099, "learning_rate": 9.121427729635183e-06, "loss": 0.9101, "step": 9283 }, { "epoch": 0.5422897196261682, "grad_norm": 1.4273741245269775, "learning_rate": 9.119543219078511e-06, "loss": 0.715, "step": 9284 }, { "epoch": 0.5423481308411215, "grad_norm": 1.1924962997436523, "learning_rate": 9.117658740033971e-06, "loss": 0.6735, "step": 9285 }, { "epoch": 0.5424065420560747, "grad_norm": 1.904801607131958, "learning_rate": 9.115774292569e-06, "loss": 0.8496, "step": 9286 }, { "epoch": 0.5424649532710281, "grad_norm": 1.6570268869400024, "learning_rate": 9.113889876751052e-06, "loss": 1.0052, "step": 9287 }, { "epoch": 0.5425233644859813, "grad_norm": 1.970900535583496, "learning_rate": 9.112005492647566e-06, "loss": 0.8047, "step": 9288 }, { "epoch": 0.5425817757009346, "grad_norm": 1.1181806325912476, "learning_rate": 9.110121140325987e-06, "loss": 0.9426, "step": 9289 }, { "epoch": 0.5426401869158879, "grad_norm": 1.2830239534378052, "learning_rate": 9.108236819853761e-06, "loss": 0.7392, "step": 9290 }, { "epoch": 0.5426985981308411, "grad_norm": 0.8657214641571045, "learning_rate": 9.106352531298321e-06, "loss": 0.7392, "step": 9291 }, { "epoch": 0.5427570093457944, "grad_norm": 0.9399757385253906, "learning_rate": 9.104468274727115e-06, "loss": 0.932, "step": 9292 }, { "epoch": 0.5428154205607477, "grad_norm": 1.428289771080017, "learning_rate": 9.102584050207578e-06, "loss": 1.0078, "step": 9293 }, { "epoch": 0.5428738317757009, "grad_norm": 1.470206618309021, "learning_rate": 9.100699857807145e-06, "loss": 0.8558, "step": 9294 }, { "epoch": 0.5429322429906542, "grad_norm": 1.683383584022522, "learning_rate": 9.098815697593258e-06, "loss": 0.8555, "step": 9295 }, { "epoch": 0.5429906542056074, "grad_norm": 1.0912435054779053, "learning_rate": 9.096931569633346e-06, "loss": 0.6876, "step": 9296 }, { "epoch": 0.5430490654205608, "grad_norm": 1.8040794134140015, "learning_rate": 9.09504747399485e-06, "loss": 0.9993, "step": 9297 }, { "epoch": 0.5431074766355141, "grad_norm": 1.2244004011154175, "learning_rate": 9.093163410745202e-06, "loss": 0.8389, "step": 9298 }, { "epoch": 0.5431658878504673, "grad_norm": 1.41934072971344, "learning_rate": 9.091279379951829e-06, "loss": 0.7596, "step": 9299 }, { "epoch": 0.5432242990654206, "grad_norm": 1.00975501537323, "learning_rate": 9.089395381682165e-06, "loss": 0.7377, "step": 9300 }, { "epoch": 0.5432827102803738, "grad_norm": 1.2258234024047852, "learning_rate": 9.087511416003636e-06, "loss": 0.7403, "step": 9301 }, { "epoch": 0.5433411214953271, "grad_norm": 1.4703943729400635, "learning_rate": 9.085627482983679e-06, "loss": 0.9343, "step": 9302 }, { "epoch": 0.5433995327102804, "grad_norm": 1.1294618844985962, "learning_rate": 9.083743582689714e-06, "loss": 0.6882, "step": 9303 }, { "epoch": 0.5434579439252336, "grad_norm": 1.2586339712142944, "learning_rate": 9.081859715189165e-06, "loss": 0.646, "step": 9304 }, { "epoch": 0.5435163551401869, "grad_norm": 2.785548686981201, "learning_rate": 9.079975880549463e-06, "loss": 0.8622, "step": 9305 }, { "epoch": 0.5435747663551402, "grad_norm": 1.3708579540252686, "learning_rate": 9.078092078838032e-06, "loss": 0.7286, "step": 9306 }, { "epoch": 0.5436331775700934, "grad_norm": 1.6527955532073975, "learning_rate": 9.076208310122287e-06, "loss": 0.863, "step": 9307 }, { "epoch": 0.5436915887850468, "grad_norm": 1.2146655321121216, "learning_rate": 9.074324574469657e-06, "loss": 0.7985, "step": 9308 }, { "epoch": 0.54375, "grad_norm": 2.1303281784057617, "learning_rate": 9.072440871947555e-06, "loss": 0.8627, "step": 9309 }, { "epoch": 0.5438084112149533, "grad_norm": 0.9551836848258972, "learning_rate": 9.07055720262341e-06, "loss": 0.7651, "step": 9310 }, { "epoch": 0.5438668224299066, "grad_norm": 1.6528586149215698, "learning_rate": 9.06867356656463e-06, "loss": 0.9387, "step": 9311 }, { "epoch": 0.5439252336448598, "grad_norm": 1.28699791431427, "learning_rate": 9.066789963838636e-06, "loss": 0.9592, "step": 9312 }, { "epoch": 0.5439836448598131, "grad_norm": 0.9836366772651672, "learning_rate": 9.064906394512842e-06, "loss": 0.7239, "step": 9313 }, { "epoch": 0.5440420560747663, "grad_norm": 1.3902193307876587, "learning_rate": 9.063022858654662e-06, "loss": 0.6933, "step": 9314 }, { "epoch": 0.5441004672897196, "grad_norm": 1.130951166152954, "learning_rate": 9.061139356331515e-06, "loss": 0.8379, "step": 9315 }, { "epoch": 0.5441588785046729, "grad_norm": 1.46720552444458, "learning_rate": 9.059255887610806e-06, "loss": 0.8052, "step": 9316 }, { "epoch": 0.5442172897196261, "grad_norm": 1.3488199710845947, "learning_rate": 9.057372452559943e-06, "loss": 0.8149, "step": 9317 }, { "epoch": 0.5442757009345794, "grad_norm": 1.1212353706359863, "learning_rate": 9.055489051246347e-06, "loss": 0.7894, "step": 9318 }, { "epoch": 0.5443341121495328, "grad_norm": 1.1369590759277344, "learning_rate": 9.053605683737412e-06, "loss": 0.7038, "step": 9319 }, { "epoch": 0.544392523364486, "grad_norm": 1.808941125869751, "learning_rate": 9.051722350100554e-06, "loss": 0.7205, "step": 9320 }, { "epoch": 0.5444509345794393, "grad_norm": 2.829747438430786, "learning_rate": 9.04983905040318e-06, "loss": 0.8194, "step": 9321 }, { "epoch": 0.5445093457943925, "grad_norm": 1.340521216392517, "learning_rate": 9.047955784712685e-06, "loss": 0.8121, "step": 9322 }, { "epoch": 0.5445677570093458, "grad_norm": 1.1593372821807861, "learning_rate": 9.046072553096485e-06, "loss": 0.7131, "step": 9323 }, { "epoch": 0.5446261682242991, "grad_norm": 1.6786084175109863, "learning_rate": 9.044189355621969e-06, "loss": 0.7816, "step": 9324 }, { "epoch": 0.5446845794392523, "grad_norm": 1.4024323225021362, "learning_rate": 9.042306192356549e-06, "loss": 0.7997, "step": 9325 }, { "epoch": 0.5447429906542056, "grad_norm": 1.0459192991256714, "learning_rate": 9.040423063367621e-06, "loss": 0.6664, "step": 9326 }, { "epoch": 0.5448014018691589, "grad_norm": 1.2007077932357788, "learning_rate": 9.038539968722578e-06, "loss": 0.6026, "step": 9327 }, { "epoch": 0.5448598130841121, "grad_norm": 1.1514688730239868, "learning_rate": 9.036656908488824e-06, "loss": 0.7578, "step": 9328 }, { "epoch": 0.5449182242990654, "grad_norm": 1.300832748413086, "learning_rate": 9.034773882733751e-06, "loss": 0.8042, "step": 9329 }, { "epoch": 0.5449766355140186, "grad_norm": 1.3855611085891724, "learning_rate": 9.032890891524758e-06, "loss": 0.6876, "step": 9330 }, { "epoch": 0.545035046728972, "grad_norm": 1.6241503953933716, "learning_rate": 9.031007934929237e-06, "loss": 0.8866, "step": 9331 }, { "epoch": 0.5450934579439253, "grad_norm": 1.387342095375061, "learning_rate": 9.029125013014575e-06, "loss": 0.8706, "step": 9332 }, { "epoch": 0.5451518691588785, "grad_norm": 1.5874238014221191, "learning_rate": 9.02724212584817e-06, "loss": 0.7436, "step": 9333 }, { "epoch": 0.5452102803738318, "grad_norm": 1.3225997686386108, "learning_rate": 9.025359273497406e-06, "loss": 0.7057, "step": 9334 }, { "epoch": 0.545268691588785, "grad_norm": 1.0305006504058838, "learning_rate": 9.023476456029678e-06, "loss": 0.8473, "step": 9335 }, { "epoch": 0.5453271028037383, "grad_norm": 1.694662094116211, "learning_rate": 9.021593673512369e-06, "loss": 0.9286, "step": 9336 }, { "epoch": 0.5453855140186916, "grad_norm": 1.4699615240097046, "learning_rate": 9.019710926012864e-06, "loss": 0.796, "step": 9337 }, { "epoch": 0.5454439252336448, "grad_norm": 1.7339671850204468, "learning_rate": 9.01782821359855e-06, "loss": 0.8388, "step": 9338 }, { "epoch": 0.5455023364485981, "grad_norm": 1.49392569065094, "learning_rate": 9.01594553633681e-06, "loss": 0.6366, "step": 9339 }, { "epoch": 0.5455607476635514, "grad_norm": 1.1698369979858398, "learning_rate": 9.014062894295028e-06, "loss": 0.7599, "step": 9340 }, { "epoch": 0.5456191588785047, "grad_norm": 1.3547757863998413, "learning_rate": 9.012180287540582e-06, "loss": 0.7738, "step": 9341 }, { "epoch": 0.545677570093458, "grad_norm": 1.4326684474945068, "learning_rate": 9.010297716140852e-06, "loss": 0.8296, "step": 9342 }, { "epoch": 0.5457359813084112, "grad_norm": 0.9578826427459717, "learning_rate": 9.00841518016322e-06, "loss": 0.7096, "step": 9343 }, { "epoch": 0.5457943925233645, "grad_norm": 1.0623376369476318, "learning_rate": 9.006532679675058e-06, "loss": 0.8031, "step": 9344 }, { "epoch": 0.5458528037383178, "grad_norm": 2.4326412677764893, "learning_rate": 9.004650214743745e-06, "loss": 0.9356, "step": 9345 }, { "epoch": 0.545911214953271, "grad_norm": 0.9621590375900269, "learning_rate": 9.002767785436656e-06, "loss": 0.8195, "step": 9346 }, { "epoch": 0.5459696261682243, "grad_norm": 1.172980546951294, "learning_rate": 9.000885391821164e-06, "loss": 0.6702, "step": 9347 }, { "epoch": 0.5460280373831776, "grad_norm": 1.5700184106826782, "learning_rate": 8.999003033964642e-06, "loss": 0.7203, "step": 9348 }, { "epoch": 0.5460864485981308, "grad_norm": 1.9714739322662354, "learning_rate": 8.997120711934455e-06, "loss": 0.7661, "step": 9349 }, { "epoch": 0.5461448598130841, "grad_norm": 1.589087963104248, "learning_rate": 8.995238425797981e-06, "loss": 0.8107, "step": 9350 }, { "epoch": 0.5462032710280373, "grad_norm": 1.962744951248169, "learning_rate": 8.993356175622587e-06, "loss": 0.8068, "step": 9351 }, { "epoch": 0.5462616822429907, "grad_norm": 1.4138330221176147, "learning_rate": 8.991473961475631e-06, "loss": 0.8232, "step": 9352 }, { "epoch": 0.546320093457944, "grad_norm": 1.2820234298706055, "learning_rate": 8.98959178342449e-06, "loss": 0.6803, "step": 9353 }, { "epoch": 0.5463785046728972, "grad_norm": 1.2541502714157104, "learning_rate": 8.98770964153652e-06, "loss": 0.7731, "step": 9354 }, { "epoch": 0.5464369158878505, "grad_norm": 0.9653539061546326, "learning_rate": 8.985827535879087e-06, "loss": 0.805, "step": 9355 }, { "epoch": 0.5464953271028037, "grad_norm": 1.0257019996643066, "learning_rate": 8.983945466519559e-06, "loss": 0.7595, "step": 9356 }, { "epoch": 0.546553738317757, "grad_norm": 1.6918128728866577, "learning_rate": 8.982063433525285e-06, "loss": 0.8975, "step": 9357 }, { "epoch": 0.5466121495327103, "grad_norm": 1.2203984260559082, "learning_rate": 8.980181436963634e-06, "loss": 0.7335, "step": 9358 }, { "epoch": 0.5466705607476635, "grad_norm": 1.408153772354126, "learning_rate": 8.978299476901959e-06, "loss": 0.7349, "step": 9359 }, { "epoch": 0.5467289719626168, "grad_norm": 1.7219951152801514, "learning_rate": 8.976417553407615e-06, "loss": 0.8447, "step": 9360 }, { "epoch": 0.5467873831775701, "grad_norm": 1.7369014024734497, "learning_rate": 8.97453566654796e-06, "loss": 0.7954, "step": 9361 }, { "epoch": 0.5468457943925233, "grad_norm": 1.0535485744476318, "learning_rate": 8.972653816390349e-06, "loss": 0.7009, "step": 9362 }, { "epoch": 0.5469042056074767, "grad_norm": 1.0147536993026733, "learning_rate": 8.970772003002133e-06, "loss": 0.5654, "step": 9363 }, { "epoch": 0.5469626168224299, "grad_norm": 1.4197505712509155, "learning_rate": 8.968890226450668e-06, "loss": 0.7595, "step": 9364 }, { "epoch": 0.5470210280373832, "grad_norm": 1.1446207761764526, "learning_rate": 8.967008486803293e-06, "loss": 0.8561, "step": 9365 }, { "epoch": 0.5470794392523365, "grad_norm": 1.4811928272247314, "learning_rate": 8.965126784127367e-06, "loss": 0.9431, "step": 9366 }, { "epoch": 0.5471378504672897, "grad_norm": 1.5075310468673706, "learning_rate": 8.963245118490232e-06, "loss": 0.8452, "step": 9367 }, { "epoch": 0.547196261682243, "grad_norm": 1.1728440523147583, "learning_rate": 8.96136348995924e-06, "loss": 0.829, "step": 9368 }, { "epoch": 0.5472546728971963, "grad_norm": 0.9157254695892334, "learning_rate": 8.959481898601729e-06, "loss": 0.5231, "step": 9369 }, { "epoch": 0.5473130841121495, "grad_norm": 1.8085519075393677, "learning_rate": 8.957600344485042e-06, "loss": 0.9571, "step": 9370 }, { "epoch": 0.5473714953271028, "grad_norm": 1.057510256767273, "learning_rate": 8.955718827676527e-06, "loss": 0.7188, "step": 9371 }, { "epoch": 0.547429906542056, "grad_norm": 3.0940849781036377, "learning_rate": 8.95383734824352e-06, "loss": 0.7785, "step": 9372 }, { "epoch": 0.5474883177570093, "grad_norm": 1.4271533489227295, "learning_rate": 8.951955906253366e-06, "loss": 1.0085, "step": 9373 }, { "epoch": 0.5475467289719627, "grad_norm": 1.7465492486953735, "learning_rate": 8.950074501773398e-06, "loss": 0.6851, "step": 9374 }, { "epoch": 0.5476051401869159, "grad_norm": 1.813834309577942, "learning_rate": 8.94819313487095e-06, "loss": 0.7676, "step": 9375 }, { "epoch": 0.5476635514018692, "grad_norm": 1.061314582824707, "learning_rate": 8.946311805613368e-06, "loss": 0.8571, "step": 9376 }, { "epoch": 0.5477219626168224, "grad_norm": 1.9996248483657837, "learning_rate": 8.944430514067973e-06, "loss": 0.8097, "step": 9377 }, { "epoch": 0.5477803738317757, "grad_norm": 1.6846764087677002, "learning_rate": 8.942549260302107e-06, "loss": 0.8024, "step": 9378 }, { "epoch": 0.547838785046729, "grad_norm": 1.1372435092926025, "learning_rate": 8.940668044383098e-06, "loss": 0.7708, "step": 9379 }, { "epoch": 0.5478971962616822, "grad_norm": 2.0210630893707275, "learning_rate": 8.938786866378273e-06, "loss": 0.9318, "step": 9380 }, { "epoch": 0.5479556074766355, "grad_norm": 1.2122430801391602, "learning_rate": 8.93690572635497e-06, "loss": 0.929, "step": 9381 }, { "epoch": 0.5480140186915888, "grad_norm": 1.3230763673782349, "learning_rate": 8.935024624380505e-06, "loss": 0.7424, "step": 9382 }, { "epoch": 0.548072429906542, "grad_norm": 2.196532964706421, "learning_rate": 8.93314356052221e-06, "loss": 0.8271, "step": 9383 }, { "epoch": 0.5481308411214953, "grad_norm": 1.7963347434997559, "learning_rate": 8.931262534847413e-06, "loss": 0.8588, "step": 9384 }, { "epoch": 0.5481892523364486, "grad_norm": 3.458422899246216, "learning_rate": 8.929381547423427e-06, "loss": 0.8928, "step": 9385 }, { "epoch": 0.5482476635514019, "grad_norm": 1.144762396812439, "learning_rate": 8.927500598317581e-06, "loss": 0.8515, "step": 9386 }, { "epoch": 0.5483060747663552, "grad_norm": 2.63757061958313, "learning_rate": 8.925619687597193e-06, "loss": 0.8157, "step": 9387 }, { "epoch": 0.5483644859813084, "grad_norm": 1.1786541938781738, "learning_rate": 8.923738815329583e-06, "loss": 0.8071, "step": 9388 }, { "epoch": 0.5484228971962617, "grad_norm": 1.7146689891815186, "learning_rate": 8.921857981582072e-06, "loss": 0.8014, "step": 9389 }, { "epoch": 0.548481308411215, "grad_norm": 1.3630048036575317, "learning_rate": 8.919977186421968e-06, "loss": 0.8368, "step": 9390 }, { "epoch": 0.5485397196261682, "grad_norm": 1.3338090181350708, "learning_rate": 8.918096429916593e-06, "loss": 0.7841, "step": 9391 }, { "epoch": 0.5485981308411215, "grad_norm": 1.1394766569137573, "learning_rate": 8.916215712133256e-06, "loss": 0.7576, "step": 9392 }, { "epoch": 0.5486565420560747, "grad_norm": 0.9830599427223206, "learning_rate": 8.914335033139274e-06, "loss": 0.7039, "step": 9393 }, { "epoch": 0.548714953271028, "grad_norm": 1.4141350984573364, "learning_rate": 8.912454393001955e-06, "loss": 0.731, "step": 9394 }, { "epoch": 0.5487733644859814, "grad_norm": 0.8757259249687195, "learning_rate": 8.910573791788606e-06, "loss": 0.7475, "step": 9395 }, { "epoch": 0.5488317757009346, "grad_norm": 1.1443424224853516, "learning_rate": 8.908693229566538e-06, "loss": 0.6262, "step": 9396 }, { "epoch": 0.5488901869158879, "grad_norm": 1.0924376249313354, "learning_rate": 8.906812706403056e-06, "loss": 0.8594, "step": 9397 }, { "epoch": 0.5489485981308411, "grad_norm": 1.0532729625701904, "learning_rate": 8.90493222236547e-06, "loss": 0.7206, "step": 9398 }, { "epoch": 0.5490070093457944, "grad_norm": 1.5898678302764893, "learning_rate": 8.903051777521077e-06, "loss": 0.7768, "step": 9399 }, { "epoch": 0.5490654205607477, "grad_norm": 1.1789416074752808, "learning_rate": 8.901171371937181e-06, "loss": 0.7265, "step": 9400 }, { "epoch": 0.5491238317757009, "grad_norm": 1.831967830657959, "learning_rate": 8.899291005681087e-06, "loss": 0.8395, "step": 9401 }, { "epoch": 0.5491822429906542, "grad_norm": 0.988301694393158, "learning_rate": 8.897410678820086e-06, "loss": 0.9277, "step": 9402 }, { "epoch": 0.5492406542056075, "grad_norm": 1.4801356792449951, "learning_rate": 8.895530391421489e-06, "loss": 0.7975, "step": 9403 }, { "epoch": 0.5492990654205607, "grad_norm": 1.4468162059783936, "learning_rate": 8.893650143552582e-06, "loss": 0.6611, "step": 9404 }, { "epoch": 0.549357476635514, "grad_norm": 1.2047739028930664, "learning_rate": 8.891769935280664e-06, "loss": 0.9364, "step": 9405 }, { "epoch": 0.5494158878504672, "grad_norm": 1.0135921239852905, "learning_rate": 8.88988976667303e-06, "loss": 0.7314, "step": 9406 }, { "epoch": 0.5494742990654206, "grad_norm": 1.3371565341949463, "learning_rate": 8.888009637796968e-06, "loss": 0.7497, "step": 9407 }, { "epoch": 0.5495327102803739, "grad_norm": 1.1487383842468262, "learning_rate": 8.886129548719775e-06, "loss": 0.6832, "step": 9408 }, { "epoch": 0.5495911214953271, "grad_norm": 1.0960204601287842, "learning_rate": 8.884249499508739e-06, "loss": 0.7496, "step": 9409 }, { "epoch": 0.5496495327102804, "grad_norm": 1.2488006353378296, "learning_rate": 8.882369490231143e-06, "loss": 0.7006, "step": 9410 }, { "epoch": 0.5497079439252337, "grad_norm": 2.0020804405212402, "learning_rate": 8.880489520954281e-06, "loss": 1.0433, "step": 9411 }, { "epoch": 0.5497663551401869, "grad_norm": 1.3582526445388794, "learning_rate": 8.878609591745433e-06, "loss": 0.7944, "step": 9412 }, { "epoch": 0.5498247663551402, "grad_norm": 0.9912340641021729, "learning_rate": 8.876729702671886e-06, "loss": 0.6548, "step": 9413 }, { "epoch": 0.5498831775700934, "grad_norm": 1.687113642692566, "learning_rate": 8.874849853800924e-06, "loss": 0.8661, "step": 9414 }, { "epoch": 0.5499415887850467, "grad_norm": 1.0198827981948853, "learning_rate": 8.872970045199822e-06, "loss": 0.7933, "step": 9415 }, { "epoch": 0.55, "grad_norm": 1.3399797677993774, "learning_rate": 8.871090276935863e-06, "loss": 0.781, "step": 9416 }, { "epoch": 0.5500584112149532, "grad_norm": 1.1537543535232544, "learning_rate": 8.869210549076328e-06, "loss": 0.844, "step": 9417 }, { "epoch": 0.5501168224299066, "grad_norm": 1.3829877376556396, "learning_rate": 8.867330861688489e-06, "loss": 0.8604, "step": 9418 }, { "epoch": 0.5501752336448598, "grad_norm": 1.1008539199829102, "learning_rate": 8.865451214839625e-06, "loss": 0.8339, "step": 9419 }, { "epoch": 0.5502336448598131, "grad_norm": 1.195002794265747, "learning_rate": 8.863571608597003e-06, "loss": 0.7339, "step": 9420 }, { "epoch": 0.5502920560747664, "grad_norm": 1.4886502027511597, "learning_rate": 8.861692043027905e-06, "loss": 0.8644, "step": 9421 }, { "epoch": 0.5503504672897196, "grad_norm": 0.9855896234512329, "learning_rate": 8.8598125181996e-06, "loss": 0.6773, "step": 9422 }, { "epoch": 0.5504088785046729, "grad_norm": 1.7148079872131348, "learning_rate": 8.857933034179349e-06, "loss": 0.7635, "step": 9423 }, { "epoch": 0.5504672897196262, "grad_norm": 1.6403816938400269, "learning_rate": 8.856053591034426e-06, "loss": 0.6697, "step": 9424 }, { "epoch": 0.5505257009345794, "grad_norm": 1.1864242553710938, "learning_rate": 8.854174188832097e-06, "loss": 0.6429, "step": 9425 }, { "epoch": 0.5505841121495327, "grad_norm": 1.8362970352172852, "learning_rate": 8.852294827639632e-06, "loss": 0.6795, "step": 9426 }, { "epoch": 0.5506425233644859, "grad_norm": 1.046818733215332, "learning_rate": 8.850415507524287e-06, "loss": 0.7246, "step": 9427 }, { "epoch": 0.5507009345794392, "grad_norm": 1.7139836549758911, "learning_rate": 8.848536228553323e-06, "loss": 0.952, "step": 9428 }, { "epoch": 0.5507593457943926, "grad_norm": 1.5771820545196533, "learning_rate": 8.846656990794009e-06, "loss": 0.7942, "step": 9429 }, { "epoch": 0.5508177570093458, "grad_norm": 1.0262196063995361, "learning_rate": 8.844777794313597e-06, "loss": 0.788, "step": 9430 }, { "epoch": 0.5508761682242991, "grad_norm": 1.9431443214416504, "learning_rate": 8.842898639179352e-06, "loss": 1.0313, "step": 9431 }, { "epoch": 0.5509345794392523, "grad_norm": 1.4653562307357788, "learning_rate": 8.841019525458523e-06, "loss": 0.7907, "step": 9432 }, { "epoch": 0.5509929906542056, "grad_norm": 0.8770025968551636, "learning_rate": 8.839140453218364e-06, "loss": 0.8308, "step": 9433 }, { "epoch": 0.5510514018691589, "grad_norm": 2.915470600128174, "learning_rate": 8.837261422526137e-06, "loss": 1.0298, "step": 9434 }, { "epoch": 0.5511098130841121, "grad_norm": 1.4845610857009888, "learning_rate": 8.835382433449081e-06, "loss": 0.8332, "step": 9435 }, { "epoch": 0.5511682242990654, "grad_norm": 1.6230052709579468, "learning_rate": 8.83350348605446e-06, "loss": 0.6766, "step": 9436 }, { "epoch": 0.5512266355140187, "grad_norm": 1.9299883842468262, "learning_rate": 8.831624580409514e-06, "loss": 0.7371, "step": 9437 }, { "epoch": 0.5512850467289719, "grad_norm": 1.5757801532745361, "learning_rate": 8.829745716581492e-06, "loss": 0.815, "step": 9438 }, { "epoch": 0.5513434579439253, "grad_norm": 1.244104266166687, "learning_rate": 8.827866894637642e-06, "loss": 0.7563, "step": 9439 }, { "epoch": 0.5514018691588785, "grad_norm": 1.7003021240234375, "learning_rate": 8.825988114645203e-06, "loss": 0.7489, "step": 9440 }, { "epoch": 0.5514602803738318, "grad_norm": 1.5064706802368164, "learning_rate": 8.824109376671425e-06, "loss": 0.6178, "step": 9441 }, { "epoch": 0.5515186915887851, "grad_norm": 1.5818419456481934, "learning_rate": 8.822230680783545e-06, "loss": 0.9411, "step": 9442 }, { "epoch": 0.5515771028037383, "grad_norm": 1.4080044031143188, "learning_rate": 8.820352027048803e-06, "loss": 0.8018, "step": 9443 }, { "epoch": 0.5516355140186916, "grad_norm": 1.256351113319397, "learning_rate": 8.818473415534436e-06, "loss": 0.7422, "step": 9444 }, { "epoch": 0.5516939252336449, "grad_norm": 1.2977317571640015, "learning_rate": 8.816594846307682e-06, "loss": 0.8433, "step": 9445 }, { "epoch": 0.5517523364485981, "grad_norm": 1.1688302755355835, "learning_rate": 8.814716319435778e-06, "loss": 0.7567, "step": 9446 }, { "epoch": 0.5518107476635514, "grad_norm": 1.990973949432373, "learning_rate": 8.81283783498596e-06, "loss": 0.9544, "step": 9447 }, { "epoch": 0.5518691588785046, "grad_norm": 1.7801743745803833, "learning_rate": 8.81095939302545e-06, "loss": 0.8049, "step": 9448 }, { "epoch": 0.5519275700934579, "grad_norm": 2.2303924560546875, "learning_rate": 8.809080993621488e-06, "loss": 0.6234, "step": 9449 }, { "epoch": 0.5519859813084113, "grad_norm": 1.418013095855713, "learning_rate": 8.807202636841298e-06, "loss": 1.0508, "step": 9450 }, { "epoch": 0.5520443925233645, "grad_norm": 1.1785776615142822, "learning_rate": 8.805324322752114e-06, "loss": 0.8391, "step": 9451 }, { "epoch": 0.5521028037383178, "grad_norm": 1.275779128074646, "learning_rate": 8.803446051421156e-06, "loss": 0.7725, "step": 9452 }, { "epoch": 0.552161214953271, "grad_norm": 1.587754249572754, "learning_rate": 8.80156782291565e-06, "loss": 0.6974, "step": 9453 }, { "epoch": 0.5522196261682243, "grad_norm": 1.3514881134033203, "learning_rate": 8.799689637302819e-06, "loss": 0.815, "step": 9454 }, { "epoch": 0.5522780373831776, "grad_norm": 1.2875547409057617, "learning_rate": 8.797811494649885e-06, "loss": 0.7231, "step": 9455 }, { "epoch": 0.5523364485981308, "grad_norm": 1.3039350509643555, "learning_rate": 8.795933395024071e-06, "loss": 0.7261, "step": 9456 }, { "epoch": 0.5523948598130841, "grad_norm": 1.2609326839447021, "learning_rate": 8.794055338492592e-06, "loss": 0.742, "step": 9457 }, { "epoch": 0.5524532710280374, "grad_norm": 1.3163567781448364, "learning_rate": 8.792177325122662e-06, "loss": 1.0212, "step": 9458 }, { "epoch": 0.5525116822429906, "grad_norm": 1.234255075454712, "learning_rate": 8.790299354981505e-06, "loss": 0.8258, "step": 9459 }, { "epoch": 0.552570093457944, "grad_norm": 1.0349398851394653, "learning_rate": 8.788421428136321e-06, "loss": 0.7221, "step": 9460 }, { "epoch": 0.5526285046728971, "grad_norm": 1.116671085357666, "learning_rate": 8.786543544654339e-06, "loss": 0.8417, "step": 9461 }, { "epoch": 0.5526869158878505, "grad_norm": 1.3414785861968994, "learning_rate": 8.784665704602758e-06, "loss": 0.9126, "step": 9462 }, { "epoch": 0.5527453271028038, "grad_norm": 1.0369923114776611, "learning_rate": 8.78278790804879e-06, "loss": 0.8168, "step": 9463 }, { "epoch": 0.552803738317757, "grad_norm": 1.5699496269226074, "learning_rate": 8.780910155059647e-06, "loss": 0.7299, "step": 9464 }, { "epoch": 0.5528621495327103, "grad_norm": 1.6545367240905762, "learning_rate": 8.779032445702526e-06, "loss": 0.7683, "step": 9465 }, { "epoch": 0.5529205607476636, "grad_norm": 1.6322952508926392, "learning_rate": 8.777154780044639e-06, "loss": 0.9176, "step": 9466 }, { "epoch": 0.5529789719626168, "grad_norm": 1.1205288171768188, "learning_rate": 8.775277158153188e-06, "loss": 0.8763, "step": 9467 }, { "epoch": 0.5530373831775701, "grad_norm": 1.0647767782211304, "learning_rate": 8.773399580095368e-06, "loss": 0.6851, "step": 9468 }, { "epoch": 0.5530957943925233, "grad_norm": 0.8210731744766235, "learning_rate": 8.771522045938389e-06, "loss": 0.5649, "step": 9469 }, { "epoch": 0.5531542056074766, "grad_norm": 1.7385424375534058, "learning_rate": 8.769644555749438e-06, "loss": 0.7814, "step": 9470 }, { "epoch": 0.55321261682243, "grad_norm": 1.0946874618530273, "learning_rate": 8.767767109595722e-06, "loss": 0.8046, "step": 9471 }, { "epoch": 0.5532710280373832, "grad_norm": 1.727349877357483, "learning_rate": 8.765889707544432e-06, "loss": 0.7949, "step": 9472 }, { "epoch": 0.5533294392523365, "grad_norm": 1.1900602579116821, "learning_rate": 8.764012349662757e-06, "loss": 0.9763, "step": 9473 }, { "epoch": 0.5533878504672897, "grad_norm": 1.2832483053207397, "learning_rate": 8.762135036017895e-06, "loss": 0.8546, "step": 9474 }, { "epoch": 0.553446261682243, "grad_norm": 1.5976146459579468, "learning_rate": 8.760257766677036e-06, "loss": 0.9197, "step": 9475 }, { "epoch": 0.5535046728971963, "grad_norm": 1.302147388458252, "learning_rate": 8.758380541707363e-06, "loss": 0.6967, "step": 9476 }, { "epoch": 0.5535630841121495, "grad_norm": 1.4356005191802979, "learning_rate": 8.756503361176068e-06, "loss": 0.7695, "step": 9477 }, { "epoch": 0.5536214953271028, "grad_norm": 1.3254727125167847, "learning_rate": 8.754626225150333e-06, "loss": 0.8257, "step": 9478 }, { "epoch": 0.5536799065420561, "grad_norm": 1.3521229028701782, "learning_rate": 8.752749133697346e-06, "loss": 0.8261, "step": 9479 }, { "epoch": 0.5537383177570093, "grad_norm": 1.0249649286270142, "learning_rate": 8.75087208688429e-06, "loss": 0.6553, "step": 9480 }, { "epoch": 0.5537967289719626, "grad_norm": 3.2283291816711426, "learning_rate": 8.74899508477834e-06, "loss": 0.822, "step": 9481 }, { "epoch": 0.5538551401869158, "grad_norm": 1.582101583480835, "learning_rate": 8.74711812744668e-06, "loss": 0.7987, "step": 9482 }, { "epoch": 0.5539135514018692, "grad_norm": 2.0081324577331543, "learning_rate": 8.745241214956484e-06, "loss": 0.7587, "step": 9483 }, { "epoch": 0.5539719626168225, "grad_norm": 1.5057168006896973, "learning_rate": 8.743364347374934e-06, "loss": 0.8385, "step": 9484 }, { "epoch": 0.5540303738317757, "grad_norm": 1.1484453678131104, "learning_rate": 8.741487524769198e-06, "loss": 0.8602, "step": 9485 }, { "epoch": 0.554088785046729, "grad_norm": 2.603841543197632, "learning_rate": 8.73961074720645e-06, "loss": 0.8952, "step": 9486 }, { "epoch": 0.5541471962616823, "grad_norm": 1.1366318464279175, "learning_rate": 8.737734014753863e-06, "loss": 0.8239, "step": 9487 }, { "epoch": 0.5542056074766355, "grad_norm": 1.2286481857299805, "learning_rate": 8.735857327478604e-06, "loss": 0.7402, "step": 9488 }, { "epoch": 0.5542640186915888, "grad_norm": 2.014174461364746, "learning_rate": 8.733980685447847e-06, "loss": 0.8708, "step": 9489 }, { "epoch": 0.554322429906542, "grad_norm": 1.6677213907241821, "learning_rate": 8.73210408872875e-06, "loss": 0.7975, "step": 9490 }, { "epoch": 0.5543808411214953, "grad_norm": 1.6497588157653809, "learning_rate": 8.73022753738848e-06, "loss": 0.7797, "step": 9491 }, { "epoch": 0.5544392523364486, "grad_norm": 1.1340208053588867, "learning_rate": 8.728351031494207e-06, "loss": 0.7615, "step": 9492 }, { "epoch": 0.5544976635514018, "grad_norm": 1.9284993410110474, "learning_rate": 8.726474571113078e-06, "loss": 0.8908, "step": 9493 }, { "epoch": 0.5545560747663552, "grad_norm": 0.9835518598556519, "learning_rate": 8.724598156312269e-06, "loss": 0.81, "step": 9494 }, { "epoch": 0.5546144859813084, "grad_norm": 1.5699928998947144, "learning_rate": 8.72272178715893e-06, "loss": 0.8282, "step": 9495 }, { "epoch": 0.5546728971962617, "grad_norm": 1.0083006620407104, "learning_rate": 8.720845463720214e-06, "loss": 0.6026, "step": 9496 }, { "epoch": 0.554731308411215, "grad_norm": 1.7564139366149902, "learning_rate": 8.718969186063285e-06, "loss": 0.7284, "step": 9497 }, { "epoch": 0.5547897196261682, "grad_norm": 0.9655340909957886, "learning_rate": 8.717092954255287e-06, "loss": 0.5998, "step": 9498 }, { "epoch": 0.5548481308411215, "grad_norm": 1.160374641418457, "learning_rate": 8.715216768363376e-06, "loss": 0.7758, "step": 9499 }, { "epoch": 0.5549065420560748, "grad_norm": 1.6109462976455688, "learning_rate": 8.713340628454706e-06, "loss": 0.7969, "step": 9500 }, { "epoch": 0.554964953271028, "grad_norm": 1.1962262392044067, "learning_rate": 8.711464534596413e-06, "loss": 0.9223, "step": 9501 }, { "epoch": 0.5550233644859813, "grad_norm": 3.2438881397247314, "learning_rate": 8.709588486855659e-06, "loss": 0.8122, "step": 9502 }, { "epoch": 0.5550817757009345, "grad_norm": 1.6032871007919312, "learning_rate": 8.707712485299576e-06, "loss": 0.736, "step": 9503 }, { "epoch": 0.5551401869158878, "grad_norm": 1.1030384302139282, "learning_rate": 8.705836529995316e-06, "loss": 0.7571, "step": 9504 }, { "epoch": 0.5551985981308412, "grad_norm": 1.3658989667892456, "learning_rate": 8.703960621010019e-06, "loss": 0.8193, "step": 9505 }, { "epoch": 0.5552570093457944, "grad_norm": 1.207492709159851, "learning_rate": 8.70208475841082e-06, "loss": 0.7631, "step": 9506 }, { "epoch": 0.5553154205607477, "grad_norm": 1.505717158317566, "learning_rate": 8.700208942264862e-06, "loss": 0.8228, "step": 9507 }, { "epoch": 0.555373831775701, "grad_norm": 1.5272527933120728, "learning_rate": 8.69833317263928e-06, "loss": 0.8739, "step": 9508 }, { "epoch": 0.5554322429906542, "grad_norm": 1.1558221578598022, "learning_rate": 8.696457449601212e-06, "loss": 0.7096, "step": 9509 }, { "epoch": 0.5554906542056075, "grad_norm": 1.352341651916504, "learning_rate": 8.694581773217788e-06, "loss": 0.9131, "step": 9510 }, { "epoch": 0.5555490654205607, "grad_norm": 0.9442968368530273, "learning_rate": 8.692706143556137e-06, "loss": 0.7581, "step": 9511 }, { "epoch": 0.555607476635514, "grad_norm": 1.3083170652389526, "learning_rate": 8.690830560683397e-06, "loss": 0.9689, "step": 9512 }, { "epoch": 0.5556658878504673, "grad_norm": 1.3826547861099243, "learning_rate": 8.68895502466669e-06, "loss": 0.9119, "step": 9513 }, { "epoch": 0.5557242990654205, "grad_norm": 1.308153510093689, "learning_rate": 8.687079535573147e-06, "loss": 0.8708, "step": 9514 }, { "epoch": 0.5557827102803738, "grad_norm": 1.4235631227493286, "learning_rate": 8.68520409346989e-06, "loss": 0.7753, "step": 9515 }, { "epoch": 0.555841121495327, "grad_norm": 1.5539348125457764, "learning_rate": 8.683328698424041e-06, "loss": 0.7983, "step": 9516 }, { "epoch": 0.5558995327102804, "grad_norm": 1.21288001537323, "learning_rate": 8.681453350502726e-06, "loss": 0.6068, "step": 9517 }, { "epoch": 0.5559579439252337, "grad_norm": 1.185457706451416, "learning_rate": 8.67957804977306e-06, "loss": 0.6812, "step": 9518 }, { "epoch": 0.5560163551401869, "grad_norm": 1.4020129442214966, "learning_rate": 8.677702796302166e-06, "loss": 0.6126, "step": 9519 }, { "epoch": 0.5560747663551402, "grad_norm": 1.5502432584762573, "learning_rate": 8.675827590157158e-06, "loss": 0.8223, "step": 9520 }, { "epoch": 0.5561331775700935, "grad_norm": 1.16249418258667, "learning_rate": 8.673952431405148e-06, "loss": 1.0041, "step": 9521 }, { "epoch": 0.5561915887850467, "grad_norm": 1.1561866998672485, "learning_rate": 8.672077320113258e-06, "loss": 0.6629, "step": 9522 }, { "epoch": 0.55625, "grad_norm": 1.4957544803619385, "learning_rate": 8.67020225634859e-06, "loss": 0.8431, "step": 9523 }, { "epoch": 0.5563084112149532, "grad_norm": 1.51270592212677, "learning_rate": 8.668327240178257e-06, "loss": 0.8129, "step": 9524 }, { "epoch": 0.5563668224299065, "grad_norm": 1.300673484802246, "learning_rate": 8.666452271669373e-06, "loss": 0.9512, "step": 9525 }, { "epoch": 0.5564252336448599, "grad_norm": 1.2986359596252441, "learning_rate": 8.66457735088903e-06, "loss": 0.6768, "step": 9526 }, { "epoch": 0.556483644859813, "grad_norm": 1.3669416904449463, "learning_rate": 8.66270247790435e-06, "loss": 0.7792, "step": 9527 }, { "epoch": 0.5565420560747664, "grad_norm": 1.2014055252075195, "learning_rate": 8.660827652782423e-06, "loss": 0.8694, "step": 9528 }, { "epoch": 0.5566004672897197, "grad_norm": 1.8489060401916504, "learning_rate": 8.658952875590356e-06, "loss": 0.8688, "step": 9529 }, { "epoch": 0.5566588785046729, "grad_norm": 1.1070725917816162, "learning_rate": 8.65707814639525e-06, "loss": 0.9938, "step": 9530 }, { "epoch": 0.5567172897196262, "grad_norm": 1.1805576086044312, "learning_rate": 8.655203465264196e-06, "loss": 0.7155, "step": 9531 }, { "epoch": 0.5567757009345794, "grad_norm": 1.0975369215011597, "learning_rate": 8.653328832264297e-06, "loss": 0.6674, "step": 9532 }, { "epoch": 0.5568341121495327, "grad_norm": 1.1519712209701538, "learning_rate": 8.651454247462647e-06, "loss": 0.7561, "step": 9533 }, { "epoch": 0.556892523364486, "grad_norm": 1.3347737789154053, "learning_rate": 8.649579710926328e-06, "loss": 0.7847, "step": 9534 }, { "epoch": 0.5569509345794392, "grad_norm": 1.0873801708221436, "learning_rate": 8.647705222722447e-06, "loss": 0.7937, "step": 9535 }, { "epoch": 0.5570093457943925, "grad_norm": 1.21183443069458, "learning_rate": 8.645830782918079e-06, "loss": 0.7044, "step": 9536 }, { "epoch": 0.5570677570093457, "grad_norm": 2.025245189666748, "learning_rate": 8.643956391580321e-06, "loss": 0.6542, "step": 9537 }, { "epoch": 0.5571261682242991, "grad_norm": 1.4018882513046265, "learning_rate": 8.642082048776257e-06, "loss": 0.7565, "step": 9538 }, { "epoch": 0.5571845794392524, "grad_norm": 0.9359543919563293, "learning_rate": 8.640207754572967e-06, "loss": 0.7148, "step": 9539 }, { "epoch": 0.5572429906542056, "grad_norm": 1.2440356016159058, "learning_rate": 8.638333509037537e-06, "loss": 0.8391, "step": 9540 }, { "epoch": 0.5573014018691589, "grad_norm": 1.5725712776184082, "learning_rate": 8.636459312237041e-06, "loss": 0.7447, "step": 9541 }, { "epoch": 0.5573598130841122, "grad_norm": 1.7817323207855225, "learning_rate": 8.63458516423857e-06, "loss": 0.8375, "step": 9542 }, { "epoch": 0.5574182242990654, "grad_norm": 1.3190120458602905, "learning_rate": 8.632711065109191e-06, "loss": 0.6631, "step": 9543 }, { "epoch": 0.5574766355140187, "grad_norm": 1.190256953239441, "learning_rate": 8.63083701491598e-06, "loss": 0.8038, "step": 9544 }, { "epoch": 0.5575350467289719, "grad_norm": 1.3931063413619995, "learning_rate": 8.628963013726013e-06, "loss": 0.8028, "step": 9545 }, { "epoch": 0.5575934579439252, "grad_norm": 1.4289484024047852, "learning_rate": 8.627089061606362e-06, "loss": 0.7425, "step": 9546 }, { "epoch": 0.5576518691588785, "grad_norm": 1.1327215433120728, "learning_rate": 8.625215158624098e-06, "loss": 0.8211, "step": 9547 }, { "epoch": 0.5577102803738317, "grad_norm": 1.0115647315979004, "learning_rate": 8.623341304846287e-06, "loss": 0.7968, "step": 9548 }, { "epoch": 0.5577686915887851, "grad_norm": 1.081945538520813, "learning_rate": 8.621467500339992e-06, "loss": 0.7093, "step": 9549 }, { "epoch": 0.5578271028037384, "grad_norm": 1.6309577226638794, "learning_rate": 8.619593745172287e-06, "loss": 0.7162, "step": 9550 }, { "epoch": 0.5578855140186916, "grad_norm": 1.1583040952682495, "learning_rate": 8.617720039410222e-06, "loss": 0.6289, "step": 9551 }, { "epoch": 0.5579439252336449, "grad_norm": 1.3753912448883057, "learning_rate": 8.615846383120873e-06, "loss": 0.7905, "step": 9552 }, { "epoch": 0.5580023364485981, "grad_norm": 1.2913532257080078, "learning_rate": 8.61397277637129e-06, "loss": 0.7078, "step": 9553 }, { "epoch": 0.5580607476635514, "grad_norm": 1.268965721130371, "learning_rate": 8.61209921922853e-06, "loss": 0.7924, "step": 9554 }, { "epoch": 0.5581191588785047, "grad_norm": 1.3899325132369995, "learning_rate": 8.610225711759657e-06, "loss": 0.7663, "step": 9555 }, { "epoch": 0.5581775700934579, "grad_norm": 1.4961059093475342, "learning_rate": 8.608352254031714e-06, "loss": 0.8037, "step": 9556 }, { "epoch": 0.5582359813084112, "grad_norm": 1.0922441482543945, "learning_rate": 8.606478846111761e-06, "loss": 0.7502, "step": 9557 }, { "epoch": 0.5582943925233644, "grad_norm": 1.0679426193237305, "learning_rate": 8.604605488066848e-06, "loss": 0.6543, "step": 9558 }, { "epoch": 0.5583528037383177, "grad_norm": 1.4130545854568481, "learning_rate": 8.602732179964017e-06, "loss": 0.8945, "step": 9559 }, { "epoch": 0.5584112149532711, "grad_norm": 1.0107464790344238, "learning_rate": 8.600858921870325e-06, "loss": 0.7152, "step": 9560 }, { "epoch": 0.5584696261682243, "grad_norm": 1.3018919229507446, "learning_rate": 8.59898571385281e-06, "loss": 0.8458, "step": 9561 }, { "epoch": 0.5585280373831776, "grad_norm": 1.425990104675293, "learning_rate": 8.597112555978517e-06, "loss": 0.8103, "step": 9562 }, { "epoch": 0.5585864485981309, "grad_norm": 1.032984733581543, "learning_rate": 8.595239448314492e-06, "loss": 0.6769, "step": 9563 }, { "epoch": 0.5586448598130841, "grad_norm": 0.9539572596549988, "learning_rate": 8.593366390927767e-06, "loss": 0.8567, "step": 9564 }, { "epoch": 0.5587032710280374, "grad_norm": 1.128736972808838, "learning_rate": 8.591493383885384e-06, "loss": 0.7828, "step": 9565 }, { "epoch": 0.5587616822429906, "grad_norm": 1.5224742889404297, "learning_rate": 8.589620427254379e-06, "loss": 0.7732, "step": 9566 }, { "epoch": 0.5588200934579439, "grad_norm": 1.6951508522033691, "learning_rate": 8.587747521101785e-06, "loss": 0.8715, "step": 9567 }, { "epoch": 0.5588785046728972, "grad_norm": 1.0974531173706055, "learning_rate": 8.585874665494641e-06, "loss": 0.6267, "step": 9568 }, { "epoch": 0.5589369158878504, "grad_norm": 1.3124291896820068, "learning_rate": 8.584001860499967e-06, "loss": 1.0751, "step": 9569 }, { "epoch": 0.5589953271028038, "grad_norm": 1.0672972202301025, "learning_rate": 8.5821291061848e-06, "loss": 0.701, "step": 9570 }, { "epoch": 0.559053738317757, "grad_norm": 1.41399085521698, "learning_rate": 8.580256402616162e-06, "loss": 0.6649, "step": 9571 }, { "epoch": 0.5591121495327103, "grad_norm": 1.3170546293258667, "learning_rate": 8.578383749861086e-06, "loss": 0.8795, "step": 9572 }, { "epoch": 0.5591705607476636, "grad_norm": 1.1408796310424805, "learning_rate": 8.576511147986587e-06, "loss": 0.9856, "step": 9573 }, { "epoch": 0.5592289719626168, "grad_norm": 1.349005937576294, "learning_rate": 8.574638597059689e-06, "loss": 0.7699, "step": 9574 }, { "epoch": 0.5592873831775701, "grad_norm": 1.347080111503601, "learning_rate": 8.572766097147416e-06, "loss": 0.7231, "step": 9575 }, { "epoch": 0.5593457943925234, "grad_norm": 1.3536022901535034, "learning_rate": 8.570893648316777e-06, "loss": 0.6841, "step": 9576 }, { "epoch": 0.5594042056074766, "grad_norm": 1.3238171339035034, "learning_rate": 8.5690212506348e-06, "loss": 0.8671, "step": 9577 }, { "epoch": 0.5594626168224299, "grad_norm": 1.4179468154907227, "learning_rate": 8.567148904168492e-06, "loss": 0.8164, "step": 9578 }, { "epoch": 0.5595210280373831, "grad_norm": 1.0216094255447388, "learning_rate": 8.565276608984865e-06, "loss": 0.7158, "step": 9579 }, { "epoch": 0.5595794392523364, "grad_norm": 1.6948732137680054, "learning_rate": 8.563404365150934e-06, "loss": 0.7745, "step": 9580 }, { "epoch": 0.5596378504672898, "grad_norm": 0.9603127241134644, "learning_rate": 8.561532172733701e-06, "loss": 0.8592, "step": 9581 }, { "epoch": 0.559696261682243, "grad_norm": 1.193717360496521, "learning_rate": 8.559660031800181e-06, "loss": 0.8027, "step": 9582 }, { "epoch": 0.5597546728971963, "grad_norm": 1.3675727844238281, "learning_rate": 8.557787942417379e-06, "loss": 0.7617, "step": 9583 }, { "epoch": 0.5598130841121496, "grad_norm": 1.317629337310791, "learning_rate": 8.555915904652285e-06, "loss": 0.8516, "step": 9584 }, { "epoch": 0.5598714953271028, "grad_norm": 1.2230173349380493, "learning_rate": 8.55404391857192e-06, "loss": 0.909, "step": 9585 }, { "epoch": 0.5599299065420561, "grad_norm": 1.3955769538879395, "learning_rate": 8.552171984243269e-06, "loss": 0.7867, "step": 9586 }, { "epoch": 0.5599883177570093, "grad_norm": 1.229753851890564, "learning_rate": 8.550300101733333e-06, "loss": 0.7577, "step": 9587 }, { "epoch": 0.5600467289719626, "grad_norm": 1.6775739192962646, "learning_rate": 8.548428271109115e-06, "loss": 0.9232, "step": 9588 }, { "epoch": 0.5601051401869159, "grad_norm": 1.315502643585205, "learning_rate": 8.546556492437598e-06, "loss": 0.8608, "step": 9589 }, { "epoch": 0.5601635514018691, "grad_norm": 1.3388123512268066, "learning_rate": 8.544684765785782e-06, "loss": 0.7696, "step": 9590 }, { "epoch": 0.5602219626168224, "grad_norm": 0.8958099484443665, "learning_rate": 8.542813091220659e-06, "loss": 0.6304, "step": 9591 }, { "epoch": 0.5602803738317756, "grad_norm": 1.7449647188186646, "learning_rate": 8.540941468809204e-06, "loss": 0.9094, "step": 9592 }, { "epoch": 0.560338785046729, "grad_norm": 1.3653783798217773, "learning_rate": 8.539069898618424e-06, "loss": 0.8447, "step": 9593 }, { "epoch": 0.5603971962616823, "grad_norm": 1.503108024597168, "learning_rate": 8.537198380715285e-06, "loss": 0.734, "step": 9594 }, { "epoch": 0.5604556074766355, "grad_norm": 1.315604567527771, "learning_rate": 8.535326915166782e-06, "loss": 0.7502, "step": 9595 }, { "epoch": 0.5605140186915888, "grad_norm": 1.2246577739715576, "learning_rate": 8.533455502039893e-06, "loss": 1.015, "step": 9596 }, { "epoch": 0.5605724299065421, "grad_norm": 1.0473766326904297, "learning_rate": 8.531584141401592e-06, "loss": 0.88, "step": 9597 }, { "epoch": 0.5606308411214953, "grad_norm": 4.947955131530762, "learning_rate": 8.529712833318862e-06, "loss": 0.7537, "step": 9598 }, { "epoch": 0.5606892523364486, "grad_norm": 1.579849362373352, "learning_rate": 8.527841577858674e-06, "loss": 0.7829, "step": 9599 }, { "epoch": 0.5607476635514018, "grad_norm": 1.1310161352157593, "learning_rate": 8.525970375088006e-06, "loss": 0.7753, "step": 9600 }, { "epoch": 0.5608060747663551, "grad_norm": 0.9441817998886108, "learning_rate": 8.52409922507383e-06, "loss": 0.8027, "step": 9601 }, { "epoch": 0.5608644859813084, "grad_norm": 1.27051842212677, "learning_rate": 8.522228127883108e-06, "loss": 0.8065, "step": 9602 }, { "epoch": 0.5609228971962616, "grad_norm": 1.5293816328048706, "learning_rate": 8.520357083582815e-06, "loss": 0.9351, "step": 9603 }, { "epoch": 0.560981308411215, "grad_norm": 2.2476065158843994, "learning_rate": 8.518486092239914e-06, "loss": 0.9225, "step": 9604 }, { "epoch": 0.5610397196261683, "grad_norm": 1.5576802492141724, "learning_rate": 8.516615153921374e-06, "loss": 0.9201, "step": 9605 }, { "epoch": 0.5610981308411215, "grad_norm": 1.8249008655548096, "learning_rate": 8.51474426869415e-06, "loss": 0.9069, "step": 9606 }, { "epoch": 0.5611565420560748, "grad_norm": 1.0306825637817383, "learning_rate": 8.512873436625204e-06, "loss": 0.8696, "step": 9607 }, { "epoch": 0.561214953271028, "grad_norm": 2.177194356918335, "learning_rate": 8.5110026577815e-06, "loss": 0.8846, "step": 9608 }, { "epoch": 0.5612733644859813, "grad_norm": 1.1348150968551636, "learning_rate": 8.509131932229982e-06, "loss": 0.7693, "step": 9609 }, { "epoch": 0.5613317757009346, "grad_norm": 1.7243939638137817, "learning_rate": 8.50726126003762e-06, "loss": 0.7891, "step": 9610 }, { "epoch": 0.5613901869158878, "grad_norm": 1.1314888000488281, "learning_rate": 8.505390641271356e-06, "loss": 0.987, "step": 9611 }, { "epoch": 0.5614485981308411, "grad_norm": 1.0729947090148926, "learning_rate": 8.503520075998141e-06, "loss": 0.7078, "step": 9612 }, { "epoch": 0.5615070093457943, "grad_norm": 0.9721317887306213, "learning_rate": 8.501649564284932e-06, "loss": 0.8204, "step": 9613 }, { "epoch": 0.5615654205607477, "grad_norm": 1.0158416032791138, "learning_rate": 8.499779106198667e-06, "loss": 0.567, "step": 9614 }, { "epoch": 0.561623831775701, "grad_norm": 1.500389814376831, "learning_rate": 8.497908701806295e-06, "loss": 0.9622, "step": 9615 }, { "epoch": 0.5616822429906542, "grad_norm": 1.0747233629226685, "learning_rate": 8.49603835117476e-06, "loss": 0.681, "step": 9616 }, { "epoch": 0.5617406542056075, "grad_norm": 1.6906121969223022, "learning_rate": 8.494168054370996e-06, "loss": 0.9323, "step": 9617 }, { "epoch": 0.5617990654205608, "grad_norm": 1.3500478267669678, "learning_rate": 8.492297811461953e-06, "loss": 0.7482, "step": 9618 }, { "epoch": 0.561857476635514, "grad_norm": 1.1874637603759766, "learning_rate": 8.490427622514559e-06, "loss": 0.8719, "step": 9619 }, { "epoch": 0.5619158878504673, "grad_norm": 1.4674174785614014, "learning_rate": 8.488557487595754e-06, "loss": 0.7839, "step": 9620 }, { "epoch": 0.5619742990654205, "grad_norm": 1.6949858665466309, "learning_rate": 8.486687406772474e-06, "loss": 0.7088, "step": 9621 }, { "epoch": 0.5620327102803738, "grad_norm": 0.8617283701896667, "learning_rate": 8.484817380111641e-06, "loss": 0.8269, "step": 9622 }, { "epoch": 0.5620911214953271, "grad_norm": 1.187770128250122, "learning_rate": 8.482947407680193e-06, "loss": 0.9223, "step": 9623 }, { "epoch": 0.5621495327102803, "grad_norm": 1.9344078302383423, "learning_rate": 8.481077489545051e-06, "loss": 0.743, "step": 9624 }, { "epoch": 0.5622079439252337, "grad_norm": 1.3623157739639282, "learning_rate": 8.47920762577315e-06, "loss": 0.7994, "step": 9625 }, { "epoch": 0.562266355140187, "grad_norm": 1.2208422422409058, "learning_rate": 8.477337816431408e-06, "loss": 0.7815, "step": 9626 }, { "epoch": 0.5623247663551402, "grad_norm": 0.8665366172790527, "learning_rate": 8.475468061586742e-06, "loss": 0.6179, "step": 9627 }, { "epoch": 0.5623831775700935, "grad_norm": 1.3769360780715942, "learning_rate": 8.473598361306079e-06, "loss": 1.0047, "step": 9628 }, { "epoch": 0.5624415887850467, "grad_norm": 1.229160189628601, "learning_rate": 8.471728715656332e-06, "loss": 0.9864, "step": 9629 }, { "epoch": 0.5625, "grad_norm": 1.2196773290634155, "learning_rate": 8.469859124704425e-06, "loss": 0.818, "step": 9630 }, { "epoch": 0.5625584112149533, "grad_norm": 1.9360051155090332, "learning_rate": 8.467989588517263e-06, "loss": 0.7964, "step": 9631 }, { "epoch": 0.5626168224299065, "grad_norm": 1.1343517303466797, "learning_rate": 8.466120107161757e-06, "loss": 0.8015, "step": 9632 }, { "epoch": 0.5626752336448598, "grad_norm": 2.319976329803467, "learning_rate": 8.464250680704826e-06, "loss": 1.0438, "step": 9633 }, { "epoch": 0.562733644859813, "grad_norm": 1.0602383613586426, "learning_rate": 8.462381309213367e-06, "loss": 0.7712, "step": 9634 }, { "epoch": 0.5627920560747663, "grad_norm": 1.214280366897583, "learning_rate": 8.4605119927543e-06, "loss": 0.806, "step": 9635 }, { "epoch": 0.5628504672897197, "grad_norm": 1.2856426239013672, "learning_rate": 8.458642731394517e-06, "loss": 0.7745, "step": 9636 }, { "epoch": 0.5629088785046729, "grad_norm": 1.1134897470474243, "learning_rate": 8.456773525200922e-06, "loss": 0.6492, "step": 9637 }, { "epoch": 0.5629672897196262, "grad_norm": 0.9882503151893616, "learning_rate": 8.454904374240422e-06, "loss": 0.6897, "step": 9638 }, { "epoch": 0.5630257009345795, "grad_norm": 1.5530942678451538, "learning_rate": 8.453035278579906e-06, "loss": 0.7904, "step": 9639 }, { "epoch": 0.5630841121495327, "grad_norm": 1.1804386377334595, "learning_rate": 8.451166238286277e-06, "loss": 0.8309, "step": 9640 }, { "epoch": 0.563142523364486, "grad_norm": 1.4136426448822021, "learning_rate": 8.449297253426428e-06, "loss": 0.717, "step": 9641 }, { "epoch": 0.5632009345794392, "grad_norm": 2.33233904838562, "learning_rate": 8.447428324067245e-06, "loss": 0.8779, "step": 9642 }, { "epoch": 0.5632593457943925, "grad_norm": 1.1866732835769653, "learning_rate": 8.445559450275627e-06, "loss": 0.7452, "step": 9643 }, { "epoch": 0.5633177570093458, "grad_norm": 2.5132944583892822, "learning_rate": 8.443690632118458e-06, "loss": 0.9175, "step": 9644 }, { "epoch": 0.563376168224299, "grad_norm": 1.8649080991744995, "learning_rate": 8.441821869662622e-06, "loss": 0.8019, "step": 9645 }, { "epoch": 0.5634345794392523, "grad_norm": 1.4189924001693726, "learning_rate": 8.439953162975011e-06, "loss": 0.7412, "step": 9646 }, { "epoch": 0.5634929906542057, "grad_norm": 2.017146348953247, "learning_rate": 8.438084512122496e-06, "loss": 0.6432, "step": 9647 }, { "epoch": 0.5635514018691589, "grad_norm": 1.3248565196990967, "learning_rate": 8.436215917171968e-06, "loss": 0.7539, "step": 9648 }, { "epoch": 0.5636098130841122, "grad_norm": 1.3905380964279175, "learning_rate": 8.434347378190299e-06, "loss": 0.6434, "step": 9649 }, { "epoch": 0.5636682242990654, "grad_norm": 1.9788271188735962, "learning_rate": 8.432478895244364e-06, "loss": 0.7919, "step": 9650 }, { "epoch": 0.5637266355140187, "grad_norm": 1.8390029668807983, "learning_rate": 8.430610468401043e-06, "loss": 0.9209, "step": 9651 }, { "epoch": 0.563785046728972, "grad_norm": 1.3218389749526978, "learning_rate": 8.428742097727203e-06, "loss": 0.745, "step": 9652 }, { "epoch": 0.5638434579439252, "grad_norm": 1.8660155534744263, "learning_rate": 8.42687378328972e-06, "loss": 0.787, "step": 9653 }, { "epoch": 0.5639018691588785, "grad_norm": 1.908193588256836, "learning_rate": 8.425005525155459e-06, "loss": 0.929, "step": 9654 }, { "epoch": 0.5639602803738317, "grad_norm": 1.6316466331481934, "learning_rate": 8.423137323391282e-06, "loss": 0.7343, "step": 9655 }, { "epoch": 0.564018691588785, "grad_norm": 1.2515432834625244, "learning_rate": 8.421269178064058e-06, "loss": 0.7174, "step": 9656 }, { "epoch": 0.5640771028037384, "grad_norm": 2.438206911087036, "learning_rate": 8.419401089240646e-06, "loss": 0.8156, "step": 9657 }, { "epoch": 0.5641355140186916, "grad_norm": 1.2453818321228027, "learning_rate": 8.417533056987911e-06, "loss": 0.8315, "step": 9658 }, { "epoch": 0.5641939252336449, "grad_norm": 1.9318863153457642, "learning_rate": 8.415665081372713e-06, "loss": 0.7278, "step": 9659 }, { "epoch": 0.5642523364485982, "grad_norm": 1.132179617881775, "learning_rate": 8.413797162461896e-06, "loss": 0.7331, "step": 9660 }, { "epoch": 0.5643107476635514, "grad_norm": 1.4266360998153687, "learning_rate": 8.411929300322324e-06, "loss": 0.8099, "step": 9661 }, { "epoch": 0.5643691588785047, "grad_norm": 1.1954686641693115, "learning_rate": 8.410061495020846e-06, "loss": 0.7433, "step": 9662 }, { "epoch": 0.5644275700934579, "grad_norm": 1.9092358350753784, "learning_rate": 8.408193746624316e-06, "loss": 0.9456, "step": 9663 }, { "epoch": 0.5644859813084112, "grad_norm": 1.4948160648345947, "learning_rate": 8.406326055199576e-06, "loss": 0.8455, "step": 9664 }, { "epoch": 0.5645443925233645, "grad_norm": 1.0560222864151, "learning_rate": 8.404458420813472e-06, "loss": 0.6302, "step": 9665 }, { "epoch": 0.5646028037383177, "grad_norm": 2.0885543823242188, "learning_rate": 8.402590843532852e-06, "loss": 0.7649, "step": 9666 }, { "epoch": 0.564661214953271, "grad_norm": 1.3297978639602661, "learning_rate": 8.400723323424556e-06, "loss": 0.8938, "step": 9667 }, { "epoch": 0.5647196261682244, "grad_norm": 1.2963413000106812, "learning_rate": 8.398855860555425e-06, "loss": 0.8076, "step": 9668 }, { "epoch": 0.5647780373831776, "grad_norm": 1.5588656663894653, "learning_rate": 8.396988454992296e-06, "loss": 0.8117, "step": 9669 }, { "epoch": 0.5648364485981309, "grad_norm": 1.1135400533676147, "learning_rate": 8.395121106802e-06, "loss": 0.707, "step": 9670 }, { "epoch": 0.5648948598130841, "grad_norm": 1.06268310546875, "learning_rate": 8.393253816051382e-06, "loss": 0.8556, "step": 9671 }, { "epoch": 0.5649532710280374, "grad_norm": 1.6835607290267944, "learning_rate": 8.39138658280726e-06, "loss": 0.9197, "step": 9672 }, { "epoch": 0.5650116822429907, "grad_norm": 1.0328551530838013, "learning_rate": 8.389519407136471e-06, "loss": 0.7553, "step": 9673 }, { "epoch": 0.5650700934579439, "grad_norm": 1.1113337278366089, "learning_rate": 8.387652289105845e-06, "loss": 0.8138, "step": 9674 }, { "epoch": 0.5651285046728972, "grad_norm": 1.282770037651062, "learning_rate": 8.385785228782197e-06, "loss": 0.9273, "step": 9675 }, { "epoch": 0.5651869158878504, "grad_norm": 1.9143397808074951, "learning_rate": 8.383918226232363e-06, "loss": 0.8664, "step": 9676 }, { "epoch": 0.5652453271028037, "grad_norm": 1.8216087818145752, "learning_rate": 8.382051281523155e-06, "loss": 0.8072, "step": 9677 }, { "epoch": 0.565303738317757, "grad_norm": 1.6351017951965332, "learning_rate": 8.380184394721397e-06, "loss": 0.7513, "step": 9678 }, { "epoch": 0.5653621495327102, "grad_norm": 1.2995375394821167, "learning_rate": 8.378317565893907e-06, "loss": 0.9339, "step": 9679 }, { "epoch": 0.5654205607476636, "grad_norm": 1.27866792678833, "learning_rate": 8.376450795107493e-06, "loss": 0.7895, "step": 9680 }, { "epoch": 0.5654789719626169, "grad_norm": 1.4901257753372192, "learning_rate": 8.374584082428975e-06, "loss": 0.8664, "step": 9681 }, { "epoch": 0.5655373831775701, "grad_norm": 1.2838836908340454, "learning_rate": 8.372717427925158e-06, "loss": 0.757, "step": 9682 }, { "epoch": 0.5655957943925234, "grad_norm": 1.5805648565292358, "learning_rate": 8.370850831662858e-06, "loss": 0.8763, "step": 9683 }, { "epoch": 0.5656542056074766, "grad_norm": 1.331969141960144, "learning_rate": 8.36898429370888e-06, "loss": 0.8896, "step": 9684 }, { "epoch": 0.5657126168224299, "grad_norm": 1.325860857963562, "learning_rate": 8.367117814130022e-06, "loss": 0.7449, "step": 9685 }, { "epoch": 0.5657710280373832, "grad_norm": 1.4654532670974731, "learning_rate": 8.365251392993093e-06, "loss": 0.9117, "step": 9686 }, { "epoch": 0.5658294392523364, "grad_norm": 0.9160820245742798, "learning_rate": 8.363385030364889e-06, "loss": 0.7038, "step": 9687 }, { "epoch": 0.5658878504672897, "grad_norm": 1.2060350179672241, "learning_rate": 8.361518726312215e-06, "loss": 0.866, "step": 9688 }, { "epoch": 0.565946261682243, "grad_norm": 0.9799579381942749, "learning_rate": 8.35965248090186e-06, "loss": 0.6249, "step": 9689 }, { "epoch": 0.5660046728971962, "grad_norm": 0.9322496056556702, "learning_rate": 8.357786294200621e-06, "loss": 0.621, "step": 9690 }, { "epoch": 0.5660630841121496, "grad_norm": 1.1001524925231934, "learning_rate": 8.355920166275294e-06, "loss": 0.846, "step": 9691 }, { "epoch": 0.5661214953271028, "grad_norm": 1.160090684890747, "learning_rate": 8.35405409719266e-06, "loss": 0.6032, "step": 9692 }, { "epoch": 0.5661799065420561, "grad_norm": 1.171697974205017, "learning_rate": 8.352188087019516e-06, "loss": 0.6377, "step": 9693 }, { "epoch": 0.5662383177570094, "grad_norm": 1.142513394355774, "learning_rate": 8.350322135822645e-06, "loss": 0.6815, "step": 9694 }, { "epoch": 0.5662967289719626, "grad_norm": 1.182194709777832, "learning_rate": 8.348456243668825e-06, "loss": 0.8285, "step": 9695 }, { "epoch": 0.5663551401869159, "grad_norm": 1.3934168815612793, "learning_rate": 8.346590410624846e-06, "loss": 0.8067, "step": 9696 }, { "epoch": 0.5664135514018691, "grad_norm": 1.3322690725326538, "learning_rate": 8.344724636757481e-06, "loss": 0.8778, "step": 9697 }, { "epoch": 0.5664719626168224, "grad_norm": 1.0598760843276978, "learning_rate": 8.34285892213351e-06, "loss": 0.853, "step": 9698 }, { "epoch": 0.5665303738317757, "grad_norm": 1.2358829975128174, "learning_rate": 8.340993266819708e-06, "loss": 0.8062, "step": 9699 }, { "epoch": 0.5665887850467289, "grad_norm": 0.9645300507545471, "learning_rate": 8.339127670882846e-06, "loss": 0.7538, "step": 9700 }, { "epoch": 0.5666471962616823, "grad_norm": 1.3908658027648926, "learning_rate": 8.3372621343897e-06, "loss": 0.8202, "step": 9701 }, { "epoch": 0.5667056074766356, "grad_norm": 1.0524570941925049, "learning_rate": 8.335396657407035e-06, "loss": 0.8155, "step": 9702 }, { "epoch": 0.5667640186915888, "grad_norm": 1.7702983617782593, "learning_rate": 8.333531240001616e-06, "loss": 0.845, "step": 9703 }, { "epoch": 0.5668224299065421, "grad_norm": 1.1131384372711182, "learning_rate": 8.331665882240213e-06, "loss": 0.7594, "step": 9704 }, { "epoch": 0.5668808411214953, "grad_norm": 1.1237305402755737, "learning_rate": 8.32980058418958e-06, "loss": 0.7193, "step": 9705 }, { "epoch": 0.5669392523364486, "grad_norm": 1.2748725414276123, "learning_rate": 8.327935345916486e-06, "loss": 0.7625, "step": 9706 }, { "epoch": 0.5669976635514019, "grad_norm": 1.2861355543136597, "learning_rate": 8.326070167487688e-06, "loss": 0.8764, "step": 9707 }, { "epoch": 0.5670560747663551, "grad_norm": 1.008770227432251, "learning_rate": 8.324205048969932e-06, "loss": 0.8015, "step": 9708 }, { "epoch": 0.5671144859813084, "grad_norm": 1.590912938117981, "learning_rate": 8.322339990429984e-06, "loss": 0.7428, "step": 9709 }, { "epoch": 0.5671728971962616, "grad_norm": 1.2340400218963623, "learning_rate": 8.320474991934589e-06, "loss": 0.8001, "step": 9710 }, { "epoch": 0.5672313084112149, "grad_norm": 1.1811398267745972, "learning_rate": 8.318610053550498e-06, "loss": 0.7236, "step": 9711 }, { "epoch": 0.5672897196261683, "grad_norm": 1.250016450881958, "learning_rate": 8.316745175344462e-06, "loss": 0.792, "step": 9712 }, { "epoch": 0.5673481308411215, "grad_norm": 1.1759427785873413, "learning_rate": 8.314880357383218e-06, "loss": 0.7629, "step": 9713 }, { "epoch": 0.5674065420560748, "grad_norm": 1.2590501308441162, "learning_rate": 8.313015599733519e-06, "loss": 0.7572, "step": 9714 }, { "epoch": 0.5674649532710281, "grad_norm": 1.3713760375976562, "learning_rate": 8.311150902462096e-06, "loss": 0.8633, "step": 9715 }, { "epoch": 0.5675233644859813, "grad_norm": 1.0382524728775024, "learning_rate": 8.309286265635696e-06, "loss": 0.6169, "step": 9716 }, { "epoch": 0.5675817757009346, "grad_norm": 1.6848652362823486, "learning_rate": 8.307421689321054e-06, "loss": 0.8016, "step": 9717 }, { "epoch": 0.5676401869158878, "grad_norm": 1.1617218255996704, "learning_rate": 8.305557173584898e-06, "loss": 0.6695, "step": 9718 }, { "epoch": 0.5676985981308411, "grad_norm": 1.4280526638031006, "learning_rate": 8.303692718493967e-06, "loss": 0.8012, "step": 9719 }, { "epoch": 0.5677570093457944, "grad_norm": 1.5689481496810913, "learning_rate": 8.301828324114986e-06, "loss": 0.8988, "step": 9720 }, { "epoch": 0.5678154205607476, "grad_norm": 1.2621115446090698, "learning_rate": 8.299963990514693e-06, "loss": 0.7537, "step": 9721 }, { "epoch": 0.5678738317757009, "grad_norm": 1.578144907951355, "learning_rate": 8.298099717759802e-06, "loss": 0.7321, "step": 9722 }, { "epoch": 0.5679322429906543, "grad_norm": 1.6125208139419556, "learning_rate": 8.29623550591704e-06, "loss": 0.909, "step": 9723 }, { "epoch": 0.5679906542056075, "grad_norm": 0.9895500540733337, "learning_rate": 8.294371355053132e-06, "loss": 0.7184, "step": 9724 }, { "epoch": 0.5680490654205608, "grad_norm": 0.9327054619789124, "learning_rate": 8.292507265234791e-06, "loss": 0.667, "step": 9725 }, { "epoch": 0.568107476635514, "grad_norm": 1.2299286127090454, "learning_rate": 8.290643236528742e-06, "loss": 0.7141, "step": 9726 }, { "epoch": 0.5681658878504673, "grad_norm": 1.1777443885803223, "learning_rate": 8.288779269001694e-06, "loss": 0.8491, "step": 9727 }, { "epoch": 0.5682242990654206, "grad_norm": 1.250004529953003, "learning_rate": 8.28691536272036e-06, "loss": 0.7682, "step": 9728 }, { "epoch": 0.5682827102803738, "grad_norm": 1.9012638330459595, "learning_rate": 8.285051517751454e-06, "loss": 0.8132, "step": 9729 }, { "epoch": 0.5683411214953271, "grad_norm": 1.226068377494812, "learning_rate": 8.28318773416168e-06, "loss": 0.896, "step": 9730 }, { "epoch": 0.5683995327102803, "grad_norm": 1.2565858364105225, "learning_rate": 8.281324012017745e-06, "loss": 0.7596, "step": 9731 }, { "epoch": 0.5684579439252336, "grad_norm": 0.9261850714683533, "learning_rate": 8.279460351386356e-06, "loss": 0.7052, "step": 9732 }, { "epoch": 0.568516355140187, "grad_norm": 1.1113393306732178, "learning_rate": 8.277596752334209e-06, "loss": 0.724, "step": 9733 }, { "epoch": 0.5685747663551401, "grad_norm": 1.2927029132843018, "learning_rate": 8.275733214928012e-06, "loss": 0.7751, "step": 9734 }, { "epoch": 0.5686331775700935, "grad_norm": 1.17327880859375, "learning_rate": 8.27386973923445e-06, "loss": 0.8003, "step": 9735 }, { "epoch": 0.5686915887850468, "grad_norm": 1.189746379852295, "learning_rate": 8.27200632532023e-06, "loss": 0.7512, "step": 9736 }, { "epoch": 0.56875, "grad_norm": 1.066825270652771, "learning_rate": 8.270142973252041e-06, "loss": 0.7906, "step": 9737 }, { "epoch": 0.5688084112149533, "grad_norm": 1.4863874912261963, "learning_rate": 8.268279683096567e-06, "loss": 0.8376, "step": 9738 }, { "epoch": 0.5688668224299065, "grad_norm": 1.1355684995651245, "learning_rate": 8.266416454920505e-06, "loss": 0.7179, "step": 9739 }, { "epoch": 0.5689252336448598, "grad_norm": 1.17360258102417, "learning_rate": 8.264553288790537e-06, "loss": 0.6111, "step": 9740 }, { "epoch": 0.5689836448598131, "grad_norm": 1.1240673065185547, "learning_rate": 8.262690184773348e-06, "loss": 0.6158, "step": 9741 }, { "epoch": 0.5690420560747663, "grad_norm": 1.7927480936050415, "learning_rate": 8.260827142935622e-06, "loss": 0.8798, "step": 9742 }, { "epoch": 0.5691004672897196, "grad_norm": 1.58917236328125, "learning_rate": 8.258964163344032e-06, "loss": 0.7171, "step": 9743 }, { "epoch": 0.569158878504673, "grad_norm": 1.5800817012786865, "learning_rate": 8.257101246065262e-06, "loss": 0.7933, "step": 9744 }, { "epoch": 0.5692172897196262, "grad_norm": 1.3814104795455933, "learning_rate": 8.255238391165982e-06, "loss": 0.7884, "step": 9745 }, { "epoch": 0.5692757009345795, "grad_norm": 0.8444312810897827, "learning_rate": 8.253375598712872e-06, "loss": 0.6279, "step": 9746 }, { "epoch": 0.5693341121495327, "grad_norm": 1.1565723419189453, "learning_rate": 8.251512868772595e-06, "loss": 0.6459, "step": 9747 }, { "epoch": 0.569392523364486, "grad_norm": 1.125022053718567, "learning_rate": 8.24965020141182e-06, "loss": 0.774, "step": 9748 }, { "epoch": 0.5694509345794393, "grad_norm": 1.2745410203933716, "learning_rate": 8.247787596697217e-06, "loss": 0.8862, "step": 9749 }, { "epoch": 0.5695093457943925, "grad_norm": 1.5264027118682861, "learning_rate": 8.245925054695447e-06, "loss": 1.1922, "step": 9750 }, { "epoch": 0.5695677570093458, "grad_norm": 1.0256019830703735, "learning_rate": 8.244062575473177e-06, "loss": 0.8831, "step": 9751 }, { "epoch": 0.569626168224299, "grad_norm": 1.3363983631134033, "learning_rate": 8.242200159097057e-06, "loss": 0.7836, "step": 9752 }, { "epoch": 0.5696845794392523, "grad_norm": 1.3543978929519653, "learning_rate": 8.24033780563375e-06, "loss": 0.7999, "step": 9753 }, { "epoch": 0.5697429906542056, "grad_norm": 1.3111926317214966, "learning_rate": 8.238475515149913e-06, "loss": 0.8086, "step": 9754 }, { "epoch": 0.5698014018691588, "grad_norm": 1.0754661560058594, "learning_rate": 8.236613287712192e-06, "loss": 0.8974, "step": 9755 }, { "epoch": 0.5698598130841122, "grad_norm": 1.141433835029602, "learning_rate": 8.23475112338724e-06, "loss": 0.7988, "step": 9756 }, { "epoch": 0.5699182242990655, "grad_norm": 1.317179560661316, "learning_rate": 8.23288902224171e-06, "loss": 0.6306, "step": 9757 }, { "epoch": 0.5699766355140187, "grad_norm": 1.7685474157333374, "learning_rate": 8.23102698434224e-06, "loss": 0.8766, "step": 9758 }, { "epoch": 0.570035046728972, "grad_norm": 2.23343825340271, "learning_rate": 8.229165009755482e-06, "loss": 0.8237, "step": 9759 }, { "epoch": 0.5700934579439252, "grad_norm": 1.2400182485580444, "learning_rate": 8.22730309854807e-06, "loss": 0.8968, "step": 9760 }, { "epoch": 0.5701518691588785, "grad_norm": 1.4058802127838135, "learning_rate": 8.225441250786643e-06, "loss": 0.7181, "step": 9761 }, { "epoch": 0.5702102803738318, "grad_norm": 1.506976842880249, "learning_rate": 8.223579466537846e-06, "loss": 0.8107, "step": 9762 }, { "epoch": 0.570268691588785, "grad_norm": 1.7072129249572754, "learning_rate": 8.221717745868304e-06, "loss": 0.7105, "step": 9763 }, { "epoch": 0.5703271028037383, "grad_norm": 1.1155916452407837, "learning_rate": 8.219856088844653e-06, "loss": 0.8035, "step": 9764 }, { "epoch": 0.5703855140186916, "grad_norm": 0.8741880655288696, "learning_rate": 8.217994495533524e-06, "loss": 0.5677, "step": 9765 }, { "epoch": 0.5704439252336448, "grad_norm": 3.5622642040252686, "learning_rate": 8.216132966001542e-06, "loss": 0.923, "step": 9766 }, { "epoch": 0.5705023364485982, "grad_norm": 0.8661391735076904, "learning_rate": 8.21427150031534e-06, "loss": 0.7209, "step": 9767 }, { "epoch": 0.5705607476635514, "grad_norm": 3.259605646133423, "learning_rate": 8.212410098541528e-06, "loss": 0.7451, "step": 9768 }, { "epoch": 0.5706191588785047, "grad_norm": 2.2511308193206787, "learning_rate": 8.210548760746738e-06, "loss": 0.7444, "step": 9769 }, { "epoch": 0.570677570093458, "grad_norm": 1.375963568687439, "learning_rate": 8.208687486997586e-06, "loss": 0.7527, "step": 9770 }, { "epoch": 0.5707359813084112, "grad_norm": 2.506899356842041, "learning_rate": 8.206826277360681e-06, "loss": 0.9313, "step": 9771 }, { "epoch": 0.5707943925233645, "grad_norm": 1.13924241065979, "learning_rate": 8.204965131902645e-06, "loss": 0.5883, "step": 9772 }, { "epoch": 0.5708528037383177, "grad_norm": 1.4602162837982178, "learning_rate": 8.203104050690087e-06, "loss": 0.9554, "step": 9773 }, { "epoch": 0.570911214953271, "grad_norm": 2.3524904251098633, "learning_rate": 8.201243033789618e-06, "loss": 0.6468, "step": 9774 }, { "epoch": 0.5709696261682243, "grad_norm": 1.3738409280776978, "learning_rate": 8.199382081267845e-06, "loss": 0.8155, "step": 9775 }, { "epoch": 0.5710280373831775, "grad_norm": 1.0574744939804077, "learning_rate": 8.197521193191366e-06, "loss": 0.9864, "step": 9776 }, { "epoch": 0.5710864485981308, "grad_norm": 1.2121939659118652, "learning_rate": 8.195660369626792e-06, "loss": 0.6862, "step": 9777 }, { "epoch": 0.5711448598130842, "grad_norm": 1.9146733283996582, "learning_rate": 8.193799610640719e-06, "loss": 0.817, "step": 9778 }, { "epoch": 0.5712032710280374, "grad_norm": 1.0291965007781982, "learning_rate": 8.191938916299747e-06, "loss": 0.7829, "step": 9779 }, { "epoch": 0.5712616822429907, "grad_norm": 1.320197343826294, "learning_rate": 8.19007828667047e-06, "loss": 0.8981, "step": 9780 }, { "epoch": 0.5713200934579439, "grad_norm": 1.500165343284607, "learning_rate": 8.188217721819477e-06, "loss": 0.705, "step": 9781 }, { "epoch": 0.5713785046728972, "grad_norm": 1.2834340333938599, "learning_rate": 8.186357221813367e-06, "loss": 0.6951, "step": 9782 }, { "epoch": 0.5714369158878505, "grad_norm": 0.9960677027702332, "learning_rate": 8.184496786718721e-06, "loss": 0.5694, "step": 9783 }, { "epoch": 0.5714953271028037, "grad_norm": 1.1213455200195312, "learning_rate": 8.182636416602136e-06, "loss": 0.9062, "step": 9784 }, { "epoch": 0.571553738317757, "grad_norm": 1.9307093620300293, "learning_rate": 8.180776111530182e-06, "loss": 0.8434, "step": 9785 }, { "epoch": 0.5716121495327103, "grad_norm": 1.1910598278045654, "learning_rate": 8.178915871569449e-06, "loss": 0.6312, "step": 9786 }, { "epoch": 0.5716705607476635, "grad_norm": 1.2329933643341064, "learning_rate": 8.177055696786516e-06, "loss": 0.7798, "step": 9787 }, { "epoch": 0.5717289719626168, "grad_norm": 1.169169306755066, "learning_rate": 8.175195587247955e-06, "loss": 0.7641, "step": 9788 }, { "epoch": 0.57178738317757, "grad_norm": 1.2308343648910522, "learning_rate": 8.173335543020347e-06, "loss": 0.8819, "step": 9789 }, { "epoch": 0.5718457943925234, "grad_norm": 1.2640986442565918, "learning_rate": 8.17147556417026e-06, "loss": 0.7141, "step": 9790 }, { "epoch": 0.5719042056074767, "grad_norm": 1.171898603439331, "learning_rate": 8.169615650764261e-06, "loss": 0.8141, "step": 9791 }, { "epoch": 0.5719626168224299, "grad_norm": 1.112006425857544, "learning_rate": 8.167755802868927e-06, "loss": 0.8429, "step": 9792 }, { "epoch": 0.5720210280373832, "grad_norm": 1.5065749883651733, "learning_rate": 8.165896020550813e-06, "loss": 0.7897, "step": 9793 }, { "epoch": 0.5720794392523364, "grad_norm": 1.734416127204895, "learning_rate": 8.164036303876489e-06, "loss": 0.8702, "step": 9794 }, { "epoch": 0.5721378504672897, "grad_norm": 1.056820034980774, "learning_rate": 8.162176652912515e-06, "loss": 0.7033, "step": 9795 }, { "epoch": 0.572196261682243, "grad_norm": 1.138629674911499, "learning_rate": 8.160317067725443e-06, "loss": 0.5811, "step": 9796 }, { "epoch": 0.5722546728971962, "grad_norm": 1.67200767993927, "learning_rate": 8.158457548381834e-06, "loss": 0.7907, "step": 9797 }, { "epoch": 0.5723130841121495, "grad_norm": 1.238381028175354, "learning_rate": 8.156598094948238e-06, "loss": 0.9604, "step": 9798 }, { "epoch": 0.5723714953271029, "grad_norm": 1.4284254312515259, "learning_rate": 8.15473870749121e-06, "loss": 0.8281, "step": 9799 }, { "epoch": 0.572429906542056, "grad_norm": 1.1001299619674683, "learning_rate": 8.152879386077301e-06, "loss": 0.794, "step": 9800 }, { "epoch": 0.5724883177570094, "grad_norm": 1.29950749874115, "learning_rate": 8.151020130773048e-06, "loss": 0.7474, "step": 9801 }, { "epoch": 0.5725467289719626, "grad_norm": 0.9558237195014954, "learning_rate": 8.149160941645002e-06, "loss": 0.6363, "step": 9802 }, { "epoch": 0.5726051401869159, "grad_norm": 1.469680905342102, "learning_rate": 8.1473018187597e-06, "loss": 0.7869, "step": 9803 }, { "epoch": 0.5726635514018692, "grad_norm": 1.55867600440979, "learning_rate": 8.14544276218369e-06, "loss": 0.8552, "step": 9804 }, { "epoch": 0.5727219626168224, "grad_norm": 1.0159523487091064, "learning_rate": 8.143583771983502e-06, "loss": 0.7061, "step": 9805 }, { "epoch": 0.5727803738317757, "grad_norm": 1.4150257110595703, "learning_rate": 8.141724848225666e-06, "loss": 0.7652, "step": 9806 }, { "epoch": 0.572838785046729, "grad_norm": 1.7668431997299194, "learning_rate": 8.139865990976722e-06, "loss": 0.594, "step": 9807 }, { "epoch": 0.5728971962616822, "grad_norm": 1.2200945615768433, "learning_rate": 8.138007200303197e-06, "loss": 0.7872, "step": 9808 }, { "epoch": 0.5729556074766355, "grad_norm": 2.2631261348724365, "learning_rate": 8.136148476271623e-06, "loss": 0.9166, "step": 9809 }, { "epoch": 0.5730140186915887, "grad_norm": 1.3910936117172241, "learning_rate": 8.134289818948517e-06, "loss": 0.8654, "step": 9810 }, { "epoch": 0.5730724299065421, "grad_norm": 1.375931739807129, "learning_rate": 8.132431228400403e-06, "loss": 0.7452, "step": 9811 }, { "epoch": 0.5731308411214954, "grad_norm": 1.8484232425689697, "learning_rate": 8.130572704693807e-06, "loss": 0.8253, "step": 9812 }, { "epoch": 0.5731892523364486, "grad_norm": 1.137258768081665, "learning_rate": 8.128714247895241e-06, "loss": 0.7689, "step": 9813 }, { "epoch": 0.5732476635514019, "grad_norm": 1.1183048486709595, "learning_rate": 8.126855858071223e-06, "loss": 0.7046, "step": 9814 }, { "epoch": 0.5733060747663551, "grad_norm": 1.3799562454223633, "learning_rate": 8.124997535288266e-06, "loss": 0.7089, "step": 9815 }, { "epoch": 0.5733644859813084, "grad_norm": 1.267287254333496, "learning_rate": 8.123139279612878e-06, "loss": 0.7941, "step": 9816 }, { "epoch": 0.5734228971962617, "grad_norm": 1.204936146736145, "learning_rate": 8.121281091111573e-06, "loss": 0.8114, "step": 9817 }, { "epoch": 0.5734813084112149, "grad_norm": 1.165664792060852, "learning_rate": 8.119422969850852e-06, "loss": 0.6947, "step": 9818 }, { "epoch": 0.5735397196261682, "grad_norm": 1.1524701118469238, "learning_rate": 8.117564915897215e-06, "loss": 0.7808, "step": 9819 }, { "epoch": 0.5735981308411215, "grad_norm": 2.451915979385376, "learning_rate": 8.115706929317172e-06, "loss": 0.8, "step": 9820 }, { "epoch": 0.5736565420560747, "grad_norm": 1.426782488822937, "learning_rate": 8.113849010177215e-06, "loss": 0.8589, "step": 9821 }, { "epoch": 0.5737149532710281, "grad_norm": 1.2586283683776855, "learning_rate": 8.111991158543844e-06, "loss": 0.7012, "step": 9822 }, { "epoch": 0.5737733644859813, "grad_norm": 1.010333776473999, "learning_rate": 8.110133374483548e-06, "loss": 0.554, "step": 9823 }, { "epoch": 0.5738317757009346, "grad_norm": 1.690826416015625, "learning_rate": 8.108275658062822e-06, "loss": 0.8062, "step": 9824 }, { "epoch": 0.5738901869158879, "grad_norm": 1.2160823345184326, "learning_rate": 8.106418009348157e-06, "loss": 0.8124, "step": 9825 }, { "epoch": 0.5739485981308411, "grad_norm": 1.383010745048523, "learning_rate": 8.104560428406031e-06, "loss": 0.738, "step": 9826 }, { "epoch": 0.5740070093457944, "grad_norm": 1.619554042816162, "learning_rate": 8.102702915302937e-06, "loss": 0.7481, "step": 9827 }, { "epoch": 0.5740654205607477, "grad_norm": 1.8862059116363525, "learning_rate": 8.100845470105356e-06, "loss": 0.7856, "step": 9828 }, { "epoch": 0.5741238317757009, "grad_norm": 0.9692659974098206, "learning_rate": 8.09898809287976e-06, "loss": 0.6579, "step": 9829 }, { "epoch": 0.5741822429906542, "grad_norm": 2.2535786628723145, "learning_rate": 8.097130783692631e-06, "loss": 0.6698, "step": 9830 }, { "epoch": 0.5742406542056074, "grad_norm": 2.2782695293426514, "learning_rate": 8.095273542610442e-06, "loss": 0.8304, "step": 9831 }, { "epoch": 0.5742990654205608, "grad_norm": 0.986250638961792, "learning_rate": 8.093416369699666e-06, "loss": 0.5472, "step": 9832 }, { "epoch": 0.5743574766355141, "grad_norm": 2.3765907287597656, "learning_rate": 8.091559265026774e-06, "loss": 0.7503, "step": 9833 }, { "epoch": 0.5744158878504673, "grad_norm": 1.8526074886322021, "learning_rate": 8.089702228658227e-06, "loss": 0.8346, "step": 9834 }, { "epoch": 0.5744742990654206, "grad_norm": 1.2176074981689453, "learning_rate": 8.087845260660495e-06, "loss": 0.7266, "step": 9835 }, { "epoch": 0.5745327102803738, "grad_norm": 1.7171077728271484, "learning_rate": 8.085988361100036e-06, "loss": 0.7323, "step": 9836 }, { "epoch": 0.5745911214953271, "grad_norm": 2.6381075382232666, "learning_rate": 8.084131530043317e-06, "loss": 0.8708, "step": 9837 }, { "epoch": 0.5746495327102804, "grad_norm": 0.9912016987800598, "learning_rate": 8.082274767556789e-06, "loss": 0.7937, "step": 9838 }, { "epoch": 0.5747079439252336, "grad_norm": 2.0194177627563477, "learning_rate": 8.080418073706904e-06, "loss": 0.9153, "step": 9839 }, { "epoch": 0.5747663551401869, "grad_norm": 3.093491554260254, "learning_rate": 8.07856144856012e-06, "loss": 0.8355, "step": 9840 }, { "epoch": 0.5748247663551402, "grad_norm": 1.2103163003921509, "learning_rate": 8.076704892182884e-06, "loss": 0.8656, "step": 9841 }, { "epoch": 0.5748831775700934, "grad_norm": 1.9538427591323853, "learning_rate": 8.07484840464165e-06, "loss": 0.7181, "step": 9842 }, { "epoch": 0.5749415887850468, "grad_norm": 1.4613271951675415, "learning_rate": 8.072991986002854e-06, "loss": 0.7424, "step": 9843 }, { "epoch": 0.575, "grad_norm": 1.5610843896865845, "learning_rate": 8.071135636332938e-06, "loss": 0.8161, "step": 9844 }, { "epoch": 0.5750584112149533, "grad_norm": 1.3424344062805176, "learning_rate": 8.069279355698352e-06, "loss": 0.8294, "step": 9845 }, { "epoch": 0.5751168224299066, "grad_norm": 1.334346890449524, "learning_rate": 8.067423144165524e-06, "loss": 0.7647, "step": 9846 }, { "epoch": 0.5751752336448598, "grad_norm": 0.986473023891449, "learning_rate": 8.065567001800893e-06, "loss": 0.7198, "step": 9847 }, { "epoch": 0.5752336448598131, "grad_norm": 1.0862714052200317, "learning_rate": 8.063710928670892e-06, "loss": 0.6959, "step": 9848 }, { "epoch": 0.5752920560747663, "grad_norm": 2.0191004276275635, "learning_rate": 8.061854924841947e-06, "loss": 0.7898, "step": 9849 }, { "epoch": 0.5753504672897196, "grad_norm": 1.0146464109420776, "learning_rate": 8.059998990380494e-06, "loss": 0.7384, "step": 9850 }, { "epoch": 0.5754088785046729, "grad_norm": 1.7673923969268799, "learning_rate": 8.058143125352946e-06, "loss": 0.6933, "step": 9851 }, { "epoch": 0.5754672897196261, "grad_norm": 1.4403526782989502, "learning_rate": 8.056287329825736e-06, "loss": 0.8021, "step": 9852 }, { "epoch": 0.5755257009345794, "grad_norm": 1.5710434913635254, "learning_rate": 8.054431603865282e-06, "loss": 0.9792, "step": 9853 }, { "epoch": 0.5755841121495328, "grad_norm": 1.0817636251449585, "learning_rate": 8.052575947537997e-06, "loss": 0.7072, "step": 9854 }, { "epoch": 0.575642523364486, "grad_norm": 1.2308952808380127, "learning_rate": 8.050720360910302e-06, "loss": 0.764, "step": 9855 }, { "epoch": 0.5757009345794393, "grad_norm": 1.072183609008789, "learning_rate": 8.048864844048603e-06, "loss": 0.9074, "step": 9856 }, { "epoch": 0.5757593457943925, "grad_norm": 1.0638915300369263, "learning_rate": 8.047009397019317e-06, "loss": 0.6338, "step": 9857 }, { "epoch": 0.5758177570093458, "grad_norm": 1.5323667526245117, "learning_rate": 8.045154019888852e-06, "loss": 0.8461, "step": 9858 }, { "epoch": 0.5758761682242991, "grad_norm": 0.9248306155204773, "learning_rate": 8.043298712723604e-06, "loss": 0.6021, "step": 9859 }, { "epoch": 0.5759345794392523, "grad_norm": 1.3881142139434814, "learning_rate": 8.041443475589984e-06, "loss": 0.8364, "step": 9860 }, { "epoch": 0.5759929906542056, "grad_norm": 1.1308295726776123, "learning_rate": 8.039588308554388e-06, "loss": 0.7211, "step": 9861 }, { "epoch": 0.5760514018691589, "grad_norm": 0.9842379689216614, "learning_rate": 8.037733211683221e-06, "loss": 0.6803, "step": 9862 }, { "epoch": 0.5761098130841121, "grad_norm": 1.6704801321029663, "learning_rate": 8.035878185042869e-06, "loss": 0.7661, "step": 9863 }, { "epoch": 0.5761682242990654, "grad_norm": 1.5091065168380737, "learning_rate": 8.034023228699725e-06, "loss": 0.6947, "step": 9864 }, { "epoch": 0.5762266355140186, "grad_norm": 1.3549057245254517, "learning_rate": 8.032168342720186e-06, "loss": 0.6989, "step": 9865 }, { "epoch": 0.576285046728972, "grad_norm": 1.7161058187484741, "learning_rate": 8.030313527170634e-06, "loss": 0.8513, "step": 9866 }, { "epoch": 0.5763434579439253, "grad_norm": 1.6647080183029175, "learning_rate": 8.028458782117458e-06, "loss": 0.8439, "step": 9867 }, { "epoch": 0.5764018691588785, "grad_norm": 1.508805274963379, "learning_rate": 8.02660410762704e-06, "loss": 0.7651, "step": 9868 }, { "epoch": 0.5764602803738318, "grad_norm": 1.1989498138427734, "learning_rate": 8.024749503765754e-06, "loss": 0.6119, "step": 9869 }, { "epoch": 0.576518691588785, "grad_norm": 1.3549548387527466, "learning_rate": 8.022894970599987e-06, "loss": 0.7909, "step": 9870 }, { "epoch": 0.5765771028037383, "grad_norm": 1.3482029438018799, "learning_rate": 8.021040508196107e-06, "loss": 0.7807, "step": 9871 }, { "epoch": 0.5766355140186916, "grad_norm": 1.166180968284607, "learning_rate": 8.019186116620485e-06, "loss": 0.8722, "step": 9872 }, { "epoch": 0.5766939252336448, "grad_norm": 1.4721401929855347, "learning_rate": 8.017331795939496e-06, "loss": 0.7478, "step": 9873 }, { "epoch": 0.5767523364485981, "grad_norm": 2.2578208446502686, "learning_rate": 8.015477546219506e-06, "loss": 0.9421, "step": 9874 }, { "epoch": 0.5768107476635514, "grad_norm": 1.0575461387634277, "learning_rate": 8.013623367526883e-06, "loss": 0.8239, "step": 9875 }, { "epoch": 0.5768691588785047, "grad_norm": 1.524850606918335, "learning_rate": 8.011769259927981e-06, "loss": 0.9081, "step": 9876 }, { "epoch": 0.576927570093458, "grad_norm": 1.246951699256897, "learning_rate": 8.009915223489166e-06, "loss": 0.702, "step": 9877 }, { "epoch": 0.5769859813084112, "grad_norm": 1.1893941164016724, "learning_rate": 8.008061258276795e-06, "loss": 0.7423, "step": 9878 }, { "epoch": 0.5770443925233645, "grad_norm": 1.3599072694778442, "learning_rate": 8.00620736435722e-06, "loss": 0.8915, "step": 9879 }, { "epoch": 0.5771028037383178, "grad_norm": 1.1657932996749878, "learning_rate": 8.004353541796794e-06, "loss": 0.7796, "step": 9880 }, { "epoch": 0.577161214953271, "grad_norm": 1.1871578693389893, "learning_rate": 8.002499790661868e-06, "loss": 0.8039, "step": 9881 }, { "epoch": 0.5772196261682243, "grad_norm": 0.8722895979881287, "learning_rate": 8.000646111018786e-06, "loss": 0.6958, "step": 9882 }, { "epoch": 0.5772780373831776, "grad_norm": 1.3233757019042969, "learning_rate": 7.998792502933897e-06, "loss": 0.7566, "step": 9883 }, { "epoch": 0.5773364485981308, "grad_norm": 1.9233535528182983, "learning_rate": 7.996938966473538e-06, "loss": 0.9102, "step": 9884 }, { "epoch": 0.5773948598130841, "grad_norm": 1.1061784029006958, "learning_rate": 7.995085501704052e-06, "loss": 0.757, "step": 9885 }, { "epoch": 0.5774532710280373, "grad_norm": 1.2918064594268799, "learning_rate": 7.993232108691775e-06, "loss": 1.0094, "step": 9886 }, { "epoch": 0.5775116822429907, "grad_norm": 1.0780514478683472, "learning_rate": 7.991378787503037e-06, "loss": 0.7143, "step": 9887 }, { "epoch": 0.577570093457944, "grad_norm": 1.1171287298202515, "learning_rate": 7.989525538204174e-06, "loss": 0.8367, "step": 9888 }, { "epoch": 0.5776285046728972, "grad_norm": 1.6340926885604858, "learning_rate": 7.987672360861514e-06, "loss": 0.709, "step": 9889 }, { "epoch": 0.5776869158878505, "grad_norm": 1.1170247793197632, "learning_rate": 7.985819255541384e-06, "loss": 1.0218, "step": 9890 }, { "epoch": 0.5777453271028037, "grad_norm": 1.3606491088867188, "learning_rate": 7.98396622231011e-06, "loss": 0.8285, "step": 9891 }, { "epoch": 0.577803738317757, "grad_norm": 0.8787750005722046, "learning_rate": 7.982113261234005e-06, "loss": 0.608, "step": 9892 }, { "epoch": 0.5778621495327103, "grad_norm": 1.1548067331314087, "learning_rate": 7.980260372379397e-06, "loss": 0.855, "step": 9893 }, { "epoch": 0.5779205607476635, "grad_norm": 1.5524747371673584, "learning_rate": 7.978407555812594e-06, "loss": 0.9346, "step": 9894 }, { "epoch": 0.5779789719626168, "grad_norm": 3.6783828735351562, "learning_rate": 7.97655481159992e-06, "loss": 0.7378, "step": 9895 }, { "epoch": 0.5780373831775701, "grad_norm": 1.3256328105926514, "learning_rate": 7.974702139807676e-06, "loss": 0.8613, "step": 9896 }, { "epoch": 0.5780957943925233, "grad_norm": 1.0825393199920654, "learning_rate": 7.972849540502173e-06, "loss": 0.745, "step": 9897 }, { "epoch": 0.5781542056074767, "grad_norm": 1.2694803476333618, "learning_rate": 7.970997013749719e-06, "loss": 0.758, "step": 9898 }, { "epoch": 0.5782126168224299, "grad_norm": 1.4349679946899414, "learning_rate": 7.969144559616615e-06, "loss": 0.7855, "step": 9899 }, { "epoch": 0.5782710280373832, "grad_norm": 1.34511137008667, "learning_rate": 7.967292178169166e-06, "loss": 0.7226, "step": 9900 }, { "epoch": 0.5783294392523365, "grad_norm": 0.9981832504272461, "learning_rate": 7.965439869473664e-06, "loss": 0.7405, "step": 9901 }, { "epoch": 0.5783878504672897, "grad_norm": 1.1872026920318604, "learning_rate": 7.963587633596405e-06, "loss": 0.8422, "step": 9902 }, { "epoch": 0.578446261682243, "grad_norm": 1.0840305089950562, "learning_rate": 7.961735470603688e-06, "loss": 0.8244, "step": 9903 }, { "epoch": 0.5785046728971963, "grad_norm": 1.1266993284225464, "learning_rate": 7.959883380561793e-06, "loss": 0.8314, "step": 9904 }, { "epoch": 0.5785630841121495, "grad_norm": 0.953610360622406, "learning_rate": 7.958031363537019e-06, "loss": 0.6986, "step": 9905 }, { "epoch": 0.5786214953271028, "grad_norm": 1.0341311693191528, "learning_rate": 7.956179419595644e-06, "loss": 0.7132, "step": 9906 }, { "epoch": 0.578679906542056, "grad_norm": 1.1321380138397217, "learning_rate": 7.954327548803948e-06, "loss": 0.6816, "step": 9907 }, { "epoch": 0.5787383177570093, "grad_norm": 2.7961387634277344, "learning_rate": 7.952475751228217e-06, "loss": 0.7289, "step": 9908 }, { "epoch": 0.5787967289719627, "grad_norm": 1.0112148523330688, "learning_rate": 7.950624026934723e-06, "loss": 0.696, "step": 9909 }, { "epoch": 0.5788551401869159, "grad_norm": 1.2414394617080688, "learning_rate": 7.948772375989746e-06, "loss": 0.7571, "step": 9910 }, { "epoch": 0.5789135514018692, "grad_norm": 1.389899730682373, "learning_rate": 7.946920798459555e-06, "loss": 0.6768, "step": 9911 }, { "epoch": 0.5789719626168224, "grad_norm": 1.7521432638168335, "learning_rate": 7.945069294410412e-06, "loss": 0.8507, "step": 9912 }, { "epoch": 0.5790303738317757, "grad_norm": 1.4411368370056152, "learning_rate": 7.943217863908595e-06, "loss": 0.7829, "step": 9913 }, { "epoch": 0.579088785046729, "grad_norm": 1.54934823513031, "learning_rate": 7.94136650702036e-06, "loss": 0.8785, "step": 9914 }, { "epoch": 0.5791471962616822, "grad_norm": 1.9890090227127075, "learning_rate": 7.939515223811973e-06, "loss": 0.9202, "step": 9915 }, { "epoch": 0.5792056074766355, "grad_norm": 1.2037696838378906, "learning_rate": 7.937664014349694e-06, "loss": 0.9116, "step": 9916 }, { "epoch": 0.5792640186915888, "grad_norm": 1.6800535917282104, "learning_rate": 7.935812878699771e-06, "loss": 0.8802, "step": 9917 }, { "epoch": 0.579322429906542, "grad_norm": 0.9888423681259155, "learning_rate": 7.933961816928465e-06, "loss": 0.7262, "step": 9918 }, { "epoch": 0.5793808411214953, "grad_norm": 1.3195432424545288, "learning_rate": 7.932110829102023e-06, "loss": 0.6964, "step": 9919 }, { "epoch": 0.5794392523364486, "grad_norm": 1.2007883787155151, "learning_rate": 7.930259915286695e-06, "loss": 0.7193, "step": 9920 }, { "epoch": 0.5794976635514019, "grad_norm": 2.0660784244537354, "learning_rate": 7.928409075548727e-06, "loss": 0.7863, "step": 9921 }, { "epoch": 0.5795560747663552, "grad_norm": 1.2795515060424805, "learning_rate": 7.926558309954354e-06, "loss": 0.7129, "step": 9922 }, { "epoch": 0.5796144859813084, "grad_norm": 1.5115641355514526, "learning_rate": 7.92470761856983e-06, "loss": 0.775, "step": 9923 }, { "epoch": 0.5796728971962617, "grad_norm": 1.1564762592315674, "learning_rate": 7.922857001461378e-06, "loss": 0.858, "step": 9924 }, { "epoch": 0.579731308411215, "grad_norm": 1.0067275762557983, "learning_rate": 7.921006458695247e-06, "loss": 0.7908, "step": 9925 }, { "epoch": 0.5797897196261682, "grad_norm": 1.1129748821258545, "learning_rate": 7.919155990337656e-06, "loss": 0.7287, "step": 9926 }, { "epoch": 0.5798481308411215, "grad_norm": 2.285006523132324, "learning_rate": 7.917305596454841e-06, "loss": 0.7661, "step": 9927 }, { "epoch": 0.5799065420560747, "grad_norm": 1.2172281742095947, "learning_rate": 7.915455277113033e-06, "loss": 0.7348, "step": 9928 }, { "epoch": 0.579964953271028, "grad_norm": 1.3827927112579346, "learning_rate": 7.913605032378448e-06, "loss": 0.6592, "step": 9929 }, { "epoch": 0.5800233644859814, "grad_norm": 1.340563178062439, "learning_rate": 7.911754862317308e-06, "loss": 0.8279, "step": 9930 }, { "epoch": 0.5800817757009346, "grad_norm": 1.2976016998291016, "learning_rate": 7.909904766995838e-06, "loss": 0.8826, "step": 9931 }, { "epoch": 0.5801401869158879, "grad_norm": 1.1784254312515259, "learning_rate": 7.908054746480247e-06, "loss": 0.8108, "step": 9932 }, { "epoch": 0.5801985981308411, "grad_norm": 1.0485641956329346, "learning_rate": 7.906204800836758e-06, "loss": 0.7748, "step": 9933 }, { "epoch": 0.5802570093457944, "grad_norm": 1.3439855575561523, "learning_rate": 7.904354930131573e-06, "loss": 0.7679, "step": 9934 }, { "epoch": 0.5803154205607477, "grad_norm": 0.9741055965423584, "learning_rate": 7.9025051344309e-06, "loss": 0.6577, "step": 9935 }, { "epoch": 0.5803738317757009, "grad_norm": 0.927141010761261, "learning_rate": 7.900655413800952e-06, "loss": 0.7072, "step": 9936 }, { "epoch": 0.5804322429906542, "grad_norm": 1.4736714363098145, "learning_rate": 7.898805768307921e-06, "loss": 0.7875, "step": 9937 }, { "epoch": 0.5804906542056075, "grad_norm": 1.4469529390335083, "learning_rate": 7.89695619801802e-06, "loss": 0.818, "step": 9938 }, { "epoch": 0.5805490654205607, "grad_norm": 1.2995686531066895, "learning_rate": 7.895106702997437e-06, "loss": 0.8405, "step": 9939 }, { "epoch": 0.580607476635514, "grad_norm": 1.9643265008926392, "learning_rate": 7.893257283312367e-06, "loss": 0.8274, "step": 9940 }, { "epoch": 0.5806658878504672, "grad_norm": 1.1229560375213623, "learning_rate": 7.891407939029007e-06, "loss": 1.0542, "step": 9941 }, { "epoch": 0.5807242990654206, "grad_norm": 1.2613064050674438, "learning_rate": 7.88955867021354e-06, "loss": 0.8015, "step": 9942 }, { "epoch": 0.5807827102803739, "grad_norm": 0.9940507411956787, "learning_rate": 7.887709476932159e-06, "loss": 0.5626, "step": 9943 }, { "epoch": 0.5808411214953271, "grad_norm": 1.5402328968048096, "learning_rate": 7.885860359251046e-06, "loss": 0.9474, "step": 9944 }, { "epoch": 0.5808995327102804, "grad_norm": 1.277681589126587, "learning_rate": 7.884011317236376e-06, "loss": 0.8636, "step": 9945 }, { "epoch": 0.5809579439252337, "grad_norm": 1.589276671409607, "learning_rate": 7.882162350954336e-06, "loss": 0.772, "step": 9946 }, { "epoch": 0.5810163551401869, "grad_norm": 1.2949756383895874, "learning_rate": 7.880313460471093e-06, "loss": 0.8227, "step": 9947 }, { "epoch": 0.5810747663551402, "grad_norm": 1.6907655000686646, "learning_rate": 7.87846464585283e-06, "loss": 0.7891, "step": 9948 }, { "epoch": 0.5811331775700934, "grad_norm": 1.2429701089859009, "learning_rate": 7.876615907165713e-06, "loss": 0.8335, "step": 9949 }, { "epoch": 0.5811915887850467, "grad_norm": 1.096600890159607, "learning_rate": 7.874767244475905e-06, "loss": 0.7384, "step": 9950 }, { "epoch": 0.58125, "grad_norm": 1.2746162414550781, "learning_rate": 7.872918657849576e-06, "loss": 0.7289, "step": 9951 }, { "epoch": 0.5813084112149532, "grad_norm": 1.228395700454712, "learning_rate": 7.871070147352887e-06, "loss": 0.7139, "step": 9952 }, { "epoch": 0.5813668224299066, "grad_norm": 1.3416597843170166, "learning_rate": 7.869221713051998e-06, "loss": 0.9051, "step": 9953 }, { "epoch": 0.5814252336448598, "grad_norm": 2.266451120376587, "learning_rate": 7.867373355013065e-06, "loss": 0.787, "step": 9954 }, { "epoch": 0.5814836448598131, "grad_norm": 1.123001217842102, "learning_rate": 7.86552507330224e-06, "loss": 0.5689, "step": 9955 }, { "epoch": 0.5815420560747664, "grad_norm": 1.1024705171585083, "learning_rate": 7.863676867985676e-06, "loss": 0.6394, "step": 9956 }, { "epoch": 0.5816004672897196, "grad_norm": 1.5190362930297852, "learning_rate": 7.861828739129522e-06, "loss": 0.8459, "step": 9957 }, { "epoch": 0.5816588785046729, "grad_norm": 1.164832353591919, "learning_rate": 7.859980686799926e-06, "loss": 0.8464, "step": 9958 }, { "epoch": 0.5817172897196262, "grad_norm": 1.1847094297409058, "learning_rate": 7.858132711063027e-06, "loss": 0.7992, "step": 9959 }, { "epoch": 0.5817757009345794, "grad_norm": 1.5744614601135254, "learning_rate": 7.856284811984963e-06, "loss": 0.7568, "step": 9960 }, { "epoch": 0.5818341121495327, "grad_norm": 1.390045404434204, "learning_rate": 7.854436989631881e-06, "loss": 0.7891, "step": 9961 }, { "epoch": 0.5818925233644859, "grad_norm": 1.5555641651153564, "learning_rate": 7.852589244069903e-06, "loss": 0.8606, "step": 9962 }, { "epoch": 0.5819509345794392, "grad_norm": 1.2491661310195923, "learning_rate": 7.850741575365174e-06, "loss": 0.9093, "step": 9963 }, { "epoch": 0.5820093457943926, "grad_norm": 1.4898531436920166, "learning_rate": 7.848893983583816e-06, "loss": 0.7064, "step": 9964 }, { "epoch": 0.5820677570093458, "grad_norm": 1.258182168006897, "learning_rate": 7.847046468791952e-06, "loss": 0.7779, "step": 9965 }, { "epoch": 0.5821261682242991, "grad_norm": 1.0747442245483398, "learning_rate": 7.845199031055717e-06, "loss": 0.7751, "step": 9966 }, { "epoch": 0.5821845794392523, "grad_norm": 1.041451334953308, "learning_rate": 7.843351670441222e-06, "loss": 0.8358, "step": 9967 }, { "epoch": 0.5822429906542056, "grad_norm": 1.837639570236206, "learning_rate": 7.841504387014589e-06, "loss": 0.7975, "step": 9968 }, { "epoch": 0.5823014018691589, "grad_norm": 1.279107928276062, "learning_rate": 7.839657180841937e-06, "loss": 0.7246, "step": 9969 }, { "epoch": 0.5823598130841121, "grad_norm": 1.4119305610656738, "learning_rate": 7.837810051989367e-06, "loss": 0.7812, "step": 9970 }, { "epoch": 0.5824182242990654, "grad_norm": 1.0247306823730469, "learning_rate": 7.835963000523004e-06, "loss": 0.6283, "step": 9971 }, { "epoch": 0.5824766355140187, "grad_norm": 1.12039053440094, "learning_rate": 7.834116026508944e-06, "loss": 0.7594, "step": 9972 }, { "epoch": 0.5825350467289719, "grad_norm": 1.0460630655288696, "learning_rate": 7.832269130013298e-06, "loss": 0.7719, "step": 9973 }, { "epoch": 0.5825934579439253, "grad_norm": 1.4948145151138306, "learning_rate": 7.830422311102165e-06, "loss": 0.9103, "step": 9974 }, { "epoch": 0.5826518691588785, "grad_norm": 1.0267924070358276, "learning_rate": 7.82857556984164e-06, "loss": 0.7059, "step": 9975 }, { "epoch": 0.5827102803738318, "grad_norm": 1.195049524307251, "learning_rate": 7.826728906297827e-06, "loss": 0.6847, "step": 9976 }, { "epoch": 0.5827686915887851, "grad_norm": 0.9200957417488098, "learning_rate": 7.824882320536814e-06, "loss": 0.9322, "step": 9977 }, { "epoch": 0.5828271028037383, "grad_norm": 1.139096975326538, "learning_rate": 7.823035812624697e-06, "loss": 0.8041, "step": 9978 }, { "epoch": 0.5828855140186916, "grad_norm": 1.055128812789917, "learning_rate": 7.821189382627556e-06, "loss": 0.6023, "step": 9979 }, { "epoch": 0.5829439252336449, "grad_norm": 1.416806936264038, "learning_rate": 7.819343030611477e-06, "loss": 0.9618, "step": 9980 }, { "epoch": 0.5830023364485981, "grad_norm": 1.1889816522598267, "learning_rate": 7.817496756642548e-06, "loss": 0.7934, "step": 9981 }, { "epoch": 0.5830607476635514, "grad_norm": 1.1066703796386719, "learning_rate": 7.815650560786843e-06, "loss": 0.735, "step": 9982 }, { "epoch": 0.5831191588785046, "grad_norm": 0.8817917704582214, "learning_rate": 7.813804443110445e-06, "loss": 0.6509, "step": 9983 }, { "epoch": 0.5831775700934579, "grad_norm": 1.976987361907959, "learning_rate": 7.811958403679422e-06, "loss": 0.9269, "step": 9984 }, { "epoch": 0.5832359813084113, "grad_norm": 1.7282235622406006, "learning_rate": 7.810112442559842e-06, "loss": 0.9083, "step": 9985 }, { "epoch": 0.5832943925233645, "grad_norm": 1.237286925315857, "learning_rate": 7.808266559817783e-06, "loss": 0.6658, "step": 9986 }, { "epoch": 0.5833528037383178, "grad_norm": 0.8799169063568115, "learning_rate": 7.806420755519304e-06, "loss": 0.6011, "step": 9987 }, { "epoch": 0.583411214953271, "grad_norm": 1.4196981191635132, "learning_rate": 7.804575029730465e-06, "loss": 0.6736, "step": 9988 }, { "epoch": 0.5834696261682243, "grad_norm": 1.8448208570480347, "learning_rate": 7.802729382517331e-06, "loss": 0.7282, "step": 9989 }, { "epoch": 0.5835280373831776, "grad_norm": 1.3403548002243042, "learning_rate": 7.800883813945957e-06, "loss": 0.8023, "step": 9990 }, { "epoch": 0.5835864485981308, "grad_norm": 1.2875185012817383, "learning_rate": 7.7990383240824e-06, "loss": 0.8072, "step": 9991 }, { "epoch": 0.5836448598130841, "grad_norm": 1.2981643676757812, "learning_rate": 7.797192912992706e-06, "loss": 0.7502, "step": 9992 }, { "epoch": 0.5837032710280374, "grad_norm": 1.5147736072540283, "learning_rate": 7.795347580742924e-06, "loss": 0.9364, "step": 9993 }, { "epoch": 0.5837616822429906, "grad_norm": 1.389877200126648, "learning_rate": 7.793502327399108e-06, "loss": 0.747, "step": 9994 }, { "epoch": 0.583820093457944, "grad_norm": 1.2791640758514404, "learning_rate": 7.791657153027286e-06, "loss": 0.8067, "step": 9995 }, { "epoch": 0.5838785046728971, "grad_norm": 1.373252511024475, "learning_rate": 7.789812057693514e-06, "loss": 0.7768, "step": 9996 }, { "epoch": 0.5839369158878505, "grad_norm": 1.3709921836853027, "learning_rate": 7.787967041463818e-06, "loss": 0.8881, "step": 9997 }, { "epoch": 0.5839953271028038, "grad_norm": 1.3159674406051636, "learning_rate": 7.786122104404234e-06, "loss": 0.804, "step": 9998 }, { "epoch": 0.584053738317757, "grad_norm": 2.020728826522827, "learning_rate": 7.784277246580801e-06, "loss": 0.7523, "step": 9999 }, { "epoch": 0.5841121495327103, "grad_norm": 1.683758020401001, "learning_rate": 7.782432468059537e-06, "loss": 0.7798, "step": 10000 }, { "epoch": 0.5841705607476636, "grad_norm": 1.1382051706314087, "learning_rate": 7.780587768906476e-06, "loss": 0.7318, "step": 10001 }, { "epoch": 0.5842289719626168, "grad_norm": 1.444640040397644, "learning_rate": 7.77874314918764e-06, "loss": 0.7775, "step": 10002 }, { "epoch": 0.5842873831775701, "grad_norm": 1.5403778553009033, "learning_rate": 7.776898608969041e-06, "loss": 0.8985, "step": 10003 }, { "epoch": 0.5843457943925233, "grad_norm": 1.1641381978988647, "learning_rate": 7.775054148316708e-06, "loss": 0.7951, "step": 10004 }, { "epoch": 0.5844042056074766, "grad_norm": 2.184295654296875, "learning_rate": 7.773209767296647e-06, "loss": 0.8041, "step": 10005 }, { "epoch": 0.58446261682243, "grad_norm": 1.2415423393249512, "learning_rate": 7.771365465974873e-06, "loss": 0.6002, "step": 10006 }, { "epoch": 0.5845210280373832, "grad_norm": 1.7219150066375732, "learning_rate": 7.769521244417398e-06, "loss": 0.7125, "step": 10007 }, { "epoch": 0.5845794392523365, "grad_norm": 1.1268291473388672, "learning_rate": 7.767677102690221e-06, "loss": 0.7678, "step": 10008 }, { "epoch": 0.5846378504672897, "grad_norm": 1.4065393209457397, "learning_rate": 7.765833040859348e-06, "loss": 0.8135, "step": 10009 }, { "epoch": 0.584696261682243, "grad_norm": 1.5397402048110962, "learning_rate": 7.763989058990778e-06, "loss": 0.7001, "step": 10010 }, { "epoch": 0.5847546728971963, "grad_norm": 1.3375910520553589, "learning_rate": 7.762145157150515e-06, "loss": 0.8643, "step": 10011 }, { "epoch": 0.5848130841121495, "grad_norm": 1.206992745399475, "learning_rate": 7.760301335404546e-06, "loss": 0.918, "step": 10012 }, { "epoch": 0.5848714953271028, "grad_norm": 1.015589952468872, "learning_rate": 7.75845759381886e-06, "loss": 0.6518, "step": 10013 }, { "epoch": 0.5849299065420561, "grad_norm": 1.2698105573654175, "learning_rate": 7.756613932459456e-06, "loss": 0.9278, "step": 10014 }, { "epoch": 0.5849883177570093, "grad_norm": 1.7568674087524414, "learning_rate": 7.754770351392311e-06, "loss": 0.788, "step": 10015 }, { "epoch": 0.5850467289719626, "grad_norm": 0.9012470245361328, "learning_rate": 7.752926850683415e-06, "loss": 0.8657, "step": 10016 }, { "epoch": 0.5851051401869158, "grad_norm": 1.4033074378967285, "learning_rate": 7.751083430398743e-06, "loss": 0.9643, "step": 10017 }, { "epoch": 0.5851635514018692, "grad_norm": 1.1200132369995117, "learning_rate": 7.749240090604271e-06, "loss": 0.7126, "step": 10018 }, { "epoch": 0.5852219626168225, "grad_norm": 2.0260486602783203, "learning_rate": 7.747396831365982e-06, "loss": 0.8345, "step": 10019 }, { "epoch": 0.5852803738317757, "grad_norm": 1.0543595552444458, "learning_rate": 7.745553652749834e-06, "loss": 0.7084, "step": 10020 }, { "epoch": 0.585338785046729, "grad_norm": 1.140323519706726, "learning_rate": 7.74371055482181e-06, "loss": 0.7366, "step": 10021 }, { "epoch": 0.5853971962616823, "grad_norm": 4.6409687995910645, "learning_rate": 7.741867537647866e-06, "loss": 0.9045, "step": 10022 }, { "epoch": 0.5854556074766355, "grad_norm": 0.9832656979560852, "learning_rate": 7.740024601293966e-06, "loss": 0.6768, "step": 10023 }, { "epoch": 0.5855140186915888, "grad_norm": 1.15715754032135, "learning_rate": 7.738181745826076e-06, "loss": 0.671, "step": 10024 }, { "epoch": 0.585572429906542, "grad_norm": 1.3570294380187988, "learning_rate": 7.736338971310143e-06, "loss": 0.9781, "step": 10025 }, { "epoch": 0.5856308411214953, "grad_norm": 1.3944803476333618, "learning_rate": 7.734496277812129e-06, "loss": 0.7547, "step": 10026 }, { "epoch": 0.5856892523364486, "grad_norm": 1.11410391330719, "learning_rate": 7.732653665397985e-06, "loss": 0.7159, "step": 10027 }, { "epoch": 0.5857476635514018, "grad_norm": 1.7399766445159912, "learning_rate": 7.730811134133651e-06, "loss": 0.7136, "step": 10028 }, { "epoch": 0.5858060747663552, "grad_norm": 1.034000039100647, "learning_rate": 7.728968684085085e-06, "loss": 0.5876, "step": 10029 }, { "epoch": 0.5858644859813084, "grad_norm": 1.3205804824829102, "learning_rate": 7.72712631531822e-06, "loss": 0.7521, "step": 10030 }, { "epoch": 0.5859228971962617, "grad_norm": 2.761897325515747, "learning_rate": 7.725284027898999e-06, "loss": 1.0182, "step": 10031 }, { "epoch": 0.585981308411215, "grad_norm": 1.180128812789917, "learning_rate": 7.72344182189336e-06, "loss": 0.7798, "step": 10032 }, { "epoch": 0.5860397196261682, "grad_norm": 2.6661882400512695, "learning_rate": 7.721599697367233e-06, "loss": 0.8469, "step": 10033 }, { "epoch": 0.5860981308411215, "grad_norm": 1.3363723754882812, "learning_rate": 7.719757654386551e-06, "loss": 0.7939, "step": 10034 }, { "epoch": 0.5861565420560748, "grad_norm": 1.249321699142456, "learning_rate": 7.71791569301724e-06, "loss": 0.8159, "step": 10035 }, { "epoch": 0.586214953271028, "grad_norm": 1.3069350719451904, "learning_rate": 7.71607381332523e-06, "loss": 0.6874, "step": 10036 }, { "epoch": 0.5862733644859813, "grad_norm": 2.5861639976501465, "learning_rate": 7.714232015376442e-06, "loss": 0.7693, "step": 10037 }, { "epoch": 0.5863317757009345, "grad_norm": 1.291355013847351, "learning_rate": 7.712390299236788e-06, "loss": 0.7048, "step": 10038 }, { "epoch": 0.5863901869158878, "grad_norm": 3.2568447589874268, "learning_rate": 7.710548664972192e-06, "loss": 0.781, "step": 10039 }, { "epoch": 0.5864485981308412, "grad_norm": 1.4432332515716553, "learning_rate": 7.708707112648562e-06, "loss": 0.8931, "step": 10040 }, { "epoch": 0.5865070093457944, "grad_norm": 2.5976274013519287, "learning_rate": 7.706865642331816e-06, "loss": 0.7564, "step": 10041 }, { "epoch": 0.5865654205607477, "grad_norm": 2.615368366241455, "learning_rate": 7.705024254087853e-06, "loss": 0.8677, "step": 10042 }, { "epoch": 0.586623831775701, "grad_norm": 1.25969660282135, "learning_rate": 7.70318294798258e-06, "loss": 0.8823, "step": 10043 }, { "epoch": 0.5866822429906542, "grad_norm": 2.409297227859497, "learning_rate": 7.701341724081903e-06, "loss": 0.8067, "step": 10044 }, { "epoch": 0.5867406542056075, "grad_norm": 1.8632338047027588, "learning_rate": 7.699500582451716e-06, "loss": 0.8585, "step": 10045 }, { "epoch": 0.5867990654205607, "grad_norm": 1.329569697380066, "learning_rate": 7.697659523157911e-06, "loss": 0.894, "step": 10046 }, { "epoch": 0.586857476635514, "grad_norm": 1.7659603357315063, "learning_rate": 7.695818546266392e-06, "loss": 0.6969, "step": 10047 }, { "epoch": 0.5869158878504673, "grad_norm": 2.663494110107422, "learning_rate": 7.693977651843036e-06, "loss": 0.7556, "step": 10048 }, { "epoch": 0.5869742990654205, "grad_norm": 1.0049933195114136, "learning_rate": 7.692136839953743e-06, "loss": 0.6635, "step": 10049 }, { "epoch": 0.5870327102803738, "grad_norm": 1.8965681791305542, "learning_rate": 7.690296110664388e-06, "loss": 0.7904, "step": 10050 }, { "epoch": 0.587091121495327, "grad_norm": 1.977304458618164, "learning_rate": 7.688455464040849e-06, "loss": 0.8295, "step": 10051 }, { "epoch": 0.5871495327102804, "grad_norm": 1.1455937623977661, "learning_rate": 7.686614900149015e-06, "loss": 0.7139, "step": 10052 }, { "epoch": 0.5872079439252337, "grad_norm": 1.1369138956069946, "learning_rate": 7.684774419054748e-06, "loss": 0.6915, "step": 10053 }, { "epoch": 0.5872663551401869, "grad_norm": 1.4286121129989624, "learning_rate": 7.682934020823933e-06, "loss": 0.8671, "step": 10054 }, { "epoch": 0.5873247663551402, "grad_norm": 1.5007909536361694, "learning_rate": 7.681093705522432e-06, "loss": 0.7308, "step": 10055 }, { "epoch": 0.5873831775700935, "grad_norm": 1.0822736024856567, "learning_rate": 7.679253473216109e-06, "loss": 0.7041, "step": 10056 }, { "epoch": 0.5874415887850467, "grad_norm": 1.5644006729125977, "learning_rate": 7.677413323970833e-06, "loss": 0.9067, "step": 10057 }, { "epoch": 0.5875, "grad_norm": 0.9810904264450073, "learning_rate": 7.67557325785246e-06, "loss": 0.6852, "step": 10058 }, { "epoch": 0.5875584112149532, "grad_norm": 1.0797884464263916, "learning_rate": 7.673733274926848e-06, "loss": 0.763, "step": 10059 }, { "epoch": 0.5876168224299065, "grad_norm": 0.9205141663551331, "learning_rate": 7.671893375259854e-06, "loss": 0.642, "step": 10060 }, { "epoch": 0.5876752336448599, "grad_norm": 1.4140498638153076, "learning_rate": 7.670053558917322e-06, "loss": 0.8267, "step": 10061 }, { "epoch": 0.587733644859813, "grad_norm": 0.9960998296737671, "learning_rate": 7.668213825965111e-06, "loss": 0.7487, "step": 10062 }, { "epoch": 0.5877920560747664, "grad_norm": 1.100785493850708, "learning_rate": 7.666374176469054e-06, "loss": 0.8043, "step": 10063 }, { "epoch": 0.5878504672897197, "grad_norm": 1.5262737274169922, "learning_rate": 7.664534610495004e-06, "loss": 0.8544, "step": 10064 }, { "epoch": 0.5879088785046729, "grad_norm": 1.1146161556243896, "learning_rate": 7.662695128108798e-06, "loss": 0.6674, "step": 10065 }, { "epoch": 0.5879672897196262, "grad_norm": 1.1767061948776245, "learning_rate": 7.660855729376266e-06, "loss": 0.7187, "step": 10066 }, { "epoch": 0.5880257009345794, "grad_norm": 1.2175229787826538, "learning_rate": 7.659016414363247e-06, "loss": 0.8096, "step": 10067 }, { "epoch": 0.5880841121495327, "grad_norm": 1.2514324188232422, "learning_rate": 7.657177183135566e-06, "loss": 0.785, "step": 10068 }, { "epoch": 0.588142523364486, "grad_norm": 0.9119951128959656, "learning_rate": 7.65533803575906e-06, "loss": 0.642, "step": 10069 }, { "epoch": 0.5882009345794392, "grad_norm": 0.9363873600959778, "learning_rate": 7.653498972299545e-06, "loss": 0.7689, "step": 10070 }, { "epoch": 0.5882593457943925, "grad_norm": 0.9533019661903381, "learning_rate": 7.651659992822845e-06, "loss": 0.6711, "step": 10071 }, { "epoch": 0.5883177570093457, "grad_norm": 1.1358880996704102, "learning_rate": 7.649821097394776e-06, "loss": 0.7874, "step": 10072 }, { "epoch": 0.5883761682242991, "grad_norm": 1.4421106576919556, "learning_rate": 7.647982286081154e-06, "loss": 0.8906, "step": 10073 }, { "epoch": 0.5884345794392524, "grad_norm": 0.9912134408950806, "learning_rate": 7.646143558947798e-06, "loss": 0.6443, "step": 10074 }, { "epoch": 0.5884929906542056, "grad_norm": 1.2785459756851196, "learning_rate": 7.64430491606051e-06, "loss": 0.7371, "step": 10075 }, { "epoch": 0.5885514018691589, "grad_norm": 1.341278076171875, "learning_rate": 7.642466357485094e-06, "loss": 0.7392, "step": 10076 }, { "epoch": 0.5886098130841122, "grad_norm": 0.7601187825202942, "learning_rate": 7.640627883287363e-06, "loss": 0.6295, "step": 10077 }, { "epoch": 0.5886682242990654, "grad_norm": 1.7878835201263428, "learning_rate": 7.638789493533103e-06, "loss": 0.9012, "step": 10078 }, { "epoch": 0.5887266355140187, "grad_norm": 1.1158087253570557, "learning_rate": 7.636951188288129e-06, "loss": 0.6851, "step": 10079 }, { "epoch": 0.5887850467289719, "grad_norm": 1.489694356918335, "learning_rate": 7.635112967618221e-06, "loss": 0.7663, "step": 10080 }, { "epoch": 0.5888434579439252, "grad_norm": 1.2281386852264404, "learning_rate": 7.633274831589174e-06, "loss": 0.7718, "step": 10081 }, { "epoch": 0.5889018691588785, "grad_norm": 0.9450724720954895, "learning_rate": 7.63143678026678e-06, "loss": 0.7805, "step": 10082 }, { "epoch": 0.5889602803738317, "grad_norm": 1.7587509155273438, "learning_rate": 7.629598813716817e-06, "loss": 0.8511, "step": 10083 }, { "epoch": 0.5890186915887851, "grad_norm": 1.2490103244781494, "learning_rate": 7.627760932005074e-06, "loss": 0.7879, "step": 10084 }, { "epoch": 0.5890771028037384, "grad_norm": 1.0965884923934937, "learning_rate": 7.625923135197328e-06, "loss": 0.7149, "step": 10085 }, { "epoch": 0.5891355140186916, "grad_norm": 1.2134337425231934, "learning_rate": 7.624085423359348e-06, "loss": 0.8581, "step": 10086 }, { "epoch": 0.5891939252336449, "grad_norm": 1.634581446647644, "learning_rate": 7.6222477965569206e-06, "loss": 0.9432, "step": 10087 }, { "epoch": 0.5892523364485981, "grad_norm": 1.5049787759780884, "learning_rate": 7.620410254855803e-06, "loss": 0.879, "step": 10088 }, { "epoch": 0.5893107476635514, "grad_norm": 1.124642252922058, "learning_rate": 7.618572798321768e-06, "loss": 0.7686, "step": 10089 }, { "epoch": 0.5893691588785047, "grad_norm": 1.216667652130127, "learning_rate": 7.616735427020582e-06, "loss": 0.6816, "step": 10090 }, { "epoch": 0.5894275700934579, "grad_norm": 1.3687958717346191, "learning_rate": 7.6148981410179966e-06, "loss": 0.7923, "step": 10091 }, { "epoch": 0.5894859813084112, "grad_norm": 1.0582940578460693, "learning_rate": 7.6130609403797784e-06, "loss": 0.793, "step": 10092 }, { "epoch": 0.5895443925233644, "grad_norm": 1.9488120079040527, "learning_rate": 7.611223825171675e-06, "loss": 0.8539, "step": 10093 }, { "epoch": 0.5896028037383177, "grad_norm": 1.2504397630691528, "learning_rate": 7.609386795459445e-06, "loss": 0.7117, "step": 10094 }, { "epoch": 0.5896612149532711, "grad_norm": 1.3309696912765503, "learning_rate": 7.607549851308835e-06, "loss": 0.6455, "step": 10095 }, { "epoch": 0.5897196261682243, "grad_norm": 1.2697603702545166, "learning_rate": 7.6057129927855845e-06, "loss": 0.828, "step": 10096 }, { "epoch": 0.5897780373831776, "grad_norm": 1.0660486221313477, "learning_rate": 7.6038762199554426e-06, "loss": 0.8553, "step": 10097 }, { "epoch": 0.5898364485981309, "grad_norm": 1.4087992906570435, "learning_rate": 7.6020395328841474e-06, "loss": 0.798, "step": 10098 }, { "epoch": 0.5898948598130841, "grad_norm": 3.922429323196411, "learning_rate": 7.6002029316374315e-06, "loss": 0.7776, "step": 10099 }, { "epoch": 0.5899532710280374, "grad_norm": 0.9407634735107422, "learning_rate": 7.598366416281031e-06, "loss": 0.6953, "step": 10100 }, { "epoch": 0.5900116822429906, "grad_norm": 1.4624627828598022, "learning_rate": 7.5965299868806756e-06, "loss": 0.7219, "step": 10101 }, { "epoch": 0.5900700934579439, "grad_norm": 1.7891645431518555, "learning_rate": 7.5946936435020926e-06, "loss": 0.7887, "step": 10102 }, { "epoch": 0.5901285046728972, "grad_norm": 1.4634488821029663, "learning_rate": 7.592857386211008e-06, "loss": 0.9805, "step": 10103 }, { "epoch": 0.5901869158878504, "grad_norm": 1.1816462278366089, "learning_rate": 7.5910212150731364e-06, "loss": 0.8745, "step": 10104 }, { "epoch": 0.5902453271028038, "grad_norm": 1.06102454662323, "learning_rate": 7.589185130154202e-06, "loss": 0.688, "step": 10105 }, { "epoch": 0.590303738317757, "grad_norm": 1.337111473083496, "learning_rate": 7.587349131519913e-06, "loss": 0.8907, "step": 10106 }, { "epoch": 0.5903621495327103, "grad_norm": 1.2298043966293335, "learning_rate": 7.585513219235991e-06, "loss": 0.6968, "step": 10107 }, { "epoch": 0.5904205607476636, "grad_norm": 1.5833611488342285, "learning_rate": 7.583677393368136e-06, "loss": 1.0011, "step": 10108 }, { "epoch": 0.5904789719626168, "grad_norm": 1.0481584072113037, "learning_rate": 7.581841653982054e-06, "loss": 0.6984, "step": 10109 }, { "epoch": 0.5905373831775701, "grad_norm": 1.2323614358901978, "learning_rate": 7.580006001143452e-06, "loss": 0.823, "step": 10110 }, { "epoch": 0.5905957943925234, "grad_norm": 1.4134149551391602, "learning_rate": 7.578170434918021e-06, "loss": 0.9227, "step": 10111 }, { "epoch": 0.5906542056074766, "grad_norm": 1.1902472972869873, "learning_rate": 7.576334955371469e-06, "loss": 0.9288, "step": 10112 }, { "epoch": 0.5907126168224299, "grad_norm": 1.0976203680038452, "learning_rate": 7.57449956256948e-06, "loss": 0.6045, "step": 10113 }, { "epoch": 0.5907710280373831, "grad_norm": 1.509454369544983, "learning_rate": 7.5726642565777445e-06, "loss": 0.9618, "step": 10114 }, { "epoch": 0.5908294392523364, "grad_norm": 1.0753389596939087, "learning_rate": 7.5708290374619554e-06, "loss": 0.7429, "step": 10115 }, { "epoch": 0.5908878504672898, "grad_norm": 1.1176646947860718, "learning_rate": 7.568993905287788e-06, "loss": 0.9091, "step": 10116 }, { "epoch": 0.590946261682243, "grad_norm": 1.2289605140686035, "learning_rate": 7.56715886012093e-06, "loss": 0.7655, "step": 10117 }, { "epoch": 0.5910046728971963, "grad_norm": 1.9830142259597778, "learning_rate": 7.5653239020270575e-06, "loss": 0.8425, "step": 10118 }, { "epoch": 0.5910630841121496, "grad_norm": 0.9445739388465881, "learning_rate": 7.563489031071837e-06, "loss": 0.7031, "step": 10119 }, { "epoch": 0.5911214953271028, "grad_norm": 1.5722875595092773, "learning_rate": 7.561654247320953e-06, "loss": 0.8119, "step": 10120 }, { "epoch": 0.5911799065420561, "grad_norm": 1.5389975309371948, "learning_rate": 7.559819550840062e-06, "loss": 0.7808, "step": 10121 }, { "epoch": 0.5912383177570093, "grad_norm": 1.5522043704986572, "learning_rate": 7.557984941694836e-06, "loss": 0.8715, "step": 10122 }, { "epoch": 0.5912967289719626, "grad_norm": 1.106170415878296, "learning_rate": 7.556150419950936e-06, "loss": 0.8246, "step": 10123 }, { "epoch": 0.5913551401869159, "grad_norm": 1.2822364568710327, "learning_rate": 7.554315985674016e-06, "loss": 0.7629, "step": 10124 }, { "epoch": 0.5914135514018691, "grad_norm": 1.2841612100601196, "learning_rate": 7.552481638929736e-06, "loss": 0.7889, "step": 10125 }, { "epoch": 0.5914719626168224, "grad_norm": 1.4162005186080933, "learning_rate": 7.550647379783746e-06, "loss": 0.7723, "step": 10126 }, { "epoch": 0.5915303738317756, "grad_norm": 1.1582847833633423, "learning_rate": 7.5488132083017e-06, "loss": 0.6913, "step": 10127 }, { "epoch": 0.591588785046729, "grad_norm": 1.3987611532211304, "learning_rate": 7.5469791245492416e-06, "loss": 0.7822, "step": 10128 }, { "epoch": 0.5916471962616823, "grad_norm": 1.5308202505111694, "learning_rate": 7.545145128592009e-06, "loss": 0.9703, "step": 10129 }, { "epoch": 0.5917056074766355, "grad_norm": 1.0038419961929321, "learning_rate": 7.54331122049565e-06, "loss": 0.8178, "step": 10130 }, { "epoch": 0.5917640186915888, "grad_norm": 1.0329580307006836, "learning_rate": 7.541477400325794e-06, "loss": 0.8087, "step": 10131 }, { "epoch": 0.5918224299065421, "grad_norm": 1.2674239873886108, "learning_rate": 7.539643668148082e-06, "loss": 0.6504, "step": 10132 }, { "epoch": 0.5918808411214953, "grad_norm": 1.3659154176712036, "learning_rate": 7.53781002402814e-06, "loss": 0.7189, "step": 10133 }, { "epoch": 0.5919392523364486, "grad_norm": 1.1020350456237793, "learning_rate": 7.535976468031594e-06, "loss": 0.8937, "step": 10134 }, { "epoch": 0.5919976635514018, "grad_norm": 1.0618276596069336, "learning_rate": 7.534143000224072e-06, "loss": 0.6887, "step": 10135 }, { "epoch": 0.5920560747663551, "grad_norm": 1.023270606994629, "learning_rate": 7.532309620671192e-06, "loss": 0.7324, "step": 10136 }, { "epoch": 0.5921144859813084, "grad_norm": 1.3216357231140137, "learning_rate": 7.530476329438578e-06, "loss": 0.8864, "step": 10137 }, { "epoch": 0.5921728971962616, "grad_norm": 1.1838313341140747, "learning_rate": 7.528643126591836e-06, "loss": 0.76, "step": 10138 }, { "epoch": 0.592231308411215, "grad_norm": 1.132668137550354, "learning_rate": 7.52681001219658e-06, "loss": 0.7004, "step": 10139 }, { "epoch": 0.5922897196261683, "grad_norm": 1.1256887912750244, "learning_rate": 7.524976986318424e-06, "loss": 0.7548, "step": 10140 }, { "epoch": 0.5923481308411215, "grad_norm": 1.1240248680114746, "learning_rate": 7.523144049022966e-06, "loss": 0.7657, "step": 10141 }, { "epoch": 0.5924065420560748, "grad_norm": 1.0453368425369263, "learning_rate": 7.521311200375812e-06, "loss": 0.6853, "step": 10142 }, { "epoch": 0.592464953271028, "grad_norm": 1.9443182945251465, "learning_rate": 7.5194784404425615e-06, "loss": 1.0222, "step": 10143 }, { "epoch": 0.5925233644859813, "grad_norm": 1.0859754085540771, "learning_rate": 7.517645769288803e-06, "loss": 0.663, "step": 10144 }, { "epoch": 0.5925817757009346, "grad_norm": 3.270263910293579, "learning_rate": 7.515813186980141e-06, "loss": 0.8828, "step": 10145 }, { "epoch": 0.5926401869158878, "grad_norm": 1.5502957105636597, "learning_rate": 7.513980693582154e-06, "loss": 0.9081, "step": 10146 }, { "epoch": 0.5926985981308411, "grad_norm": 1.67817223072052, "learning_rate": 7.512148289160435e-06, "loss": 0.6679, "step": 10147 }, { "epoch": 0.5927570093457943, "grad_norm": 2.666477918624878, "learning_rate": 7.5103159737805656e-06, "loss": 0.9455, "step": 10148 }, { "epoch": 0.5928154205607477, "grad_norm": 1.5480746030807495, "learning_rate": 7.5084837475081205e-06, "loss": 0.9286, "step": 10149 }, { "epoch": 0.592873831775701, "grad_norm": 2.4078266620635986, "learning_rate": 7.506651610408684e-06, "loss": 0.713, "step": 10150 }, { "epoch": 0.5929322429906542, "grad_norm": 2.506316661834717, "learning_rate": 7.504819562547821e-06, "loss": 0.7759, "step": 10151 }, { "epoch": 0.5929906542056075, "grad_norm": 1.29348623752594, "learning_rate": 7.502987603991111e-06, "loss": 0.8671, "step": 10152 }, { "epoch": 0.5930490654205608, "grad_norm": 2.3162293434143066, "learning_rate": 7.501155734804117e-06, "loss": 0.8582, "step": 10153 }, { "epoch": 0.593107476635514, "grad_norm": 2.5650923252105713, "learning_rate": 7.4993239550524e-06, "loss": 0.7971, "step": 10154 }, { "epoch": 0.5931658878504673, "grad_norm": 1.4365017414093018, "learning_rate": 7.497492264801522e-06, "loss": 0.9536, "step": 10155 }, { "epoch": 0.5932242990654205, "grad_norm": 2.782646417617798, "learning_rate": 7.495660664117046e-06, "loss": 0.856, "step": 10156 }, { "epoch": 0.5932827102803738, "grad_norm": 1.318163514137268, "learning_rate": 7.493829153064517e-06, "loss": 0.6167, "step": 10157 }, { "epoch": 0.5933411214953271, "grad_norm": 1.1079739332199097, "learning_rate": 7.491997731709492e-06, "loss": 0.8322, "step": 10158 }, { "epoch": 0.5933995327102803, "grad_norm": 1.6081894636154175, "learning_rate": 7.490166400117515e-06, "loss": 0.6793, "step": 10159 }, { "epoch": 0.5934579439252337, "grad_norm": 1.8483754396438599, "learning_rate": 7.488335158354134e-06, "loss": 0.8381, "step": 10160 }, { "epoch": 0.593516355140187, "grad_norm": 1.3036646842956543, "learning_rate": 7.486504006484892e-06, "loss": 0.7242, "step": 10161 }, { "epoch": 0.5935747663551402, "grad_norm": 1.7407885789871216, "learning_rate": 7.4846729445753215e-06, "loss": 0.8891, "step": 10162 }, { "epoch": 0.5936331775700935, "grad_norm": 1.3262104988098145, "learning_rate": 7.48284197269096e-06, "loss": 0.767, "step": 10163 }, { "epoch": 0.5936915887850467, "grad_norm": 1.3866126537322998, "learning_rate": 7.4810110908973385e-06, "loss": 0.983, "step": 10164 }, { "epoch": 0.59375, "grad_norm": 1.5619267225265503, "learning_rate": 7.47918029925999e-06, "loss": 0.6587, "step": 10165 }, { "epoch": 0.5938084112149533, "grad_norm": 1.745530128479004, "learning_rate": 7.477349597844434e-06, "loss": 0.7673, "step": 10166 }, { "epoch": 0.5938668224299065, "grad_norm": 0.9044356942176819, "learning_rate": 7.475518986716193e-06, "loss": 0.6028, "step": 10167 }, { "epoch": 0.5939252336448598, "grad_norm": 1.2074896097183228, "learning_rate": 7.4736884659407894e-06, "loss": 0.7096, "step": 10168 }, { "epoch": 0.593983644859813, "grad_norm": 3.0247604846954346, "learning_rate": 7.471858035583734e-06, "loss": 0.8013, "step": 10169 }, { "epoch": 0.5940420560747663, "grad_norm": 1.7161314487457275, "learning_rate": 7.470027695710547e-06, "loss": 0.836, "step": 10170 }, { "epoch": 0.5941004672897197, "grad_norm": 1.5328255891799927, "learning_rate": 7.468197446386729e-06, "loss": 0.7315, "step": 10171 }, { "epoch": 0.5941588785046729, "grad_norm": 2.6179120540618896, "learning_rate": 7.466367287677788e-06, "loss": 0.7434, "step": 10172 }, { "epoch": 0.5942172897196262, "grad_norm": 1.0220133066177368, "learning_rate": 7.464537219649232e-06, "loss": 0.6063, "step": 10173 }, { "epoch": 0.5942757009345795, "grad_norm": 1.6127694845199585, "learning_rate": 7.462707242366551e-06, "loss": 0.8518, "step": 10174 }, { "epoch": 0.5943341121495327, "grad_norm": 2.1491196155548096, "learning_rate": 7.460877355895249e-06, "loss": 0.8153, "step": 10175 }, { "epoch": 0.594392523364486, "grad_norm": 0.9823739528656006, "learning_rate": 7.459047560300816e-06, "loss": 0.7764, "step": 10176 }, { "epoch": 0.5944509345794392, "grad_norm": 1.4005982875823975, "learning_rate": 7.457217855648737e-06, "loss": 0.8313, "step": 10177 }, { "epoch": 0.5945093457943925, "grad_norm": 1.5996201038360596, "learning_rate": 7.455388242004509e-06, "loss": 0.7294, "step": 10178 }, { "epoch": 0.5945677570093458, "grad_norm": 1.893427848815918, "learning_rate": 7.453558719433605e-06, "loss": 0.8747, "step": 10179 }, { "epoch": 0.594626168224299, "grad_norm": 1.2529364824295044, "learning_rate": 7.45172928800151e-06, "loss": 1.0178, "step": 10180 }, { "epoch": 0.5946845794392523, "grad_norm": 1.3010042905807495, "learning_rate": 7.449899947773702e-06, "loss": 0.7086, "step": 10181 }, { "epoch": 0.5947429906542057, "grad_norm": 2.095717191696167, "learning_rate": 7.448070698815647e-06, "loss": 0.6884, "step": 10182 }, { "epoch": 0.5948014018691589, "grad_norm": 1.6739412546157837, "learning_rate": 7.446241541192823e-06, "loss": 1.0183, "step": 10183 }, { "epoch": 0.5948598130841122, "grad_norm": 2.6252965927124023, "learning_rate": 7.444412474970688e-06, "loss": 0.7136, "step": 10184 }, { "epoch": 0.5949182242990654, "grad_norm": 2.3110735416412354, "learning_rate": 7.442583500214715e-06, "loss": 0.9805, "step": 10185 }, { "epoch": 0.5949766355140187, "grad_norm": 1.2910363674163818, "learning_rate": 7.440754616990363e-06, "loss": 0.8351, "step": 10186 }, { "epoch": 0.595035046728972, "grad_norm": 1.6945396661758423, "learning_rate": 7.4389258253630815e-06, "loss": 0.805, "step": 10187 }, { "epoch": 0.5950934579439252, "grad_norm": 1.8905245065689087, "learning_rate": 7.437097125398329e-06, "loss": 0.795, "step": 10188 }, { "epoch": 0.5951518691588785, "grad_norm": 1.390439510345459, "learning_rate": 7.435268517161556e-06, "loss": 0.5993, "step": 10189 }, { "epoch": 0.5952102803738317, "grad_norm": 1.0154467821121216, "learning_rate": 7.433440000718212e-06, "loss": 0.6838, "step": 10190 }, { "epoch": 0.595268691588785, "grad_norm": 1.4582598209381104, "learning_rate": 7.431611576133736e-06, "loss": 0.7359, "step": 10191 }, { "epoch": 0.5953271028037384, "grad_norm": 1.513686180114746, "learning_rate": 7.4297832434735675e-06, "loss": 0.7316, "step": 10192 }, { "epoch": 0.5953855140186916, "grad_norm": 0.952458381652832, "learning_rate": 7.42795500280315e-06, "loss": 0.7468, "step": 10193 }, { "epoch": 0.5954439252336449, "grad_norm": 1.7482668161392212, "learning_rate": 7.426126854187912e-06, "loss": 0.7448, "step": 10194 }, { "epoch": 0.5955023364485982, "grad_norm": 1.0296434164047241, "learning_rate": 7.42429879769329e-06, "loss": 0.6777, "step": 10195 }, { "epoch": 0.5955607476635514, "grad_norm": 1.2974804639816284, "learning_rate": 7.4224708333847055e-06, "loss": 0.7512, "step": 10196 }, { "epoch": 0.5956191588785047, "grad_norm": 1.7135659456253052, "learning_rate": 7.420642961327582e-06, "loss": 0.8899, "step": 10197 }, { "epoch": 0.5956775700934579, "grad_norm": 1.5993714332580566, "learning_rate": 7.418815181587347e-06, "loss": 0.7457, "step": 10198 }, { "epoch": 0.5957359813084112, "grad_norm": 1.528996229171753, "learning_rate": 7.4169874942294104e-06, "loss": 0.8074, "step": 10199 }, { "epoch": 0.5957943925233645, "grad_norm": 1.6120405197143555, "learning_rate": 7.415159899319191e-06, "loss": 0.7837, "step": 10200 }, { "epoch": 0.5958528037383177, "grad_norm": 1.8364191055297852, "learning_rate": 7.4133323969220996e-06, "loss": 0.7694, "step": 10201 }, { "epoch": 0.595911214953271, "grad_norm": 1.8889611959457397, "learning_rate": 7.411504987103539e-06, "loss": 0.9298, "step": 10202 }, { "epoch": 0.5959696261682244, "grad_norm": 1.165838599205017, "learning_rate": 7.409677669928923e-06, "loss": 0.7949, "step": 10203 }, { "epoch": 0.5960280373831776, "grad_norm": 0.8607756495475769, "learning_rate": 7.40785044546364e-06, "loss": 0.6227, "step": 10204 }, { "epoch": 0.5960864485981309, "grad_norm": 1.624319314956665, "learning_rate": 7.406023313773097e-06, "loss": 0.8794, "step": 10205 }, { "epoch": 0.5961448598130841, "grad_norm": 2.08327054977417, "learning_rate": 7.404196274922688e-06, "loss": 0.7932, "step": 10206 }, { "epoch": 0.5962032710280374, "grad_norm": 1.4407098293304443, "learning_rate": 7.402369328977796e-06, "loss": 0.772, "step": 10207 }, { "epoch": 0.5962616822429907, "grad_norm": 1.3342608213424683, "learning_rate": 7.400542476003816e-06, "loss": 0.6542, "step": 10208 }, { "epoch": 0.5963200934579439, "grad_norm": 2.313849449157715, "learning_rate": 7.398715716066127e-06, "loss": 0.9715, "step": 10209 }, { "epoch": 0.5963785046728972, "grad_norm": 1.5328298807144165, "learning_rate": 7.396889049230116e-06, "loss": 0.8082, "step": 10210 }, { "epoch": 0.5964369158878504, "grad_norm": 1.535183072090149, "learning_rate": 7.39506247556116e-06, "loss": 0.6767, "step": 10211 }, { "epoch": 0.5964953271028037, "grad_norm": 1.6572291851043701, "learning_rate": 7.393235995124626e-06, "loss": 0.8304, "step": 10212 }, { "epoch": 0.596553738317757, "grad_norm": 1.0904377698898315, "learning_rate": 7.391409607985891e-06, "loss": 0.7486, "step": 10213 }, { "epoch": 0.5966121495327102, "grad_norm": 1.4129446744918823, "learning_rate": 7.389583314210325e-06, "loss": 0.9062, "step": 10214 }, { "epoch": 0.5966705607476636, "grad_norm": 1.2500100135803223, "learning_rate": 7.387757113863283e-06, "loss": 0.7475, "step": 10215 }, { "epoch": 0.5967289719626169, "grad_norm": 0.9424556493759155, "learning_rate": 7.385931007010134e-06, "loss": 0.6708, "step": 10216 }, { "epoch": 0.5967873831775701, "grad_norm": 0.998334527015686, "learning_rate": 7.384104993716232e-06, "loss": 0.7485, "step": 10217 }, { "epoch": 0.5968457943925234, "grad_norm": 1.325575351715088, "learning_rate": 7.382279074046933e-06, "loss": 0.8355, "step": 10218 }, { "epoch": 0.5969042056074766, "grad_norm": 1.0962061882019043, "learning_rate": 7.3804532480675895e-06, "loss": 0.6241, "step": 10219 }, { "epoch": 0.5969626168224299, "grad_norm": 1.136783242225647, "learning_rate": 7.378627515843543e-06, "loss": 0.8555, "step": 10220 }, { "epoch": 0.5970210280373832, "grad_norm": 1.2375553846359253, "learning_rate": 7.376801877440143e-06, "loss": 0.7576, "step": 10221 }, { "epoch": 0.5970794392523364, "grad_norm": 1.3117022514343262, "learning_rate": 7.374976332922726e-06, "loss": 0.8115, "step": 10222 }, { "epoch": 0.5971378504672897, "grad_norm": 0.9067711234092712, "learning_rate": 7.373150882356637e-06, "loss": 0.6447, "step": 10223 }, { "epoch": 0.597196261682243, "grad_norm": 1.1644470691680908, "learning_rate": 7.371325525807202e-06, "loss": 0.8651, "step": 10224 }, { "epoch": 0.5972546728971962, "grad_norm": 1.3658312559127808, "learning_rate": 7.369500263339755e-06, "loss": 0.7543, "step": 10225 }, { "epoch": 0.5973130841121496, "grad_norm": 0.967600405216217, "learning_rate": 7.367675095019623e-06, "loss": 0.6723, "step": 10226 }, { "epoch": 0.5973714953271028, "grad_norm": 1.2035841941833496, "learning_rate": 7.365850020912129e-06, "loss": 0.7363, "step": 10227 }, { "epoch": 0.5974299065420561, "grad_norm": 0.9232385754585266, "learning_rate": 7.364025041082598e-06, "loss": 0.77, "step": 10228 }, { "epoch": 0.5974883177570094, "grad_norm": 1.1202094554901123, "learning_rate": 7.362200155596344e-06, "loss": 0.7316, "step": 10229 }, { "epoch": 0.5975467289719626, "grad_norm": 1.134010672569275, "learning_rate": 7.360375364518677e-06, "loss": 0.8032, "step": 10230 }, { "epoch": 0.5976051401869159, "grad_norm": 1.6749950647354126, "learning_rate": 7.358550667914915e-06, "loss": 0.8387, "step": 10231 }, { "epoch": 0.5976635514018691, "grad_norm": 1.6678098440170288, "learning_rate": 7.356726065850358e-06, "loss": 0.807, "step": 10232 }, { "epoch": 0.5977219626168224, "grad_norm": 1.6874282360076904, "learning_rate": 7.354901558390315e-06, "loss": 0.9221, "step": 10233 }, { "epoch": 0.5977803738317757, "grad_norm": 1.7357761859893799, "learning_rate": 7.353077145600085e-06, "loss": 0.8783, "step": 10234 }, { "epoch": 0.5978387850467289, "grad_norm": 1.2695139646530151, "learning_rate": 7.351252827544961e-06, "loss": 0.8242, "step": 10235 }, { "epoch": 0.5978971962616823, "grad_norm": 1.2924602031707764, "learning_rate": 7.3494286042902455e-06, "loss": 0.7638, "step": 10236 }, { "epoch": 0.5979556074766356, "grad_norm": 1.181280255317688, "learning_rate": 7.347604475901218e-06, "loss": 0.6818, "step": 10237 }, { "epoch": 0.5980140186915888, "grad_norm": 4.523761749267578, "learning_rate": 7.345780442443174e-06, "loss": 0.682, "step": 10238 }, { "epoch": 0.5980724299065421, "grad_norm": 1.4139032363891602, "learning_rate": 7.343956503981393e-06, "loss": 0.9637, "step": 10239 }, { "epoch": 0.5981308411214953, "grad_norm": 1.0103907585144043, "learning_rate": 7.342132660581152e-06, "loss": 0.7251, "step": 10240 }, { "epoch": 0.5981892523364486, "grad_norm": 1.1977956295013428, "learning_rate": 7.340308912307732e-06, "loss": 0.8336, "step": 10241 }, { "epoch": 0.5982476635514019, "grad_norm": 1.0679036378860474, "learning_rate": 7.3384852592264036e-06, "loss": 0.7764, "step": 10242 }, { "epoch": 0.5983060747663551, "grad_norm": 1.192175030708313, "learning_rate": 7.336661701402439e-06, "loss": 0.7343, "step": 10243 }, { "epoch": 0.5983644859813084, "grad_norm": 0.9949758052825928, "learning_rate": 7.334838238901106e-06, "loss": 0.6309, "step": 10244 }, { "epoch": 0.5984228971962616, "grad_norm": 1.2374825477600098, "learning_rate": 7.33301487178766e-06, "loss": 0.6185, "step": 10245 }, { "epoch": 0.5984813084112149, "grad_norm": 1.5672699213027954, "learning_rate": 7.331191600127369e-06, "loss": 0.8889, "step": 10246 }, { "epoch": 0.5985397196261683, "grad_norm": 1.0675908327102661, "learning_rate": 7.329368423985481e-06, "loss": 0.6073, "step": 10247 }, { "epoch": 0.5985981308411215, "grad_norm": 1.6318405866622925, "learning_rate": 7.32754534342726e-06, "loss": 0.8773, "step": 10248 }, { "epoch": 0.5986565420560748, "grad_norm": 1.3886655569076538, "learning_rate": 7.325722358517944e-06, "loss": 0.7169, "step": 10249 }, { "epoch": 0.5987149532710281, "grad_norm": 1.7172731161117554, "learning_rate": 7.323899469322781e-06, "loss": 0.7577, "step": 10250 }, { "epoch": 0.5987733644859813, "grad_norm": 0.9093917012214661, "learning_rate": 7.32207667590702e-06, "loss": 0.6831, "step": 10251 }, { "epoch": 0.5988317757009346, "grad_norm": 1.3400118350982666, "learning_rate": 7.3202539783358915e-06, "loss": 0.7963, "step": 10252 }, { "epoch": 0.5988901869158878, "grad_norm": 1.0810561180114746, "learning_rate": 7.318431376674639e-06, "loss": 0.7059, "step": 10253 }, { "epoch": 0.5989485981308411, "grad_norm": 2.0964550971984863, "learning_rate": 7.31660887098849e-06, "loss": 0.8329, "step": 10254 }, { "epoch": 0.5990070093457944, "grad_norm": 1.2723644971847534, "learning_rate": 7.314786461342671e-06, "loss": 0.824, "step": 10255 }, { "epoch": 0.5990654205607476, "grad_norm": 2.4226233959198, "learning_rate": 7.312964147802415e-06, "loss": 0.983, "step": 10256 }, { "epoch": 0.5991238317757009, "grad_norm": 1.5660326480865479, "learning_rate": 7.311141930432933e-06, "loss": 0.9265, "step": 10257 }, { "epoch": 0.5991822429906543, "grad_norm": 2.1116528511047363, "learning_rate": 7.309319809299453e-06, "loss": 0.8009, "step": 10258 }, { "epoch": 0.5992406542056075, "grad_norm": 1.1546863317489624, "learning_rate": 7.307497784467186e-06, "loss": 0.6413, "step": 10259 }, { "epoch": 0.5992990654205608, "grad_norm": 1.2055919170379639, "learning_rate": 7.30567585600134e-06, "loss": 0.7534, "step": 10260 }, { "epoch": 0.599357476635514, "grad_norm": 1.5464158058166504, "learning_rate": 7.3038540239671315e-06, "loss": 1.0166, "step": 10261 }, { "epoch": 0.5994158878504673, "grad_norm": 1.3498401641845703, "learning_rate": 7.3020322884297565e-06, "loss": 0.9102, "step": 10262 }, { "epoch": 0.5994742990654206, "grad_norm": 1.251434326171875, "learning_rate": 7.300210649454422e-06, "loss": 0.6715, "step": 10263 }, { "epoch": 0.5995327102803738, "grad_norm": 1.619456171989441, "learning_rate": 7.298389107106327e-06, "loss": 0.8302, "step": 10264 }, { "epoch": 0.5995911214953271, "grad_norm": 1.0316208600997925, "learning_rate": 7.296567661450656e-06, "loss": 0.7355, "step": 10265 }, { "epoch": 0.5996495327102803, "grad_norm": 1.448004961013794, "learning_rate": 7.2947463125526095e-06, "loss": 0.8147, "step": 10266 }, { "epoch": 0.5997079439252336, "grad_norm": 1.2825325727462769, "learning_rate": 7.292925060477367e-06, "loss": 0.6555, "step": 10267 }, { "epoch": 0.599766355140187, "grad_norm": 1.4969511032104492, "learning_rate": 7.29110390529012e-06, "loss": 0.919, "step": 10268 }, { "epoch": 0.5998247663551401, "grad_norm": 1.06724214553833, "learning_rate": 7.289282847056047e-06, "loss": 0.6815, "step": 10269 }, { "epoch": 0.5998831775700935, "grad_norm": 1.0889948606491089, "learning_rate": 7.28746188584032e-06, "loss": 0.6942, "step": 10270 }, { "epoch": 0.5999415887850468, "grad_norm": 1.3930535316467285, "learning_rate": 7.285641021708118e-06, "loss": 0.842, "step": 10271 }, { "epoch": 0.6, "grad_norm": 1.3894473314285278, "learning_rate": 7.283820254724609e-06, "loss": 0.6989, "step": 10272 }, { "epoch": 0.6000584112149533, "grad_norm": 1.753485083580017, "learning_rate": 7.281999584954955e-06, "loss": 0.7649, "step": 10273 }, { "epoch": 0.6001168224299065, "grad_norm": 1.0342713594436646, "learning_rate": 7.2801790124643255e-06, "loss": 0.7386, "step": 10274 }, { "epoch": 0.6001752336448598, "grad_norm": 1.612730622291565, "learning_rate": 7.2783585373178765e-06, "loss": 0.8862, "step": 10275 }, { "epoch": 0.6002336448598131, "grad_norm": 0.9715995788574219, "learning_rate": 7.276538159580766e-06, "loss": 0.7491, "step": 10276 }, { "epoch": 0.6002920560747663, "grad_norm": 1.2529923915863037, "learning_rate": 7.2747178793181474e-06, "loss": 0.8232, "step": 10277 }, { "epoch": 0.6003504672897196, "grad_norm": 1.1423473358154297, "learning_rate": 7.272897696595165e-06, "loss": 0.7515, "step": 10278 }, { "epoch": 0.600408878504673, "grad_norm": 1.513580322265625, "learning_rate": 7.271077611476967e-06, "loss": 0.8275, "step": 10279 }, { "epoch": 0.6004672897196262, "grad_norm": 1.2918000221252441, "learning_rate": 7.2692576240286945e-06, "loss": 0.7206, "step": 10280 }, { "epoch": 0.6005257009345795, "grad_norm": 1.0674738883972168, "learning_rate": 7.267437734315493e-06, "loss": 0.8474, "step": 10281 }, { "epoch": 0.6005841121495327, "grad_norm": 1.1536891460418701, "learning_rate": 7.265617942402488e-06, "loss": 0.6122, "step": 10282 }, { "epoch": 0.600642523364486, "grad_norm": 2.026590585708618, "learning_rate": 7.263798248354812e-06, "loss": 0.8678, "step": 10283 }, { "epoch": 0.6007009345794393, "grad_norm": 0.9775304794311523, "learning_rate": 7.261978652237598e-06, "loss": 0.7922, "step": 10284 }, { "epoch": 0.6007593457943925, "grad_norm": 1.1377595663070679, "learning_rate": 7.260159154115967e-06, "loss": 0.7266, "step": 10285 }, { "epoch": 0.6008177570093458, "grad_norm": 2.0888636112213135, "learning_rate": 7.258339754055045e-06, "loss": 0.7891, "step": 10286 }, { "epoch": 0.600876168224299, "grad_norm": 1.3351664543151855, "learning_rate": 7.256520452119944e-06, "loss": 0.7435, "step": 10287 }, { "epoch": 0.6009345794392523, "grad_norm": 1.6024876832962036, "learning_rate": 7.254701248375777e-06, "loss": 0.7695, "step": 10288 }, { "epoch": 0.6009929906542056, "grad_norm": 1.340495228767395, "learning_rate": 7.252882142887663e-06, "loss": 0.7405, "step": 10289 }, { "epoch": 0.6010514018691588, "grad_norm": 1.3720204830169678, "learning_rate": 7.251063135720699e-06, "loss": 0.8492, "step": 10290 }, { "epoch": 0.6011098130841122, "grad_norm": 2.0923380851745605, "learning_rate": 7.249244226939994e-06, "loss": 1.0341, "step": 10291 }, { "epoch": 0.6011682242990655, "grad_norm": 3.2033627033233643, "learning_rate": 7.247425416610647e-06, "loss": 0.959, "step": 10292 }, { "epoch": 0.6012266355140187, "grad_norm": 1.4534528255462646, "learning_rate": 7.245606704797754e-06, "loss": 0.7055, "step": 10293 }, { "epoch": 0.601285046728972, "grad_norm": 1.3784081935882568, "learning_rate": 7.24378809156641e-06, "loss": 0.6966, "step": 10294 }, { "epoch": 0.6013434579439252, "grad_norm": 1.3156554698944092, "learning_rate": 7.2419695769816985e-06, "loss": 0.7168, "step": 10295 }, { "epoch": 0.6014018691588785, "grad_norm": 1.2877345085144043, "learning_rate": 7.240151161108712e-06, "loss": 0.7611, "step": 10296 }, { "epoch": 0.6014602803738318, "grad_norm": 1.28531014919281, "learning_rate": 7.238332844012533e-06, "loss": 0.7162, "step": 10297 }, { "epoch": 0.601518691588785, "grad_norm": 1.541715145111084, "learning_rate": 7.236514625758231e-06, "loss": 0.7529, "step": 10298 }, { "epoch": 0.6015771028037383, "grad_norm": 1.5164417028427124, "learning_rate": 7.234696506410892e-06, "loss": 0.7402, "step": 10299 }, { "epoch": 0.6016355140186916, "grad_norm": 1.1558032035827637, "learning_rate": 7.2328784860355795e-06, "loss": 0.622, "step": 10300 }, { "epoch": 0.6016939252336448, "grad_norm": 1.5605382919311523, "learning_rate": 7.231060564697367e-06, "loss": 0.9045, "step": 10301 }, { "epoch": 0.6017523364485982, "grad_norm": 1.8504759073257446, "learning_rate": 7.229242742461322e-06, "loss": 1.1054, "step": 10302 }, { "epoch": 0.6018107476635514, "grad_norm": 1.4724591970443726, "learning_rate": 7.2274250193924954e-06, "loss": 0.8379, "step": 10303 }, { "epoch": 0.6018691588785047, "grad_norm": 2.067103624343872, "learning_rate": 7.2256073955559515e-06, "loss": 0.7915, "step": 10304 }, { "epoch": 0.601927570093458, "grad_norm": 1.2325180768966675, "learning_rate": 7.223789871016742e-06, "loss": 0.8494, "step": 10305 }, { "epoch": 0.6019859813084112, "grad_norm": 1.03806734085083, "learning_rate": 7.221972445839923e-06, "loss": 0.7787, "step": 10306 }, { "epoch": 0.6020443925233645, "grad_norm": 1.0203194618225098, "learning_rate": 7.220155120090535e-06, "loss": 0.736, "step": 10307 }, { "epoch": 0.6021028037383177, "grad_norm": 1.0230894088745117, "learning_rate": 7.21833789383362e-06, "loss": 0.7048, "step": 10308 }, { "epoch": 0.602161214953271, "grad_norm": 1.2213547229766846, "learning_rate": 7.216520767134223e-06, "loss": 0.8904, "step": 10309 }, { "epoch": 0.6022196261682243, "grad_norm": 1.0188605785369873, "learning_rate": 7.2147037400573765e-06, "loss": 0.8984, "step": 10310 }, { "epoch": 0.6022780373831775, "grad_norm": 1.0122380256652832, "learning_rate": 7.212886812668118e-06, "loss": 0.9608, "step": 10311 }, { "epoch": 0.6023364485981308, "grad_norm": 1.1888339519500732, "learning_rate": 7.21106998503147e-06, "loss": 0.7142, "step": 10312 }, { "epoch": 0.6023948598130842, "grad_norm": 1.8855136632919312, "learning_rate": 7.20925325721246e-06, "loss": 0.6698, "step": 10313 }, { "epoch": 0.6024532710280374, "grad_norm": 1.3803818225860596, "learning_rate": 7.2074366292761145e-06, "loss": 0.8055, "step": 10314 }, { "epoch": 0.6025116822429907, "grad_norm": 1.3166627883911133, "learning_rate": 7.205620101287445e-06, "loss": 0.7276, "step": 10315 }, { "epoch": 0.6025700934579439, "grad_norm": 1.1469820737838745, "learning_rate": 7.2038036733114714e-06, "loss": 0.8534, "step": 10316 }, { "epoch": 0.6026285046728972, "grad_norm": 1.0984318256378174, "learning_rate": 7.201987345413201e-06, "loss": 0.7032, "step": 10317 }, { "epoch": 0.6026869158878505, "grad_norm": 1.4484635591506958, "learning_rate": 7.200171117657644e-06, "loss": 0.8154, "step": 10318 }, { "epoch": 0.6027453271028037, "grad_norm": 1.3696489334106445, "learning_rate": 7.198354990109806e-06, "loss": 0.9059, "step": 10319 }, { "epoch": 0.602803738317757, "grad_norm": 1.269791603088379, "learning_rate": 7.196538962834682e-06, "loss": 0.7796, "step": 10320 }, { "epoch": 0.6028621495327103, "grad_norm": 1.423361897468567, "learning_rate": 7.194723035897273e-06, "loss": 1.0852, "step": 10321 }, { "epoch": 0.6029205607476635, "grad_norm": 1.23707914352417, "learning_rate": 7.192907209362573e-06, "loss": 0.8066, "step": 10322 }, { "epoch": 0.6029789719626168, "grad_norm": 1.1167289018630981, "learning_rate": 7.1910914832955656e-06, "loss": 0.9171, "step": 10323 }, { "epoch": 0.60303738317757, "grad_norm": 1.2158955335617065, "learning_rate": 7.1892758577612445e-06, "loss": 0.8495, "step": 10324 }, { "epoch": 0.6030957943925234, "grad_norm": 1.7257901430130005, "learning_rate": 7.187460332824584e-06, "loss": 0.9141, "step": 10325 }, { "epoch": 0.6031542056074767, "grad_norm": 1.3474279642105103, "learning_rate": 7.185644908550571e-06, "loss": 0.7164, "step": 10326 }, { "epoch": 0.6032126168224299, "grad_norm": 2.0483930110931396, "learning_rate": 7.183829585004178e-06, "loss": 0.805, "step": 10327 }, { "epoch": 0.6032710280373832, "grad_norm": 1.1150141954421997, "learning_rate": 7.182014362250374e-06, "loss": 0.8363, "step": 10328 }, { "epoch": 0.6033294392523364, "grad_norm": 1.272086262702942, "learning_rate": 7.1801992403541285e-06, "loss": 0.7867, "step": 10329 }, { "epoch": 0.6033878504672897, "grad_norm": 1.3693740367889404, "learning_rate": 7.1783842193804095e-06, "loss": 0.6953, "step": 10330 }, { "epoch": 0.603446261682243, "grad_norm": 1.5635511875152588, "learning_rate": 7.176569299394172e-06, "loss": 0.9951, "step": 10331 }, { "epoch": 0.6035046728971962, "grad_norm": 1.3355567455291748, "learning_rate": 7.1747544804603755e-06, "loss": 0.8647, "step": 10332 }, { "epoch": 0.6035630841121495, "grad_norm": 1.24424147605896, "learning_rate": 7.172939762643971e-06, "loss": 0.8172, "step": 10333 }, { "epoch": 0.6036214953271029, "grad_norm": 1.4306896924972534, "learning_rate": 7.1711251460099156e-06, "loss": 0.809, "step": 10334 }, { "epoch": 0.603679906542056, "grad_norm": 1.3974343538284302, "learning_rate": 7.169310630623152e-06, "loss": 0.8711, "step": 10335 }, { "epoch": 0.6037383177570094, "grad_norm": 1.1737639904022217, "learning_rate": 7.167496216548618e-06, "loss": 0.7433, "step": 10336 }, { "epoch": 0.6037967289719626, "grad_norm": 1.232871413230896, "learning_rate": 7.16568190385126e-06, "loss": 0.7654, "step": 10337 }, { "epoch": 0.6038551401869159, "grad_norm": 1.0775165557861328, "learning_rate": 7.163867692596007e-06, "loss": 0.7035, "step": 10338 }, { "epoch": 0.6039135514018692, "grad_norm": 1.225989818572998, "learning_rate": 7.162053582847799e-06, "loss": 0.6788, "step": 10339 }, { "epoch": 0.6039719626168224, "grad_norm": 1.0322386026382446, "learning_rate": 7.160239574671557e-06, "loss": 0.7211, "step": 10340 }, { "epoch": 0.6040303738317757, "grad_norm": 1.0631957054138184, "learning_rate": 7.158425668132205e-06, "loss": 0.7649, "step": 10341 }, { "epoch": 0.604088785046729, "grad_norm": 1.5432181358337402, "learning_rate": 7.156611863294669e-06, "loss": 0.7733, "step": 10342 }, { "epoch": 0.6041471962616822, "grad_norm": 1.304459810256958, "learning_rate": 7.154798160223861e-06, "loss": 0.9156, "step": 10343 }, { "epoch": 0.6042056074766355, "grad_norm": 1.1761329174041748, "learning_rate": 7.152984558984704e-06, "loss": 0.6802, "step": 10344 }, { "epoch": 0.6042640186915887, "grad_norm": 1.655632495880127, "learning_rate": 7.151171059642099e-06, "loss": 0.7409, "step": 10345 }, { "epoch": 0.6043224299065421, "grad_norm": 1.291736364364624, "learning_rate": 7.149357662260952e-06, "loss": 0.7746, "step": 10346 }, { "epoch": 0.6043808411214954, "grad_norm": 1.2915135622024536, "learning_rate": 7.147544366906173e-06, "loss": 0.7905, "step": 10347 }, { "epoch": 0.6044392523364486, "grad_norm": 1.117548942565918, "learning_rate": 7.145731173642653e-06, "loss": 0.7117, "step": 10348 }, { "epoch": 0.6044976635514019, "grad_norm": 1.054032802581787, "learning_rate": 7.143918082535293e-06, "loss": 0.6975, "step": 10349 }, { "epoch": 0.6045560747663551, "grad_norm": 1.6850316524505615, "learning_rate": 7.142105093648981e-06, "loss": 0.9119, "step": 10350 }, { "epoch": 0.6046144859813084, "grad_norm": 2.206634998321533, "learning_rate": 7.140292207048607e-06, "loss": 0.8069, "step": 10351 }, { "epoch": 0.6046728971962617, "grad_norm": 1.446277141571045, "learning_rate": 7.138479422799058e-06, "loss": 0.7754, "step": 10352 }, { "epoch": 0.6047313084112149, "grad_norm": 1.6069916486740112, "learning_rate": 7.136666740965208e-06, "loss": 1.0004, "step": 10353 }, { "epoch": 0.6047897196261682, "grad_norm": 1.7569230794906616, "learning_rate": 7.134854161611941e-06, "loss": 0.7764, "step": 10354 }, { "epoch": 0.6048481308411215, "grad_norm": 1.3141010999679565, "learning_rate": 7.133041684804128e-06, "loss": 0.8636, "step": 10355 }, { "epoch": 0.6049065420560747, "grad_norm": 1.5069141387939453, "learning_rate": 7.131229310606635e-06, "loss": 0.7407, "step": 10356 }, { "epoch": 0.6049649532710281, "grad_norm": 1.5778610706329346, "learning_rate": 7.1294170390843335e-06, "loss": 0.8641, "step": 10357 }, { "epoch": 0.6050233644859813, "grad_norm": 1.8505219221115112, "learning_rate": 7.127604870302081e-06, "loss": 0.8277, "step": 10358 }, { "epoch": 0.6050817757009346, "grad_norm": 1.207786202430725, "learning_rate": 7.125792804324741e-06, "loss": 0.7395, "step": 10359 }, { "epoch": 0.6051401869158879, "grad_norm": 1.8015652894973755, "learning_rate": 7.123980841217168e-06, "loss": 0.844, "step": 10360 }, { "epoch": 0.6051985981308411, "grad_norm": 1.1605204343795776, "learning_rate": 7.1221689810442086e-06, "loss": 0.8837, "step": 10361 }, { "epoch": 0.6052570093457944, "grad_norm": 1.6378464698791504, "learning_rate": 7.120357223870715e-06, "loss": 0.775, "step": 10362 }, { "epoch": 0.6053154205607477, "grad_norm": 1.4255449771881104, "learning_rate": 7.118545569761528e-06, "loss": 0.7315, "step": 10363 }, { "epoch": 0.6053738317757009, "grad_norm": 1.7122669219970703, "learning_rate": 7.116734018781494e-06, "loss": 0.868, "step": 10364 }, { "epoch": 0.6054322429906542, "grad_norm": 1.3442177772521973, "learning_rate": 7.114922570995441e-06, "loss": 0.7131, "step": 10365 }, { "epoch": 0.6054906542056074, "grad_norm": 1.718627691268921, "learning_rate": 7.113111226468208e-06, "loss": 0.7782, "step": 10366 }, { "epoch": 0.6055490654205608, "grad_norm": 1.0935277938842773, "learning_rate": 7.111299985264621e-06, "loss": 0.7732, "step": 10367 }, { "epoch": 0.6056074766355141, "grad_norm": 1.40553617477417, "learning_rate": 7.109488847449506e-06, "loss": 0.6538, "step": 10368 }, { "epoch": 0.6056658878504673, "grad_norm": 1.5714037418365479, "learning_rate": 7.10767781308769e-06, "loss": 0.9199, "step": 10369 }, { "epoch": 0.6057242990654206, "grad_norm": 1.3824357986450195, "learning_rate": 7.105866882243986e-06, "loss": 0.8277, "step": 10370 }, { "epoch": 0.6057827102803738, "grad_norm": 1.3567917346954346, "learning_rate": 7.104056054983206e-06, "loss": 0.6237, "step": 10371 }, { "epoch": 0.6058411214953271, "grad_norm": 1.1385704278945923, "learning_rate": 7.1022453313701675e-06, "loss": 0.643, "step": 10372 }, { "epoch": 0.6058995327102804, "grad_norm": 1.3115549087524414, "learning_rate": 7.100434711469668e-06, "loss": 0.7677, "step": 10373 }, { "epoch": 0.6059579439252336, "grad_norm": 1.6323736906051636, "learning_rate": 7.098624195346523e-06, "loss": 0.9018, "step": 10374 }, { "epoch": 0.6060163551401869, "grad_norm": 1.1284722089767456, "learning_rate": 7.096813783065524e-06, "loss": 0.7421, "step": 10375 }, { "epoch": 0.6060747663551402, "grad_norm": 1.412634015083313, "learning_rate": 7.0950034746914655e-06, "loss": 0.8036, "step": 10376 }, { "epoch": 0.6061331775700934, "grad_norm": 1.2174789905548096, "learning_rate": 7.093193270289147e-06, "loss": 0.8192, "step": 10377 }, { "epoch": 0.6061915887850468, "grad_norm": 1.2376041412353516, "learning_rate": 7.09138316992335e-06, "loss": 0.7281, "step": 10378 }, { "epoch": 0.60625, "grad_norm": 2.0057876110076904, "learning_rate": 7.089573173658863e-06, "loss": 0.878, "step": 10379 }, { "epoch": 0.6063084112149533, "grad_norm": 1.4821807146072388, "learning_rate": 7.087763281560467e-06, "loss": 0.9984, "step": 10380 }, { "epoch": 0.6063668224299066, "grad_norm": 1.021083116531372, "learning_rate": 7.085953493692934e-06, "loss": 0.7443, "step": 10381 }, { "epoch": 0.6064252336448598, "grad_norm": 1.6184254884719849, "learning_rate": 7.084143810121044e-06, "loss": 0.6773, "step": 10382 }, { "epoch": 0.6064836448598131, "grad_norm": 1.9423943758010864, "learning_rate": 7.082334230909566e-06, "loss": 0.7127, "step": 10383 }, { "epoch": 0.6065420560747663, "grad_norm": 1.3163399696350098, "learning_rate": 7.080524756123259e-06, "loss": 0.7511, "step": 10384 }, { "epoch": 0.6066004672897196, "grad_norm": 2.6225152015686035, "learning_rate": 7.078715385826897e-06, "loss": 0.9354, "step": 10385 }, { "epoch": 0.6066588785046729, "grad_norm": 1.4302643537521362, "learning_rate": 7.076906120085228e-06, "loss": 0.9032, "step": 10386 }, { "epoch": 0.6067172897196261, "grad_norm": 1.1603728532791138, "learning_rate": 7.075096958963012e-06, "loss": 0.7632, "step": 10387 }, { "epoch": 0.6067757009345794, "grad_norm": 0.8308242559432983, "learning_rate": 7.073287902525001e-06, "loss": 0.746, "step": 10388 }, { "epoch": 0.6068341121495328, "grad_norm": 1.1386597156524658, "learning_rate": 7.071478950835937e-06, "loss": 0.6567, "step": 10389 }, { "epoch": 0.606892523364486, "grad_norm": 1.263262391090393, "learning_rate": 7.069670103960568e-06, "loss": 0.7128, "step": 10390 }, { "epoch": 0.6069509345794393, "grad_norm": 1.537928581237793, "learning_rate": 7.067861361963631e-06, "loss": 0.8607, "step": 10391 }, { "epoch": 0.6070093457943925, "grad_norm": 0.8911581039428711, "learning_rate": 7.066052724909867e-06, "loss": 0.7027, "step": 10392 }, { "epoch": 0.6070677570093458, "grad_norm": 1.3229213953018188, "learning_rate": 7.064244192864005e-06, "loss": 0.8489, "step": 10393 }, { "epoch": 0.6071261682242991, "grad_norm": 1.3795310258865356, "learning_rate": 7.062435765890771e-06, "loss": 0.9165, "step": 10394 }, { "epoch": 0.6071845794392523, "grad_norm": 1.5397223234176636, "learning_rate": 7.0606274440548935e-06, "loss": 0.6934, "step": 10395 }, { "epoch": 0.6072429906542056, "grad_norm": 1.8662618398666382, "learning_rate": 7.058819227421091e-06, "loss": 0.7595, "step": 10396 }, { "epoch": 0.6073014018691589, "grad_norm": 1.1042698621749878, "learning_rate": 7.057011116054087e-06, "loss": 0.7035, "step": 10397 }, { "epoch": 0.6073598130841121, "grad_norm": 1.0681008100509644, "learning_rate": 7.055203110018587e-06, "loss": 0.7672, "step": 10398 }, { "epoch": 0.6074182242990654, "grad_norm": 1.5466727018356323, "learning_rate": 7.053395209379302e-06, "loss": 0.8236, "step": 10399 }, { "epoch": 0.6074766355140186, "grad_norm": 1.4732247591018677, "learning_rate": 7.051587414200942e-06, "loss": 0.7822, "step": 10400 }, { "epoch": 0.607535046728972, "grad_norm": 1.8047502040863037, "learning_rate": 7.049779724548206e-06, "loss": 0.8826, "step": 10401 }, { "epoch": 0.6075934579439253, "grad_norm": 1.0837980508804321, "learning_rate": 7.047972140485797e-06, "loss": 0.8254, "step": 10402 }, { "epoch": 0.6076518691588785, "grad_norm": 1.4805707931518555, "learning_rate": 7.046164662078403e-06, "loss": 0.8115, "step": 10403 }, { "epoch": 0.6077102803738318, "grad_norm": 1.427211880683899, "learning_rate": 7.044357289390718e-06, "loss": 1.0362, "step": 10404 }, { "epoch": 0.607768691588785, "grad_norm": 1.171225666999817, "learning_rate": 7.042550022487431e-06, "loss": 0.8132, "step": 10405 }, { "epoch": 0.6078271028037383, "grad_norm": 1.1907920837402344, "learning_rate": 7.040742861433218e-06, "loss": 0.6748, "step": 10406 }, { "epoch": 0.6078855140186916, "grad_norm": 1.1275112628936768, "learning_rate": 7.03893580629277e-06, "loss": 0.8938, "step": 10407 }, { "epoch": 0.6079439252336448, "grad_norm": 1.151687502861023, "learning_rate": 7.037128857130755e-06, "loss": 0.6525, "step": 10408 }, { "epoch": 0.6080023364485981, "grad_norm": 1.2660561800003052, "learning_rate": 7.035322014011843e-06, "loss": 0.7928, "step": 10409 }, { "epoch": 0.6080607476635514, "grad_norm": 1.7502135038375854, "learning_rate": 7.03351527700071e-06, "loss": 0.9006, "step": 10410 }, { "epoch": 0.6081191588785047, "grad_norm": 0.7980853319168091, "learning_rate": 7.031708646162012e-06, "loss": 0.6498, "step": 10411 }, { "epoch": 0.608177570093458, "grad_norm": 1.2179826498031616, "learning_rate": 7.0299021215604146e-06, "loss": 0.792, "step": 10412 }, { "epoch": 0.6082359813084112, "grad_norm": 1.057923436164856, "learning_rate": 7.028095703260576e-06, "loss": 0.7039, "step": 10413 }, { "epoch": 0.6082943925233645, "grad_norm": 0.883299708366394, "learning_rate": 7.026289391327141e-06, "loss": 0.5636, "step": 10414 }, { "epoch": 0.6083528037383178, "grad_norm": 2.305830955505371, "learning_rate": 7.024483185824767e-06, "loss": 0.6547, "step": 10415 }, { "epoch": 0.608411214953271, "grad_norm": 0.9906942248344421, "learning_rate": 7.022677086818094e-06, "loss": 0.5721, "step": 10416 }, { "epoch": 0.6084696261682243, "grad_norm": 1.1380093097686768, "learning_rate": 7.020871094371767e-06, "loss": 0.7486, "step": 10417 }, { "epoch": 0.6085280373831776, "grad_norm": 1.2970010042190552, "learning_rate": 7.019065208550426e-06, "loss": 0.9491, "step": 10418 }, { "epoch": 0.6085864485981308, "grad_norm": 1.358285665512085, "learning_rate": 7.017259429418696e-06, "loss": 0.7195, "step": 10419 }, { "epoch": 0.6086448598130841, "grad_norm": 0.9923219680786133, "learning_rate": 7.015453757041214e-06, "loss": 0.8454, "step": 10420 }, { "epoch": 0.6087032710280373, "grad_norm": 0.8747149705886841, "learning_rate": 7.013648191482603e-06, "loss": 0.5315, "step": 10421 }, { "epoch": 0.6087616822429907, "grad_norm": 1.4363365173339844, "learning_rate": 7.01184273280749e-06, "loss": 0.7285, "step": 10422 }, { "epoch": 0.608820093457944, "grad_norm": 1.146036148071289, "learning_rate": 7.01003738108049e-06, "loss": 0.8209, "step": 10423 }, { "epoch": 0.6088785046728972, "grad_norm": 1.2434886693954468, "learning_rate": 7.0082321363662145e-06, "loss": 0.7533, "step": 10424 }, { "epoch": 0.6089369158878505, "grad_norm": 1.2224229574203491, "learning_rate": 7.006426998729281e-06, "loss": 0.6752, "step": 10425 }, { "epoch": 0.6089953271028037, "grad_norm": 1.2568488121032715, "learning_rate": 7.004621968234291e-06, "loss": 0.7492, "step": 10426 }, { "epoch": 0.609053738317757, "grad_norm": 1.6537160873413086, "learning_rate": 7.002817044945853e-06, "loss": 0.8286, "step": 10427 }, { "epoch": 0.6091121495327103, "grad_norm": 1.302770972251892, "learning_rate": 7.0010122289285635e-06, "loss": 0.8557, "step": 10428 }, { "epoch": 0.6091705607476635, "grad_norm": 1.4469199180603027, "learning_rate": 6.999207520247015e-06, "loss": 0.7379, "step": 10429 }, { "epoch": 0.6092289719626168, "grad_norm": 1.1966594457626343, "learning_rate": 6.997402918965808e-06, "loss": 0.732, "step": 10430 }, { "epoch": 0.6092873831775701, "grad_norm": 1.3721202611923218, "learning_rate": 6.995598425149517e-06, "loss": 0.8024, "step": 10431 }, { "epoch": 0.6093457943925233, "grad_norm": 1.3752351999282837, "learning_rate": 6.99379403886274e-06, "loss": 0.8786, "step": 10432 }, { "epoch": 0.6094042056074767, "grad_norm": 1.7770673036575317, "learning_rate": 6.991989760170051e-06, "loss": 0.8796, "step": 10433 }, { "epoch": 0.6094626168224299, "grad_norm": 0.908721387386322, "learning_rate": 6.990185589136023e-06, "loss": 0.7371, "step": 10434 }, { "epoch": 0.6095210280373832, "grad_norm": 1.2610645294189453, "learning_rate": 6.988381525825234e-06, "loss": 0.7726, "step": 10435 }, { "epoch": 0.6095794392523365, "grad_norm": 1.1379461288452148, "learning_rate": 6.986577570302248e-06, "loss": 0.8736, "step": 10436 }, { "epoch": 0.6096378504672897, "grad_norm": 1.209854006767273, "learning_rate": 6.984773722631635e-06, "loss": 0.7828, "step": 10437 }, { "epoch": 0.609696261682243, "grad_norm": 2.0725796222686768, "learning_rate": 6.982969982877954e-06, "loss": 0.8502, "step": 10438 }, { "epoch": 0.6097546728971963, "grad_norm": 1.129561185836792, "learning_rate": 6.981166351105755e-06, "loss": 0.9142, "step": 10439 }, { "epoch": 0.6098130841121495, "grad_norm": 1.6203943490982056, "learning_rate": 6.979362827379603e-06, "loss": 0.886, "step": 10440 }, { "epoch": 0.6098714953271028, "grad_norm": 1.3104076385498047, "learning_rate": 6.97755941176404e-06, "loss": 0.8067, "step": 10441 }, { "epoch": 0.609929906542056, "grad_norm": 1.1624481678009033, "learning_rate": 6.97575610432361e-06, "loss": 0.6672, "step": 10442 }, { "epoch": 0.6099883177570093, "grad_norm": 1.99941885471344, "learning_rate": 6.973952905122862e-06, "loss": 0.7397, "step": 10443 }, { "epoch": 0.6100467289719627, "grad_norm": 0.9391601085662842, "learning_rate": 6.9721498142263266e-06, "loss": 0.7716, "step": 10444 }, { "epoch": 0.6101051401869159, "grad_norm": 1.3740190267562866, "learning_rate": 6.9703468316985414e-06, "loss": 0.7119, "step": 10445 }, { "epoch": 0.6101635514018692, "grad_norm": 1.918308973312378, "learning_rate": 6.968543957604037e-06, "loss": 0.7665, "step": 10446 }, { "epoch": 0.6102219626168224, "grad_norm": 1.287868857383728, "learning_rate": 6.966741192007334e-06, "loss": 0.7603, "step": 10447 }, { "epoch": 0.6102803738317757, "grad_norm": 1.4354193210601807, "learning_rate": 6.964938534972958e-06, "loss": 0.859, "step": 10448 }, { "epoch": 0.610338785046729, "grad_norm": 1.571079969406128, "learning_rate": 6.963135986565428e-06, "loss": 0.8187, "step": 10449 }, { "epoch": 0.6103971962616822, "grad_norm": 1.8061456680297852, "learning_rate": 6.961333546849258e-06, "loss": 0.7207, "step": 10450 }, { "epoch": 0.6104556074766355, "grad_norm": 1.3703240156173706, "learning_rate": 6.959531215888961e-06, "loss": 0.7155, "step": 10451 }, { "epoch": 0.6105140186915888, "grad_norm": 2.2090003490448, "learning_rate": 6.957728993749038e-06, "loss": 0.8737, "step": 10452 }, { "epoch": 0.610572429906542, "grad_norm": 1.1211915016174316, "learning_rate": 6.955926880493995e-06, "loss": 0.7231, "step": 10453 }, { "epoch": 0.6106308411214953, "grad_norm": 1.5450299978256226, "learning_rate": 6.9541248761883285e-06, "loss": 0.8776, "step": 10454 }, { "epoch": 0.6106892523364486, "grad_norm": 1.2844288349151611, "learning_rate": 6.952322980896541e-06, "loss": 0.6681, "step": 10455 }, { "epoch": 0.6107476635514019, "grad_norm": 1.7294286489486694, "learning_rate": 6.950521194683115e-06, "loss": 0.7633, "step": 10456 }, { "epoch": 0.6108060747663552, "grad_norm": 1.257286787033081, "learning_rate": 6.948719517612539e-06, "loss": 0.8924, "step": 10457 }, { "epoch": 0.6108644859813084, "grad_norm": 1.81063711643219, "learning_rate": 6.946917949749299e-06, "loss": 0.819, "step": 10458 }, { "epoch": 0.6109228971962617, "grad_norm": 1.3259562253952026, "learning_rate": 6.9451164911578704e-06, "loss": 0.8942, "step": 10459 }, { "epoch": 0.610981308411215, "grad_norm": 1.0329210758209229, "learning_rate": 6.943315141902735e-06, "loss": 0.6421, "step": 10460 }, { "epoch": 0.6110397196261682, "grad_norm": 2.5640761852264404, "learning_rate": 6.94151390204836e-06, "loss": 1.0079, "step": 10461 }, { "epoch": 0.6110981308411215, "grad_norm": 1.3210101127624512, "learning_rate": 6.9397127716592115e-06, "loss": 0.7362, "step": 10462 }, { "epoch": 0.6111565420560747, "grad_norm": 1.0211715698242188, "learning_rate": 6.937911750799758e-06, "loss": 0.6936, "step": 10463 }, { "epoch": 0.611214953271028, "grad_norm": 2.363743782043457, "learning_rate": 6.936110839534451e-06, "loss": 0.8447, "step": 10464 }, { "epoch": 0.6112733644859814, "grad_norm": 1.1276224851608276, "learning_rate": 6.934310037927758e-06, "loss": 0.6893, "step": 10465 }, { "epoch": 0.6113317757009346, "grad_norm": 1.7981754541397095, "learning_rate": 6.932509346044122e-06, "loss": 0.7393, "step": 10466 }, { "epoch": 0.6113901869158879, "grad_norm": 1.1834053993225098, "learning_rate": 6.930708763947991e-06, "loss": 0.7994, "step": 10467 }, { "epoch": 0.6114485981308411, "grad_norm": 1.2435261011123657, "learning_rate": 6.928908291703815e-06, "loss": 0.7251, "step": 10468 }, { "epoch": 0.6115070093457944, "grad_norm": 1.8932087421417236, "learning_rate": 6.927107929376028e-06, "loss": 0.8474, "step": 10469 }, { "epoch": 0.6115654205607477, "grad_norm": 0.9686084985733032, "learning_rate": 6.9253076770290695e-06, "loss": 0.6337, "step": 10470 }, { "epoch": 0.6116238317757009, "grad_norm": 1.3129006624221802, "learning_rate": 6.923507534727374e-06, "loss": 0.7055, "step": 10471 }, { "epoch": 0.6116822429906542, "grad_norm": 1.6821237802505493, "learning_rate": 6.92170750253536e-06, "loss": 0.8967, "step": 10472 }, { "epoch": 0.6117406542056075, "grad_norm": 1.192967414855957, "learning_rate": 6.919907580517464e-06, "loss": 0.6384, "step": 10473 }, { "epoch": 0.6117990654205607, "grad_norm": 1.1430367231369019, "learning_rate": 6.918107768738097e-06, "loss": 0.7014, "step": 10474 }, { "epoch": 0.611857476635514, "grad_norm": 1.1972908973693848, "learning_rate": 6.916308067261682e-06, "loss": 0.8132, "step": 10475 }, { "epoch": 0.6119158878504672, "grad_norm": 1.0237277746200562, "learning_rate": 6.9145084761526305e-06, "loss": 0.787, "step": 10476 }, { "epoch": 0.6119742990654206, "grad_norm": 1.0924594402313232, "learning_rate": 6.912708995475346e-06, "loss": 0.6325, "step": 10477 }, { "epoch": 0.6120327102803739, "grad_norm": 1.254009485244751, "learning_rate": 6.910909625294238e-06, "loss": 0.8193, "step": 10478 }, { "epoch": 0.6120911214953271, "grad_norm": 1.0553028583526611, "learning_rate": 6.909110365673704e-06, "loss": 0.8175, "step": 10479 }, { "epoch": 0.6121495327102804, "grad_norm": 1.400601863861084, "learning_rate": 6.9073112166781455e-06, "loss": 0.8327, "step": 10480 }, { "epoch": 0.6122079439252337, "grad_norm": 1.436576247215271, "learning_rate": 6.905512178371949e-06, "loss": 0.7602, "step": 10481 }, { "epoch": 0.6122663551401869, "grad_norm": 1.255288004875183, "learning_rate": 6.903713250819506e-06, "loss": 0.7954, "step": 10482 }, { "epoch": 0.6123247663551402, "grad_norm": 1.1839698553085327, "learning_rate": 6.901914434085204e-06, "loss": 0.7595, "step": 10483 }, { "epoch": 0.6123831775700934, "grad_norm": 1.1970174312591553, "learning_rate": 6.900115728233418e-06, "loss": 0.7483, "step": 10484 }, { "epoch": 0.6124415887850467, "grad_norm": 1.1019484996795654, "learning_rate": 6.8983171333285335e-06, "loss": 0.7735, "step": 10485 }, { "epoch": 0.6125, "grad_norm": 1.523212194442749, "learning_rate": 6.896518649434916e-06, "loss": 0.8261, "step": 10486 }, { "epoch": 0.6125584112149532, "grad_norm": 2.3204641342163086, "learning_rate": 6.8947202766169344e-06, "loss": 0.7306, "step": 10487 }, { "epoch": 0.6126168224299066, "grad_norm": 1.346412181854248, "learning_rate": 6.89292201493896e-06, "loss": 0.724, "step": 10488 }, { "epoch": 0.6126752336448598, "grad_norm": 1.044317603111267, "learning_rate": 6.891123864465343e-06, "loss": 0.7866, "step": 10489 }, { "epoch": 0.6127336448598131, "grad_norm": 1.2633495330810547, "learning_rate": 6.8893258252604536e-06, "loss": 0.7481, "step": 10490 }, { "epoch": 0.6127920560747664, "grad_norm": 1.0917655229568481, "learning_rate": 6.887527897388635e-06, "loss": 0.709, "step": 10491 }, { "epoch": 0.6128504672897196, "grad_norm": 1.1276111602783203, "learning_rate": 6.885730080914239e-06, "loss": 0.7565, "step": 10492 }, { "epoch": 0.6129088785046729, "grad_norm": 1.2268636226654053, "learning_rate": 6.883932375901615e-06, "loss": 0.8013, "step": 10493 }, { "epoch": 0.6129672897196262, "grad_norm": 1.446110486984253, "learning_rate": 6.882134782415095e-06, "loss": 0.8497, "step": 10494 }, { "epoch": 0.6130257009345794, "grad_norm": 1.1937540769577026, "learning_rate": 6.880337300519025e-06, "loss": 0.8337, "step": 10495 }, { "epoch": 0.6130841121495327, "grad_norm": 1.5141264200210571, "learning_rate": 6.8785399302777346e-06, "loss": 0.7423, "step": 10496 }, { "epoch": 0.6131425233644859, "grad_norm": 1.5387210845947266, "learning_rate": 6.8767426717555475e-06, "loss": 0.7699, "step": 10497 }, { "epoch": 0.6132009345794392, "grad_norm": 1.274366021156311, "learning_rate": 6.874945525016798e-06, "loss": 0.6769, "step": 10498 }, { "epoch": 0.6132593457943926, "grad_norm": 1.2735940217971802, "learning_rate": 6.873148490125803e-06, "loss": 0.8166, "step": 10499 }, { "epoch": 0.6133177570093458, "grad_norm": 1.4007107019424438, "learning_rate": 6.8713515671468765e-06, "loss": 0.732, "step": 10500 }, { "epoch": 0.6133761682242991, "grad_norm": 0.8993301391601562, "learning_rate": 6.869554756144339e-06, "loss": 0.7092, "step": 10501 }, { "epoch": 0.6134345794392523, "grad_norm": 1.737028956413269, "learning_rate": 6.867758057182491e-06, "loss": 0.802, "step": 10502 }, { "epoch": 0.6134929906542056, "grad_norm": 1.6032634973526, "learning_rate": 6.865961470325644e-06, "loss": 0.833, "step": 10503 }, { "epoch": 0.6135514018691589, "grad_norm": 1.1067538261413574, "learning_rate": 6.8641649956380975e-06, "loss": 0.7526, "step": 10504 }, { "epoch": 0.6136098130841121, "grad_norm": 1.5604654550552368, "learning_rate": 6.862368633184142e-06, "loss": 0.7306, "step": 10505 }, { "epoch": 0.6136682242990654, "grad_norm": 1.8250021934509277, "learning_rate": 6.860572383028082e-06, "loss": 0.6842, "step": 10506 }, { "epoch": 0.6137266355140187, "grad_norm": 1.4461852312088013, "learning_rate": 6.858776245234197e-06, "loss": 0.6752, "step": 10507 }, { "epoch": 0.6137850467289719, "grad_norm": 1.2255127429962158, "learning_rate": 6.856980219866778e-06, "loss": 0.6286, "step": 10508 }, { "epoch": 0.6138434579439253, "grad_norm": 1.8625106811523438, "learning_rate": 6.855184306990106e-06, "loss": 1.0162, "step": 10509 }, { "epoch": 0.6139018691588785, "grad_norm": 1.3584121465682983, "learning_rate": 6.85338850666845e-06, "loss": 0.9359, "step": 10510 }, { "epoch": 0.6139602803738318, "grad_norm": 1.3537617921829224, "learning_rate": 6.851592818966091e-06, "loss": 1.0044, "step": 10511 }, { "epoch": 0.6140186915887851, "grad_norm": 1.0766069889068604, "learning_rate": 6.8497972439472915e-06, "loss": 0.8345, "step": 10512 }, { "epoch": 0.6140771028037383, "grad_norm": 1.6262463331222534, "learning_rate": 6.848001781676325e-06, "loss": 0.9435, "step": 10513 }, { "epoch": 0.6141355140186916, "grad_norm": 1.362604022026062, "learning_rate": 6.846206432217446e-06, "loss": 0.828, "step": 10514 }, { "epoch": 0.6141939252336449, "grad_norm": 1.2243542671203613, "learning_rate": 6.844411195634911e-06, "loss": 0.8353, "step": 10515 }, { "epoch": 0.6142523364485981, "grad_norm": 1.6556191444396973, "learning_rate": 6.842616071992975e-06, "loss": 0.9251, "step": 10516 }, { "epoch": 0.6143107476635514, "grad_norm": 1.212822675704956, "learning_rate": 6.840821061355883e-06, "loss": 0.7931, "step": 10517 }, { "epoch": 0.6143691588785046, "grad_norm": 1.1042894124984741, "learning_rate": 6.839026163787887e-06, "loss": 0.6409, "step": 10518 }, { "epoch": 0.6144275700934579, "grad_norm": 2.351186513900757, "learning_rate": 6.837231379353222e-06, "loss": 0.7857, "step": 10519 }, { "epoch": 0.6144859813084113, "grad_norm": 1.2498046159744263, "learning_rate": 6.8354367081161235e-06, "loss": 0.7334, "step": 10520 }, { "epoch": 0.6145443925233645, "grad_norm": 1.0359899997711182, "learning_rate": 6.833642150140829e-06, "loss": 0.6878, "step": 10521 }, { "epoch": 0.6146028037383178, "grad_norm": 1.5538045167922974, "learning_rate": 6.831847705491559e-06, "loss": 0.771, "step": 10522 }, { "epoch": 0.614661214953271, "grad_norm": 1.6854110956192017, "learning_rate": 6.830053374232547e-06, "loss": 0.7945, "step": 10523 }, { "epoch": 0.6147196261682243, "grad_norm": 1.659257173538208, "learning_rate": 6.8282591564280074e-06, "loss": 0.8787, "step": 10524 }, { "epoch": 0.6147780373831776, "grad_norm": 1.1921098232269287, "learning_rate": 6.826465052142157e-06, "loss": 0.7381, "step": 10525 }, { "epoch": 0.6148364485981308, "grad_norm": 1.0602186918258667, "learning_rate": 6.824671061439213e-06, "loss": 0.6844, "step": 10526 }, { "epoch": 0.6148948598130841, "grad_norm": 1.5144509077072144, "learning_rate": 6.8228771843833745e-06, "loss": 0.7579, "step": 10527 }, { "epoch": 0.6149532710280374, "grad_norm": 1.0508003234863281, "learning_rate": 6.821083421038854e-06, "loss": 0.7336, "step": 10528 }, { "epoch": 0.6150116822429906, "grad_norm": 2.435713768005371, "learning_rate": 6.8192897714698495e-06, "loss": 0.595, "step": 10529 }, { "epoch": 0.615070093457944, "grad_norm": 1.6045677661895752, "learning_rate": 6.8174962357405486e-06, "loss": 0.6365, "step": 10530 }, { "epoch": 0.6151285046728971, "grad_norm": 1.3767385482788086, "learning_rate": 6.815702813915157e-06, "loss": 0.9232, "step": 10531 }, { "epoch": 0.6151869158878505, "grad_norm": 1.2437461614608765, "learning_rate": 6.8139095060578495e-06, "loss": 0.7409, "step": 10532 }, { "epoch": 0.6152453271028038, "grad_norm": 1.2040945291519165, "learning_rate": 6.812116312232819e-06, "loss": 0.7615, "step": 10533 }, { "epoch": 0.615303738317757, "grad_norm": 1.1606525182724, "learning_rate": 6.810323232504245e-06, "loss": 0.7462, "step": 10534 }, { "epoch": 0.6153621495327103, "grad_norm": 1.426934838294983, "learning_rate": 6.808530266936295e-06, "loss": 0.801, "step": 10535 }, { "epoch": 0.6154205607476636, "grad_norm": 1.1178275346755981, "learning_rate": 6.806737415593145e-06, "loss": 0.806, "step": 10536 }, { "epoch": 0.6154789719626168, "grad_norm": 1.7745915651321411, "learning_rate": 6.804944678538963e-06, "loss": 0.8582, "step": 10537 }, { "epoch": 0.6155373831775701, "grad_norm": 1.0858848094940186, "learning_rate": 6.8031520558379136e-06, "loss": 0.8929, "step": 10538 }, { "epoch": 0.6155957943925233, "grad_norm": 1.241377830505371, "learning_rate": 6.801359547554156e-06, "loss": 0.8174, "step": 10539 }, { "epoch": 0.6156542056074766, "grad_norm": 1.2839456796646118, "learning_rate": 6.799567153751838e-06, "loss": 0.7224, "step": 10540 }, { "epoch": 0.61571261682243, "grad_norm": 1.2909544706344604, "learning_rate": 6.797774874495119e-06, "loss": 0.6904, "step": 10541 }, { "epoch": 0.6157710280373832, "grad_norm": 1.0909968614578247, "learning_rate": 6.795982709848141e-06, "loss": 0.7443, "step": 10542 }, { "epoch": 0.6158294392523365, "grad_norm": 1.4003868103027344, "learning_rate": 6.794190659875052e-06, "loss": 0.7941, "step": 10543 }, { "epoch": 0.6158878504672897, "grad_norm": 1.5106807947158813, "learning_rate": 6.792398724639985e-06, "loss": 0.6893, "step": 10544 }, { "epoch": 0.615946261682243, "grad_norm": 1.5188055038452148, "learning_rate": 6.7906069042070745e-06, "loss": 0.8262, "step": 10545 }, { "epoch": 0.6160046728971963, "grad_norm": 1.137832760810852, "learning_rate": 6.788815198640457e-06, "loss": 0.6849, "step": 10546 }, { "epoch": 0.6160630841121495, "grad_norm": 1.5724185705184937, "learning_rate": 6.787023608004251e-06, "loss": 0.8858, "step": 10547 }, { "epoch": 0.6161214953271028, "grad_norm": 1.2178568840026855, "learning_rate": 6.785232132362586e-06, "loss": 0.9408, "step": 10548 }, { "epoch": 0.6161799065420561, "grad_norm": 1.2888121604919434, "learning_rate": 6.783440771779576e-06, "loss": 0.8071, "step": 10549 }, { "epoch": 0.6162383177570093, "grad_norm": 1.760962724685669, "learning_rate": 6.781649526319334e-06, "loss": 0.8481, "step": 10550 }, { "epoch": 0.6162967289719626, "grad_norm": 1.0470508337020874, "learning_rate": 6.779858396045974e-06, "loss": 0.7314, "step": 10551 }, { "epoch": 0.6163551401869158, "grad_norm": 1.2110989093780518, "learning_rate": 6.778067381023596e-06, "loss": 0.6646, "step": 10552 }, { "epoch": 0.6164135514018692, "grad_norm": 1.2206634283065796, "learning_rate": 6.776276481316309e-06, "loss": 0.8122, "step": 10553 }, { "epoch": 0.6164719626168225, "grad_norm": 1.1787954568862915, "learning_rate": 6.774485696988205e-06, "loss": 0.7757, "step": 10554 }, { "epoch": 0.6165303738317757, "grad_norm": 1.2199281454086304, "learning_rate": 6.772695028103375e-06, "loss": 0.8054, "step": 10555 }, { "epoch": 0.616588785046729, "grad_norm": 1.1763594150543213, "learning_rate": 6.770904474725916e-06, "loss": 0.7931, "step": 10556 }, { "epoch": 0.6166471962616823, "grad_norm": 1.1435970067977905, "learning_rate": 6.769114036919909e-06, "loss": 0.8276, "step": 10557 }, { "epoch": 0.6167056074766355, "grad_norm": 1.0001413822174072, "learning_rate": 6.767323714749432e-06, "loss": 0.761, "step": 10558 }, { "epoch": 0.6167640186915888, "grad_norm": 0.9972187280654907, "learning_rate": 6.76553350827857e-06, "loss": 0.8371, "step": 10559 }, { "epoch": 0.616822429906542, "grad_norm": 1.7219207286834717, "learning_rate": 6.763743417571384e-06, "loss": 0.7867, "step": 10560 }, { "epoch": 0.6168808411214953, "grad_norm": 1.0010796785354614, "learning_rate": 6.761953442691953e-06, "loss": 0.6647, "step": 10561 }, { "epoch": 0.6169392523364486, "grad_norm": 1.2361810207366943, "learning_rate": 6.76016358370434e-06, "loss": 0.7184, "step": 10562 }, { "epoch": 0.6169976635514018, "grad_norm": 1.518522024154663, "learning_rate": 6.758373840672594e-06, "loss": 0.874, "step": 10563 }, { "epoch": 0.6170560747663552, "grad_norm": 1.34098219871521, "learning_rate": 6.756584213660787e-06, "loss": 0.8634, "step": 10564 }, { "epoch": 0.6171144859813084, "grad_norm": 1.1690481901168823, "learning_rate": 6.754794702732961e-06, "loss": 0.7122, "step": 10565 }, { "epoch": 0.6171728971962617, "grad_norm": 1.0122239589691162, "learning_rate": 6.7530053079531664e-06, "loss": 0.6559, "step": 10566 }, { "epoch": 0.617231308411215, "grad_norm": 1.0972890853881836, "learning_rate": 6.7512160293854486e-06, "loss": 0.597, "step": 10567 }, { "epoch": 0.6172897196261682, "grad_norm": 1.3087619543075562, "learning_rate": 6.749426867093842e-06, "loss": 0.8319, "step": 10568 }, { "epoch": 0.6173481308411215, "grad_norm": 0.9029966592788696, "learning_rate": 6.747637821142387e-06, "loss": 0.5878, "step": 10569 }, { "epoch": 0.6174065420560748, "grad_norm": 1.180026888847351, "learning_rate": 6.74584889159511e-06, "loss": 0.8391, "step": 10570 }, { "epoch": 0.617464953271028, "grad_norm": 1.7226380109786987, "learning_rate": 6.744060078516044e-06, "loss": 0.9048, "step": 10571 }, { "epoch": 0.6175233644859813, "grad_norm": 1.2503368854522705, "learning_rate": 6.742271381969211e-06, "loss": 0.8806, "step": 10572 }, { "epoch": 0.6175817757009345, "grad_norm": 1.8166121244430542, "learning_rate": 6.740482802018622e-06, "loss": 0.8594, "step": 10573 }, { "epoch": 0.6176401869158878, "grad_norm": 1.1090489625930786, "learning_rate": 6.7386943387283e-06, "loss": 0.7796, "step": 10574 }, { "epoch": 0.6176985981308412, "grad_norm": 1.575290322303772, "learning_rate": 6.7369059921622495e-06, "loss": 0.8117, "step": 10575 }, { "epoch": 0.6177570093457944, "grad_norm": 0.9639027118682861, "learning_rate": 6.735117762384482e-06, "loss": 0.7732, "step": 10576 }, { "epoch": 0.6178154205607477, "grad_norm": 1.3467967510223389, "learning_rate": 6.733329649458995e-06, "loss": 0.7998, "step": 10577 }, { "epoch": 0.617873831775701, "grad_norm": 1.303167462348938, "learning_rate": 6.731541653449786e-06, "loss": 1.0087, "step": 10578 }, { "epoch": 0.6179322429906542, "grad_norm": 2.081298589706421, "learning_rate": 6.729753774420855e-06, "loss": 0.7775, "step": 10579 }, { "epoch": 0.6179906542056075, "grad_norm": 1.3655626773834229, "learning_rate": 6.72796601243618e-06, "loss": 0.916, "step": 10580 }, { "epoch": 0.6180490654205607, "grad_norm": 1.0477197170257568, "learning_rate": 6.726178367559759e-06, "loss": 0.6911, "step": 10581 }, { "epoch": 0.618107476635514, "grad_norm": 1.0520635843276978, "learning_rate": 6.724390839855563e-06, "loss": 0.612, "step": 10582 }, { "epoch": 0.6181658878504673, "grad_norm": 1.4241740703582764, "learning_rate": 6.722603429387573e-06, "loss": 0.9823, "step": 10583 }, { "epoch": 0.6182242990654205, "grad_norm": 1.1692194938659668, "learning_rate": 6.7208161362197646e-06, "loss": 0.7926, "step": 10584 }, { "epoch": 0.6182827102803738, "grad_norm": 1.2657357454299927, "learning_rate": 6.7190289604160986e-06, "loss": 0.7044, "step": 10585 }, { "epoch": 0.618341121495327, "grad_norm": 1.454712986946106, "learning_rate": 6.717241902040545e-06, "loss": 0.7971, "step": 10586 }, { "epoch": 0.6183995327102804, "grad_norm": 1.0578534603118896, "learning_rate": 6.715454961157064e-06, "loss": 0.9327, "step": 10587 }, { "epoch": 0.6184579439252337, "grad_norm": 1.4241725206375122, "learning_rate": 6.713668137829605e-06, "loss": 0.8175, "step": 10588 }, { "epoch": 0.6185163551401869, "grad_norm": 3.6068694591522217, "learning_rate": 6.711881432122129e-06, "loss": 0.8305, "step": 10589 }, { "epoch": 0.6185747663551402, "grad_norm": 1.3156846761703491, "learning_rate": 6.710094844098575e-06, "loss": 0.8946, "step": 10590 }, { "epoch": 0.6186331775700935, "grad_norm": 1.2861677408218384, "learning_rate": 6.708308373822891e-06, "loss": 0.7699, "step": 10591 }, { "epoch": 0.6186915887850467, "grad_norm": 0.9575145244598389, "learning_rate": 6.706522021359017e-06, "loss": 0.6625, "step": 10592 }, { "epoch": 0.61875, "grad_norm": 1.3764523267745972, "learning_rate": 6.704735786770882e-06, "loss": 0.7685, "step": 10593 }, { "epoch": 0.6188084112149532, "grad_norm": 0.9861412048339844, "learning_rate": 6.702949670122421e-06, "loss": 0.7637, "step": 10594 }, { "epoch": 0.6188668224299065, "grad_norm": 1.9681620597839355, "learning_rate": 6.7011636714775575e-06, "loss": 0.854, "step": 10595 }, { "epoch": 0.6189252336448599, "grad_norm": 1.0983139276504517, "learning_rate": 6.699377790900216e-06, "loss": 0.7131, "step": 10596 }, { "epoch": 0.618983644859813, "grad_norm": 1.1596767902374268, "learning_rate": 6.6975920284543175e-06, "loss": 0.8053, "step": 10597 }, { "epoch": 0.6190420560747664, "grad_norm": 1.5320895910263062, "learning_rate": 6.695806384203767e-06, "loss": 0.9596, "step": 10598 }, { "epoch": 0.6191004672897197, "grad_norm": 1.1695858240127563, "learning_rate": 6.69402085821248e-06, "loss": 0.726, "step": 10599 }, { "epoch": 0.6191588785046729, "grad_norm": 1.175896406173706, "learning_rate": 6.692235450544359e-06, "loss": 0.7918, "step": 10600 }, { "epoch": 0.6192172897196262, "grad_norm": 1.1762855052947998, "learning_rate": 6.69045016126331e-06, "loss": 0.7121, "step": 10601 }, { "epoch": 0.6192757009345794, "grad_norm": 1.3815258741378784, "learning_rate": 6.688664990433224e-06, "loss": 0.8519, "step": 10602 }, { "epoch": 0.6193341121495327, "grad_norm": 1.2247364521026611, "learning_rate": 6.686879938117992e-06, "loss": 0.6572, "step": 10603 }, { "epoch": 0.619392523364486, "grad_norm": 1.0706344842910767, "learning_rate": 6.685095004381508e-06, "loss": 0.8197, "step": 10604 }, { "epoch": 0.6194509345794392, "grad_norm": 1.9896926879882812, "learning_rate": 6.683310189287652e-06, "loss": 0.7786, "step": 10605 }, { "epoch": 0.6195093457943925, "grad_norm": 1.2080940008163452, "learning_rate": 6.68152549290031e-06, "loss": 0.6844, "step": 10606 }, { "epoch": 0.6195677570093457, "grad_norm": 1.0836260318756104, "learning_rate": 6.679740915283348e-06, "loss": 0.7198, "step": 10607 }, { "epoch": 0.6196261682242991, "grad_norm": 1.3280234336853027, "learning_rate": 6.67795645650064e-06, "loss": 0.8043, "step": 10608 }, { "epoch": 0.6196845794392524, "grad_norm": 1.2928295135498047, "learning_rate": 6.676172116616061e-06, "loss": 0.6875, "step": 10609 }, { "epoch": 0.6197429906542056, "grad_norm": 1.1844853162765503, "learning_rate": 6.674387895693464e-06, "loss": 0.9515, "step": 10610 }, { "epoch": 0.6198014018691589, "grad_norm": 0.9163511991500854, "learning_rate": 6.672603793796708e-06, "loss": 0.8006, "step": 10611 }, { "epoch": 0.6198598130841122, "grad_norm": 0.9948832392692566, "learning_rate": 6.670819810989656e-06, "loss": 0.6774, "step": 10612 }, { "epoch": 0.6199182242990654, "grad_norm": 1.0453453063964844, "learning_rate": 6.669035947336144e-06, "loss": 0.8011, "step": 10613 }, { "epoch": 0.6199766355140187, "grad_norm": 1.2829731702804565, "learning_rate": 6.667252202900034e-06, "loss": 0.8547, "step": 10614 }, { "epoch": 0.6200350467289719, "grad_norm": 1.2131304740905762, "learning_rate": 6.665468577745156e-06, "loss": 0.7687, "step": 10615 }, { "epoch": 0.6200934579439252, "grad_norm": 1.4302560091018677, "learning_rate": 6.663685071935346e-06, "loss": 0.7577, "step": 10616 }, { "epoch": 0.6201518691588785, "grad_norm": 1.1815146207809448, "learning_rate": 6.661901685534446e-06, "loss": 0.8255, "step": 10617 }, { "epoch": 0.6202102803738317, "grad_norm": 1.0739879608154297, "learning_rate": 6.660118418606277e-06, "loss": 0.6242, "step": 10618 }, { "epoch": 0.6202686915887851, "grad_norm": 1.2854522466659546, "learning_rate": 6.658335271214666e-06, "loss": 0.7646, "step": 10619 }, { "epoch": 0.6203271028037384, "grad_norm": 1.1639641523361206, "learning_rate": 6.656552243423437e-06, "loss": 0.7154, "step": 10620 }, { "epoch": 0.6203855140186916, "grad_norm": 1.3378756046295166, "learning_rate": 6.654769335296393e-06, "loss": 0.6159, "step": 10621 }, { "epoch": 0.6204439252336449, "grad_norm": 1.1058520078659058, "learning_rate": 6.652986546897362e-06, "loss": 0.6396, "step": 10622 }, { "epoch": 0.6205023364485981, "grad_norm": 1.2953873872756958, "learning_rate": 6.651203878290139e-06, "loss": 0.7387, "step": 10623 }, { "epoch": 0.6205607476635514, "grad_norm": 1.0242239236831665, "learning_rate": 6.6494213295385325e-06, "loss": 0.8066, "step": 10624 }, { "epoch": 0.6206191588785047, "grad_norm": 1.174897313117981, "learning_rate": 6.647638900706341e-06, "loss": 0.953, "step": 10625 }, { "epoch": 0.6206775700934579, "grad_norm": 1.6645675897598267, "learning_rate": 6.645856591857356e-06, "loss": 0.7093, "step": 10626 }, { "epoch": 0.6207359813084112, "grad_norm": 0.9258248805999756, "learning_rate": 6.644074403055368e-06, "loss": 0.7277, "step": 10627 }, { "epoch": 0.6207943925233644, "grad_norm": 0.7746616005897522, "learning_rate": 6.6422923343641635e-06, "loss": 0.5737, "step": 10628 }, { "epoch": 0.6208528037383177, "grad_norm": 1.1221725940704346, "learning_rate": 6.640510385847525e-06, "loss": 0.8047, "step": 10629 }, { "epoch": 0.6209112149532711, "grad_norm": 1.2148820161819458, "learning_rate": 6.638728557569231e-06, "loss": 0.7, "step": 10630 }, { "epoch": 0.6209696261682243, "grad_norm": 1.1745281219482422, "learning_rate": 6.636946849593049e-06, "loss": 0.7777, "step": 10631 }, { "epoch": 0.6210280373831776, "grad_norm": 1.0804675817489624, "learning_rate": 6.635165261982751e-06, "loss": 0.7108, "step": 10632 }, { "epoch": 0.6210864485981309, "grad_norm": 1.228123426437378, "learning_rate": 6.6333837948021e-06, "loss": 0.7204, "step": 10633 }, { "epoch": 0.6211448598130841, "grad_norm": 1.740102767944336, "learning_rate": 6.63160244811486e-06, "loss": 0.8342, "step": 10634 }, { "epoch": 0.6212032710280374, "grad_norm": 1.1357688903808594, "learning_rate": 6.62982122198478e-06, "loss": 0.6824, "step": 10635 }, { "epoch": 0.6212616822429906, "grad_norm": 1.4460070133209229, "learning_rate": 6.628040116475613e-06, "loss": 0.9045, "step": 10636 }, { "epoch": 0.6213200934579439, "grad_norm": 1.5023552179336548, "learning_rate": 6.6262591316511105e-06, "loss": 0.8081, "step": 10637 }, { "epoch": 0.6213785046728972, "grad_norm": 4.072132587432861, "learning_rate": 6.62447826757501e-06, "loss": 0.7762, "step": 10638 }, { "epoch": 0.6214369158878504, "grad_norm": 1.2983860969543457, "learning_rate": 6.622697524311055e-06, "loss": 0.8465, "step": 10639 }, { "epoch": 0.6214953271028038, "grad_norm": 1.2617638111114502, "learning_rate": 6.6209169019229735e-06, "loss": 0.7071, "step": 10640 }, { "epoch": 0.621553738317757, "grad_norm": 1.7990784645080566, "learning_rate": 6.6191364004744975e-06, "loss": 0.8039, "step": 10641 }, { "epoch": 0.6216121495327103, "grad_norm": 1.2111560106277466, "learning_rate": 6.617356020029355e-06, "loss": 0.7599, "step": 10642 }, { "epoch": 0.6216705607476636, "grad_norm": 1.441291332244873, "learning_rate": 6.615575760651262e-06, "loss": 0.9007, "step": 10643 }, { "epoch": 0.6217289719626168, "grad_norm": 1.0418633222579956, "learning_rate": 6.613795622403939e-06, "loss": 0.6126, "step": 10644 }, { "epoch": 0.6217873831775701, "grad_norm": 1.1606992483139038, "learning_rate": 6.6120156053510995e-06, "loss": 0.7753, "step": 10645 }, { "epoch": 0.6218457943925234, "grad_norm": 1.1183743476867676, "learning_rate": 6.610235709556443e-06, "loss": 0.7637, "step": 10646 }, { "epoch": 0.6219042056074766, "grad_norm": 1.1886883974075317, "learning_rate": 6.6084559350836854e-06, "loss": 1.0123, "step": 10647 }, { "epoch": 0.6219626168224299, "grad_norm": 1.3689658641815186, "learning_rate": 6.606676281996516e-06, "loss": 0.7411, "step": 10648 }, { "epoch": 0.6220210280373831, "grad_norm": 0.9988873600959778, "learning_rate": 6.604896750358636e-06, "loss": 0.749, "step": 10649 }, { "epoch": 0.6220794392523364, "grad_norm": 1.1736654043197632, "learning_rate": 6.603117340233735e-06, "loss": 0.7113, "step": 10650 }, { "epoch": 0.6221378504672898, "grad_norm": 2.081019401550293, "learning_rate": 6.601338051685493e-06, "loss": 0.9589, "step": 10651 }, { "epoch": 0.622196261682243, "grad_norm": 1.1015795469284058, "learning_rate": 6.599558884777599e-06, "loss": 0.6457, "step": 10652 }, { "epoch": 0.6222546728971963, "grad_norm": 1.1582616567611694, "learning_rate": 6.5977798395737284e-06, "loss": 0.6262, "step": 10653 }, { "epoch": 0.6223130841121496, "grad_norm": 1.1587694883346558, "learning_rate": 6.596000916137555e-06, "loss": 0.679, "step": 10654 }, { "epoch": 0.6223714953271028, "grad_norm": 1.7566142082214355, "learning_rate": 6.594222114532749e-06, "loss": 0.9626, "step": 10655 }, { "epoch": 0.6224299065420561, "grad_norm": 1.5512903928756714, "learning_rate": 6.592443434822968e-06, "loss": 0.7736, "step": 10656 }, { "epoch": 0.6224883177570093, "grad_norm": 1.4711155891418457, "learning_rate": 6.590664877071881e-06, "loss": 0.9283, "step": 10657 }, { "epoch": 0.6225467289719626, "grad_norm": 1.403451919555664, "learning_rate": 6.588886441343136e-06, "loss": 0.7126, "step": 10658 }, { "epoch": 0.6226051401869159, "grad_norm": 1.2120206356048584, "learning_rate": 6.5871081277003924e-06, "loss": 0.6963, "step": 10659 }, { "epoch": 0.6226635514018691, "grad_norm": 0.9404550790786743, "learning_rate": 6.585329936207292e-06, "loss": 0.7592, "step": 10660 }, { "epoch": 0.6227219626168224, "grad_norm": 1.5021218061447144, "learning_rate": 6.583551866927475e-06, "loss": 0.8582, "step": 10661 }, { "epoch": 0.6227803738317756, "grad_norm": 1.3795496225357056, "learning_rate": 6.581773919924586e-06, "loss": 0.6048, "step": 10662 }, { "epoch": 0.622838785046729, "grad_norm": 1.2678366899490356, "learning_rate": 6.579996095262253e-06, "loss": 0.7522, "step": 10663 }, { "epoch": 0.6228971962616823, "grad_norm": 1.0830072164535522, "learning_rate": 6.578218393004114e-06, "loss": 0.6926, "step": 10664 }, { "epoch": 0.6229556074766355, "grad_norm": 1.053736925125122, "learning_rate": 6.576440813213784e-06, "loss": 0.7282, "step": 10665 }, { "epoch": 0.6230140186915888, "grad_norm": 2.100037097930908, "learning_rate": 6.574663355954889e-06, "loss": 0.8418, "step": 10666 }, { "epoch": 0.6230724299065421, "grad_norm": 1.2683557271957397, "learning_rate": 6.5728860212910475e-06, "loss": 0.7296, "step": 10667 }, { "epoch": 0.6231308411214953, "grad_norm": 1.5621999502182007, "learning_rate": 6.5711088092858666e-06, "loss": 0.652, "step": 10668 }, { "epoch": 0.6231892523364486, "grad_norm": 1.3412781953811646, "learning_rate": 6.569331720002955e-06, "loss": 0.7501, "step": 10669 }, { "epoch": 0.6232476635514018, "grad_norm": 1.3792774677276611, "learning_rate": 6.5675547535059185e-06, "loss": 0.7474, "step": 10670 }, { "epoch": 0.6233060747663551, "grad_norm": 1.7799748182296753, "learning_rate": 6.565777909858351e-06, "loss": 0.6631, "step": 10671 }, { "epoch": 0.6233644859813084, "grad_norm": 1.6033178567886353, "learning_rate": 6.564001189123854e-06, "loss": 0.854, "step": 10672 }, { "epoch": 0.6234228971962616, "grad_norm": 1.4753373861312866, "learning_rate": 6.5622245913660135e-06, "loss": 0.7399, "step": 10673 }, { "epoch": 0.623481308411215, "grad_norm": 1.225081443786621, "learning_rate": 6.5604481166484126e-06, "loss": 0.7363, "step": 10674 }, { "epoch": 0.6235397196261683, "grad_norm": 2.0216009616851807, "learning_rate": 6.558671765034639e-06, "loss": 0.767, "step": 10675 }, { "epoch": 0.6235981308411215, "grad_norm": 1.0045921802520752, "learning_rate": 6.556895536588262e-06, "loss": 0.6687, "step": 10676 }, { "epoch": 0.6236565420560748, "grad_norm": 1.3893990516662598, "learning_rate": 6.555119431372858e-06, "loss": 0.8764, "step": 10677 }, { "epoch": 0.623714953271028, "grad_norm": 1.3550015687942505, "learning_rate": 6.553343449451999e-06, "loss": 0.7852, "step": 10678 }, { "epoch": 0.6237733644859813, "grad_norm": 0.9407490491867065, "learning_rate": 6.551567590889236e-06, "loss": 0.6779, "step": 10679 }, { "epoch": 0.6238317757009346, "grad_norm": 1.3078734874725342, "learning_rate": 6.549791855748143e-06, "loss": 0.7476, "step": 10680 }, { "epoch": 0.6238901869158878, "grad_norm": 1.4773435592651367, "learning_rate": 6.548016244092265e-06, "loss": 0.9209, "step": 10681 }, { "epoch": 0.6239485981308411, "grad_norm": 1.0171812772750854, "learning_rate": 6.546240755985156e-06, "loss": 0.8542, "step": 10682 }, { "epoch": 0.6240070093457943, "grad_norm": 0.9057170152664185, "learning_rate": 6.5444653914903644e-06, "loss": 0.7163, "step": 10683 }, { "epoch": 0.6240654205607477, "grad_norm": 1.5148603916168213, "learning_rate": 6.542690150671424e-06, "loss": 0.8857, "step": 10684 }, { "epoch": 0.624123831775701, "grad_norm": 1.3097238540649414, "learning_rate": 6.540915033591877e-06, "loss": 0.7589, "step": 10685 }, { "epoch": 0.6241822429906542, "grad_norm": 1.4360918998718262, "learning_rate": 6.539140040315255e-06, "loss": 1.0113, "step": 10686 }, { "epoch": 0.6242406542056075, "grad_norm": 0.9994479417800903, "learning_rate": 6.537365170905088e-06, "loss": 0.6174, "step": 10687 }, { "epoch": 0.6242990654205608, "grad_norm": 1.4508923292160034, "learning_rate": 6.5355904254249006e-06, "loss": 0.6842, "step": 10688 }, { "epoch": 0.624357476635514, "grad_norm": 0.9530491232872009, "learning_rate": 6.533815803938206e-06, "loss": 0.7729, "step": 10689 }, { "epoch": 0.6244158878504673, "grad_norm": 1.4597116708755493, "learning_rate": 6.532041306508524e-06, "loss": 0.8857, "step": 10690 }, { "epoch": 0.6244742990654205, "grad_norm": 1.0914794206619263, "learning_rate": 6.530266933199363e-06, "loss": 0.8222, "step": 10691 }, { "epoch": 0.6245327102803738, "grad_norm": 1.0282390117645264, "learning_rate": 6.528492684074233e-06, "loss": 0.7804, "step": 10692 }, { "epoch": 0.6245911214953271, "grad_norm": 1.1902457475662231, "learning_rate": 6.52671855919663e-06, "loss": 0.7786, "step": 10693 }, { "epoch": 0.6246495327102803, "grad_norm": 1.3025628328323364, "learning_rate": 6.524944558630052e-06, "loss": 0.7748, "step": 10694 }, { "epoch": 0.6247079439252337, "grad_norm": 1.143852949142456, "learning_rate": 6.523170682437996e-06, "loss": 0.8698, "step": 10695 }, { "epoch": 0.624766355140187, "grad_norm": 1.1024458408355713, "learning_rate": 6.521396930683943e-06, "loss": 0.7608, "step": 10696 }, { "epoch": 0.6248247663551402, "grad_norm": 7.977809429168701, "learning_rate": 6.519623303431387e-06, "loss": 0.7172, "step": 10697 }, { "epoch": 0.6248831775700935, "grad_norm": 1.4233943223953247, "learning_rate": 6.5178498007438e-06, "loss": 0.6845, "step": 10698 }, { "epoch": 0.6249415887850467, "grad_norm": 0.9845978021621704, "learning_rate": 6.516076422684654e-06, "loss": 0.8979, "step": 10699 }, { "epoch": 0.625, "grad_norm": 1.0980117321014404, "learning_rate": 6.5143031693174286e-06, "loss": 0.7002, "step": 10700 }, { "epoch": 0.6250584112149533, "grad_norm": 1.1986520290374756, "learning_rate": 6.5125300407055814e-06, "loss": 0.6432, "step": 10701 }, { "epoch": 0.6251168224299065, "grad_norm": 0.9303235411643982, "learning_rate": 6.510757036912578e-06, "loss": 0.7314, "step": 10702 }, { "epoch": 0.6251752336448598, "grad_norm": 1.394158959388733, "learning_rate": 6.5089841580018755e-06, "loss": 0.8474, "step": 10703 }, { "epoch": 0.625233644859813, "grad_norm": 1.1885942220687866, "learning_rate": 6.507211404036922e-06, "loss": 0.9148, "step": 10704 }, { "epoch": 0.6252920560747663, "grad_norm": 0.9473317265510559, "learning_rate": 6.505438775081174e-06, "loss": 0.6556, "step": 10705 }, { "epoch": 0.6253504672897197, "grad_norm": 1.238074541091919, "learning_rate": 6.503666271198066e-06, "loss": 0.7892, "step": 10706 }, { "epoch": 0.6254088785046729, "grad_norm": 0.9114755988121033, "learning_rate": 6.501893892451042e-06, "loss": 0.7144, "step": 10707 }, { "epoch": 0.6254672897196262, "grad_norm": 1.4430845975875854, "learning_rate": 6.500121638903538e-06, "loss": 0.931, "step": 10708 }, { "epoch": 0.6255257009345795, "grad_norm": 1.2476577758789062, "learning_rate": 6.498349510618979e-06, "loss": 0.8503, "step": 10709 }, { "epoch": 0.6255841121495327, "grad_norm": 1.5992976427078247, "learning_rate": 6.496577507660795e-06, "loss": 0.686, "step": 10710 }, { "epoch": 0.625642523364486, "grad_norm": 1.1790333986282349, "learning_rate": 6.494805630092402e-06, "loss": 0.7233, "step": 10711 }, { "epoch": 0.6257009345794392, "grad_norm": 1.2184240818023682, "learning_rate": 6.493033877977224e-06, "loss": 0.8364, "step": 10712 }, { "epoch": 0.6257593457943925, "grad_norm": 1.643911361694336, "learning_rate": 6.491262251378669e-06, "loss": 0.7918, "step": 10713 }, { "epoch": 0.6258177570093458, "grad_norm": 0.877302348613739, "learning_rate": 6.489490750360143e-06, "loss": 0.6583, "step": 10714 }, { "epoch": 0.625876168224299, "grad_norm": 1.8106369972229004, "learning_rate": 6.4877193749850535e-06, "loss": 0.7661, "step": 10715 }, { "epoch": 0.6259345794392523, "grad_norm": 1.5487107038497925, "learning_rate": 6.4859481253167946e-06, "loss": 0.8583, "step": 10716 }, { "epoch": 0.6259929906542057, "grad_norm": 1.5866436958312988, "learning_rate": 6.484177001418767e-06, "loss": 0.6962, "step": 10717 }, { "epoch": 0.6260514018691589, "grad_norm": 1.4976434707641602, "learning_rate": 6.4824060033543535e-06, "loss": 0.9099, "step": 10718 }, { "epoch": 0.6261098130841122, "grad_norm": 1.6231850385665894, "learning_rate": 6.480635131186941e-06, "loss": 0.8431, "step": 10719 }, { "epoch": 0.6261682242990654, "grad_norm": 1.6321943998336792, "learning_rate": 6.4788643849799116e-06, "loss": 0.9135, "step": 10720 }, { "epoch": 0.6262266355140187, "grad_norm": 1.3829765319824219, "learning_rate": 6.4770937647966405e-06, "loss": 0.6875, "step": 10721 }, { "epoch": 0.626285046728972, "grad_norm": 1.2620725631713867, "learning_rate": 6.475323270700502e-06, "loss": 0.7417, "step": 10722 }, { "epoch": 0.6263434579439252, "grad_norm": 1.7053539752960205, "learning_rate": 6.473552902754862e-06, "loss": 0.7069, "step": 10723 }, { "epoch": 0.6264018691588785, "grad_norm": 1.0014208555221558, "learning_rate": 6.471782661023078e-06, "loss": 0.8083, "step": 10724 }, { "epoch": 0.6264602803738317, "grad_norm": 1.8901519775390625, "learning_rate": 6.470012545568518e-06, "loss": 0.8507, "step": 10725 }, { "epoch": 0.626518691588785, "grad_norm": 2.0762810707092285, "learning_rate": 6.468242556454527e-06, "loss": 0.885, "step": 10726 }, { "epoch": 0.6265771028037384, "grad_norm": 0.9696858525276184, "learning_rate": 6.4664726937444545e-06, "loss": 0.8184, "step": 10727 }, { "epoch": 0.6266355140186916, "grad_norm": 1.2935904264450073, "learning_rate": 6.464702957501651e-06, "loss": 0.7309, "step": 10728 }, { "epoch": 0.6266939252336449, "grad_norm": 1.2967820167541504, "learning_rate": 6.46293334778945e-06, "loss": 0.7014, "step": 10729 }, { "epoch": 0.6267523364485982, "grad_norm": 1.2490580081939697, "learning_rate": 6.461163864671196e-06, "loss": 0.7692, "step": 10730 }, { "epoch": 0.6268107476635514, "grad_norm": 1.5252765417099, "learning_rate": 6.45939450821021e-06, "loss": 0.8471, "step": 10731 }, { "epoch": 0.6268691588785047, "grad_norm": 1.0180933475494385, "learning_rate": 6.4576252784698215e-06, "loss": 0.7537, "step": 10732 }, { "epoch": 0.6269275700934579, "grad_norm": 1.131347417831421, "learning_rate": 6.455856175513357e-06, "loss": 0.8394, "step": 10733 }, { "epoch": 0.6269859813084112, "grad_norm": 1.3446027040481567, "learning_rate": 6.454087199404127e-06, "loss": 0.9563, "step": 10734 }, { "epoch": 0.6270443925233645, "grad_norm": 1.0459915399551392, "learning_rate": 6.452318350205449e-06, "loss": 0.8019, "step": 10735 }, { "epoch": 0.6271028037383177, "grad_norm": 1.0984187126159668, "learning_rate": 6.45054962798063e-06, "loss": 0.7499, "step": 10736 }, { "epoch": 0.627161214953271, "grad_norm": 1.3435754776000977, "learning_rate": 6.4487810327929726e-06, "loss": 0.731, "step": 10737 }, { "epoch": 0.6272196261682244, "grad_norm": 1.3395204544067383, "learning_rate": 6.447012564705779e-06, "loss": 0.8081, "step": 10738 }, { "epoch": 0.6272780373831776, "grad_norm": 1.4742134809494019, "learning_rate": 6.44524422378234e-06, "loss": 0.694, "step": 10739 }, { "epoch": 0.6273364485981309, "grad_norm": 1.238281011581421, "learning_rate": 6.443476010085949e-06, "loss": 0.9181, "step": 10740 }, { "epoch": 0.6273948598130841, "grad_norm": 1.107884407043457, "learning_rate": 6.441707923679891e-06, "loss": 0.8298, "step": 10741 }, { "epoch": 0.6274532710280374, "grad_norm": 1.322251558303833, "learning_rate": 6.439939964627442e-06, "loss": 0.6968, "step": 10742 }, { "epoch": 0.6275116822429907, "grad_norm": 1.0324262380599976, "learning_rate": 6.4381721329918855e-06, "loss": 0.8446, "step": 10743 }, { "epoch": 0.6275700934579439, "grad_norm": 1.0903273820877075, "learning_rate": 6.436404428836488e-06, "loss": 0.6555, "step": 10744 }, { "epoch": 0.6276285046728972, "grad_norm": 1.2191932201385498, "learning_rate": 6.434636852224521e-06, "loss": 0.6647, "step": 10745 }, { "epoch": 0.6276869158878504, "grad_norm": 1.1424474716186523, "learning_rate": 6.432869403219248e-06, "loss": 0.8909, "step": 10746 }, { "epoch": 0.6277453271028037, "grad_norm": 1.3817193508148193, "learning_rate": 6.43110208188392e-06, "loss": 0.6914, "step": 10747 }, { "epoch": 0.627803738317757, "grad_norm": 2.2587456703186035, "learning_rate": 6.429334888281795e-06, "loss": 0.855, "step": 10748 }, { "epoch": 0.6278621495327102, "grad_norm": 1.5550360679626465, "learning_rate": 6.427567822476123e-06, "loss": 0.7285, "step": 10749 }, { "epoch": 0.6279205607476636, "grad_norm": 1.1837942600250244, "learning_rate": 6.425800884530151e-06, "loss": 0.749, "step": 10750 }, { "epoch": 0.6279789719626169, "grad_norm": 1.629543662071228, "learning_rate": 6.424034074507113e-06, "loss": 0.851, "step": 10751 }, { "epoch": 0.6280373831775701, "grad_norm": 1.3852851390838623, "learning_rate": 6.422267392470245e-06, "loss": 0.6363, "step": 10752 }, { "epoch": 0.6280957943925234, "grad_norm": 1.8225951194763184, "learning_rate": 6.4205008384827805e-06, "loss": 0.8615, "step": 10753 }, { "epoch": 0.6281542056074766, "grad_norm": 1.507662296295166, "learning_rate": 6.4187344126079434e-06, "loss": 0.7985, "step": 10754 }, { "epoch": 0.6282126168224299, "grad_norm": 2.6992454528808594, "learning_rate": 6.416968114908959e-06, "loss": 0.6816, "step": 10755 }, { "epoch": 0.6282710280373832, "grad_norm": 2.661257743835449, "learning_rate": 6.415201945449041e-06, "loss": 0.6916, "step": 10756 }, { "epoch": 0.6283294392523364, "grad_norm": 2.0459704399108887, "learning_rate": 6.413435904291401e-06, "loss": 0.9054, "step": 10757 }, { "epoch": 0.6283878504672897, "grad_norm": 0.97248774766922, "learning_rate": 6.411669991499252e-06, "loss": 0.5121, "step": 10758 }, { "epoch": 0.628446261682243, "grad_norm": 1.2572672367095947, "learning_rate": 6.409904207135789e-06, "loss": 0.907, "step": 10759 }, { "epoch": 0.6285046728971962, "grad_norm": 1.509791374206543, "learning_rate": 6.408138551264216e-06, "loss": 0.7825, "step": 10760 }, { "epoch": 0.6285630841121496, "grad_norm": 1.327826738357544, "learning_rate": 6.406373023947728e-06, "loss": 0.9078, "step": 10761 }, { "epoch": 0.6286214953271028, "grad_norm": 1.3341782093048096, "learning_rate": 6.4046076252495085e-06, "loss": 0.93, "step": 10762 }, { "epoch": 0.6286799065420561, "grad_norm": 0.913532555103302, "learning_rate": 6.40284235523275e-06, "loss": 0.5095, "step": 10763 }, { "epoch": 0.6287383177570094, "grad_norm": 1.196022629737854, "learning_rate": 6.401077213960626e-06, "loss": 0.67, "step": 10764 }, { "epoch": 0.6287967289719626, "grad_norm": 0.9491350650787354, "learning_rate": 6.399312201496316e-06, "loss": 0.5549, "step": 10765 }, { "epoch": 0.6288551401869159, "grad_norm": 1.8891605138778687, "learning_rate": 6.397547317902992e-06, "loss": 0.9077, "step": 10766 }, { "epoch": 0.6289135514018691, "grad_norm": 5.868122577667236, "learning_rate": 6.395782563243814e-06, "loss": 0.8254, "step": 10767 }, { "epoch": 0.6289719626168224, "grad_norm": 1.2449554204940796, "learning_rate": 6.394017937581951e-06, "loss": 0.598, "step": 10768 }, { "epoch": 0.6290303738317757, "grad_norm": 1.3286476135253906, "learning_rate": 6.3922534409805536e-06, "loss": 0.6558, "step": 10769 }, { "epoch": 0.6290887850467289, "grad_norm": 1.2605347633361816, "learning_rate": 6.390489073502781e-06, "loss": 0.7896, "step": 10770 }, { "epoch": 0.6291471962616823, "grad_norm": 1.1858289241790771, "learning_rate": 6.3887248352117785e-06, "loss": 0.7724, "step": 10771 }, { "epoch": 0.6292056074766356, "grad_norm": 1.57454514503479, "learning_rate": 6.386960726170686e-06, "loss": 0.8919, "step": 10772 }, { "epoch": 0.6292640186915888, "grad_norm": 1.0593624114990234, "learning_rate": 6.385196746442644e-06, "loss": 0.7654, "step": 10773 }, { "epoch": 0.6293224299065421, "grad_norm": 1.1309590339660645, "learning_rate": 6.383432896090788e-06, "loss": 0.8417, "step": 10774 }, { "epoch": 0.6293808411214953, "grad_norm": 1.28717839717865, "learning_rate": 6.381669175178249e-06, "loss": 0.8314, "step": 10775 }, { "epoch": 0.6294392523364486, "grad_norm": 1.5609766244888306, "learning_rate": 6.379905583768149e-06, "loss": 0.9087, "step": 10776 }, { "epoch": 0.6294976635514019, "grad_norm": 1.2489949464797974, "learning_rate": 6.378142121923605e-06, "loss": 0.7448, "step": 10777 }, { "epoch": 0.6295560747663551, "grad_norm": 1.799302339553833, "learning_rate": 6.376378789707738e-06, "loss": 0.8592, "step": 10778 }, { "epoch": 0.6296144859813084, "grad_norm": 1.0051591396331787, "learning_rate": 6.374615587183654e-06, "loss": 0.6872, "step": 10779 }, { "epoch": 0.6296728971962616, "grad_norm": 2.0201923847198486, "learning_rate": 6.372852514414467e-06, "loss": 0.8801, "step": 10780 }, { "epoch": 0.6297313084112149, "grad_norm": 1.2494746446609497, "learning_rate": 6.371089571463271e-06, "loss": 0.7117, "step": 10781 }, { "epoch": 0.6297897196261683, "grad_norm": 1.3582634925842285, "learning_rate": 6.369326758393164e-06, "loss": 0.8869, "step": 10782 }, { "epoch": 0.6298481308411215, "grad_norm": 1.2157114744186401, "learning_rate": 6.367564075267243e-06, "loss": 0.8427, "step": 10783 }, { "epoch": 0.6299065420560748, "grad_norm": 1.6066392660140991, "learning_rate": 6.365801522148591e-06, "loss": 0.7171, "step": 10784 }, { "epoch": 0.6299649532710281, "grad_norm": 1.0031455755233765, "learning_rate": 6.36403909910029e-06, "loss": 0.7131, "step": 10785 }, { "epoch": 0.6300233644859813, "grad_norm": 1.1509807109832764, "learning_rate": 6.3622768061854214e-06, "loss": 0.8443, "step": 10786 }, { "epoch": 0.6300817757009346, "grad_norm": 2.288581132888794, "learning_rate": 6.360514643467055e-06, "loss": 0.9113, "step": 10787 }, { "epoch": 0.6301401869158878, "grad_norm": 1.1688333749771118, "learning_rate": 6.358752611008267e-06, "loss": 0.7879, "step": 10788 }, { "epoch": 0.6301985981308411, "grad_norm": 1.3540698289871216, "learning_rate": 6.356990708872116e-06, "loss": 0.7254, "step": 10789 }, { "epoch": 0.6302570093457944, "grad_norm": 1.8532906770706177, "learning_rate": 6.35522893712166e-06, "loss": 0.7306, "step": 10790 }, { "epoch": 0.6303154205607476, "grad_norm": 1.3384565114974976, "learning_rate": 6.353467295819962e-06, "loss": 0.8908, "step": 10791 }, { "epoch": 0.6303738317757009, "grad_norm": 1.4596710205078125, "learning_rate": 6.351705785030063e-06, "loss": 0.8177, "step": 10792 }, { "epoch": 0.6304322429906543, "grad_norm": 1.7233880758285522, "learning_rate": 6.349944404815014e-06, "loss": 0.6865, "step": 10793 }, { "epoch": 0.6304906542056075, "grad_norm": 1.2489863634109497, "learning_rate": 6.348183155237855e-06, "loss": 0.9238, "step": 10794 }, { "epoch": 0.6305490654205608, "grad_norm": 1.9520188570022583, "learning_rate": 6.346422036361619e-06, "loss": 0.7364, "step": 10795 }, { "epoch": 0.630607476635514, "grad_norm": 1.088663935661316, "learning_rate": 6.344661048249345e-06, "loss": 0.7134, "step": 10796 }, { "epoch": 0.6306658878504673, "grad_norm": 1.572878122329712, "learning_rate": 6.342900190964053e-06, "loss": 0.8322, "step": 10797 }, { "epoch": 0.6307242990654206, "grad_norm": 1.5064146518707275, "learning_rate": 6.341139464568768e-06, "loss": 0.7731, "step": 10798 }, { "epoch": 0.6307827102803738, "grad_norm": 1.4690155982971191, "learning_rate": 6.339378869126511e-06, "loss": 0.7316, "step": 10799 }, { "epoch": 0.6308411214953271, "grad_norm": 1.426448941230774, "learning_rate": 6.337618404700286e-06, "loss": 0.7846, "step": 10800 }, { "epoch": 0.6308995327102803, "grad_norm": 1.180380940437317, "learning_rate": 6.335858071353109e-06, "loss": 0.8293, "step": 10801 }, { "epoch": 0.6309579439252336, "grad_norm": 1.4735493659973145, "learning_rate": 6.334097869147978e-06, "loss": 0.7379, "step": 10802 }, { "epoch": 0.631016355140187, "grad_norm": 0.8904195427894592, "learning_rate": 6.3323377981478975e-06, "loss": 0.7195, "step": 10803 }, { "epoch": 0.6310747663551401, "grad_norm": 0.9394158124923706, "learning_rate": 6.330577858415861e-06, "loss": 0.7917, "step": 10804 }, { "epoch": 0.6311331775700935, "grad_norm": 1.1396121978759766, "learning_rate": 6.32881805001485e-06, "loss": 0.6708, "step": 10805 }, { "epoch": 0.6311915887850468, "grad_norm": 1.1619150638580322, "learning_rate": 6.3270583730078575e-06, "loss": 0.839, "step": 10806 }, { "epoch": 0.63125, "grad_norm": 1.7918421030044556, "learning_rate": 6.32529882745786e-06, "loss": 0.8057, "step": 10807 }, { "epoch": 0.6313084112149533, "grad_norm": 1.199101448059082, "learning_rate": 6.3235394134278374e-06, "loss": 0.7875, "step": 10808 }, { "epoch": 0.6313668224299065, "grad_norm": 1.1889928579330444, "learning_rate": 6.321780130980752e-06, "loss": 0.6403, "step": 10809 }, { "epoch": 0.6314252336448598, "grad_norm": 1.2370095252990723, "learning_rate": 6.320020980179575e-06, "loss": 0.9282, "step": 10810 }, { "epoch": 0.6314836448598131, "grad_norm": 1.293699860572815, "learning_rate": 6.318261961087268e-06, "loss": 0.6628, "step": 10811 }, { "epoch": 0.6315420560747663, "grad_norm": 1.4065645933151245, "learning_rate": 6.316503073766784e-06, "loss": 0.8262, "step": 10812 }, { "epoch": 0.6316004672897196, "grad_norm": 1.1998913288116455, "learning_rate": 6.314744318281081e-06, "loss": 0.7292, "step": 10813 }, { "epoch": 0.631658878504673, "grad_norm": 1.198997139930725, "learning_rate": 6.312985694693099e-06, "loss": 0.8336, "step": 10814 }, { "epoch": 0.6317172897196262, "grad_norm": 1.7128829956054688, "learning_rate": 6.311227203065783e-06, "loss": 0.7639, "step": 10815 }, { "epoch": 0.6317757009345795, "grad_norm": 1.1719950437545776, "learning_rate": 6.309468843462074e-06, "loss": 0.7159, "step": 10816 }, { "epoch": 0.6318341121495327, "grad_norm": 1.3949716091156006, "learning_rate": 6.307710615944897e-06, "loss": 0.7125, "step": 10817 }, { "epoch": 0.631892523364486, "grad_norm": 1.5542083978652954, "learning_rate": 6.305952520577188e-06, "loss": 0.7292, "step": 10818 }, { "epoch": 0.6319509345794393, "grad_norm": 1.6743590831756592, "learning_rate": 6.304194557421867e-06, "loss": 0.7248, "step": 10819 }, { "epoch": 0.6320093457943925, "grad_norm": 1.2513216733932495, "learning_rate": 6.30243672654185e-06, "loss": 0.7486, "step": 10820 }, { "epoch": 0.6320677570093458, "grad_norm": 1.1259117126464844, "learning_rate": 6.300679028000059e-06, "loss": 0.7425, "step": 10821 }, { "epoch": 0.632126168224299, "grad_norm": 1.2582676410675049, "learning_rate": 6.298921461859393e-06, "loss": 0.8674, "step": 10822 }, { "epoch": 0.6321845794392523, "grad_norm": 0.961378812789917, "learning_rate": 6.297164028182763e-06, "loss": 0.6962, "step": 10823 }, { "epoch": 0.6322429906542056, "grad_norm": 1.6160824298858643, "learning_rate": 6.2954067270330684e-06, "loss": 0.8332, "step": 10824 }, { "epoch": 0.6323014018691588, "grad_norm": 1.142964482307434, "learning_rate": 6.293649558473201e-06, "loss": 0.7537, "step": 10825 }, { "epoch": 0.6323598130841122, "grad_norm": 1.3129559755325317, "learning_rate": 6.291892522566054e-06, "loss": 0.8219, "step": 10826 }, { "epoch": 0.6324182242990655, "grad_norm": 0.7993046045303345, "learning_rate": 6.290135619374509e-06, "loss": 0.6618, "step": 10827 }, { "epoch": 0.6324766355140187, "grad_norm": 1.1223814487457275, "learning_rate": 6.288378848961453e-06, "loss": 0.7338, "step": 10828 }, { "epoch": 0.632535046728972, "grad_norm": 0.9626593589782715, "learning_rate": 6.286622211389759e-06, "loss": 0.7189, "step": 10829 }, { "epoch": 0.6325934579439252, "grad_norm": 1.4238325357437134, "learning_rate": 6.284865706722294e-06, "loss": 0.7456, "step": 10830 }, { "epoch": 0.6326518691588785, "grad_norm": 1.2781141996383667, "learning_rate": 6.283109335021931e-06, "loss": 0.8921, "step": 10831 }, { "epoch": 0.6327102803738318, "grad_norm": 1.60348641872406, "learning_rate": 6.281353096351526e-06, "loss": 0.7273, "step": 10832 }, { "epoch": 0.632768691588785, "grad_norm": 1.5047835111618042, "learning_rate": 6.279596990773943e-06, "loss": 0.6593, "step": 10833 }, { "epoch": 0.6328271028037383, "grad_norm": 1.060664415359497, "learning_rate": 6.2778410183520275e-06, "loss": 0.7805, "step": 10834 }, { "epoch": 0.6328855140186916, "grad_norm": 1.0836405754089355, "learning_rate": 6.276085179148628e-06, "loss": 0.7041, "step": 10835 }, { "epoch": 0.6329439252336448, "grad_norm": 1.784787893295288, "learning_rate": 6.2743294732265905e-06, "loss": 0.7462, "step": 10836 }, { "epoch": 0.6330023364485982, "grad_norm": 1.4173130989074707, "learning_rate": 6.2725739006487515e-06, "loss": 0.8084, "step": 10837 }, { "epoch": 0.6330607476635514, "grad_norm": 1.709357500076294, "learning_rate": 6.270818461477941e-06, "loss": 0.8384, "step": 10838 }, { "epoch": 0.6331191588785047, "grad_norm": 1.5313875675201416, "learning_rate": 6.269063155776991e-06, "loss": 0.7881, "step": 10839 }, { "epoch": 0.633177570093458, "grad_norm": 0.9848946928977966, "learning_rate": 6.267307983608721e-06, "loss": 0.7573, "step": 10840 }, { "epoch": 0.6332359813084112, "grad_norm": 1.3916021585464478, "learning_rate": 6.265552945035958e-06, "loss": 0.9424, "step": 10841 }, { "epoch": 0.6332943925233645, "grad_norm": 1.529570460319519, "learning_rate": 6.263798040121508e-06, "loss": 0.7685, "step": 10842 }, { "epoch": 0.6333528037383177, "grad_norm": 1.3047689199447632, "learning_rate": 6.262043268928181e-06, "loss": 0.8377, "step": 10843 }, { "epoch": 0.633411214953271, "grad_norm": 1.0142284631729126, "learning_rate": 6.260288631518785e-06, "loss": 0.6542, "step": 10844 }, { "epoch": 0.6334696261682243, "grad_norm": 1.238868236541748, "learning_rate": 6.258534127956115e-06, "loss": 0.7515, "step": 10845 }, { "epoch": 0.6335280373831775, "grad_norm": 2.2401928901672363, "learning_rate": 6.256779758302973e-06, "loss": 0.8217, "step": 10846 }, { "epoch": 0.6335864485981308, "grad_norm": 1.2191543579101562, "learning_rate": 6.2550255226221435e-06, "loss": 0.6801, "step": 10847 }, { "epoch": 0.6336448598130842, "grad_norm": 2.3884646892547607, "learning_rate": 6.2532714209764105e-06, "loss": 0.7675, "step": 10848 }, { "epoch": 0.6337032710280374, "grad_norm": 1.4700462818145752, "learning_rate": 6.2515174534285604e-06, "loss": 0.9136, "step": 10849 }, { "epoch": 0.6337616822429907, "grad_norm": 1.5307400226593018, "learning_rate": 6.249763620041363e-06, "loss": 0.7503, "step": 10850 }, { "epoch": 0.6338200934579439, "grad_norm": 1.034590721130371, "learning_rate": 6.248009920877591e-06, "loss": 0.7311, "step": 10851 }, { "epoch": 0.6338785046728972, "grad_norm": 1.471554160118103, "learning_rate": 6.246256356000012e-06, "loss": 0.8, "step": 10852 }, { "epoch": 0.6339369158878505, "grad_norm": 1.4870975017547607, "learning_rate": 6.2445029254713844e-06, "loss": 0.7925, "step": 10853 }, { "epoch": 0.6339953271028037, "grad_norm": 1.1012828350067139, "learning_rate": 6.24274962935447e-06, "loss": 0.669, "step": 10854 }, { "epoch": 0.634053738317757, "grad_norm": 1.4904556274414062, "learning_rate": 6.2409964677120125e-06, "loss": 0.7726, "step": 10855 }, { "epoch": 0.6341121495327103, "grad_norm": 1.1725929975509644, "learning_rate": 6.239243440606766e-06, "loss": 0.7425, "step": 10856 }, { "epoch": 0.6341705607476635, "grad_norm": 1.7397842407226562, "learning_rate": 6.23749054810147e-06, "loss": 0.9436, "step": 10857 }, { "epoch": 0.6342289719626168, "grad_norm": 1.1562981605529785, "learning_rate": 6.235737790258859e-06, "loss": 0.8028, "step": 10858 }, { "epoch": 0.63428738317757, "grad_norm": 0.960192084312439, "learning_rate": 6.23398516714167e-06, "loss": 0.6573, "step": 10859 }, { "epoch": 0.6343457943925234, "grad_norm": 2.0823986530303955, "learning_rate": 6.232232678812624e-06, "loss": 0.6888, "step": 10860 }, { "epoch": 0.6344042056074767, "grad_norm": 1.174407720565796, "learning_rate": 6.230480325334449e-06, "loss": 0.7173, "step": 10861 }, { "epoch": 0.6344626168224299, "grad_norm": 1.5955978631973267, "learning_rate": 6.228728106769866e-06, "loss": 0.8162, "step": 10862 }, { "epoch": 0.6345210280373832, "grad_norm": 1.2439121007919312, "learning_rate": 6.226976023181579e-06, "loss": 0.7401, "step": 10863 }, { "epoch": 0.6345794392523364, "grad_norm": 0.9281548261642456, "learning_rate": 6.225224074632303e-06, "loss": 0.5742, "step": 10864 }, { "epoch": 0.6346378504672897, "grad_norm": 1.888728380203247, "learning_rate": 6.223472261184738e-06, "loss": 0.8119, "step": 10865 }, { "epoch": 0.634696261682243, "grad_norm": 1.2438602447509766, "learning_rate": 6.221720582901587e-06, "loss": 0.7218, "step": 10866 }, { "epoch": 0.6347546728971962, "grad_norm": 1.2933145761489868, "learning_rate": 6.2199690398455385e-06, "loss": 0.7171, "step": 10867 }, { "epoch": 0.6348130841121495, "grad_norm": 1.2095547914505005, "learning_rate": 6.218217632079282e-06, "loss": 0.8584, "step": 10868 }, { "epoch": 0.6348714953271029, "grad_norm": 1.2421849966049194, "learning_rate": 6.216466359665504e-06, "loss": 0.8092, "step": 10869 }, { "epoch": 0.634929906542056, "grad_norm": 1.8798649311065674, "learning_rate": 6.21471522266688e-06, "loss": 0.8494, "step": 10870 }, { "epoch": 0.6349883177570094, "grad_norm": 1.0619680881500244, "learning_rate": 6.212964221146094e-06, "loss": 0.701, "step": 10871 }, { "epoch": 0.6350467289719626, "grad_norm": 1.2119135856628418, "learning_rate": 6.211213355165805e-06, "loss": 0.7275, "step": 10872 }, { "epoch": 0.6351051401869159, "grad_norm": 1.2149770259857178, "learning_rate": 6.2094626247886795e-06, "loss": 0.6831, "step": 10873 }, { "epoch": 0.6351635514018692, "grad_norm": 1.0226410627365112, "learning_rate": 6.207712030077382e-06, "loss": 0.8375, "step": 10874 }, { "epoch": 0.6352219626168224, "grad_norm": 1.217951774597168, "learning_rate": 6.2059615710945585e-06, "loss": 0.611, "step": 10875 }, { "epoch": 0.6352803738317757, "grad_norm": 4.688187599182129, "learning_rate": 6.204211247902872e-06, "loss": 0.9743, "step": 10876 }, { "epoch": 0.635338785046729, "grad_norm": 0.9911982417106628, "learning_rate": 6.202461060564959e-06, "loss": 0.7732, "step": 10877 }, { "epoch": 0.6353971962616822, "grad_norm": 1.658135175704956, "learning_rate": 6.200711009143459e-06, "loss": 0.7923, "step": 10878 }, { "epoch": 0.6354556074766355, "grad_norm": 1.1999441385269165, "learning_rate": 6.1989610937010134e-06, "loss": 0.7611, "step": 10879 }, { "epoch": 0.6355140186915887, "grad_norm": 1.3157775402069092, "learning_rate": 6.197211314300247e-06, "loss": 0.8512, "step": 10880 }, { "epoch": 0.6355724299065421, "grad_norm": 1.1042593717575073, "learning_rate": 6.1954616710037886e-06, "loss": 0.8131, "step": 10881 }, { "epoch": 0.6356308411214954, "grad_norm": 2.111621618270874, "learning_rate": 6.1937121638742615e-06, "loss": 0.7946, "step": 10882 }, { "epoch": 0.6356892523364486, "grad_norm": 1.0993908643722534, "learning_rate": 6.191962792974273e-06, "loss": 0.7154, "step": 10883 }, { "epoch": 0.6357476635514019, "grad_norm": 1.941693663597107, "learning_rate": 6.190213558366445e-06, "loss": 0.6115, "step": 10884 }, { "epoch": 0.6358060747663551, "grad_norm": 1.8143301010131836, "learning_rate": 6.188464460113374e-06, "loss": 0.7642, "step": 10885 }, { "epoch": 0.6358644859813084, "grad_norm": 1.2664836645126343, "learning_rate": 6.186715498277669e-06, "loss": 0.8004, "step": 10886 }, { "epoch": 0.6359228971962617, "grad_norm": 1.0101081132888794, "learning_rate": 6.184966672921926e-06, "loss": 0.7782, "step": 10887 }, { "epoch": 0.6359813084112149, "grad_norm": 2.13175630569458, "learning_rate": 6.183217984108729e-06, "loss": 0.7522, "step": 10888 }, { "epoch": 0.6360397196261682, "grad_norm": 1.2984617948532104, "learning_rate": 6.181469431900673e-06, "loss": 0.6837, "step": 10889 }, { "epoch": 0.6360981308411215, "grad_norm": 1.3149354457855225, "learning_rate": 6.179721016360335e-06, "loss": 0.6687, "step": 10890 }, { "epoch": 0.6361565420560747, "grad_norm": 1.1010493040084839, "learning_rate": 6.1779727375502975e-06, "loss": 0.7194, "step": 10891 }, { "epoch": 0.6362149532710281, "grad_norm": 1.1256191730499268, "learning_rate": 6.1762245955331266e-06, "loss": 0.8003, "step": 10892 }, { "epoch": 0.6362733644859813, "grad_norm": 0.9857245683670044, "learning_rate": 6.17447659037139e-06, "loss": 0.736, "step": 10893 }, { "epoch": 0.6363317757009346, "grad_norm": 1.2680569887161255, "learning_rate": 6.172728722127652e-06, "loss": 0.7069, "step": 10894 }, { "epoch": 0.6363901869158879, "grad_norm": 1.3556617498397827, "learning_rate": 6.170980990864472e-06, "loss": 0.703, "step": 10895 }, { "epoch": 0.6364485981308411, "grad_norm": 1.1861445903778076, "learning_rate": 6.169233396644397e-06, "loss": 0.7469, "step": 10896 }, { "epoch": 0.6365070093457944, "grad_norm": 1.3318562507629395, "learning_rate": 6.16748593952998e-06, "loss": 0.6789, "step": 10897 }, { "epoch": 0.6365654205607477, "grad_norm": 1.0191808938980103, "learning_rate": 6.165738619583758e-06, "loss": 0.7538, "step": 10898 }, { "epoch": 0.6366238317757009, "grad_norm": 1.5671014785766602, "learning_rate": 6.163991436868276e-06, "loss": 0.8955, "step": 10899 }, { "epoch": 0.6366822429906542, "grad_norm": 1.137906789779663, "learning_rate": 6.162244391446061e-06, "loss": 0.7967, "step": 10900 }, { "epoch": 0.6367406542056074, "grad_norm": 2.4077677726745605, "learning_rate": 6.16049748337964e-06, "loss": 0.8388, "step": 10901 }, { "epoch": 0.6367990654205608, "grad_norm": 1.1912347078323364, "learning_rate": 6.15875071273154e-06, "loss": 0.7908, "step": 10902 }, { "epoch": 0.6368574766355141, "grad_norm": 2.0274884700775146, "learning_rate": 6.157004079564277e-06, "loss": 0.8099, "step": 10903 }, { "epoch": 0.6369158878504673, "grad_norm": 1.9255146980285645, "learning_rate": 6.155257583940369e-06, "loss": 0.8334, "step": 10904 }, { "epoch": 0.6369742990654206, "grad_norm": 1.4417158365249634, "learning_rate": 6.153511225922317e-06, "loss": 0.844, "step": 10905 }, { "epoch": 0.6370327102803738, "grad_norm": 1.9276398420333862, "learning_rate": 6.1517650055726274e-06, "loss": 0.8461, "step": 10906 }, { "epoch": 0.6370911214953271, "grad_norm": 1.416599988937378, "learning_rate": 6.1500189229538e-06, "loss": 0.7614, "step": 10907 }, { "epoch": 0.6371495327102804, "grad_norm": 1.2950254678726196, "learning_rate": 6.148272978128322e-06, "loss": 0.7845, "step": 10908 }, { "epoch": 0.6372079439252336, "grad_norm": 1.3316630125045776, "learning_rate": 6.146527171158692e-06, "loss": 0.6888, "step": 10909 }, { "epoch": 0.6372663551401869, "grad_norm": 1.2491060495376587, "learning_rate": 6.144781502107388e-06, "loss": 0.6649, "step": 10910 }, { "epoch": 0.6373247663551402, "grad_norm": 1.4415796995162964, "learning_rate": 6.1430359710368845e-06, "loss": 0.998, "step": 10911 }, { "epoch": 0.6373831775700934, "grad_norm": 2.325777292251587, "learning_rate": 6.141290578009664e-06, "loss": 0.8724, "step": 10912 }, { "epoch": 0.6374415887850468, "grad_norm": 1.66732919216156, "learning_rate": 6.1395453230881884e-06, "loss": 0.9337, "step": 10913 }, { "epoch": 0.6375, "grad_norm": 1.1517002582550049, "learning_rate": 6.137800206334925e-06, "loss": 0.8482, "step": 10914 }, { "epoch": 0.6375584112149533, "grad_norm": 1.124853491783142, "learning_rate": 6.136055227812334e-06, "loss": 0.6763, "step": 10915 }, { "epoch": 0.6376168224299066, "grad_norm": 1.2320271730422974, "learning_rate": 6.134310387582862e-06, "loss": 0.6032, "step": 10916 }, { "epoch": 0.6376752336448598, "grad_norm": 2.006805896759033, "learning_rate": 6.132565685708967e-06, "loss": 0.8522, "step": 10917 }, { "epoch": 0.6377336448598131, "grad_norm": 1.1257022619247437, "learning_rate": 6.130821122253086e-06, "loss": 0.715, "step": 10918 }, { "epoch": 0.6377920560747663, "grad_norm": 1.3079819679260254, "learning_rate": 6.1290766972776624e-06, "loss": 0.8113, "step": 10919 }, { "epoch": 0.6378504672897196, "grad_norm": 0.9297521710395813, "learning_rate": 6.127332410845131e-06, "loss": 0.501, "step": 10920 }, { "epoch": 0.6379088785046729, "grad_norm": 1.5213121175765991, "learning_rate": 6.125588263017915e-06, "loss": 0.7286, "step": 10921 }, { "epoch": 0.6379672897196261, "grad_norm": 2.0689587593078613, "learning_rate": 6.123844253858445e-06, "loss": 0.7838, "step": 10922 }, { "epoch": 0.6380257009345794, "grad_norm": 1.6906132698059082, "learning_rate": 6.122100383429136e-06, "loss": 0.9186, "step": 10923 }, { "epoch": 0.6380841121495328, "grad_norm": 1.0624380111694336, "learning_rate": 6.120356651792407e-06, "loss": 0.7114, "step": 10924 }, { "epoch": 0.638142523364486, "grad_norm": 1.3350706100463867, "learning_rate": 6.118613059010663e-06, "loss": 0.7523, "step": 10925 }, { "epoch": 0.6382009345794393, "grad_norm": 1.1528797149658203, "learning_rate": 6.1168696051463084e-06, "loss": 0.6127, "step": 10926 }, { "epoch": 0.6382593457943925, "grad_norm": 1.093892216682434, "learning_rate": 6.115126290261746e-06, "loss": 0.8438, "step": 10927 }, { "epoch": 0.6383177570093458, "grad_norm": 2.120537519454956, "learning_rate": 6.1133831144193645e-06, "loss": 0.8984, "step": 10928 }, { "epoch": 0.6383761682242991, "grad_norm": 1.0615772008895874, "learning_rate": 6.111640077681562e-06, "loss": 0.6828, "step": 10929 }, { "epoch": 0.6384345794392523, "grad_norm": 1.4282041788101196, "learning_rate": 6.109897180110716e-06, "loss": 0.844, "step": 10930 }, { "epoch": 0.6384929906542056, "grad_norm": 1.4267644882202148, "learning_rate": 6.108154421769203e-06, "loss": 0.8178, "step": 10931 }, { "epoch": 0.6385514018691589, "grad_norm": 1.6408634185791016, "learning_rate": 6.106411802719409e-06, "loss": 1.0052, "step": 10932 }, { "epoch": 0.6386098130841121, "grad_norm": 1.0489152669906616, "learning_rate": 6.10466932302369e-06, "loss": 0.6988, "step": 10933 }, { "epoch": 0.6386682242990654, "grad_norm": 1.1184648275375366, "learning_rate": 6.102926982744423e-06, "loss": 0.7553, "step": 10934 }, { "epoch": 0.6387266355140186, "grad_norm": 1.0451205968856812, "learning_rate": 6.10118478194396e-06, "loss": 0.8952, "step": 10935 }, { "epoch": 0.638785046728972, "grad_norm": 1.4100561141967773, "learning_rate": 6.099442720684654e-06, "loss": 0.9483, "step": 10936 }, { "epoch": 0.6388434579439253, "grad_norm": 1.4282329082489014, "learning_rate": 6.097700799028863e-06, "loss": 0.8348, "step": 10937 }, { "epoch": 0.6389018691588785, "grad_norm": 0.9941645264625549, "learning_rate": 6.095959017038922e-06, "loss": 0.8135, "step": 10938 }, { "epoch": 0.6389602803738318, "grad_norm": 1.8011573553085327, "learning_rate": 6.094217374777176e-06, "loss": 1.0748, "step": 10939 }, { "epoch": 0.639018691588785, "grad_norm": 2.358814001083374, "learning_rate": 6.09247587230596e-06, "loss": 0.7679, "step": 10940 }, { "epoch": 0.6390771028037383, "grad_norm": 1.4318439960479736, "learning_rate": 6.090734509687597e-06, "loss": 0.7587, "step": 10941 }, { "epoch": 0.6391355140186916, "grad_norm": 1.0546292066574097, "learning_rate": 6.088993286984422e-06, "loss": 0.7529, "step": 10942 }, { "epoch": 0.6391939252336448, "grad_norm": 0.7254908680915833, "learning_rate": 6.087252204258745e-06, "loss": 0.5117, "step": 10943 }, { "epoch": 0.6392523364485981, "grad_norm": 1.7290358543395996, "learning_rate": 6.085511261572885e-06, "loss": 0.6284, "step": 10944 }, { "epoch": 0.6393107476635514, "grad_norm": 1.8674529790878296, "learning_rate": 6.083770458989154e-06, "loss": 0.839, "step": 10945 }, { "epoch": 0.6393691588785047, "grad_norm": 1.5039292573928833, "learning_rate": 6.0820297965698495e-06, "loss": 0.7451, "step": 10946 }, { "epoch": 0.639427570093458, "grad_norm": 1.4663362503051758, "learning_rate": 6.080289274377276e-06, "loss": 0.9291, "step": 10947 }, { "epoch": 0.6394859813084112, "grad_norm": 1.1633985042572021, "learning_rate": 6.078548892473725e-06, "loss": 0.7805, "step": 10948 }, { "epoch": 0.6395443925233645, "grad_norm": 1.2258317470550537, "learning_rate": 6.07680865092149e-06, "loss": 1.0951, "step": 10949 }, { "epoch": 0.6396028037383178, "grad_norm": 1.2083333730697632, "learning_rate": 6.075068549782853e-06, "loss": 0.793, "step": 10950 }, { "epoch": 0.639661214953271, "grad_norm": 1.2048325538635254, "learning_rate": 6.073328589120091e-06, "loss": 0.8498, "step": 10951 }, { "epoch": 0.6397196261682243, "grad_norm": 1.31582772731781, "learning_rate": 6.071588768995483e-06, "loss": 0.7774, "step": 10952 }, { "epoch": 0.6397780373831776, "grad_norm": 1.677970051765442, "learning_rate": 6.0698490894712955e-06, "loss": 0.8303, "step": 10953 }, { "epoch": 0.6398364485981308, "grad_norm": 1.0833837985992432, "learning_rate": 6.0681095506097906e-06, "loss": 0.6746, "step": 10954 }, { "epoch": 0.6398948598130841, "grad_norm": 1.3075921535491943, "learning_rate": 6.066370152473233e-06, "loss": 0.6282, "step": 10955 }, { "epoch": 0.6399532710280373, "grad_norm": 1.2448123693466187, "learning_rate": 6.064630895123871e-06, "loss": 0.687, "step": 10956 }, { "epoch": 0.6400116822429907, "grad_norm": 1.204217791557312, "learning_rate": 6.062891778623961e-06, "loss": 0.8078, "step": 10957 }, { "epoch": 0.640070093457944, "grad_norm": 1.224246859550476, "learning_rate": 6.061152803035741e-06, "loss": 0.8533, "step": 10958 }, { "epoch": 0.6401285046728972, "grad_norm": 1.4023720026016235, "learning_rate": 6.05941396842145e-06, "loss": 0.6415, "step": 10959 }, { "epoch": 0.6401869158878505, "grad_norm": 1.0667327642440796, "learning_rate": 6.057675274843327e-06, "loss": 0.7166, "step": 10960 }, { "epoch": 0.6402453271028037, "grad_norm": 1.7020134925842285, "learning_rate": 6.055936722363596e-06, "loss": 0.7423, "step": 10961 }, { "epoch": 0.640303738317757, "grad_norm": 1.1174557209014893, "learning_rate": 6.054198311044486e-06, "loss": 0.812, "step": 10962 }, { "epoch": 0.6403621495327103, "grad_norm": 1.0002104043960571, "learning_rate": 6.052460040948212e-06, "loss": 0.7824, "step": 10963 }, { "epoch": 0.6404205607476635, "grad_norm": 1.5424331426620483, "learning_rate": 6.050721912136985e-06, "loss": 0.9195, "step": 10964 }, { "epoch": 0.6404789719626168, "grad_norm": 1.2644129991531372, "learning_rate": 6.048983924673022e-06, "loss": 0.8632, "step": 10965 }, { "epoch": 0.6405373831775701, "grad_norm": 1.2311935424804688, "learning_rate": 6.047246078618516e-06, "loss": 0.7435, "step": 10966 }, { "epoch": 0.6405957943925233, "grad_norm": 1.800491213798523, "learning_rate": 6.045508374035678e-06, "loss": 0.7738, "step": 10967 }, { "epoch": 0.6406542056074767, "grad_norm": 1.8366979360580444, "learning_rate": 6.0437708109866945e-06, "loss": 0.7198, "step": 10968 }, { "epoch": 0.6407126168224299, "grad_norm": 1.2136242389678955, "learning_rate": 6.0420333895337525e-06, "loss": 0.7235, "step": 10969 }, { "epoch": 0.6407710280373832, "grad_norm": 1.3161253929138184, "learning_rate": 6.040296109739041e-06, "loss": 0.6347, "step": 10970 }, { "epoch": 0.6408294392523365, "grad_norm": 2.071608781814575, "learning_rate": 6.0385589716647316e-06, "loss": 0.7326, "step": 10971 }, { "epoch": 0.6408878504672897, "grad_norm": 1.0445221662521362, "learning_rate": 6.036821975373004e-06, "loss": 0.7595, "step": 10972 }, { "epoch": 0.640946261682243, "grad_norm": 1.5193949937820435, "learning_rate": 6.035085120926025e-06, "loss": 0.7721, "step": 10973 }, { "epoch": 0.6410046728971963, "grad_norm": 1.1544082164764404, "learning_rate": 6.03334840838595e-06, "loss": 0.6786, "step": 10974 }, { "epoch": 0.6410630841121495, "grad_norm": 3.239004135131836, "learning_rate": 6.031611837814951e-06, "loss": 0.7717, "step": 10975 }, { "epoch": 0.6411214953271028, "grad_norm": 2.824522018432617, "learning_rate": 6.02987540927517e-06, "loss": 0.5358, "step": 10976 }, { "epoch": 0.641179906542056, "grad_norm": 4.767365455627441, "learning_rate": 6.028139122828759e-06, "loss": 0.6829, "step": 10977 }, { "epoch": 0.6412383177570093, "grad_norm": 1.1584680080413818, "learning_rate": 6.026402978537862e-06, "loss": 0.8009, "step": 10978 }, { "epoch": 0.6412967289719627, "grad_norm": 1.2344974279403687, "learning_rate": 6.0246669764646126e-06, "loss": 0.8356, "step": 10979 }, { "epoch": 0.6413551401869159, "grad_norm": 1.3741563558578491, "learning_rate": 6.022931116671147e-06, "loss": 0.7155, "step": 10980 }, { "epoch": 0.6414135514018692, "grad_norm": 1.4439353942871094, "learning_rate": 6.021195399219591e-06, "loss": 0.8968, "step": 10981 }, { "epoch": 0.6414719626168224, "grad_norm": 1.0095090866088867, "learning_rate": 6.019459824172069e-06, "loss": 0.7814, "step": 10982 }, { "epoch": 0.6415303738317757, "grad_norm": 1.239699125289917, "learning_rate": 6.017724391590698e-06, "loss": 0.8714, "step": 10983 }, { "epoch": 0.641588785046729, "grad_norm": 1.3310707807540894, "learning_rate": 6.015989101537586e-06, "loss": 0.7808, "step": 10984 }, { "epoch": 0.6416471962616822, "grad_norm": 1.126220703125, "learning_rate": 6.014253954074847e-06, "loss": 0.6843, "step": 10985 }, { "epoch": 0.6417056074766355, "grad_norm": 1.0478044748306274, "learning_rate": 6.012518949264576e-06, "loss": 0.6183, "step": 10986 }, { "epoch": 0.6417640186915888, "grad_norm": 5.831762313842773, "learning_rate": 6.010784087168877e-06, "loss": 0.7185, "step": 10987 }, { "epoch": 0.641822429906542, "grad_norm": 1.1223410367965698, "learning_rate": 6.009049367849839e-06, "loss": 0.6918, "step": 10988 }, { "epoch": 0.6418808411214953, "grad_norm": 1.6863354444503784, "learning_rate": 6.007314791369545e-06, "loss": 0.6269, "step": 10989 }, { "epoch": 0.6419392523364486, "grad_norm": 1.0143650770187378, "learning_rate": 6.005580357790084e-06, "loss": 0.5778, "step": 10990 }, { "epoch": 0.6419976635514019, "grad_norm": 1.4736984968185425, "learning_rate": 6.003846067173522e-06, "loss": 0.7423, "step": 10991 }, { "epoch": 0.6420560747663552, "grad_norm": 1.5718101263046265, "learning_rate": 6.002111919581942e-06, "loss": 0.6808, "step": 10992 }, { "epoch": 0.6421144859813084, "grad_norm": 1.116304636001587, "learning_rate": 6.000377915077404e-06, "loss": 0.7684, "step": 10993 }, { "epoch": 0.6421728971962617, "grad_norm": 1.4140444993972778, "learning_rate": 5.9986440537219695e-06, "loss": 0.9397, "step": 10994 }, { "epoch": 0.642231308411215, "grad_norm": 1.6614463329315186, "learning_rate": 5.996910335577697e-06, "loss": 0.8906, "step": 10995 }, { "epoch": 0.6422897196261682, "grad_norm": 1.1500897407531738, "learning_rate": 5.995176760706632e-06, "loss": 0.7294, "step": 10996 }, { "epoch": 0.6423481308411215, "grad_norm": 1.337302327156067, "learning_rate": 5.993443329170827e-06, "loss": 0.7996, "step": 10997 }, { "epoch": 0.6424065420560747, "grad_norm": 1.3904666900634766, "learning_rate": 5.991710041032321e-06, "loss": 0.8721, "step": 10998 }, { "epoch": 0.642464953271028, "grad_norm": 1.2086310386657715, "learning_rate": 5.989976896353143e-06, "loss": 0.777, "step": 10999 }, { "epoch": 0.6425233644859814, "grad_norm": 0.9692435264587402, "learning_rate": 5.988243895195334e-06, "loss": 0.7757, "step": 11000 }, { "epoch": 0.6425817757009346, "grad_norm": 1.0813202857971191, "learning_rate": 5.986511037620909e-06, "loss": 0.6324, "step": 11001 }, { "epoch": 0.6426401869158879, "grad_norm": 1.023199200630188, "learning_rate": 5.984778323691896e-06, "loss": 0.7082, "step": 11002 }, { "epoch": 0.6426985981308411, "grad_norm": 1.5166208744049072, "learning_rate": 5.983045753470308e-06, "loss": 0.7613, "step": 11003 }, { "epoch": 0.6427570093457944, "grad_norm": 2.86191463470459, "learning_rate": 5.98131332701815e-06, "loss": 0.9404, "step": 11004 }, { "epoch": 0.6428154205607477, "grad_norm": 0.9399176239967346, "learning_rate": 5.9795810443974335e-06, "loss": 0.7822, "step": 11005 }, { "epoch": 0.6428738317757009, "grad_norm": 1.3369375467300415, "learning_rate": 5.977848905670152e-06, "loss": 0.7123, "step": 11006 }, { "epoch": 0.6429322429906542, "grad_norm": 1.1012334823608398, "learning_rate": 5.976116910898304e-06, "loss": 0.7994, "step": 11007 }, { "epoch": 0.6429906542056075, "grad_norm": 1.0287437438964844, "learning_rate": 5.974385060143879e-06, "loss": 0.8718, "step": 11008 }, { "epoch": 0.6430490654205607, "grad_norm": 1.4779715538024902, "learning_rate": 5.972653353468858e-06, "loss": 0.7177, "step": 11009 }, { "epoch": 0.643107476635514, "grad_norm": 1.1022449731826782, "learning_rate": 5.970921790935221e-06, "loss": 0.8454, "step": 11010 }, { "epoch": 0.6431658878504672, "grad_norm": 0.9690074920654297, "learning_rate": 5.9691903726049465e-06, "loss": 0.714, "step": 11011 }, { "epoch": 0.6432242990654206, "grad_norm": 1.4763308763504028, "learning_rate": 5.967459098539994e-06, "loss": 0.7558, "step": 11012 }, { "epoch": 0.6432827102803739, "grad_norm": 1.20870840549469, "learning_rate": 5.965727968802333e-06, "loss": 0.7254, "step": 11013 }, { "epoch": 0.6433411214953271, "grad_norm": 0.9111003875732422, "learning_rate": 5.963996983453919e-06, "loss": 0.6592, "step": 11014 }, { "epoch": 0.6433995327102804, "grad_norm": 1.1192688941955566, "learning_rate": 5.962266142556712e-06, "loss": 0.7999, "step": 11015 }, { "epoch": 0.6434579439252337, "grad_norm": 1.1479231119155884, "learning_rate": 5.960535446172651e-06, "loss": 0.7792, "step": 11016 }, { "epoch": 0.6435163551401869, "grad_norm": 0.9435920715332031, "learning_rate": 5.958804894363681e-06, "loss": 0.6382, "step": 11017 }, { "epoch": 0.6435747663551402, "grad_norm": 1.1666498184204102, "learning_rate": 5.957074487191743e-06, "loss": 0.7017, "step": 11018 }, { "epoch": 0.6436331775700934, "grad_norm": 1.1404786109924316, "learning_rate": 5.955344224718764e-06, "loss": 0.7582, "step": 11019 }, { "epoch": 0.6436915887850467, "grad_norm": 1.8374810218811035, "learning_rate": 5.95361410700668e-06, "loss": 0.842, "step": 11020 }, { "epoch": 0.64375, "grad_norm": 1.4530287981033325, "learning_rate": 5.951884134117406e-06, "loss": 0.7637, "step": 11021 }, { "epoch": 0.6438084112149532, "grad_norm": 2.03863525390625, "learning_rate": 5.950154306112859e-06, "loss": 0.835, "step": 11022 }, { "epoch": 0.6438668224299066, "grad_norm": 5.817525386810303, "learning_rate": 5.948424623054954e-06, "loss": 0.929, "step": 11023 }, { "epoch": 0.6439252336448598, "grad_norm": 1.4620803594589233, "learning_rate": 5.946695085005591e-06, "loss": 0.8585, "step": 11024 }, { "epoch": 0.6439836448598131, "grad_norm": 1.5499122142791748, "learning_rate": 5.944965692026683e-06, "loss": 0.7037, "step": 11025 }, { "epoch": 0.6440420560747664, "grad_norm": 1.294594645500183, "learning_rate": 5.943236444180116e-06, "loss": 0.7069, "step": 11026 }, { "epoch": 0.6441004672897196, "grad_norm": 1.0535187721252441, "learning_rate": 5.941507341527781e-06, "loss": 0.7321, "step": 11027 }, { "epoch": 0.6441588785046729, "grad_norm": 1.4269076585769653, "learning_rate": 5.939778384131573e-06, "loss": 0.7383, "step": 11028 }, { "epoch": 0.6442172897196262, "grad_norm": 1.8479334115982056, "learning_rate": 5.938049572053362e-06, "loss": 0.7554, "step": 11029 }, { "epoch": 0.6442757009345794, "grad_norm": 1.3740509748458862, "learning_rate": 5.936320905355029e-06, "loss": 0.6956, "step": 11030 }, { "epoch": 0.6443341121495327, "grad_norm": 1.1989624500274658, "learning_rate": 5.934592384098443e-06, "loss": 0.7844, "step": 11031 }, { "epoch": 0.6443925233644859, "grad_norm": 1.6015315055847168, "learning_rate": 5.932864008345464e-06, "loss": 0.8095, "step": 11032 }, { "epoch": 0.6444509345794392, "grad_norm": 1.6132185459136963, "learning_rate": 5.931135778157964e-06, "loss": 0.8769, "step": 11033 }, { "epoch": 0.6445093457943926, "grad_norm": 1.1484254598617554, "learning_rate": 5.929407693597783e-06, "loss": 0.7441, "step": 11034 }, { "epoch": 0.6445677570093458, "grad_norm": 1.30441153049469, "learning_rate": 5.927679754726781e-06, "loss": 0.7882, "step": 11035 }, { "epoch": 0.6446261682242991, "grad_norm": 1.238275170326233, "learning_rate": 5.925951961606799e-06, "loss": 0.7097, "step": 11036 }, { "epoch": 0.6446845794392523, "grad_norm": 2.009579658508301, "learning_rate": 5.924224314299672e-06, "loss": 0.8375, "step": 11037 }, { "epoch": 0.6447429906542056, "grad_norm": 1.6475392580032349, "learning_rate": 5.9224968128672376e-06, "loss": 0.8157, "step": 11038 }, { "epoch": 0.6448014018691589, "grad_norm": 1.4611413478851318, "learning_rate": 5.920769457371323e-06, "loss": 0.7635, "step": 11039 }, { "epoch": 0.6448598130841121, "grad_norm": 1.2580242156982422, "learning_rate": 5.919042247873752e-06, "loss": 0.825, "step": 11040 }, { "epoch": 0.6449182242990654, "grad_norm": 1.3345706462860107, "learning_rate": 5.917315184436345e-06, "loss": 0.643, "step": 11041 }, { "epoch": 0.6449766355140187, "grad_norm": 2.3749122619628906, "learning_rate": 5.9155882671209085e-06, "loss": 0.8167, "step": 11042 }, { "epoch": 0.6450350467289719, "grad_norm": 1.505549430847168, "learning_rate": 5.913861495989255e-06, "loss": 0.9152, "step": 11043 }, { "epoch": 0.6450934579439253, "grad_norm": 1.1903483867645264, "learning_rate": 5.912134871103183e-06, "loss": 0.7926, "step": 11044 }, { "epoch": 0.6451518691588785, "grad_norm": 2.080944299697876, "learning_rate": 5.910408392524495e-06, "loss": 0.938, "step": 11045 }, { "epoch": 0.6452102803738318, "grad_norm": 1.0877512693405151, "learning_rate": 5.908682060314979e-06, "loss": 0.7293, "step": 11046 }, { "epoch": 0.6452686915887851, "grad_norm": 1.366634726524353, "learning_rate": 5.906955874536419e-06, "loss": 0.9152, "step": 11047 }, { "epoch": 0.6453271028037383, "grad_norm": 1.1073824167251587, "learning_rate": 5.905229835250605e-06, "loss": 0.7177, "step": 11048 }, { "epoch": 0.6453855140186916, "grad_norm": 1.537408471107483, "learning_rate": 5.903503942519299e-06, "loss": 0.7859, "step": 11049 }, { "epoch": 0.6454439252336449, "grad_norm": 1.5332168340682983, "learning_rate": 5.901778196404289e-06, "loss": 0.835, "step": 11050 }, { "epoch": 0.6455023364485981, "grad_norm": 1.8116583824157715, "learning_rate": 5.9000525969673295e-06, "loss": 0.7128, "step": 11051 }, { "epoch": 0.6455607476635514, "grad_norm": 1.241256594657898, "learning_rate": 5.898327144270179e-06, "loss": 0.7527, "step": 11052 }, { "epoch": 0.6456191588785046, "grad_norm": 1.1691864728927612, "learning_rate": 5.896601838374603e-06, "loss": 0.8322, "step": 11053 }, { "epoch": 0.6456775700934579, "grad_norm": 1.2151579856872559, "learning_rate": 5.894876679342342e-06, "loss": 0.8057, "step": 11054 }, { "epoch": 0.6457359813084113, "grad_norm": 1.2095921039581299, "learning_rate": 5.893151667235144e-06, "loss": 0.7366, "step": 11055 }, { "epoch": 0.6457943925233645, "grad_norm": 1.058630347251892, "learning_rate": 5.8914268021147514e-06, "loss": 0.7727, "step": 11056 }, { "epoch": 0.6458528037383178, "grad_norm": 1.555424690246582, "learning_rate": 5.889702084042889e-06, "loss": 0.962, "step": 11057 }, { "epoch": 0.645911214953271, "grad_norm": 1.0321847200393677, "learning_rate": 5.887977513081297e-06, "loss": 0.801, "step": 11058 }, { "epoch": 0.6459696261682243, "grad_norm": 1.0070024728775024, "learning_rate": 5.886253089291689e-06, "loss": 0.8579, "step": 11059 }, { "epoch": 0.6460280373831776, "grad_norm": 1.0715197324752808, "learning_rate": 5.8845288127357905e-06, "loss": 0.7438, "step": 11060 }, { "epoch": 0.6460864485981308, "grad_norm": 1.4047514200210571, "learning_rate": 5.882804683475314e-06, "loss": 0.6999, "step": 11061 }, { "epoch": 0.6461448598130841, "grad_norm": 1.1698843240737915, "learning_rate": 5.88108070157196e-06, "loss": 0.8847, "step": 11062 }, { "epoch": 0.6462032710280374, "grad_norm": 1.4170546531677246, "learning_rate": 5.879356867087439e-06, "loss": 0.8579, "step": 11063 }, { "epoch": 0.6462616822429906, "grad_norm": 1.1860431432724, "learning_rate": 5.877633180083443e-06, "loss": 0.8981, "step": 11064 }, { "epoch": 0.646320093457944, "grad_norm": 1.3382320404052734, "learning_rate": 5.875909640621667e-06, "loss": 0.8312, "step": 11065 }, { "epoch": 0.6463785046728971, "grad_norm": 1.0247400999069214, "learning_rate": 5.8741862487638e-06, "loss": 0.6781, "step": 11066 }, { "epoch": 0.6464369158878505, "grad_norm": 1.1998685598373413, "learning_rate": 5.8724630045715145e-06, "loss": 0.7173, "step": 11067 }, { "epoch": 0.6464953271028038, "grad_norm": 1.2165727615356445, "learning_rate": 5.870739908106496e-06, "loss": 0.8435, "step": 11068 }, { "epoch": 0.646553738317757, "grad_norm": 1.021438479423523, "learning_rate": 5.869016959430412e-06, "loss": 0.7372, "step": 11069 }, { "epoch": 0.6466121495327103, "grad_norm": 1.6773838996887207, "learning_rate": 5.867294158604921e-06, "loss": 0.8703, "step": 11070 }, { "epoch": 0.6466705607476636, "grad_norm": 1.2020574808120728, "learning_rate": 5.865571505691694e-06, "loss": 0.8882, "step": 11071 }, { "epoch": 0.6467289719626168, "grad_norm": 1.0407572984695435, "learning_rate": 5.86384900075238e-06, "loss": 0.678, "step": 11072 }, { "epoch": 0.6467873831775701, "grad_norm": 1.4513471126556396, "learning_rate": 5.86212664384863e-06, "loss": 0.6962, "step": 11073 }, { "epoch": 0.6468457943925233, "grad_norm": 1.3856879472732544, "learning_rate": 5.860404435042091e-06, "loss": 0.9484, "step": 11074 }, { "epoch": 0.6469042056074766, "grad_norm": 1.4142638444900513, "learning_rate": 5.858682374394395e-06, "loss": 0.6581, "step": 11075 }, { "epoch": 0.64696261682243, "grad_norm": 1.410684585571289, "learning_rate": 5.856960461967181e-06, "loss": 0.8147, "step": 11076 }, { "epoch": 0.6470210280373832, "grad_norm": 1.9765799045562744, "learning_rate": 5.855238697822075e-06, "loss": 0.7208, "step": 11077 }, { "epoch": 0.6470794392523365, "grad_norm": 1.0430221557617188, "learning_rate": 5.853517082020706e-06, "loss": 0.7852, "step": 11078 }, { "epoch": 0.6471378504672897, "grad_norm": 1.0787585973739624, "learning_rate": 5.8517956146246826e-06, "loss": 0.8187, "step": 11079 }, { "epoch": 0.647196261682243, "grad_norm": 1.0659812688827515, "learning_rate": 5.850074295695621e-06, "loss": 0.7293, "step": 11080 }, { "epoch": 0.6472546728971963, "grad_norm": 1.3620325326919556, "learning_rate": 5.848353125295133e-06, "loss": 0.7948, "step": 11081 }, { "epoch": 0.6473130841121495, "grad_norm": 1.003308653831482, "learning_rate": 5.8466321034848105e-06, "loss": 0.7032, "step": 11082 }, { "epoch": 0.6473714953271028, "grad_norm": 1.2936005592346191, "learning_rate": 5.844911230326263e-06, "loss": 0.7432, "step": 11083 }, { "epoch": 0.6474299065420561, "grad_norm": 1.1062508821487427, "learning_rate": 5.843190505881071e-06, "loss": 0.6469, "step": 11084 }, { "epoch": 0.6474883177570093, "grad_norm": 1.0183312892913818, "learning_rate": 5.841469930210821e-06, "loss": 0.8648, "step": 11085 }, { "epoch": 0.6475467289719626, "grad_norm": 1.335633397102356, "learning_rate": 5.839749503377103e-06, "loss": 0.8519, "step": 11086 }, { "epoch": 0.6476051401869158, "grad_norm": 1.8459292650222778, "learning_rate": 5.838029225441481e-06, "loss": 0.8476, "step": 11087 }, { "epoch": 0.6476635514018692, "grad_norm": 1.248928189277649, "learning_rate": 5.836309096465533e-06, "loss": 0.8143, "step": 11088 }, { "epoch": 0.6477219626168225, "grad_norm": 1.133581519126892, "learning_rate": 5.834589116510816e-06, "loss": 0.6789, "step": 11089 }, { "epoch": 0.6477803738317757, "grad_norm": 1.200987458229065, "learning_rate": 5.832869285638893e-06, "loss": 0.8083, "step": 11090 }, { "epoch": 0.647838785046729, "grad_norm": 1.1208826303482056, "learning_rate": 5.831149603911323e-06, "loss": 0.7039, "step": 11091 }, { "epoch": 0.6478971962616823, "grad_norm": 1.6359784603118896, "learning_rate": 5.829430071389645e-06, "loss": 0.8966, "step": 11092 }, { "epoch": 0.6479556074766355, "grad_norm": 1.1607457399368286, "learning_rate": 5.8277106881354125e-06, "loss": 0.8085, "step": 11093 }, { "epoch": 0.6480140186915888, "grad_norm": 1.14108407497406, "learning_rate": 5.825991454210153e-06, "loss": 0.692, "step": 11094 }, { "epoch": 0.648072429906542, "grad_norm": 1.4406776428222656, "learning_rate": 5.824272369675403e-06, "loss": 0.7582, "step": 11095 }, { "epoch": 0.6481308411214953, "grad_norm": 1.1979550123214722, "learning_rate": 5.822553434592695e-06, "loss": 0.7381, "step": 11096 }, { "epoch": 0.6481892523364486, "grad_norm": 1.1506495475769043, "learning_rate": 5.8208346490235425e-06, "loss": 0.7708, "step": 11097 }, { "epoch": 0.6482476635514018, "grad_norm": 0.9603205323219299, "learning_rate": 5.81911601302947e-06, "loss": 0.6775, "step": 11098 }, { "epoch": 0.6483060747663552, "grad_norm": 1.3407795429229736, "learning_rate": 5.817397526671979e-06, "loss": 0.7951, "step": 11099 }, { "epoch": 0.6483644859813084, "grad_norm": 2.5099024772644043, "learning_rate": 5.815679190012582e-06, "loss": 0.9515, "step": 11100 }, { "epoch": 0.6484228971962617, "grad_norm": 0.8828970789909363, "learning_rate": 5.813961003112782e-06, "loss": 0.5443, "step": 11101 }, { "epoch": 0.648481308411215, "grad_norm": 1.136888861656189, "learning_rate": 5.812242966034065e-06, "loss": 0.7276, "step": 11102 }, { "epoch": 0.6485397196261682, "grad_norm": 1.3087663650512695, "learning_rate": 5.810525078837932e-06, "loss": 0.7751, "step": 11103 }, { "epoch": 0.6485981308411215, "grad_norm": 1.1591099500656128, "learning_rate": 5.808807341585859e-06, "loss": 0.8881, "step": 11104 }, { "epoch": 0.6486565420560748, "grad_norm": 0.9103543162345886, "learning_rate": 5.807089754339324e-06, "loss": 0.654, "step": 11105 }, { "epoch": 0.648714953271028, "grad_norm": 1.4817378520965576, "learning_rate": 5.805372317159803e-06, "loss": 0.7038, "step": 11106 }, { "epoch": 0.6487733644859813, "grad_norm": 2.232011079788208, "learning_rate": 5.803655030108765e-06, "loss": 0.8022, "step": 11107 }, { "epoch": 0.6488317757009345, "grad_norm": 1.3773083686828613, "learning_rate": 5.801937893247675e-06, "loss": 0.7496, "step": 11108 }, { "epoch": 0.6488901869158878, "grad_norm": 1.1756713390350342, "learning_rate": 5.800220906637991e-06, "loss": 0.6034, "step": 11109 }, { "epoch": 0.6489485981308412, "grad_norm": 1.0584641695022583, "learning_rate": 5.798504070341156e-06, "loss": 0.6857, "step": 11110 }, { "epoch": 0.6490070093457944, "grad_norm": 1.0192865133285522, "learning_rate": 5.796787384418625e-06, "loss": 0.6979, "step": 11111 }, { "epoch": 0.6490654205607477, "grad_norm": 2.144996404647827, "learning_rate": 5.795070848931835e-06, "loss": 0.7777, "step": 11112 }, { "epoch": 0.649123831775701, "grad_norm": 1.1382811069488525, "learning_rate": 5.793354463942229e-06, "loss": 0.8533, "step": 11113 }, { "epoch": 0.6491822429906542, "grad_norm": 0.908430278301239, "learning_rate": 5.791638229511233e-06, "loss": 0.6938, "step": 11114 }, { "epoch": 0.6492406542056075, "grad_norm": 1.4968466758728027, "learning_rate": 5.789922145700267e-06, "loss": 0.9172, "step": 11115 }, { "epoch": 0.6492990654205607, "grad_norm": 1.4600087404251099, "learning_rate": 5.788206212570757e-06, "loss": 0.7499, "step": 11116 }, { "epoch": 0.649357476635514, "grad_norm": 1.0939850807189941, "learning_rate": 5.786490430184115e-06, "loss": 0.731, "step": 11117 }, { "epoch": 0.6494158878504673, "grad_norm": 1.3777955770492554, "learning_rate": 5.784774798601755e-06, "loss": 0.6555, "step": 11118 }, { "epoch": 0.6494742990654205, "grad_norm": 1.3476396799087524, "learning_rate": 5.783059317885076e-06, "loss": 0.7003, "step": 11119 }, { "epoch": 0.6495327102803738, "grad_norm": 1.0443463325500488, "learning_rate": 5.781343988095473e-06, "loss": 0.7159, "step": 11120 }, { "epoch": 0.649591121495327, "grad_norm": 1.0193400382995605, "learning_rate": 5.779628809294347e-06, "loss": 0.6425, "step": 11121 }, { "epoch": 0.6496495327102804, "grad_norm": 1.3360151052474976, "learning_rate": 5.777913781543076e-06, "loss": 0.8211, "step": 11122 }, { "epoch": 0.6497079439252337, "grad_norm": 1.0319457054138184, "learning_rate": 5.776198904903047e-06, "loss": 0.6074, "step": 11123 }, { "epoch": 0.6497663551401869, "grad_norm": 0.8525901436805725, "learning_rate": 5.7744841794356424e-06, "loss": 0.6521, "step": 11124 }, { "epoch": 0.6498247663551402, "grad_norm": 1.8738559484481812, "learning_rate": 5.772769605202221e-06, "loss": 0.8439, "step": 11125 }, { "epoch": 0.6498831775700935, "grad_norm": 1.0807535648345947, "learning_rate": 5.771055182264159e-06, "loss": 0.8712, "step": 11126 }, { "epoch": 0.6499415887850467, "grad_norm": 1.5583285093307495, "learning_rate": 5.7693409106828106e-06, "loss": 0.8794, "step": 11127 }, { "epoch": 0.65, "grad_norm": 1.5852937698364258, "learning_rate": 5.767626790519529e-06, "loss": 0.734, "step": 11128 }, { "epoch": 0.6500584112149532, "grad_norm": 1.0051419734954834, "learning_rate": 5.765912821835675e-06, "loss": 0.8159, "step": 11129 }, { "epoch": 0.6501168224299065, "grad_norm": 1.2439155578613281, "learning_rate": 5.764199004692579e-06, "loss": 0.8007, "step": 11130 }, { "epoch": 0.6501752336448599, "grad_norm": 1.2921372652053833, "learning_rate": 5.7624853391515915e-06, "loss": 0.7182, "step": 11131 }, { "epoch": 0.650233644859813, "grad_norm": 1.5625584125518799, "learning_rate": 5.760771825274034e-06, "loss": 0.6451, "step": 11132 }, { "epoch": 0.6502920560747664, "grad_norm": 0.9381025433540344, "learning_rate": 5.759058463121241e-06, "loss": 0.7743, "step": 11133 }, { "epoch": 0.6503504672897197, "grad_norm": 1.5577846765518188, "learning_rate": 5.757345252754538e-06, "loss": 0.8776, "step": 11134 }, { "epoch": 0.6504088785046729, "grad_norm": 1.8918818235397339, "learning_rate": 5.755632194235235e-06, "loss": 0.9349, "step": 11135 }, { "epoch": 0.6504672897196262, "grad_norm": 1.070589542388916, "learning_rate": 5.75391928762465e-06, "loss": 0.6446, "step": 11136 }, { "epoch": 0.6505257009345794, "grad_norm": 1.1143053770065308, "learning_rate": 5.7522065329840856e-06, "loss": 0.6103, "step": 11137 }, { "epoch": 0.6505841121495327, "grad_norm": 1.2260024547576904, "learning_rate": 5.7504939303748375e-06, "loss": 0.683, "step": 11138 }, { "epoch": 0.650642523364486, "grad_norm": 1.21793794631958, "learning_rate": 5.748781479858206e-06, "loss": 0.8322, "step": 11139 }, { "epoch": 0.6507009345794392, "grad_norm": 1.949958086013794, "learning_rate": 5.7470691814954816e-06, "loss": 0.9096, "step": 11140 }, { "epoch": 0.6507593457943925, "grad_norm": 1.3809417486190796, "learning_rate": 5.74535703534795e-06, "loss": 0.859, "step": 11141 }, { "epoch": 0.6508177570093457, "grad_norm": 1.3274271488189697, "learning_rate": 5.743645041476889e-06, "loss": 0.6859, "step": 11142 }, { "epoch": 0.6508761682242991, "grad_norm": 1.3560733795166016, "learning_rate": 5.741933199943566e-06, "loss": 0.805, "step": 11143 }, { "epoch": 0.6509345794392524, "grad_norm": 1.1629329919815063, "learning_rate": 5.7402215108092544e-06, "loss": 0.7871, "step": 11144 }, { "epoch": 0.6509929906542056, "grad_norm": 1.0152448415756226, "learning_rate": 5.738509974135214e-06, "loss": 0.6847, "step": 11145 }, { "epoch": 0.6510514018691589, "grad_norm": 1.5003873109817505, "learning_rate": 5.736798589982709e-06, "loss": 0.8881, "step": 11146 }, { "epoch": 0.6511098130841122, "grad_norm": 1.0739177465438843, "learning_rate": 5.735087358412984e-06, "loss": 0.8359, "step": 11147 }, { "epoch": 0.6511682242990654, "grad_norm": 0.9882823824882507, "learning_rate": 5.733376279487284e-06, "loss": 0.5625, "step": 11148 }, { "epoch": 0.6512266355140187, "grad_norm": 1.252718448638916, "learning_rate": 5.731665353266852e-06, "loss": 0.7712, "step": 11149 }, { "epoch": 0.6512850467289719, "grad_norm": 1.2351651191711426, "learning_rate": 5.7299545798129245e-06, "loss": 0.8621, "step": 11150 }, { "epoch": 0.6513434579439252, "grad_norm": 1.179946780204773, "learning_rate": 5.728243959186732e-06, "loss": 0.7327, "step": 11151 }, { "epoch": 0.6514018691588785, "grad_norm": 1.486726999282837, "learning_rate": 5.726533491449498e-06, "loss": 0.9059, "step": 11152 }, { "epoch": 0.6514602803738317, "grad_norm": 0.9164848327636719, "learning_rate": 5.724823176662437e-06, "loss": 0.7795, "step": 11153 }, { "epoch": 0.6515186915887851, "grad_norm": 1.510391354560852, "learning_rate": 5.723113014886768e-06, "loss": 0.8601, "step": 11154 }, { "epoch": 0.6515771028037384, "grad_norm": 1.9275872707366943, "learning_rate": 5.72140300618369e-06, "loss": 0.8387, "step": 11155 }, { "epoch": 0.6516355140186916, "grad_norm": 1.440850853919983, "learning_rate": 5.719693150614419e-06, "loss": 0.8358, "step": 11156 }, { "epoch": 0.6516939252336449, "grad_norm": 1.632830023765564, "learning_rate": 5.717983448240143e-06, "loss": 0.8224, "step": 11157 }, { "epoch": 0.6517523364485981, "grad_norm": 1.1641286611557007, "learning_rate": 5.716273899122053e-06, "loss": 0.73, "step": 11158 }, { "epoch": 0.6518107476635514, "grad_norm": 1.0891965627670288, "learning_rate": 5.7145645033213406e-06, "loss": 0.8186, "step": 11159 }, { "epoch": 0.6518691588785047, "grad_norm": 1.2689275741577148, "learning_rate": 5.712855260899177e-06, "loss": 0.7828, "step": 11160 }, { "epoch": 0.6519275700934579, "grad_norm": 1.0026206970214844, "learning_rate": 5.711146171916744e-06, "loss": 0.7565, "step": 11161 }, { "epoch": 0.6519859813084112, "grad_norm": 0.9600657224655151, "learning_rate": 5.709437236435211e-06, "loss": 0.7887, "step": 11162 }, { "epoch": 0.6520443925233644, "grad_norm": 1.6526453495025635, "learning_rate": 5.7077284545157385e-06, "loss": 0.7612, "step": 11163 }, { "epoch": 0.6521028037383177, "grad_norm": 1.614614486694336, "learning_rate": 5.7060198262194914e-06, "loss": 0.8777, "step": 11164 }, { "epoch": 0.6521612149532711, "grad_norm": 1.2176849842071533, "learning_rate": 5.704311351607612e-06, "loss": 0.7879, "step": 11165 }, { "epoch": 0.6522196261682243, "grad_norm": 1.4896715879440308, "learning_rate": 5.702603030741255e-06, "loss": 0.7579, "step": 11166 }, { "epoch": 0.6522780373831776, "grad_norm": 1.1051602363586426, "learning_rate": 5.7008948636815655e-06, "loss": 0.8354, "step": 11167 }, { "epoch": 0.6523364485981309, "grad_norm": 1.3669387102127075, "learning_rate": 5.6991868504896705e-06, "loss": 0.8732, "step": 11168 }, { "epoch": 0.6523948598130841, "grad_norm": 1.1855745315551758, "learning_rate": 5.697478991226711e-06, "loss": 0.856, "step": 11169 }, { "epoch": 0.6524532710280374, "grad_norm": 7.381005764007568, "learning_rate": 5.695771285953802e-06, "loss": 0.9586, "step": 11170 }, { "epoch": 0.6525116822429906, "grad_norm": 1.2794538736343384, "learning_rate": 5.694063734732074e-06, "loss": 0.7872, "step": 11171 }, { "epoch": 0.6525700934579439, "grad_norm": 1.316465973854065, "learning_rate": 5.692356337622631e-06, "loss": 0.828, "step": 11172 }, { "epoch": 0.6526285046728972, "grad_norm": 1.40189790725708, "learning_rate": 5.690649094686589e-06, "loss": 0.8432, "step": 11173 }, { "epoch": 0.6526869158878504, "grad_norm": 1.2562569379806519, "learning_rate": 5.688942005985052e-06, "loss": 0.7419, "step": 11174 }, { "epoch": 0.6527453271028038, "grad_norm": 1.821824550628662, "learning_rate": 5.6872350715791116e-06, "loss": 0.8742, "step": 11175 }, { "epoch": 0.652803738317757, "grad_norm": 1.2097322940826416, "learning_rate": 5.685528291529867e-06, "loss": 0.6638, "step": 11176 }, { "epoch": 0.6528621495327103, "grad_norm": 1.251429796218872, "learning_rate": 5.683821665898397e-06, "loss": 0.8361, "step": 11177 }, { "epoch": 0.6529205607476636, "grad_norm": 1.4182052612304688, "learning_rate": 5.682115194745789e-06, "loss": 0.8892, "step": 11178 }, { "epoch": 0.6529789719626168, "grad_norm": 1.060821771621704, "learning_rate": 5.6804088781331215e-06, "loss": 0.6327, "step": 11179 }, { "epoch": 0.6530373831775701, "grad_norm": 1.4873887300491333, "learning_rate": 5.678702716121458e-06, "loss": 0.8673, "step": 11180 }, { "epoch": 0.6530957943925234, "grad_norm": 1.4664976596832275, "learning_rate": 5.676996708771865e-06, "loss": 0.771, "step": 11181 }, { "epoch": 0.6531542056074766, "grad_norm": 1.0154346227645874, "learning_rate": 5.675290856145399e-06, "loss": 0.6477, "step": 11182 }, { "epoch": 0.6532126168224299, "grad_norm": 0.9620991349220276, "learning_rate": 5.673585158303119e-06, "loss": 0.6609, "step": 11183 }, { "epoch": 0.6532710280373831, "grad_norm": 1.4893146753311157, "learning_rate": 5.671879615306074e-06, "loss": 0.7579, "step": 11184 }, { "epoch": 0.6533294392523364, "grad_norm": 1.2252906560897827, "learning_rate": 5.670174227215304e-06, "loss": 0.6509, "step": 11185 }, { "epoch": 0.6533878504672898, "grad_norm": 1.0831011533737183, "learning_rate": 5.66846899409184e-06, "loss": 0.7391, "step": 11186 }, { "epoch": 0.653446261682243, "grad_norm": 1.396650791168213, "learning_rate": 5.666763915996725e-06, "loss": 0.906, "step": 11187 }, { "epoch": 0.6535046728971963, "grad_norm": 1.255486249923706, "learning_rate": 5.665058992990968e-06, "loss": 0.8912, "step": 11188 }, { "epoch": 0.6535630841121496, "grad_norm": 1.1295442581176758, "learning_rate": 5.66335422513561e-06, "loss": 0.6135, "step": 11189 }, { "epoch": 0.6536214953271028, "grad_norm": 1.5650333166122437, "learning_rate": 5.661649612491655e-06, "loss": 0.5085, "step": 11190 }, { "epoch": 0.6536799065420561, "grad_norm": 1.1983654499053955, "learning_rate": 5.659945155120108e-06, "loss": 0.7821, "step": 11191 }, { "epoch": 0.6537383177570093, "grad_norm": 1.1825288534164429, "learning_rate": 5.658240853081982e-06, "loss": 0.6444, "step": 11192 }, { "epoch": 0.6537967289719626, "grad_norm": 0.7566733956336975, "learning_rate": 5.656536706438267e-06, "loss": 0.5393, "step": 11193 }, { "epoch": 0.6538551401869159, "grad_norm": 1.2067607641220093, "learning_rate": 5.654832715249959e-06, "loss": 0.698, "step": 11194 }, { "epoch": 0.6539135514018691, "grad_norm": 1.3765945434570312, "learning_rate": 5.6531288795780496e-06, "loss": 0.6797, "step": 11195 }, { "epoch": 0.6539719626168224, "grad_norm": 2.4513304233551025, "learning_rate": 5.651425199483511e-06, "loss": 0.7598, "step": 11196 }, { "epoch": 0.6540303738317756, "grad_norm": 1.4080421924591064, "learning_rate": 5.649721675027329e-06, "loss": 1.0554, "step": 11197 }, { "epoch": 0.654088785046729, "grad_norm": 2.8966925144195557, "learning_rate": 5.648018306270463e-06, "loss": 0.8607, "step": 11198 }, { "epoch": 0.6541471962616823, "grad_norm": 2.4755144119262695, "learning_rate": 5.646315093273884e-06, "loss": 0.7437, "step": 11199 }, { "epoch": 0.6542056074766355, "grad_norm": 1.1208186149597168, "learning_rate": 5.644612036098554e-06, "loss": 0.8241, "step": 11200 }, { "epoch": 0.6542640186915888, "grad_norm": 1.7022733688354492, "learning_rate": 5.64290913480542e-06, "loss": 0.6166, "step": 11201 }, { "epoch": 0.6543224299065421, "grad_norm": 2.515061378479004, "learning_rate": 5.641206389455436e-06, "loss": 0.8073, "step": 11202 }, { "epoch": 0.6543808411214953, "grad_norm": 1.2089303731918335, "learning_rate": 5.6395038001095385e-06, "loss": 0.7131, "step": 11203 }, { "epoch": 0.6544392523364486, "grad_norm": 1.9135186672210693, "learning_rate": 5.637801366828669e-06, "loss": 0.7673, "step": 11204 }, { "epoch": 0.6544976635514018, "grad_norm": 1.3789775371551514, "learning_rate": 5.636099089673754e-06, "loss": 0.7794, "step": 11205 }, { "epoch": 0.6545560747663551, "grad_norm": 1.0829626321792603, "learning_rate": 5.634396968705722e-06, "loss": 0.787, "step": 11206 }, { "epoch": 0.6546144859813084, "grad_norm": 1.5561109781265259, "learning_rate": 5.632695003985497e-06, "loss": 0.8491, "step": 11207 }, { "epoch": 0.6546728971962616, "grad_norm": 1.678137183189392, "learning_rate": 5.630993195573984e-06, "loss": 0.707, "step": 11208 }, { "epoch": 0.654731308411215, "grad_norm": 1.7363176345825195, "learning_rate": 5.629291543532103e-06, "loss": 0.7013, "step": 11209 }, { "epoch": 0.6547897196261683, "grad_norm": 1.0417743921279907, "learning_rate": 5.627590047920747e-06, "loss": 0.6686, "step": 11210 }, { "epoch": 0.6548481308411215, "grad_norm": 1.4551225900650024, "learning_rate": 5.625888708800817e-06, "loss": 0.6785, "step": 11211 }, { "epoch": 0.6549065420560748, "grad_norm": 1.2618420124053955, "learning_rate": 5.624187526233211e-06, "loss": 0.7713, "step": 11212 }, { "epoch": 0.654964953271028, "grad_norm": 1.1943193674087524, "learning_rate": 5.622486500278807e-06, "loss": 0.6236, "step": 11213 }, { "epoch": 0.6550233644859813, "grad_norm": 1.89883553981781, "learning_rate": 5.620785630998493e-06, "loss": 0.8806, "step": 11214 }, { "epoch": 0.6550817757009346, "grad_norm": 1.4116195440292358, "learning_rate": 5.619084918453137e-06, "loss": 0.7198, "step": 11215 }, { "epoch": 0.6551401869158878, "grad_norm": 1.1208178997039795, "learning_rate": 5.617384362703612e-06, "loss": 0.6355, "step": 11216 }, { "epoch": 0.6551985981308411, "grad_norm": 1.4387953281402588, "learning_rate": 5.615683963810785e-06, "loss": 0.7826, "step": 11217 }, { "epoch": 0.6552570093457943, "grad_norm": 1.477634072303772, "learning_rate": 5.6139837218355096e-06, "loss": 0.787, "step": 11218 }, { "epoch": 0.6553154205607477, "grad_norm": 1.3422528505325317, "learning_rate": 5.612283636838645e-06, "loss": 0.755, "step": 11219 }, { "epoch": 0.655373831775701, "grad_norm": 1.609745740890503, "learning_rate": 5.610583708881032e-06, "loss": 0.8136, "step": 11220 }, { "epoch": 0.6554322429906542, "grad_norm": 1.7196587324142456, "learning_rate": 5.6088839380235075e-06, "loss": 1.027, "step": 11221 }, { "epoch": 0.6554906542056075, "grad_norm": 1.0518038272857666, "learning_rate": 5.607184324326922e-06, "loss": 0.6849, "step": 11222 }, { "epoch": 0.6555490654205608, "grad_norm": 1.9105119705200195, "learning_rate": 5.605484867852093e-06, "loss": 0.8062, "step": 11223 }, { "epoch": 0.655607476635514, "grad_norm": 1.0439319610595703, "learning_rate": 5.6037855686598545e-06, "loss": 0.7312, "step": 11224 }, { "epoch": 0.6556658878504673, "grad_norm": 1.8710578680038452, "learning_rate": 5.602086426811022e-06, "loss": 0.9376, "step": 11225 }, { "epoch": 0.6557242990654205, "grad_norm": 1.450282335281372, "learning_rate": 5.600387442366402e-06, "loss": 0.6279, "step": 11226 }, { "epoch": 0.6557827102803738, "grad_norm": 1.6362687349319458, "learning_rate": 5.598688615386809e-06, "loss": 0.712, "step": 11227 }, { "epoch": 0.6558411214953271, "grad_norm": 1.2879084348678589, "learning_rate": 5.596989945933046e-06, "loss": 0.6973, "step": 11228 }, { "epoch": 0.6558995327102803, "grad_norm": 1.2586640119552612, "learning_rate": 5.595291434065911e-06, "loss": 0.8134, "step": 11229 }, { "epoch": 0.6559579439252337, "grad_norm": 1.4342283010482788, "learning_rate": 5.593593079846191e-06, "loss": 0.9919, "step": 11230 }, { "epoch": 0.656016355140187, "grad_norm": 1.1694821119308472, "learning_rate": 5.591894883334668e-06, "loss": 0.8432, "step": 11231 }, { "epoch": 0.6560747663551402, "grad_norm": 1.5628869533538818, "learning_rate": 5.590196844592126e-06, "loss": 0.7233, "step": 11232 }, { "epoch": 0.6561331775700935, "grad_norm": 1.0436104536056519, "learning_rate": 5.588498963679339e-06, "loss": 0.6104, "step": 11233 }, { "epoch": 0.6561915887850467, "grad_norm": 0.98028165102005, "learning_rate": 5.586801240657076e-06, "loss": 0.7346, "step": 11234 }, { "epoch": 0.65625, "grad_norm": 1.3813875913619995, "learning_rate": 5.585103675586101e-06, "loss": 0.6382, "step": 11235 }, { "epoch": 0.6563084112149533, "grad_norm": 1.2477343082427979, "learning_rate": 5.583406268527163e-06, "loss": 0.8234, "step": 11236 }, { "epoch": 0.6563668224299065, "grad_norm": 1.578171730041504, "learning_rate": 5.581709019541024e-06, "loss": 0.7556, "step": 11237 }, { "epoch": 0.6564252336448598, "grad_norm": 0.945175051689148, "learning_rate": 5.580011928688419e-06, "loss": 0.712, "step": 11238 }, { "epoch": 0.656483644859813, "grad_norm": 3.7965149879455566, "learning_rate": 5.5783149960300944e-06, "loss": 0.669, "step": 11239 }, { "epoch": 0.6565420560747663, "grad_norm": 1.6305001974105835, "learning_rate": 5.576618221626786e-06, "loss": 0.8616, "step": 11240 }, { "epoch": 0.6566004672897197, "grad_norm": 1.2670570611953735, "learning_rate": 5.574921605539216e-06, "loss": 0.6343, "step": 11241 }, { "epoch": 0.6566588785046729, "grad_norm": 1.696523904800415, "learning_rate": 5.573225147828116e-06, "loss": 0.6977, "step": 11242 }, { "epoch": 0.6567172897196262, "grad_norm": 3.2490832805633545, "learning_rate": 5.571528848554195e-06, "loss": 0.8848, "step": 11243 }, { "epoch": 0.6567757009345795, "grad_norm": 1.0806899070739746, "learning_rate": 5.569832707778169e-06, "loss": 0.7444, "step": 11244 }, { "epoch": 0.6568341121495327, "grad_norm": 1.4217735528945923, "learning_rate": 5.5681367255607445e-06, "loss": 0.7019, "step": 11245 }, { "epoch": 0.656892523364486, "grad_norm": 1.9161115884780884, "learning_rate": 5.566440901962619e-06, "loss": 0.8275, "step": 11246 }, { "epoch": 0.6569509345794392, "grad_norm": 1.2555813789367676, "learning_rate": 5.564745237044491e-06, "loss": 0.8853, "step": 11247 }, { "epoch": 0.6570093457943925, "grad_norm": 1.61239492893219, "learning_rate": 5.563049730867045e-06, "loss": 0.7481, "step": 11248 }, { "epoch": 0.6570677570093458, "grad_norm": 1.547236680984497, "learning_rate": 5.561354383490966e-06, "loss": 0.8006, "step": 11249 }, { "epoch": 0.657126168224299, "grad_norm": 1.183353304862976, "learning_rate": 5.559659194976935e-06, "loss": 0.8285, "step": 11250 }, { "epoch": 0.6571845794392523, "grad_norm": 1.3800040483474731, "learning_rate": 5.557964165385617e-06, "loss": 0.6961, "step": 11251 }, { "epoch": 0.6572429906542057, "grad_norm": 1.2780073881149292, "learning_rate": 5.5562692947776875e-06, "loss": 0.7988, "step": 11252 }, { "epoch": 0.6573014018691589, "grad_norm": 1.0396174192428589, "learning_rate": 5.554574583213801e-06, "loss": 0.865, "step": 11253 }, { "epoch": 0.6573598130841122, "grad_norm": 1.281864881515503, "learning_rate": 5.552880030754606e-06, "loss": 0.5853, "step": 11254 }, { "epoch": 0.6574182242990654, "grad_norm": 1.0684794187545776, "learning_rate": 5.551185637460765e-06, "loss": 0.7801, "step": 11255 }, { "epoch": 0.6574766355140187, "grad_norm": 0.9962054491043091, "learning_rate": 5.5494914033929126e-06, "loss": 0.6374, "step": 11256 }, { "epoch": 0.657535046728972, "grad_norm": 1.1588433980941772, "learning_rate": 5.5477973286116926e-06, "loss": 0.7053, "step": 11257 }, { "epoch": 0.6575934579439252, "grad_norm": 1.0855140686035156, "learning_rate": 5.546103413177734e-06, "loss": 0.7378, "step": 11258 }, { "epoch": 0.6576518691588785, "grad_norm": 1.2505078315734863, "learning_rate": 5.544409657151658e-06, "loss": 0.8028, "step": 11259 }, { "epoch": 0.6577102803738317, "grad_norm": 1.0774825811386108, "learning_rate": 5.542716060594091e-06, "loss": 0.8597, "step": 11260 }, { "epoch": 0.657768691588785, "grad_norm": 1.3367422819137573, "learning_rate": 5.5410226235656465e-06, "loss": 0.6879, "step": 11261 }, { "epoch": 0.6578271028037384, "grad_norm": 1.3009065389633179, "learning_rate": 5.539329346126938e-06, "loss": 0.7035, "step": 11262 }, { "epoch": 0.6578855140186916, "grad_norm": 1.4782987833023071, "learning_rate": 5.537636228338566e-06, "loss": 0.9451, "step": 11263 }, { "epoch": 0.6579439252336449, "grad_norm": 2.062706470489502, "learning_rate": 5.535943270261122e-06, "loss": 0.8808, "step": 11264 }, { "epoch": 0.6580023364485982, "grad_norm": 1.03598153591156, "learning_rate": 5.5342504719552026e-06, "loss": 0.7115, "step": 11265 }, { "epoch": 0.6580607476635514, "grad_norm": 1.6183419227600098, "learning_rate": 5.532557833481398e-06, "loss": 0.7085, "step": 11266 }, { "epoch": 0.6581191588785047, "grad_norm": 1.0555555820465088, "learning_rate": 5.530865354900288e-06, "loss": 0.5418, "step": 11267 }, { "epoch": 0.6581775700934579, "grad_norm": 1.5262688398361206, "learning_rate": 5.529173036272446e-06, "loss": 0.8149, "step": 11268 }, { "epoch": 0.6582359813084112, "grad_norm": 0.9897528886795044, "learning_rate": 5.527480877658437e-06, "loss": 0.675, "step": 11269 }, { "epoch": 0.6582943925233645, "grad_norm": 1.5394680500030518, "learning_rate": 5.525788879118832e-06, "loss": 0.782, "step": 11270 }, { "epoch": 0.6583528037383177, "grad_norm": 1.2923917770385742, "learning_rate": 5.5240970407141754e-06, "loss": 0.8319, "step": 11271 }, { "epoch": 0.658411214953271, "grad_norm": 1.1155924797058105, "learning_rate": 5.522405362505039e-06, "loss": 0.6525, "step": 11272 }, { "epoch": 0.6584696261682244, "grad_norm": 1.8425205945968628, "learning_rate": 5.520713844551957e-06, "loss": 0.7907, "step": 11273 }, { "epoch": 0.6585280373831776, "grad_norm": 1.6027936935424805, "learning_rate": 5.519022486915469e-06, "loss": 0.88, "step": 11274 }, { "epoch": 0.6585864485981309, "grad_norm": 1.3856277465820312, "learning_rate": 5.517331289656115e-06, "loss": 0.7138, "step": 11275 }, { "epoch": 0.6586448598130841, "grad_norm": 2.0782663822174072, "learning_rate": 5.515640252834417e-06, "loss": 0.9432, "step": 11276 }, { "epoch": 0.6587032710280374, "grad_norm": 0.9059908986091614, "learning_rate": 5.513949376510905e-06, "loss": 0.6958, "step": 11277 }, { "epoch": 0.6587616822429907, "grad_norm": 1.1128687858581543, "learning_rate": 5.512258660746099e-06, "loss": 0.6934, "step": 11278 }, { "epoch": 0.6588200934579439, "grad_norm": 1.328161358833313, "learning_rate": 5.5105681056005e-06, "loss": 0.7044, "step": 11279 }, { "epoch": 0.6588785046728972, "grad_norm": 1.186639428138733, "learning_rate": 5.508877711134626e-06, "loss": 0.687, "step": 11280 }, { "epoch": 0.6589369158878504, "grad_norm": 0.977644681930542, "learning_rate": 5.507187477408966e-06, "loss": 0.645, "step": 11281 }, { "epoch": 0.6589953271028037, "grad_norm": 1.5932985544204712, "learning_rate": 5.505497404484021e-06, "loss": 0.8688, "step": 11282 }, { "epoch": 0.659053738317757, "grad_norm": 1.0904890298843384, "learning_rate": 5.503807492420284e-06, "loss": 0.8081, "step": 11283 }, { "epoch": 0.6591121495327102, "grad_norm": 1.1818875074386597, "learning_rate": 5.502117741278229e-06, "loss": 0.7775, "step": 11284 }, { "epoch": 0.6591705607476636, "grad_norm": 1.4409910440444946, "learning_rate": 5.500428151118341e-06, "loss": 0.7388, "step": 11285 }, { "epoch": 0.6592289719626169, "grad_norm": 1.2916371822357178, "learning_rate": 5.498738722001084e-06, "loss": 0.6043, "step": 11286 }, { "epoch": 0.6592873831775701, "grad_norm": 1.3629502058029175, "learning_rate": 5.497049453986928e-06, "loss": 0.6716, "step": 11287 }, { "epoch": 0.6593457943925234, "grad_norm": 1.341761589050293, "learning_rate": 5.495360347136336e-06, "loss": 0.6708, "step": 11288 }, { "epoch": 0.6594042056074766, "grad_norm": 1.997700572013855, "learning_rate": 5.493671401509756e-06, "loss": 0.7003, "step": 11289 }, { "epoch": 0.6594626168224299, "grad_norm": 1.1736007928848267, "learning_rate": 5.491982617167644e-06, "loss": 0.8027, "step": 11290 }, { "epoch": 0.6595210280373832, "grad_norm": 1.8822773694992065, "learning_rate": 5.490293994170432e-06, "loss": 0.9322, "step": 11291 }, { "epoch": 0.6595794392523364, "grad_norm": 1.568931221961975, "learning_rate": 5.488605532578569e-06, "loss": 0.805, "step": 11292 }, { "epoch": 0.6596378504672897, "grad_norm": 0.6873255372047424, "learning_rate": 5.4869172324524754e-06, "loss": 0.5383, "step": 11293 }, { "epoch": 0.659696261682243, "grad_norm": 1.1918833255767822, "learning_rate": 5.485229093852582e-06, "loss": 0.8612, "step": 11294 }, { "epoch": 0.6597546728971962, "grad_norm": 1.432517409324646, "learning_rate": 5.483541116839311e-06, "loss": 0.6366, "step": 11295 }, { "epoch": 0.6598130841121496, "grad_norm": 1.1581652164459229, "learning_rate": 5.4818533014730746e-06, "loss": 0.822, "step": 11296 }, { "epoch": 0.6598714953271028, "grad_norm": 2.641378164291382, "learning_rate": 5.480165647814275e-06, "loss": 0.7223, "step": 11297 }, { "epoch": 0.6599299065420561, "grad_norm": 1.1909407377243042, "learning_rate": 5.4784781559233165e-06, "loss": 0.8316, "step": 11298 }, { "epoch": 0.6599883177570094, "grad_norm": 1.2644884586334229, "learning_rate": 5.476790825860601e-06, "loss": 0.7387, "step": 11299 }, { "epoch": 0.6600467289719626, "grad_norm": 1.1930488348007202, "learning_rate": 5.475103657686518e-06, "loss": 0.8428, "step": 11300 }, { "epoch": 0.6601051401869159, "grad_norm": 1.535335898399353, "learning_rate": 5.4734166514614495e-06, "loss": 0.7196, "step": 11301 }, { "epoch": 0.6601635514018691, "grad_norm": 1.1377030611038208, "learning_rate": 5.471729807245773e-06, "loss": 0.8109, "step": 11302 }, { "epoch": 0.6602219626168224, "grad_norm": 0.9891220927238464, "learning_rate": 5.4700431250998675e-06, "loss": 0.6983, "step": 11303 }, { "epoch": 0.6602803738317757, "grad_norm": 1.4773571491241455, "learning_rate": 5.468356605084088e-06, "loss": 0.7754, "step": 11304 }, { "epoch": 0.6603387850467289, "grad_norm": 1.120593547821045, "learning_rate": 5.466670247258815e-06, "loss": 0.8421, "step": 11305 }, { "epoch": 0.6603971962616823, "grad_norm": 1.6015383005142212, "learning_rate": 5.464984051684394e-06, "loss": 0.7652, "step": 11306 }, { "epoch": 0.6604556074766356, "grad_norm": 1.4296077489852905, "learning_rate": 5.463298018421171e-06, "loss": 0.8456, "step": 11307 }, { "epoch": 0.6605140186915888, "grad_norm": 1.5268938541412354, "learning_rate": 5.4616121475295e-06, "loss": 0.5204, "step": 11308 }, { "epoch": 0.6605724299065421, "grad_norm": 1.198087453842163, "learning_rate": 5.459926439069709e-06, "loss": 0.6939, "step": 11309 }, { "epoch": 0.6606308411214953, "grad_norm": 2.7895684242248535, "learning_rate": 5.458240893102137e-06, "loss": 0.8715, "step": 11310 }, { "epoch": 0.6606892523364486, "grad_norm": 1.366089940071106, "learning_rate": 5.456555509687114e-06, "loss": 0.9479, "step": 11311 }, { "epoch": 0.6607476635514019, "grad_norm": 1.449209213256836, "learning_rate": 5.45487028888495e-06, "loss": 0.7911, "step": 11312 }, { "epoch": 0.6608060747663551, "grad_norm": 1.489638328552246, "learning_rate": 5.453185230755973e-06, "loss": 0.7508, "step": 11313 }, { "epoch": 0.6608644859813084, "grad_norm": 1.2420227527618408, "learning_rate": 5.451500335360482e-06, "loss": 0.7909, "step": 11314 }, { "epoch": 0.6609228971962616, "grad_norm": 0.9707740545272827, "learning_rate": 5.449815602758786e-06, "loss": 0.6071, "step": 11315 }, { "epoch": 0.6609813084112149, "grad_norm": 1.590137004852295, "learning_rate": 5.448131033011184e-06, "loss": 0.7482, "step": 11316 }, { "epoch": 0.6610397196261683, "grad_norm": 1.2088688611984253, "learning_rate": 5.44644662617796e-06, "loss": 0.7097, "step": 11317 }, { "epoch": 0.6610981308411215, "grad_norm": 1.0993382930755615, "learning_rate": 5.44476238231941e-06, "loss": 0.7722, "step": 11318 }, { "epoch": 0.6611565420560748, "grad_norm": 2.079988718032837, "learning_rate": 5.443078301495807e-06, "loss": 0.7085, "step": 11319 }, { "epoch": 0.6612149532710281, "grad_norm": 1.080567717552185, "learning_rate": 5.441394383767427e-06, "loss": 0.7159, "step": 11320 }, { "epoch": 0.6612733644859813, "grad_norm": 1.1547127962112427, "learning_rate": 5.439710629194542e-06, "loss": 0.7643, "step": 11321 }, { "epoch": 0.6613317757009346, "grad_norm": 1.764127492904663, "learning_rate": 5.43802703783741e-06, "loss": 0.8493, "step": 11322 }, { "epoch": 0.6613901869158878, "grad_norm": 1.4250682592391968, "learning_rate": 5.436343609756293e-06, "loss": 0.8912, "step": 11323 }, { "epoch": 0.6614485981308411, "grad_norm": 1.4513379335403442, "learning_rate": 5.434660345011434e-06, "loss": 0.923, "step": 11324 }, { "epoch": 0.6615070093457944, "grad_norm": 1.6481159925460815, "learning_rate": 5.432977243663089e-06, "loss": 0.9233, "step": 11325 }, { "epoch": 0.6615654205607476, "grad_norm": 1.086276888847351, "learning_rate": 5.431294305771486e-06, "loss": 0.678, "step": 11326 }, { "epoch": 0.6616238317757009, "grad_norm": 1.9830247163772583, "learning_rate": 5.429611531396863e-06, "loss": 0.8511, "step": 11327 }, { "epoch": 0.6616822429906543, "grad_norm": 1.013980507850647, "learning_rate": 5.4279289205994546e-06, "loss": 0.706, "step": 11328 }, { "epoch": 0.6617406542056075, "grad_norm": 1.013313889503479, "learning_rate": 5.4262464734394705e-06, "loss": 0.7059, "step": 11329 }, { "epoch": 0.6617990654205608, "grad_norm": 1.7658964395523071, "learning_rate": 5.424564189977137e-06, "loss": 0.674, "step": 11330 }, { "epoch": 0.661857476635514, "grad_norm": 1.1124628782272339, "learning_rate": 5.422882070272656e-06, "loss": 0.6357, "step": 11331 }, { "epoch": 0.6619158878504673, "grad_norm": 1.3351620435714722, "learning_rate": 5.421200114386234e-06, "loss": 0.7174, "step": 11332 }, { "epoch": 0.6619742990654206, "grad_norm": 1.3109240531921387, "learning_rate": 5.419518322378075e-06, "loss": 0.6364, "step": 11333 }, { "epoch": 0.6620327102803738, "grad_norm": 1.1078593730926514, "learning_rate": 5.417836694308365e-06, "loss": 0.7369, "step": 11334 }, { "epoch": 0.6620911214953271, "grad_norm": 1.9532467126846313, "learning_rate": 5.416155230237294e-06, "loss": 0.7875, "step": 11335 }, { "epoch": 0.6621495327102803, "grad_norm": 1.6999905109405518, "learning_rate": 5.414473930225042e-06, "loss": 0.7227, "step": 11336 }, { "epoch": 0.6622079439252336, "grad_norm": 1.1659308671951294, "learning_rate": 5.412792794331776e-06, "loss": 0.7887, "step": 11337 }, { "epoch": 0.662266355140187, "grad_norm": 1.138867735862732, "learning_rate": 5.411111822617678e-06, "loss": 0.6027, "step": 11338 }, { "epoch": 0.6623247663551401, "grad_norm": 1.2123271226882935, "learning_rate": 5.409431015142903e-06, "loss": 0.7527, "step": 11339 }, { "epoch": 0.6623831775700935, "grad_norm": 1.0342787504196167, "learning_rate": 5.407750371967613e-06, "loss": 0.7923, "step": 11340 }, { "epoch": 0.6624415887850468, "grad_norm": 1.2516483068466187, "learning_rate": 5.4060698931519574e-06, "loss": 0.8633, "step": 11341 }, { "epoch": 0.6625, "grad_norm": 1.120360016822815, "learning_rate": 5.404389578756077e-06, "loss": 0.8956, "step": 11342 }, { "epoch": 0.6625584112149533, "grad_norm": 0.9549927711486816, "learning_rate": 5.402709428840115e-06, "loss": 0.5957, "step": 11343 }, { "epoch": 0.6626168224299065, "grad_norm": 1.3528401851654053, "learning_rate": 5.401029443464205e-06, "loss": 0.7066, "step": 11344 }, { "epoch": 0.6626752336448598, "grad_norm": 1.237438440322876, "learning_rate": 5.399349622688479e-06, "loss": 0.6549, "step": 11345 }, { "epoch": 0.6627336448598131, "grad_norm": 1.1362011432647705, "learning_rate": 5.397669966573056e-06, "loss": 0.7869, "step": 11346 }, { "epoch": 0.6627920560747663, "grad_norm": 1.007574439048767, "learning_rate": 5.395990475178047e-06, "loss": 0.893, "step": 11347 }, { "epoch": 0.6628504672897196, "grad_norm": 1.4773313999176025, "learning_rate": 5.3943111485635644e-06, "loss": 0.962, "step": 11348 }, { "epoch": 0.662908878504673, "grad_norm": 1.3868129253387451, "learning_rate": 5.392631986789721e-06, "loss": 0.7738, "step": 11349 }, { "epoch": 0.6629672897196262, "grad_norm": 1.5801727771759033, "learning_rate": 5.390952989916602e-06, "loss": 0.8967, "step": 11350 }, { "epoch": 0.6630257009345795, "grad_norm": 1.528639554977417, "learning_rate": 5.3892741580043096e-06, "loss": 0.9663, "step": 11351 }, { "epoch": 0.6630841121495327, "grad_norm": 0.9662078619003296, "learning_rate": 5.387595491112924e-06, "loss": 0.7738, "step": 11352 }, { "epoch": 0.663142523364486, "grad_norm": 1.4159404039382935, "learning_rate": 5.385916989302527e-06, "loss": 0.9122, "step": 11353 }, { "epoch": 0.6632009345794393, "grad_norm": 0.8133694529533386, "learning_rate": 5.3842386526332e-06, "loss": 0.7058, "step": 11354 }, { "epoch": 0.6632593457943925, "grad_norm": 1.3282474279403687, "learning_rate": 5.382560481165002e-06, "loss": 0.7645, "step": 11355 }, { "epoch": 0.6633177570093458, "grad_norm": 0.9566579461097717, "learning_rate": 5.380882474958005e-06, "loss": 0.7678, "step": 11356 }, { "epoch": 0.663376168224299, "grad_norm": 1.1035152673721313, "learning_rate": 5.379204634072257e-06, "loss": 0.8456, "step": 11357 }, { "epoch": 0.6634345794392523, "grad_norm": 2.3878822326660156, "learning_rate": 5.377526958567818e-06, "loss": 0.7252, "step": 11358 }, { "epoch": 0.6634929906542056, "grad_norm": 1.148470163345337, "learning_rate": 5.375849448504724e-06, "loss": 0.989, "step": 11359 }, { "epoch": 0.6635514018691588, "grad_norm": 1.1081809997558594, "learning_rate": 5.374172103943018e-06, "loss": 0.7098, "step": 11360 }, { "epoch": 0.6636098130841122, "grad_norm": 1.4057508707046509, "learning_rate": 5.37249492494274e-06, "loss": 0.6234, "step": 11361 }, { "epoch": 0.6636682242990655, "grad_norm": 1.354486346244812, "learning_rate": 5.370817911563905e-06, "loss": 0.7366, "step": 11362 }, { "epoch": 0.6637266355140187, "grad_norm": 1.4262304306030273, "learning_rate": 5.369141063866546e-06, "loss": 0.9309, "step": 11363 }, { "epoch": 0.663785046728972, "grad_norm": 1.543743371963501, "learning_rate": 5.367464381910667e-06, "loss": 0.7473, "step": 11364 }, { "epoch": 0.6638434579439252, "grad_norm": 1.2669240236282349, "learning_rate": 5.365787865756287e-06, "loss": 0.7717, "step": 11365 }, { "epoch": 0.6639018691588785, "grad_norm": 0.772363007068634, "learning_rate": 5.364111515463408e-06, "loss": 0.7517, "step": 11366 }, { "epoch": 0.6639602803738318, "grad_norm": 1.6356168985366821, "learning_rate": 5.3624353310920226e-06, "loss": 0.8221, "step": 11367 }, { "epoch": 0.664018691588785, "grad_norm": 0.967820405960083, "learning_rate": 5.36075931270213e-06, "loss": 0.6973, "step": 11368 }, { "epoch": 0.6640771028037383, "grad_norm": 1.1014314889907837, "learning_rate": 5.359083460353712e-06, "loss": 0.8458, "step": 11369 }, { "epoch": 0.6641355140186916, "grad_norm": 1.6934823989868164, "learning_rate": 5.357407774106741e-06, "loss": 0.8247, "step": 11370 }, { "epoch": 0.6641939252336448, "grad_norm": 1.1783229112625122, "learning_rate": 5.355732254021205e-06, "loss": 0.6403, "step": 11371 }, { "epoch": 0.6642523364485982, "grad_norm": 0.9402704238891602, "learning_rate": 5.354056900157063e-06, "loss": 0.792, "step": 11372 }, { "epoch": 0.6643107476635514, "grad_norm": 1.1487895250320435, "learning_rate": 5.352381712574282e-06, "loss": 0.7515, "step": 11373 }, { "epoch": 0.6643691588785047, "grad_norm": 1.8562430143356323, "learning_rate": 5.350706691332816e-06, "loss": 0.7077, "step": 11374 }, { "epoch": 0.664427570093458, "grad_norm": 1.422980546951294, "learning_rate": 5.3490318364926105e-06, "loss": 0.7661, "step": 11375 }, { "epoch": 0.6644859813084112, "grad_norm": 1.3546429872512817, "learning_rate": 5.347357148113613e-06, "loss": 0.8034, "step": 11376 }, { "epoch": 0.6645443925233645, "grad_norm": 1.7276731729507446, "learning_rate": 5.345682626255764e-06, "loss": 0.8383, "step": 11377 }, { "epoch": 0.6646028037383177, "grad_norm": 1.7691742181777954, "learning_rate": 5.344008270978995e-06, "loss": 0.8881, "step": 11378 }, { "epoch": 0.664661214953271, "grad_norm": 1.5435370206832886, "learning_rate": 5.342334082343235e-06, "loss": 0.672, "step": 11379 }, { "epoch": 0.6647196261682243, "grad_norm": 1.3810838460922241, "learning_rate": 5.3406600604083935e-06, "loss": 0.746, "step": 11380 }, { "epoch": 0.6647780373831775, "grad_norm": 1.4562067985534668, "learning_rate": 5.338986205234393e-06, "loss": 0.7712, "step": 11381 }, { "epoch": 0.6648364485981308, "grad_norm": 0.9904056191444397, "learning_rate": 5.337312516881141e-06, "loss": 0.647, "step": 11382 }, { "epoch": 0.6648948598130842, "grad_norm": 2.0119693279266357, "learning_rate": 5.3356389954085455e-06, "loss": 0.9246, "step": 11383 }, { "epoch": 0.6649532710280374, "grad_norm": 0.9759936332702637, "learning_rate": 5.333965640876495e-06, "loss": 0.8263, "step": 11384 }, { "epoch": 0.6650116822429907, "grad_norm": 2.3359932899475098, "learning_rate": 5.33229245334488e-06, "loss": 0.8877, "step": 11385 }, { "epoch": 0.6650700934579439, "grad_norm": 1.176632046699524, "learning_rate": 5.330619432873585e-06, "loss": 0.8448, "step": 11386 }, { "epoch": 0.6651285046728972, "grad_norm": 1.1942434310913086, "learning_rate": 5.328946579522493e-06, "loss": 0.6129, "step": 11387 }, { "epoch": 0.6651869158878505, "grad_norm": 1.2600669860839844, "learning_rate": 5.327273893351477e-06, "loss": 0.6027, "step": 11388 }, { "epoch": 0.6652453271028037, "grad_norm": 1.3601735830307007, "learning_rate": 5.325601374420399e-06, "loss": 0.7531, "step": 11389 }, { "epoch": 0.665303738317757, "grad_norm": 1.5015747547149658, "learning_rate": 5.323929022789121e-06, "loss": 0.8859, "step": 11390 }, { "epoch": 0.6653621495327103, "grad_norm": 2.0424113273620605, "learning_rate": 5.322256838517499e-06, "loss": 0.8508, "step": 11391 }, { "epoch": 0.6654205607476635, "grad_norm": 3.36702561378479, "learning_rate": 5.320584821665378e-06, "loss": 0.6241, "step": 11392 }, { "epoch": 0.6654789719626168, "grad_norm": 0.8728432059288025, "learning_rate": 5.3189129722926025e-06, "loss": 0.6311, "step": 11393 }, { "epoch": 0.66553738317757, "grad_norm": 1.487743616104126, "learning_rate": 5.317241290459012e-06, "loss": 0.6496, "step": 11394 }, { "epoch": 0.6655957943925234, "grad_norm": 1.1585607528686523, "learning_rate": 5.315569776224433e-06, "loss": 0.7537, "step": 11395 }, { "epoch": 0.6656542056074767, "grad_norm": 1.097234845161438, "learning_rate": 5.313898429648694e-06, "loss": 0.7249, "step": 11396 }, { "epoch": 0.6657126168224299, "grad_norm": 0.9157850742340088, "learning_rate": 5.312227250791608e-06, "loss": 0.746, "step": 11397 }, { "epoch": 0.6657710280373832, "grad_norm": 1.2727105617523193, "learning_rate": 5.3105562397129915e-06, "loss": 0.7941, "step": 11398 }, { "epoch": 0.6658294392523364, "grad_norm": 1.6510814428329468, "learning_rate": 5.308885396472655e-06, "loss": 0.7093, "step": 11399 }, { "epoch": 0.6658878504672897, "grad_norm": 1.1768330335617065, "learning_rate": 5.307214721130389e-06, "loss": 0.7111, "step": 11400 }, { "epoch": 0.665946261682243, "grad_norm": 0.9924618601799011, "learning_rate": 5.305544213745999e-06, "loss": 0.72, "step": 11401 }, { "epoch": 0.6660046728971962, "grad_norm": 1.2961041927337646, "learning_rate": 5.303873874379264e-06, "loss": 0.7823, "step": 11402 }, { "epoch": 0.6660630841121495, "grad_norm": 1.5685582160949707, "learning_rate": 5.302203703089971e-06, "loss": 0.8688, "step": 11403 }, { "epoch": 0.6661214953271029, "grad_norm": 1.0611149072647095, "learning_rate": 5.3005336999379e-06, "loss": 0.5617, "step": 11404 }, { "epoch": 0.666179906542056, "grad_norm": 1.079801321029663, "learning_rate": 5.298863864982814e-06, "loss": 0.8915, "step": 11405 }, { "epoch": 0.6662383177570094, "grad_norm": 1.7134135961532593, "learning_rate": 5.2971941982844855e-06, "loss": 0.7224, "step": 11406 }, { "epoch": 0.6662967289719626, "grad_norm": 1.23408043384552, "learning_rate": 5.295524699902668e-06, "loss": 0.7426, "step": 11407 }, { "epoch": 0.6663551401869159, "grad_norm": 1.5525457859039307, "learning_rate": 5.293855369897112e-06, "loss": 0.7817, "step": 11408 }, { "epoch": 0.6664135514018692, "grad_norm": 1.43146550655365, "learning_rate": 5.292186208327565e-06, "loss": 0.5104, "step": 11409 }, { "epoch": 0.6664719626168224, "grad_norm": 1.0026161670684814, "learning_rate": 5.29051721525377e-06, "loss": 0.6349, "step": 11410 }, { "epoch": 0.6665303738317757, "grad_norm": 1.711091160774231, "learning_rate": 5.288848390735464e-06, "loss": 0.9589, "step": 11411 }, { "epoch": 0.666588785046729, "grad_norm": 1.8193639516830444, "learning_rate": 5.287179734832373e-06, "loss": 0.8613, "step": 11412 }, { "epoch": 0.6666471962616822, "grad_norm": 1.5870106220245361, "learning_rate": 5.285511247604213e-06, "loss": 0.752, "step": 11413 }, { "epoch": 0.6667056074766355, "grad_norm": 1.1981098651885986, "learning_rate": 5.283842929110705e-06, "loss": 0.7664, "step": 11414 }, { "epoch": 0.6667640186915887, "grad_norm": 1.3257756233215332, "learning_rate": 5.28217477941156e-06, "loss": 0.7124, "step": 11415 }, { "epoch": 0.6668224299065421, "grad_norm": 1.8075686693191528, "learning_rate": 5.280506798566485e-06, "loss": 0.7034, "step": 11416 }, { "epoch": 0.6668808411214954, "grad_norm": 1.1723510026931763, "learning_rate": 5.2788389866351755e-06, "loss": 0.6587, "step": 11417 }, { "epoch": 0.6669392523364486, "grad_norm": 1.5337769985198975, "learning_rate": 5.277171343677319e-06, "loss": 0.7003, "step": 11418 }, { "epoch": 0.6669976635514019, "grad_norm": 2.193016767501831, "learning_rate": 5.275503869752605e-06, "loss": 0.7487, "step": 11419 }, { "epoch": 0.6670560747663551, "grad_norm": 1.5210484266281128, "learning_rate": 5.273836564920715e-06, "loss": 0.9963, "step": 11420 }, { "epoch": 0.6671144859813084, "grad_norm": 0.8850092887878418, "learning_rate": 5.272169429241325e-06, "loss": 0.6062, "step": 11421 }, { "epoch": 0.6671728971962617, "grad_norm": 2.947113275527954, "learning_rate": 5.270502462774099e-06, "loss": 0.7666, "step": 11422 }, { "epoch": 0.6672313084112149, "grad_norm": 1.9586925506591797, "learning_rate": 5.268835665578696e-06, "loss": 0.6966, "step": 11423 }, { "epoch": 0.6672897196261682, "grad_norm": 1.296000361442566, "learning_rate": 5.26716903771478e-06, "loss": 0.7552, "step": 11424 }, { "epoch": 0.6673481308411215, "grad_norm": 1.83407723903656, "learning_rate": 5.265502579241991e-06, "loss": 0.8496, "step": 11425 }, { "epoch": 0.6674065420560747, "grad_norm": 1.918344497680664, "learning_rate": 5.263836290219979e-06, "loss": 0.7084, "step": 11426 }, { "epoch": 0.6674649532710281, "grad_norm": 0.9643909931182861, "learning_rate": 5.262170170708383e-06, "loss": 0.7074, "step": 11427 }, { "epoch": 0.6675233644859813, "grad_norm": 1.592548131942749, "learning_rate": 5.260504220766829e-06, "loss": 0.8212, "step": 11428 }, { "epoch": 0.6675817757009346, "grad_norm": 1.1266850233078003, "learning_rate": 5.258838440454947e-06, "loss": 0.644, "step": 11429 }, { "epoch": 0.6676401869158879, "grad_norm": 1.9969749450683594, "learning_rate": 5.257172829832353e-06, "loss": 0.8328, "step": 11430 }, { "epoch": 0.6676985981308411, "grad_norm": 1.0787371397018433, "learning_rate": 5.255507388958662e-06, "loss": 0.7357, "step": 11431 }, { "epoch": 0.6677570093457944, "grad_norm": 2.218090534210205, "learning_rate": 5.253842117893484e-06, "loss": 0.6903, "step": 11432 }, { "epoch": 0.6678154205607477, "grad_norm": 1.7357152700424194, "learning_rate": 5.2521770166964135e-06, "loss": 0.7656, "step": 11433 }, { "epoch": 0.6678738317757009, "grad_norm": 1.207649827003479, "learning_rate": 5.250512085427053e-06, "loss": 0.8055, "step": 11434 }, { "epoch": 0.6679322429906542, "grad_norm": 0.9042620658874512, "learning_rate": 5.248847324144983e-06, "loss": 0.5394, "step": 11435 }, { "epoch": 0.6679906542056074, "grad_norm": 2.73868727684021, "learning_rate": 5.247182732909792e-06, "loss": 0.8776, "step": 11436 }, { "epoch": 0.6680490654205608, "grad_norm": 1.4241218566894531, "learning_rate": 5.245518311781062e-06, "loss": 0.8231, "step": 11437 }, { "epoch": 0.6681074766355141, "grad_norm": 1.3921560049057007, "learning_rate": 5.243854060818352e-06, "loss": 0.8094, "step": 11438 }, { "epoch": 0.6681658878504673, "grad_norm": 1.4562362432479858, "learning_rate": 5.242189980081236e-06, "loss": 0.9043, "step": 11439 }, { "epoch": 0.6682242990654206, "grad_norm": 1.5458824634552002, "learning_rate": 5.240526069629265e-06, "loss": 0.9512, "step": 11440 }, { "epoch": 0.6682827102803738, "grad_norm": 1.1464651823043823, "learning_rate": 5.238862329522e-06, "loss": 0.654, "step": 11441 }, { "epoch": 0.6683411214953271, "grad_norm": 1.2303389310836792, "learning_rate": 5.237198759818977e-06, "loss": 0.7874, "step": 11442 }, { "epoch": 0.6683995327102804, "grad_norm": 1.3138806819915771, "learning_rate": 5.2355353605797445e-06, "loss": 0.8493, "step": 11443 }, { "epoch": 0.6684579439252336, "grad_norm": 1.2203189134597778, "learning_rate": 5.233872131863838e-06, "loss": 0.6942, "step": 11444 }, { "epoch": 0.6685163551401869, "grad_norm": 1.1126405000686646, "learning_rate": 5.232209073730777e-06, "loss": 0.7507, "step": 11445 }, { "epoch": 0.6685747663551402, "grad_norm": 1.3579524755477905, "learning_rate": 5.23054618624009e-06, "loss": 0.8884, "step": 11446 }, { "epoch": 0.6686331775700934, "grad_norm": 1.6810017824172974, "learning_rate": 5.22888346945129e-06, "loss": 0.7747, "step": 11447 }, { "epoch": 0.6686915887850468, "grad_norm": 1.2265173196792603, "learning_rate": 5.227220923423887e-06, "loss": 0.8297, "step": 11448 }, { "epoch": 0.66875, "grad_norm": 1.0875024795532227, "learning_rate": 5.225558548217389e-06, "loss": 0.822, "step": 11449 }, { "epoch": 0.6688084112149533, "grad_norm": 1.3555594682693481, "learning_rate": 5.223896343891286e-06, "loss": 0.7787, "step": 11450 }, { "epoch": 0.6688668224299066, "grad_norm": 1.3789870738983154, "learning_rate": 5.222234310505076e-06, "loss": 0.7776, "step": 11451 }, { "epoch": 0.6689252336448598, "grad_norm": 1.013838291168213, "learning_rate": 5.220572448118239e-06, "loss": 0.6209, "step": 11452 }, { "epoch": 0.6689836448598131, "grad_norm": 1.0026440620422363, "learning_rate": 5.218910756790256e-06, "loss": 0.6675, "step": 11453 }, { "epoch": 0.6690420560747663, "grad_norm": 1.5343996286392212, "learning_rate": 5.217249236580604e-06, "loss": 1.0412, "step": 11454 }, { "epoch": 0.6691004672897196, "grad_norm": 1.40828537940979, "learning_rate": 5.215587887548743e-06, "loss": 0.6945, "step": 11455 }, { "epoch": 0.6691588785046729, "grad_norm": 0.9824512004852295, "learning_rate": 5.213926709754143e-06, "loss": 0.6685, "step": 11456 }, { "epoch": 0.6692172897196261, "grad_norm": 1.0898703336715698, "learning_rate": 5.212265703256251e-06, "loss": 0.777, "step": 11457 }, { "epoch": 0.6692757009345794, "grad_norm": 0.9958239197731018, "learning_rate": 5.210604868114513e-06, "loss": 0.686, "step": 11458 }, { "epoch": 0.6693341121495328, "grad_norm": 1.1359879970550537, "learning_rate": 5.208944204388377e-06, "loss": 0.7503, "step": 11459 }, { "epoch": 0.669392523364486, "grad_norm": 1.2950315475463867, "learning_rate": 5.207283712137279e-06, "loss": 0.823, "step": 11460 }, { "epoch": 0.6694509345794393, "grad_norm": 0.8585611581802368, "learning_rate": 5.205623391420651e-06, "loss": 0.6998, "step": 11461 }, { "epoch": 0.6695093457943925, "grad_norm": 0.9835303425788879, "learning_rate": 5.203963242297913e-06, "loss": 0.6974, "step": 11462 }, { "epoch": 0.6695677570093458, "grad_norm": 1.4506902694702148, "learning_rate": 5.202303264828482e-06, "loss": 0.75, "step": 11463 }, { "epoch": 0.6696261682242991, "grad_norm": 2.7853939533233643, "learning_rate": 5.200643459071772e-06, "loss": 0.8482, "step": 11464 }, { "epoch": 0.6696845794392523, "grad_norm": 1.3730469942092896, "learning_rate": 5.198983825087191e-06, "loss": 0.7747, "step": 11465 }, { "epoch": 0.6697429906542056, "grad_norm": 1.7682079076766968, "learning_rate": 5.197324362934131e-06, "loss": 0.7961, "step": 11466 }, { "epoch": 0.6698014018691589, "grad_norm": 0.8468750715255737, "learning_rate": 5.195665072671995e-06, "loss": 0.786, "step": 11467 }, { "epoch": 0.6698598130841121, "grad_norm": 1.042715311050415, "learning_rate": 5.194005954360161e-06, "loss": 0.5052, "step": 11468 }, { "epoch": 0.6699182242990654, "grad_norm": 1.1294255256652832, "learning_rate": 5.192347008058014e-06, "loss": 0.8694, "step": 11469 }, { "epoch": 0.6699766355140186, "grad_norm": 1.1630610227584839, "learning_rate": 5.190688233824932e-06, "loss": 0.6553, "step": 11470 }, { "epoch": 0.670035046728972, "grad_norm": 1.2084784507751465, "learning_rate": 5.189029631720277e-06, "loss": 0.8091, "step": 11471 }, { "epoch": 0.6700934579439253, "grad_norm": 1.2916479110717773, "learning_rate": 5.187371201803417e-06, "loss": 0.8446, "step": 11472 }, { "epoch": 0.6701518691588785, "grad_norm": 1.6361145973205566, "learning_rate": 5.185712944133704e-06, "loss": 0.7995, "step": 11473 }, { "epoch": 0.6702102803738318, "grad_norm": 1.3707728385925293, "learning_rate": 5.184054858770493e-06, "loss": 0.8966, "step": 11474 }, { "epoch": 0.670268691588785, "grad_norm": 1.2411824464797974, "learning_rate": 5.1823969457731225e-06, "loss": 0.8462, "step": 11475 }, { "epoch": 0.6703271028037383, "grad_norm": 1.608950138092041, "learning_rate": 5.180739205200932e-06, "loss": 0.778, "step": 11476 }, { "epoch": 0.6703855140186916, "grad_norm": 1.996750831604004, "learning_rate": 5.179081637113259e-06, "loss": 0.7877, "step": 11477 }, { "epoch": 0.6704439252336448, "grad_norm": 1.328105092048645, "learning_rate": 5.177424241569419e-06, "loss": 0.9024, "step": 11478 }, { "epoch": 0.6705023364485981, "grad_norm": 1.3731805086135864, "learning_rate": 5.17576701862874e-06, "loss": 0.7293, "step": 11479 }, { "epoch": 0.6705607476635514, "grad_norm": 1.9889602661132812, "learning_rate": 5.174109968350528e-06, "loss": 1.021, "step": 11480 }, { "epoch": 0.6706191588785047, "grad_norm": 0.9850389957427979, "learning_rate": 5.172453090794094e-06, "loss": 0.5336, "step": 11481 }, { "epoch": 0.670677570093458, "grad_norm": 1.940744161605835, "learning_rate": 5.170796386018741e-06, "loss": 0.6614, "step": 11482 }, { "epoch": 0.6707359813084112, "grad_norm": 1.606282114982605, "learning_rate": 5.1691398540837564e-06, "loss": 0.8794, "step": 11483 }, { "epoch": 0.6707943925233645, "grad_norm": 1.1651594638824463, "learning_rate": 5.167483495048438e-06, "loss": 0.6838, "step": 11484 }, { "epoch": 0.6708528037383178, "grad_norm": 1.1466361284255981, "learning_rate": 5.165827308972058e-06, "loss": 0.8002, "step": 11485 }, { "epoch": 0.670911214953271, "grad_norm": 1.4904407262802124, "learning_rate": 5.164171295913898e-06, "loss": 0.9105, "step": 11486 }, { "epoch": 0.6709696261682243, "grad_norm": 1.0169827938079834, "learning_rate": 5.1625154559332295e-06, "loss": 0.6189, "step": 11487 }, { "epoch": 0.6710280373831776, "grad_norm": 1.1041280031204224, "learning_rate": 5.16085978908931e-06, "loss": 0.7033, "step": 11488 }, { "epoch": 0.6710864485981308, "grad_norm": 1.2051862478256226, "learning_rate": 5.159204295441405e-06, "loss": 0.8414, "step": 11489 }, { "epoch": 0.6711448598130841, "grad_norm": 1.3377574682235718, "learning_rate": 5.157548975048761e-06, "loss": 0.6378, "step": 11490 }, { "epoch": 0.6712032710280373, "grad_norm": 1.2492313385009766, "learning_rate": 5.155893827970618e-06, "loss": 0.9725, "step": 11491 }, { "epoch": 0.6712616822429907, "grad_norm": 0.9580584168434143, "learning_rate": 5.154238854266221e-06, "loss": 0.6755, "step": 11492 }, { "epoch": 0.671320093457944, "grad_norm": 1.4428874254226685, "learning_rate": 5.152584053994802e-06, "loss": 0.8881, "step": 11493 }, { "epoch": 0.6713785046728972, "grad_norm": 1.3651100397109985, "learning_rate": 5.15092942721559e-06, "loss": 0.8046, "step": 11494 }, { "epoch": 0.6714369158878505, "grad_norm": 1.7175118923187256, "learning_rate": 5.149274973987804e-06, "loss": 0.6869, "step": 11495 }, { "epoch": 0.6714953271028037, "grad_norm": 1.1725927591323853, "learning_rate": 5.147620694370649e-06, "loss": 0.7101, "step": 11496 }, { "epoch": 0.671553738317757, "grad_norm": 0.9635185599327087, "learning_rate": 5.145966588423341e-06, "loss": 0.7323, "step": 11497 }, { "epoch": 0.6716121495327103, "grad_norm": 1.1412047147750854, "learning_rate": 5.144312656205081e-06, "loss": 0.7203, "step": 11498 }, { "epoch": 0.6716705607476635, "grad_norm": 1.4799100160598755, "learning_rate": 5.142658897775068e-06, "loss": 0.846, "step": 11499 }, { "epoch": 0.6717289719626168, "grad_norm": 0.9460088610649109, "learning_rate": 5.141005313192486e-06, "loss": 0.7519, "step": 11500 }, { "epoch": 0.6717873831775701, "grad_norm": 1.087025761604309, "learning_rate": 5.139351902516516e-06, "loss": 0.7871, "step": 11501 }, { "epoch": 0.6718457943925233, "grad_norm": 1.2672780752182007, "learning_rate": 5.137698665806337e-06, "loss": 0.8276, "step": 11502 }, { "epoch": 0.6719042056074767, "grad_norm": 1.2082442045211792, "learning_rate": 5.136045603121118e-06, "loss": 0.7856, "step": 11503 }, { "epoch": 0.6719626168224299, "grad_norm": 1.1099720001220703, "learning_rate": 5.134392714520032e-06, "loss": 0.7852, "step": 11504 }, { "epoch": 0.6720210280373832, "grad_norm": 1.3195335865020752, "learning_rate": 5.132740000062227e-06, "loss": 0.8807, "step": 11505 }, { "epoch": 0.6720794392523365, "grad_norm": 1.0025297403335571, "learning_rate": 5.131087459806854e-06, "loss": 0.6834, "step": 11506 }, { "epoch": 0.6721378504672897, "grad_norm": 1.973257064819336, "learning_rate": 5.1294350938130675e-06, "loss": 0.6854, "step": 11507 }, { "epoch": 0.672196261682243, "grad_norm": 1.417233943939209, "learning_rate": 5.127782902139997e-06, "loss": 0.5794, "step": 11508 }, { "epoch": 0.6722546728971963, "grad_norm": 1.269609808921814, "learning_rate": 5.12613088484678e-06, "loss": 0.7698, "step": 11509 }, { "epoch": 0.6723130841121495, "grad_norm": 1.2054394483566284, "learning_rate": 5.124479041992548e-06, "loss": 0.653, "step": 11510 }, { "epoch": 0.6723714953271028, "grad_norm": 1.053026795387268, "learning_rate": 5.122827373636412e-06, "loss": 0.7367, "step": 11511 }, { "epoch": 0.672429906542056, "grad_norm": 1.2811968326568604, "learning_rate": 5.121175879837494e-06, "loss": 0.7469, "step": 11512 }, { "epoch": 0.6724883177570093, "grad_norm": 1.0040849447250366, "learning_rate": 5.119524560654896e-06, "loss": 0.7523, "step": 11513 }, { "epoch": 0.6725467289719627, "grad_norm": 1.2105056047439575, "learning_rate": 5.117873416147724e-06, "loss": 0.7076, "step": 11514 }, { "epoch": 0.6726051401869159, "grad_norm": 1.0381724834442139, "learning_rate": 5.116222446375075e-06, "loss": 0.894, "step": 11515 }, { "epoch": 0.6726635514018692, "grad_norm": 1.0219488143920898, "learning_rate": 5.114571651396033e-06, "loss": 0.7819, "step": 11516 }, { "epoch": 0.6727219626168224, "grad_norm": 1.1430319547653198, "learning_rate": 5.112921031269686e-06, "loss": 0.8354, "step": 11517 }, { "epoch": 0.6727803738317757, "grad_norm": 1.0675281286239624, "learning_rate": 5.1112705860551074e-06, "loss": 0.8085, "step": 11518 }, { "epoch": 0.672838785046729, "grad_norm": 1.6001708507537842, "learning_rate": 5.109620315811368e-06, "loss": 0.881, "step": 11519 }, { "epoch": 0.6728971962616822, "grad_norm": 3.996000289916992, "learning_rate": 5.107970220597536e-06, "loss": 0.8689, "step": 11520 }, { "epoch": 0.6729556074766355, "grad_norm": 1.0871531963348389, "learning_rate": 5.106320300472662e-06, "loss": 0.7721, "step": 11521 }, { "epoch": 0.6730140186915888, "grad_norm": 1.1596553325653076, "learning_rate": 5.104670555495808e-06, "loss": 0.6974, "step": 11522 }, { "epoch": 0.673072429906542, "grad_norm": 1.3157413005828857, "learning_rate": 5.103020985726012e-06, "loss": 0.7498, "step": 11523 }, { "epoch": 0.6731308411214953, "grad_norm": 1.3869938850402832, "learning_rate": 5.1013715912223105e-06, "loss": 0.872, "step": 11524 }, { "epoch": 0.6731892523364486, "grad_norm": 1.095844030380249, "learning_rate": 5.099722372043742e-06, "loss": 0.7931, "step": 11525 }, { "epoch": 0.6732476635514019, "grad_norm": 1.1905622482299805, "learning_rate": 5.098073328249331e-06, "loss": 0.8242, "step": 11526 }, { "epoch": 0.6733060747663552, "grad_norm": 1.3615049123764038, "learning_rate": 5.096424459898103e-06, "loss": 0.7641, "step": 11527 }, { "epoch": 0.6733644859813084, "grad_norm": 1.250719666481018, "learning_rate": 5.0947757670490675e-06, "loss": 0.9241, "step": 11528 }, { "epoch": 0.6734228971962617, "grad_norm": 1.3044284582138062, "learning_rate": 5.093127249761229e-06, "loss": 0.8658, "step": 11529 }, { "epoch": 0.673481308411215, "grad_norm": 1.1200801134109497, "learning_rate": 5.0914789080935925e-06, "loss": 0.7584, "step": 11530 }, { "epoch": 0.6735397196261682, "grad_norm": 1.4226946830749512, "learning_rate": 5.089830742105153e-06, "loss": 0.8179, "step": 11531 }, { "epoch": 0.6735981308411215, "grad_norm": 1.2491635084152222, "learning_rate": 5.088182751854903e-06, "loss": 0.7144, "step": 11532 }, { "epoch": 0.6736565420560747, "grad_norm": 1.3855427503585815, "learning_rate": 5.086534937401823e-06, "loss": 0.7967, "step": 11533 }, { "epoch": 0.673714953271028, "grad_norm": 1.1309484243392944, "learning_rate": 5.084887298804883e-06, "loss": 0.6592, "step": 11534 }, { "epoch": 0.6737733644859814, "grad_norm": 1.1220552921295166, "learning_rate": 5.0832398361230595e-06, "loss": 0.7426, "step": 11535 }, { "epoch": 0.6738317757009346, "grad_norm": 1.2055182456970215, "learning_rate": 5.081592549415315e-06, "loss": 0.8583, "step": 11536 }, { "epoch": 0.6738901869158879, "grad_norm": 1.3210337162017822, "learning_rate": 5.079945438740611e-06, "loss": 0.8946, "step": 11537 }, { "epoch": 0.6739485981308411, "grad_norm": 1.0911911725997925, "learning_rate": 5.078298504157894e-06, "loss": 0.7328, "step": 11538 }, { "epoch": 0.6740070093457944, "grad_norm": 1.3233097791671753, "learning_rate": 5.076651745726107e-06, "loss": 0.7487, "step": 11539 }, { "epoch": 0.6740654205607477, "grad_norm": 1.3033534288406372, "learning_rate": 5.0750051635041946e-06, "loss": 0.6504, "step": 11540 }, { "epoch": 0.6741238317757009, "grad_norm": 1.0231975317001343, "learning_rate": 5.073358757551081e-06, "loss": 0.594, "step": 11541 }, { "epoch": 0.6741822429906542, "grad_norm": 1.4210339784622192, "learning_rate": 5.071712527925697e-06, "loss": 0.7735, "step": 11542 }, { "epoch": 0.6742406542056075, "grad_norm": 1.406362771987915, "learning_rate": 5.070066474686967e-06, "loss": 0.7139, "step": 11543 }, { "epoch": 0.6742990654205607, "grad_norm": 1.252797245979309, "learning_rate": 5.068420597893795e-06, "loss": 0.8001, "step": 11544 }, { "epoch": 0.674357476635514, "grad_norm": 1.4580683708190918, "learning_rate": 5.066774897605096e-06, "loss": 0.6787, "step": 11545 }, { "epoch": 0.6744158878504672, "grad_norm": 1.0753482580184937, "learning_rate": 5.065129373879762e-06, "loss": 0.6162, "step": 11546 }, { "epoch": 0.6744742990654206, "grad_norm": 1.4582765102386475, "learning_rate": 5.063484026776695e-06, "loss": 0.8384, "step": 11547 }, { "epoch": 0.6745327102803739, "grad_norm": 1.2376903295516968, "learning_rate": 5.061838856354781e-06, "loss": 0.7602, "step": 11548 }, { "epoch": 0.6745911214953271, "grad_norm": 1.0707805156707764, "learning_rate": 5.060193862672899e-06, "loss": 0.8118, "step": 11549 }, { "epoch": 0.6746495327102804, "grad_norm": 1.3471769094467163, "learning_rate": 5.058549045789933e-06, "loss": 0.8431, "step": 11550 }, { "epoch": 0.6747079439252337, "grad_norm": 1.0224146842956543, "learning_rate": 5.05690440576474e-06, "loss": 0.7533, "step": 11551 }, { "epoch": 0.6747663551401869, "grad_norm": 0.9726420044898987, "learning_rate": 5.055259942656187e-06, "loss": 0.7146, "step": 11552 }, { "epoch": 0.6748247663551402, "grad_norm": 1.249346375465393, "learning_rate": 5.053615656523136e-06, "loss": 0.6347, "step": 11553 }, { "epoch": 0.6748831775700934, "grad_norm": 1.1522483825683594, "learning_rate": 5.051971547424432e-06, "loss": 0.8649, "step": 11554 }, { "epoch": 0.6749415887850467, "grad_norm": 1.219592571258545, "learning_rate": 5.050327615418921e-06, "loss": 0.6301, "step": 11555 }, { "epoch": 0.675, "grad_norm": 0.9914543628692627, "learning_rate": 5.048683860565435e-06, "loss": 0.6771, "step": 11556 }, { "epoch": 0.6750584112149532, "grad_norm": 1.0409601926803589, "learning_rate": 5.047040282922815e-06, "loss": 0.7341, "step": 11557 }, { "epoch": 0.6751168224299066, "grad_norm": 1.358279824256897, "learning_rate": 5.045396882549875e-06, "loss": 0.9814, "step": 11558 }, { "epoch": 0.6751752336448598, "grad_norm": 0.8989133238792419, "learning_rate": 5.043753659505437e-06, "loss": 0.5858, "step": 11559 }, { "epoch": 0.6752336448598131, "grad_norm": 0.8842030763626099, "learning_rate": 5.04211061384832e-06, "loss": 0.6399, "step": 11560 }, { "epoch": 0.6752920560747664, "grad_norm": 1.0377248525619507, "learning_rate": 5.04046774563732e-06, "loss": 0.723, "step": 11561 }, { "epoch": 0.6753504672897196, "grad_norm": 1.3146953582763672, "learning_rate": 5.038825054931244e-06, "loss": 0.7726, "step": 11562 }, { "epoch": 0.6754088785046729, "grad_norm": 1.4478806257247925, "learning_rate": 5.037182541788876e-06, "loss": 0.7745, "step": 11563 }, { "epoch": 0.6754672897196262, "grad_norm": 1.2336708307266235, "learning_rate": 5.03554020626901e-06, "loss": 0.5969, "step": 11564 }, { "epoch": 0.6755257009345794, "grad_norm": 1.7985819578170776, "learning_rate": 5.033898048430428e-06, "loss": 0.7286, "step": 11565 }, { "epoch": 0.6755841121495327, "grad_norm": 1.4439688920974731, "learning_rate": 5.032256068331894e-06, "loss": 0.9513, "step": 11566 }, { "epoch": 0.6756425233644859, "grad_norm": 1.2370842695236206, "learning_rate": 5.030614266032188e-06, "loss": 0.7274, "step": 11567 }, { "epoch": 0.6757009345794392, "grad_norm": 2.043815851211548, "learning_rate": 5.02897264159006e-06, "loss": 0.735, "step": 11568 }, { "epoch": 0.6757593457943926, "grad_norm": 1.6928317546844482, "learning_rate": 5.0273311950642685e-06, "loss": 0.7564, "step": 11569 }, { "epoch": 0.6758177570093458, "grad_norm": 1.8177930116653442, "learning_rate": 5.025689926513568e-06, "loss": 0.6693, "step": 11570 }, { "epoch": 0.6758761682242991, "grad_norm": 1.935931921005249, "learning_rate": 5.024048835996693e-06, "loss": 0.7308, "step": 11571 }, { "epoch": 0.6759345794392523, "grad_norm": 1.1751878261566162, "learning_rate": 5.0224079235723855e-06, "loss": 0.8225, "step": 11572 }, { "epoch": 0.6759929906542056, "grad_norm": 1.0536483526229858, "learning_rate": 5.020767189299369e-06, "loss": 0.6263, "step": 11573 }, { "epoch": 0.6760514018691589, "grad_norm": 1.9660804271697998, "learning_rate": 5.019126633236367e-06, "loss": 0.7349, "step": 11574 }, { "epoch": 0.6761098130841121, "grad_norm": 1.7343318462371826, "learning_rate": 5.017486255442097e-06, "loss": 0.859, "step": 11575 }, { "epoch": 0.6761682242990654, "grad_norm": 1.5468990802764893, "learning_rate": 5.0158460559752706e-06, "loss": 0.8841, "step": 11576 }, { "epoch": 0.6762266355140187, "grad_norm": 1.823673963546753, "learning_rate": 5.0142060348945946e-06, "loss": 0.6755, "step": 11577 }, { "epoch": 0.6762850467289719, "grad_norm": 1.5686852931976318, "learning_rate": 5.012566192258763e-06, "loss": 0.9382, "step": 11578 }, { "epoch": 0.6763434579439253, "grad_norm": 1.265792727470398, "learning_rate": 5.0109265281264614e-06, "loss": 0.8139, "step": 11579 }, { "epoch": 0.6764018691588785, "grad_norm": 1.8913546800613403, "learning_rate": 5.009287042556381e-06, "loss": 0.8595, "step": 11580 }, { "epoch": 0.6764602803738318, "grad_norm": 1.5820528268814087, "learning_rate": 5.0076477356072025e-06, "loss": 0.9627, "step": 11581 }, { "epoch": 0.6765186915887851, "grad_norm": 1.554783582687378, "learning_rate": 5.006008607337591e-06, "loss": 0.8169, "step": 11582 }, { "epoch": 0.6765771028037383, "grad_norm": 2.0615196228027344, "learning_rate": 5.004369657806218e-06, "loss": 0.759, "step": 11583 }, { "epoch": 0.6766355140186916, "grad_norm": 1.6222686767578125, "learning_rate": 5.002730887071736e-06, "loss": 0.7815, "step": 11584 }, { "epoch": 0.6766939252336449, "grad_norm": 1.3251467943191528, "learning_rate": 5.001092295192801e-06, "loss": 0.7253, "step": 11585 }, { "epoch": 0.6767523364485981, "grad_norm": 1.673487901687622, "learning_rate": 4.999453882228064e-06, "loss": 0.8123, "step": 11586 }, { "epoch": 0.6768107476635514, "grad_norm": 2.2943601608276367, "learning_rate": 4.997815648236156e-06, "loss": 0.9027, "step": 11587 }, { "epoch": 0.6768691588785046, "grad_norm": 0.9431536793708801, "learning_rate": 4.996177593275719e-06, "loss": 0.815, "step": 11588 }, { "epoch": 0.6769275700934579, "grad_norm": 1.3655575513839722, "learning_rate": 4.994539717405372e-06, "loss": 0.7615, "step": 11589 }, { "epoch": 0.6769859813084113, "grad_norm": 1.7769302129745483, "learning_rate": 4.992902020683744e-06, "loss": 0.8119, "step": 11590 }, { "epoch": 0.6770443925233645, "grad_norm": 1.6116994619369507, "learning_rate": 4.991264503169441e-06, "loss": 0.9126, "step": 11591 }, { "epoch": 0.6771028037383178, "grad_norm": 1.6761277914047241, "learning_rate": 4.989627164921073e-06, "loss": 0.8062, "step": 11592 }, { "epoch": 0.677161214953271, "grad_norm": 1.1706929206848145, "learning_rate": 4.9879900059972496e-06, "loss": 0.6701, "step": 11593 }, { "epoch": 0.6772196261682243, "grad_norm": 1.5072575807571411, "learning_rate": 4.986353026456554e-06, "loss": 0.7814, "step": 11594 }, { "epoch": 0.6772780373831776, "grad_norm": 1.092706322669983, "learning_rate": 4.984716226357585e-06, "loss": 0.6272, "step": 11595 }, { "epoch": 0.6773364485981308, "grad_norm": 1.476114273071289, "learning_rate": 4.983079605758916e-06, "loss": 0.8061, "step": 11596 }, { "epoch": 0.6773948598130841, "grad_norm": 2.1013848781585693, "learning_rate": 4.981443164719126e-06, "loss": 0.7954, "step": 11597 }, { "epoch": 0.6774532710280374, "grad_norm": 1.4995030164718628, "learning_rate": 4.979806903296789e-06, "loss": 0.8571, "step": 11598 }, { "epoch": 0.6775116822429906, "grad_norm": 1.9765613079071045, "learning_rate": 4.978170821550459e-06, "loss": 0.8539, "step": 11599 }, { "epoch": 0.677570093457944, "grad_norm": 2.348243236541748, "learning_rate": 4.976534919538702e-06, "loss": 0.9248, "step": 11600 }, { "epoch": 0.6776285046728971, "grad_norm": 1.0578871965408325, "learning_rate": 4.974899197320059e-06, "loss": 0.7871, "step": 11601 }, { "epoch": 0.6776869158878505, "grad_norm": 1.459721326828003, "learning_rate": 4.973263654953078e-06, "loss": 0.6864, "step": 11602 }, { "epoch": 0.6777453271028038, "grad_norm": 2.019139051437378, "learning_rate": 4.9716282924963e-06, "loss": 0.8289, "step": 11603 }, { "epoch": 0.677803738317757, "grad_norm": 1.5784375667572021, "learning_rate": 4.969993110008248e-06, "loss": 0.8266, "step": 11604 }, { "epoch": 0.6778621495327103, "grad_norm": 1.273911476135254, "learning_rate": 4.968358107547453e-06, "loss": 0.8354, "step": 11605 }, { "epoch": 0.6779205607476636, "grad_norm": 1.4937361478805542, "learning_rate": 4.966723285172429e-06, "loss": 0.8948, "step": 11606 }, { "epoch": 0.6779789719626168, "grad_norm": 1.2362114191055298, "learning_rate": 4.965088642941686e-06, "loss": 0.7735, "step": 11607 }, { "epoch": 0.6780373831775701, "grad_norm": 1.0172901153564453, "learning_rate": 4.963454180913729e-06, "loss": 0.73, "step": 11608 }, { "epoch": 0.6780957943925233, "grad_norm": 1.5458462238311768, "learning_rate": 4.96181989914706e-06, "loss": 0.8226, "step": 11609 }, { "epoch": 0.6781542056074766, "grad_norm": 1.4768009185791016, "learning_rate": 4.960185797700173e-06, "loss": 0.8021, "step": 11610 }, { "epoch": 0.67821261682243, "grad_norm": 1.2778400182724, "learning_rate": 4.95855187663155e-06, "loss": 0.7832, "step": 11611 }, { "epoch": 0.6782710280373832, "grad_norm": 1.6113462448120117, "learning_rate": 4.956918135999667e-06, "loss": 0.6533, "step": 11612 }, { "epoch": 0.6783294392523365, "grad_norm": 1.3704379796981812, "learning_rate": 4.955284575862999e-06, "loss": 0.7166, "step": 11613 }, { "epoch": 0.6783878504672897, "grad_norm": 1.1956123113632202, "learning_rate": 4.953651196280012e-06, "loss": 0.605, "step": 11614 }, { "epoch": 0.678446261682243, "grad_norm": 0.9671343564987183, "learning_rate": 4.952017997309172e-06, "loss": 0.7294, "step": 11615 }, { "epoch": 0.6785046728971963, "grad_norm": 1.378166675567627, "learning_rate": 4.950384979008928e-06, "loss": 0.7477, "step": 11616 }, { "epoch": 0.6785630841121495, "grad_norm": 1.300020694732666, "learning_rate": 4.948752141437719e-06, "loss": 0.7871, "step": 11617 }, { "epoch": 0.6786214953271028, "grad_norm": 1.0098717212677002, "learning_rate": 4.9471194846539945e-06, "loss": 0.7512, "step": 11618 }, { "epoch": 0.6786799065420561, "grad_norm": 1.0680433511734009, "learning_rate": 4.945487008716186e-06, "loss": 0.6815, "step": 11619 }, { "epoch": 0.6787383177570093, "grad_norm": 1.1808745861053467, "learning_rate": 4.943854713682723e-06, "loss": 0.7211, "step": 11620 }, { "epoch": 0.6787967289719626, "grad_norm": 1.7064288854599, "learning_rate": 4.9422225996120256e-06, "loss": 0.8619, "step": 11621 }, { "epoch": 0.6788551401869158, "grad_norm": 1.0783054828643799, "learning_rate": 4.940590666562502e-06, "loss": 0.5839, "step": 11622 }, { "epoch": 0.6789135514018692, "grad_norm": 0.8778427839279175, "learning_rate": 4.93895891459257e-06, "loss": 0.7887, "step": 11623 }, { "epoch": 0.6789719626168225, "grad_norm": 1.0208686590194702, "learning_rate": 4.937327343760617e-06, "loss": 0.7026, "step": 11624 }, { "epoch": 0.6790303738317757, "grad_norm": 1.2721682786941528, "learning_rate": 4.935695954125057e-06, "loss": 0.6948, "step": 11625 }, { "epoch": 0.679088785046729, "grad_norm": 1.030289888381958, "learning_rate": 4.934064745744267e-06, "loss": 0.7231, "step": 11626 }, { "epoch": 0.6791471962616823, "grad_norm": 1.1778782606124878, "learning_rate": 4.932433718676627e-06, "loss": 0.8879, "step": 11627 }, { "epoch": 0.6792056074766355, "grad_norm": 0.9782363176345825, "learning_rate": 4.930802872980522e-06, "loss": 0.7963, "step": 11628 }, { "epoch": 0.6792640186915888, "grad_norm": 1.2996866703033447, "learning_rate": 4.929172208714309e-06, "loss": 0.8065, "step": 11629 }, { "epoch": 0.679322429906542, "grad_norm": 2.5790183544158936, "learning_rate": 4.927541725936357e-06, "loss": 0.792, "step": 11630 }, { "epoch": 0.6793808411214953, "grad_norm": 1.181649923324585, "learning_rate": 4.925911424705027e-06, "loss": 0.777, "step": 11631 }, { "epoch": 0.6794392523364486, "grad_norm": 1.0499205589294434, "learning_rate": 4.924281305078658e-06, "loss": 0.7829, "step": 11632 }, { "epoch": 0.6794976635514018, "grad_norm": 0.838142454624176, "learning_rate": 4.922651367115603e-06, "loss": 0.6696, "step": 11633 }, { "epoch": 0.6795560747663552, "grad_norm": 1.2050946950912476, "learning_rate": 4.921021610874191e-06, "loss": 0.794, "step": 11634 }, { "epoch": 0.6796144859813084, "grad_norm": 0.7419887185096741, "learning_rate": 4.919392036412753e-06, "loss": 0.5874, "step": 11635 }, { "epoch": 0.6796728971962617, "grad_norm": 1.5201876163482666, "learning_rate": 4.91776264378962e-06, "loss": 0.869, "step": 11636 }, { "epoch": 0.679731308411215, "grad_norm": 1.3028230667114258, "learning_rate": 4.9161334330631e-06, "loss": 0.7652, "step": 11637 }, { "epoch": 0.6797897196261682, "grad_norm": 1.0736346244812012, "learning_rate": 4.91450440429151e-06, "loss": 0.8854, "step": 11638 }, { "epoch": 0.6798481308411215, "grad_norm": 1.0979126691818237, "learning_rate": 4.912875557533151e-06, "loss": 0.9137, "step": 11639 }, { "epoch": 0.6799065420560748, "grad_norm": 0.884863018989563, "learning_rate": 4.911246892846317e-06, "loss": 0.7326, "step": 11640 }, { "epoch": 0.679964953271028, "grad_norm": 1.2244994640350342, "learning_rate": 4.909618410289304e-06, "loss": 0.6187, "step": 11641 }, { "epoch": 0.6800233644859813, "grad_norm": 1.0205405950546265, "learning_rate": 4.907990109920394e-06, "loss": 0.7212, "step": 11642 }, { "epoch": 0.6800817757009345, "grad_norm": 1.0388202667236328, "learning_rate": 4.90636199179787e-06, "loss": 0.9637, "step": 11643 }, { "epoch": 0.6801401869158878, "grad_norm": 1.115552306175232, "learning_rate": 4.9047340559799995e-06, "loss": 0.8235, "step": 11644 }, { "epoch": 0.6801985981308412, "grad_norm": 1.2096970081329346, "learning_rate": 4.903106302525043e-06, "loss": 0.8956, "step": 11645 }, { "epoch": 0.6802570093457944, "grad_norm": 0.9912765622138977, "learning_rate": 4.9014787314912635e-06, "loss": 0.8573, "step": 11646 }, { "epoch": 0.6803154205607477, "grad_norm": 1.3139638900756836, "learning_rate": 4.8998513429369135e-06, "loss": 0.7945, "step": 11647 }, { "epoch": 0.680373831775701, "grad_norm": 1.3374384641647339, "learning_rate": 4.89822413692024e-06, "loss": 0.7526, "step": 11648 }, { "epoch": 0.6804322429906542, "grad_norm": 1.1916396617889404, "learning_rate": 4.896597113499479e-06, "loss": 0.7757, "step": 11649 }, { "epoch": 0.6804906542056075, "grad_norm": 1.1374998092651367, "learning_rate": 4.89497027273286e-06, "loss": 0.6948, "step": 11650 }, { "epoch": 0.6805490654205607, "grad_norm": 1.400368571281433, "learning_rate": 4.893343614678611e-06, "loss": 0.8278, "step": 11651 }, { "epoch": 0.680607476635514, "grad_norm": 1.2063024044036865, "learning_rate": 4.891717139394952e-06, "loss": 0.8005, "step": 11652 }, { "epoch": 0.6806658878504673, "grad_norm": 1.3120278120040894, "learning_rate": 4.890090846940097e-06, "loss": 0.737, "step": 11653 }, { "epoch": 0.6807242990654205, "grad_norm": 1.1154348850250244, "learning_rate": 4.888464737372254e-06, "loss": 0.857, "step": 11654 }, { "epoch": 0.6807827102803738, "grad_norm": 1.0143085718154907, "learning_rate": 4.8868388107496135e-06, "loss": 0.7147, "step": 11655 }, { "epoch": 0.680841121495327, "grad_norm": 0.8982242941856384, "learning_rate": 4.8852130671303765e-06, "loss": 0.7507, "step": 11656 }, { "epoch": 0.6808995327102804, "grad_norm": 1.4026234149932861, "learning_rate": 4.883587506572721e-06, "loss": 0.7881, "step": 11657 }, { "epoch": 0.6809579439252337, "grad_norm": 1.3064885139465332, "learning_rate": 4.881962129134839e-06, "loss": 0.8346, "step": 11658 }, { "epoch": 0.6810163551401869, "grad_norm": 1.0197312831878662, "learning_rate": 4.8803369348748995e-06, "loss": 0.8249, "step": 11659 }, { "epoch": 0.6810747663551402, "grad_norm": 1.0892527103424072, "learning_rate": 4.878711923851062e-06, "loss": 0.8242, "step": 11660 }, { "epoch": 0.6811331775700935, "grad_norm": 1.0549277067184448, "learning_rate": 4.877087096121497e-06, "loss": 0.866, "step": 11661 }, { "epoch": 0.6811915887850467, "grad_norm": 1.1154063940048218, "learning_rate": 4.875462451744348e-06, "loss": 0.8418, "step": 11662 }, { "epoch": 0.68125, "grad_norm": 0.8963853120803833, "learning_rate": 4.8738379907777675e-06, "loss": 0.8746, "step": 11663 }, { "epoch": 0.6813084112149532, "grad_norm": 1.0390876531600952, "learning_rate": 4.872213713279901e-06, "loss": 0.8129, "step": 11664 }, { "epoch": 0.6813668224299065, "grad_norm": 1.4287675619125366, "learning_rate": 4.8705896193088716e-06, "loss": 0.8353, "step": 11665 }, { "epoch": 0.6814252336448599, "grad_norm": 1.0639564990997314, "learning_rate": 4.868965708922818e-06, "loss": 0.6865, "step": 11666 }, { "epoch": 0.681483644859813, "grad_norm": 1.6851420402526855, "learning_rate": 4.8673419821798505e-06, "loss": 0.8125, "step": 11667 }, { "epoch": 0.6815420560747664, "grad_norm": 1.298453450202942, "learning_rate": 4.865718439138089e-06, "loss": 1.0966, "step": 11668 }, { "epoch": 0.6816004672897197, "grad_norm": 1.266695261001587, "learning_rate": 4.864095079855643e-06, "loss": 0.6395, "step": 11669 }, { "epoch": 0.6816588785046729, "grad_norm": 1.5135689973831177, "learning_rate": 4.862471904390609e-06, "loss": 0.802, "step": 11670 }, { "epoch": 0.6817172897196262, "grad_norm": 1.4825807809829712, "learning_rate": 4.860848912801086e-06, "loss": 0.7141, "step": 11671 }, { "epoch": 0.6817757009345794, "grad_norm": 1.0714788436889648, "learning_rate": 4.859226105145156e-06, "loss": 0.6547, "step": 11672 }, { "epoch": 0.6818341121495327, "grad_norm": 1.697028398513794, "learning_rate": 4.857603481480907e-06, "loss": 0.7395, "step": 11673 }, { "epoch": 0.681892523364486, "grad_norm": 0.9672458171844482, "learning_rate": 4.855981041866408e-06, "loss": 0.6766, "step": 11674 }, { "epoch": 0.6819509345794392, "grad_norm": 1.0585353374481201, "learning_rate": 4.854358786359729e-06, "loss": 0.8106, "step": 11675 }, { "epoch": 0.6820093457943925, "grad_norm": 1.0775567293167114, "learning_rate": 4.852736715018937e-06, "loss": 0.8885, "step": 11676 }, { "epoch": 0.6820677570093457, "grad_norm": 1.4354805946350098, "learning_rate": 4.851114827902077e-06, "loss": 0.8657, "step": 11677 }, { "epoch": 0.6821261682242991, "grad_norm": 1.6609406471252441, "learning_rate": 4.849493125067207e-06, "loss": 0.8842, "step": 11678 }, { "epoch": 0.6821845794392524, "grad_norm": 1.2602792978286743, "learning_rate": 4.847871606572362e-06, "loss": 0.8077, "step": 11679 }, { "epoch": 0.6822429906542056, "grad_norm": 1.360411524772644, "learning_rate": 4.846250272475579e-06, "loss": 0.789, "step": 11680 }, { "epoch": 0.6823014018691589, "grad_norm": 1.1996561288833618, "learning_rate": 4.8446291228348904e-06, "loss": 0.7205, "step": 11681 }, { "epoch": 0.6823598130841122, "grad_norm": 1.5750538110733032, "learning_rate": 4.843008157708312e-06, "loss": 0.8767, "step": 11682 }, { "epoch": 0.6824182242990654, "grad_norm": 1.2035752534866333, "learning_rate": 4.841387377153866e-06, "loss": 0.7481, "step": 11683 }, { "epoch": 0.6824766355140187, "grad_norm": 1.275214433670044, "learning_rate": 4.8397667812295556e-06, "loss": 0.8962, "step": 11684 }, { "epoch": 0.6825350467289719, "grad_norm": 6.362448215484619, "learning_rate": 4.838146369993384e-06, "loss": 0.9706, "step": 11685 }, { "epoch": 0.6825934579439252, "grad_norm": 1.1274645328521729, "learning_rate": 4.836526143503351e-06, "loss": 0.6885, "step": 11686 }, { "epoch": 0.6826518691588785, "grad_norm": 1.9565318822860718, "learning_rate": 4.8349061018174385e-06, "loss": 0.8471, "step": 11687 }, { "epoch": 0.6827102803738317, "grad_norm": 1.1163827180862427, "learning_rate": 4.833286244993637e-06, "loss": 0.7286, "step": 11688 }, { "epoch": 0.6827686915887851, "grad_norm": 1.2056703567504883, "learning_rate": 4.831666573089918e-06, "loss": 0.7453, "step": 11689 }, { "epoch": 0.6828271028037384, "grad_norm": 1.5405280590057373, "learning_rate": 4.8300470861642425e-06, "loss": 0.7115, "step": 11690 }, { "epoch": 0.6828855140186916, "grad_norm": 1.2457810640335083, "learning_rate": 4.82842778427459e-06, "loss": 0.8705, "step": 11691 }, { "epoch": 0.6829439252336449, "grad_norm": 1.6975408792495728, "learning_rate": 4.826808667478906e-06, "loss": 0.705, "step": 11692 }, { "epoch": 0.6830023364485981, "grad_norm": 1.8011101484298706, "learning_rate": 4.825189735835138e-06, "loss": 0.8442, "step": 11693 }, { "epoch": 0.6830607476635514, "grad_norm": 1.1168615818023682, "learning_rate": 4.823570989401235e-06, "loss": 0.7873, "step": 11694 }, { "epoch": 0.6831191588785047, "grad_norm": 1.054681658744812, "learning_rate": 4.821952428235127e-06, "loss": 0.5746, "step": 11695 }, { "epoch": 0.6831775700934579, "grad_norm": 1.1113816499710083, "learning_rate": 4.820334052394746e-06, "loss": 0.7758, "step": 11696 }, { "epoch": 0.6832359813084112, "grad_norm": 1.3866236209869385, "learning_rate": 4.8187158619380195e-06, "loss": 0.7914, "step": 11697 }, { "epoch": 0.6832943925233644, "grad_norm": 1.931151032447815, "learning_rate": 4.817097856922853e-06, "loss": 0.9465, "step": 11698 }, { "epoch": 0.6833528037383177, "grad_norm": 1.490763545036316, "learning_rate": 4.815480037407167e-06, "loss": 0.8444, "step": 11699 }, { "epoch": 0.6834112149532711, "grad_norm": 1.1167137622833252, "learning_rate": 4.813862403448857e-06, "loss": 0.7191, "step": 11700 }, { "epoch": 0.6834696261682243, "grad_norm": 1.6654127836227417, "learning_rate": 4.812244955105821e-06, "loss": 0.7543, "step": 11701 }, { "epoch": 0.6835280373831776, "grad_norm": 1.0413798093795776, "learning_rate": 4.810627692435951e-06, "loss": 0.6836, "step": 11702 }, { "epoch": 0.6835864485981309, "grad_norm": 1.3634587526321411, "learning_rate": 4.809010615497126e-06, "loss": 0.635, "step": 11703 }, { "epoch": 0.6836448598130841, "grad_norm": 1.1237322092056274, "learning_rate": 4.807393724347227e-06, "loss": 0.7107, "step": 11704 }, { "epoch": 0.6837032710280374, "grad_norm": 0.9099960327148438, "learning_rate": 4.805777019044118e-06, "loss": 0.698, "step": 11705 }, { "epoch": 0.6837616822429906, "grad_norm": 1.7833049297332764, "learning_rate": 4.804160499645667e-06, "loss": 0.7172, "step": 11706 }, { "epoch": 0.6838200934579439, "grad_norm": 1.6798031330108643, "learning_rate": 4.802544166209725e-06, "loss": 0.9841, "step": 11707 }, { "epoch": 0.6838785046728972, "grad_norm": 1.1661741733551025, "learning_rate": 4.800928018794146e-06, "loss": 0.8434, "step": 11708 }, { "epoch": 0.6839369158878504, "grad_norm": 1.2217450141906738, "learning_rate": 4.799312057456774e-06, "loss": 0.7438, "step": 11709 }, { "epoch": 0.6839953271028038, "grad_norm": 1.4083555936813354, "learning_rate": 4.797696282255439e-06, "loss": 0.7934, "step": 11710 }, { "epoch": 0.684053738317757, "grad_norm": 1.114565372467041, "learning_rate": 4.79608069324798e-06, "loss": 0.8327, "step": 11711 }, { "epoch": 0.6841121495327103, "grad_norm": 1.0345350503921509, "learning_rate": 4.79446529049221e-06, "loss": 0.6314, "step": 11712 }, { "epoch": 0.6841705607476636, "grad_norm": 1.382698655128479, "learning_rate": 4.792850074045948e-06, "loss": 0.863, "step": 11713 }, { "epoch": 0.6842289719626168, "grad_norm": 1.2379053831100464, "learning_rate": 4.791235043967012e-06, "loss": 0.6965, "step": 11714 }, { "epoch": 0.6842873831775701, "grad_norm": 1.0193440914154053, "learning_rate": 4.789620200313194e-06, "loss": 0.8095, "step": 11715 }, { "epoch": 0.6843457943925234, "grad_norm": 3.0072500705718994, "learning_rate": 4.788005543142299e-06, "loss": 0.6167, "step": 11716 }, { "epoch": 0.6844042056074766, "grad_norm": 1.667852520942688, "learning_rate": 4.786391072512108e-06, "loss": 0.8021, "step": 11717 }, { "epoch": 0.6844626168224299, "grad_norm": 1.0319048166275024, "learning_rate": 4.784776788480409e-06, "loss": 0.6236, "step": 11718 }, { "epoch": 0.6845210280373831, "grad_norm": 1.0304239988327026, "learning_rate": 4.783162691104983e-06, "loss": 0.7241, "step": 11719 }, { "epoch": 0.6845794392523364, "grad_norm": 1.2000877857208252, "learning_rate": 4.781548780443588e-06, "loss": 0.8205, "step": 11720 }, { "epoch": 0.6846378504672898, "grad_norm": 1.162667989730835, "learning_rate": 4.779935056553998e-06, "loss": 0.7049, "step": 11721 }, { "epoch": 0.684696261682243, "grad_norm": 0.8473421931266785, "learning_rate": 4.778321519493966e-06, "loss": 0.7444, "step": 11722 }, { "epoch": 0.6847546728971963, "grad_norm": 3.679490566253662, "learning_rate": 4.776708169321231e-06, "loss": 0.8932, "step": 11723 }, { "epoch": 0.6848130841121496, "grad_norm": 1.1021246910095215, "learning_rate": 4.775095006093553e-06, "loss": 0.7536, "step": 11724 }, { "epoch": 0.6848714953271028, "grad_norm": 1.2939032316207886, "learning_rate": 4.773482029868657e-06, "loss": 0.7295, "step": 11725 }, { "epoch": 0.6849299065420561, "grad_norm": 1.1045317649841309, "learning_rate": 4.7718692407042785e-06, "loss": 0.7764, "step": 11726 }, { "epoch": 0.6849883177570093, "grad_norm": 1.4944936037063599, "learning_rate": 4.770256638658137e-06, "loss": 1.036, "step": 11727 }, { "epoch": 0.6850467289719626, "grad_norm": 0.9357036352157593, "learning_rate": 4.768644223787947e-06, "loss": 0.8553, "step": 11728 }, { "epoch": 0.6851051401869159, "grad_norm": 1.1560908555984497, "learning_rate": 4.767031996151419e-06, "loss": 0.7842, "step": 11729 }, { "epoch": 0.6851635514018691, "grad_norm": 1.364402174949646, "learning_rate": 4.765419955806257e-06, "loss": 0.8217, "step": 11730 }, { "epoch": 0.6852219626168224, "grad_norm": 1.5265460014343262, "learning_rate": 4.763808102810159e-06, "loss": 0.8123, "step": 11731 }, { "epoch": 0.6852803738317756, "grad_norm": 1.2496168613433838, "learning_rate": 4.762196437220813e-06, "loss": 0.7934, "step": 11732 }, { "epoch": 0.685338785046729, "grad_norm": 0.9094675779342651, "learning_rate": 4.760584959095896e-06, "loss": 0.6497, "step": 11733 }, { "epoch": 0.6853971962616823, "grad_norm": 1.7343196868896484, "learning_rate": 4.7589736684930895e-06, "loss": 0.836, "step": 11734 }, { "epoch": 0.6854556074766355, "grad_norm": 0.9742944836616516, "learning_rate": 4.757362565470061e-06, "loss": 0.7043, "step": 11735 }, { "epoch": 0.6855140186915888, "grad_norm": 1.1371999979019165, "learning_rate": 4.755751650084477e-06, "loss": 0.6991, "step": 11736 }, { "epoch": 0.6855724299065421, "grad_norm": 1.79135262966156, "learning_rate": 4.75414092239399e-06, "loss": 0.7465, "step": 11737 }, { "epoch": 0.6856308411214953, "grad_norm": 1.0627686977386475, "learning_rate": 4.752530382456244e-06, "loss": 0.6848, "step": 11738 }, { "epoch": 0.6856892523364486, "grad_norm": 1.6503283977508545, "learning_rate": 4.750920030328889e-06, "loss": 0.8635, "step": 11739 }, { "epoch": 0.6857476635514018, "grad_norm": 1.590039849281311, "learning_rate": 4.749309866069551e-06, "loss": 0.8751, "step": 11740 }, { "epoch": 0.6858060747663551, "grad_norm": 1.365359902381897, "learning_rate": 4.747699889735873e-06, "loss": 0.6488, "step": 11741 }, { "epoch": 0.6858644859813084, "grad_norm": 1.8695106506347656, "learning_rate": 4.74609010138547e-06, "loss": 0.6914, "step": 11742 }, { "epoch": 0.6859228971962616, "grad_norm": 1.0199273824691772, "learning_rate": 4.744480501075952e-06, "loss": 0.6684, "step": 11743 }, { "epoch": 0.685981308411215, "grad_norm": 2.2157487869262695, "learning_rate": 4.742871088864935e-06, "loss": 0.8337, "step": 11744 }, { "epoch": 0.6860397196261683, "grad_norm": 0.8087528347969055, "learning_rate": 4.741261864810017e-06, "loss": 0.6438, "step": 11745 }, { "epoch": 0.6860981308411215, "grad_norm": 1.4012020826339722, "learning_rate": 4.739652828968794e-06, "loss": 0.8426, "step": 11746 }, { "epoch": 0.6861565420560748, "grad_norm": 1.533871054649353, "learning_rate": 4.738043981398858e-06, "loss": 0.8204, "step": 11747 }, { "epoch": 0.686214953271028, "grad_norm": 1.1474463939666748, "learning_rate": 4.736435322157784e-06, "loss": 0.8656, "step": 11748 }, { "epoch": 0.6862733644859813, "grad_norm": 1.7863495349884033, "learning_rate": 4.734826851303155e-06, "loss": 0.7159, "step": 11749 }, { "epoch": 0.6863317757009346, "grad_norm": 1.3128283023834229, "learning_rate": 4.73321856889253e-06, "loss": 0.869, "step": 11750 }, { "epoch": 0.6863901869158878, "grad_norm": 1.0572941303253174, "learning_rate": 4.731610474983477e-06, "loss": 0.8619, "step": 11751 }, { "epoch": 0.6864485981308411, "grad_norm": 1.9044411182403564, "learning_rate": 4.730002569633552e-06, "loss": 0.619, "step": 11752 }, { "epoch": 0.6865070093457943, "grad_norm": 1.4833036661148071, "learning_rate": 4.728394852900297e-06, "loss": 0.7414, "step": 11753 }, { "epoch": 0.6865654205607477, "grad_norm": 1.1169915199279785, "learning_rate": 4.726787324841259e-06, "loss": 0.6522, "step": 11754 }, { "epoch": 0.686623831775701, "grad_norm": 1.285906434059143, "learning_rate": 4.72517998551397e-06, "loss": 0.8407, "step": 11755 }, { "epoch": 0.6866822429906542, "grad_norm": 1.6646851301193237, "learning_rate": 4.72357283497595e-06, "loss": 0.8482, "step": 11756 }, { "epoch": 0.6867406542056075, "grad_norm": 0.9461501836776733, "learning_rate": 4.721965873284736e-06, "loss": 0.6548, "step": 11757 }, { "epoch": 0.6867990654205608, "grad_norm": 1.1953827142715454, "learning_rate": 4.72035910049783e-06, "loss": 0.7469, "step": 11758 }, { "epoch": 0.686857476635514, "grad_norm": 1.2247694730758667, "learning_rate": 4.718752516672746e-06, "loss": 0.8028, "step": 11759 }, { "epoch": 0.6869158878504673, "grad_norm": 1.2281006574630737, "learning_rate": 4.717146121866982e-06, "loss": 0.7857, "step": 11760 }, { "epoch": 0.6869742990654205, "grad_norm": 1.2135486602783203, "learning_rate": 4.715539916138029e-06, "loss": 0.7223, "step": 11761 }, { "epoch": 0.6870327102803738, "grad_norm": 1.3742849826812744, "learning_rate": 4.713933899543377e-06, "loss": 0.7411, "step": 11762 }, { "epoch": 0.6870911214953271, "grad_norm": 1.0934288501739502, "learning_rate": 4.712328072140505e-06, "loss": 0.6866, "step": 11763 }, { "epoch": 0.6871495327102803, "grad_norm": 1.3963756561279297, "learning_rate": 4.7107224339868925e-06, "loss": 0.9579, "step": 11764 }, { "epoch": 0.6872079439252337, "grad_norm": 1.3367449045181274, "learning_rate": 4.709116985140003e-06, "loss": 0.8061, "step": 11765 }, { "epoch": 0.687266355140187, "grad_norm": 0.9147659540176392, "learning_rate": 4.707511725657291e-06, "loss": 0.7565, "step": 11766 }, { "epoch": 0.6873247663551402, "grad_norm": 1.0532327890396118, "learning_rate": 4.705906655596214e-06, "loss": 0.8889, "step": 11767 }, { "epoch": 0.6873831775700935, "grad_norm": 1.3733655214309692, "learning_rate": 4.7043017750142185e-06, "loss": 0.7664, "step": 11768 }, { "epoch": 0.6874415887850467, "grad_norm": 1.512679934501648, "learning_rate": 4.702697083968748e-06, "loss": 0.8482, "step": 11769 }, { "epoch": 0.6875, "grad_norm": 1.0194324254989624, "learning_rate": 4.701092582517232e-06, "loss": 0.7618, "step": 11770 }, { "epoch": 0.6875584112149533, "grad_norm": 1.3039166927337646, "learning_rate": 4.699488270717094e-06, "loss": 0.8298, "step": 11771 }, { "epoch": 0.6876168224299065, "grad_norm": 1.0944745540618896, "learning_rate": 4.697884148625758e-06, "loss": 0.715, "step": 11772 }, { "epoch": 0.6876752336448598, "grad_norm": 0.9292259812355042, "learning_rate": 4.6962802163006286e-06, "loss": 0.7809, "step": 11773 }, { "epoch": 0.687733644859813, "grad_norm": 1.1080602407455444, "learning_rate": 4.694676473799124e-06, "loss": 0.7166, "step": 11774 }, { "epoch": 0.6877920560747663, "grad_norm": 1.317723035812378, "learning_rate": 4.693072921178637e-06, "loss": 0.7181, "step": 11775 }, { "epoch": 0.6878504672897197, "grad_norm": 1.317657709121704, "learning_rate": 4.691469558496555e-06, "loss": 0.7796, "step": 11776 }, { "epoch": 0.6879088785046729, "grad_norm": 1.5858688354492188, "learning_rate": 4.6898663858102735e-06, "loss": 0.7356, "step": 11777 }, { "epoch": 0.6879672897196262, "grad_norm": 1.3244423866271973, "learning_rate": 4.68826340317716e-06, "loss": 0.8103, "step": 11778 }, { "epoch": 0.6880257009345795, "grad_norm": 1.2393769025802612, "learning_rate": 4.686660610654593e-06, "loss": 0.8241, "step": 11779 }, { "epoch": 0.6880841121495327, "grad_norm": 1.065789818763733, "learning_rate": 4.68505800829994e-06, "loss": 0.7007, "step": 11780 }, { "epoch": 0.688142523364486, "grad_norm": 1.1397621631622314, "learning_rate": 4.6834555961705505e-06, "loss": 0.8501, "step": 11781 }, { "epoch": 0.6882009345794392, "grad_norm": 1.2294361591339111, "learning_rate": 4.681853374323786e-06, "loss": 0.6983, "step": 11782 }, { "epoch": 0.6882593457943925, "grad_norm": 1.2744492292404175, "learning_rate": 4.680251342816982e-06, "loss": 0.9017, "step": 11783 }, { "epoch": 0.6883177570093458, "grad_norm": 0.9980562329292297, "learning_rate": 4.6786495017074795e-06, "loss": 0.8325, "step": 11784 }, { "epoch": 0.688376168224299, "grad_norm": 1.4571399688720703, "learning_rate": 4.6770478510526155e-06, "loss": 0.8129, "step": 11785 }, { "epoch": 0.6884345794392523, "grad_norm": 1.1626744270324707, "learning_rate": 4.675446390909703e-06, "loss": 0.7644, "step": 11786 }, { "epoch": 0.6884929906542057, "grad_norm": 1.0320154428482056, "learning_rate": 4.67384512133607e-06, "loss": 0.7515, "step": 11787 }, { "epoch": 0.6885514018691589, "grad_norm": 1.2479208707809448, "learning_rate": 4.67224404238902e-06, "loss": 0.8043, "step": 11788 }, { "epoch": 0.6886098130841122, "grad_norm": 3.680497169494629, "learning_rate": 4.670643154125856e-06, "loss": 0.6932, "step": 11789 }, { "epoch": 0.6886682242990654, "grad_norm": 1.3187650442123413, "learning_rate": 4.669042456603883e-06, "loss": 0.6846, "step": 11790 }, { "epoch": 0.6887266355140187, "grad_norm": 1.3055576086044312, "learning_rate": 4.667441949880381e-06, "loss": 0.7553, "step": 11791 }, { "epoch": 0.688785046728972, "grad_norm": 1.3750423192977905, "learning_rate": 4.665841634012642e-06, "loss": 0.7355, "step": 11792 }, { "epoch": 0.6888434579439252, "grad_norm": 1.2901318073272705, "learning_rate": 4.664241509057934e-06, "loss": 0.7689, "step": 11793 }, { "epoch": 0.6889018691588785, "grad_norm": 1.2541719675064087, "learning_rate": 4.662641575073536e-06, "loss": 0.9581, "step": 11794 }, { "epoch": 0.6889602803738317, "grad_norm": 1.308091163635254, "learning_rate": 4.661041832116699e-06, "loss": 0.7511, "step": 11795 }, { "epoch": 0.689018691588785, "grad_norm": 1.4250056743621826, "learning_rate": 4.659442280244687e-06, "loss": 0.766, "step": 11796 }, { "epoch": 0.6890771028037384, "grad_norm": 1.3535441160202026, "learning_rate": 4.657842919514751e-06, "loss": 0.7092, "step": 11797 }, { "epoch": 0.6891355140186916, "grad_norm": 1.0580378770828247, "learning_rate": 4.656243749984126e-06, "loss": 0.8698, "step": 11798 }, { "epoch": 0.6891939252336449, "grad_norm": 1.5095471143722534, "learning_rate": 4.654644771710054e-06, "loss": 0.9547, "step": 11799 }, { "epoch": 0.6892523364485982, "grad_norm": 1.2591664791107178, "learning_rate": 4.653045984749756e-06, "loss": 0.8139, "step": 11800 }, { "epoch": 0.6893107476635514, "grad_norm": 1.1847437620162964, "learning_rate": 4.6514473891604584e-06, "loss": 0.662, "step": 11801 }, { "epoch": 0.6893691588785047, "grad_norm": 1.654544711112976, "learning_rate": 4.64984898499938e-06, "loss": 0.7667, "step": 11802 }, { "epoch": 0.6894275700934579, "grad_norm": 1.6268553733825684, "learning_rate": 4.648250772323719e-06, "loss": 0.7786, "step": 11803 }, { "epoch": 0.6894859813084112, "grad_norm": 1.1621840000152588, "learning_rate": 4.646652751190687e-06, "loss": 0.7761, "step": 11804 }, { "epoch": 0.6895443925233645, "grad_norm": 1.1868982315063477, "learning_rate": 4.645054921657471e-06, "loss": 0.7163, "step": 11805 }, { "epoch": 0.6896028037383177, "grad_norm": 1.7650959491729736, "learning_rate": 4.643457283781256e-06, "loss": 0.8291, "step": 11806 }, { "epoch": 0.689661214953271, "grad_norm": 0.8828972578048706, "learning_rate": 4.641859837619231e-06, "loss": 0.7637, "step": 11807 }, { "epoch": 0.6897196261682244, "grad_norm": 1.6601758003234863, "learning_rate": 4.6402625832285665e-06, "loss": 0.8265, "step": 11808 }, { "epoch": 0.6897780373831776, "grad_norm": 1.603116750717163, "learning_rate": 4.638665520666426e-06, "loss": 0.8214, "step": 11809 }, { "epoch": 0.6898364485981309, "grad_norm": 1.1566827297210693, "learning_rate": 4.637068649989973e-06, "loss": 0.7205, "step": 11810 }, { "epoch": 0.6898948598130841, "grad_norm": 2.670891523361206, "learning_rate": 4.635471971256357e-06, "loss": 0.8645, "step": 11811 }, { "epoch": 0.6899532710280374, "grad_norm": 1.132684588432312, "learning_rate": 4.633875484522726e-06, "loss": 0.7315, "step": 11812 }, { "epoch": 0.6900116822429907, "grad_norm": 1.2088959217071533, "learning_rate": 4.632279189846223e-06, "loss": 0.8805, "step": 11813 }, { "epoch": 0.6900700934579439, "grad_norm": 1.1600092649459839, "learning_rate": 4.6306830872839734e-06, "loss": 1.0184, "step": 11814 }, { "epoch": 0.6901285046728972, "grad_norm": 1.4619437456130981, "learning_rate": 4.629087176893111e-06, "loss": 0.7746, "step": 11815 }, { "epoch": 0.6901869158878504, "grad_norm": 1.1212090253829956, "learning_rate": 4.627491458730747e-06, "loss": 0.7644, "step": 11816 }, { "epoch": 0.6902453271028037, "grad_norm": 0.974322497844696, "learning_rate": 4.625895932853994e-06, "loss": 0.7303, "step": 11817 }, { "epoch": 0.690303738317757, "grad_norm": 1.0726656913757324, "learning_rate": 4.624300599319964e-06, "loss": 0.7055, "step": 11818 }, { "epoch": 0.6903621495327102, "grad_norm": 1.291707158088684, "learning_rate": 4.622705458185747e-06, "loss": 0.7803, "step": 11819 }, { "epoch": 0.6904205607476636, "grad_norm": 0.8651607036590576, "learning_rate": 4.62111050950844e-06, "loss": 0.6276, "step": 11820 }, { "epoch": 0.6904789719626169, "grad_norm": 1.2847108840942383, "learning_rate": 4.6195157533451205e-06, "loss": 0.8273, "step": 11821 }, { "epoch": 0.6905373831775701, "grad_norm": 1.3134421110153198, "learning_rate": 4.617921189752871e-06, "loss": 0.8524, "step": 11822 }, { "epoch": 0.6905957943925234, "grad_norm": 11.655962944030762, "learning_rate": 4.6163268187887645e-06, "loss": 0.8168, "step": 11823 }, { "epoch": 0.6906542056074766, "grad_norm": 1.0471400022506714, "learning_rate": 4.614732640509857e-06, "loss": 0.7569, "step": 11824 }, { "epoch": 0.6907126168224299, "grad_norm": 1.420965552330017, "learning_rate": 4.613138654973213e-06, "loss": 0.9723, "step": 11825 }, { "epoch": 0.6907710280373832, "grad_norm": 1.5169355869293213, "learning_rate": 4.611544862235875e-06, "loss": 0.7484, "step": 11826 }, { "epoch": 0.6908294392523364, "grad_norm": 1.315148949623108, "learning_rate": 4.609951262354893e-06, "loss": 0.7817, "step": 11827 }, { "epoch": 0.6908878504672897, "grad_norm": 1.2027475833892822, "learning_rate": 4.608357855387295e-06, "loss": 0.7573, "step": 11828 }, { "epoch": 0.690946261682243, "grad_norm": 1.8603663444519043, "learning_rate": 4.606764641390114e-06, "loss": 0.8043, "step": 11829 }, { "epoch": 0.6910046728971962, "grad_norm": 1.4501358270645142, "learning_rate": 4.605171620420378e-06, "loss": 0.7647, "step": 11830 }, { "epoch": 0.6910630841121496, "grad_norm": 1.4213885068893433, "learning_rate": 4.6035787925350915e-06, "loss": 0.8174, "step": 11831 }, { "epoch": 0.6911214953271028, "grad_norm": 1.4038808345794678, "learning_rate": 4.6019861577912726e-06, "loss": 0.7381, "step": 11832 }, { "epoch": 0.6911799065420561, "grad_norm": 2.3541207313537598, "learning_rate": 4.600393716245915e-06, "loss": 0.683, "step": 11833 }, { "epoch": 0.6912383177570094, "grad_norm": 1.4728940725326538, "learning_rate": 4.598801467956017e-06, "loss": 0.923, "step": 11834 }, { "epoch": 0.6912967289719626, "grad_norm": 1.7451318502426147, "learning_rate": 4.597209412978568e-06, "loss": 0.6985, "step": 11835 }, { "epoch": 0.6913551401869159, "grad_norm": 1.2766623497009277, "learning_rate": 4.595617551370545e-06, "loss": 0.6617, "step": 11836 }, { "epoch": 0.6914135514018691, "grad_norm": 1.761723518371582, "learning_rate": 4.594025883188925e-06, "loss": 0.6047, "step": 11837 }, { "epoch": 0.6914719626168224, "grad_norm": 1.467503309249878, "learning_rate": 4.592434408490673e-06, "loss": 0.7552, "step": 11838 }, { "epoch": 0.6915303738317757, "grad_norm": 1.8251999616622925, "learning_rate": 4.590843127332744e-06, "loss": 0.7871, "step": 11839 }, { "epoch": 0.6915887850467289, "grad_norm": 1.837945818901062, "learning_rate": 4.589252039772101e-06, "loss": 0.9985, "step": 11840 }, { "epoch": 0.6916471962616823, "grad_norm": 1.121955156326294, "learning_rate": 4.587661145865683e-06, "loss": 0.6952, "step": 11841 }, { "epoch": 0.6917056074766356, "grad_norm": 1.662866234779358, "learning_rate": 4.5860704456704345e-06, "loss": 0.7352, "step": 11842 }, { "epoch": 0.6917640186915888, "grad_norm": 1.413744568824768, "learning_rate": 4.584479939243284e-06, "loss": 0.7203, "step": 11843 }, { "epoch": 0.6918224299065421, "grad_norm": 1.343500018119812, "learning_rate": 4.582889626641154e-06, "loss": 0.6687, "step": 11844 }, { "epoch": 0.6918808411214953, "grad_norm": 1.196693778038025, "learning_rate": 4.581299507920965e-06, "loss": 0.7663, "step": 11845 }, { "epoch": 0.6919392523364486, "grad_norm": 1.4757592678070068, "learning_rate": 4.579709583139631e-06, "loss": 0.7101, "step": 11846 }, { "epoch": 0.6919976635514019, "grad_norm": 2.1291661262512207, "learning_rate": 4.578119852354058e-06, "loss": 0.852, "step": 11847 }, { "epoch": 0.6920560747663551, "grad_norm": 1.286275029182434, "learning_rate": 4.57653031562114e-06, "loss": 0.7499, "step": 11848 }, { "epoch": 0.6921144859813084, "grad_norm": 1.1888370513916016, "learning_rate": 4.574940972997766e-06, "loss": 0.7676, "step": 11849 }, { "epoch": 0.6921728971962616, "grad_norm": 1.5435538291931152, "learning_rate": 4.57335182454082e-06, "loss": 0.7184, "step": 11850 }, { "epoch": 0.6922313084112149, "grad_norm": 1.7893335819244385, "learning_rate": 4.57176287030718e-06, "loss": 0.8161, "step": 11851 }, { "epoch": 0.6922897196261683, "grad_norm": 1.0500386953353882, "learning_rate": 4.570174110353721e-06, "loss": 0.7514, "step": 11852 }, { "epoch": 0.6923481308411215, "grad_norm": 2.0497632026672363, "learning_rate": 4.5685855447373005e-06, "loss": 0.7763, "step": 11853 }, { "epoch": 0.6924065420560748, "grad_norm": 2.1195228099823, "learning_rate": 4.566997173514771e-06, "loss": 0.8653, "step": 11854 }, { "epoch": 0.6924649532710281, "grad_norm": 1.4889671802520752, "learning_rate": 4.565408996742984e-06, "loss": 0.7059, "step": 11855 }, { "epoch": 0.6925233644859813, "grad_norm": 1.8558130264282227, "learning_rate": 4.563821014478783e-06, "loss": 0.911, "step": 11856 }, { "epoch": 0.6925817757009346, "grad_norm": 1.0899444818496704, "learning_rate": 4.562233226779006e-06, "loss": 0.7558, "step": 11857 }, { "epoch": 0.6926401869158878, "grad_norm": 1.558180570602417, "learning_rate": 4.560645633700477e-06, "loss": 0.7825, "step": 11858 }, { "epoch": 0.6926985981308411, "grad_norm": 0.9153243899345398, "learning_rate": 4.5590582353000135e-06, "loss": 0.6853, "step": 11859 }, { "epoch": 0.6927570093457944, "grad_norm": 1.4808738231658936, "learning_rate": 4.5574710316344375e-06, "loss": 0.6047, "step": 11860 }, { "epoch": 0.6928154205607476, "grad_norm": 2.8953089714050293, "learning_rate": 4.555884022760547e-06, "loss": 0.6483, "step": 11861 }, { "epoch": 0.6928738317757009, "grad_norm": 4.007261753082275, "learning_rate": 4.554297208735148e-06, "loss": 0.7134, "step": 11862 }, { "epoch": 0.6929322429906543, "grad_norm": 1.8399049043655396, "learning_rate": 4.552710589615035e-06, "loss": 0.7626, "step": 11863 }, { "epoch": 0.6929906542056075, "grad_norm": 2.1565730571746826, "learning_rate": 4.5511241654569885e-06, "loss": 0.7043, "step": 11864 }, { "epoch": 0.6930490654205608, "grad_norm": 2.2839174270629883, "learning_rate": 4.549537936317795e-06, "loss": 0.904, "step": 11865 }, { "epoch": 0.693107476635514, "grad_norm": 1.6841676235198975, "learning_rate": 4.547951902254219e-06, "loss": 0.7472, "step": 11866 }, { "epoch": 0.6931658878504673, "grad_norm": 0.9342228174209595, "learning_rate": 4.5463660633230275e-06, "loss": 0.6073, "step": 11867 }, { "epoch": 0.6932242990654206, "grad_norm": 1.3558934926986694, "learning_rate": 4.544780419580986e-06, "loss": 0.7791, "step": 11868 }, { "epoch": 0.6932827102803738, "grad_norm": 1.0505614280700684, "learning_rate": 4.543194971084836e-06, "loss": 0.7353, "step": 11869 }, { "epoch": 0.6933411214953271, "grad_norm": 1.2004746198654175, "learning_rate": 4.541609717891329e-06, "loss": 0.8431, "step": 11870 }, { "epoch": 0.6933995327102803, "grad_norm": 0.9414281845092773, "learning_rate": 4.5400246600572e-06, "loss": 0.7002, "step": 11871 }, { "epoch": 0.6934579439252336, "grad_norm": 1.965411901473999, "learning_rate": 4.53843979763917e-06, "loss": 0.8316, "step": 11872 }, { "epoch": 0.693516355140187, "grad_norm": 1.0574016571044922, "learning_rate": 4.536855130693979e-06, "loss": 0.7105, "step": 11873 }, { "epoch": 0.6935747663551401, "grad_norm": 1.651519536972046, "learning_rate": 4.535270659278332e-06, "loss": 0.6776, "step": 11874 }, { "epoch": 0.6936331775700935, "grad_norm": 1.241033911705017, "learning_rate": 4.533686383448943e-06, "loss": 0.7013, "step": 11875 }, { "epoch": 0.6936915887850468, "grad_norm": 1.1249127388000488, "learning_rate": 4.532102303262513e-06, "loss": 0.7453, "step": 11876 }, { "epoch": 0.69375, "grad_norm": 1.085448145866394, "learning_rate": 4.530518418775734e-06, "loss": 0.8242, "step": 11877 }, { "epoch": 0.6938084112149533, "grad_norm": 1.293468713760376, "learning_rate": 4.5289347300452955e-06, "loss": 0.6985, "step": 11878 }, { "epoch": 0.6938668224299065, "grad_norm": 1.2620930671691895, "learning_rate": 4.527351237127882e-06, "loss": 0.8457, "step": 11879 }, { "epoch": 0.6939252336448598, "grad_norm": 1.4370468854904175, "learning_rate": 4.525767940080169e-06, "loss": 0.8539, "step": 11880 }, { "epoch": 0.6939836448598131, "grad_norm": 0.9393895268440247, "learning_rate": 4.52418483895882e-06, "loss": 0.6859, "step": 11881 }, { "epoch": 0.6940420560747663, "grad_norm": 1.9689830541610718, "learning_rate": 4.522601933820494e-06, "loss": 0.7683, "step": 11882 }, { "epoch": 0.6941004672897196, "grad_norm": 1.342124104499817, "learning_rate": 4.5210192247218456e-06, "loss": 0.769, "step": 11883 }, { "epoch": 0.694158878504673, "grad_norm": 1.216416597366333, "learning_rate": 4.519436711719522e-06, "loss": 0.8156, "step": 11884 }, { "epoch": 0.6942172897196262, "grad_norm": 1.0804270505905151, "learning_rate": 4.5178543948701645e-06, "loss": 0.782, "step": 11885 }, { "epoch": 0.6942757009345795, "grad_norm": 1.1520417928695679, "learning_rate": 4.516272274230403e-06, "loss": 0.8353, "step": 11886 }, { "epoch": 0.6943341121495327, "grad_norm": 0.8801128268241882, "learning_rate": 4.514690349856859e-06, "loss": 0.7429, "step": 11887 }, { "epoch": 0.694392523364486, "grad_norm": 1.065548062324524, "learning_rate": 4.513108621806155e-06, "loss": 0.7393, "step": 11888 }, { "epoch": 0.6944509345794393, "grad_norm": 1.3385146856307983, "learning_rate": 4.511527090134901e-06, "loss": 0.8404, "step": 11889 }, { "epoch": 0.6945093457943925, "grad_norm": 1.2200417518615723, "learning_rate": 4.5099457548997035e-06, "loss": 0.8001, "step": 11890 }, { "epoch": 0.6945677570093458, "grad_norm": 1.2933578491210938, "learning_rate": 4.508364616157158e-06, "loss": 0.768, "step": 11891 }, { "epoch": 0.694626168224299, "grad_norm": 1.0399227142333984, "learning_rate": 4.506783673963851e-06, "loss": 0.7201, "step": 11892 }, { "epoch": 0.6946845794392523, "grad_norm": 1.062175989151001, "learning_rate": 4.50520292837637e-06, "loss": 0.8045, "step": 11893 }, { "epoch": 0.6947429906542056, "grad_norm": 1.1732147932052612, "learning_rate": 4.503622379451286e-06, "loss": 0.5866, "step": 11894 }, { "epoch": 0.6948014018691588, "grad_norm": 1.2142417430877686, "learning_rate": 4.5020420272451715e-06, "loss": 0.6418, "step": 11895 }, { "epoch": 0.6948598130841122, "grad_norm": 1.0632472038269043, "learning_rate": 4.5004618718145905e-06, "loss": 0.7237, "step": 11896 }, { "epoch": 0.6949182242990655, "grad_norm": 1.356415867805481, "learning_rate": 4.4988819132160935e-06, "loss": 0.7915, "step": 11897 }, { "epoch": 0.6949766355140187, "grad_norm": 1.514382004737854, "learning_rate": 4.497302151506232e-06, "loss": 0.799, "step": 11898 }, { "epoch": 0.695035046728972, "grad_norm": 1.7696197032928467, "learning_rate": 4.495722586741541e-06, "loss": 0.8357, "step": 11899 }, { "epoch": 0.6950934579439252, "grad_norm": 1.3742642402648926, "learning_rate": 4.4941432189785574e-06, "loss": 0.874, "step": 11900 }, { "epoch": 0.6951518691588785, "grad_norm": 0.9542502164840698, "learning_rate": 4.492564048273812e-06, "loss": 0.5893, "step": 11901 }, { "epoch": 0.6952102803738318, "grad_norm": 0.8538463115692139, "learning_rate": 4.490985074683818e-06, "loss": 0.6501, "step": 11902 }, { "epoch": 0.695268691588785, "grad_norm": 0.960990846157074, "learning_rate": 4.489406298265093e-06, "loss": 0.5787, "step": 11903 }, { "epoch": 0.6953271028037383, "grad_norm": 1.0176185369491577, "learning_rate": 4.487827719074137e-06, "loss": 0.7291, "step": 11904 }, { "epoch": 0.6953855140186916, "grad_norm": 1.1159695386886597, "learning_rate": 4.48624933716745e-06, "loss": 0.7503, "step": 11905 }, { "epoch": 0.6954439252336448, "grad_norm": 0.9017250537872314, "learning_rate": 4.48467115260153e-06, "loss": 0.6565, "step": 11906 }, { "epoch": 0.6955023364485982, "grad_norm": 1.0227041244506836, "learning_rate": 4.48309316543285e-06, "loss": 0.8787, "step": 11907 }, { "epoch": 0.6955607476635514, "grad_norm": 1.1803988218307495, "learning_rate": 4.481515375717898e-06, "loss": 0.8578, "step": 11908 }, { "epoch": 0.6956191588785047, "grad_norm": 1.0669236183166504, "learning_rate": 4.4799377835131356e-06, "loss": 0.8937, "step": 11909 }, { "epoch": 0.695677570093458, "grad_norm": 1.3408219814300537, "learning_rate": 4.4783603888750325e-06, "loss": 0.8642, "step": 11910 }, { "epoch": 0.6957359813084112, "grad_norm": 1.0369338989257812, "learning_rate": 4.476783191860039e-06, "loss": 0.7252, "step": 11911 }, { "epoch": 0.6957943925233645, "grad_norm": 1.2462730407714844, "learning_rate": 4.475206192524606e-06, "loss": 0.8428, "step": 11912 }, { "epoch": 0.6958528037383177, "grad_norm": 1.0462254285812378, "learning_rate": 4.473629390925179e-06, "loss": 0.7085, "step": 11913 }, { "epoch": 0.695911214953271, "grad_norm": 1.241226077079773, "learning_rate": 4.472052787118187e-06, "loss": 0.7945, "step": 11914 }, { "epoch": 0.6959696261682243, "grad_norm": 1.4170812368392944, "learning_rate": 4.470476381160065e-06, "loss": 0.8307, "step": 11915 }, { "epoch": 0.6960280373831775, "grad_norm": 0.9364302754402161, "learning_rate": 4.4689001731072236e-06, "loss": 0.6194, "step": 11916 }, { "epoch": 0.6960864485981308, "grad_norm": 1.0477794408798218, "learning_rate": 4.467324163016083e-06, "loss": 0.7016, "step": 11917 }, { "epoch": 0.6961448598130842, "grad_norm": 1.0771480798721313, "learning_rate": 4.465748350943051e-06, "loss": 0.6663, "step": 11918 }, { "epoch": 0.6962032710280374, "grad_norm": 0.9498634934425354, "learning_rate": 4.464172736944525e-06, "loss": 0.6566, "step": 11919 }, { "epoch": 0.6962616822429907, "grad_norm": 1.2273924350738525, "learning_rate": 4.462597321076892e-06, "loss": 0.7761, "step": 11920 }, { "epoch": 0.6963200934579439, "grad_norm": 1.3212196826934814, "learning_rate": 4.461022103396543e-06, "loss": 0.7122, "step": 11921 }, { "epoch": 0.6963785046728972, "grad_norm": 1.2397332191467285, "learning_rate": 4.459447083959855e-06, "loss": 0.7242, "step": 11922 }, { "epoch": 0.6964369158878505, "grad_norm": 1.1123491525650024, "learning_rate": 4.457872262823202e-06, "loss": 0.6885, "step": 11923 }, { "epoch": 0.6964953271028037, "grad_norm": 1.0390381813049316, "learning_rate": 4.4562976400429445e-06, "loss": 0.7542, "step": 11924 }, { "epoch": 0.696553738317757, "grad_norm": 1.3227524757385254, "learning_rate": 4.454723215675436e-06, "loss": 0.7613, "step": 11925 }, { "epoch": 0.6966121495327103, "grad_norm": 1.0101590156555176, "learning_rate": 4.4531489897770345e-06, "loss": 0.8515, "step": 11926 }, { "epoch": 0.6966705607476635, "grad_norm": 1.0991817712783813, "learning_rate": 4.451574962404073e-06, "loss": 0.6589, "step": 11927 }, { "epoch": 0.6967289719626168, "grad_norm": 1.2096797227859497, "learning_rate": 4.450001133612891e-06, "loss": 0.8075, "step": 11928 }, { "epoch": 0.69678738317757, "grad_norm": 1.3997348546981812, "learning_rate": 4.448427503459822e-06, "loss": 0.7803, "step": 11929 }, { "epoch": 0.6968457943925234, "grad_norm": 1.1704020500183105, "learning_rate": 4.44685407200118e-06, "loss": 0.7964, "step": 11930 }, { "epoch": 0.6969042056074767, "grad_norm": 0.936135470867157, "learning_rate": 4.445280839293284e-06, "loss": 0.6598, "step": 11931 }, { "epoch": 0.6969626168224299, "grad_norm": 1.086621642112732, "learning_rate": 4.443707805392438e-06, "loss": 0.7662, "step": 11932 }, { "epoch": 0.6970210280373832, "grad_norm": 0.9992280006408691, "learning_rate": 4.442134970354941e-06, "loss": 0.6854, "step": 11933 }, { "epoch": 0.6970794392523364, "grad_norm": 2.351344108581543, "learning_rate": 4.4405623342370916e-06, "loss": 0.8278, "step": 11934 }, { "epoch": 0.6971378504672897, "grad_norm": 0.9297662973403931, "learning_rate": 4.438989897095169e-06, "loss": 0.6982, "step": 11935 }, { "epoch": 0.697196261682243, "grad_norm": 1.0799487829208374, "learning_rate": 4.437417658985457e-06, "loss": 0.666, "step": 11936 }, { "epoch": 0.6972546728971962, "grad_norm": 1.0422414541244507, "learning_rate": 4.435845619964221e-06, "loss": 0.6583, "step": 11937 }, { "epoch": 0.6973130841121495, "grad_norm": 0.9996538758277893, "learning_rate": 4.4342737800877274e-06, "loss": 0.6897, "step": 11938 }, { "epoch": 0.6973714953271029, "grad_norm": 0.9606376886367798, "learning_rate": 4.43270213941224e-06, "loss": 0.8955, "step": 11939 }, { "epoch": 0.697429906542056, "grad_norm": 1.0040903091430664, "learning_rate": 4.4311306979940005e-06, "loss": 0.7725, "step": 11940 }, { "epoch": 0.6974883177570094, "grad_norm": 1.0319911241531372, "learning_rate": 4.429559455889258e-06, "loss": 0.7434, "step": 11941 }, { "epoch": 0.6975467289719626, "grad_norm": 1.6341110467910767, "learning_rate": 4.427988413154241e-06, "loss": 0.8987, "step": 11942 }, { "epoch": 0.6976051401869159, "grad_norm": 0.9785192012786865, "learning_rate": 4.4264175698451875e-06, "loss": 0.7764, "step": 11943 }, { "epoch": 0.6976635514018692, "grad_norm": 0.9652164578437805, "learning_rate": 4.424846926018309e-06, "loss": 0.9299, "step": 11944 }, { "epoch": 0.6977219626168224, "grad_norm": 1.274949312210083, "learning_rate": 4.423276481729825e-06, "loss": 0.6792, "step": 11945 }, { "epoch": 0.6977803738317757, "grad_norm": 1.1279487609863281, "learning_rate": 4.4217062370359456e-06, "loss": 0.7489, "step": 11946 }, { "epoch": 0.697838785046729, "grad_norm": 1.0770759582519531, "learning_rate": 4.420136191992864e-06, "loss": 0.7786, "step": 11947 }, { "epoch": 0.6978971962616822, "grad_norm": 1.736970067024231, "learning_rate": 4.418566346656782e-06, "loss": 0.827, "step": 11948 }, { "epoch": 0.6979556074766355, "grad_norm": 1.1564271450042725, "learning_rate": 4.416996701083876e-06, "loss": 0.8215, "step": 11949 }, { "epoch": 0.6980140186915887, "grad_norm": 1.044113039970398, "learning_rate": 4.415427255330329e-06, "loss": 0.6446, "step": 11950 }, { "epoch": 0.6980724299065421, "grad_norm": 1.1067888736724854, "learning_rate": 4.413858009452315e-06, "loss": 0.6993, "step": 11951 }, { "epoch": 0.6981308411214954, "grad_norm": 1.6754696369171143, "learning_rate": 4.412288963505994e-06, "loss": 0.7194, "step": 11952 }, { "epoch": 0.6981892523364486, "grad_norm": 1.0159763097763062, "learning_rate": 4.410720117547528e-06, "loss": 0.7034, "step": 11953 }, { "epoch": 0.6982476635514019, "grad_norm": 1.3738372325897217, "learning_rate": 4.40915147163306e-06, "loss": 0.6937, "step": 11954 }, { "epoch": 0.6983060747663551, "grad_norm": 1.793614387512207, "learning_rate": 4.407583025818737e-06, "loss": 0.8389, "step": 11955 }, { "epoch": 0.6983644859813084, "grad_norm": 3.0137360095977783, "learning_rate": 4.406014780160698e-06, "loss": 0.7317, "step": 11956 }, { "epoch": 0.6984228971962617, "grad_norm": 1.32472562789917, "learning_rate": 4.404446734715064e-06, "loss": 0.7646, "step": 11957 }, { "epoch": 0.6984813084112149, "grad_norm": 2.062959671020508, "learning_rate": 4.402878889537965e-06, "loss": 0.9118, "step": 11958 }, { "epoch": 0.6985397196261682, "grad_norm": 1.0409444570541382, "learning_rate": 4.401311244685511e-06, "loss": 0.7207, "step": 11959 }, { "epoch": 0.6985981308411215, "grad_norm": 1.0560801029205322, "learning_rate": 4.399743800213805e-06, "loss": 0.7059, "step": 11960 }, { "epoch": 0.6986565420560747, "grad_norm": 2.157874584197998, "learning_rate": 4.39817655617895e-06, "loss": 0.7495, "step": 11961 }, { "epoch": 0.6987149532710281, "grad_norm": 1.6069778203964233, "learning_rate": 4.396609512637039e-06, "loss": 0.8313, "step": 11962 }, { "epoch": 0.6987733644859813, "grad_norm": 1.9265145063400269, "learning_rate": 4.3950426696441626e-06, "loss": 0.7341, "step": 11963 }, { "epoch": 0.6988317757009346, "grad_norm": 1.8867990970611572, "learning_rate": 4.393476027256393e-06, "loss": 0.7516, "step": 11964 }, { "epoch": 0.6988901869158879, "grad_norm": 1.3171863555908203, "learning_rate": 4.391909585529801e-06, "loss": 0.7527, "step": 11965 }, { "epoch": 0.6989485981308411, "grad_norm": 1.839160680770874, "learning_rate": 4.390343344520452e-06, "loss": 0.8191, "step": 11966 }, { "epoch": 0.6990070093457944, "grad_norm": 1.1197538375854492, "learning_rate": 4.3887773042844015e-06, "loss": 0.6787, "step": 11967 }, { "epoch": 0.6990654205607477, "grad_norm": 1.3196678161621094, "learning_rate": 4.387211464877705e-06, "loss": 0.9522, "step": 11968 }, { "epoch": 0.6991238317757009, "grad_norm": 1.3227146863937378, "learning_rate": 4.385645826356402e-06, "loss": 0.7857, "step": 11969 }, { "epoch": 0.6991822429906542, "grad_norm": 1.2658865451812744, "learning_rate": 4.384080388776521e-06, "loss": 0.6141, "step": 11970 }, { "epoch": 0.6992406542056074, "grad_norm": 1.261505126953125, "learning_rate": 4.382515152194097e-06, "loss": 0.8113, "step": 11971 }, { "epoch": 0.6992990654205608, "grad_norm": 1.292661190032959, "learning_rate": 4.380950116665148e-06, "loss": 0.6502, "step": 11972 }, { "epoch": 0.6993574766355141, "grad_norm": 2.0890955924987793, "learning_rate": 4.379385282245693e-06, "loss": 0.8624, "step": 11973 }, { "epoch": 0.6994158878504673, "grad_norm": 0.9654529094696045, "learning_rate": 4.377820648991734e-06, "loss": 0.6201, "step": 11974 }, { "epoch": 0.6994742990654206, "grad_norm": 0.9823974370956421, "learning_rate": 4.376256216959267e-06, "loss": 0.7395, "step": 11975 }, { "epoch": 0.6995327102803738, "grad_norm": 1.2811170816421509, "learning_rate": 4.374691986204293e-06, "loss": 0.9045, "step": 11976 }, { "epoch": 0.6995911214953271, "grad_norm": 1.3409343957901, "learning_rate": 4.373127956782785e-06, "loss": 0.6765, "step": 11977 }, { "epoch": 0.6996495327102804, "grad_norm": 0.9833881258964539, "learning_rate": 4.37156412875073e-06, "loss": 0.7886, "step": 11978 }, { "epoch": 0.6997079439252336, "grad_norm": 1.1832181215286255, "learning_rate": 4.370000502164098e-06, "loss": 0.7325, "step": 11979 }, { "epoch": 0.6997663551401869, "grad_norm": 2.6989407539367676, "learning_rate": 4.368437077078845e-06, "loss": 0.8191, "step": 11980 }, { "epoch": 0.6998247663551402, "grad_norm": 1.1811559200286865, "learning_rate": 4.366873853550937e-06, "loss": 0.5999, "step": 11981 }, { "epoch": 0.6998831775700934, "grad_norm": 1.027014136314392, "learning_rate": 4.3653108316363136e-06, "loss": 0.7546, "step": 11982 }, { "epoch": 0.6999415887850468, "grad_norm": 1.247767686843872, "learning_rate": 4.36374801139092e-06, "loss": 0.6485, "step": 11983 }, { "epoch": 0.7, "grad_norm": 1.979532241821289, "learning_rate": 4.3621853928706955e-06, "loss": 0.8097, "step": 11984 }, { "epoch": 0.7000584112149533, "grad_norm": 3.5268125534057617, "learning_rate": 4.360622976131559e-06, "loss": 0.8517, "step": 11985 }, { "epoch": 0.7001168224299066, "grad_norm": 0.9331574440002441, "learning_rate": 4.359060761229436e-06, "loss": 0.8245, "step": 11986 }, { "epoch": 0.7001752336448598, "grad_norm": 1.5927889347076416, "learning_rate": 4.357498748220236e-06, "loss": 0.7562, "step": 11987 }, { "epoch": 0.7002336448598131, "grad_norm": 1.4520139694213867, "learning_rate": 4.3559369371598645e-06, "loss": 0.6633, "step": 11988 }, { "epoch": 0.7002920560747663, "grad_norm": 1.1583219766616821, "learning_rate": 4.354375328104225e-06, "loss": 0.8208, "step": 11989 }, { "epoch": 0.7003504672897196, "grad_norm": 1.1119025945663452, "learning_rate": 4.352813921109202e-06, "loss": 0.74, "step": 11990 }, { "epoch": 0.7004088785046729, "grad_norm": 2.0093259811401367, "learning_rate": 4.351252716230685e-06, "loss": 0.7535, "step": 11991 }, { "epoch": 0.7004672897196261, "grad_norm": 1.1383699178695679, "learning_rate": 4.349691713524546e-06, "loss": 0.8154, "step": 11992 }, { "epoch": 0.7005257009345794, "grad_norm": 1.3068358898162842, "learning_rate": 4.3481309130466535e-06, "loss": 0.8959, "step": 11993 }, { "epoch": 0.7005841121495328, "grad_norm": 1.3887308835983276, "learning_rate": 4.346570314852871e-06, "loss": 0.8309, "step": 11994 }, { "epoch": 0.700642523364486, "grad_norm": 1.2453820705413818, "learning_rate": 4.345009918999055e-06, "loss": 0.8934, "step": 11995 }, { "epoch": 0.7007009345794393, "grad_norm": 1.1797996759414673, "learning_rate": 4.3434497255410555e-06, "loss": 0.6546, "step": 11996 }, { "epoch": 0.7007593457943925, "grad_norm": 1.2191835641860962, "learning_rate": 4.341889734534709e-06, "loss": 0.8557, "step": 11997 }, { "epoch": 0.7008177570093458, "grad_norm": 0.8860979676246643, "learning_rate": 4.340329946035846e-06, "loss": 0.6704, "step": 11998 }, { "epoch": 0.7008761682242991, "grad_norm": 1.1635688543319702, "learning_rate": 4.338770360100296e-06, "loss": 0.7306, "step": 11999 }, { "epoch": 0.7009345794392523, "grad_norm": 1.2958946228027344, "learning_rate": 4.337210976783876e-06, "loss": 0.9563, "step": 12000 }, { "epoch": 0.7009929906542056, "grad_norm": 1.6248054504394531, "learning_rate": 4.335651796142404e-06, "loss": 0.6497, "step": 12001 }, { "epoch": 0.7010514018691589, "grad_norm": 1.790744662284851, "learning_rate": 4.334092818231677e-06, "loss": 0.6896, "step": 12002 }, { "epoch": 0.7011098130841121, "grad_norm": 1.1019724607467651, "learning_rate": 4.3325340431074906e-06, "loss": 0.7294, "step": 12003 }, { "epoch": 0.7011682242990654, "grad_norm": 1.30496346950531, "learning_rate": 4.330975470825636e-06, "loss": 0.7466, "step": 12004 }, { "epoch": 0.7012266355140186, "grad_norm": 1.2327196598052979, "learning_rate": 4.329417101441898e-06, "loss": 0.8085, "step": 12005 }, { "epoch": 0.701285046728972, "grad_norm": 1.7114583253860474, "learning_rate": 4.327858935012054e-06, "loss": 0.9379, "step": 12006 }, { "epoch": 0.7013434579439253, "grad_norm": 1.2728829383850098, "learning_rate": 4.326300971591867e-06, "loss": 0.6912, "step": 12007 }, { "epoch": 0.7014018691588785, "grad_norm": 2.1115455627441406, "learning_rate": 4.324743211237096e-06, "loss": 0.8433, "step": 12008 }, { "epoch": 0.7014602803738318, "grad_norm": 0.9969999194145203, "learning_rate": 4.323185654003501e-06, "loss": 0.7595, "step": 12009 }, { "epoch": 0.701518691588785, "grad_norm": 1.1342467069625854, "learning_rate": 4.32162829994682e-06, "loss": 0.8515, "step": 12010 }, { "epoch": 0.7015771028037383, "grad_norm": 1.6349780559539795, "learning_rate": 4.320071149122795e-06, "loss": 0.8499, "step": 12011 }, { "epoch": 0.7016355140186916, "grad_norm": 1.2791855335235596, "learning_rate": 4.318514201587163e-06, "loss": 0.746, "step": 12012 }, { "epoch": 0.7016939252336448, "grad_norm": 0.9244834780693054, "learning_rate": 4.316957457395639e-06, "loss": 0.7134, "step": 12013 }, { "epoch": 0.7017523364485981, "grad_norm": 1.1825813055038452, "learning_rate": 4.315400916603949e-06, "loss": 0.7065, "step": 12014 }, { "epoch": 0.7018107476635514, "grad_norm": 1.42017662525177, "learning_rate": 4.313844579267793e-06, "loss": 0.8064, "step": 12015 }, { "epoch": 0.7018691588785047, "grad_norm": 1.6638522148132324, "learning_rate": 4.312288445442879e-06, "loss": 0.7682, "step": 12016 }, { "epoch": 0.701927570093458, "grad_norm": 1.2927002906799316, "learning_rate": 4.310732515184904e-06, "loss": 0.7755, "step": 12017 }, { "epoch": 0.7019859813084112, "grad_norm": 1.4087848663330078, "learning_rate": 4.30917678854955e-06, "loss": 0.7639, "step": 12018 }, { "epoch": 0.7020443925233645, "grad_norm": 1.650993824005127, "learning_rate": 4.307621265592505e-06, "loss": 0.7336, "step": 12019 }, { "epoch": 0.7021028037383178, "grad_norm": 1.6235740184783936, "learning_rate": 4.3060659463694335e-06, "loss": 0.7555, "step": 12020 }, { "epoch": 0.702161214953271, "grad_norm": 1.7786725759506226, "learning_rate": 4.304510830936005e-06, "loss": 0.8399, "step": 12021 }, { "epoch": 0.7022196261682243, "grad_norm": 1.2654253244400024, "learning_rate": 4.302955919347883e-06, "loss": 0.9616, "step": 12022 }, { "epoch": 0.7022780373831776, "grad_norm": 1.2954391241073608, "learning_rate": 4.3014012116607105e-06, "loss": 0.8386, "step": 12023 }, { "epoch": 0.7023364485981308, "grad_norm": 1.3834141492843628, "learning_rate": 4.29984670793014e-06, "loss": 0.7624, "step": 12024 }, { "epoch": 0.7023948598130841, "grad_norm": 1.2730534076690674, "learning_rate": 4.298292408211799e-06, "loss": 0.8263, "step": 12025 }, { "epoch": 0.7024532710280373, "grad_norm": 1.3092644214630127, "learning_rate": 4.296738312561326e-06, "loss": 0.633, "step": 12026 }, { "epoch": 0.7025116822429907, "grad_norm": 1.0471986532211304, "learning_rate": 4.2951844210343354e-06, "loss": 0.6691, "step": 12027 }, { "epoch": 0.702570093457944, "grad_norm": 1.0203684568405151, "learning_rate": 4.293630733686445e-06, "loss": 0.801, "step": 12028 }, { "epoch": 0.7026285046728972, "grad_norm": 0.8858461976051331, "learning_rate": 4.292077250573265e-06, "loss": 0.6611, "step": 12029 }, { "epoch": 0.7026869158878505, "grad_norm": 1.2076159715652466, "learning_rate": 4.290523971750391e-06, "loss": 0.713, "step": 12030 }, { "epoch": 0.7027453271028037, "grad_norm": 2.1427299976348877, "learning_rate": 4.288970897273421e-06, "loss": 0.8346, "step": 12031 }, { "epoch": 0.702803738317757, "grad_norm": 1.3275890350341797, "learning_rate": 4.287418027197935e-06, "loss": 0.8811, "step": 12032 }, { "epoch": 0.7028621495327103, "grad_norm": 1.0126534700393677, "learning_rate": 4.285865361579513e-06, "loss": 0.868, "step": 12033 }, { "epoch": 0.7029205607476635, "grad_norm": 0.9662439227104187, "learning_rate": 4.2843129004737315e-06, "loss": 0.7546, "step": 12034 }, { "epoch": 0.7029789719626168, "grad_norm": 1.2649279832839966, "learning_rate": 4.282760643936148e-06, "loss": 0.9387, "step": 12035 }, { "epoch": 0.7030373831775701, "grad_norm": 0.943853497505188, "learning_rate": 4.281208592022318e-06, "loss": 0.6177, "step": 12036 }, { "epoch": 0.7030957943925233, "grad_norm": 1.403927206993103, "learning_rate": 4.279656744787792e-06, "loss": 1.0354, "step": 12037 }, { "epoch": 0.7031542056074767, "grad_norm": 1.1010708808898926, "learning_rate": 4.278105102288113e-06, "loss": 0.6278, "step": 12038 }, { "epoch": 0.7032126168224299, "grad_norm": 1.3303412199020386, "learning_rate": 4.276553664578816e-06, "loss": 0.9014, "step": 12039 }, { "epoch": 0.7032710280373832, "grad_norm": 1.2598354816436768, "learning_rate": 4.275002431715429e-06, "loss": 0.8036, "step": 12040 }, { "epoch": 0.7033294392523365, "grad_norm": 1.1690343618392944, "learning_rate": 4.2734514037534644e-06, "loss": 0.7848, "step": 12041 }, { "epoch": 0.7033878504672897, "grad_norm": 1.3538885116577148, "learning_rate": 4.271900580748444e-06, "loss": 0.8346, "step": 12042 }, { "epoch": 0.703446261682243, "grad_norm": 2.2396514415740967, "learning_rate": 4.270349962755863e-06, "loss": 0.9671, "step": 12043 }, { "epoch": 0.7035046728971963, "grad_norm": 1.134641408920288, "learning_rate": 4.268799549831225e-06, "loss": 0.7641, "step": 12044 }, { "epoch": 0.7035630841121495, "grad_norm": 2.1062114238739014, "learning_rate": 4.267249342030023e-06, "loss": 0.78, "step": 12045 }, { "epoch": 0.7036214953271028, "grad_norm": 1.1563594341278076, "learning_rate": 4.265699339407733e-06, "loss": 0.6641, "step": 12046 }, { "epoch": 0.703679906542056, "grad_norm": 1.480444073677063, "learning_rate": 4.264149542019837e-06, "loss": 0.6829, "step": 12047 }, { "epoch": 0.7037383177570093, "grad_norm": 0.9308667778968811, "learning_rate": 4.262599949921797e-06, "loss": 0.6002, "step": 12048 }, { "epoch": 0.7037967289719627, "grad_norm": 1.5548768043518066, "learning_rate": 4.261050563169078e-06, "loss": 0.6421, "step": 12049 }, { "epoch": 0.7038551401869159, "grad_norm": 2.2155697345733643, "learning_rate": 4.259501381817136e-06, "loss": 0.892, "step": 12050 }, { "epoch": 0.7039135514018692, "grad_norm": 1.4933207035064697, "learning_rate": 4.25795240592141e-06, "loss": 0.8248, "step": 12051 }, { "epoch": 0.7039719626168224, "grad_norm": 2.284291982650757, "learning_rate": 4.256403635537346e-06, "loss": 0.7599, "step": 12052 }, { "epoch": 0.7040303738317757, "grad_norm": 1.6914916038513184, "learning_rate": 4.25485507072037e-06, "loss": 0.6466, "step": 12053 }, { "epoch": 0.704088785046729, "grad_norm": 1.2416274547576904, "learning_rate": 4.253306711525907e-06, "loss": 0.6274, "step": 12054 }, { "epoch": 0.7041471962616822, "grad_norm": 2.6710000038146973, "learning_rate": 4.25175855800938e-06, "loss": 0.8133, "step": 12055 }, { "epoch": 0.7042056074766355, "grad_norm": 1.2680143117904663, "learning_rate": 4.25021061022619e-06, "loss": 0.7226, "step": 12056 }, { "epoch": 0.7042640186915888, "grad_norm": 0.8074358701705933, "learning_rate": 4.248662868231747e-06, "loss": 0.5707, "step": 12057 }, { "epoch": 0.704322429906542, "grad_norm": 2.2640066146850586, "learning_rate": 4.247115332081438e-06, "loss": 0.8033, "step": 12058 }, { "epoch": 0.7043808411214953, "grad_norm": 1.6170759201049805, "learning_rate": 4.2455680018306555e-06, "loss": 0.7342, "step": 12059 }, { "epoch": 0.7044392523364486, "grad_norm": 1.4888685941696167, "learning_rate": 4.244020877534776e-06, "loss": 0.9257, "step": 12060 }, { "epoch": 0.7044976635514019, "grad_norm": 1.7130606174468994, "learning_rate": 4.242473959249172e-06, "loss": 0.7152, "step": 12061 }, { "epoch": 0.7045560747663552, "grad_norm": 1.8523688316345215, "learning_rate": 4.2409272470292165e-06, "loss": 0.7163, "step": 12062 }, { "epoch": 0.7046144859813084, "grad_norm": 2.0185399055480957, "learning_rate": 4.239380740930257e-06, "loss": 0.8181, "step": 12063 }, { "epoch": 0.7046728971962617, "grad_norm": 1.1959797143936157, "learning_rate": 4.237834441007652e-06, "loss": 0.6815, "step": 12064 }, { "epoch": 0.704731308411215, "grad_norm": 1.7426074743270874, "learning_rate": 4.236288347316738e-06, "loss": 0.6482, "step": 12065 }, { "epoch": 0.7047897196261682, "grad_norm": 1.5032227039337158, "learning_rate": 4.234742459912853e-06, "loss": 0.5771, "step": 12066 }, { "epoch": 0.7048481308411215, "grad_norm": 1.6513043642044067, "learning_rate": 4.2331967788513295e-06, "loss": 0.8205, "step": 12067 }, { "epoch": 0.7049065420560747, "grad_norm": 1.3420937061309814, "learning_rate": 4.2316513041874815e-06, "loss": 0.8708, "step": 12068 }, { "epoch": 0.704964953271028, "grad_norm": 1.8436954021453857, "learning_rate": 4.230106035976631e-06, "loss": 0.8503, "step": 12069 }, { "epoch": 0.7050233644859814, "grad_norm": 1.6043033599853516, "learning_rate": 4.228560974274075e-06, "loss": 0.8105, "step": 12070 }, { "epoch": 0.7050817757009346, "grad_norm": 1.0138028860092163, "learning_rate": 4.227016119135115e-06, "loss": 0.4639, "step": 12071 }, { "epoch": 0.7051401869158879, "grad_norm": 2.7989563941955566, "learning_rate": 4.22547147061505e-06, "loss": 0.7444, "step": 12072 }, { "epoch": 0.7051985981308411, "grad_norm": 1.7340335845947266, "learning_rate": 4.223927028769152e-06, "loss": 0.738, "step": 12073 }, { "epoch": 0.7052570093457944, "grad_norm": 3.1874186992645264, "learning_rate": 4.222382793652709e-06, "loss": 0.8729, "step": 12074 }, { "epoch": 0.7053154205607477, "grad_norm": 0.9337106943130493, "learning_rate": 4.220838765320983e-06, "loss": 0.6169, "step": 12075 }, { "epoch": 0.7053738317757009, "grad_norm": 1.7266807556152344, "learning_rate": 4.2192949438292355e-06, "loss": 0.7129, "step": 12076 }, { "epoch": 0.7054322429906542, "grad_norm": 1.3053903579711914, "learning_rate": 4.217751329232722e-06, "loss": 0.77, "step": 12077 }, { "epoch": 0.7054906542056075, "grad_norm": 1.814443826675415, "learning_rate": 4.21620792158669e-06, "loss": 0.6425, "step": 12078 }, { "epoch": 0.7055490654205607, "grad_norm": 1.187874436378479, "learning_rate": 4.214664720946384e-06, "loss": 0.7109, "step": 12079 }, { "epoch": 0.705607476635514, "grad_norm": 1.933497428894043, "learning_rate": 4.213121727367031e-06, "loss": 0.8009, "step": 12080 }, { "epoch": 0.7056658878504672, "grad_norm": 1.687591314315796, "learning_rate": 4.211578940903852e-06, "loss": 0.7962, "step": 12081 }, { "epoch": 0.7057242990654206, "grad_norm": 1.562153697013855, "learning_rate": 4.21003636161207e-06, "loss": 0.8462, "step": 12082 }, { "epoch": 0.7057827102803739, "grad_norm": 1.473236322402954, "learning_rate": 4.2084939895468925e-06, "loss": 0.6999, "step": 12083 }, { "epoch": 0.7058411214953271, "grad_norm": 0.9653329849243164, "learning_rate": 4.206951824763528e-06, "loss": 0.8776, "step": 12084 }, { "epoch": 0.7058995327102804, "grad_norm": 2.276967763900757, "learning_rate": 4.2054098673171655e-06, "loss": 0.7319, "step": 12085 }, { "epoch": 0.7059579439252337, "grad_norm": 1.8248035907745361, "learning_rate": 4.20386811726299e-06, "loss": 0.8615, "step": 12086 }, { "epoch": 0.7060163551401869, "grad_norm": 1.3493704795837402, "learning_rate": 4.202326574656186e-06, "loss": 0.7688, "step": 12087 }, { "epoch": 0.7060747663551402, "grad_norm": 1.4785667657852173, "learning_rate": 4.200785239551927e-06, "loss": 0.8151, "step": 12088 }, { "epoch": 0.7061331775700934, "grad_norm": 0.9463486671447754, "learning_rate": 4.19924411200538e-06, "loss": 0.7071, "step": 12089 }, { "epoch": 0.7061915887850467, "grad_norm": 1.5183593034744263, "learning_rate": 4.197703192071701e-06, "loss": 0.7588, "step": 12090 }, { "epoch": 0.70625, "grad_norm": 1.3544000387191772, "learning_rate": 4.196162479806034e-06, "loss": 0.66, "step": 12091 }, { "epoch": 0.7063084112149532, "grad_norm": 0.8496066927909851, "learning_rate": 4.194621975263534e-06, "loss": 0.7975, "step": 12092 }, { "epoch": 0.7063668224299066, "grad_norm": 1.2817440032958984, "learning_rate": 4.1930816784993255e-06, "loss": 0.5771, "step": 12093 }, { "epoch": 0.7064252336448598, "grad_norm": 1.3148740530014038, "learning_rate": 4.191541589568543e-06, "loss": 0.7935, "step": 12094 }, { "epoch": 0.7064836448598131, "grad_norm": 1.309698462486267, "learning_rate": 4.1900017085263085e-06, "loss": 0.9982, "step": 12095 }, { "epoch": 0.7065420560747664, "grad_norm": 1.6563023328781128, "learning_rate": 4.188462035427731e-06, "loss": 0.7494, "step": 12096 }, { "epoch": 0.7066004672897196, "grad_norm": 1.5924183130264282, "learning_rate": 4.186922570327921e-06, "loss": 0.8177, "step": 12097 }, { "epoch": 0.7066588785046729, "grad_norm": 1.1979011297225952, "learning_rate": 4.185383313281971e-06, "loss": 0.6334, "step": 12098 }, { "epoch": 0.7067172897196262, "grad_norm": 1.2638020515441895, "learning_rate": 4.183844264344975e-06, "loss": 0.8267, "step": 12099 }, { "epoch": 0.7067757009345794, "grad_norm": 1.1196001768112183, "learning_rate": 4.182305423572022e-06, "loss": 0.643, "step": 12100 }, { "epoch": 0.7068341121495327, "grad_norm": 0.7924894690513611, "learning_rate": 4.180766791018178e-06, "loss": 0.4659, "step": 12101 }, { "epoch": 0.7068925233644859, "grad_norm": 1.1042863130569458, "learning_rate": 4.17922836673852e-06, "loss": 0.5194, "step": 12102 }, { "epoch": 0.7069509345794392, "grad_norm": 1.3903114795684814, "learning_rate": 4.177690150788104e-06, "loss": 0.7469, "step": 12103 }, { "epoch": 0.7070093457943926, "grad_norm": 1.2370126247406006, "learning_rate": 4.176152143221984e-06, "loss": 0.767, "step": 12104 }, { "epoch": 0.7070677570093458, "grad_norm": 1.4145621061325073, "learning_rate": 4.1746143440952135e-06, "loss": 0.6761, "step": 12105 }, { "epoch": 0.7071261682242991, "grad_norm": 0.9579271674156189, "learning_rate": 4.173076753462821e-06, "loss": 0.8152, "step": 12106 }, { "epoch": 0.7071845794392523, "grad_norm": 1.1724826097488403, "learning_rate": 4.171539371379847e-06, "loss": 0.7241, "step": 12107 }, { "epoch": 0.7072429906542056, "grad_norm": 1.802962303161621, "learning_rate": 4.170002197901311e-06, "loss": 0.7361, "step": 12108 }, { "epoch": 0.7073014018691589, "grad_norm": 1.1010829210281372, "learning_rate": 4.168465233082226e-06, "loss": 0.7696, "step": 12109 }, { "epoch": 0.7073598130841121, "grad_norm": 1.4502676725387573, "learning_rate": 4.166928476977604e-06, "loss": 0.6646, "step": 12110 }, { "epoch": 0.7074182242990654, "grad_norm": 1.4787867069244385, "learning_rate": 4.165391929642448e-06, "loss": 0.7753, "step": 12111 }, { "epoch": 0.7074766355140187, "grad_norm": 1.4407728910446167, "learning_rate": 4.163855591131755e-06, "loss": 0.7375, "step": 12112 }, { "epoch": 0.7075350467289719, "grad_norm": 1.8221169710159302, "learning_rate": 4.162319461500507e-06, "loss": 0.9324, "step": 12113 }, { "epoch": 0.7075934579439253, "grad_norm": 0.9860743880271912, "learning_rate": 4.16078354080368e-06, "loss": 0.7631, "step": 12114 }, { "epoch": 0.7076518691588785, "grad_norm": 1.4296855926513672, "learning_rate": 4.15924782909625e-06, "loss": 0.7756, "step": 12115 }, { "epoch": 0.7077102803738318, "grad_norm": 1.360687255859375, "learning_rate": 4.157712326433181e-06, "loss": 0.7557, "step": 12116 }, { "epoch": 0.7077686915887851, "grad_norm": 1.193312406539917, "learning_rate": 4.156177032869432e-06, "loss": 0.6803, "step": 12117 }, { "epoch": 0.7078271028037383, "grad_norm": 2.1785922050476074, "learning_rate": 4.15464194845995e-06, "loss": 0.7937, "step": 12118 }, { "epoch": 0.7078855140186916, "grad_norm": 0.9662495255470276, "learning_rate": 4.153107073259671e-06, "loss": 0.7069, "step": 12119 }, { "epoch": 0.7079439252336449, "grad_norm": 1.2691502571105957, "learning_rate": 4.151572407323537e-06, "loss": 0.6073, "step": 12120 }, { "epoch": 0.7080023364485981, "grad_norm": 1.12924063205719, "learning_rate": 4.150037950706469e-06, "loss": 0.7723, "step": 12121 }, { "epoch": 0.7080607476635514, "grad_norm": 0.9751401543617249, "learning_rate": 4.1485037034633945e-06, "loss": 0.8244, "step": 12122 }, { "epoch": 0.7081191588785046, "grad_norm": 1.632427453994751, "learning_rate": 4.14696966564922e-06, "loss": 0.7759, "step": 12123 }, { "epoch": 0.7081775700934579, "grad_norm": 1.180487036705017, "learning_rate": 4.145435837318845e-06, "loss": 0.8442, "step": 12124 }, { "epoch": 0.7082359813084113, "grad_norm": 1.23207688331604, "learning_rate": 4.143902218527175e-06, "loss": 0.8764, "step": 12125 }, { "epoch": 0.7082943925233645, "grad_norm": 1.1412385702133179, "learning_rate": 4.142368809329087e-06, "loss": 0.9125, "step": 12126 }, { "epoch": 0.7083528037383178, "grad_norm": 0.8790662884712219, "learning_rate": 4.140835609779479e-06, "loss": 0.7031, "step": 12127 }, { "epoch": 0.708411214953271, "grad_norm": 1.190765142440796, "learning_rate": 4.139302619933217e-06, "loss": 0.9469, "step": 12128 }, { "epoch": 0.7084696261682243, "grad_norm": 1.27004075050354, "learning_rate": 4.1377698398451635e-06, "loss": 0.8845, "step": 12129 }, { "epoch": 0.7085280373831776, "grad_norm": 1.209498643875122, "learning_rate": 4.136237269570186e-06, "loss": 0.8564, "step": 12130 }, { "epoch": 0.7085864485981308, "grad_norm": 1.012582778930664, "learning_rate": 4.134704909163129e-06, "loss": 0.6905, "step": 12131 }, { "epoch": 0.7086448598130841, "grad_norm": 1.3353073596954346, "learning_rate": 4.133172758678839e-06, "loss": 0.8094, "step": 12132 }, { "epoch": 0.7087032710280374, "grad_norm": 1.1160303354263306, "learning_rate": 4.131640818172157e-06, "loss": 0.661, "step": 12133 }, { "epoch": 0.7087616822429906, "grad_norm": 1.2415144443511963, "learning_rate": 4.130109087697905e-06, "loss": 0.7269, "step": 12134 }, { "epoch": 0.708820093457944, "grad_norm": 2.349153757095337, "learning_rate": 4.128577567310913e-06, "loss": 0.7984, "step": 12135 }, { "epoch": 0.7088785046728971, "grad_norm": 1.2963058948516846, "learning_rate": 4.127046257065986e-06, "loss": 0.865, "step": 12136 }, { "epoch": 0.7089369158878505, "grad_norm": 0.912908673286438, "learning_rate": 4.125515157017934e-06, "loss": 0.7518, "step": 12137 }, { "epoch": 0.7089953271028038, "grad_norm": 0.9690924882888794, "learning_rate": 4.123984267221562e-06, "loss": 0.6505, "step": 12138 }, { "epoch": 0.709053738317757, "grad_norm": 1.2223740816116333, "learning_rate": 4.122453587731653e-06, "loss": 0.8203, "step": 12139 }, { "epoch": 0.7091121495327103, "grad_norm": 1.2939822673797607, "learning_rate": 4.1209231186029985e-06, "loss": 0.8071, "step": 12140 }, { "epoch": 0.7091705607476636, "grad_norm": 1.2993836402893066, "learning_rate": 4.119392859890367e-06, "loss": 0.7633, "step": 12141 }, { "epoch": 0.7092289719626168, "grad_norm": 1.5957310199737549, "learning_rate": 4.117862811648535e-06, "loss": 0.7941, "step": 12142 }, { "epoch": 0.7092873831775701, "grad_norm": 1.052939772605896, "learning_rate": 4.116332973932256e-06, "loss": 0.748, "step": 12143 }, { "epoch": 0.7093457943925233, "grad_norm": 1.1267781257629395, "learning_rate": 4.1148033467962915e-06, "loss": 0.711, "step": 12144 }, { "epoch": 0.7094042056074766, "grad_norm": 1.5267199277877808, "learning_rate": 4.113273930295386e-06, "loss": 0.7819, "step": 12145 }, { "epoch": 0.70946261682243, "grad_norm": 1.1837650537490845, "learning_rate": 4.1117447244842775e-06, "loss": 0.7379, "step": 12146 }, { "epoch": 0.7095210280373832, "grad_norm": 1.0773216485977173, "learning_rate": 4.110215729417694e-06, "loss": 0.7725, "step": 12147 }, { "epoch": 0.7095794392523365, "grad_norm": 1.1046028137207031, "learning_rate": 4.108686945150361e-06, "loss": 0.7299, "step": 12148 }, { "epoch": 0.7096378504672897, "grad_norm": 1.0816233158111572, "learning_rate": 4.107158371736997e-06, "loss": 0.8391, "step": 12149 }, { "epoch": 0.709696261682243, "grad_norm": 0.8056933879852295, "learning_rate": 4.105630009232312e-06, "loss": 0.6972, "step": 12150 }, { "epoch": 0.7097546728971963, "grad_norm": 1.2896699905395508, "learning_rate": 4.104101857691005e-06, "loss": 0.8669, "step": 12151 }, { "epoch": 0.7098130841121495, "grad_norm": 1.2072079181671143, "learning_rate": 4.1025739171677655e-06, "loss": 0.6005, "step": 12152 }, { "epoch": 0.7098714953271028, "grad_norm": 1.224956750869751, "learning_rate": 4.101046187717284e-06, "loss": 0.7676, "step": 12153 }, { "epoch": 0.7099299065420561, "grad_norm": 1.2112253904342651, "learning_rate": 4.099518669394238e-06, "loss": 0.9043, "step": 12154 }, { "epoch": 0.7099883177570093, "grad_norm": 1.1781983375549316, "learning_rate": 4.0979913622533e-06, "loss": 0.6315, "step": 12155 }, { "epoch": 0.7100467289719626, "grad_norm": 1.6655927896499634, "learning_rate": 4.096464266349134e-06, "loss": 0.5913, "step": 12156 }, { "epoch": 0.7101051401869158, "grad_norm": 1.0342482328414917, "learning_rate": 4.094937381736389e-06, "loss": 0.6879, "step": 12157 }, { "epoch": 0.7101635514018692, "grad_norm": 0.9793524742126465, "learning_rate": 4.093410708469722e-06, "loss": 0.8197, "step": 12158 }, { "epoch": 0.7102219626168225, "grad_norm": 1.1547484397888184, "learning_rate": 4.091884246603762e-06, "loss": 0.7223, "step": 12159 }, { "epoch": 0.7102803738317757, "grad_norm": 1.1452620029449463, "learning_rate": 4.090357996193156e-06, "loss": 0.8152, "step": 12160 }, { "epoch": 0.710338785046729, "grad_norm": 1.3088258504867554, "learning_rate": 4.088831957292524e-06, "loss": 0.8079, "step": 12161 }, { "epoch": 0.7103971962616823, "grad_norm": 1.2902048826217651, "learning_rate": 4.087306129956478e-06, "loss": 0.7614, "step": 12162 }, { "epoch": 0.7104556074766355, "grad_norm": 1.384922981262207, "learning_rate": 4.085780514239639e-06, "loss": 0.777, "step": 12163 }, { "epoch": 0.7105140186915888, "grad_norm": 0.9110764861106873, "learning_rate": 4.084255110196599e-06, "loss": 0.603, "step": 12164 }, { "epoch": 0.710572429906542, "grad_norm": 1.2646182775497437, "learning_rate": 4.082729917881958e-06, "loss": 0.7601, "step": 12165 }, { "epoch": 0.7106308411214953, "grad_norm": 1.1875659227371216, "learning_rate": 4.081204937350308e-06, "loss": 0.8594, "step": 12166 }, { "epoch": 0.7106892523364486, "grad_norm": 1.0780291557312012, "learning_rate": 4.079680168656221e-06, "loss": 0.9202, "step": 12167 }, { "epoch": 0.7107476635514018, "grad_norm": 1.5669289827346802, "learning_rate": 4.078155611854278e-06, "loss": 0.7054, "step": 12168 }, { "epoch": 0.7108060747663552, "grad_norm": 0.9955150485038757, "learning_rate": 4.0766312669990345e-06, "loss": 0.6115, "step": 12169 }, { "epoch": 0.7108644859813084, "grad_norm": 1.0328179597854614, "learning_rate": 4.0751071341450535e-06, "loss": 0.7265, "step": 12170 }, { "epoch": 0.7109228971962617, "grad_norm": 0.8202188014984131, "learning_rate": 4.073583213346888e-06, "loss": 0.5774, "step": 12171 }, { "epoch": 0.710981308411215, "grad_norm": 1.7823052406311035, "learning_rate": 4.07205950465907e-06, "loss": 0.7312, "step": 12172 }, { "epoch": 0.7110397196261682, "grad_norm": 1.109885573387146, "learning_rate": 4.070536008136146e-06, "loss": 0.7103, "step": 12173 }, { "epoch": 0.7110981308411215, "grad_norm": 1.018656611442566, "learning_rate": 4.0690127238326326e-06, "loss": 0.7559, "step": 12174 }, { "epoch": 0.7111565420560748, "grad_norm": 1.219175934791565, "learning_rate": 4.067489651803057e-06, "loss": 0.7954, "step": 12175 }, { "epoch": 0.711214953271028, "grad_norm": 1.2522028684616089, "learning_rate": 4.065966792101924e-06, "loss": 0.8088, "step": 12176 }, { "epoch": 0.7112733644859813, "grad_norm": 1.2853114604949951, "learning_rate": 4.064444144783741e-06, "loss": 0.8652, "step": 12177 }, { "epoch": 0.7113317757009345, "grad_norm": 1.098972201347351, "learning_rate": 4.0629217099030095e-06, "loss": 0.6959, "step": 12178 }, { "epoch": 0.7113901869158878, "grad_norm": 1.2136948108673096, "learning_rate": 4.0613994875142084e-06, "loss": 0.9333, "step": 12179 }, { "epoch": 0.7114485981308412, "grad_norm": 1.6206767559051514, "learning_rate": 4.059877477671829e-06, "loss": 0.704, "step": 12180 }, { "epoch": 0.7115070093457944, "grad_norm": 1.4138104915618896, "learning_rate": 4.058355680430337e-06, "loss": 0.8148, "step": 12181 }, { "epoch": 0.7115654205607477, "grad_norm": 1.3040978908538818, "learning_rate": 4.056834095844201e-06, "loss": 0.7306, "step": 12182 }, { "epoch": 0.711623831775701, "grad_norm": 1.9992778301239014, "learning_rate": 4.055312723967885e-06, "loss": 0.75, "step": 12183 }, { "epoch": 0.7116822429906542, "grad_norm": 1.1344159841537476, "learning_rate": 4.05379156485583e-06, "loss": 0.7498, "step": 12184 }, { "epoch": 0.7117406542056075, "grad_norm": 1.594281792640686, "learning_rate": 4.052270618562489e-06, "loss": 0.8462, "step": 12185 }, { "epoch": 0.7117990654205607, "grad_norm": 1.239372968673706, "learning_rate": 4.050749885142291e-06, "loss": 0.5935, "step": 12186 }, { "epoch": 0.711857476635514, "grad_norm": 1.140001893043518, "learning_rate": 4.049229364649665e-06, "loss": 0.8866, "step": 12187 }, { "epoch": 0.7119158878504673, "grad_norm": 1.240607500076294, "learning_rate": 4.047709057139037e-06, "loss": 0.7826, "step": 12188 }, { "epoch": 0.7119742990654205, "grad_norm": 0.9189279675483704, "learning_rate": 4.046188962664811e-06, "loss": 0.6474, "step": 12189 }, { "epoch": 0.7120327102803738, "grad_norm": 1.2858222723007202, "learning_rate": 4.044669081281402e-06, "loss": 0.8144, "step": 12190 }, { "epoch": 0.712091121495327, "grad_norm": 1.0208626985549927, "learning_rate": 4.0431494130432e-06, "loss": 0.625, "step": 12191 }, { "epoch": 0.7121495327102804, "grad_norm": 1.4831252098083496, "learning_rate": 4.041629958004592e-06, "loss": 0.7943, "step": 12192 }, { "epoch": 0.7122079439252337, "grad_norm": 1.6095930337905884, "learning_rate": 4.040110716219972e-06, "loss": 0.7531, "step": 12193 }, { "epoch": 0.7122663551401869, "grad_norm": 0.91129469871521, "learning_rate": 4.038591687743705e-06, "loss": 0.6978, "step": 12194 }, { "epoch": 0.7123247663551402, "grad_norm": 1.1705894470214844, "learning_rate": 4.037072872630163e-06, "loss": 0.6298, "step": 12195 }, { "epoch": 0.7123831775700935, "grad_norm": 1.8496595621109009, "learning_rate": 4.035554270933706e-06, "loss": 0.802, "step": 12196 }, { "epoch": 0.7124415887850467, "grad_norm": 1.005285382270813, "learning_rate": 4.034035882708678e-06, "loss": 0.7192, "step": 12197 }, { "epoch": 0.7125, "grad_norm": 1.500893473625183, "learning_rate": 4.032517708009429e-06, "loss": 0.9089, "step": 12198 }, { "epoch": 0.7125584112149532, "grad_norm": 1.3527579307556152, "learning_rate": 4.030999746890295e-06, "loss": 0.7756, "step": 12199 }, { "epoch": 0.7126168224299065, "grad_norm": 0.968925416469574, "learning_rate": 4.029481999405609e-06, "loss": 0.8199, "step": 12200 }, { "epoch": 0.7126752336448599, "grad_norm": 1.4756842851638794, "learning_rate": 4.027964465609687e-06, "loss": 0.8614, "step": 12201 }, { "epoch": 0.712733644859813, "grad_norm": 1.195726752281189, "learning_rate": 4.02644714555684e-06, "loss": 0.7597, "step": 12202 }, { "epoch": 0.7127920560747664, "grad_norm": 1.0017826557159424, "learning_rate": 4.024930039301378e-06, "loss": 0.5758, "step": 12203 }, { "epoch": 0.7128504672897197, "grad_norm": 1.433912754058838, "learning_rate": 4.023413146897601e-06, "loss": 0.8589, "step": 12204 }, { "epoch": 0.7129088785046729, "grad_norm": 1.4151583909988403, "learning_rate": 4.021896468399795e-06, "loss": 0.7518, "step": 12205 }, { "epoch": 0.7129672897196262, "grad_norm": 1.0152901411056519, "learning_rate": 4.020380003862247e-06, "loss": 0.7706, "step": 12206 }, { "epoch": 0.7130257009345794, "grad_norm": 1.0103482007980347, "learning_rate": 4.018863753339228e-06, "loss": 0.7516, "step": 12207 }, { "epoch": 0.7130841121495327, "grad_norm": 1.3414713144302368, "learning_rate": 4.017347716885012e-06, "loss": 0.8087, "step": 12208 }, { "epoch": 0.713142523364486, "grad_norm": 1.2268569469451904, "learning_rate": 4.01583189455385e-06, "loss": 0.6143, "step": 12209 }, { "epoch": 0.7132009345794392, "grad_norm": 1.0571987628936768, "learning_rate": 4.014316286399999e-06, "loss": 0.795, "step": 12210 }, { "epoch": 0.7132593457943925, "grad_norm": 1.013250470161438, "learning_rate": 4.012800892477708e-06, "loss": 0.7815, "step": 12211 }, { "epoch": 0.7133177570093457, "grad_norm": 1.4916454553604126, "learning_rate": 4.011285712841208e-06, "loss": 1.0513, "step": 12212 }, { "epoch": 0.7133761682242991, "grad_norm": 1.4168336391448975, "learning_rate": 4.009770747544731e-06, "loss": 0.8756, "step": 12213 }, { "epoch": 0.7134345794392524, "grad_norm": 1.493701696395874, "learning_rate": 4.008255996642495e-06, "loss": 0.8862, "step": 12214 }, { "epoch": 0.7134929906542056, "grad_norm": 0.993728518486023, "learning_rate": 4.006741460188716e-06, "loss": 0.7764, "step": 12215 }, { "epoch": 0.7135514018691589, "grad_norm": 1.4080466032028198, "learning_rate": 4.005227138237604e-06, "loss": 0.7347, "step": 12216 }, { "epoch": 0.7136098130841122, "grad_norm": 5.611662864685059, "learning_rate": 4.003713030843351e-06, "loss": 0.9337, "step": 12217 }, { "epoch": 0.7136682242990654, "grad_norm": 2.3452107906341553, "learning_rate": 4.002199138060157e-06, "loss": 0.9931, "step": 12218 }, { "epoch": 0.7137266355140187, "grad_norm": 1.1013739109039307, "learning_rate": 4.000685459942193e-06, "loss": 0.7517, "step": 12219 }, { "epoch": 0.7137850467289719, "grad_norm": 0.8885149359703064, "learning_rate": 3.999171996543643e-06, "loss": 0.6037, "step": 12220 }, { "epoch": 0.7138434579439252, "grad_norm": 1.415371060371399, "learning_rate": 3.997658747918674e-06, "loss": 0.7051, "step": 12221 }, { "epoch": 0.7139018691588785, "grad_norm": 1.1367543935775757, "learning_rate": 3.996145714121444e-06, "loss": 0.8514, "step": 12222 }, { "epoch": 0.7139602803738317, "grad_norm": 1.1844533681869507, "learning_rate": 3.99463289520611e-06, "loss": 0.8507, "step": 12223 }, { "epoch": 0.7140186915887851, "grad_norm": 1.2730321884155273, "learning_rate": 3.993120291226812e-06, "loss": 0.7326, "step": 12224 }, { "epoch": 0.7140771028037384, "grad_norm": 1.423246145248413, "learning_rate": 3.991607902237682e-06, "loss": 0.8848, "step": 12225 }, { "epoch": 0.7141355140186916, "grad_norm": 1.0541001558303833, "learning_rate": 3.990095728292862e-06, "loss": 0.8247, "step": 12226 }, { "epoch": 0.7141939252336449, "grad_norm": 1.4317394495010376, "learning_rate": 3.988583769446464e-06, "loss": 0.7981, "step": 12227 }, { "epoch": 0.7142523364485981, "grad_norm": 1.4407302141189575, "learning_rate": 3.98707202575261e-06, "loss": 0.7927, "step": 12228 }, { "epoch": 0.7143107476635514, "grad_norm": 1.2035924196243286, "learning_rate": 3.9855604972654014e-06, "loss": 0.7593, "step": 12229 }, { "epoch": 0.7143691588785047, "grad_norm": 1.1228652000427246, "learning_rate": 3.984049184038934e-06, "loss": 0.7626, "step": 12230 }, { "epoch": 0.7144275700934579, "grad_norm": 1.5047962665557861, "learning_rate": 3.982538086127301e-06, "loss": 0.8144, "step": 12231 }, { "epoch": 0.7144859813084112, "grad_norm": 1.3881467580795288, "learning_rate": 3.981027203584587e-06, "loss": 0.8036, "step": 12232 }, { "epoch": 0.7145443925233644, "grad_norm": 1.3443247079849243, "learning_rate": 3.97951653646487e-06, "loss": 0.9199, "step": 12233 }, { "epoch": 0.7146028037383177, "grad_norm": 1.3302130699157715, "learning_rate": 3.978006084822214e-06, "loss": 0.6802, "step": 12234 }, { "epoch": 0.7146612149532711, "grad_norm": 1.0810359716415405, "learning_rate": 3.9764958487106786e-06, "loss": 0.6691, "step": 12235 }, { "epoch": 0.7147196261682243, "grad_norm": 1.4254215955734253, "learning_rate": 3.974985828184316e-06, "loss": 0.8052, "step": 12236 }, { "epoch": 0.7147780373831776, "grad_norm": 1.2726683616638184, "learning_rate": 3.9734760232971715e-06, "loss": 0.8269, "step": 12237 }, { "epoch": 0.7148364485981309, "grad_norm": 1.6055567264556885, "learning_rate": 3.9719664341032875e-06, "loss": 0.7918, "step": 12238 }, { "epoch": 0.7148948598130841, "grad_norm": 1.863044261932373, "learning_rate": 3.970457060656687e-06, "loss": 0.8205, "step": 12239 }, { "epoch": 0.7149532710280374, "grad_norm": 0.7937080264091492, "learning_rate": 3.96894790301139e-06, "loss": 0.6437, "step": 12240 }, { "epoch": 0.7150116822429906, "grad_norm": 1.5036512613296509, "learning_rate": 3.967438961221417e-06, "loss": 0.9547, "step": 12241 }, { "epoch": 0.7150700934579439, "grad_norm": 0.9727789163589478, "learning_rate": 3.965930235340762e-06, "loss": 0.6273, "step": 12242 }, { "epoch": 0.7151285046728972, "grad_norm": 0.9603826403617859, "learning_rate": 3.964421725423438e-06, "loss": 0.6223, "step": 12243 }, { "epoch": 0.7151869158878504, "grad_norm": 1.1016665697097778, "learning_rate": 3.962913431523431e-06, "loss": 0.8193, "step": 12244 }, { "epoch": 0.7152453271028038, "grad_norm": 1.0918748378753662, "learning_rate": 3.961405353694716e-06, "loss": 0.7126, "step": 12245 }, { "epoch": 0.715303738317757, "grad_norm": 1.1285691261291504, "learning_rate": 3.9598974919912796e-06, "loss": 0.6624, "step": 12246 }, { "epoch": 0.7153621495327103, "grad_norm": 1.4533822536468506, "learning_rate": 3.9583898464670776e-06, "loss": 0.8749, "step": 12247 }, { "epoch": 0.7154205607476636, "grad_norm": 1.2525607347488403, "learning_rate": 3.956882417176076e-06, "loss": 0.7017, "step": 12248 }, { "epoch": 0.7154789719626168, "grad_norm": 1.229957938194275, "learning_rate": 3.955375204172231e-06, "loss": 0.7602, "step": 12249 }, { "epoch": 0.7155373831775701, "grad_norm": 1.3045434951782227, "learning_rate": 3.953868207509477e-06, "loss": 0.7886, "step": 12250 }, { "epoch": 0.7155957943925234, "grad_norm": 1.2330909967422485, "learning_rate": 3.95236142724176e-06, "loss": 0.872, "step": 12251 }, { "epoch": 0.7156542056074766, "grad_norm": 1.3836352825164795, "learning_rate": 3.950854863422999e-06, "loss": 0.8587, "step": 12252 }, { "epoch": 0.7157126168224299, "grad_norm": 1.6574355363845825, "learning_rate": 3.949348516107121e-06, "loss": 0.6927, "step": 12253 }, { "epoch": 0.7157710280373831, "grad_norm": 1.1828229427337646, "learning_rate": 3.94784238534804e-06, "loss": 0.8065, "step": 12254 }, { "epoch": 0.7158294392523364, "grad_norm": 1.4425424337387085, "learning_rate": 3.946336471199658e-06, "loss": 0.6914, "step": 12255 }, { "epoch": 0.7158878504672898, "grad_norm": 1.5242702960968018, "learning_rate": 3.944830773715876e-06, "loss": 0.9746, "step": 12256 }, { "epoch": 0.715946261682243, "grad_norm": 1.410794734954834, "learning_rate": 3.943325292950579e-06, "loss": 0.7058, "step": 12257 }, { "epoch": 0.7160046728971963, "grad_norm": 1.4477006196975708, "learning_rate": 3.941820028957652e-06, "loss": 0.7052, "step": 12258 }, { "epoch": 0.7160630841121496, "grad_norm": 1.342939853668213, "learning_rate": 3.940314981790972e-06, "loss": 0.6843, "step": 12259 }, { "epoch": 0.7161214953271028, "grad_norm": 2.9888253211975098, "learning_rate": 3.938810151504402e-06, "loss": 0.9063, "step": 12260 }, { "epoch": 0.7161799065420561, "grad_norm": 1.528465986251831, "learning_rate": 3.9373055381518035e-06, "loss": 0.8807, "step": 12261 }, { "epoch": 0.7162383177570093, "grad_norm": 1.3834151029586792, "learning_rate": 3.935801141787027e-06, "loss": 0.7736, "step": 12262 }, { "epoch": 0.7162967289719626, "grad_norm": 1.6371632814407349, "learning_rate": 3.93429696246391e-06, "loss": 0.7408, "step": 12263 }, { "epoch": 0.7163551401869159, "grad_norm": 1.9361926317214966, "learning_rate": 3.932793000236295e-06, "loss": 0.91, "step": 12264 }, { "epoch": 0.7164135514018691, "grad_norm": 1.4217872619628906, "learning_rate": 3.931289255158008e-06, "loss": 0.9492, "step": 12265 }, { "epoch": 0.7164719626168224, "grad_norm": 1.4472894668579102, "learning_rate": 3.92978572728287e-06, "loss": 0.854, "step": 12266 }, { "epoch": 0.7165303738317756, "grad_norm": 0.9108009934425354, "learning_rate": 3.928282416664694e-06, "loss": 0.8377, "step": 12267 }, { "epoch": 0.716588785046729, "grad_norm": 1.6188948154449463, "learning_rate": 3.926779323357278e-06, "loss": 0.9709, "step": 12268 }, { "epoch": 0.7166471962616823, "grad_norm": 1.0901668071746826, "learning_rate": 3.925276447414424e-06, "loss": 0.7532, "step": 12269 }, { "epoch": 0.7167056074766355, "grad_norm": 1.5340251922607422, "learning_rate": 3.923773788889919e-06, "loss": 0.8596, "step": 12270 }, { "epoch": 0.7167640186915888, "grad_norm": 1.311862587928772, "learning_rate": 3.92227134783755e-06, "loss": 0.7825, "step": 12271 }, { "epoch": 0.7168224299065421, "grad_norm": 1.021916151046753, "learning_rate": 3.920769124311085e-06, "loss": 0.6789, "step": 12272 }, { "epoch": 0.7168808411214953, "grad_norm": 1.1135929822921753, "learning_rate": 3.919267118364286e-06, "loss": 0.834, "step": 12273 }, { "epoch": 0.7169392523364486, "grad_norm": 2.221910238265991, "learning_rate": 3.91776533005092e-06, "loss": 0.7403, "step": 12274 }, { "epoch": 0.7169976635514018, "grad_norm": 1.565805196762085, "learning_rate": 3.916263759424724e-06, "loss": 0.8064, "step": 12275 }, { "epoch": 0.7170560747663551, "grad_norm": 1.0064698457717896, "learning_rate": 3.914762406539455e-06, "loss": 0.6045, "step": 12276 }, { "epoch": 0.7171144859813084, "grad_norm": 1.5473707914352417, "learning_rate": 3.913261271448842e-06, "loss": 0.7677, "step": 12277 }, { "epoch": 0.7171728971962616, "grad_norm": 1.1135954856872559, "learning_rate": 3.911760354206605e-06, "loss": 0.8557, "step": 12278 }, { "epoch": 0.717231308411215, "grad_norm": 1.4970901012420654, "learning_rate": 3.910259654866473e-06, "loss": 0.8275, "step": 12279 }, { "epoch": 0.7172897196261683, "grad_norm": 0.9867801070213318, "learning_rate": 3.908759173482147e-06, "loss": 0.6292, "step": 12280 }, { "epoch": 0.7173481308411215, "grad_norm": 1.162700891494751, "learning_rate": 3.907258910107337e-06, "loss": 0.7554, "step": 12281 }, { "epoch": 0.7174065420560748, "grad_norm": 0.9566280245780945, "learning_rate": 3.905758864795739e-06, "loss": 0.6129, "step": 12282 }, { "epoch": 0.717464953271028, "grad_norm": 1.5795800685882568, "learning_rate": 3.904259037601035e-06, "loss": 0.7631, "step": 12283 }, { "epoch": 0.7175233644859813, "grad_norm": 0.9468510150909424, "learning_rate": 3.902759428576912e-06, "loss": 0.7389, "step": 12284 }, { "epoch": 0.7175817757009346, "grad_norm": 2.4149935245513916, "learning_rate": 3.901260037777034e-06, "loss": 0.676, "step": 12285 }, { "epoch": 0.7176401869158878, "grad_norm": 1.6911159753799438, "learning_rate": 3.899760865255069e-06, "loss": 0.7929, "step": 12286 }, { "epoch": 0.7176985981308411, "grad_norm": 1.1619536876678467, "learning_rate": 3.898261911064678e-06, "loss": 0.6686, "step": 12287 }, { "epoch": 0.7177570093457943, "grad_norm": 1.0733966827392578, "learning_rate": 3.896763175259502e-06, "loss": 0.652, "step": 12288 }, { "epoch": 0.7178154205607477, "grad_norm": 1.0133330821990967, "learning_rate": 3.895264657893187e-06, "loss": 0.6037, "step": 12289 }, { "epoch": 0.717873831775701, "grad_norm": 1.346010446548462, "learning_rate": 3.893766359019361e-06, "loss": 0.7076, "step": 12290 }, { "epoch": 0.7179322429906542, "grad_norm": 1.519882082939148, "learning_rate": 3.892268278691651e-06, "loss": 0.9053, "step": 12291 }, { "epoch": 0.7179906542056075, "grad_norm": 1.5037939548492432, "learning_rate": 3.89077041696368e-06, "loss": 0.8301, "step": 12292 }, { "epoch": 0.7180490654205608, "grad_norm": 1.5137088298797607, "learning_rate": 3.889272773889049e-06, "loss": 0.6992, "step": 12293 }, { "epoch": 0.718107476635514, "grad_norm": 2.2524421215057373, "learning_rate": 3.887775349521366e-06, "loss": 0.6273, "step": 12294 }, { "epoch": 0.7181658878504673, "grad_norm": 1.4069502353668213, "learning_rate": 3.886278143914219e-06, "loss": 0.731, "step": 12295 }, { "epoch": 0.7182242990654205, "grad_norm": 1.3006682395935059, "learning_rate": 3.884781157121201e-06, "loss": 0.7458, "step": 12296 }, { "epoch": 0.7182827102803738, "grad_norm": 1.3679248094558716, "learning_rate": 3.883284389195883e-06, "loss": 0.8911, "step": 12297 }, { "epoch": 0.7183411214953271, "grad_norm": 1.2375152111053467, "learning_rate": 3.8817878401918375e-06, "loss": 0.7165, "step": 12298 }, { "epoch": 0.7183995327102803, "grad_norm": 1.5944950580596924, "learning_rate": 3.880291510162633e-06, "loss": 0.8699, "step": 12299 }, { "epoch": 0.7184579439252337, "grad_norm": 1.4539225101470947, "learning_rate": 3.878795399161815e-06, "loss": 0.6509, "step": 12300 }, { "epoch": 0.718516355140187, "grad_norm": 1.3192864656448364, "learning_rate": 3.877299507242937e-06, "loss": 0.6541, "step": 12301 }, { "epoch": 0.7185747663551402, "grad_norm": 1.5603159666061401, "learning_rate": 3.875803834459532e-06, "loss": 0.7219, "step": 12302 }, { "epoch": 0.7186331775700935, "grad_norm": 1.0360785722732544, "learning_rate": 3.874308380865135e-06, "loss": 0.7457, "step": 12303 }, { "epoch": 0.7186915887850467, "grad_norm": 1.7039620876312256, "learning_rate": 3.872813146513272e-06, "loss": 0.7503, "step": 12304 }, { "epoch": 0.71875, "grad_norm": 1.9249953031539917, "learning_rate": 3.871318131457452e-06, "loss": 0.8314, "step": 12305 }, { "epoch": 0.7188084112149533, "grad_norm": 1.3241437673568726, "learning_rate": 3.86982333575119e-06, "loss": 0.6636, "step": 12306 }, { "epoch": 0.7188668224299065, "grad_norm": 1.088905930519104, "learning_rate": 3.86832875944798e-06, "loss": 0.6923, "step": 12307 }, { "epoch": 0.7189252336448598, "grad_norm": 2.520066261291504, "learning_rate": 3.86683440260131e-06, "loss": 0.5607, "step": 12308 }, { "epoch": 0.718983644859813, "grad_norm": 1.2996909618377686, "learning_rate": 3.865340265264674e-06, "loss": 0.7121, "step": 12309 }, { "epoch": 0.7190420560747663, "grad_norm": 1.2587465047836304, "learning_rate": 3.863846347491542e-06, "loss": 0.792, "step": 12310 }, { "epoch": 0.7191004672897197, "grad_norm": 1.151918888092041, "learning_rate": 3.862352649335387e-06, "loss": 0.8387, "step": 12311 }, { "epoch": 0.7191588785046729, "grad_norm": 1.0863839387893677, "learning_rate": 3.860859170849666e-06, "loss": 0.7048, "step": 12312 }, { "epoch": 0.7192172897196262, "grad_norm": 1.1083142757415771, "learning_rate": 3.859365912087828e-06, "loss": 0.5865, "step": 12313 }, { "epoch": 0.7192757009345795, "grad_norm": 1.0723931789398193, "learning_rate": 3.857872873103322e-06, "loss": 0.6923, "step": 12314 }, { "epoch": 0.7193341121495327, "grad_norm": 0.918401300907135, "learning_rate": 3.8563800539495845e-06, "loss": 0.8448, "step": 12315 }, { "epoch": 0.719392523364486, "grad_norm": 1.1009882688522339, "learning_rate": 3.854887454680048e-06, "loss": 0.6704, "step": 12316 }, { "epoch": 0.7194509345794392, "grad_norm": 1.1891189813613892, "learning_rate": 3.85339507534813e-06, "loss": 0.9469, "step": 12317 }, { "epoch": 0.7195093457943925, "grad_norm": 1.140757441520691, "learning_rate": 3.85190291600724e-06, "loss": 0.9863, "step": 12318 }, { "epoch": 0.7195677570093458, "grad_norm": 1.3730980157852173, "learning_rate": 3.850410976710786e-06, "loss": 0.7862, "step": 12319 }, { "epoch": 0.719626168224299, "grad_norm": 1.5430467128753662, "learning_rate": 3.848919257512172e-06, "loss": 0.7769, "step": 12320 }, { "epoch": 0.7196845794392523, "grad_norm": 1.5230967998504639, "learning_rate": 3.847427758464777e-06, "loss": 0.8023, "step": 12321 }, { "epoch": 0.7197429906542057, "grad_norm": 0.956375002861023, "learning_rate": 3.845936479621992e-06, "loss": 0.6574, "step": 12322 }, { "epoch": 0.7198014018691589, "grad_norm": 1.1767611503601074, "learning_rate": 3.844445421037184e-06, "loss": 0.7401, "step": 12323 }, { "epoch": 0.7198598130841122, "grad_norm": 1.341469645500183, "learning_rate": 3.8429545827637206e-06, "loss": 0.7543, "step": 12324 }, { "epoch": 0.7199182242990654, "grad_norm": 1.0934323072433472, "learning_rate": 3.841463964854966e-06, "loss": 0.7855, "step": 12325 }, { "epoch": 0.7199766355140187, "grad_norm": 1.097320318222046, "learning_rate": 3.839973567364261e-06, "loss": 0.7253, "step": 12326 }, { "epoch": 0.720035046728972, "grad_norm": 1.738193154335022, "learning_rate": 3.838483390344955e-06, "loss": 0.7509, "step": 12327 }, { "epoch": 0.7200934579439252, "grad_norm": 1.0780308246612549, "learning_rate": 3.836993433850377e-06, "loss": 0.803, "step": 12328 }, { "epoch": 0.7201518691588785, "grad_norm": 1.5212453603744507, "learning_rate": 3.83550369793386e-06, "loss": 0.9749, "step": 12329 }, { "epoch": 0.7202102803738317, "grad_norm": 1.3581262826919556, "learning_rate": 3.8340141826487155e-06, "loss": 0.6398, "step": 12330 }, { "epoch": 0.720268691588785, "grad_norm": 1.814185380935669, "learning_rate": 3.832524888048257e-06, "loss": 0.7122, "step": 12331 }, { "epoch": 0.7203271028037384, "grad_norm": 0.9062609076499939, "learning_rate": 3.8310358141857915e-06, "loss": 0.657, "step": 12332 }, { "epoch": 0.7203855140186916, "grad_norm": 1.582258701324463, "learning_rate": 3.829546961114608e-06, "loss": 0.712, "step": 12333 }, { "epoch": 0.7204439252336449, "grad_norm": 1.0556690692901611, "learning_rate": 3.828058328887998e-06, "loss": 0.7118, "step": 12334 }, { "epoch": 0.7205023364485982, "grad_norm": 1.2485872507095337, "learning_rate": 3.826569917559235e-06, "loss": 0.7919, "step": 12335 }, { "epoch": 0.7205607476635514, "grad_norm": 1.2376796007156372, "learning_rate": 3.825081727181594e-06, "loss": 0.7377, "step": 12336 }, { "epoch": 0.7206191588785047, "grad_norm": 1.0916575193405151, "learning_rate": 3.823593757808342e-06, "loss": 0.6905, "step": 12337 }, { "epoch": 0.7206775700934579, "grad_norm": 1.0585732460021973, "learning_rate": 3.822106009492728e-06, "loss": 0.734, "step": 12338 }, { "epoch": 0.7207359813084112, "grad_norm": 1.388271689414978, "learning_rate": 3.820618482288004e-06, "loss": 0.8, "step": 12339 }, { "epoch": 0.7207943925233645, "grad_norm": 1.0061533451080322, "learning_rate": 3.819131176247408e-06, "loss": 0.8664, "step": 12340 }, { "epoch": 0.7208528037383177, "grad_norm": 1.0962666273117065, "learning_rate": 3.817644091424164e-06, "loss": 0.8153, "step": 12341 }, { "epoch": 0.720911214953271, "grad_norm": 0.8811531066894531, "learning_rate": 3.81615722787151e-06, "loss": 0.7647, "step": 12342 }, { "epoch": 0.7209696261682244, "grad_norm": 1.2809325456619263, "learning_rate": 3.8146705856426515e-06, "loss": 0.699, "step": 12343 }, { "epoch": 0.7210280373831776, "grad_norm": 0.8832541108131409, "learning_rate": 3.813184164790803e-06, "loss": 0.6669, "step": 12344 }, { "epoch": 0.7210864485981309, "grad_norm": 1.1562104225158691, "learning_rate": 3.811697965369161e-06, "loss": 0.7454, "step": 12345 }, { "epoch": 0.7211448598130841, "grad_norm": 0.999866783618927, "learning_rate": 3.810211987430914e-06, "loss": 0.7616, "step": 12346 }, { "epoch": 0.7212032710280374, "grad_norm": 1.3944228887557983, "learning_rate": 3.8087262310292506e-06, "loss": 0.9945, "step": 12347 }, { "epoch": 0.7212616822429907, "grad_norm": 1.3873398303985596, "learning_rate": 3.8072406962173457e-06, "loss": 0.7431, "step": 12348 }, { "epoch": 0.7213200934579439, "grad_norm": 1.335125207901001, "learning_rate": 3.8057553830483716e-06, "loss": 0.6238, "step": 12349 }, { "epoch": 0.7213785046728972, "grad_norm": 1.6164785623550415, "learning_rate": 3.8042702915754857e-06, "loss": 0.8756, "step": 12350 }, { "epoch": 0.7214369158878504, "grad_norm": 1.5627498626708984, "learning_rate": 3.802785421851836e-06, "loss": 0.7546, "step": 12351 }, { "epoch": 0.7214953271028037, "grad_norm": 1.1250762939453125, "learning_rate": 3.801300773930571e-06, "loss": 0.7099, "step": 12352 }, { "epoch": 0.721553738317757, "grad_norm": 1.6933308839797974, "learning_rate": 3.7998163478648263e-06, "loss": 0.7682, "step": 12353 }, { "epoch": 0.7216121495327102, "grad_norm": 1.155335545539856, "learning_rate": 3.798332143707735e-06, "loss": 0.8417, "step": 12354 }, { "epoch": 0.7216705607476636, "grad_norm": 1.2429760694503784, "learning_rate": 3.796848161512414e-06, "loss": 0.6904, "step": 12355 }, { "epoch": 0.7217289719626169, "grad_norm": 1.0422993898391724, "learning_rate": 3.795364401331972e-06, "loss": 0.8578, "step": 12356 }, { "epoch": 0.7217873831775701, "grad_norm": 1.1089835166931152, "learning_rate": 3.793880863219519e-06, "loss": 0.8527, "step": 12357 }, { "epoch": 0.7218457943925234, "grad_norm": 1.5098254680633545, "learning_rate": 3.792397547228149e-06, "loss": 0.8637, "step": 12358 }, { "epoch": 0.7219042056074766, "grad_norm": 1.4616831541061401, "learning_rate": 3.7909144534109577e-06, "loss": 0.9613, "step": 12359 }, { "epoch": 0.7219626168224299, "grad_norm": 1.1222821474075317, "learning_rate": 3.789431581821019e-06, "loss": 0.7949, "step": 12360 }, { "epoch": 0.7220210280373832, "grad_norm": 1.0344927310943604, "learning_rate": 3.787948932511405e-06, "loss": 0.8414, "step": 12361 }, { "epoch": 0.7220794392523364, "grad_norm": 1.22407066822052, "learning_rate": 3.7864665055351855e-06, "loss": 0.6964, "step": 12362 }, { "epoch": 0.7221378504672897, "grad_norm": 1.0730842351913452, "learning_rate": 3.7849843009454133e-06, "loss": 0.5894, "step": 12363 }, { "epoch": 0.722196261682243, "grad_norm": 1.7117083072662354, "learning_rate": 3.7835023187951382e-06, "loss": 0.7533, "step": 12364 }, { "epoch": 0.7222546728971962, "grad_norm": 1.1980350017547607, "learning_rate": 3.782020559137407e-06, "loss": 0.6892, "step": 12365 }, { "epoch": 0.7223130841121496, "grad_norm": 1.3340816497802734, "learning_rate": 3.7805390220252445e-06, "loss": 0.7685, "step": 12366 }, { "epoch": 0.7223714953271028, "grad_norm": 1.3733766078948975, "learning_rate": 3.779057707511683e-06, "loss": 0.7531, "step": 12367 }, { "epoch": 0.7224299065420561, "grad_norm": 1.0962716341018677, "learning_rate": 3.7775766156497327e-06, "loss": 0.772, "step": 12368 }, { "epoch": 0.7224883177570094, "grad_norm": 0.9415647387504578, "learning_rate": 3.7760957464924075e-06, "loss": 0.8604, "step": 12369 }, { "epoch": 0.7225467289719626, "grad_norm": 1.2592264413833618, "learning_rate": 3.774615100092711e-06, "loss": 0.7184, "step": 12370 }, { "epoch": 0.7226051401869159, "grad_norm": 2.0703086853027344, "learning_rate": 3.773134676503629e-06, "loss": 0.7957, "step": 12371 }, { "epoch": 0.7226635514018691, "grad_norm": 1.2288247346878052, "learning_rate": 3.771654475778156e-06, "loss": 0.8361, "step": 12372 }, { "epoch": 0.7227219626168224, "grad_norm": 1.6698068380355835, "learning_rate": 3.7701744979692645e-06, "loss": 0.7777, "step": 12373 }, { "epoch": 0.7227803738317757, "grad_norm": 1.087721586227417, "learning_rate": 3.768694743129916e-06, "loss": 0.6795, "step": 12374 }, { "epoch": 0.7228387850467289, "grad_norm": 1.6532654762268066, "learning_rate": 3.7672152113130866e-06, "loss": 0.7628, "step": 12375 }, { "epoch": 0.7228971962616823, "grad_norm": 1.1457005739212036, "learning_rate": 3.765735902571721e-06, "loss": 0.8064, "step": 12376 }, { "epoch": 0.7229556074766356, "grad_norm": 1.8565058708190918, "learning_rate": 3.764256816958769e-06, "loss": 0.8399, "step": 12377 }, { "epoch": 0.7230140186915888, "grad_norm": 2.3712711334228516, "learning_rate": 3.762777954527166e-06, "loss": 0.8033, "step": 12378 }, { "epoch": 0.7230724299065421, "grad_norm": 1.2322840690612793, "learning_rate": 3.761299315329836e-06, "loss": 0.8571, "step": 12379 }, { "epoch": 0.7231308411214953, "grad_norm": 1.5658849477767944, "learning_rate": 3.759820899419707e-06, "loss": 0.8117, "step": 12380 }, { "epoch": 0.7231892523364486, "grad_norm": 1.6837575435638428, "learning_rate": 3.7583427068496916e-06, "loss": 0.9186, "step": 12381 }, { "epoch": 0.7232476635514019, "grad_norm": 1.269318699836731, "learning_rate": 3.7568647376726973e-06, "loss": 0.7942, "step": 12382 }, { "epoch": 0.7233060747663551, "grad_norm": 1.1832371950149536, "learning_rate": 3.7553869919416186e-06, "loss": 0.8564, "step": 12383 }, { "epoch": 0.7233644859813084, "grad_norm": 1.6189452409744263, "learning_rate": 3.7539094697093424e-06, "loss": 0.8214, "step": 12384 }, { "epoch": 0.7234228971962616, "grad_norm": 1.486798644065857, "learning_rate": 3.7524321710287527e-06, "loss": 0.8231, "step": 12385 }, { "epoch": 0.7234813084112149, "grad_norm": 1.0537655353546143, "learning_rate": 3.750955095952724e-06, "loss": 0.7692, "step": 12386 }, { "epoch": 0.7235397196261683, "grad_norm": 1.12092924118042, "learning_rate": 3.7494782445341247e-06, "loss": 0.7007, "step": 12387 }, { "epoch": 0.7235981308411215, "grad_norm": 1.4921860694885254, "learning_rate": 3.7480016168258083e-06, "loss": 0.9182, "step": 12388 }, { "epoch": 0.7236565420560748, "grad_norm": 1.271177887916565, "learning_rate": 3.7465252128806216e-06, "loss": 0.8746, "step": 12389 }, { "epoch": 0.7237149532710281, "grad_norm": 1.3145601749420166, "learning_rate": 3.74504903275141e-06, "loss": 0.8783, "step": 12390 }, { "epoch": 0.7237733644859813, "grad_norm": 1.0242668390274048, "learning_rate": 3.743573076491005e-06, "loss": 0.6028, "step": 12391 }, { "epoch": 0.7238317757009346, "grad_norm": 1.1517939567565918, "learning_rate": 3.742097344152238e-06, "loss": 0.7252, "step": 12392 }, { "epoch": 0.7238901869158878, "grad_norm": 1.102673888206482, "learning_rate": 3.740621835787921e-06, "loss": 0.7581, "step": 12393 }, { "epoch": 0.7239485981308411, "grad_norm": 1.335969090461731, "learning_rate": 3.7391465514508607e-06, "loss": 0.8107, "step": 12394 }, { "epoch": 0.7240070093457944, "grad_norm": 1.2265830039978027, "learning_rate": 3.737671491193865e-06, "loss": 0.7601, "step": 12395 }, { "epoch": 0.7240654205607476, "grad_norm": 1.439490556716919, "learning_rate": 3.7361966550697216e-06, "loss": 0.7875, "step": 12396 }, { "epoch": 0.7241238317757009, "grad_norm": 0.9997532367706299, "learning_rate": 3.734722043131218e-06, "loss": 0.7209, "step": 12397 }, { "epoch": 0.7241822429906543, "grad_norm": 1.4674298763275146, "learning_rate": 3.733247655431135e-06, "loss": 0.89, "step": 12398 }, { "epoch": 0.7242406542056075, "grad_norm": 1.4422366619110107, "learning_rate": 3.731773492022236e-06, "loss": 0.7593, "step": 12399 }, { "epoch": 0.7242990654205608, "grad_norm": 1.2943049669265747, "learning_rate": 3.7302995529572884e-06, "loss": 0.7023, "step": 12400 }, { "epoch": 0.724357476635514, "grad_norm": 1.124636173248291, "learning_rate": 3.7288258382890387e-06, "loss": 0.6404, "step": 12401 }, { "epoch": 0.7244158878504673, "grad_norm": 1.3881347179412842, "learning_rate": 3.7273523480702356e-06, "loss": 0.7607, "step": 12402 }, { "epoch": 0.7244742990654206, "grad_norm": 1.4096139669418335, "learning_rate": 3.7258790823536205e-06, "loss": 0.7328, "step": 12403 }, { "epoch": 0.7245327102803738, "grad_norm": 1.1910300254821777, "learning_rate": 3.7244060411919136e-06, "loss": 0.6761, "step": 12404 }, { "epoch": 0.7245911214953271, "grad_norm": 1.369959831237793, "learning_rate": 3.7229332246378457e-06, "loss": 0.6849, "step": 12405 }, { "epoch": 0.7246495327102803, "grad_norm": 1.3259955644607544, "learning_rate": 3.7214606327441203e-06, "loss": 0.8308, "step": 12406 }, { "epoch": 0.7247079439252336, "grad_norm": 1.1687099933624268, "learning_rate": 3.7199882655634476e-06, "loss": 0.6302, "step": 12407 }, { "epoch": 0.724766355140187, "grad_norm": 1.0323302745819092, "learning_rate": 3.7185161231485266e-06, "loss": 0.6976, "step": 12408 }, { "epoch": 0.7248247663551401, "grad_norm": 1.2134277820587158, "learning_rate": 3.7170442055520418e-06, "loss": 0.6596, "step": 12409 }, { "epoch": 0.7248831775700935, "grad_norm": 2.033489465713501, "learning_rate": 3.7155725128266786e-06, "loss": 0.7651, "step": 12410 }, { "epoch": 0.7249415887850468, "grad_norm": 0.9285220503807068, "learning_rate": 3.7141010450251035e-06, "loss": 0.7669, "step": 12411 }, { "epoch": 0.725, "grad_norm": 1.1717219352722168, "learning_rate": 3.7126298021999897e-06, "loss": 0.8345, "step": 12412 }, { "epoch": 0.7250584112149533, "grad_norm": 1.0170563459396362, "learning_rate": 3.7111587844039845e-06, "loss": 0.7421, "step": 12413 }, { "epoch": 0.7251168224299065, "grad_norm": 0.9758273959159851, "learning_rate": 3.7096879916897423e-06, "loss": 0.8239, "step": 12414 }, { "epoch": 0.7251752336448598, "grad_norm": 1.019814133644104, "learning_rate": 3.7082174241099055e-06, "loss": 0.7609, "step": 12415 }, { "epoch": 0.7252336448598131, "grad_norm": 0.9185499548912048, "learning_rate": 3.7067470817171015e-06, "loss": 0.7715, "step": 12416 }, { "epoch": 0.7252920560747663, "grad_norm": 1.158780574798584, "learning_rate": 3.70527696456396e-06, "loss": 0.7357, "step": 12417 }, { "epoch": 0.7253504672897196, "grad_norm": 2.1326541900634766, "learning_rate": 3.703807072703092e-06, "loss": 0.9028, "step": 12418 }, { "epoch": 0.725408878504673, "grad_norm": 0.9833248257637024, "learning_rate": 3.7023374061871075e-06, "loss": 0.7691, "step": 12419 }, { "epoch": 0.7254672897196262, "grad_norm": 1.6496113538742065, "learning_rate": 3.7008679650686132e-06, "loss": 0.8077, "step": 12420 }, { "epoch": 0.7255257009345795, "grad_norm": 1.04755437374115, "learning_rate": 3.6993987494001914e-06, "loss": 0.7628, "step": 12421 }, { "epoch": 0.7255841121495327, "grad_norm": 1.0323033332824707, "learning_rate": 3.6979297592344353e-06, "loss": 0.7311, "step": 12422 }, { "epoch": 0.725642523364486, "grad_norm": 0.8786536455154419, "learning_rate": 3.696460994623913e-06, "loss": 0.7098, "step": 12423 }, { "epoch": 0.7257009345794393, "grad_norm": 1.5199861526489258, "learning_rate": 3.694992455621196e-06, "loss": 0.7818, "step": 12424 }, { "epoch": 0.7257593457943925, "grad_norm": 1.7386133670806885, "learning_rate": 3.693524142278849e-06, "loss": 0.7311, "step": 12425 }, { "epoch": 0.7258177570093458, "grad_norm": 1.1324684619903564, "learning_rate": 3.6920560546494153e-06, "loss": 0.8606, "step": 12426 }, { "epoch": 0.725876168224299, "grad_norm": 1.2554068565368652, "learning_rate": 3.690588192785447e-06, "loss": 1.0342, "step": 12427 }, { "epoch": 0.7259345794392523, "grad_norm": 1.4718037843704224, "learning_rate": 3.689120556739475e-06, "loss": 0.8773, "step": 12428 }, { "epoch": 0.7259929906542056, "grad_norm": 1.0653132200241089, "learning_rate": 3.687653146564025e-06, "loss": 0.8284, "step": 12429 }, { "epoch": 0.7260514018691588, "grad_norm": 1.2786865234375, "learning_rate": 3.6861859623116193e-06, "loss": 0.8152, "step": 12430 }, { "epoch": 0.7261098130841122, "grad_norm": 1.2733252048492432, "learning_rate": 3.6847190040347724e-06, "loss": 0.7242, "step": 12431 }, { "epoch": 0.7261682242990655, "grad_norm": 1.234614610671997, "learning_rate": 3.683252271785982e-06, "loss": 0.8167, "step": 12432 }, { "epoch": 0.7262266355140187, "grad_norm": 1.0728493928909302, "learning_rate": 3.681785765617749e-06, "loss": 0.7894, "step": 12433 }, { "epoch": 0.726285046728972, "grad_norm": 1.341677188873291, "learning_rate": 3.680319485582554e-06, "loss": 0.7123, "step": 12434 }, { "epoch": 0.7263434579439252, "grad_norm": 1.5604039430618286, "learning_rate": 3.6788534317328806e-06, "loss": 0.7848, "step": 12435 }, { "epoch": 0.7264018691588785, "grad_norm": 1.0651713609695435, "learning_rate": 3.6773876041212033e-06, "loss": 0.8246, "step": 12436 }, { "epoch": 0.7264602803738318, "grad_norm": 1.1756045818328857, "learning_rate": 3.6759220027999754e-06, "loss": 0.7396, "step": 12437 }, { "epoch": 0.726518691588785, "grad_norm": 0.9635664820671082, "learning_rate": 3.674456627821662e-06, "loss": 0.632, "step": 12438 }, { "epoch": 0.7265771028037383, "grad_norm": 1.1560547351837158, "learning_rate": 3.672991479238701e-06, "loss": 0.6977, "step": 12439 }, { "epoch": 0.7266355140186916, "grad_norm": 1.5432085990905762, "learning_rate": 3.6715265571035354e-06, "loss": 0.8063, "step": 12440 }, { "epoch": 0.7266939252336448, "grad_norm": 1.205406665802002, "learning_rate": 3.670061861468599e-06, "loss": 0.7718, "step": 12441 }, { "epoch": 0.7267523364485982, "grad_norm": 1.1619354486465454, "learning_rate": 3.668597392386306e-06, "loss": 0.858, "step": 12442 }, { "epoch": 0.7268107476635514, "grad_norm": 1.3287899494171143, "learning_rate": 3.66713314990908e-06, "loss": 0.711, "step": 12443 }, { "epoch": 0.7268691588785047, "grad_norm": 1.1447252035140991, "learning_rate": 3.665669134089319e-06, "loss": 0.7496, "step": 12444 }, { "epoch": 0.726927570093458, "grad_norm": 1.2781038284301758, "learning_rate": 3.664205344979428e-06, "loss": 0.9189, "step": 12445 }, { "epoch": 0.7269859813084112, "grad_norm": 1.473402976989746, "learning_rate": 3.662741782631789e-06, "loss": 0.6947, "step": 12446 }, { "epoch": 0.7270443925233645, "grad_norm": 1.161302924156189, "learning_rate": 3.6612784470987893e-06, "loss": 0.777, "step": 12447 }, { "epoch": 0.7271028037383177, "grad_norm": 1.2724016904830933, "learning_rate": 3.659815338432805e-06, "loss": 0.7694, "step": 12448 }, { "epoch": 0.727161214953271, "grad_norm": 1.154464840888977, "learning_rate": 3.658352456686196e-06, "loss": 0.6708, "step": 12449 }, { "epoch": 0.7272196261682243, "grad_norm": 1.062194585800171, "learning_rate": 3.6568898019113243e-06, "loss": 0.6219, "step": 12450 }, { "epoch": 0.7272780373831775, "grad_norm": 1.0561176538467407, "learning_rate": 3.655427374160535e-06, "loss": 0.7191, "step": 12451 }, { "epoch": 0.7273364485981308, "grad_norm": 0.9463967680931091, "learning_rate": 3.6539651734861705e-06, "loss": 0.7663, "step": 12452 }, { "epoch": 0.7273948598130842, "grad_norm": 1.4020336866378784, "learning_rate": 3.652503199940569e-06, "loss": 0.8175, "step": 12453 }, { "epoch": 0.7274532710280374, "grad_norm": 1.0335782766342163, "learning_rate": 3.6510414535760487e-06, "loss": 0.8247, "step": 12454 }, { "epoch": 0.7275116822429907, "grad_norm": 1.0749096870422363, "learning_rate": 3.6495799344449325e-06, "loss": 0.8473, "step": 12455 }, { "epoch": 0.7275700934579439, "grad_norm": 1.3798682689666748, "learning_rate": 3.648118642599522e-06, "loss": 0.8684, "step": 12456 }, { "epoch": 0.7276285046728972, "grad_norm": 0.8984421491622925, "learning_rate": 3.646657578092121e-06, "loss": 0.7507, "step": 12457 }, { "epoch": 0.7276869158878505, "grad_norm": 1.0766080617904663, "learning_rate": 3.6451967409750276e-06, "loss": 0.7951, "step": 12458 }, { "epoch": 0.7277453271028037, "grad_norm": 2.4632768630981445, "learning_rate": 3.643736131300517e-06, "loss": 0.7956, "step": 12459 }, { "epoch": 0.727803738317757, "grad_norm": 0.817592203617096, "learning_rate": 3.6422757491208727e-06, "loss": 0.7946, "step": 12460 }, { "epoch": 0.7278621495327103, "grad_norm": 1.3462101221084595, "learning_rate": 3.6408155944883606e-06, "loss": 0.7181, "step": 12461 }, { "epoch": 0.7279205607476635, "grad_norm": 1.016684651374817, "learning_rate": 3.6393556674552354e-06, "loss": 0.73, "step": 12462 }, { "epoch": 0.7279789719626168, "grad_norm": 1.2097115516662598, "learning_rate": 3.6378959680737534e-06, "loss": 0.9961, "step": 12463 }, { "epoch": 0.72803738317757, "grad_norm": 1.412001609802246, "learning_rate": 3.6364364963961584e-06, "loss": 0.7561, "step": 12464 }, { "epoch": 0.7280957943925234, "grad_norm": 1.1244349479675293, "learning_rate": 3.6349772524746874e-06, "loss": 0.7547, "step": 12465 }, { "epoch": 0.7281542056074767, "grad_norm": 1.0005840063095093, "learning_rate": 3.633518236361567e-06, "loss": 0.8267, "step": 12466 }, { "epoch": 0.7282126168224299, "grad_norm": 1.4885176420211792, "learning_rate": 3.632059448109011e-06, "loss": 0.8719, "step": 12467 }, { "epoch": 0.7282710280373832, "grad_norm": 0.9716853499412537, "learning_rate": 3.6306008877692346e-06, "loss": 0.7234, "step": 12468 }, { "epoch": 0.7283294392523364, "grad_norm": 1.4136557579040527, "learning_rate": 3.629142555394439e-06, "loss": 0.7862, "step": 12469 }, { "epoch": 0.7283878504672897, "grad_norm": 3.6085474491119385, "learning_rate": 3.627684451036826e-06, "loss": 0.8855, "step": 12470 }, { "epoch": 0.728446261682243, "grad_norm": 1.361018180847168, "learning_rate": 3.626226574748575e-06, "loss": 0.8276, "step": 12471 }, { "epoch": 0.7285046728971962, "grad_norm": 1.3829691410064697, "learning_rate": 3.624768926581862e-06, "loss": 0.7157, "step": 12472 }, { "epoch": 0.7285630841121495, "grad_norm": 1.2482353448867798, "learning_rate": 3.6233115065888612e-06, "loss": 0.6238, "step": 12473 }, { "epoch": 0.7286214953271029, "grad_norm": 2.004814863204956, "learning_rate": 3.6218543148217343e-06, "loss": 0.896, "step": 12474 }, { "epoch": 0.728679906542056, "grad_norm": 1.4254158735275269, "learning_rate": 3.6203973513326395e-06, "loss": 0.747, "step": 12475 }, { "epoch": 0.7287383177570094, "grad_norm": 1.0661672353744507, "learning_rate": 3.6189406161737173e-06, "loss": 0.7972, "step": 12476 }, { "epoch": 0.7287967289719626, "grad_norm": 0.959356963634491, "learning_rate": 3.6174841093971025e-06, "loss": 0.6245, "step": 12477 }, { "epoch": 0.7288551401869159, "grad_norm": 1.8957973718643188, "learning_rate": 3.6160278310549322e-06, "loss": 0.8438, "step": 12478 }, { "epoch": 0.7289135514018692, "grad_norm": 0.8986909985542297, "learning_rate": 3.6145717811993197e-06, "loss": 0.5976, "step": 12479 }, { "epoch": 0.7289719626168224, "grad_norm": 0.821483314037323, "learning_rate": 3.6131159598823806e-06, "loss": 0.567, "step": 12480 }, { "epoch": 0.7290303738317757, "grad_norm": 1.3027774095535278, "learning_rate": 3.6116603671562255e-06, "loss": 0.8791, "step": 12481 }, { "epoch": 0.729088785046729, "grad_norm": 1.5874446630477905, "learning_rate": 3.610205003072942e-06, "loss": 0.5645, "step": 12482 }, { "epoch": 0.7291471962616822, "grad_norm": 1.31226646900177, "learning_rate": 3.6087498676846267e-06, "loss": 0.7466, "step": 12483 }, { "epoch": 0.7292056074766355, "grad_norm": 1.055019736289978, "learning_rate": 3.607294961043353e-06, "loss": 0.6604, "step": 12484 }, { "epoch": 0.7292640186915887, "grad_norm": 1.917353630065918, "learning_rate": 3.6058402832011953e-06, "loss": 0.7589, "step": 12485 }, { "epoch": 0.7293224299065421, "grad_norm": 1.6881183385849, "learning_rate": 3.604385834210221e-06, "loss": 0.7377, "step": 12486 }, { "epoch": 0.7293808411214954, "grad_norm": 1.7627190351486206, "learning_rate": 3.60293161412248e-06, "loss": 0.7746, "step": 12487 }, { "epoch": 0.7294392523364486, "grad_norm": 1.2117453813552856, "learning_rate": 3.601477622990026e-06, "loss": 0.8247, "step": 12488 }, { "epoch": 0.7294976635514019, "grad_norm": 1.4838727712631226, "learning_rate": 3.6000238608648918e-06, "loss": 0.6169, "step": 12489 }, { "epoch": 0.7295560747663551, "grad_norm": 1.3385220766067505, "learning_rate": 3.5985703277991123e-06, "loss": 0.6646, "step": 12490 }, { "epoch": 0.7296144859813084, "grad_norm": 1.014504075050354, "learning_rate": 3.5971170238447128e-06, "loss": 0.7572, "step": 12491 }, { "epoch": 0.7296728971962617, "grad_norm": 1.7289516925811768, "learning_rate": 3.5956639490537003e-06, "loss": 0.9394, "step": 12492 }, { "epoch": 0.7297313084112149, "grad_norm": 1.3244858980178833, "learning_rate": 3.594211103478091e-06, "loss": 0.75, "step": 12493 }, { "epoch": 0.7297897196261682, "grad_norm": 1.362000823020935, "learning_rate": 3.592758487169877e-06, "loss": 0.56, "step": 12494 }, { "epoch": 0.7298481308411215, "grad_norm": 0.9182769656181335, "learning_rate": 3.5913061001810477e-06, "loss": 0.6203, "step": 12495 }, { "epoch": 0.7299065420560747, "grad_norm": 1.42601478099823, "learning_rate": 3.589853942563586e-06, "loss": 0.785, "step": 12496 }, { "epoch": 0.7299649532710281, "grad_norm": 1.0356892347335815, "learning_rate": 3.5884020143694666e-06, "loss": 0.8463, "step": 12497 }, { "epoch": 0.7300233644859813, "grad_norm": 1.2456331253051758, "learning_rate": 3.586950315650658e-06, "loss": 0.9488, "step": 12498 }, { "epoch": 0.7300817757009346, "grad_norm": 1.3274065256118774, "learning_rate": 3.5854988464591144e-06, "loss": 0.8896, "step": 12499 }, { "epoch": 0.7301401869158879, "grad_norm": 1.0840086936950684, "learning_rate": 3.584047606846781e-06, "loss": 0.6254, "step": 12500 }, { "epoch": 0.7301985981308411, "grad_norm": 1.1757150888442993, "learning_rate": 3.5825965968656018e-06, "loss": 0.7329, "step": 12501 }, { "epoch": 0.7302570093457944, "grad_norm": 1.2380303144454956, "learning_rate": 3.5811458165675105e-06, "loss": 0.8214, "step": 12502 }, { "epoch": 0.7303154205607477, "grad_norm": 2.1923232078552246, "learning_rate": 3.579695266004435e-06, "loss": 1.045, "step": 12503 }, { "epoch": 0.7303738317757009, "grad_norm": 1.2042236328125, "learning_rate": 3.578244945228286e-06, "loss": 0.7592, "step": 12504 }, { "epoch": 0.7304322429906542, "grad_norm": 1.7361907958984375, "learning_rate": 3.5767948542909715e-06, "loss": 0.6243, "step": 12505 }, { "epoch": 0.7304906542056074, "grad_norm": 1.4208869934082031, "learning_rate": 3.5753449932443905e-06, "loss": 0.8513, "step": 12506 }, { "epoch": 0.7305490654205608, "grad_norm": 0.9429603219032288, "learning_rate": 3.573895362140437e-06, "loss": 0.9289, "step": 12507 }, { "epoch": 0.7306074766355141, "grad_norm": 0.8516732454299927, "learning_rate": 3.572445961030998e-06, "loss": 0.4985, "step": 12508 }, { "epoch": 0.7306658878504673, "grad_norm": 1.8626372814178467, "learning_rate": 3.5709967899679434e-06, "loss": 0.6516, "step": 12509 }, { "epoch": 0.7307242990654206, "grad_norm": 1.9089521169662476, "learning_rate": 3.5695478490031375e-06, "loss": 0.8793, "step": 12510 }, { "epoch": 0.7307827102803738, "grad_norm": 1.2383543252944946, "learning_rate": 3.5680991381884456e-06, "loss": 0.731, "step": 12511 }, { "epoch": 0.7308411214953271, "grad_norm": 0.9228642582893372, "learning_rate": 3.566650657575712e-06, "loss": 0.4966, "step": 12512 }, { "epoch": 0.7308995327102804, "grad_norm": 1.7153654098510742, "learning_rate": 3.56520240721678e-06, "loss": 0.5654, "step": 12513 }, { "epoch": 0.7309579439252336, "grad_norm": 1.1804307699203491, "learning_rate": 3.5637543871634895e-06, "loss": 0.8696, "step": 12514 }, { "epoch": 0.7310163551401869, "grad_norm": 1.4573192596435547, "learning_rate": 3.5623065974676573e-06, "loss": 0.7024, "step": 12515 }, { "epoch": 0.7310747663551402, "grad_norm": 0.9037908911705017, "learning_rate": 3.5608590381811083e-06, "loss": 0.6892, "step": 12516 }, { "epoch": 0.7311331775700934, "grad_norm": 1.08683443069458, "learning_rate": 3.5594117093556448e-06, "loss": 0.7113, "step": 12517 }, { "epoch": 0.7311915887850468, "grad_norm": 1.3424268960952759, "learning_rate": 3.557964611043071e-06, "loss": 0.6636, "step": 12518 }, { "epoch": 0.73125, "grad_norm": 0.9736259579658508, "learning_rate": 3.5565177432951824e-06, "loss": 0.7545, "step": 12519 }, { "epoch": 0.7313084112149533, "grad_norm": 1.6084212064743042, "learning_rate": 3.555071106163758e-06, "loss": 0.752, "step": 12520 }, { "epoch": 0.7313668224299066, "grad_norm": 1.4354702234268188, "learning_rate": 3.5536246997005785e-06, "loss": 0.7634, "step": 12521 }, { "epoch": 0.7314252336448598, "grad_norm": 1.0351965427398682, "learning_rate": 3.552178523957407e-06, "loss": 0.7322, "step": 12522 }, { "epoch": 0.7314836448598131, "grad_norm": 0.9794294238090515, "learning_rate": 3.550732578986006e-06, "loss": 0.5997, "step": 12523 }, { "epoch": 0.7315420560747663, "grad_norm": 1.100829839706421, "learning_rate": 3.5492868648381296e-06, "loss": 0.6901, "step": 12524 }, { "epoch": 0.7316004672897196, "grad_norm": 0.9228979349136353, "learning_rate": 3.5478413815655146e-06, "loss": 0.7689, "step": 12525 }, { "epoch": 0.7316588785046729, "grad_norm": 1.005473256111145, "learning_rate": 3.546396129219901e-06, "loss": 0.7888, "step": 12526 }, { "epoch": 0.7317172897196261, "grad_norm": 1.4052664041519165, "learning_rate": 3.5449511078530106e-06, "loss": 0.7865, "step": 12527 }, { "epoch": 0.7317757009345794, "grad_norm": 1.082990288734436, "learning_rate": 3.5435063175165685e-06, "loss": 0.775, "step": 12528 }, { "epoch": 0.7318341121495328, "grad_norm": 1.316365361213684, "learning_rate": 3.5420617582622765e-06, "loss": 0.7213, "step": 12529 }, { "epoch": 0.731892523364486, "grad_norm": 1.2418649196624756, "learning_rate": 3.5406174301418407e-06, "loss": 0.704, "step": 12530 }, { "epoch": 0.7319509345794393, "grad_norm": 1.021619439125061, "learning_rate": 3.5391733332069565e-06, "loss": 0.8563, "step": 12531 }, { "epoch": 0.7320093457943925, "grad_norm": 0.9020920991897583, "learning_rate": 3.5377294675093043e-06, "loss": 0.7775, "step": 12532 }, { "epoch": 0.7320677570093458, "grad_norm": 0.9814605712890625, "learning_rate": 3.5362858331005666e-06, "loss": 0.6412, "step": 12533 }, { "epoch": 0.7321261682242991, "grad_norm": 1.3413804769515991, "learning_rate": 3.5348424300324058e-06, "loss": 0.7793, "step": 12534 }, { "epoch": 0.7321845794392523, "grad_norm": 3.0493671894073486, "learning_rate": 3.533399258356485e-06, "loss": 0.8768, "step": 12535 }, { "epoch": 0.7322429906542056, "grad_norm": 1.1823121309280396, "learning_rate": 3.53195631812446e-06, "loss": 0.6977, "step": 12536 }, { "epoch": 0.7323014018691589, "grad_norm": 2.0223891735076904, "learning_rate": 3.5305136093879687e-06, "loss": 0.661, "step": 12537 }, { "epoch": 0.7323598130841121, "grad_norm": 0.8841942548751831, "learning_rate": 3.5290711321986514e-06, "loss": 0.622, "step": 12538 }, { "epoch": 0.7324182242990654, "grad_norm": 1.0221563577651978, "learning_rate": 3.5276288866081297e-06, "loss": 0.6401, "step": 12539 }, { "epoch": 0.7324766355140186, "grad_norm": 1.0968724489212036, "learning_rate": 3.526186872668026e-06, "loss": 0.857, "step": 12540 }, { "epoch": 0.732535046728972, "grad_norm": 1.3129687309265137, "learning_rate": 3.524745090429955e-06, "loss": 0.9333, "step": 12541 }, { "epoch": 0.7325934579439253, "grad_norm": 1.0821070671081543, "learning_rate": 3.5233035399455107e-06, "loss": 0.7143, "step": 12542 }, { "epoch": 0.7326518691588785, "grad_norm": 1.1435966491699219, "learning_rate": 3.5218622212662946e-06, "loss": 0.8886, "step": 12543 }, { "epoch": 0.7327102803738318, "grad_norm": 1.2319254875183105, "learning_rate": 3.520421134443889e-06, "loss": 0.7302, "step": 12544 }, { "epoch": 0.732768691588785, "grad_norm": 1.2608890533447266, "learning_rate": 3.5189802795298676e-06, "loss": 0.8622, "step": 12545 }, { "epoch": 0.7328271028037383, "grad_norm": 1.2467454671859741, "learning_rate": 3.5175396565758037e-06, "loss": 0.6859, "step": 12546 }, { "epoch": 0.7328855140186916, "grad_norm": 1.2457643747329712, "learning_rate": 3.5160992656332616e-06, "loss": 0.7334, "step": 12547 }, { "epoch": 0.7329439252336448, "grad_norm": 1.2598717212677002, "learning_rate": 3.514659106753786e-06, "loss": 0.717, "step": 12548 }, { "epoch": 0.7330023364485981, "grad_norm": 1.0714211463928223, "learning_rate": 3.5132191799889282e-06, "loss": 0.7475, "step": 12549 }, { "epoch": 0.7330607476635514, "grad_norm": 2.063464879989624, "learning_rate": 3.5117794853902188e-06, "loss": 0.6495, "step": 12550 }, { "epoch": 0.7331191588785047, "grad_norm": 1.0083547830581665, "learning_rate": 3.5103400230091866e-06, "loss": 0.6516, "step": 12551 }, { "epoch": 0.733177570093458, "grad_norm": 1.6884852647781372, "learning_rate": 3.5089007928973563e-06, "loss": 0.8079, "step": 12552 }, { "epoch": 0.7332359813084112, "grad_norm": 1.0306406021118164, "learning_rate": 3.507461795106232e-06, "loss": 0.8223, "step": 12553 }, { "epoch": 0.7332943925233645, "grad_norm": 1.0762813091278076, "learning_rate": 3.506023029687321e-06, "loss": 0.5915, "step": 12554 }, { "epoch": 0.7333528037383178, "grad_norm": 1.0028499364852905, "learning_rate": 3.504584496692112e-06, "loss": 0.7808, "step": 12555 }, { "epoch": 0.733411214953271, "grad_norm": 1.3797587156295776, "learning_rate": 3.5031461961720958e-06, "loss": 0.7459, "step": 12556 }, { "epoch": 0.7334696261682243, "grad_norm": 1.1389907598495483, "learning_rate": 3.501708128178751e-06, "loss": 0.7645, "step": 12557 }, { "epoch": 0.7335280373831776, "grad_norm": 0.8325144052505493, "learning_rate": 3.500270292763542e-06, "loss": 0.6552, "step": 12558 }, { "epoch": 0.7335864485981308, "grad_norm": 1.2466604709625244, "learning_rate": 3.498832689977938e-06, "loss": 0.9312, "step": 12559 }, { "epoch": 0.7336448598130841, "grad_norm": 1.3579788208007812, "learning_rate": 3.4973953198733814e-06, "loss": 0.8613, "step": 12560 }, { "epoch": 0.7337032710280373, "grad_norm": 1.1028865575790405, "learning_rate": 3.4959581825013256e-06, "loss": 0.7794, "step": 12561 }, { "epoch": 0.7337616822429907, "grad_norm": 1.6720149517059326, "learning_rate": 3.4945212779132e-06, "loss": 0.8773, "step": 12562 }, { "epoch": 0.733820093457944, "grad_norm": 0.9963188171386719, "learning_rate": 3.493084606160435e-06, "loss": 0.7406, "step": 12563 }, { "epoch": 0.7338785046728972, "grad_norm": 1.0776382684707642, "learning_rate": 3.4916481672944537e-06, "loss": 0.7655, "step": 12564 }, { "epoch": 0.7339369158878505, "grad_norm": 1.7081159353256226, "learning_rate": 3.490211961366661e-06, "loss": 0.8352, "step": 12565 }, { "epoch": 0.7339953271028037, "grad_norm": 1.1893733739852905, "learning_rate": 3.4887759884284645e-06, "loss": 0.643, "step": 12566 }, { "epoch": 0.734053738317757, "grad_norm": 1.040502905845642, "learning_rate": 3.4873402485312548e-06, "loss": 0.6857, "step": 12567 }, { "epoch": 0.7341121495327103, "grad_norm": 1.458375334739685, "learning_rate": 3.485904741726419e-06, "loss": 0.8688, "step": 12568 }, { "epoch": 0.7341705607476635, "grad_norm": 1.3591547012329102, "learning_rate": 3.484469468065339e-06, "loss": 0.7817, "step": 12569 }, { "epoch": 0.7342289719626168, "grad_norm": 1.0783966779708862, "learning_rate": 3.4830344275993766e-06, "loss": 0.6981, "step": 12570 }, { "epoch": 0.7342873831775701, "grad_norm": 1.20041823387146, "learning_rate": 3.481599620379902e-06, "loss": 0.7409, "step": 12571 }, { "epoch": 0.7343457943925233, "grad_norm": 1.4778509140014648, "learning_rate": 3.480165046458258e-06, "loss": 0.7891, "step": 12572 }, { "epoch": 0.7344042056074767, "grad_norm": 0.9665443301200867, "learning_rate": 3.4787307058857946e-06, "loss": 0.7357, "step": 12573 }, { "epoch": 0.7344626168224299, "grad_norm": 1.3023748397827148, "learning_rate": 3.477296598713851e-06, "loss": 0.8229, "step": 12574 }, { "epoch": 0.7345210280373832, "grad_norm": 1.3175231218338013, "learning_rate": 3.475862724993746e-06, "loss": 0.7002, "step": 12575 }, { "epoch": 0.7345794392523365, "grad_norm": 1.384529948234558, "learning_rate": 3.474429084776808e-06, "loss": 0.8096, "step": 12576 }, { "epoch": 0.7346378504672897, "grad_norm": 1.6564360857009888, "learning_rate": 3.4729956781143446e-06, "loss": 0.8585, "step": 12577 }, { "epoch": 0.734696261682243, "grad_norm": 1.405055284500122, "learning_rate": 3.471562505057653e-06, "loss": 0.9198, "step": 12578 }, { "epoch": 0.7347546728971963, "grad_norm": 0.972029983997345, "learning_rate": 3.4701295656580324e-06, "loss": 0.8106, "step": 12579 }, { "epoch": 0.7348130841121495, "grad_norm": 1.6690804958343506, "learning_rate": 3.468696859966768e-06, "loss": 0.8562, "step": 12580 }, { "epoch": 0.7348714953271028, "grad_norm": 1.0806612968444824, "learning_rate": 3.4672643880351407e-06, "loss": 0.9275, "step": 12581 }, { "epoch": 0.734929906542056, "grad_norm": 1.2654030323028564, "learning_rate": 3.4658321499144152e-06, "loss": 0.8312, "step": 12582 }, { "epoch": 0.7349883177570093, "grad_norm": 1.1270637512207031, "learning_rate": 3.464400145655852e-06, "loss": 0.868, "step": 12583 }, { "epoch": 0.7350467289719627, "grad_norm": 1.0292494297027588, "learning_rate": 3.4629683753107034e-06, "loss": 0.7431, "step": 12584 }, { "epoch": 0.7351051401869159, "grad_norm": 1.4675655364990234, "learning_rate": 3.4615368389302152e-06, "loss": 0.7795, "step": 12585 }, { "epoch": 0.7351635514018692, "grad_norm": 1.0568525791168213, "learning_rate": 3.4601055365656265e-06, "loss": 0.8123, "step": 12586 }, { "epoch": 0.7352219626168224, "grad_norm": 0.8635420203208923, "learning_rate": 3.4586744682681606e-06, "loss": 0.6848, "step": 12587 }, { "epoch": 0.7352803738317757, "grad_norm": 1.081438660621643, "learning_rate": 3.4572436340890327e-06, "loss": 0.8157, "step": 12588 }, { "epoch": 0.735338785046729, "grad_norm": 0.8931123614311218, "learning_rate": 3.4558130340794573e-06, "loss": 0.6984, "step": 12589 }, { "epoch": 0.7353971962616822, "grad_norm": 1.57892906665802, "learning_rate": 3.4543826682906358e-06, "loss": 0.6814, "step": 12590 }, { "epoch": 0.7354556074766355, "grad_norm": 1.0559577941894531, "learning_rate": 3.452952536773766e-06, "loss": 0.7562, "step": 12591 }, { "epoch": 0.7355140186915888, "grad_norm": 1.026131510734558, "learning_rate": 3.4515226395800303e-06, "loss": 0.7081, "step": 12592 }, { "epoch": 0.735572429906542, "grad_norm": 0.9619103670120239, "learning_rate": 3.4500929767606006e-06, "loss": 0.6908, "step": 12593 }, { "epoch": 0.7356308411214953, "grad_norm": 1.2467085123062134, "learning_rate": 3.4486635483666543e-06, "loss": 0.7298, "step": 12594 }, { "epoch": 0.7356892523364486, "grad_norm": 1.1278927326202393, "learning_rate": 3.4472343544493405e-06, "loss": 0.6146, "step": 12595 }, { "epoch": 0.7357476635514019, "grad_norm": 1.0412380695343018, "learning_rate": 3.4458053950598237e-06, "loss": 0.6722, "step": 12596 }, { "epoch": 0.7358060747663552, "grad_norm": 1.2244492769241333, "learning_rate": 3.444376670249242e-06, "loss": 0.6526, "step": 12597 }, { "epoch": 0.7358644859813084, "grad_norm": 1.0405540466308594, "learning_rate": 3.4429481800687257e-06, "loss": 0.7692, "step": 12598 }, { "epoch": 0.7359228971962617, "grad_norm": 1.0852826833724976, "learning_rate": 3.4415199245694084e-06, "loss": 0.7737, "step": 12599 }, { "epoch": 0.735981308411215, "grad_norm": 1.197584629058838, "learning_rate": 3.4400919038024026e-06, "loss": 0.6395, "step": 12600 }, { "epoch": 0.7360397196261682, "grad_norm": 1.3320814371109009, "learning_rate": 3.4386641178188208e-06, "loss": 0.7919, "step": 12601 }, { "epoch": 0.7360981308411215, "grad_norm": 1.2455259561538696, "learning_rate": 3.437236566669767e-06, "loss": 0.7625, "step": 12602 }, { "epoch": 0.7361565420560747, "grad_norm": 1.362974762916565, "learning_rate": 3.435809250406329e-06, "loss": 0.7304, "step": 12603 }, { "epoch": 0.736214953271028, "grad_norm": 1.005638599395752, "learning_rate": 3.4343821690795975e-06, "loss": 0.9437, "step": 12604 }, { "epoch": 0.7362733644859814, "grad_norm": 0.9686838984489441, "learning_rate": 3.432955322740642e-06, "loss": 0.7234, "step": 12605 }, { "epoch": 0.7363317757009346, "grad_norm": 0.8968873620033264, "learning_rate": 3.4315287114405327e-06, "loss": 0.6483, "step": 12606 }, { "epoch": 0.7363901869158879, "grad_norm": 1.3043922185897827, "learning_rate": 3.430102335230333e-06, "loss": 0.6964, "step": 12607 }, { "epoch": 0.7364485981308411, "grad_norm": 1.1436314582824707, "learning_rate": 3.4286761941610867e-06, "loss": 0.9962, "step": 12608 }, { "epoch": 0.7365070093457944, "grad_norm": 1.156204104423523, "learning_rate": 3.4272502882838444e-06, "loss": 0.7933, "step": 12609 }, { "epoch": 0.7365654205607477, "grad_norm": 1.0164027214050293, "learning_rate": 3.425824617649636e-06, "loss": 0.7796, "step": 12610 }, { "epoch": 0.7366238317757009, "grad_norm": 1.2664942741394043, "learning_rate": 3.4243991823094834e-06, "loss": 0.8098, "step": 12611 }, { "epoch": 0.7366822429906542, "grad_norm": 1.104743480682373, "learning_rate": 3.422973982314408e-06, "loss": 0.739, "step": 12612 }, { "epoch": 0.7367406542056075, "grad_norm": 1.0072656869888306, "learning_rate": 3.4215490177154176e-06, "loss": 0.7505, "step": 12613 }, { "epoch": 0.7367990654205607, "grad_norm": 0.9847716689109802, "learning_rate": 3.4201242885635167e-06, "loss": 0.6822, "step": 12614 }, { "epoch": 0.736857476635514, "grad_norm": 1.1195094585418701, "learning_rate": 3.4186997949096946e-06, "loss": 0.766, "step": 12615 }, { "epoch": 0.7369158878504672, "grad_norm": 1.4532934427261353, "learning_rate": 3.4172755368049304e-06, "loss": 0.7411, "step": 12616 }, { "epoch": 0.7369742990654206, "grad_norm": 1.3660478591918945, "learning_rate": 3.4158515143002023e-06, "loss": 0.7065, "step": 12617 }, { "epoch": 0.7370327102803739, "grad_norm": 1.0713392496109009, "learning_rate": 3.414427727446479e-06, "loss": 0.8032, "step": 12618 }, { "epoch": 0.7370911214953271, "grad_norm": 1.1162898540496826, "learning_rate": 3.4130041762947197e-06, "loss": 0.747, "step": 12619 }, { "epoch": 0.7371495327102804, "grad_norm": 1.6625676155090332, "learning_rate": 3.411580860895872e-06, "loss": 0.6293, "step": 12620 }, { "epoch": 0.7372079439252337, "grad_norm": 1.290746808052063, "learning_rate": 3.4101577813008733e-06, "loss": 0.8223, "step": 12621 }, { "epoch": 0.7372663551401869, "grad_norm": 1.2232967615127563, "learning_rate": 3.4087349375606626e-06, "loss": 0.6905, "step": 12622 }, { "epoch": 0.7373247663551402, "grad_norm": 1.0278823375701904, "learning_rate": 3.40731232972616e-06, "loss": 0.6927, "step": 12623 }, { "epoch": 0.7373831775700934, "grad_norm": 1.9642707109451294, "learning_rate": 3.4058899578482884e-06, "loss": 0.9596, "step": 12624 }, { "epoch": 0.7374415887850467, "grad_norm": 1.3702856302261353, "learning_rate": 3.4044678219779514e-06, "loss": 0.6263, "step": 12625 }, { "epoch": 0.7375, "grad_norm": 1.2708944082260132, "learning_rate": 3.403045922166044e-06, "loss": 0.7305, "step": 12626 }, { "epoch": 0.7375584112149532, "grad_norm": 0.9618971943855286, "learning_rate": 3.401624258463464e-06, "loss": 0.7618, "step": 12627 }, { "epoch": 0.7376168224299066, "grad_norm": 2.060671091079712, "learning_rate": 3.400202830921083e-06, "loss": 0.8106, "step": 12628 }, { "epoch": 0.7376752336448598, "grad_norm": 0.947812557220459, "learning_rate": 3.398781639589789e-06, "loss": 0.8772, "step": 12629 }, { "epoch": 0.7377336448598131, "grad_norm": 1.1673835515975952, "learning_rate": 3.397360684520441e-06, "loss": 0.7286, "step": 12630 }, { "epoch": 0.7377920560747664, "grad_norm": 1.529741644859314, "learning_rate": 3.3959399657638916e-06, "loss": 0.8108, "step": 12631 }, { "epoch": 0.7378504672897196, "grad_norm": 1.5364747047424316, "learning_rate": 3.394519483370997e-06, "loss": 0.8678, "step": 12632 }, { "epoch": 0.7379088785046729, "grad_norm": 1.296496868133545, "learning_rate": 3.39309923739259e-06, "loss": 0.8342, "step": 12633 }, { "epoch": 0.7379672897196262, "grad_norm": 1.3139845132827759, "learning_rate": 3.391679227879504e-06, "loss": 0.8413, "step": 12634 }, { "epoch": 0.7380257009345794, "grad_norm": 1.1883231401443481, "learning_rate": 3.3902594548825686e-06, "loss": 0.8623, "step": 12635 }, { "epoch": 0.7380841121495327, "grad_norm": 1.8970028162002563, "learning_rate": 3.388839918452589e-06, "loss": 0.8896, "step": 12636 }, { "epoch": 0.7381425233644859, "grad_norm": 1.103995442390442, "learning_rate": 3.387420618640379e-06, "loss": 0.9265, "step": 12637 }, { "epoch": 0.7382009345794392, "grad_norm": 1.1264091730117798, "learning_rate": 3.3860015554967294e-06, "loss": 0.6748, "step": 12638 }, { "epoch": 0.7382593457943926, "grad_norm": 1.6334563493728638, "learning_rate": 3.3845827290724333e-06, "loss": 0.6508, "step": 12639 }, { "epoch": 0.7383177570093458, "grad_norm": 1.1601272821426392, "learning_rate": 3.3831641394182747e-06, "loss": 0.6696, "step": 12640 }, { "epoch": 0.7383761682242991, "grad_norm": 1.3121777772903442, "learning_rate": 3.3817457865850177e-06, "loss": 0.7557, "step": 12641 }, { "epoch": 0.7384345794392523, "grad_norm": 0.9508020877838135, "learning_rate": 3.3803276706234356e-06, "loss": 0.811, "step": 12642 }, { "epoch": 0.7384929906542056, "grad_norm": 1.5940706729888916, "learning_rate": 3.378909791584274e-06, "loss": 0.7031, "step": 12643 }, { "epoch": 0.7385514018691589, "grad_norm": 2.5685489177703857, "learning_rate": 3.377492149518289e-06, "loss": 0.8339, "step": 12644 }, { "epoch": 0.7386098130841121, "grad_norm": 1.0542762279510498, "learning_rate": 3.37607474447621e-06, "loss": 0.8585, "step": 12645 }, { "epoch": 0.7386682242990654, "grad_norm": 1.1041206121444702, "learning_rate": 3.3746575765087707e-06, "loss": 0.7624, "step": 12646 }, { "epoch": 0.7387266355140187, "grad_norm": 1.2049696445465088, "learning_rate": 3.3732406456666976e-06, "loss": 0.9102, "step": 12647 }, { "epoch": 0.7387850467289719, "grad_norm": 1.0889512300491333, "learning_rate": 3.3718239520006947e-06, "loss": 0.8004, "step": 12648 }, { "epoch": 0.7388434579439253, "grad_norm": 1.700340747833252, "learning_rate": 3.370407495561474e-06, "loss": 0.8134, "step": 12649 }, { "epoch": 0.7389018691588785, "grad_norm": 1.5409528017044067, "learning_rate": 3.368991276399726e-06, "loss": 0.736, "step": 12650 }, { "epoch": 0.7389602803738318, "grad_norm": 1.2241727113723755, "learning_rate": 3.3675752945661387e-06, "loss": 0.9984, "step": 12651 }, { "epoch": 0.7390186915887851, "grad_norm": 1.1324845552444458, "learning_rate": 3.3661595501113963e-06, "loss": 0.6287, "step": 12652 }, { "epoch": 0.7390771028037383, "grad_norm": 1.8152718544006348, "learning_rate": 3.3647440430861635e-06, "loss": 0.7216, "step": 12653 }, { "epoch": 0.7391355140186916, "grad_norm": 1.0489543676376343, "learning_rate": 3.363328773541106e-06, "loss": 0.6125, "step": 12654 }, { "epoch": 0.7391939252336449, "grad_norm": 1.2809847593307495, "learning_rate": 3.361913741526872e-06, "loss": 0.5989, "step": 12655 }, { "epoch": 0.7392523364485981, "grad_norm": 0.9295221567153931, "learning_rate": 3.3604989470941095e-06, "loss": 0.6801, "step": 12656 }, { "epoch": 0.7393107476635514, "grad_norm": 1.111513376235962, "learning_rate": 3.35908439029346e-06, "loss": 0.9226, "step": 12657 }, { "epoch": 0.7393691588785046, "grad_norm": 1.4559601545333862, "learning_rate": 3.357670071175546e-06, "loss": 0.7228, "step": 12658 }, { "epoch": 0.7394275700934579, "grad_norm": 1.7965031862258911, "learning_rate": 3.3562559897909842e-06, "loss": 0.7794, "step": 12659 }, { "epoch": 0.7394859813084113, "grad_norm": 1.5597480535507202, "learning_rate": 3.3548421461903912e-06, "loss": 0.6699, "step": 12660 }, { "epoch": 0.7395443925233645, "grad_norm": 2.0045535564422607, "learning_rate": 3.3534285404243615e-06, "loss": 0.8406, "step": 12661 }, { "epoch": 0.7396028037383178, "grad_norm": 1.0428053140640259, "learning_rate": 3.3520151725435015e-06, "loss": 0.7017, "step": 12662 }, { "epoch": 0.739661214953271, "grad_norm": 0.9118928909301758, "learning_rate": 3.3506020425983887e-06, "loss": 0.6834, "step": 12663 }, { "epoch": 0.7397196261682243, "grad_norm": 1.1256165504455566, "learning_rate": 3.349189150639598e-06, "loss": 0.7049, "step": 12664 }, { "epoch": 0.7397780373831776, "grad_norm": 0.9233496189117432, "learning_rate": 3.347776496717704e-06, "loss": 0.7238, "step": 12665 }, { "epoch": 0.7398364485981308, "grad_norm": 1.2150949239730835, "learning_rate": 3.3463640808832597e-06, "loss": 0.8344, "step": 12666 }, { "epoch": 0.7398948598130841, "grad_norm": 1.4496760368347168, "learning_rate": 3.3449519031868193e-06, "loss": 0.9941, "step": 12667 }, { "epoch": 0.7399532710280374, "grad_norm": 1.0646930932998657, "learning_rate": 3.34353996367893e-06, "loss": 0.7206, "step": 12668 }, { "epoch": 0.7400116822429906, "grad_norm": 2.0545599460601807, "learning_rate": 3.3421282624101193e-06, "loss": 0.7684, "step": 12669 }, { "epoch": 0.740070093457944, "grad_norm": 0.9133132100105286, "learning_rate": 3.3407167994309175e-06, "loss": 0.6492, "step": 12670 }, { "epoch": 0.7401285046728971, "grad_norm": 1.080256700515747, "learning_rate": 3.3393055747918378e-06, "loss": 0.6609, "step": 12671 }, { "epoch": 0.7401869158878505, "grad_norm": 1.2222918272018433, "learning_rate": 3.3378945885433912e-06, "loss": 0.7028, "step": 12672 }, { "epoch": 0.7402453271028038, "grad_norm": 1.8537461757659912, "learning_rate": 3.336483840736081e-06, "loss": 0.9057, "step": 12673 }, { "epoch": 0.740303738317757, "grad_norm": 1.1051114797592163, "learning_rate": 3.335073331420391e-06, "loss": 0.7337, "step": 12674 }, { "epoch": 0.7403621495327103, "grad_norm": 1.4007526636123657, "learning_rate": 3.3336630606468136e-06, "loss": 0.7974, "step": 12675 }, { "epoch": 0.7404205607476636, "grad_norm": 2.732267379760742, "learning_rate": 3.332253028465814e-06, "loss": 0.8484, "step": 12676 }, { "epoch": 0.7404789719626168, "grad_norm": 1.4790388345718384, "learning_rate": 3.3308432349278664e-06, "loss": 0.8677, "step": 12677 }, { "epoch": 0.7405373831775701, "grad_norm": 1.1233289241790771, "learning_rate": 3.3294336800834213e-06, "loss": 0.5896, "step": 12678 }, { "epoch": 0.7405957943925233, "grad_norm": 1.9142613410949707, "learning_rate": 3.32802436398293e-06, "loss": 0.6385, "step": 12679 }, { "epoch": 0.7406542056074766, "grad_norm": 1.0503861904144287, "learning_rate": 3.326615286676839e-06, "loss": 0.7474, "step": 12680 }, { "epoch": 0.74071261682243, "grad_norm": 0.972460925579071, "learning_rate": 3.3252064482155687e-06, "loss": 0.6866, "step": 12681 }, { "epoch": 0.7407710280373832, "grad_norm": 0.9723246097564697, "learning_rate": 3.3237978486495536e-06, "loss": 0.5645, "step": 12682 }, { "epoch": 0.7408294392523365, "grad_norm": 1.8285577297210693, "learning_rate": 3.3223894880291986e-06, "loss": 0.7585, "step": 12683 }, { "epoch": 0.7408878504672897, "grad_norm": 1.527535319328308, "learning_rate": 3.3209813664049152e-06, "loss": 0.8452, "step": 12684 }, { "epoch": 0.740946261682243, "grad_norm": 1.2243069410324097, "learning_rate": 3.319573483827103e-06, "loss": 0.7106, "step": 12685 }, { "epoch": 0.7410046728971963, "grad_norm": 1.021529197692871, "learning_rate": 3.318165840346146e-06, "loss": 0.7089, "step": 12686 }, { "epoch": 0.7410630841121495, "grad_norm": 1.1746611595153809, "learning_rate": 3.3167584360124295e-06, "loss": 0.7538, "step": 12687 }, { "epoch": 0.7411214953271028, "grad_norm": 1.0785788297653198, "learning_rate": 3.31535127087632e-06, "loss": 0.8055, "step": 12688 }, { "epoch": 0.7411799065420561, "grad_norm": 1.1108695268630981, "learning_rate": 3.3139443449881834e-06, "loss": 0.8875, "step": 12689 }, { "epoch": 0.7412383177570093, "grad_norm": 1.9455904960632324, "learning_rate": 3.3125376583983783e-06, "loss": 0.8415, "step": 12690 }, { "epoch": 0.7412967289719626, "grad_norm": 1.0538173913955688, "learning_rate": 3.3111312111572447e-06, "loss": 0.7159, "step": 12691 }, { "epoch": 0.7413551401869158, "grad_norm": 1.7504693269729614, "learning_rate": 3.309725003315125e-06, "loss": 0.7101, "step": 12692 }, { "epoch": 0.7414135514018692, "grad_norm": 1.2750569581985474, "learning_rate": 3.3083190349223473e-06, "loss": 0.6745, "step": 12693 }, { "epoch": 0.7414719626168225, "grad_norm": 0.8260944485664368, "learning_rate": 3.3069133060292246e-06, "loss": 0.5525, "step": 12694 }, { "epoch": 0.7415303738317757, "grad_norm": 1.1643507480621338, "learning_rate": 3.305507816686082e-06, "loss": 0.7252, "step": 12695 }, { "epoch": 0.741588785046729, "grad_norm": 1.0838403701782227, "learning_rate": 3.3041025669432123e-06, "loss": 0.677, "step": 12696 }, { "epoch": 0.7416471962616823, "grad_norm": 1.0678491592407227, "learning_rate": 3.302697556850919e-06, "loss": 0.9527, "step": 12697 }, { "epoch": 0.7417056074766355, "grad_norm": 1.1586027145385742, "learning_rate": 3.3012927864594835e-06, "loss": 0.7142, "step": 12698 }, { "epoch": 0.7417640186915888, "grad_norm": 1.2854303121566772, "learning_rate": 3.2998882558191793e-06, "loss": 0.9352, "step": 12699 }, { "epoch": 0.741822429906542, "grad_norm": 1.0356813669204712, "learning_rate": 3.2984839649802815e-06, "loss": 0.6026, "step": 12700 }, { "epoch": 0.7418808411214953, "grad_norm": 1.0355606079101562, "learning_rate": 3.2970799139930475e-06, "loss": 0.6729, "step": 12701 }, { "epoch": 0.7419392523364486, "grad_norm": 1.277264952659607, "learning_rate": 3.2956761029077343e-06, "loss": 0.8285, "step": 12702 }, { "epoch": 0.7419976635514018, "grad_norm": 0.8987588286399841, "learning_rate": 3.2942725317745815e-06, "loss": 0.6339, "step": 12703 }, { "epoch": 0.7420560747663552, "grad_norm": 1.0223881006240845, "learning_rate": 3.29286920064382e-06, "loss": 0.6716, "step": 12704 }, { "epoch": 0.7421144859813084, "grad_norm": 0.9201570153236389, "learning_rate": 3.2914661095656807e-06, "loss": 0.6693, "step": 12705 }, { "epoch": 0.7421728971962617, "grad_norm": 1.9268471002578735, "learning_rate": 3.2900632585903802e-06, "loss": 0.6493, "step": 12706 }, { "epoch": 0.742231308411215, "grad_norm": 1.1285310983657837, "learning_rate": 3.2886606477681314e-06, "loss": 0.6253, "step": 12707 }, { "epoch": 0.7422897196261682, "grad_norm": 1.3806477785110474, "learning_rate": 3.2872582771491303e-06, "loss": 0.7873, "step": 12708 }, { "epoch": 0.7423481308411215, "grad_norm": 1.1023476123809814, "learning_rate": 3.285856146783565e-06, "loss": 0.6993, "step": 12709 }, { "epoch": 0.7424065420560748, "grad_norm": 1.0693833827972412, "learning_rate": 3.2844542567216277e-06, "loss": 0.8778, "step": 12710 }, { "epoch": 0.742464953271028, "grad_norm": 1.1414421796798706, "learning_rate": 3.2830526070134806e-06, "loss": 0.7702, "step": 12711 }, { "epoch": 0.7425233644859813, "grad_norm": 1.0479166507720947, "learning_rate": 3.2816511977093034e-06, "loss": 0.8783, "step": 12712 }, { "epoch": 0.7425817757009345, "grad_norm": 1.0880616903305054, "learning_rate": 3.2802500288592477e-06, "loss": 0.7326, "step": 12713 }, { "epoch": 0.7426401869158878, "grad_norm": 2.3526077270507812, "learning_rate": 3.2788491005134583e-06, "loss": 0.7819, "step": 12714 }, { "epoch": 0.7426985981308412, "grad_norm": 0.9978624582290649, "learning_rate": 3.277448412722083e-06, "loss": 0.7273, "step": 12715 }, { "epoch": 0.7427570093457944, "grad_norm": 1.1015827655792236, "learning_rate": 3.276047965535245e-06, "loss": 0.7597, "step": 12716 }, { "epoch": 0.7428154205607477, "grad_norm": 1.1302568912506104, "learning_rate": 3.274647759003071e-06, "loss": 0.6593, "step": 12717 }, { "epoch": 0.742873831775701, "grad_norm": 1.202314019203186, "learning_rate": 3.27324779317568e-06, "loss": 0.7738, "step": 12718 }, { "epoch": 0.7429322429906542, "grad_norm": 0.9995986223220825, "learning_rate": 3.2718480681031695e-06, "loss": 0.8198, "step": 12719 }, { "epoch": 0.7429906542056075, "grad_norm": 0.9542753100395203, "learning_rate": 3.2704485838356435e-06, "loss": 0.8084, "step": 12720 }, { "epoch": 0.7430490654205607, "grad_norm": 1.30815851688385, "learning_rate": 3.269049340423185e-06, "loss": 0.8372, "step": 12721 }, { "epoch": 0.743107476635514, "grad_norm": 1.3273766040802002, "learning_rate": 3.267650337915876e-06, "loss": 0.7787, "step": 12722 }, { "epoch": 0.7431658878504673, "grad_norm": 0.9989593029022217, "learning_rate": 3.2662515763637914e-06, "loss": 0.7302, "step": 12723 }, { "epoch": 0.7432242990654205, "grad_norm": 1.2925784587860107, "learning_rate": 3.2648530558169865e-06, "loss": 0.7026, "step": 12724 }, { "epoch": 0.7432827102803738, "grad_norm": 1.3148002624511719, "learning_rate": 3.2634547763255233e-06, "loss": 0.7244, "step": 12725 }, { "epoch": 0.743341121495327, "grad_norm": 0.9285942316055298, "learning_rate": 3.262056737939443e-06, "loss": 0.6268, "step": 12726 }, { "epoch": 0.7433995327102804, "grad_norm": 1.1518512964248657, "learning_rate": 3.2606589407087752e-06, "loss": 0.7829, "step": 12727 }, { "epoch": 0.7434579439252337, "grad_norm": 0.8254096508026123, "learning_rate": 3.259261384683562e-06, "loss": 0.7561, "step": 12728 }, { "epoch": 0.7435163551401869, "grad_norm": 1.1204941272735596, "learning_rate": 3.257864069913812e-06, "loss": 0.7405, "step": 12729 }, { "epoch": 0.7435747663551402, "grad_norm": 1.290998935699463, "learning_rate": 3.2564669964495443e-06, "loss": 0.7843, "step": 12730 }, { "epoch": 0.7436331775700935, "grad_norm": 0.9714826941490173, "learning_rate": 3.2550701643407556e-06, "loss": 0.7508, "step": 12731 }, { "epoch": 0.7436915887850467, "grad_norm": 1.479719877243042, "learning_rate": 3.253673573637438e-06, "loss": 0.8049, "step": 12732 }, { "epoch": 0.74375, "grad_norm": 1.5141947269439697, "learning_rate": 3.2522772243895794e-06, "loss": 0.8485, "step": 12733 }, { "epoch": 0.7438084112149532, "grad_norm": 1.102734088897705, "learning_rate": 3.2508811166471554e-06, "loss": 0.7119, "step": 12734 }, { "epoch": 0.7438668224299065, "grad_norm": 1.4580785036087036, "learning_rate": 3.249485250460137e-06, "loss": 0.8141, "step": 12735 }, { "epoch": 0.7439252336448599, "grad_norm": 1.1446818113327026, "learning_rate": 3.24808962587848e-06, "loss": 0.8659, "step": 12736 }, { "epoch": 0.743983644859813, "grad_norm": 1.0577517747879028, "learning_rate": 3.246694242952132e-06, "loss": 0.5778, "step": 12737 }, { "epoch": 0.7440420560747664, "grad_norm": 1.2559462785720825, "learning_rate": 3.2452991017310365e-06, "loss": 0.8809, "step": 12738 }, { "epoch": 0.7441004672897197, "grad_norm": 1.3217806816101074, "learning_rate": 3.243904202265128e-06, "loss": 0.9563, "step": 12739 }, { "epoch": 0.7441588785046729, "grad_norm": 1.3278027772903442, "learning_rate": 3.242509544604333e-06, "loss": 0.6413, "step": 12740 }, { "epoch": 0.7442172897196262, "grad_norm": 1.2787518501281738, "learning_rate": 3.2411151287985653e-06, "loss": 0.813, "step": 12741 }, { "epoch": 0.7442757009345794, "grad_norm": 1.2860383987426758, "learning_rate": 3.2397209548977284e-06, "loss": 0.8291, "step": 12742 }, { "epoch": 0.7443341121495327, "grad_norm": 1.2362045049667358, "learning_rate": 3.238327022951725e-06, "loss": 0.8088, "step": 12743 }, { "epoch": 0.744392523364486, "grad_norm": 1.2315136194229126, "learning_rate": 3.236933333010438e-06, "loss": 0.798, "step": 12744 }, { "epoch": 0.7444509345794392, "grad_norm": 1.2103546857833862, "learning_rate": 3.2355398851237608e-06, "loss": 0.8688, "step": 12745 }, { "epoch": 0.7445093457943925, "grad_norm": 1.1032378673553467, "learning_rate": 3.2341466793415577e-06, "loss": 0.8528, "step": 12746 }, { "epoch": 0.7445677570093457, "grad_norm": 1.0636709928512573, "learning_rate": 3.232753715713691e-06, "loss": 0.7629, "step": 12747 }, { "epoch": 0.7446261682242991, "grad_norm": 1.0498498678207397, "learning_rate": 3.2313609942900214e-06, "loss": 0.8974, "step": 12748 }, { "epoch": 0.7446845794392524, "grad_norm": 1.0176597833633423, "learning_rate": 3.2299685151203886e-06, "loss": 0.7228, "step": 12749 }, { "epoch": 0.7447429906542056, "grad_norm": 1.0384764671325684, "learning_rate": 3.2285762782546346e-06, "loss": 0.7623, "step": 12750 }, { "epoch": 0.7448014018691589, "grad_norm": 0.9047891497612, "learning_rate": 3.2271842837425917e-06, "loss": 0.4233, "step": 12751 }, { "epoch": 0.7448598130841122, "grad_norm": 1.129726529121399, "learning_rate": 3.225792531634072e-06, "loss": 0.812, "step": 12752 }, { "epoch": 0.7449182242990654, "grad_norm": 1.0480265617370605, "learning_rate": 3.224401021978896e-06, "loss": 0.7016, "step": 12753 }, { "epoch": 0.7449766355140187, "grad_norm": 1.0091733932495117, "learning_rate": 3.223009754826858e-06, "loss": 0.8604, "step": 12754 }, { "epoch": 0.7450350467289719, "grad_norm": 1.14239501953125, "learning_rate": 3.221618730227758e-06, "loss": 0.8956, "step": 12755 }, { "epoch": 0.7450934579439252, "grad_norm": 1.2281346321105957, "learning_rate": 3.220227948231384e-06, "loss": 0.7324, "step": 12756 }, { "epoch": 0.7451518691588785, "grad_norm": 1.2494609355926514, "learning_rate": 3.218837408887505e-06, "loss": 0.6805, "step": 12757 }, { "epoch": 0.7452102803738317, "grad_norm": 1.1572400331497192, "learning_rate": 3.217447112245897e-06, "loss": 0.9177, "step": 12758 }, { "epoch": 0.7452686915887851, "grad_norm": 1.1189342737197876, "learning_rate": 3.2160570583563145e-06, "loss": 0.7527, "step": 12759 }, { "epoch": 0.7453271028037384, "grad_norm": 1.2253977060317993, "learning_rate": 3.2146672472685092e-06, "loss": 0.7839, "step": 12760 }, { "epoch": 0.7453855140186916, "grad_norm": 0.9153037071228027, "learning_rate": 3.2132776790322294e-06, "loss": 0.7779, "step": 12761 }, { "epoch": 0.7454439252336449, "grad_norm": 0.98526531457901, "learning_rate": 3.211888353697199e-06, "loss": 0.7393, "step": 12762 }, { "epoch": 0.7455023364485981, "grad_norm": 1.7185167074203491, "learning_rate": 3.2104992713131523e-06, "loss": 0.77, "step": 12763 }, { "epoch": 0.7455607476635514, "grad_norm": 1.0650080442428589, "learning_rate": 3.2091104319297963e-06, "loss": 0.6692, "step": 12764 }, { "epoch": 0.7456191588785047, "grad_norm": 2.0158331394195557, "learning_rate": 3.2077218355968464e-06, "loss": 0.8093, "step": 12765 }, { "epoch": 0.7456775700934579, "grad_norm": 1.038529634475708, "learning_rate": 3.2063334823639957e-06, "loss": 0.7806, "step": 12766 }, { "epoch": 0.7457359813084112, "grad_norm": 1.27500319480896, "learning_rate": 3.2049453722809365e-06, "loss": 0.6367, "step": 12767 }, { "epoch": 0.7457943925233644, "grad_norm": 0.9409042000770569, "learning_rate": 3.2035575053973533e-06, "loss": 0.7298, "step": 12768 }, { "epoch": 0.7458528037383177, "grad_norm": 1.1907645463943481, "learning_rate": 3.202169881762912e-06, "loss": 0.7708, "step": 12769 }, { "epoch": 0.7459112149532711, "grad_norm": 1.1134811639785767, "learning_rate": 3.2007825014272844e-06, "loss": 0.9468, "step": 12770 }, { "epoch": 0.7459696261682243, "grad_norm": 1.1115809679031372, "learning_rate": 3.199395364440118e-06, "loss": 0.7855, "step": 12771 }, { "epoch": 0.7460280373831776, "grad_norm": 1.248811960220337, "learning_rate": 3.1980084708510616e-06, "loss": 1.0519, "step": 12772 }, { "epoch": 0.7460864485981309, "grad_norm": 1.2463057041168213, "learning_rate": 3.196621820709759e-06, "loss": 0.806, "step": 12773 }, { "epoch": 0.7461448598130841, "grad_norm": 1.3098474740982056, "learning_rate": 3.1952354140658346e-06, "loss": 0.8213, "step": 12774 }, { "epoch": 0.7462032710280374, "grad_norm": 1.3333795070648193, "learning_rate": 3.1938492509689057e-06, "loss": 0.9196, "step": 12775 }, { "epoch": 0.7462616822429906, "grad_norm": 1.2455626726150513, "learning_rate": 3.1924633314685905e-06, "loss": 0.7063, "step": 12776 }, { "epoch": 0.7463200934579439, "grad_norm": 1.3326053619384766, "learning_rate": 3.1910776556144828e-06, "loss": 0.8832, "step": 12777 }, { "epoch": 0.7463785046728972, "grad_norm": 1.4577319622039795, "learning_rate": 3.189692223456189e-06, "loss": 0.8495, "step": 12778 }, { "epoch": 0.7464369158878504, "grad_norm": 0.8522090911865234, "learning_rate": 3.1883070350432874e-06, "loss": 0.6763, "step": 12779 }, { "epoch": 0.7464953271028038, "grad_norm": 1.1561390161514282, "learning_rate": 3.186922090425354e-06, "loss": 0.8244, "step": 12780 }, { "epoch": 0.746553738317757, "grad_norm": 2.2491140365600586, "learning_rate": 3.1855373896519602e-06, "loss": 0.7185, "step": 12781 }, { "epoch": 0.7466121495327103, "grad_norm": 1.2678799629211426, "learning_rate": 3.1841529327726616e-06, "loss": 0.9375, "step": 12782 }, { "epoch": 0.7466705607476636, "grad_norm": 1.232330322265625, "learning_rate": 3.1827687198370117e-06, "loss": 0.9326, "step": 12783 }, { "epoch": 0.7467289719626168, "grad_norm": 1.0828790664672852, "learning_rate": 3.1813847508945537e-06, "loss": 0.7252, "step": 12784 }, { "epoch": 0.7467873831775701, "grad_norm": 0.9174808859825134, "learning_rate": 3.1800010259948168e-06, "loss": 0.6667, "step": 12785 }, { "epoch": 0.7468457943925234, "grad_norm": 1.0138161182403564, "learning_rate": 3.178617545187329e-06, "loss": 0.742, "step": 12786 }, { "epoch": 0.7469042056074766, "grad_norm": 1.7983450889587402, "learning_rate": 3.1772343085216027e-06, "loss": 0.7859, "step": 12787 }, { "epoch": 0.7469626168224299, "grad_norm": 1.1455477476119995, "learning_rate": 3.1758513160471462e-06, "loss": 0.846, "step": 12788 }, { "epoch": 0.7470210280373831, "grad_norm": 1.1715831756591797, "learning_rate": 3.174468567813461e-06, "loss": 0.875, "step": 12789 }, { "epoch": 0.7470794392523364, "grad_norm": 1.1120792627334595, "learning_rate": 3.17308606387003e-06, "loss": 0.794, "step": 12790 }, { "epoch": 0.7471378504672898, "grad_norm": 1.249733328819275, "learning_rate": 3.1717038042663418e-06, "loss": 0.7174, "step": 12791 }, { "epoch": 0.747196261682243, "grad_norm": 0.9441935420036316, "learning_rate": 3.17032178905186e-06, "loss": 0.6921, "step": 12792 }, { "epoch": 0.7472546728971963, "grad_norm": 1.3611302375793457, "learning_rate": 3.1689400182760522e-06, "loss": 0.7773, "step": 12793 }, { "epoch": 0.7473130841121496, "grad_norm": 1.2195961475372314, "learning_rate": 3.1675584919883763e-06, "loss": 0.7799, "step": 12794 }, { "epoch": 0.7473714953271028, "grad_norm": 1.046897053718567, "learning_rate": 3.1661772102382704e-06, "loss": 0.7782, "step": 12795 }, { "epoch": 0.7474299065420561, "grad_norm": 1.3886146545410156, "learning_rate": 3.16479617307518e-06, "loss": 0.8152, "step": 12796 }, { "epoch": 0.7474883177570093, "grad_norm": 1.049636721611023, "learning_rate": 3.1634153805485245e-06, "loss": 0.5184, "step": 12797 }, { "epoch": 0.7475467289719626, "grad_norm": 7.285259246826172, "learning_rate": 3.162034832707731e-06, "loss": 0.7379, "step": 12798 }, { "epoch": 0.7476051401869159, "grad_norm": 1.0326497554779053, "learning_rate": 3.1606545296022038e-06, "loss": 0.6919, "step": 12799 }, { "epoch": 0.7476635514018691, "grad_norm": 1.0004535913467407, "learning_rate": 3.159274471281348e-06, "loss": 0.6913, "step": 12800 }, { "epoch": 0.7477219626168224, "grad_norm": 1.4767718315124512, "learning_rate": 3.15789465779456e-06, "loss": 0.7869, "step": 12801 }, { "epoch": 0.7477803738317756, "grad_norm": 1.1316182613372803, "learning_rate": 3.156515089191218e-06, "loss": 0.7559, "step": 12802 }, { "epoch": 0.747838785046729, "grad_norm": 1.0694189071655273, "learning_rate": 3.1551357655207026e-06, "loss": 0.7128, "step": 12803 }, { "epoch": 0.7478971962616823, "grad_norm": 1.3561609983444214, "learning_rate": 3.1537566868323767e-06, "loss": 0.8609, "step": 12804 }, { "epoch": 0.7479556074766355, "grad_norm": 1.1755114793777466, "learning_rate": 3.1523778531755998e-06, "loss": 0.6727, "step": 12805 }, { "epoch": 0.7480140186915888, "grad_norm": 1.3103983402252197, "learning_rate": 3.1509992645997267e-06, "loss": 0.8876, "step": 12806 }, { "epoch": 0.7480724299065421, "grad_norm": 1.3842217922210693, "learning_rate": 3.1496209211540883e-06, "loss": 0.7909, "step": 12807 }, { "epoch": 0.7481308411214953, "grad_norm": 1.5792464017868042, "learning_rate": 3.148242822888026e-06, "loss": 0.8485, "step": 12808 }, { "epoch": 0.7481892523364486, "grad_norm": 2.637173652648926, "learning_rate": 3.146864969850857e-06, "loss": 0.7241, "step": 12809 }, { "epoch": 0.7482476635514018, "grad_norm": 1.3266606330871582, "learning_rate": 3.1454873620918903e-06, "loss": 0.5521, "step": 12810 }, { "epoch": 0.7483060747663551, "grad_norm": 1.2380419969558716, "learning_rate": 3.144109999660444e-06, "loss": 0.7027, "step": 12811 }, { "epoch": 0.7483644859813084, "grad_norm": 1.08613121509552, "learning_rate": 3.142732882605807e-06, "loss": 0.7288, "step": 12812 }, { "epoch": 0.7484228971962616, "grad_norm": 1.349416732788086, "learning_rate": 3.141356010977271e-06, "loss": 0.8169, "step": 12813 }, { "epoch": 0.748481308411215, "grad_norm": 0.9422030448913574, "learning_rate": 3.1399793848241133e-06, "loss": 0.6258, "step": 12814 }, { "epoch": 0.7485397196261683, "grad_norm": 1.189638376235962, "learning_rate": 3.1386030041956004e-06, "loss": 0.7544, "step": 12815 }, { "epoch": 0.7485981308411215, "grad_norm": 1.7459771633148193, "learning_rate": 3.137226869140997e-06, "loss": 0.7934, "step": 12816 }, { "epoch": 0.7486565420560748, "grad_norm": 1.4299426078796387, "learning_rate": 3.135850979709557e-06, "loss": 0.7845, "step": 12817 }, { "epoch": 0.748714953271028, "grad_norm": 1.310624599456787, "learning_rate": 3.1344753359505275e-06, "loss": 0.7151, "step": 12818 }, { "epoch": 0.7487733644859813, "grad_norm": 1.149463176727295, "learning_rate": 3.133099937913139e-06, "loss": 0.8457, "step": 12819 }, { "epoch": 0.7488317757009346, "grad_norm": 0.8718388676643372, "learning_rate": 3.131724785646616e-06, "loss": 0.6978, "step": 12820 }, { "epoch": 0.7488901869158878, "grad_norm": 2.448920965194702, "learning_rate": 3.1303498792001786e-06, "loss": 0.7055, "step": 12821 }, { "epoch": 0.7489485981308411, "grad_norm": 1.013548493385315, "learning_rate": 3.128975218623036e-06, "loss": 0.7771, "step": 12822 }, { "epoch": 0.7490070093457943, "grad_norm": 0.9953500628471375, "learning_rate": 3.1276008039643915e-06, "loss": 0.6112, "step": 12823 }, { "epoch": 0.7490654205607477, "grad_norm": 1.080363392829895, "learning_rate": 3.126226635273433e-06, "loss": 0.7486, "step": 12824 }, { "epoch": 0.749123831775701, "grad_norm": 1.0513272285461426, "learning_rate": 3.124852712599339e-06, "loss": 0.7017, "step": 12825 }, { "epoch": 0.7491822429906542, "grad_norm": 1.3410797119140625, "learning_rate": 3.123479035991287e-06, "loss": 0.7152, "step": 12826 }, { "epoch": 0.7492406542056075, "grad_norm": 0.985468864440918, "learning_rate": 3.122105605498442e-06, "loss": 0.7534, "step": 12827 }, { "epoch": 0.7492990654205608, "grad_norm": 1.2853320837020874, "learning_rate": 3.120732421169963e-06, "loss": 0.8214, "step": 12828 }, { "epoch": 0.749357476635514, "grad_norm": 1.3031094074249268, "learning_rate": 3.1193594830549943e-06, "loss": 0.9013, "step": 12829 }, { "epoch": 0.7494158878504673, "grad_norm": 1.4035497903823853, "learning_rate": 3.1179867912026697e-06, "loss": 0.7831, "step": 12830 }, { "epoch": 0.7494742990654205, "grad_norm": 1.9602631330490112, "learning_rate": 3.1166143456621267e-06, "loss": 0.8618, "step": 12831 }, { "epoch": 0.7495327102803738, "grad_norm": 1.0807240009307861, "learning_rate": 3.115242146482479e-06, "loss": 0.8363, "step": 12832 }, { "epoch": 0.7495911214953271, "grad_norm": 0.9112011194229126, "learning_rate": 3.1138701937128415e-06, "loss": 0.7056, "step": 12833 }, { "epoch": 0.7496495327102803, "grad_norm": 1.1863008737564087, "learning_rate": 3.1124984874023203e-06, "loss": 0.6471, "step": 12834 }, { "epoch": 0.7497079439252337, "grad_norm": 1.1151124238967896, "learning_rate": 3.111127027600004e-06, "loss": 0.6405, "step": 12835 }, { "epoch": 0.749766355140187, "grad_norm": 1.912265658378601, "learning_rate": 3.1097558143549833e-06, "loss": 0.9111, "step": 12836 }, { "epoch": 0.7498247663551402, "grad_norm": 1.1954354047775269, "learning_rate": 3.10838484771633e-06, "loss": 0.7865, "step": 12837 }, { "epoch": 0.7498831775700935, "grad_norm": 1.765122413635254, "learning_rate": 3.1070141277331144e-06, "loss": 0.7797, "step": 12838 }, { "epoch": 0.7499415887850467, "grad_norm": 1.4342362880706787, "learning_rate": 3.105643654454399e-06, "loss": 0.7595, "step": 12839 }, { "epoch": 0.75, "grad_norm": 0.7670701146125793, "learning_rate": 3.1042734279292264e-06, "loss": 0.6226, "step": 12840 }, { "epoch": 0.7500584112149533, "grad_norm": 1.1341748237609863, "learning_rate": 3.1029034482066445e-06, "loss": 0.7518, "step": 12841 }, { "epoch": 0.7501168224299065, "grad_norm": 1.1626696586608887, "learning_rate": 3.101533715335684e-06, "loss": 0.7581, "step": 12842 }, { "epoch": 0.7501752336448598, "grad_norm": 1.4397433996200562, "learning_rate": 3.100164229365361e-06, "loss": 0.735, "step": 12843 }, { "epoch": 0.750233644859813, "grad_norm": 1.1090415716171265, "learning_rate": 3.0987949903447036e-06, "loss": 0.6493, "step": 12844 }, { "epoch": 0.7502920560747663, "grad_norm": 1.1221932172775269, "learning_rate": 3.0974259983227084e-06, "loss": 0.6248, "step": 12845 }, { "epoch": 0.7503504672897197, "grad_norm": 1.1002830266952515, "learning_rate": 3.096057253348378e-06, "loss": 0.5993, "step": 12846 }, { "epoch": 0.7504088785046729, "grad_norm": 1.2053844928741455, "learning_rate": 3.0946887554706972e-06, "loss": 0.9694, "step": 12847 }, { "epoch": 0.7504672897196262, "grad_norm": 1.063372254371643, "learning_rate": 3.093320504738644e-06, "loss": 0.8289, "step": 12848 }, { "epoch": 0.7505257009345795, "grad_norm": 1.334306001663208, "learning_rate": 3.091952501201191e-06, "loss": 0.7392, "step": 12849 }, { "epoch": 0.7505841121495327, "grad_norm": 1.2865701913833618, "learning_rate": 3.090584744907299e-06, "loss": 0.7967, "step": 12850 }, { "epoch": 0.750642523364486, "grad_norm": 1.6102975606918335, "learning_rate": 3.089217235905927e-06, "loss": 0.7666, "step": 12851 }, { "epoch": 0.7507009345794392, "grad_norm": 0.8850224018096924, "learning_rate": 3.0878499742460124e-06, "loss": 0.6559, "step": 12852 }, { "epoch": 0.7507593457943925, "grad_norm": 1.1836636066436768, "learning_rate": 3.08648295997649e-06, "loss": 0.8499, "step": 12853 }, { "epoch": 0.7508177570093458, "grad_norm": 1.9500056505203247, "learning_rate": 3.085116193146287e-06, "loss": 0.8213, "step": 12854 }, { "epoch": 0.750876168224299, "grad_norm": 1.169596791267395, "learning_rate": 3.0837496738043237e-06, "loss": 0.875, "step": 12855 }, { "epoch": 0.7509345794392523, "grad_norm": 1.5747601985931396, "learning_rate": 3.082383401999509e-06, "loss": 0.9099, "step": 12856 }, { "epoch": 0.7509929906542057, "grad_norm": 1.043115258216858, "learning_rate": 3.0810173777807417e-06, "loss": 0.7246, "step": 12857 }, { "epoch": 0.7510514018691589, "grad_norm": 1.4385535717010498, "learning_rate": 3.079651601196908e-06, "loss": 0.631, "step": 12858 }, { "epoch": 0.7511098130841122, "grad_norm": 1.1644023656845093, "learning_rate": 3.078286072296893e-06, "loss": 0.6607, "step": 12859 }, { "epoch": 0.7511682242990654, "grad_norm": 1.348388910293579, "learning_rate": 3.0769207911295718e-06, "loss": 0.6883, "step": 12860 }, { "epoch": 0.7512266355140187, "grad_norm": 1.4902247190475464, "learning_rate": 3.07555575774381e-06, "loss": 0.8789, "step": 12861 }, { "epoch": 0.751285046728972, "grad_norm": 1.4798979759216309, "learning_rate": 3.074190972188461e-06, "loss": 0.8197, "step": 12862 }, { "epoch": 0.7513434579439252, "grad_norm": 0.9532703161239624, "learning_rate": 3.0728264345123673e-06, "loss": 0.7492, "step": 12863 }, { "epoch": 0.7514018691588785, "grad_norm": 1.0777148008346558, "learning_rate": 3.071462144764373e-06, "loss": 0.6496, "step": 12864 }, { "epoch": 0.7514602803738317, "grad_norm": 1.144971251487732, "learning_rate": 3.0700981029933017e-06, "loss": 0.6792, "step": 12865 }, { "epoch": 0.751518691588785, "grad_norm": 3.120476484298706, "learning_rate": 3.068734309247976e-06, "loss": 0.847, "step": 12866 }, { "epoch": 0.7515771028037384, "grad_norm": 0.8076434135437012, "learning_rate": 3.0673707635772097e-06, "loss": 0.6058, "step": 12867 }, { "epoch": 0.7516355140186916, "grad_norm": 1.1928865909576416, "learning_rate": 3.0660074660297988e-06, "loss": 0.8264, "step": 12868 }, { "epoch": 0.7516939252336449, "grad_norm": 1.692980408668518, "learning_rate": 3.064644416654543e-06, "loss": 0.7692, "step": 12869 }, { "epoch": 0.7517523364485982, "grad_norm": 1.2419817447662354, "learning_rate": 3.063281615500221e-06, "loss": 0.6815, "step": 12870 }, { "epoch": 0.7518107476635514, "grad_norm": 1.0745469331741333, "learning_rate": 3.06191906261561e-06, "loss": 0.8908, "step": 12871 }, { "epoch": 0.7518691588785047, "grad_norm": 1.2886114120483398, "learning_rate": 3.060556758049481e-06, "loss": 0.6614, "step": 12872 }, { "epoch": 0.7519275700934579, "grad_norm": 1.2821706533432007, "learning_rate": 3.0591947018505863e-06, "loss": 0.7514, "step": 12873 }, { "epoch": 0.7519859813084112, "grad_norm": 3.3508293628692627, "learning_rate": 3.0578328940676782e-06, "loss": 0.8299, "step": 12874 }, { "epoch": 0.7520443925233645, "grad_norm": 1.1649316549301147, "learning_rate": 3.0564713347494936e-06, "loss": 0.7992, "step": 12875 }, { "epoch": 0.7521028037383177, "grad_norm": 1.6432842016220093, "learning_rate": 3.055110023944765e-06, "loss": 0.7765, "step": 12876 }, { "epoch": 0.752161214953271, "grad_norm": 1.0458729267120361, "learning_rate": 3.053748961702219e-06, "loss": 0.9106, "step": 12877 }, { "epoch": 0.7522196261682244, "grad_norm": 1.2222250699996948, "learning_rate": 3.052388148070561e-06, "loss": 0.8122, "step": 12878 }, { "epoch": 0.7522780373831776, "grad_norm": 1.2063337564468384, "learning_rate": 3.0510275830985013e-06, "loss": 0.8351, "step": 12879 }, { "epoch": 0.7523364485981309, "grad_norm": 1.2404701709747314, "learning_rate": 3.0496672668347318e-06, "loss": 1.0544, "step": 12880 }, { "epoch": 0.7523948598130841, "grad_norm": 1.3795772790908813, "learning_rate": 3.0483071993279433e-06, "loss": 0.9397, "step": 12881 }, { "epoch": 0.7524532710280374, "grad_norm": 1.7059379816055298, "learning_rate": 3.046947380626808e-06, "loss": 0.7675, "step": 12882 }, { "epoch": 0.7525116822429907, "grad_norm": 1.4576873779296875, "learning_rate": 3.0455878107799985e-06, "loss": 0.8321, "step": 12883 }, { "epoch": 0.7525700934579439, "grad_norm": 0.960673987865448, "learning_rate": 3.0442284898361764e-06, "loss": 0.726, "step": 12884 }, { "epoch": 0.7526285046728972, "grad_norm": 1.026743769645691, "learning_rate": 3.0428694178439887e-06, "loss": 0.5988, "step": 12885 }, { "epoch": 0.7526869158878504, "grad_norm": 1.8452785015106201, "learning_rate": 3.041510594852077e-06, "loss": 0.8973, "step": 12886 }, { "epoch": 0.7527453271028037, "grad_norm": 1.5590687990188599, "learning_rate": 3.0401520209090774e-06, "loss": 0.8063, "step": 12887 }, { "epoch": 0.752803738317757, "grad_norm": 0.9601745009422302, "learning_rate": 3.038793696063612e-06, "loss": 0.6808, "step": 12888 }, { "epoch": 0.7528621495327102, "grad_norm": 1.1437488794326782, "learning_rate": 3.0374356203643008e-06, "loss": 0.6666, "step": 12889 }, { "epoch": 0.7529205607476636, "grad_norm": 0.9718766808509827, "learning_rate": 3.0360777938597463e-06, "loss": 0.9059, "step": 12890 }, { "epoch": 0.7529789719626169, "grad_norm": 1.0218883752822876, "learning_rate": 3.0347202165985435e-06, "loss": 0.8919, "step": 12891 }, { "epoch": 0.7530373831775701, "grad_norm": 1.1095784902572632, "learning_rate": 3.033362888629284e-06, "loss": 0.7548, "step": 12892 }, { "epoch": 0.7530957943925234, "grad_norm": 1.2966785430908203, "learning_rate": 3.0320058100005477e-06, "loss": 0.6161, "step": 12893 }, { "epoch": 0.7531542056074766, "grad_norm": 1.5306357145309448, "learning_rate": 3.0306489807609075e-06, "loss": 0.8889, "step": 12894 }, { "epoch": 0.7532126168224299, "grad_norm": 1.19408118724823, "learning_rate": 3.029292400958923e-06, "loss": 0.7206, "step": 12895 }, { "epoch": 0.7532710280373832, "grad_norm": 1.3770816326141357, "learning_rate": 3.0279360706431437e-06, "loss": 0.8654, "step": 12896 }, { "epoch": 0.7533294392523364, "grad_norm": 1.116404414176941, "learning_rate": 3.0265799898621196e-06, "loss": 0.819, "step": 12897 }, { "epoch": 0.7533878504672897, "grad_norm": 1.1480975151062012, "learning_rate": 3.0252241586643805e-06, "loss": 0.6416, "step": 12898 }, { "epoch": 0.753446261682243, "grad_norm": 1.6581158638000488, "learning_rate": 3.0238685770984534e-06, "loss": 0.6025, "step": 12899 }, { "epoch": 0.7535046728971962, "grad_norm": 1.1675535440444946, "learning_rate": 3.0225132452128614e-06, "loss": 0.7257, "step": 12900 }, { "epoch": 0.7535630841121496, "grad_norm": 1.3605834245681763, "learning_rate": 3.0211581630561036e-06, "loss": 0.996, "step": 12901 }, { "epoch": 0.7536214953271028, "grad_norm": 1.1750380992889404, "learning_rate": 3.0198033306766873e-06, "loss": 0.8401, "step": 12902 }, { "epoch": 0.7536799065420561, "grad_norm": 0.9080755114555359, "learning_rate": 3.018448748123097e-06, "loss": 0.6623, "step": 12903 }, { "epoch": 0.7537383177570094, "grad_norm": 1.3953933715820312, "learning_rate": 3.0170944154438152e-06, "loss": 0.7554, "step": 12904 }, { "epoch": 0.7537967289719626, "grad_norm": 1.25984787940979, "learning_rate": 3.01574033268732e-06, "loss": 0.6591, "step": 12905 }, { "epoch": 0.7538551401869159, "grad_norm": 1.3513214588165283, "learning_rate": 3.0143864999020665e-06, "loss": 0.662, "step": 12906 }, { "epoch": 0.7539135514018691, "grad_norm": 0.9157570004463196, "learning_rate": 3.013032917136518e-06, "loss": 0.674, "step": 12907 }, { "epoch": 0.7539719626168224, "grad_norm": 1.1066336631774902, "learning_rate": 3.011679584439111e-06, "loss": 0.658, "step": 12908 }, { "epoch": 0.7540303738317757, "grad_norm": 1.0397967100143433, "learning_rate": 3.0103265018582863e-06, "loss": 0.786, "step": 12909 }, { "epoch": 0.7540887850467289, "grad_norm": 1.3769861459732056, "learning_rate": 3.008973669442475e-06, "loss": 0.8334, "step": 12910 }, { "epoch": 0.7541471962616823, "grad_norm": 1.0753592252731323, "learning_rate": 3.00762108724009e-06, "loss": 0.6818, "step": 12911 }, { "epoch": 0.7542056074766356, "grad_norm": 0.9917983412742615, "learning_rate": 3.0062687552995475e-06, "loss": 0.8459, "step": 12912 }, { "epoch": 0.7542640186915888, "grad_norm": 1.7516953945159912, "learning_rate": 3.0049166736692416e-06, "loss": 0.8466, "step": 12913 }, { "epoch": 0.7543224299065421, "grad_norm": 1.3478926420211792, "learning_rate": 3.0035648423975694e-06, "loss": 0.7931, "step": 12914 }, { "epoch": 0.7543808411214953, "grad_norm": 1.0801115036010742, "learning_rate": 3.002213261532909e-06, "loss": 0.6054, "step": 12915 }, { "epoch": 0.7544392523364486, "grad_norm": 1.2603511810302734, "learning_rate": 3.0008619311236376e-06, "loss": 0.7424, "step": 12916 }, { "epoch": 0.7544976635514019, "grad_norm": 1.9814600944519043, "learning_rate": 2.9995108512181227e-06, "loss": 0.7127, "step": 12917 }, { "epoch": 0.7545560747663551, "grad_norm": 0.9927541613578796, "learning_rate": 2.9981600218647144e-06, "loss": 0.6926, "step": 12918 }, { "epoch": 0.7546144859813084, "grad_norm": 0.9201173782348633, "learning_rate": 2.9968094431117655e-06, "loss": 0.7516, "step": 12919 }, { "epoch": 0.7546728971962616, "grad_norm": 1.3484927415847778, "learning_rate": 2.9954591150076084e-06, "loss": 0.5596, "step": 12920 }, { "epoch": 0.7547313084112149, "grad_norm": 1.2357600927352905, "learning_rate": 2.9941090376005742e-06, "loss": 0.8279, "step": 12921 }, { "epoch": 0.7547897196261683, "grad_norm": 6.146370887756348, "learning_rate": 2.992759210938988e-06, "loss": 0.8405, "step": 12922 }, { "epoch": 0.7548481308411215, "grad_norm": 2.0688960552215576, "learning_rate": 2.991409635071154e-06, "loss": 0.6713, "step": 12923 }, { "epoch": 0.7549065420560748, "grad_norm": 1.033347249031067, "learning_rate": 2.990060310045381e-06, "loss": 0.6781, "step": 12924 }, { "epoch": 0.7549649532710281, "grad_norm": 1.5558979511260986, "learning_rate": 2.9887112359099536e-06, "loss": 0.8689, "step": 12925 }, { "epoch": 0.7550233644859813, "grad_norm": 1.5780218839645386, "learning_rate": 2.9873624127131628e-06, "loss": 0.9057, "step": 12926 }, { "epoch": 0.7550817757009346, "grad_norm": 0.8947979211807251, "learning_rate": 2.9860138405032846e-06, "loss": 0.7339, "step": 12927 }, { "epoch": 0.7551401869158878, "grad_norm": 1.5459668636322021, "learning_rate": 2.98466551932858e-06, "loss": 0.8254, "step": 12928 }, { "epoch": 0.7551985981308411, "grad_norm": 1.0999685525894165, "learning_rate": 2.983317449237312e-06, "loss": 0.6933, "step": 12929 }, { "epoch": 0.7552570093457944, "grad_norm": 1.650497317314148, "learning_rate": 2.9819696302777257e-06, "loss": 0.8053, "step": 12930 }, { "epoch": 0.7553154205607476, "grad_norm": 1.1699333190917969, "learning_rate": 2.9806220624980584e-06, "loss": 0.7792, "step": 12931 }, { "epoch": 0.7553738317757009, "grad_norm": 1.2427667379379272, "learning_rate": 2.979274745946542e-06, "loss": 0.7885, "step": 12932 }, { "epoch": 0.7554322429906543, "grad_norm": 1.8828214406967163, "learning_rate": 2.9779276806713998e-06, "loss": 0.8439, "step": 12933 }, { "epoch": 0.7554906542056075, "grad_norm": 1.4162664413452148, "learning_rate": 2.9765808667208452e-06, "loss": 0.8606, "step": 12934 }, { "epoch": 0.7555490654205608, "grad_norm": 1.5582655668258667, "learning_rate": 2.97523430414308e-06, "loss": 0.9196, "step": 12935 }, { "epoch": 0.755607476635514, "grad_norm": 1.2662745714187622, "learning_rate": 2.973887992986294e-06, "loss": 0.8489, "step": 12936 }, { "epoch": 0.7556658878504673, "grad_norm": 0.8726274967193604, "learning_rate": 2.9725419332986772e-06, "loss": 0.8272, "step": 12937 }, { "epoch": 0.7557242990654206, "grad_norm": 1.3113385438919067, "learning_rate": 2.971196125128405e-06, "loss": 0.7204, "step": 12938 }, { "epoch": 0.7557827102803738, "grad_norm": 1.580777883529663, "learning_rate": 2.969850568523648e-06, "loss": 0.8192, "step": 12939 }, { "epoch": 0.7558411214953271, "grad_norm": 0.9781416058540344, "learning_rate": 2.9685052635325616e-06, "loss": 0.7586, "step": 12940 }, { "epoch": 0.7558995327102803, "grad_norm": 1.6521035432815552, "learning_rate": 2.9671602102032926e-06, "loss": 0.9274, "step": 12941 }, { "epoch": 0.7559579439252336, "grad_norm": 1.1935142278671265, "learning_rate": 2.965815408583983e-06, "loss": 0.671, "step": 12942 }, { "epoch": 0.756016355140187, "grad_norm": 1.209160566329956, "learning_rate": 2.9644708587227687e-06, "loss": 0.8369, "step": 12943 }, { "epoch": 0.7560747663551401, "grad_norm": 1.3196214437484741, "learning_rate": 2.963126560667765e-06, "loss": 0.7008, "step": 12944 }, { "epoch": 0.7561331775700935, "grad_norm": 1.15262770652771, "learning_rate": 2.961782514467092e-06, "loss": 0.7961, "step": 12945 }, { "epoch": 0.7561915887850468, "grad_norm": 0.8724417686462402, "learning_rate": 2.9604387201688466e-06, "loss": 0.6548, "step": 12946 }, { "epoch": 0.75625, "grad_norm": 1.2080721855163574, "learning_rate": 2.959095177821132e-06, "loss": 0.8725, "step": 12947 }, { "epoch": 0.7563084112149533, "grad_norm": 1.0301979780197144, "learning_rate": 2.957751887472027e-06, "loss": 0.8534, "step": 12948 }, { "epoch": 0.7563668224299065, "grad_norm": 1.4818181991577148, "learning_rate": 2.956408849169612e-06, "loss": 0.94, "step": 12949 }, { "epoch": 0.7564252336448598, "grad_norm": 1.0535767078399658, "learning_rate": 2.9550660629619586e-06, "loss": 0.6664, "step": 12950 }, { "epoch": 0.7564836448598131, "grad_norm": 1.2287181615829468, "learning_rate": 2.95372352889712e-06, "loss": 0.7846, "step": 12951 }, { "epoch": 0.7565420560747663, "grad_norm": 1.3864796161651611, "learning_rate": 2.952381247023153e-06, "loss": 0.8074, "step": 12952 }, { "epoch": 0.7566004672897196, "grad_norm": 0.868218719959259, "learning_rate": 2.9510392173880906e-06, "loss": 0.625, "step": 12953 }, { "epoch": 0.756658878504673, "grad_norm": 0.8794881701469421, "learning_rate": 2.9496974400399714e-06, "loss": 0.7124, "step": 12954 }, { "epoch": 0.7567172897196262, "grad_norm": 1.681388258934021, "learning_rate": 2.948355915026818e-06, "loss": 0.9112, "step": 12955 }, { "epoch": 0.7567757009345795, "grad_norm": 1.0655325651168823, "learning_rate": 2.9470146423966404e-06, "loss": 0.7739, "step": 12956 }, { "epoch": 0.7568341121495327, "grad_norm": 0.9789931178092957, "learning_rate": 2.945673622197449e-06, "loss": 0.7839, "step": 12957 }, { "epoch": 0.756892523364486, "grad_norm": 1.3656023740768433, "learning_rate": 2.9443328544772343e-06, "loss": 0.6642, "step": 12958 }, { "epoch": 0.7569509345794393, "grad_norm": 1.1537880897521973, "learning_rate": 2.9429923392839855e-06, "loss": 0.7262, "step": 12959 }, { "epoch": 0.7570093457943925, "grad_norm": 1.0573735237121582, "learning_rate": 2.9416520766656844e-06, "loss": 0.8353, "step": 12960 }, { "epoch": 0.7570677570093458, "grad_norm": 1.0759665966033936, "learning_rate": 2.940312066670293e-06, "loss": 0.8196, "step": 12961 }, { "epoch": 0.757126168224299, "grad_norm": 0.9832799434661865, "learning_rate": 2.938972309345778e-06, "loss": 0.6685, "step": 12962 }, { "epoch": 0.7571845794392523, "grad_norm": 0.9437094330787659, "learning_rate": 2.937632804740087e-06, "loss": 0.7839, "step": 12963 }, { "epoch": 0.7572429906542056, "grad_norm": 1.3016122579574585, "learning_rate": 2.936293552901157e-06, "loss": 0.7037, "step": 12964 }, { "epoch": 0.7573014018691588, "grad_norm": 1.9338724613189697, "learning_rate": 2.9349545538769265e-06, "loss": 0.8893, "step": 12965 }, { "epoch": 0.7573598130841122, "grad_norm": 2.340980052947998, "learning_rate": 2.9336158077153176e-06, "loss": 0.7945, "step": 12966 }, { "epoch": 0.7574182242990655, "grad_norm": 0.7695824503898621, "learning_rate": 2.932277314464248e-06, "loss": 0.5909, "step": 12967 }, { "epoch": 0.7574766355140187, "grad_norm": 0.9182835221290588, "learning_rate": 2.9309390741716214e-06, "loss": 0.5785, "step": 12968 }, { "epoch": 0.757535046728972, "grad_norm": 1.2957344055175781, "learning_rate": 2.9296010868853296e-06, "loss": 0.7375, "step": 12969 }, { "epoch": 0.7575934579439252, "grad_norm": 1.4853217601776123, "learning_rate": 2.928263352653263e-06, "loss": 0.8744, "step": 12970 }, { "epoch": 0.7576518691588785, "grad_norm": 1.3787692785263062, "learning_rate": 2.926925871523302e-06, "loss": 0.913, "step": 12971 }, { "epoch": 0.7577102803738318, "grad_norm": 1.1227449178695679, "learning_rate": 2.925588643543318e-06, "loss": 0.6381, "step": 12972 }, { "epoch": 0.757768691588785, "grad_norm": 0.9861204624176025, "learning_rate": 2.924251668761167e-06, "loss": 0.5648, "step": 12973 }, { "epoch": 0.7578271028037383, "grad_norm": 1.5973163843154907, "learning_rate": 2.9229149472246976e-06, "loss": 0.8295, "step": 12974 }, { "epoch": 0.7578855140186916, "grad_norm": 1.024232029914856, "learning_rate": 2.921578478981757e-06, "loss": 0.8875, "step": 12975 }, { "epoch": 0.7579439252336448, "grad_norm": 1.5131902694702148, "learning_rate": 2.9202422640801755e-06, "loss": 0.822, "step": 12976 }, { "epoch": 0.7580023364485982, "grad_norm": 1.1474956274032593, "learning_rate": 2.918906302567782e-06, "loss": 0.6082, "step": 12977 }, { "epoch": 0.7580607476635514, "grad_norm": 1.8659013509750366, "learning_rate": 2.9175705944923884e-06, "loss": 0.7806, "step": 12978 }, { "epoch": 0.7581191588785047, "grad_norm": 0.903160035610199, "learning_rate": 2.9162351399017964e-06, "loss": 0.6492, "step": 12979 }, { "epoch": 0.758177570093458, "grad_norm": 0.988872766494751, "learning_rate": 2.9148999388438094e-06, "loss": 0.8749, "step": 12980 }, { "epoch": 0.7582359813084112, "grad_norm": 0.9330278038978577, "learning_rate": 2.913564991366209e-06, "loss": 0.599, "step": 12981 }, { "epoch": 0.7582943925233645, "grad_norm": 1.017122745513916, "learning_rate": 2.9122302975167773e-06, "loss": 0.7503, "step": 12982 }, { "epoch": 0.7583528037383177, "grad_norm": 4.030069351196289, "learning_rate": 2.9108958573432864e-06, "loss": 0.6784, "step": 12983 }, { "epoch": 0.758411214953271, "grad_norm": 0.9117748141288757, "learning_rate": 2.9095616708934903e-06, "loss": 0.6274, "step": 12984 }, { "epoch": 0.7584696261682243, "grad_norm": 1.405185341835022, "learning_rate": 2.908227738215148e-06, "loss": 0.9, "step": 12985 }, { "epoch": 0.7585280373831775, "grad_norm": 1.1333398818969727, "learning_rate": 2.9068940593559946e-06, "loss": 0.7589, "step": 12986 }, { "epoch": 0.7585864485981308, "grad_norm": 0.9853311777114868, "learning_rate": 2.9055606343637667e-06, "loss": 0.6761, "step": 12987 }, { "epoch": 0.7586448598130842, "grad_norm": 1.7501790523529053, "learning_rate": 2.904227463286191e-06, "loss": 0.794, "step": 12988 }, { "epoch": 0.7587032710280374, "grad_norm": 1.5120751857757568, "learning_rate": 2.902894546170978e-06, "loss": 0.7929, "step": 12989 }, { "epoch": 0.7587616822429907, "grad_norm": 1.1878429651260376, "learning_rate": 2.9015618830658375e-06, "loss": 0.7539, "step": 12990 }, { "epoch": 0.7588200934579439, "grad_norm": 1.1883114576339722, "learning_rate": 2.9002294740184613e-06, "loss": 0.9159, "step": 12991 }, { "epoch": 0.7588785046728972, "grad_norm": 1.988878846168518, "learning_rate": 2.8988973190765413e-06, "loss": 0.8604, "step": 12992 }, { "epoch": 0.7589369158878505, "grad_norm": 1.7969757318496704, "learning_rate": 2.8975654182877576e-06, "loss": 0.6729, "step": 12993 }, { "epoch": 0.7589953271028037, "grad_norm": 1.4191175699234009, "learning_rate": 2.8962337716997755e-06, "loss": 0.7269, "step": 12994 }, { "epoch": 0.759053738317757, "grad_norm": 1.6548008918762207, "learning_rate": 2.8949023793602595e-06, "loss": 0.7648, "step": 12995 }, { "epoch": 0.7591121495327103, "grad_norm": 1.9610555171966553, "learning_rate": 2.893571241316857e-06, "loss": 0.7401, "step": 12996 }, { "epoch": 0.7591705607476635, "grad_norm": 1.8440392017364502, "learning_rate": 2.892240357617214e-06, "loss": 0.8354, "step": 12997 }, { "epoch": 0.7592289719626168, "grad_norm": 1.2703773975372314, "learning_rate": 2.8909097283089606e-06, "loss": 0.8281, "step": 12998 }, { "epoch": 0.75928738317757, "grad_norm": 1.8927377462387085, "learning_rate": 2.889579353439721e-06, "loss": 0.7986, "step": 12999 }, { "epoch": 0.7593457943925234, "grad_norm": 1.516923427581787, "learning_rate": 2.8882492330571153e-06, "loss": 0.5847, "step": 13000 }, { "epoch": 0.7594042056074767, "grad_norm": 1.2353788614273071, "learning_rate": 2.886919367208746e-06, "loss": 0.6683, "step": 13001 }, { "epoch": 0.7594626168224299, "grad_norm": 1.283774971961975, "learning_rate": 2.8855897559422053e-06, "loss": 0.9794, "step": 13002 }, { "epoch": 0.7595210280373832, "grad_norm": 1.1722384691238403, "learning_rate": 2.8842603993050865e-06, "loss": 0.7005, "step": 13003 }, { "epoch": 0.7595794392523364, "grad_norm": 1.2072851657867432, "learning_rate": 2.882931297344965e-06, "loss": 0.7392, "step": 13004 }, { "epoch": 0.7596378504672897, "grad_norm": 1.6070963144302368, "learning_rate": 2.8816024501094166e-06, "loss": 0.8244, "step": 13005 }, { "epoch": 0.759696261682243, "grad_norm": 1.1925150156021118, "learning_rate": 2.8802738576459966e-06, "loss": 0.7812, "step": 13006 }, { "epoch": 0.7597546728971962, "grad_norm": 1.1013730764389038, "learning_rate": 2.878945520002252e-06, "loss": 0.7973, "step": 13007 }, { "epoch": 0.7598130841121495, "grad_norm": 1.2488778829574585, "learning_rate": 2.8776174372257316e-06, "loss": 0.6042, "step": 13008 }, { "epoch": 0.7598714953271029, "grad_norm": 1.7097816467285156, "learning_rate": 2.8762896093639648e-06, "loss": 0.8137, "step": 13009 }, { "epoch": 0.759929906542056, "grad_norm": 0.9061761498451233, "learning_rate": 2.87496203646448e-06, "loss": 0.664, "step": 13010 }, { "epoch": 0.7599883177570094, "grad_norm": 1.2184196710586548, "learning_rate": 2.873634718574789e-06, "loss": 0.7228, "step": 13011 }, { "epoch": 0.7600467289719626, "grad_norm": 2.2845029830932617, "learning_rate": 2.8723076557423934e-06, "loss": 0.7418, "step": 13012 }, { "epoch": 0.7601051401869159, "grad_norm": 1.1049230098724365, "learning_rate": 2.8709808480147974e-06, "loss": 0.7133, "step": 13013 }, { "epoch": 0.7601635514018692, "grad_norm": 1.2137138843536377, "learning_rate": 2.8696542954394802e-06, "loss": 0.7106, "step": 13014 }, { "epoch": 0.7602219626168224, "grad_norm": 1.1809208393096924, "learning_rate": 2.8683279980639246e-06, "loss": 0.6475, "step": 13015 }, { "epoch": 0.7602803738317757, "grad_norm": 1.598320484161377, "learning_rate": 2.8670019559356023e-06, "loss": 0.7232, "step": 13016 }, { "epoch": 0.760338785046729, "grad_norm": 1.638777494430542, "learning_rate": 2.8656761691019673e-06, "loss": 0.6554, "step": 13017 }, { "epoch": 0.7603971962616822, "grad_norm": 1.235036015510559, "learning_rate": 2.8643506376104757e-06, "loss": 0.7271, "step": 13018 }, { "epoch": 0.7604556074766355, "grad_norm": 1.1946440935134888, "learning_rate": 2.8630253615085636e-06, "loss": 0.5727, "step": 13019 }, { "epoch": 0.7605140186915887, "grad_norm": 1.3977024555206299, "learning_rate": 2.861700340843666e-06, "loss": 0.6114, "step": 13020 }, { "epoch": 0.7605724299065421, "grad_norm": 1.1529241800308228, "learning_rate": 2.86037557566321e-06, "loss": 0.9532, "step": 13021 }, { "epoch": 0.7606308411214954, "grad_norm": 1.187996745109558, "learning_rate": 2.859051066014604e-06, "loss": 0.7367, "step": 13022 }, { "epoch": 0.7606892523364486, "grad_norm": 1.3428683280944824, "learning_rate": 2.8577268119452584e-06, "loss": 0.9992, "step": 13023 }, { "epoch": 0.7607476635514019, "grad_norm": 1.7736756801605225, "learning_rate": 2.8564028135025635e-06, "loss": 0.7251, "step": 13024 }, { "epoch": 0.7608060747663551, "grad_norm": 1.0693702697753906, "learning_rate": 2.8550790707339084e-06, "loss": 0.5303, "step": 13025 }, { "epoch": 0.7608644859813084, "grad_norm": 1.47708261013031, "learning_rate": 2.853755583686675e-06, "loss": 0.823, "step": 13026 }, { "epoch": 0.7609228971962617, "grad_norm": 1.3415213823318481, "learning_rate": 2.852432352408224e-06, "loss": 0.6453, "step": 13027 }, { "epoch": 0.7609813084112149, "grad_norm": 2.22694730758667, "learning_rate": 2.8511093769459217e-06, "loss": 0.885, "step": 13028 }, { "epoch": 0.7610397196261682, "grad_norm": 0.8885108828544617, "learning_rate": 2.8497866573471133e-06, "loss": 0.6821, "step": 13029 }, { "epoch": 0.7610981308411215, "grad_norm": 1.2360574007034302, "learning_rate": 2.848464193659144e-06, "loss": 0.6262, "step": 13030 }, { "epoch": 0.7611565420560747, "grad_norm": 1.145754337310791, "learning_rate": 2.8471419859293416e-06, "loss": 0.7698, "step": 13031 }, { "epoch": 0.7612149532710281, "grad_norm": 1.2122397422790527, "learning_rate": 2.845820034205029e-06, "loss": 0.5722, "step": 13032 }, { "epoch": 0.7612733644859813, "grad_norm": 1.1215486526489258, "learning_rate": 2.8444983385335255e-06, "loss": 0.8255, "step": 13033 }, { "epoch": 0.7613317757009346, "grad_norm": 0.9968143105506897, "learning_rate": 2.8431768989621278e-06, "loss": 0.6448, "step": 13034 }, { "epoch": 0.7613901869158879, "grad_norm": 1.7173075675964355, "learning_rate": 2.8418557155381376e-06, "loss": 0.643, "step": 13035 }, { "epoch": 0.7614485981308411, "grad_norm": 1.0635173320770264, "learning_rate": 2.840534788308835e-06, "loss": 0.6549, "step": 13036 }, { "epoch": 0.7615070093457944, "grad_norm": 0.8694619536399841, "learning_rate": 2.839214117321499e-06, "loss": 0.5347, "step": 13037 }, { "epoch": 0.7615654205607477, "grad_norm": 1.0652368068695068, "learning_rate": 2.837893702623402e-06, "loss": 0.8199, "step": 13038 }, { "epoch": 0.7616238317757009, "grad_norm": 0.9015920162200928, "learning_rate": 2.8365735442617957e-06, "loss": 0.557, "step": 13039 }, { "epoch": 0.7616822429906542, "grad_norm": 1.7403570413589478, "learning_rate": 2.835253642283935e-06, "loss": 0.8002, "step": 13040 }, { "epoch": 0.7617406542056074, "grad_norm": 1.1232832670211792, "learning_rate": 2.833933996737054e-06, "loss": 0.7021, "step": 13041 }, { "epoch": 0.7617990654205608, "grad_norm": 1.7722219228744507, "learning_rate": 2.832614607668388e-06, "loss": 0.6843, "step": 13042 }, { "epoch": 0.7618574766355141, "grad_norm": 1.355070948600769, "learning_rate": 2.83129547512516e-06, "loss": 0.696, "step": 13043 }, { "epoch": 0.7619158878504673, "grad_norm": 1.53472900390625, "learning_rate": 2.829976599154577e-06, "loss": 0.7606, "step": 13044 }, { "epoch": 0.7619742990654206, "grad_norm": 1.0560134649276733, "learning_rate": 2.8286579798038494e-06, "loss": 0.8962, "step": 13045 }, { "epoch": 0.7620327102803738, "grad_norm": 1.4829699993133545, "learning_rate": 2.827339617120168e-06, "loss": 0.7664, "step": 13046 }, { "epoch": 0.7620911214953271, "grad_norm": 1.140950322151184, "learning_rate": 2.826021511150715e-06, "loss": 0.8739, "step": 13047 }, { "epoch": 0.7621495327102804, "grad_norm": 1.0246955156326294, "learning_rate": 2.824703661942669e-06, "loss": 0.7204, "step": 13048 }, { "epoch": 0.7622079439252336, "grad_norm": 0.9701436161994934, "learning_rate": 2.823386069543197e-06, "loss": 0.7741, "step": 13049 }, { "epoch": 0.7622663551401869, "grad_norm": 0.9782329201698303, "learning_rate": 2.822068733999459e-06, "loss": 0.6375, "step": 13050 }, { "epoch": 0.7623247663551402, "grad_norm": 2.1466152667999268, "learning_rate": 2.8207516553586014e-06, "loss": 0.6905, "step": 13051 }, { "epoch": 0.7623831775700934, "grad_norm": 1.0112948417663574, "learning_rate": 2.819434833667758e-06, "loss": 0.7597, "step": 13052 }, { "epoch": 0.7624415887850468, "grad_norm": 1.3153355121612549, "learning_rate": 2.818118268974065e-06, "loss": 0.7796, "step": 13053 }, { "epoch": 0.7625, "grad_norm": 1.2237905263900757, "learning_rate": 2.81680196132464e-06, "loss": 0.8664, "step": 13054 }, { "epoch": 0.7625584112149533, "grad_norm": 1.0793744325637817, "learning_rate": 2.815485910766599e-06, "loss": 0.7651, "step": 13055 }, { "epoch": 0.7626168224299066, "grad_norm": 0.875059962272644, "learning_rate": 2.8141701173470417e-06, "loss": 0.5451, "step": 13056 }, { "epoch": 0.7626752336448598, "grad_norm": 1.3208935260772705, "learning_rate": 2.812854581113057e-06, "loss": 0.6439, "step": 13057 }, { "epoch": 0.7627336448598131, "grad_norm": 1.1871176958084106, "learning_rate": 2.8115393021117323e-06, "loss": 0.7925, "step": 13058 }, { "epoch": 0.7627920560747663, "grad_norm": 1.0964070558547974, "learning_rate": 2.8102242803901457e-06, "loss": 0.6827, "step": 13059 }, { "epoch": 0.7628504672897196, "grad_norm": 1.4012283086776733, "learning_rate": 2.808909515995357e-06, "loss": 0.7755, "step": 13060 }, { "epoch": 0.7629088785046729, "grad_norm": 1.2219318151474, "learning_rate": 2.8075950089744285e-06, "loss": 0.7568, "step": 13061 }, { "epoch": 0.7629672897196261, "grad_norm": 0.9833552837371826, "learning_rate": 2.806280759374399e-06, "loss": 0.6749, "step": 13062 }, { "epoch": 0.7630257009345794, "grad_norm": 1.0614248514175415, "learning_rate": 2.8049667672423155e-06, "loss": 0.72, "step": 13063 }, { "epoch": 0.7630841121495328, "grad_norm": 1.2109591960906982, "learning_rate": 2.8036530326251986e-06, "loss": 0.7302, "step": 13064 }, { "epoch": 0.763142523364486, "grad_norm": 1.5175193548202515, "learning_rate": 2.8023395555700717e-06, "loss": 0.7015, "step": 13065 }, { "epoch": 0.7632009345794393, "grad_norm": 1.6709346771240234, "learning_rate": 2.801026336123948e-06, "loss": 0.8934, "step": 13066 }, { "epoch": 0.7632593457943925, "grad_norm": 0.9762141704559326, "learning_rate": 2.7997133743338213e-06, "loss": 0.703, "step": 13067 }, { "epoch": 0.7633177570093458, "grad_norm": 1.1632411479949951, "learning_rate": 2.7984006702466906e-06, "loss": 0.7434, "step": 13068 }, { "epoch": 0.7633761682242991, "grad_norm": 1.7461031675338745, "learning_rate": 2.797088223909532e-06, "loss": 0.8275, "step": 13069 }, { "epoch": 0.7634345794392523, "grad_norm": 1.0900393724441528, "learning_rate": 2.7957760353693207e-06, "loss": 0.6544, "step": 13070 }, { "epoch": 0.7634929906542056, "grad_norm": 1.0897977352142334, "learning_rate": 2.794464104673027e-06, "loss": 0.7417, "step": 13071 }, { "epoch": 0.7635514018691589, "grad_norm": 1.1404330730438232, "learning_rate": 2.793152431867596e-06, "loss": 0.6704, "step": 13072 }, { "epoch": 0.7636098130841121, "grad_norm": 1.1935505867004395, "learning_rate": 2.791841016999982e-06, "loss": 0.6988, "step": 13073 }, { "epoch": 0.7636682242990654, "grad_norm": 3.5972986221313477, "learning_rate": 2.7905298601171147e-06, "loss": 0.754, "step": 13074 }, { "epoch": 0.7637266355140186, "grad_norm": 1.4827022552490234, "learning_rate": 2.789218961265924e-06, "loss": 0.8478, "step": 13075 }, { "epoch": 0.763785046728972, "grad_norm": 1.0932728052139282, "learning_rate": 2.78790832049333e-06, "loss": 0.659, "step": 13076 }, { "epoch": 0.7638434579439253, "grad_norm": 1.2480146884918213, "learning_rate": 2.786597937846237e-06, "loss": 0.7087, "step": 13077 }, { "epoch": 0.7639018691588785, "grad_norm": 1.5008145570755005, "learning_rate": 2.78528781337155e-06, "loss": 0.6544, "step": 13078 }, { "epoch": 0.7639602803738318, "grad_norm": 1.1112592220306396, "learning_rate": 2.7839779471161554e-06, "loss": 0.7065, "step": 13079 }, { "epoch": 0.764018691588785, "grad_norm": 1.28849196434021, "learning_rate": 2.7826683391269318e-06, "loss": 0.6643, "step": 13080 }, { "epoch": 0.7640771028037383, "grad_norm": 1.3735828399658203, "learning_rate": 2.781358989450753e-06, "loss": 0.644, "step": 13081 }, { "epoch": 0.7641355140186916, "grad_norm": 1.395987629890442, "learning_rate": 2.780049898134484e-06, "loss": 0.7194, "step": 13082 }, { "epoch": 0.7641939252336448, "grad_norm": 1.7880017757415771, "learning_rate": 2.778741065224978e-06, "loss": 0.6549, "step": 13083 }, { "epoch": 0.7642523364485981, "grad_norm": 1.0819436311721802, "learning_rate": 2.7774324907690773e-06, "loss": 0.7552, "step": 13084 }, { "epoch": 0.7643107476635514, "grad_norm": 1.4361178874969482, "learning_rate": 2.7761241748136148e-06, "loss": 0.6419, "step": 13085 }, { "epoch": 0.7643691588785047, "grad_norm": 0.964057445526123, "learning_rate": 2.7748161174054167e-06, "loss": 0.8465, "step": 13086 }, { "epoch": 0.764427570093458, "grad_norm": 1.205655813217163, "learning_rate": 2.7735083185913015e-06, "loss": 0.7187, "step": 13087 }, { "epoch": 0.7644859813084112, "grad_norm": 1.400244116783142, "learning_rate": 2.7722007784180772e-06, "loss": 0.809, "step": 13088 }, { "epoch": 0.7645443925233645, "grad_norm": 2.1466641426086426, "learning_rate": 2.77089349693254e-06, "loss": 0.8496, "step": 13089 }, { "epoch": 0.7646028037383178, "grad_norm": 2.0733556747436523, "learning_rate": 2.769586474181474e-06, "loss": 0.871, "step": 13090 }, { "epoch": 0.764661214953271, "grad_norm": 1.6781740188598633, "learning_rate": 2.768279710211663e-06, "loss": 0.8935, "step": 13091 }, { "epoch": 0.7647196261682243, "grad_norm": 1.831223726272583, "learning_rate": 2.766973205069875e-06, "loss": 0.7358, "step": 13092 }, { "epoch": 0.7647780373831776, "grad_norm": 1.9612146615982056, "learning_rate": 2.765666958802876e-06, "loss": 0.8409, "step": 13093 }, { "epoch": 0.7648364485981308, "grad_norm": 1.031556487083435, "learning_rate": 2.7643609714574128e-06, "loss": 0.6943, "step": 13094 }, { "epoch": 0.7648948598130841, "grad_norm": 1.1812219619750977, "learning_rate": 2.763055243080225e-06, "loss": 0.7479, "step": 13095 }, { "epoch": 0.7649532710280373, "grad_norm": 1.1213552951812744, "learning_rate": 2.7617497737180508e-06, "loss": 0.6481, "step": 13096 }, { "epoch": 0.7650116822429907, "grad_norm": 2.3857791423797607, "learning_rate": 2.760444563417607e-06, "loss": 0.9126, "step": 13097 }, { "epoch": 0.765070093457944, "grad_norm": 0.8711024522781372, "learning_rate": 2.7591396122256175e-06, "loss": 0.6803, "step": 13098 }, { "epoch": 0.7651285046728972, "grad_norm": 1.1042920351028442, "learning_rate": 2.757834920188782e-06, "loss": 0.7479, "step": 13099 }, { "epoch": 0.7651869158878505, "grad_norm": 3.272749662399292, "learning_rate": 2.7565304873537933e-06, "loss": 0.8044, "step": 13100 }, { "epoch": 0.7652453271028037, "grad_norm": 1.1397298574447632, "learning_rate": 2.7552263137673453e-06, "loss": 0.7031, "step": 13101 }, { "epoch": 0.765303738317757, "grad_norm": 1.1515777111053467, "learning_rate": 2.7539223994761067e-06, "loss": 0.7017, "step": 13102 }, { "epoch": 0.7653621495327103, "grad_norm": 1.1410759687423706, "learning_rate": 2.7526187445267507e-06, "loss": 0.7853, "step": 13103 }, { "epoch": 0.7654205607476635, "grad_norm": 1.0714139938354492, "learning_rate": 2.7513153489659373e-06, "loss": 0.7653, "step": 13104 }, { "epoch": 0.7654789719626168, "grad_norm": 1.4318114519119263, "learning_rate": 2.7500122128403107e-06, "loss": 0.7623, "step": 13105 }, { "epoch": 0.7655373831775701, "grad_norm": 1.2390121221542358, "learning_rate": 2.7487093361965176e-06, "loss": 0.8066, "step": 13106 }, { "epoch": 0.7655957943925233, "grad_norm": 0.8679767847061157, "learning_rate": 2.7474067190811827e-06, "loss": 0.678, "step": 13107 }, { "epoch": 0.7656542056074767, "grad_norm": 1.7790616750717163, "learning_rate": 2.7461043615409287e-06, "loss": 0.7008, "step": 13108 }, { "epoch": 0.7657126168224299, "grad_norm": 1.2871897220611572, "learning_rate": 2.7448022636223725e-06, "loss": 0.7657, "step": 13109 }, { "epoch": 0.7657710280373832, "grad_norm": 1.3135693073272705, "learning_rate": 2.743500425372111e-06, "loss": 0.6604, "step": 13110 }, { "epoch": 0.7658294392523365, "grad_norm": 1.046388864517212, "learning_rate": 2.7421988468367432e-06, "loss": 0.699, "step": 13111 }, { "epoch": 0.7658878504672897, "grad_norm": 1.2624696493148804, "learning_rate": 2.7408975280628513e-06, "loss": 0.9365, "step": 13112 }, { "epoch": 0.765946261682243, "grad_norm": 0.979121744632721, "learning_rate": 2.7395964690970067e-06, "loss": 0.8097, "step": 13113 }, { "epoch": 0.7660046728971963, "grad_norm": 1.303269863128662, "learning_rate": 2.7382956699857778e-06, "loss": 0.7711, "step": 13114 }, { "epoch": 0.7660630841121495, "grad_norm": 1.1186598539352417, "learning_rate": 2.7369951307757214e-06, "loss": 0.6912, "step": 13115 }, { "epoch": 0.7661214953271028, "grad_norm": 1.7855312824249268, "learning_rate": 2.7356948515133883e-06, "loss": 0.72, "step": 13116 }, { "epoch": 0.766179906542056, "grad_norm": 1.468246579170227, "learning_rate": 2.734394832245313e-06, "loss": 0.7082, "step": 13117 }, { "epoch": 0.7662383177570093, "grad_norm": 1.0826939344406128, "learning_rate": 2.7330950730180206e-06, "loss": 0.694, "step": 13118 }, { "epoch": 0.7662967289719627, "grad_norm": 1.5453953742980957, "learning_rate": 2.7317955738780333e-06, "loss": 0.7837, "step": 13119 }, { "epoch": 0.7663551401869159, "grad_norm": 1.247125506401062, "learning_rate": 2.7304963348718616e-06, "loss": 0.9784, "step": 13120 }, { "epoch": 0.7664135514018692, "grad_norm": 1.4674417972564697, "learning_rate": 2.7291973560460093e-06, "loss": 0.9005, "step": 13121 }, { "epoch": 0.7664719626168224, "grad_norm": 1.0735843181610107, "learning_rate": 2.7278986374469642e-06, "loss": 0.7318, "step": 13122 }, { "epoch": 0.7665303738317757, "grad_norm": 1.4442732334136963, "learning_rate": 2.726600179121204e-06, "loss": 0.7466, "step": 13123 }, { "epoch": 0.766588785046729, "grad_norm": 1.2731748819351196, "learning_rate": 2.725301981115207e-06, "loss": 0.763, "step": 13124 }, { "epoch": 0.7666471962616822, "grad_norm": 1.0612905025482178, "learning_rate": 2.7240040434754354e-06, "loss": 0.9084, "step": 13125 }, { "epoch": 0.7667056074766355, "grad_norm": 1.6589120626449585, "learning_rate": 2.7227063662483456e-06, "loss": 0.7709, "step": 13126 }, { "epoch": 0.7667640186915888, "grad_norm": 1.9979888200759888, "learning_rate": 2.7214089494803796e-06, "loss": 0.7838, "step": 13127 }, { "epoch": 0.766822429906542, "grad_norm": 1.0126856565475464, "learning_rate": 2.720111793217971e-06, "loss": 0.7528, "step": 13128 }, { "epoch": 0.7668808411214953, "grad_norm": 3.037860155105591, "learning_rate": 2.71881489750755e-06, "loss": 0.7297, "step": 13129 }, { "epoch": 0.7669392523364486, "grad_norm": 1.1172367334365845, "learning_rate": 2.7175182623955265e-06, "loss": 0.835, "step": 13130 }, { "epoch": 0.7669976635514019, "grad_norm": 1.368037223815918, "learning_rate": 2.7162218879283174e-06, "loss": 0.7601, "step": 13131 }, { "epoch": 0.7670560747663552, "grad_norm": 0.9992244839668274, "learning_rate": 2.714925774152317e-06, "loss": 0.8567, "step": 13132 }, { "epoch": 0.7671144859813084, "grad_norm": 1.0753998756408691, "learning_rate": 2.7136299211139104e-06, "loss": 0.6902, "step": 13133 }, { "epoch": 0.7671728971962617, "grad_norm": 1.0216842889785767, "learning_rate": 2.7123343288594817e-06, "loss": 0.7415, "step": 13134 }, { "epoch": 0.767231308411215, "grad_norm": 1.1064544916152954, "learning_rate": 2.711038997435397e-06, "loss": 0.7653, "step": 13135 }, { "epoch": 0.7672897196261682, "grad_norm": 1.0200270414352417, "learning_rate": 2.7097439268880187e-06, "loss": 0.8788, "step": 13136 }, { "epoch": 0.7673481308411215, "grad_norm": 2.001112461090088, "learning_rate": 2.7084491172637016e-06, "loss": 0.7207, "step": 13137 }, { "epoch": 0.7674065420560747, "grad_norm": 1.0065388679504395, "learning_rate": 2.707154568608783e-06, "loss": 0.795, "step": 13138 }, { "epoch": 0.767464953271028, "grad_norm": 1.182943344116211, "learning_rate": 2.7058602809695987e-06, "loss": 0.6339, "step": 13139 }, { "epoch": 0.7675233644859814, "grad_norm": 1.147718906402588, "learning_rate": 2.704566254392469e-06, "loss": 0.5893, "step": 13140 }, { "epoch": 0.7675817757009346, "grad_norm": 1.2189780473709106, "learning_rate": 2.7032724889237104e-06, "loss": 1.079, "step": 13141 }, { "epoch": 0.7676401869158879, "grad_norm": 1.1872990131378174, "learning_rate": 2.701978984609629e-06, "loss": 0.859, "step": 13142 }, { "epoch": 0.7676985981308411, "grad_norm": 1.3250781297683716, "learning_rate": 2.700685741496516e-06, "loss": 0.8448, "step": 13143 }, { "epoch": 0.7677570093457944, "grad_norm": 1.6158039569854736, "learning_rate": 2.6993927596306622e-06, "loss": 0.7077, "step": 13144 }, { "epoch": 0.7678154205607477, "grad_norm": 0.94993656873703, "learning_rate": 2.698100039058339e-06, "loss": 0.7088, "step": 13145 }, { "epoch": 0.7678738317757009, "grad_norm": 2.4489381313323975, "learning_rate": 2.6968075798258197e-06, "loss": 0.7789, "step": 13146 }, { "epoch": 0.7679322429906542, "grad_norm": 0.9418963193893433, "learning_rate": 2.6955153819793565e-06, "loss": 0.7447, "step": 13147 }, { "epoch": 0.7679906542056075, "grad_norm": 1.5087226629257202, "learning_rate": 2.6942234455651995e-06, "loss": 0.8085, "step": 13148 }, { "epoch": 0.7680490654205607, "grad_norm": 0.8947284817695618, "learning_rate": 2.692931770629593e-06, "loss": 0.6137, "step": 13149 }, { "epoch": 0.768107476635514, "grad_norm": 1.4714760780334473, "learning_rate": 2.691640357218759e-06, "loss": 0.8309, "step": 13150 }, { "epoch": 0.7681658878504672, "grad_norm": 1.2348039150238037, "learning_rate": 2.690349205378926e-06, "loss": 0.8828, "step": 13151 }, { "epoch": 0.7682242990654206, "grad_norm": 1.2246229648590088, "learning_rate": 2.6890583151562965e-06, "loss": 0.8368, "step": 13152 }, { "epoch": 0.7682827102803739, "grad_norm": 1.0436152219772339, "learning_rate": 2.687767686597078e-06, "loss": 0.7288, "step": 13153 }, { "epoch": 0.7683411214953271, "grad_norm": 1.0081127882003784, "learning_rate": 2.686477319747466e-06, "loss": 0.6003, "step": 13154 }, { "epoch": 0.7683995327102804, "grad_norm": 3.7294464111328125, "learning_rate": 2.685187214653635e-06, "loss": 0.6997, "step": 13155 }, { "epoch": 0.7684579439252337, "grad_norm": 1.1916052103042603, "learning_rate": 2.6838973713617666e-06, "loss": 0.7871, "step": 13156 }, { "epoch": 0.7685163551401869, "grad_norm": 0.9443236589431763, "learning_rate": 2.6826077899180183e-06, "loss": 0.6974, "step": 13157 }, { "epoch": 0.7685747663551402, "grad_norm": 1.044769525527954, "learning_rate": 2.681318470368549e-06, "loss": 0.7066, "step": 13158 }, { "epoch": 0.7686331775700934, "grad_norm": 1.3939439058303833, "learning_rate": 2.680029412759506e-06, "loss": 1.0278, "step": 13159 }, { "epoch": 0.7686915887850467, "grad_norm": 1.0866262912750244, "learning_rate": 2.6787406171370213e-06, "loss": 0.7762, "step": 13160 }, { "epoch": 0.76875, "grad_norm": 1.2311755418777466, "learning_rate": 2.677452083547226e-06, "loss": 0.8086, "step": 13161 }, { "epoch": 0.7688084112149532, "grad_norm": 1.0020358562469482, "learning_rate": 2.6761638120362356e-06, "loss": 0.7103, "step": 13162 }, { "epoch": 0.7688668224299066, "grad_norm": 1.495418667793274, "learning_rate": 2.674875802650152e-06, "loss": 0.8122, "step": 13163 }, { "epoch": 0.7689252336448598, "grad_norm": 0.9961822628974915, "learning_rate": 2.6735880554350858e-06, "loss": 0.6578, "step": 13164 }, { "epoch": 0.7689836448598131, "grad_norm": 1.1843608617782593, "learning_rate": 2.6723005704371164e-06, "loss": 0.766, "step": 13165 }, { "epoch": 0.7690420560747664, "grad_norm": 1.767103910446167, "learning_rate": 2.6710133477023315e-06, "loss": 0.8423, "step": 13166 }, { "epoch": 0.7691004672897196, "grad_norm": 1.6269941329956055, "learning_rate": 2.6697263872767974e-06, "loss": 0.8676, "step": 13167 }, { "epoch": 0.7691588785046729, "grad_norm": 1.2112218141555786, "learning_rate": 2.6684396892065736e-06, "loss": 0.7801, "step": 13168 }, { "epoch": 0.7692172897196262, "grad_norm": 1.0565989017486572, "learning_rate": 2.6671532535377132e-06, "loss": 0.6359, "step": 13169 }, { "epoch": 0.7692757009345794, "grad_norm": 1.0347121953964233, "learning_rate": 2.6658670803162624e-06, "loss": 0.8032, "step": 13170 }, { "epoch": 0.7693341121495327, "grad_norm": 1.7102819681167603, "learning_rate": 2.6645811695882475e-06, "loss": 0.853, "step": 13171 }, { "epoch": 0.7693925233644859, "grad_norm": 1.5326391458511353, "learning_rate": 2.6632955213996993e-06, "loss": 0.8429, "step": 13172 }, { "epoch": 0.7694509345794392, "grad_norm": 0.9699275493621826, "learning_rate": 2.6620101357966253e-06, "loss": 0.7371, "step": 13173 }, { "epoch": 0.7695093457943926, "grad_norm": 1.0319827795028687, "learning_rate": 2.660725012825033e-06, "loss": 0.5827, "step": 13174 }, { "epoch": 0.7695677570093458, "grad_norm": 1.3427778482437134, "learning_rate": 2.6594401525309222e-06, "loss": 0.8512, "step": 13175 }, { "epoch": 0.7696261682242991, "grad_norm": 1.0763438940048218, "learning_rate": 2.6581555549602712e-06, "loss": 0.6888, "step": 13176 }, { "epoch": 0.7696845794392523, "grad_norm": 1.098630666732788, "learning_rate": 2.6568712201590628e-06, "loss": 0.7232, "step": 13177 }, { "epoch": 0.7697429906542056, "grad_norm": 1.2201608419418335, "learning_rate": 2.655587148173259e-06, "loss": 0.6882, "step": 13178 }, { "epoch": 0.7698014018691589, "grad_norm": 1.1365482807159424, "learning_rate": 2.6543033390488226e-06, "loss": 0.7733, "step": 13179 }, { "epoch": 0.7698598130841121, "grad_norm": 0.8989086151123047, "learning_rate": 2.653019792831698e-06, "loss": 0.7009, "step": 13180 }, { "epoch": 0.7699182242990654, "grad_norm": 1.1681618690490723, "learning_rate": 2.6517365095678248e-06, "loss": 0.8463, "step": 13181 }, { "epoch": 0.7699766355140187, "grad_norm": 1.1655933856964111, "learning_rate": 2.6504534893031366e-06, "loss": 0.7488, "step": 13182 }, { "epoch": 0.7700350467289719, "grad_norm": 1.1579655408859253, "learning_rate": 2.6491707320835468e-06, "loss": 0.7783, "step": 13183 }, { "epoch": 0.7700934579439253, "grad_norm": 1.0596750974655151, "learning_rate": 2.6478882379549743e-06, "loss": 0.8156, "step": 13184 }, { "epoch": 0.7701518691588785, "grad_norm": 1.1515697240829468, "learning_rate": 2.6466060069633117e-06, "loss": 0.7773, "step": 13185 }, { "epoch": 0.7702102803738318, "grad_norm": 0.90716952085495, "learning_rate": 2.6453240391544556e-06, "loss": 0.785, "step": 13186 }, { "epoch": 0.7702686915887851, "grad_norm": 1.2863472700119019, "learning_rate": 2.6440423345742905e-06, "loss": 0.8713, "step": 13187 }, { "epoch": 0.7703271028037383, "grad_norm": 0.9333947896957397, "learning_rate": 2.642760893268684e-06, "loss": 0.6671, "step": 13188 }, { "epoch": 0.7703855140186916, "grad_norm": 1.2190641164779663, "learning_rate": 2.641479715283506e-06, "loss": 0.973, "step": 13189 }, { "epoch": 0.7704439252336449, "grad_norm": 1.985343098640442, "learning_rate": 2.640198800664604e-06, "loss": 0.7611, "step": 13190 }, { "epoch": 0.7705023364485981, "grad_norm": 1.6264184713363647, "learning_rate": 2.6389181494578255e-06, "loss": 0.7646, "step": 13191 }, { "epoch": 0.7705607476635514, "grad_norm": 1.021466851234436, "learning_rate": 2.63763776170901e-06, "loss": 0.7619, "step": 13192 }, { "epoch": 0.7706191588785046, "grad_norm": 1.320671796798706, "learning_rate": 2.6363576374639765e-06, "loss": 0.7707, "step": 13193 }, { "epoch": 0.7706775700934579, "grad_norm": 1.1128363609313965, "learning_rate": 2.635077776768549e-06, "loss": 0.6463, "step": 13194 }, { "epoch": 0.7707359813084113, "grad_norm": 1.266506314277649, "learning_rate": 2.6337981796685296e-06, "loss": 0.7493, "step": 13195 }, { "epoch": 0.7707943925233645, "grad_norm": 1.336337685585022, "learning_rate": 2.6325188462097107e-06, "loss": 0.588, "step": 13196 }, { "epoch": 0.7708528037383178, "grad_norm": 1.0740081071853638, "learning_rate": 2.631239776437893e-06, "loss": 0.8157, "step": 13197 }, { "epoch": 0.770911214953271, "grad_norm": 1.2180191278457642, "learning_rate": 2.629960970398845e-06, "loss": 0.8534, "step": 13198 }, { "epoch": 0.7709696261682243, "grad_norm": 0.8952761292457581, "learning_rate": 2.6286824281383426e-06, "loss": 0.7696, "step": 13199 }, { "epoch": 0.7710280373831776, "grad_norm": 0.9121246933937073, "learning_rate": 2.627404149702143e-06, "loss": 0.7778, "step": 13200 }, { "epoch": 0.7710864485981308, "grad_norm": 1.0175085067749023, "learning_rate": 2.6261261351359947e-06, "loss": 0.7604, "step": 13201 }, { "epoch": 0.7711448598130841, "grad_norm": 1.1574674844741821, "learning_rate": 2.6248483844856387e-06, "loss": 0.7895, "step": 13202 }, { "epoch": 0.7712032710280374, "grad_norm": 1.3298203945159912, "learning_rate": 2.623570897796809e-06, "loss": 0.749, "step": 13203 }, { "epoch": 0.7712616822429906, "grad_norm": 1.6235244274139404, "learning_rate": 2.6222936751152307e-06, "loss": 0.6772, "step": 13204 }, { "epoch": 0.771320093457944, "grad_norm": 1.7956323623657227, "learning_rate": 2.621016716486612e-06, "loss": 0.9126, "step": 13205 }, { "epoch": 0.7713785046728971, "grad_norm": 1.1137425899505615, "learning_rate": 2.6197400219566537e-06, "loss": 0.7707, "step": 13206 }, { "epoch": 0.7714369158878505, "grad_norm": 0.9482833743095398, "learning_rate": 2.618463591571052e-06, "loss": 0.7757, "step": 13207 }, { "epoch": 0.7714953271028038, "grad_norm": 0.9538525342941284, "learning_rate": 2.6171874253754924e-06, "loss": 0.6295, "step": 13208 }, { "epoch": 0.771553738317757, "grad_norm": 1.2074781656265259, "learning_rate": 2.615911523415653e-06, "loss": 0.8255, "step": 13209 }, { "epoch": 0.7716121495327103, "grad_norm": 1.2745039463043213, "learning_rate": 2.6146358857371943e-06, "loss": 0.7523, "step": 13210 }, { "epoch": 0.7716705607476636, "grad_norm": 2.1026651859283447, "learning_rate": 2.6133605123857707e-06, "loss": 0.8029, "step": 13211 }, { "epoch": 0.7717289719626168, "grad_norm": 1.0819716453552246, "learning_rate": 2.612085403407034e-06, "loss": 0.7293, "step": 13212 }, { "epoch": 0.7717873831775701, "grad_norm": 1.1992052793502808, "learning_rate": 2.6108105588466124e-06, "loss": 0.6816, "step": 13213 }, { "epoch": 0.7718457943925233, "grad_norm": 1.6526801586151123, "learning_rate": 2.609535978750145e-06, "loss": 0.6905, "step": 13214 }, { "epoch": 0.7719042056074766, "grad_norm": 1.3751623630523682, "learning_rate": 2.6082616631632453e-06, "loss": 0.7634, "step": 13215 }, { "epoch": 0.77196261682243, "grad_norm": 0.9275327324867249, "learning_rate": 2.6069876121315173e-06, "loss": 0.7875, "step": 13216 }, { "epoch": 0.7720210280373832, "grad_norm": 1.3551602363586426, "learning_rate": 2.6057138257005665e-06, "loss": 0.844, "step": 13217 }, { "epoch": 0.7720794392523365, "grad_norm": 0.9493504762649536, "learning_rate": 2.604440303915976e-06, "loss": 0.7613, "step": 13218 }, { "epoch": 0.7721378504672897, "grad_norm": 1.0641058683395386, "learning_rate": 2.6031670468233304e-06, "loss": 1.0283, "step": 13219 }, { "epoch": 0.772196261682243, "grad_norm": 0.9527341723442078, "learning_rate": 2.6018940544682024e-06, "loss": 0.6721, "step": 13220 }, { "epoch": 0.7722546728971963, "grad_norm": 0.884721040725708, "learning_rate": 2.6006213268961488e-06, "loss": 0.7084, "step": 13221 }, { "epoch": 0.7723130841121495, "grad_norm": 1.3335191011428833, "learning_rate": 2.599348864152725e-06, "loss": 0.706, "step": 13222 }, { "epoch": 0.7723714953271028, "grad_norm": 1.057736873626709, "learning_rate": 2.598076666283469e-06, "loss": 0.7071, "step": 13223 }, { "epoch": 0.7724299065420561, "grad_norm": 1.2326750755310059, "learning_rate": 2.596804733333915e-06, "loss": 0.5484, "step": 13224 }, { "epoch": 0.7724883177570093, "grad_norm": 1.360593318939209, "learning_rate": 2.5955330653495904e-06, "loss": 0.6712, "step": 13225 }, { "epoch": 0.7725467289719626, "grad_norm": 1.091370701789856, "learning_rate": 2.594261662376003e-06, "loss": 0.7037, "step": 13226 }, { "epoch": 0.7726051401869158, "grad_norm": 1.440968632698059, "learning_rate": 2.592990524458664e-06, "loss": 0.8707, "step": 13227 }, { "epoch": 0.7726635514018692, "grad_norm": 1.0572245121002197, "learning_rate": 2.591719651643063e-06, "loss": 0.7038, "step": 13228 }, { "epoch": 0.7727219626168225, "grad_norm": 1.4476368427276611, "learning_rate": 2.590449043974682e-06, "loss": 0.6225, "step": 13229 }, { "epoch": 0.7727803738317757, "grad_norm": 1.0818278789520264, "learning_rate": 2.5891787014990064e-06, "loss": 0.7779, "step": 13230 }, { "epoch": 0.772838785046729, "grad_norm": 1.5100460052490234, "learning_rate": 2.5879086242614958e-06, "loss": 0.6946, "step": 13231 }, { "epoch": 0.7728971962616823, "grad_norm": 1.3658907413482666, "learning_rate": 2.5866388123076124e-06, "loss": 0.7151, "step": 13232 }, { "epoch": 0.7729556074766355, "grad_norm": 1.0164134502410889, "learning_rate": 2.585369265682799e-06, "loss": 0.7254, "step": 13233 }, { "epoch": 0.7730140186915888, "grad_norm": 1.7167620658874512, "learning_rate": 2.584099984432492e-06, "loss": 0.7057, "step": 13234 }, { "epoch": 0.773072429906542, "grad_norm": 1.8687281608581543, "learning_rate": 2.5828309686021237e-06, "loss": 0.7715, "step": 13235 }, { "epoch": 0.7731308411214953, "grad_norm": 1.440051794052124, "learning_rate": 2.5815622182371116e-06, "loss": 0.847, "step": 13236 }, { "epoch": 0.7731892523364486, "grad_norm": 1.4347741603851318, "learning_rate": 2.580293733382867e-06, "loss": 0.7137, "step": 13237 }, { "epoch": 0.7732476635514018, "grad_norm": 2.012552261352539, "learning_rate": 2.57902551408479e-06, "loss": 0.7034, "step": 13238 }, { "epoch": 0.7733060747663552, "grad_norm": 7.136087894439697, "learning_rate": 2.5777575603882654e-06, "loss": 0.6568, "step": 13239 }, { "epoch": 0.7733644859813084, "grad_norm": 1.0659321546554565, "learning_rate": 2.5764898723386776e-06, "loss": 0.7843, "step": 13240 }, { "epoch": 0.7734228971962617, "grad_norm": 1.3489443063735962, "learning_rate": 2.5752224499813994e-06, "loss": 0.8905, "step": 13241 }, { "epoch": 0.773481308411215, "grad_norm": 1.102597951889038, "learning_rate": 2.573955293361794e-06, "loss": 0.7071, "step": 13242 }, { "epoch": 0.7735397196261682, "grad_norm": 1.2463818788528442, "learning_rate": 2.572688402525211e-06, "loss": 0.8349, "step": 13243 }, { "epoch": 0.7735981308411215, "grad_norm": 1.4922913312911987, "learning_rate": 2.57142177751699e-06, "loss": 0.757, "step": 13244 }, { "epoch": 0.7736565420560748, "grad_norm": 1.5004968643188477, "learning_rate": 2.570155418382473e-06, "loss": 0.7958, "step": 13245 }, { "epoch": 0.773714953271028, "grad_norm": 1.572716474533081, "learning_rate": 2.568889325166971e-06, "loss": 0.8109, "step": 13246 }, { "epoch": 0.7737733644859813, "grad_norm": 1.3522217273712158, "learning_rate": 2.567623497915813e-06, "loss": 0.8565, "step": 13247 }, { "epoch": 0.7738317757009345, "grad_norm": 1.1697734594345093, "learning_rate": 2.5663579366742962e-06, "loss": 0.8426, "step": 13248 }, { "epoch": 0.7738901869158878, "grad_norm": 1.3171180486679077, "learning_rate": 2.565092641487714e-06, "loss": 0.6257, "step": 13249 }, { "epoch": 0.7739485981308412, "grad_norm": 1.1438456773757935, "learning_rate": 2.5638276124013582e-06, "loss": 0.7007, "step": 13250 }, { "epoch": 0.7740070093457944, "grad_norm": 1.1775559186935425, "learning_rate": 2.562562849460498e-06, "loss": 0.846, "step": 13251 }, { "epoch": 0.7740654205607477, "grad_norm": 1.7553435564041138, "learning_rate": 2.561298352710404e-06, "loss": 0.8055, "step": 13252 }, { "epoch": 0.774123831775701, "grad_norm": 1.2283869981765747, "learning_rate": 2.5600341221963354e-06, "loss": 0.718, "step": 13253 }, { "epoch": 0.7741822429906542, "grad_norm": 1.1463696956634521, "learning_rate": 2.5587701579635347e-06, "loss": 0.7694, "step": 13254 }, { "epoch": 0.7742406542056075, "grad_norm": 1.093174934387207, "learning_rate": 2.5575064600572465e-06, "loss": 0.7811, "step": 13255 }, { "epoch": 0.7742990654205607, "grad_norm": 0.9686114192008972, "learning_rate": 2.5562430285226913e-06, "loss": 0.7196, "step": 13256 }, { "epoch": 0.774357476635514, "grad_norm": 1.0526385307312012, "learning_rate": 2.554979863405094e-06, "loss": 0.6522, "step": 13257 }, { "epoch": 0.7744158878504673, "grad_norm": 1.0605688095092773, "learning_rate": 2.553716964749664e-06, "loss": 0.8419, "step": 13258 }, { "epoch": 0.7744742990654205, "grad_norm": 1.1643792390823364, "learning_rate": 2.552454332601597e-06, "loss": 0.6684, "step": 13259 }, { "epoch": 0.7745327102803738, "grad_norm": 1.0356824398040771, "learning_rate": 2.55119196700609e-06, "loss": 0.6728, "step": 13260 }, { "epoch": 0.774591121495327, "grad_norm": 1.5078972578048706, "learning_rate": 2.5499298680083173e-06, "loss": 0.816, "step": 13261 }, { "epoch": 0.7746495327102804, "grad_norm": 0.9543592929840088, "learning_rate": 2.5486680356534533e-06, "loss": 0.6905, "step": 13262 }, { "epoch": 0.7747079439252337, "grad_norm": 1.5520926713943481, "learning_rate": 2.5474064699866617e-06, "loss": 0.7731, "step": 13263 }, { "epoch": 0.7747663551401869, "grad_norm": 1.3322348594665527, "learning_rate": 2.5461451710530905e-06, "loss": 0.716, "step": 13264 }, { "epoch": 0.7748247663551402, "grad_norm": 1.0510601997375488, "learning_rate": 2.5448841388978874e-06, "loss": 0.7262, "step": 13265 }, { "epoch": 0.7748831775700935, "grad_norm": 1.0703482627868652, "learning_rate": 2.5436233735661798e-06, "loss": 0.84, "step": 13266 }, { "epoch": 0.7749415887850467, "grad_norm": 0.977781355381012, "learning_rate": 2.542362875103097e-06, "loss": 0.6652, "step": 13267 }, { "epoch": 0.775, "grad_norm": 1.2405688762664795, "learning_rate": 2.541102643553748e-06, "loss": 0.9894, "step": 13268 }, { "epoch": 0.7750584112149532, "grad_norm": 1.2086536884307861, "learning_rate": 2.539842678963239e-06, "loss": 0.8967, "step": 13269 }, { "epoch": 0.7751168224299065, "grad_norm": 0.9416629076004028, "learning_rate": 2.5385829813766693e-06, "loss": 0.607, "step": 13270 }, { "epoch": 0.7751752336448599, "grad_norm": 0.9567347764968872, "learning_rate": 2.537323550839117e-06, "loss": 0.6671, "step": 13271 }, { "epoch": 0.775233644859813, "grad_norm": 1.1868499517440796, "learning_rate": 2.536064387395666e-06, "loss": 0.7359, "step": 13272 }, { "epoch": 0.7752920560747664, "grad_norm": 0.8621296286582947, "learning_rate": 2.5348054910913732e-06, "loss": 0.6736, "step": 13273 }, { "epoch": 0.7753504672897197, "grad_norm": 1.538878083229065, "learning_rate": 2.533546861971302e-06, "loss": 0.7154, "step": 13274 }, { "epoch": 0.7754088785046729, "grad_norm": 1.204882264137268, "learning_rate": 2.5322885000804996e-06, "loss": 0.8303, "step": 13275 }, { "epoch": 0.7754672897196262, "grad_norm": 0.9899560213088989, "learning_rate": 2.531030405464e-06, "loss": 0.7325, "step": 13276 }, { "epoch": 0.7755257009345794, "grad_norm": 1.3069822788238525, "learning_rate": 2.529772578166836e-06, "loss": 0.7833, "step": 13277 }, { "epoch": 0.7755841121495327, "grad_norm": 8.101462364196777, "learning_rate": 2.528515018234022e-06, "loss": 0.7738, "step": 13278 }, { "epoch": 0.775642523364486, "grad_norm": 1.311282992362976, "learning_rate": 2.5272577257105634e-06, "loss": 0.8122, "step": 13279 }, { "epoch": 0.7757009345794392, "grad_norm": 1.3170065879821777, "learning_rate": 2.52600070064147e-06, "loss": 0.8767, "step": 13280 }, { "epoch": 0.7757593457943925, "grad_norm": 1.049752116203308, "learning_rate": 2.5247439430717225e-06, "loss": 0.7208, "step": 13281 }, { "epoch": 0.7758177570093457, "grad_norm": 1.241660237312317, "learning_rate": 2.5234874530463083e-06, "loss": 0.6705, "step": 13282 }, { "epoch": 0.7758761682242991, "grad_norm": 0.9663494229316711, "learning_rate": 2.5222312306101925e-06, "loss": 0.798, "step": 13283 }, { "epoch": 0.7759345794392524, "grad_norm": 0.924403727054596, "learning_rate": 2.520975275808336e-06, "loss": 0.62, "step": 13284 }, { "epoch": 0.7759929906542056, "grad_norm": 0.8598775863647461, "learning_rate": 2.5197195886856906e-06, "loss": 0.8233, "step": 13285 }, { "epoch": 0.7760514018691589, "grad_norm": 1.3978263139724731, "learning_rate": 2.5184641692872035e-06, "loss": 0.7743, "step": 13286 }, { "epoch": 0.7761098130841122, "grad_norm": 1.3893178701400757, "learning_rate": 2.5172090176578e-06, "loss": 0.7589, "step": 13287 }, { "epoch": 0.7761682242990654, "grad_norm": 1.1522787809371948, "learning_rate": 2.5159541338424087e-06, "loss": 0.7493, "step": 13288 }, { "epoch": 0.7762266355140187, "grad_norm": 1.1738309860229492, "learning_rate": 2.5146995178859356e-06, "loss": 0.8362, "step": 13289 }, { "epoch": 0.7762850467289719, "grad_norm": 0.9759562611579895, "learning_rate": 2.5134451698332896e-06, "loss": 0.5712, "step": 13290 }, { "epoch": 0.7763434579439252, "grad_norm": 1.033911108970642, "learning_rate": 2.5121910897293665e-06, "loss": 0.7538, "step": 13291 }, { "epoch": 0.7764018691588785, "grad_norm": 1.2090122699737549, "learning_rate": 2.5109372776190443e-06, "loss": 0.7095, "step": 13292 }, { "epoch": 0.7764602803738317, "grad_norm": 1.0070240497589111, "learning_rate": 2.5096837335472045e-06, "loss": 0.7919, "step": 13293 }, { "epoch": 0.7765186915887851, "grad_norm": 1.0851751565933228, "learning_rate": 2.508430457558706e-06, "loss": 0.7204, "step": 13294 }, { "epoch": 0.7765771028037384, "grad_norm": 1.1917929649353027, "learning_rate": 2.5071774496984068e-06, "loss": 0.7294, "step": 13295 }, { "epoch": 0.7766355140186916, "grad_norm": 0.8998571634292603, "learning_rate": 2.505924710011156e-06, "loss": 0.6643, "step": 13296 }, { "epoch": 0.7766939252336449, "grad_norm": 1.340618371963501, "learning_rate": 2.5046722385417845e-06, "loss": 0.8427, "step": 13297 }, { "epoch": 0.7767523364485981, "grad_norm": 1.2339555025100708, "learning_rate": 2.5034200353351256e-06, "loss": 0.8116, "step": 13298 }, { "epoch": 0.7768107476635514, "grad_norm": 1.1442759037017822, "learning_rate": 2.502168100435989e-06, "loss": 0.8362, "step": 13299 }, { "epoch": 0.7768691588785047, "grad_norm": 1.0234431028366089, "learning_rate": 2.5009164338891888e-06, "loss": 0.7633, "step": 13300 }, { "epoch": 0.7769275700934579, "grad_norm": 1.0118552446365356, "learning_rate": 2.499665035739517e-06, "loss": 0.7136, "step": 13301 }, { "epoch": 0.7769859813084112, "grad_norm": 1.1519924402236938, "learning_rate": 2.4984139060317658e-06, "loss": 0.672, "step": 13302 }, { "epoch": 0.7770443925233644, "grad_norm": 1.2629926204681396, "learning_rate": 2.4971630448107166e-06, "loss": 0.8877, "step": 13303 }, { "epoch": 0.7771028037383177, "grad_norm": 1.343694806098938, "learning_rate": 2.495912452121132e-06, "loss": 0.7847, "step": 13304 }, { "epoch": 0.7771612149532711, "grad_norm": 1.1275789737701416, "learning_rate": 2.4946621280077765e-06, "loss": 0.7225, "step": 13305 }, { "epoch": 0.7772196261682243, "grad_norm": 1.0957988500595093, "learning_rate": 2.4934120725153966e-06, "loss": 0.7027, "step": 13306 }, { "epoch": 0.7772780373831776, "grad_norm": 1.0245118141174316, "learning_rate": 2.492162285688734e-06, "loss": 0.8193, "step": 13307 }, { "epoch": 0.7773364485981309, "grad_norm": 0.9158581495285034, "learning_rate": 2.490912767572523e-06, "loss": 0.5826, "step": 13308 }, { "epoch": 0.7773948598130841, "grad_norm": 1.1149781942367554, "learning_rate": 2.489663518211478e-06, "loss": 0.6465, "step": 13309 }, { "epoch": 0.7774532710280374, "grad_norm": 1.1942907571792603, "learning_rate": 2.4884145376503166e-06, "loss": 0.7075, "step": 13310 }, { "epoch": 0.7775116822429906, "grad_norm": 1.0204424858093262, "learning_rate": 2.4871658259337383e-06, "loss": 0.8369, "step": 13311 }, { "epoch": 0.7775700934579439, "grad_norm": 1.0338163375854492, "learning_rate": 2.4859173831064287e-06, "loss": 0.7486, "step": 13312 }, { "epoch": 0.7776285046728972, "grad_norm": 1.0108410120010376, "learning_rate": 2.484669209213083e-06, "loss": 0.7848, "step": 13313 }, { "epoch": 0.7776869158878504, "grad_norm": 0.9143860936164856, "learning_rate": 2.4834213042983635e-06, "loss": 0.766, "step": 13314 }, { "epoch": 0.7777453271028038, "grad_norm": 1.0871981382369995, "learning_rate": 2.482173668406942e-06, "loss": 0.6805, "step": 13315 }, { "epoch": 0.777803738317757, "grad_norm": 1.2037400007247925, "learning_rate": 2.480926301583467e-06, "loss": 0.8333, "step": 13316 }, { "epoch": 0.7778621495327103, "grad_norm": 0.8559102416038513, "learning_rate": 2.4796792038725814e-06, "loss": 0.6941, "step": 13317 }, { "epoch": 0.7779205607476636, "grad_norm": 1.1410826444625854, "learning_rate": 2.478432375318922e-06, "loss": 0.7843, "step": 13318 }, { "epoch": 0.7779789719626168, "grad_norm": 1.3089491128921509, "learning_rate": 2.4771858159671127e-06, "loss": 0.7223, "step": 13319 }, { "epoch": 0.7780373831775701, "grad_norm": 1.3172833919525146, "learning_rate": 2.4759395258617726e-06, "loss": 0.7951, "step": 13320 }, { "epoch": 0.7780957943925234, "grad_norm": 1.2481831312179565, "learning_rate": 2.474693505047504e-06, "loss": 0.6204, "step": 13321 }, { "epoch": 0.7781542056074766, "grad_norm": 1.0241671800613403, "learning_rate": 2.4734477535689006e-06, "loss": 0.7735, "step": 13322 }, { "epoch": 0.7782126168224299, "grad_norm": 1.1548757553100586, "learning_rate": 2.4722022714705498e-06, "loss": 0.6738, "step": 13323 }, { "epoch": 0.7782710280373831, "grad_norm": 3.841506004333496, "learning_rate": 2.47095705879703e-06, "loss": 0.9316, "step": 13324 }, { "epoch": 0.7783294392523364, "grad_norm": 1.1989576816558838, "learning_rate": 2.4697121155929094e-06, "loss": 0.903, "step": 13325 }, { "epoch": 0.7783878504672898, "grad_norm": 1.1305551528930664, "learning_rate": 2.4684674419027445e-06, "loss": 0.6175, "step": 13326 }, { "epoch": 0.778446261682243, "grad_norm": 1.4542292356491089, "learning_rate": 2.4672230377710794e-06, "loss": 0.6266, "step": 13327 }, { "epoch": 0.7785046728971963, "grad_norm": 1.6216298341751099, "learning_rate": 2.465978903242453e-06, "loss": 0.8916, "step": 13328 }, { "epoch": 0.7785630841121496, "grad_norm": 1.0869946479797363, "learning_rate": 2.4647350383613965e-06, "loss": 0.5546, "step": 13329 }, { "epoch": 0.7786214953271028, "grad_norm": 1.3451037406921387, "learning_rate": 2.463491443172431e-06, "loss": 0.7936, "step": 13330 }, { "epoch": 0.7786799065420561, "grad_norm": 1.640708088874817, "learning_rate": 2.462248117720061e-06, "loss": 0.8627, "step": 13331 }, { "epoch": 0.7787383177570093, "grad_norm": 1.0563315153121948, "learning_rate": 2.4610050620487846e-06, "loss": 0.8593, "step": 13332 }, { "epoch": 0.7787967289719626, "grad_norm": 1.7975560426712036, "learning_rate": 2.459762276203097e-06, "loss": 0.8009, "step": 13333 }, { "epoch": 0.7788551401869159, "grad_norm": 1.4576746225357056, "learning_rate": 2.4585197602274723e-06, "loss": 0.735, "step": 13334 }, { "epoch": 0.7789135514018691, "grad_norm": 1.4804227352142334, "learning_rate": 2.457277514166384e-06, "loss": 0.8757, "step": 13335 }, { "epoch": 0.7789719626168224, "grad_norm": 0.8507369160652161, "learning_rate": 2.456035538064295e-06, "loss": 0.7485, "step": 13336 }, { "epoch": 0.7790303738317756, "grad_norm": 1.3962204456329346, "learning_rate": 2.4547938319656527e-06, "loss": 0.762, "step": 13337 }, { "epoch": 0.779088785046729, "grad_norm": 1.2973824739456177, "learning_rate": 2.453552395914903e-06, "loss": 0.732, "step": 13338 }, { "epoch": 0.7791471962616823, "grad_norm": 1.4137462377548218, "learning_rate": 2.452311229956471e-06, "loss": 0.8117, "step": 13339 }, { "epoch": 0.7792056074766355, "grad_norm": 1.2413973808288574, "learning_rate": 2.451070334134784e-06, "loss": 0.7565, "step": 13340 }, { "epoch": 0.7792640186915888, "grad_norm": 1.0504286289215088, "learning_rate": 2.4498297084942556e-06, "loss": 0.7057, "step": 13341 }, { "epoch": 0.7793224299065421, "grad_norm": 1.6309010982513428, "learning_rate": 2.4485893530792835e-06, "loss": 0.7495, "step": 13342 }, { "epoch": 0.7793808411214953, "grad_norm": 1.2420116662979126, "learning_rate": 2.447349267934266e-06, "loss": 0.6961, "step": 13343 }, { "epoch": 0.7794392523364486, "grad_norm": 1.0672917366027832, "learning_rate": 2.4461094531035846e-06, "loss": 0.7363, "step": 13344 }, { "epoch": 0.7794976635514018, "grad_norm": 1.7430191040039062, "learning_rate": 2.4448699086316073e-06, "loss": 0.7594, "step": 13345 }, { "epoch": 0.7795560747663551, "grad_norm": 1.3365641832351685, "learning_rate": 2.443630634562709e-06, "loss": 0.8937, "step": 13346 }, { "epoch": 0.7796144859813084, "grad_norm": 1.9296801090240479, "learning_rate": 2.4423916309412353e-06, "loss": 0.6584, "step": 13347 }, { "epoch": 0.7796728971962616, "grad_norm": 1.2802238464355469, "learning_rate": 2.4411528978115373e-06, "loss": 0.6707, "step": 13348 }, { "epoch": 0.779731308411215, "grad_norm": 1.606490969657898, "learning_rate": 2.4399144352179484e-06, "loss": 0.8454, "step": 13349 }, { "epoch": 0.7797897196261683, "grad_norm": 2.021352767944336, "learning_rate": 2.4386762432047884e-06, "loss": 0.9292, "step": 13350 }, { "epoch": 0.7798481308411215, "grad_norm": 1.1159389019012451, "learning_rate": 2.4374383218163777e-06, "loss": 0.6776, "step": 13351 }, { "epoch": 0.7799065420560748, "grad_norm": 1.444402813911438, "learning_rate": 2.436200671097022e-06, "loss": 0.7414, "step": 13352 }, { "epoch": 0.779964953271028, "grad_norm": 1.3881436586380005, "learning_rate": 2.4349632910910204e-06, "loss": 0.7206, "step": 13353 }, { "epoch": 0.7800233644859813, "grad_norm": 1.2001482248306274, "learning_rate": 2.4337261818426573e-06, "loss": 0.7132, "step": 13354 }, { "epoch": 0.7800817757009346, "grad_norm": 1.3761612176895142, "learning_rate": 2.432489343396206e-06, "loss": 0.858, "step": 13355 }, { "epoch": 0.7801401869158878, "grad_norm": 1.5267889499664307, "learning_rate": 2.431252775795936e-06, "loss": 0.8012, "step": 13356 }, { "epoch": 0.7801985981308411, "grad_norm": 1.7956122159957886, "learning_rate": 2.4300164790861058e-06, "loss": 0.8036, "step": 13357 }, { "epoch": 0.7802570093457943, "grad_norm": 1.2716318368911743, "learning_rate": 2.428780453310967e-06, "loss": 0.6835, "step": 13358 }, { "epoch": 0.7803154205607477, "grad_norm": 1.338401198387146, "learning_rate": 2.427544698514753e-06, "loss": 0.8527, "step": 13359 }, { "epoch": 0.780373831775701, "grad_norm": 1.0965062379837036, "learning_rate": 2.426309214741691e-06, "loss": 0.6368, "step": 13360 }, { "epoch": 0.7804322429906542, "grad_norm": 1.1145131587982178, "learning_rate": 2.425074002036002e-06, "loss": 0.7917, "step": 13361 }, { "epoch": 0.7804906542056075, "grad_norm": 1.4291884899139404, "learning_rate": 2.4238390604418948e-06, "loss": 0.8864, "step": 13362 }, { "epoch": 0.7805490654205608, "grad_norm": 1.2332807779312134, "learning_rate": 2.4226043900035723e-06, "loss": 0.8638, "step": 13363 }, { "epoch": 0.780607476635514, "grad_norm": 1.113623857498169, "learning_rate": 2.421369990765221e-06, "loss": 0.7909, "step": 13364 }, { "epoch": 0.7806658878504673, "grad_norm": 1.0700738430023193, "learning_rate": 2.420135862771017e-06, "loss": 0.7014, "step": 13365 }, { "epoch": 0.7807242990654205, "grad_norm": 1.601187825202942, "learning_rate": 2.4189020060651382e-06, "loss": 0.8049, "step": 13366 }, { "epoch": 0.7807827102803738, "grad_norm": 1.0563850402832031, "learning_rate": 2.417668420691738e-06, "loss": 0.6807, "step": 13367 }, { "epoch": 0.7808411214953271, "grad_norm": 0.8848657011985779, "learning_rate": 2.4164351066949697e-06, "loss": 0.7428, "step": 13368 }, { "epoch": 0.7808995327102803, "grad_norm": 1.1992651224136353, "learning_rate": 2.415202064118979e-06, "loss": 0.8165, "step": 13369 }, { "epoch": 0.7809579439252337, "grad_norm": 0.8883364200592041, "learning_rate": 2.4139692930078905e-06, "loss": 0.7541, "step": 13370 }, { "epoch": 0.781016355140187, "grad_norm": 1.3519293069839478, "learning_rate": 2.4127367934058323e-06, "loss": 0.7332, "step": 13371 }, { "epoch": 0.7810747663551402, "grad_norm": 0.9839845895767212, "learning_rate": 2.4115045653569092e-06, "loss": 0.7892, "step": 13372 }, { "epoch": 0.7811331775700935, "grad_norm": 0.9900632500648499, "learning_rate": 2.4102726089052277e-06, "loss": 0.7257, "step": 13373 }, { "epoch": 0.7811915887850467, "grad_norm": 1.2190734148025513, "learning_rate": 2.4090409240948833e-06, "loss": 0.6833, "step": 13374 }, { "epoch": 0.78125, "grad_norm": 1.1728764772415161, "learning_rate": 2.4078095109699506e-06, "loss": 0.6888, "step": 13375 }, { "epoch": 0.7813084112149533, "grad_norm": 1.2091264724731445, "learning_rate": 2.4065783695745125e-06, "loss": 0.7679, "step": 13376 }, { "epoch": 0.7813668224299065, "grad_norm": 1.7865831851959229, "learning_rate": 2.405347499952623e-06, "loss": 0.6079, "step": 13377 }, { "epoch": 0.7814252336448598, "grad_norm": 1.0181549787521362, "learning_rate": 2.4041169021483414e-06, "loss": 0.6141, "step": 13378 }, { "epoch": 0.781483644859813, "grad_norm": 2.2516956329345703, "learning_rate": 2.402886576205712e-06, "loss": 0.779, "step": 13379 }, { "epoch": 0.7815420560747663, "grad_norm": 0.9607318043708801, "learning_rate": 2.401656522168765e-06, "loss": 0.7947, "step": 13380 }, { "epoch": 0.7816004672897197, "grad_norm": 1.2660068273544312, "learning_rate": 2.4004267400815294e-06, "loss": 0.8236, "step": 13381 }, { "epoch": 0.7816588785046729, "grad_norm": 1.5787122249603271, "learning_rate": 2.399197229988015e-06, "loss": 0.675, "step": 13382 }, { "epoch": 0.7817172897196262, "grad_norm": 1.418461799621582, "learning_rate": 2.397967991932232e-06, "loss": 0.841, "step": 13383 }, { "epoch": 0.7817757009345795, "grad_norm": 1.3927180767059326, "learning_rate": 2.3967390259581703e-06, "loss": 0.9542, "step": 13384 }, { "epoch": 0.7818341121495327, "grad_norm": 1.5463848114013672, "learning_rate": 2.3955103321098182e-06, "loss": 0.7569, "step": 13385 }, { "epoch": 0.781892523364486, "grad_norm": 1.0174229145050049, "learning_rate": 2.3942819104311545e-06, "loss": 0.6735, "step": 13386 }, { "epoch": 0.7819509345794392, "grad_norm": 2.0103228092193604, "learning_rate": 2.3930537609661385e-06, "loss": 0.7487, "step": 13387 }, { "epoch": 0.7820093457943925, "grad_norm": 2.0404908657073975, "learning_rate": 2.3918258837587337e-06, "loss": 0.6214, "step": 13388 }, { "epoch": 0.7820677570093458, "grad_norm": 0.9297184944152832, "learning_rate": 2.390598278852879e-06, "loss": 0.6738, "step": 13389 }, { "epoch": 0.782126168224299, "grad_norm": 1.9116870164871216, "learning_rate": 2.3893709462925163e-06, "loss": 0.9585, "step": 13390 }, { "epoch": 0.7821845794392523, "grad_norm": 2.026341199874878, "learning_rate": 2.3881438861215744e-06, "loss": 0.7729, "step": 13391 }, { "epoch": 0.7822429906542057, "grad_norm": 1.3044806718826294, "learning_rate": 2.3869170983839642e-06, "loss": 0.6873, "step": 13392 }, { "epoch": 0.7823014018691589, "grad_norm": 1.234931230545044, "learning_rate": 2.3856905831236e-06, "loss": 0.6886, "step": 13393 }, { "epoch": 0.7823598130841122, "grad_norm": 2.736577033996582, "learning_rate": 2.384464340384374e-06, "loss": 0.8209, "step": 13394 }, { "epoch": 0.7824182242990654, "grad_norm": 1.7165179252624512, "learning_rate": 2.3832383702101747e-06, "loss": 0.7678, "step": 13395 }, { "epoch": 0.7824766355140187, "grad_norm": 1.7167061567306519, "learning_rate": 2.382012672644887e-06, "loss": 0.9232, "step": 13396 }, { "epoch": 0.782535046728972, "grad_norm": 1.6768550872802734, "learning_rate": 2.3807872477323736e-06, "loss": 0.724, "step": 13397 }, { "epoch": 0.7825934579439252, "grad_norm": 1.4419846534729004, "learning_rate": 2.379562095516492e-06, "loss": 0.8041, "step": 13398 }, { "epoch": 0.7826518691588785, "grad_norm": 1.331243872642517, "learning_rate": 2.378337216041097e-06, "loss": 0.9163, "step": 13399 }, { "epoch": 0.7827102803738317, "grad_norm": 1.1362780332565308, "learning_rate": 2.37711260935002e-06, "loss": 0.6632, "step": 13400 }, { "epoch": 0.782768691588785, "grad_norm": 1.3244916200637817, "learning_rate": 2.375888275487096e-06, "loss": 0.7536, "step": 13401 }, { "epoch": 0.7828271028037384, "grad_norm": 1.7336392402648926, "learning_rate": 2.374664214496146e-06, "loss": 0.8027, "step": 13402 }, { "epoch": 0.7828855140186916, "grad_norm": 1.1581158638000488, "learning_rate": 2.3734404264209744e-06, "loss": 0.8675, "step": 13403 }, { "epoch": 0.7829439252336449, "grad_norm": 0.9660871028900146, "learning_rate": 2.372216911305387e-06, "loss": 0.677, "step": 13404 }, { "epoch": 0.7830023364485982, "grad_norm": 0.9189037084579468, "learning_rate": 2.37099366919317e-06, "loss": 0.7052, "step": 13405 }, { "epoch": 0.7830607476635514, "grad_norm": 1.3313673734664917, "learning_rate": 2.3697707001281054e-06, "loss": 0.8061, "step": 13406 }, { "epoch": 0.7831191588785047, "grad_norm": 1.221124291419983, "learning_rate": 2.3685480041539676e-06, "loss": 0.5776, "step": 13407 }, { "epoch": 0.7831775700934579, "grad_norm": 1.2676057815551758, "learning_rate": 2.367325581314511e-06, "loss": 0.7383, "step": 13408 }, { "epoch": 0.7832359813084112, "grad_norm": 1.621618628501892, "learning_rate": 2.3661034316534935e-06, "loss": 0.7073, "step": 13409 }, { "epoch": 0.7832943925233645, "grad_norm": 0.9859165549278259, "learning_rate": 2.364881555214651e-06, "loss": 0.6447, "step": 13410 }, { "epoch": 0.7833528037383177, "grad_norm": 1.3722485303878784, "learning_rate": 2.363659952041717e-06, "loss": 0.7558, "step": 13411 }, { "epoch": 0.783411214953271, "grad_norm": 1.461175560951233, "learning_rate": 2.362438622178418e-06, "loss": 0.9576, "step": 13412 }, { "epoch": 0.7834696261682244, "grad_norm": 1.1386598348617554, "learning_rate": 2.361217565668459e-06, "loss": 0.8481, "step": 13413 }, { "epoch": 0.7835280373831776, "grad_norm": 0.9736343622207642, "learning_rate": 2.3599967825555493e-06, "loss": 0.8114, "step": 13414 }, { "epoch": 0.7835864485981309, "grad_norm": 1.485168695449829, "learning_rate": 2.358776272883375e-06, "loss": 0.7948, "step": 13415 }, { "epoch": 0.7836448598130841, "grad_norm": 0.9971268177032471, "learning_rate": 2.3575560366956252e-06, "loss": 0.607, "step": 13416 }, { "epoch": 0.7837032710280374, "grad_norm": 1.2747255563735962, "learning_rate": 2.3563360740359663e-06, "loss": 0.8655, "step": 13417 }, { "epoch": 0.7837616822429907, "grad_norm": 1.1792558431625366, "learning_rate": 2.3551163849480664e-06, "loss": 1.0027, "step": 13418 }, { "epoch": 0.7838200934579439, "grad_norm": 1.3276931047439575, "learning_rate": 2.3538969694755797e-06, "loss": 0.8313, "step": 13419 }, { "epoch": 0.7838785046728972, "grad_norm": 1.20938241481781, "learning_rate": 2.3526778276621452e-06, "loss": 0.7148, "step": 13420 }, { "epoch": 0.7839369158878504, "grad_norm": 1.346998929977417, "learning_rate": 2.3514589595514025e-06, "loss": 0.7497, "step": 13421 }, { "epoch": 0.7839953271028037, "grad_norm": 1.7529892921447754, "learning_rate": 2.3502403651869687e-06, "loss": 0.766, "step": 13422 }, { "epoch": 0.784053738317757, "grad_norm": 0.9790130257606506, "learning_rate": 2.3490220446124635e-06, "loss": 0.8031, "step": 13423 }, { "epoch": 0.7841121495327102, "grad_norm": 1.4191471338272095, "learning_rate": 2.3478039978714916e-06, "loss": 0.8257, "step": 13424 }, { "epoch": 0.7841705607476636, "grad_norm": 1.068913459777832, "learning_rate": 2.3465862250076445e-06, "loss": 0.7459, "step": 13425 }, { "epoch": 0.7842289719626169, "grad_norm": 1.3022067546844482, "learning_rate": 2.3453687260645107e-06, "loss": 0.6597, "step": 13426 }, { "epoch": 0.7842873831775701, "grad_norm": 1.065201997756958, "learning_rate": 2.3441515010856597e-06, "loss": 0.8402, "step": 13427 }, { "epoch": 0.7843457943925234, "grad_norm": 1.285800576210022, "learning_rate": 2.342934550114662e-06, "loss": 0.6169, "step": 13428 }, { "epoch": 0.7844042056074766, "grad_norm": 0.9132324457168579, "learning_rate": 2.341717873195073e-06, "loss": 0.7777, "step": 13429 }, { "epoch": 0.7844626168224299, "grad_norm": 0.9527384042739868, "learning_rate": 2.3405014703704332e-06, "loss": 0.7284, "step": 13430 }, { "epoch": 0.7845210280373832, "grad_norm": 1.4616289138793945, "learning_rate": 2.3392853416842864e-06, "loss": 0.8028, "step": 13431 }, { "epoch": 0.7845794392523364, "grad_norm": 1.1298224925994873, "learning_rate": 2.3380694871801534e-06, "loss": 0.8379, "step": 13432 }, { "epoch": 0.7846378504672897, "grad_norm": 1.0399072170257568, "learning_rate": 2.3368539069015483e-06, "loss": 0.8092, "step": 13433 }, { "epoch": 0.784696261682243, "grad_norm": 1.0517842769622803, "learning_rate": 2.3356386008919807e-06, "loss": 0.6902, "step": 13434 }, { "epoch": 0.7847546728971962, "grad_norm": 0.7821060419082642, "learning_rate": 2.334423569194948e-06, "loss": 0.4759, "step": 13435 }, { "epoch": 0.7848130841121496, "grad_norm": 1.090835690498352, "learning_rate": 2.3332088118539374e-06, "loss": 0.8888, "step": 13436 }, { "epoch": 0.7848714953271028, "grad_norm": 1.1816707849502563, "learning_rate": 2.3319943289124248e-06, "loss": 0.8008, "step": 13437 }, { "epoch": 0.7849299065420561, "grad_norm": 1.115795373916626, "learning_rate": 2.3307801204138748e-06, "loss": 0.6955, "step": 13438 }, { "epoch": 0.7849883177570094, "grad_norm": 0.9518140554428101, "learning_rate": 2.329566186401746e-06, "loss": 0.6876, "step": 13439 }, { "epoch": 0.7850467289719626, "grad_norm": 0.9210162162780762, "learning_rate": 2.3283525269194873e-06, "loss": 0.7344, "step": 13440 }, { "epoch": 0.7851051401869159, "grad_norm": 1.0427957773208618, "learning_rate": 2.3271391420105384e-06, "loss": 0.6868, "step": 13441 }, { "epoch": 0.7851635514018691, "grad_norm": 1.1070560216903687, "learning_rate": 2.325926031718325e-06, "loss": 0.6617, "step": 13442 }, { "epoch": 0.7852219626168224, "grad_norm": 1.0832263231277466, "learning_rate": 2.3247131960862614e-06, "loss": 0.5088, "step": 13443 }, { "epoch": 0.7852803738317757, "grad_norm": 1.0920652151107788, "learning_rate": 2.323500635157759e-06, "loss": 0.8896, "step": 13444 }, { "epoch": 0.7853387850467289, "grad_norm": 1.0152660608291626, "learning_rate": 2.322288348976217e-06, "loss": 0.7498, "step": 13445 }, { "epoch": 0.7853971962616823, "grad_norm": 1.016465663909912, "learning_rate": 2.3210763375850255e-06, "loss": 0.7647, "step": 13446 }, { "epoch": 0.7854556074766356, "grad_norm": 1.0657967329025269, "learning_rate": 2.3198646010275614e-06, "loss": 0.8356, "step": 13447 }, { "epoch": 0.7855140186915888, "grad_norm": 0.9626348614692688, "learning_rate": 2.31865313934719e-06, "loss": 0.6716, "step": 13448 }, { "epoch": 0.7855724299065421, "grad_norm": 0.9402345418930054, "learning_rate": 2.317441952587276e-06, "loss": 0.7676, "step": 13449 }, { "epoch": 0.7856308411214953, "grad_norm": 1.2950845956802368, "learning_rate": 2.3162310407911625e-06, "loss": 0.6633, "step": 13450 }, { "epoch": 0.7856892523364486, "grad_norm": 1.2194855213165283, "learning_rate": 2.3150204040021927e-06, "loss": 0.6853, "step": 13451 }, { "epoch": 0.7857476635514019, "grad_norm": 1.1164191961288452, "learning_rate": 2.3138100422636987e-06, "loss": 0.8227, "step": 13452 }, { "epoch": 0.7858060747663551, "grad_norm": 1.0572786331176758, "learning_rate": 2.312599955618994e-06, "loss": 0.7777, "step": 13453 }, { "epoch": 0.7858644859813084, "grad_norm": 1.050650954246521, "learning_rate": 2.3113901441113953e-06, "loss": 0.8186, "step": 13454 }, { "epoch": 0.7859228971962616, "grad_norm": 1.700168490409851, "learning_rate": 2.3101806077841937e-06, "loss": 0.7352, "step": 13455 }, { "epoch": 0.7859813084112149, "grad_norm": 1.0106806755065918, "learning_rate": 2.308971346680686e-06, "loss": 0.8036, "step": 13456 }, { "epoch": 0.7860397196261683, "grad_norm": 1.5909538269042969, "learning_rate": 2.3077623608441535e-06, "loss": 0.8127, "step": 13457 }, { "epoch": 0.7860981308411215, "grad_norm": 1.0169528722763062, "learning_rate": 2.30655365031786e-06, "loss": 0.7879, "step": 13458 }, { "epoch": 0.7861565420560748, "grad_norm": 1.6801655292510986, "learning_rate": 2.305345215145074e-06, "loss": 0.7191, "step": 13459 }, { "epoch": 0.7862149532710281, "grad_norm": 1.024040699005127, "learning_rate": 2.304137055369038e-06, "loss": 0.6104, "step": 13460 }, { "epoch": 0.7862733644859813, "grad_norm": 1.347261667251587, "learning_rate": 2.302929171032997e-06, "loss": 0.8192, "step": 13461 }, { "epoch": 0.7863317757009346, "grad_norm": 1.0574157238006592, "learning_rate": 2.301721562180186e-06, "loss": 0.7457, "step": 13462 }, { "epoch": 0.7863901869158878, "grad_norm": 1.2530393600463867, "learning_rate": 2.3005142288538183e-06, "loss": 0.8214, "step": 13463 }, { "epoch": 0.7864485981308411, "grad_norm": 1.2284828424453735, "learning_rate": 2.2993071710971115e-06, "loss": 0.7842, "step": 13464 }, { "epoch": 0.7865070093457944, "grad_norm": 2.013935089111328, "learning_rate": 2.298100388953265e-06, "loss": 0.8918, "step": 13465 }, { "epoch": 0.7865654205607476, "grad_norm": 0.9869218468666077, "learning_rate": 2.2968938824654662e-06, "loss": 0.775, "step": 13466 }, { "epoch": 0.7866238317757009, "grad_norm": 0.8691692352294922, "learning_rate": 2.295687651676901e-06, "loss": 0.6133, "step": 13467 }, { "epoch": 0.7866822429906543, "grad_norm": 0.9268889427185059, "learning_rate": 2.294481696630739e-06, "loss": 0.6359, "step": 13468 }, { "epoch": 0.7867406542056075, "grad_norm": 1.7788127660751343, "learning_rate": 2.2932760173701473e-06, "loss": 0.8276, "step": 13469 }, { "epoch": 0.7867990654205608, "grad_norm": 1.2583417892456055, "learning_rate": 2.292070613938274e-06, "loss": 0.8745, "step": 13470 }, { "epoch": 0.786857476635514, "grad_norm": 1.566249966621399, "learning_rate": 2.29086548637826e-06, "loss": 0.9289, "step": 13471 }, { "epoch": 0.7869158878504673, "grad_norm": 1.3402007818222046, "learning_rate": 2.2896606347332375e-06, "loss": 0.8141, "step": 13472 }, { "epoch": 0.7869742990654206, "grad_norm": 0.9783856868743896, "learning_rate": 2.288456059046331e-06, "loss": 0.7594, "step": 13473 }, { "epoch": 0.7870327102803738, "grad_norm": 1.2865562438964844, "learning_rate": 2.2872517593606557e-06, "loss": 0.7962, "step": 13474 }, { "epoch": 0.7870911214953271, "grad_norm": 1.6964976787567139, "learning_rate": 2.2860477357193112e-06, "loss": 0.8453, "step": 13475 }, { "epoch": 0.7871495327102803, "grad_norm": 0.8807451725006104, "learning_rate": 2.284843988165387e-06, "loss": 0.7739, "step": 13476 }, { "epoch": 0.7872079439252336, "grad_norm": 0.9250586628913879, "learning_rate": 2.2836405167419696e-06, "loss": 0.6292, "step": 13477 }, { "epoch": 0.787266355140187, "grad_norm": 1.3406351804733276, "learning_rate": 2.2824373214921313e-06, "loss": 0.8405, "step": 13478 }, { "epoch": 0.7873247663551401, "grad_norm": 1.217218041419983, "learning_rate": 2.2812344024589385e-06, "loss": 0.6434, "step": 13479 }, { "epoch": 0.7873831775700935, "grad_norm": 1.2062195539474487, "learning_rate": 2.2800317596854414e-06, "loss": 0.9034, "step": 13480 }, { "epoch": 0.7874415887850468, "grad_norm": 1.0050759315490723, "learning_rate": 2.278829393214682e-06, "loss": 0.621, "step": 13481 }, { "epoch": 0.7875, "grad_norm": 1.3620775938034058, "learning_rate": 2.2776273030896966e-06, "loss": 0.6439, "step": 13482 }, { "epoch": 0.7875584112149533, "grad_norm": 1.0702416896820068, "learning_rate": 2.2764254893535066e-06, "loss": 0.7877, "step": 13483 }, { "epoch": 0.7876168224299065, "grad_norm": 1.1401010751724243, "learning_rate": 2.275223952049125e-06, "loss": 0.6853, "step": 13484 }, { "epoch": 0.7876752336448598, "grad_norm": 0.857218861579895, "learning_rate": 2.2740226912195607e-06, "loss": 0.7308, "step": 13485 }, { "epoch": 0.7877336448598131, "grad_norm": 1.3622819185256958, "learning_rate": 2.272821706907802e-06, "loss": 0.7558, "step": 13486 }, { "epoch": 0.7877920560747663, "grad_norm": 1.153848648071289, "learning_rate": 2.271620999156837e-06, "loss": 0.6051, "step": 13487 }, { "epoch": 0.7878504672897196, "grad_norm": 1.0468168258666992, "learning_rate": 2.270420568009636e-06, "loss": 0.7895, "step": 13488 }, { "epoch": 0.787908878504673, "grad_norm": 1.0724477767944336, "learning_rate": 2.2692204135091643e-06, "loss": 0.654, "step": 13489 }, { "epoch": 0.7879672897196262, "grad_norm": 1.0842783451080322, "learning_rate": 2.2680205356983797e-06, "loss": 0.6093, "step": 13490 }, { "epoch": 0.7880257009345795, "grad_norm": 1.0024418830871582, "learning_rate": 2.266820934620222e-06, "loss": 0.6379, "step": 13491 }, { "epoch": 0.7880841121495327, "grad_norm": 2.475964307785034, "learning_rate": 2.265621610317631e-06, "loss": 0.8586, "step": 13492 }, { "epoch": 0.788142523364486, "grad_norm": 1.3518542051315308, "learning_rate": 2.264422562833524e-06, "loss": 0.863, "step": 13493 }, { "epoch": 0.7882009345794393, "grad_norm": 1.1330845355987549, "learning_rate": 2.2632237922108203e-06, "loss": 0.6111, "step": 13494 }, { "epoch": 0.7882593457943925, "grad_norm": 1.1381863355636597, "learning_rate": 2.2620252984924275e-06, "loss": 0.8955, "step": 13495 }, { "epoch": 0.7883177570093458, "grad_norm": 0.992132842540741, "learning_rate": 2.260827081721233e-06, "loss": 0.7711, "step": 13496 }, { "epoch": 0.788376168224299, "grad_norm": 1.0616146326065063, "learning_rate": 2.2596291419401296e-06, "loss": 0.6752, "step": 13497 }, { "epoch": 0.7884345794392523, "grad_norm": 0.9257476925849915, "learning_rate": 2.258431479191985e-06, "loss": 0.5951, "step": 13498 }, { "epoch": 0.7884929906542056, "grad_norm": 0.9903459548950195, "learning_rate": 2.2572340935196713e-06, "loss": 0.6454, "step": 13499 }, { "epoch": 0.7885514018691588, "grad_norm": 1.3210272789001465, "learning_rate": 2.256036984966038e-06, "loss": 0.7855, "step": 13500 }, { "epoch": 0.7886098130841122, "grad_norm": 1.2428858280181885, "learning_rate": 2.2548401535739316e-06, "loss": 0.7435, "step": 13501 }, { "epoch": 0.7886682242990655, "grad_norm": 1.4548777341842651, "learning_rate": 2.2536435993861926e-06, "loss": 0.783, "step": 13502 }, { "epoch": 0.7887266355140187, "grad_norm": 1.2411495447158813, "learning_rate": 2.252447322445639e-06, "loss": 0.922, "step": 13503 }, { "epoch": 0.788785046728972, "grad_norm": 1.2556408643722534, "learning_rate": 2.2512513227950926e-06, "loss": 0.7965, "step": 13504 }, { "epoch": 0.7888434579439252, "grad_norm": 1.068668246269226, "learning_rate": 2.2500556004773545e-06, "loss": 0.6139, "step": 13505 }, { "epoch": 0.7889018691588785, "grad_norm": 1.3006319999694824, "learning_rate": 2.248860155535221e-06, "loss": 0.8136, "step": 13506 }, { "epoch": 0.7889602803738318, "grad_norm": 1.031673789024353, "learning_rate": 2.247664988011482e-06, "loss": 0.7006, "step": 13507 }, { "epoch": 0.789018691588785, "grad_norm": 1.2492703199386597, "learning_rate": 2.2464700979489076e-06, "loss": 0.8378, "step": 13508 }, { "epoch": 0.7890771028037383, "grad_norm": 0.768328070640564, "learning_rate": 2.245275485390269e-06, "loss": 0.8845, "step": 13509 }, { "epoch": 0.7891355140186916, "grad_norm": 1.8030848503112793, "learning_rate": 2.244081150378318e-06, "loss": 1.0027, "step": 13510 }, { "epoch": 0.7891939252336448, "grad_norm": 1.1076228618621826, "learning_rate": 2.2428870929558012e-06, "loss": 0.7299, "step": 13511 }, { "epoch": 0.7892523364485982, "grad_norm": 1.0283905267715454, "learning_rate": 2.2416933131654584e-06, "loss": 0.667, "step": 13512 }, { "epoch": 0.7893107476635514, "grad_norm": 1.764388918876648, "learning_rate": 2.2404998110500133e-06, "loss": 0.7748, "step": 13513 }, { "epoch": 0.7893691588785047, "grad_norm": 1.458552360534668, "learning_rate": 2.2393065866521792e-06, "loss": 0.8538, "step": 13514 }, { "epoch": 0.789427570093458, "grad_norm": 1.2775154113769531, "learning_rate": 2.2381136400146686e-06, "loss": 0.8115, "step": 13515 }, { "epoch": 0.7894859813084112, "grad_norm": 0.8918085694313049, "learning_rate": 2.2369209711801708e-06, "loss": 0.6095, "step": 13516 }, { "epoch": 0.7895443925233645, "grad_norm": 0.9160469174385071, "learning_rate": 2.235728580191375e-06, "loss": 0.5596, "step": 13517 }, { "epoch": 0.7896028037383177, "grad_norm": 1.3878791332244873, "learning_rate": 2.234536467090963e-06, "loss": 0.7502, "step": 13518 }, { "epoch": 0.789661214953271, "grad_norm": 1.2276747226715088, "learning_rate": 2.2333446319215923e-06, "loss": 0.6718, "step": 13519 }, { "epoch": 0.7897196261682243, "grad_norm": 3.253281593322754, "learning_rate": 2.232153074725928e-06, "loss": 0.7541, "step": 13520 }, { "epoch": 0.7897780373831775, "grad_norm": 1.7930512428283691, "learning_rate": 2.230961795546609e-06, "loss": 0.869, "step": 13521 }, { "epoch": 0.7898364485981308, "grad_norm": 1.5657668113708496, "learning_rate": 2.229770794426276e-06, "loss": 0.715, "step": 13522 }, { "epoch": 0.7898948598130842, "grad_norm": 1.173548936843872, "learning_rate": 2.228580071407558e-06, "loss": 0.8505, "step": 13523 }, { "epoch": 0.7899532710280374, "grad_norm": 0.9090325832366943, "learning_rate": 2.2273896265330665e-06, "loss": 0.7088, "step": 13524 }, { "epoch": 0.7900116822429907, "grad_norm": 1.0426034927368164, "learning_rate": 2.226199459845413e-06, "loss": 0.6127, "step": 13525 }, { "epoch": 0.7900700934579439, "grad_norm": 1.2005817890167236, "learning_rate": 2.22500957138719e-06, "loss": 0.7967, "step": 13526 }, { "epoch": 0.7901285046728972, "grad_norm": 1.4288535118103027, "learning_rate": 2.2238199612009858e-06, "loss": 0.7615, "step": 13527 }, { "epoch": 0.7901869158878505, "grad_norm": 1.2548317909240723, "learning_rate": 2.222630629329382e-06, "loss": 0.8648, "step": 13528 }, { "epoch": 0.7902453271028037, "grad_norm": 1.053610920906067, "learning_rate": 2.2214415758149386e-06, "loss": 0.7993, "step": 13529 }, { "epoch": 0.790303738317757, "grad_norm": 1.6641765832901, "learning_rate": 2.2202528007002176e-06, "loss": 0.821, "step": 13530 }, { "epoch": 0.7903621495327103, "grad_norm": 1.0102503299713135, "learning_rate": 2.2190643040277625e-06, "loss": 0.6468, "step": 13531 }, { "epoch": 0.7904205607476635, "grad_norm": 0.8166118264198303, "learning_rate": 2.2178760858401147e-06, "loss": 0.5442, "step": 13532 }, { "epoch": 0.7904789719626168, "grad_norm": 0.9613721966743469, "learning_rate": 2.2166881461797953e-06, "loss": 0.629, "step": 13533 }, { "epoch": 0.79053738317757, "grad_norm": 1.1619606018066406, "learning_rate": 2.215500485089325e-06, "loss": 0.7899, "step": 13534 }, { "epoch": 0.7905957943925234, "grad_norm": 1.2410117387771606, "learning_rate": 2.214313102611213e-06, "loss": 0.715, "step": 13535 }, { "epoch": 0.7906542056074767, "grad_norm": 1.063775897026062, "learning_rate": 2.213125998787953e-06, "loss": 0.7973, "step": 13536 }, { "epoch": 0.7907126168224299, "grad_norm": 1.5445934534072876, "learning_rate": 2.2119391736620342e-06, "loss": 0.6842, "step": 13537 }, { "epoch": 0.7907710280373832, "grad_norm": 1.211273431777954, "learning_rate": 2.210752627275932e-06, "loss": 0.6977, "step": 13538 }, { "epoch": 0.7908294392523364, "grad_norm": 1.2813223600387573, "learning_rate": 2.209566359672114e-06, "loss": 0.6835, "step": 13539 }, { "epoch": 0.7908878504672897, "grad_norm": 1.6444021463394165, "learning_rate": 2.208380370893041e-06, "loss": 0.6218, "step": 13540 }, { "epoch": 0.790946261682243, "grad_norm": 1.0212587118148804, "learning_rate": 2.2071946609811554e-06, "loss": 0.736, "step": 13541 }, { "epoch": 0.7910046728971962, "grad_norm": 1.0141594409942627, "learning_rate": 2.2060092299788995e-06, "loss": 0.8685, "step": 13542 }, { "epoch": 0.7910630841121495, "grad_norm": 2.0336577892303467, "learning_rate": 2.2048240779286946e-06, "loss": 0.829, "step": 13543 }, { "epoch": 0.7911214953271029, "grad_norm": 1.110344409942627, "learning_rate": 2.2036392048729618e-06, "loss": 0.8503, "step": 13544 }, { "epoch": 0.791179906542056, "grad_norm": 1.23239266872406, "learning_rate": 2.20245461085411e-06, "loss": 0.7751, "step": 13545 }, { "epoch": 0.7912383177570094, "grad_norm": 1.7536301612854004, "learning_rate": 2.2012702959145325e-06, "loss": 0.6394, "step": 13546 }, { "epoch": 0.7912967289719626, "grad_norm": 1.346881628036499, "learning_rate": 2.2000862600966224e-06, "loss": 0.7628, "step": 13547 }, { "epoch": 0.7913551401869159, "grad_norm": 1.059654712677002, "learning_rate": 2.1989025034427523e-06, "loss": 0.7009, "step": 13548 }, { "epoch": 0.7914135514018692, "grad_norm": 1.2270190715789795, "learning_rate": 2.1977190259952887e-06, "loss": 0.671, "step": 13549 }, { "epoch": 0.7914719626168224, "grad_norm": 0.970702052116394, "learning_rate": 2.196535827796592e-06, "loss": 0.6321, "step": 13550 }, { "epoch": 0.7915303738317757, "grad_norm": 1.4800310134887695, "learning_rate": 2.195352908889008e-06, "loss": 0.8105, "step": 13551 }, { "epoch": 0.791588785046729, "grad_norm": 1.2792365550994873, "learning_rate": 2.1941702693148783e-06, "loss": 0.7594, "step": 13552 }, { "epoch": 0.7916471962616822, "grad_norm": 1.1446536779403687, "learning_rate": 2.1929879091165264e-06, "loss": 0.8265, "step": 13553 }, { "epoch": 0.7917056074766355, "grad_norm": 0.9992858171463013, "learning_rate": 2.1918058283362677e-06, "loss": 0.7615, "step": 13554 }, { "epoch": 0.7917640186915887, "grad_norm": 2.058197498321533, "learning_rate": 2.1906240270164124e-06, "loss": 0.7247, "step": 13555 }, { "epoch": 0.7918224299065421, "grad_norm": 1.040205478668213, "learning_rate": 2.1894425051992587e-06, "loss": 0.5981, "step": 13556 }, { "epoch": 0.7918808411214954, "grad_norm": 1.150687575340271, "learning_rate": 2.188261262927096e-06, "loss": 0.8237, "step": 13557 }, { "epoch": 0.7919392523364486, "grad_norm": 1.0859216451644897, "learning_rate": 2.187080300242198e-06, "loss": 0.7874, "step": 13558 }, { "epoch": 0.7919976635514019, "grad_norm": 1.6379590034484863, "learning_rate": 2.185899617186832e-06, "loss": 0.7605, "step": 13559 }, { "epoch": 0.7920560747663551, "grad_norm": 1.4164001941680908, "learning_rate": 2.1847192138032546e-06, "loss": 0.876, "step": 13560 }, { "epoch": 0.7921144859813084, "grad_norm": 1.510225772857666, "learning_rate": 2.1835390901337173e-06, "loss": 0.8771, "step": 13561 }, { "epoch": 0.7921728971962617, "grad_norm": 1.302594542503357, "learning_rate": 2.1823592462204567e-06, "loss": 0.9885, "step": 13562 }, { "epoch": 0.7922313084112149, "grad_norm": 1.7906849384307861, "learning_rate": 2.1811796821056997e-06, "loss": 0.7353, "step": 13563 }, { "epoch": 0.7922897196261682, "grad_norm": 1.0787659883499146, "learning_rate": 2.180000397831659e-06, "loss": 0.7067, "step": 13564 }, { "epoch": 0.7923481308411215, "grad_norm": 0.8846263289451599, "learning_rate": 2.178821393440549e-06, "loss": 0.6912, "step": 13565 }, { "epoch": 0.7924065420560747, "grad_norm": 0.9212952852249146, "learning_rate": 2.1776426689745587e-06, "loss": 0.7086, "step": 13566 }, { "epoch": 0.7924649532710281, "grad_norm": 1.1055512428283691, "learning_rate": 2.176464224475886e-06, "loss": 0.6666, "step": 13567 }, { "epoch": 0.7925233644859813, "grad_norm": 1.4417014122009277, "learning_rate": 2.1752860599867033e-06, "loss": 0.8214, "step": 13568 }, { "epoch": 0.7925817757009346, "grad_norm": 2.140150308609009, "learning_rate": 2.174108175549173e-06, "loss": 0.7227, "step": 13569 }, { "epoch": 0.7926401869158879, "grad_norm": 0.9112186431884766, "learning_rate": 2.1729305712054606e-06, "loss": 0.6973, "step": 13570 }, { "epoch": 0.7926985981308411, "grad_norm": 1.5031695365905762, "learning_rate": 2.1717532469977067e-06, "loss": 0.7634, "step": 13571 }, { "epoch": 0.7927570093457944, "grad_norm": 1.265629768371582, "learning_rate": 2.170576202968051e-06, "loss": 0.6737, "step": 13572 }, { "epoch": 0.7928154205607477, "grad_norm": 1.2540796995162964, "learning_rate": 2.1693994391586236e-06, "loss": 0.861, "step": 13573 }, { "epoch": 0.7928738317757009, "grad_norm": 1.0856807231903076, "learning_rate": 2.1682229556115377e-06, "loss": 0.7707, "step": 13574 }, { "epoch": 0.7929322429906542, "grad_norm": 1.4393211603164673, "learning_rate": 2.167046752368902e-06, "loss": 0.8507, "step": 13575 }, { "epoch": 0.7929906542056074, "grad_norm": 1.3949843645095825, "learning_rate": 2.1658708294728128e-06, "loss": 0.8092, "step": 13576 }, { "epoch": 0.7930490654205608, "grad_norm": 1.1894901990890503, "learning_rate": 2.1646951869653566e-06, "loss": 0.6653, "step": 13577 }, { "epoch": 0.7931074766355141, "grad_norm": 1.4245527982711792, "learning_rate": 2.1635198248886134e-06, "loss": 0.7803, "step": 13578 }, { "epoch": 0.7931658878504673, "grad_norm": 1.444344401359558, "learning_rate": 2.162344743284647e-06, "loss": 0.6822, "step": 13579 }, { "epoch": 0.7932242990654206, "grad_norm": 0.904130756855011, "learning_rate": 2.161169942195518e-06, "loss": 0.5982, "step": 13580 }, { "epoch": 0.7932827102803738, "grad_norm": 1.384832501411438, "learning_rate": 2.1599954216632703e-06, "loss": 0.6514, "step": 13581 }, { "epoch": 0.7933411214953271, "grad_norm": 0.9779571294784546, "learning_rate": 2.1588211817299387e-06, "loss": 0.8058, "step": 13582 }, { "epoch": 0.7933995327102804, "grad_norm": 1.2339099645614624, "learning_rate": 2.1576472224375534e-06, "loss": 0.7927, "step": 13583 }, { "epoch": 0.7934579439252336, "grad_norm": 1.1991270780563354, "learning_rate": 2.156473543828129e-06, "loss": 0.7837, "step": 13584 }, { "epoch": 0.7935163551401869, "grad_norm": 1.4108895063400269, "learning_rate": 2.1553001459436785e-06, "loss": 0.6949, "step": 13585 }, { "epoch": 0.7935747663551402, "grad_norm": 1.1673654317855835, "learning_rate": 2.1541270288261918e-06, "loss": 0.8685, "step": 13586 }, { "epoch": 0.7936331775700934, "grad_norm": 1.0965396165847778, "learning_rate": 2.1529541925176555e-06, "loss": 0.7849, "step": 13587 }, { "epoch": 0.7936915887850468, "grad_norm": 1.5862674713134766, "learning_rate": 2.1517816370600488e-06, "loss": 0.8541, "step": 13588 }, { "epoch": 0.79375, "grad_norm": 1.1352159976959229, "learning_rate": 2.1506093624953373e-06, "loss": 0.7991, "step": 13589 }, { "epoch": 0.7938084112149533, "grad_norm": 1.113542914390564, "learning_rate": 2.14943736886548e-06, "loss": 0.8228, "step": 13590 }, { "epoch": 0.7938668224299066, "grad_norm": 1.037688136100769, "learning_rate": 2.1482656562124216e-06, "loss": 0.7458, "step": 13591 }, { "epoch": 0.7939252336448598, "grad_norm": 0.9562198519706726, "learning_rate": 2.1470942245780957e-06, "loss": 0.6476, "step": 13592 }, { "epoch": 0.7939836448598131, "grad_norm": 1.092883586883545, "learning_rate": 2.14592307400443e-06, "loss": 0.7052, "step": 13593 }, { "epoch": 0.7940420560747663, "grad_norm": 1.206008791923523, "learning_rate": 2.144752204533341e-06, "loss": 0.6225, "step": 13594 }, { "epoch": 0.7941004672897196, "grad_norm": 1.0048515796661377, "learning_rate": 2.1435816162067403e-06, "loss": 0.715, "step": 13595 }, { "epoch": 0.7941588785046729, "grad_norm": 1.2505414485931396, "learning_rate": 2.1424113090665178e-06, "loss": 0.7199, "step": 13596 }, { "epoch": 0.7942172897196261, "grad_norm": 1.1069713830947876, "learning_rate": 2.141241283154558e-06, "loss": 0.7103, "step": 13597 }, { "epoch": 0.7942757009345794, "grad_norm": 0.9620909094810486, "learning_rate": 2.1400715385127437e-06, "loss": 0.6612, "step": 13598 }, { "epoch": 0.7943341121495328, "grad_norm": 1.2493236064910889, "learning_rate": 2.1389020751829316e-06, "loss": 0.7646, "step": 13599 }, { "epoch": 0.794392523364486, "grad_norm": 1.3629730939865112, "learning_rate": 2.1377328932069874e-06, "loss": 0.8349, "step": 13600 }, { "epoch": 0.7944509345794393, "grad_norm": 1.3442505598068237, "learning_rate": 2.1365639926267534e-06, "loss": 0.7988, "step": 13601 }, { "epoch": 0.7945093457943925, "grad_norm": 1.033608317375183, "learning_rate": 2.1353953734840615e-06, "loss": 0.6691, "step": 13602 }, { "epoch": 0.7945677570093458, "grad_norm": 1.1881970167160034, "learning_rate": 2.134227035820743e-06, "loss": 0.7577, "step": 13603 }, { "epoch": 0.7946261682242991, "grad_norm": 1.2756333351135254, "learning_rate": 2.133058979678607e-06, "loss": 0.7277, "step": 13604 }, { "epoch": 0.7946845794392523, "grad_norm": 1.6505279541015625, "learning_rate": 2.1318912050994646e-06, "loss": 0.8244, "step": 13605 }, { "epoch": 0.7947429906542056, "grad_norm": 1.0492483377456665, "learning_rate": 2.1307237121251112e-06, "loss": 0.8451, "step": 13606 }, { "epoch": 0.7948014018691589, "grad_norm": 1.030304193496704, "learning_rate": 2.1295565007973274e-06, "loss": 0.8167, "step": 13607 }, { "epoch": 0.7948598130841121, "grad_norm": 1.2178936004638672, "learning_rate": 2.128389571157894e-06, "loss": 0.7676, "step": 13608 }, { "epoch": 0.7949182242990654, "grad_norm": 1.1508779525756836, "learning_rate": 2.1272229232485707e-06, "loss": 0.7492, "step": 13609 }, { "epoch": 0.7949766355140186, "grad_norm": 1.013709306716919, "learning_rate": 2.1260565571111156e-06, "loss": 0.7166, "step": 13610 }, { "epoch": 0.795035046728972, "grad_norm": 1.0012378692626953, "learning_rate": 2.1248904727872764e-06, "loss": 0.6305, "step": 13611 }, { "epoch": 0.7950934579439253, "grad_norm": 1.8289241790771484, "learning_rate": 2.123724670318782e-06, "loss": 0.7095, "step": 13612 }, { "epoch": 0.7951518691588785, "grad_norm": 1.087298035621643, "learning_rate": 2.122559149747364e-06, "loss": 0.8346, "step": 13613 }, { "epoch": 0.7952102803738318, "grad_norm": 1.073801875114441, "learning_rate": 2.1213939111147295e-06, "loss": 0.712, "step": 13614 }, { "epoch": 0.795268691588785, "grad_norm": 1.2070266008377075, "learning_rate": 2.1202289544625908e-06, "loss": 0.7448, "step": 13615 }, { "epoch": 0.7953271028037383, "grad_norm": 1.030824065208435, "learning_rate": 2.1190642798326367e-06, "loss": 0.6997, "step": 13616 }, { "epoch": 0.7953855140186916, "grad_norm": 1.0127519369125366, "learning_rate": 2.1178998872665534e-06, "loss": 0.697, "step": 13617 }, { "epoch": 0.7954439252336448, "grad_norm": 1.4259138107299805, "learning_rate": 2.116735776806018e-06, "loss": 0.6076, "step": 13618 }, { "epoch": 0.7955023364485981, "grad_norm": 0.9573628306388855, "learning_rate": 2.1155719484926894e-06, "loss": 0.5585, "step": 13619 }, { "epoch": 0.7955607476635514, "grad_norm": 1.014283537864685, "learning_rate": 2.1144084023682287e-06, "loss": 0.9415, "step": 13620 }, { "epoch": 0.7956191588785047, "grad_norm": 1.4353845119476318, "learning_rate": 2.1132451384742736e-06, "loss": 0.9142, "step": 13621 }, { "epoch": 0.795677570093458, "grad_norm": 1.2413238286972046, "learning_rate": 2.1120821568524596e-06, "loss": 0.7935, "step": 13622 }, { "epoch": 0.7957359813084112, "grad_norm": 1.1427741050720215, "learning_rate": 2.110919457544415e-06, "loss": 0.6861, "step": 13623 }, { "epoch": 0.7957943925233645, "grad_norm": 0.9870851635932922, "learning_rate": 2.10975704059175e-06, "loss": 0.6118, "step": 13624 }, { "epoch": 0.7958528037383178, "grad_norm": 0.9814536571502686, "learning_rate": 2.1085949060360654e-06, "loss": 0.6372, "step": 13625 }, { "epoch": 0.795911214953271, "grad_norm": 1.2517718076705933, "learning_rate": 2.107433053918958e-06, "loss": 0.7872, "step": 13626 }, { "epoch": 0.7959696261682243, "grad_norm": 1.2141762971878052, "learning_rate": 2.1062714842820107e-06, "loss": 0.7778, "step": 13627 }, { "epoch": 0.7960280373831776, "grad_norm": 1.0715957880020142, "learning_rate": 2.1051101971668007e-06, "loss": 0.8387, "step": 13628 }, { "epoch": 0.7960864485981308, "grad_norm": 0.9176779389381409, "learning_rate": 2.103949192614888e-06, "loss": 0.5954, "step": 13629 }, { "epoch": 0.7961448598130841, "grad_norm": 1.2969461679458618, "learning_rate": 2.1027884706678214e-06, "loss": 0.7284, "step": 13630 }, { "epoch": 0.7962032710280373, "grad_norm": 1.191588282585144, "learning_rate": 2.101628031367152e-06, "loss": 0.9318, "step": 13631 }, { "epoch": 0.7962616822429907, "grad_norm": 0.9667164087295532, "learning_rate": 2.100467874754403e-06, "loss": 0.6795, "step": 13632 }, { "epoch": 0.796320093457944, "grad_norm": 1.0231037139892578, "learning_rate": 2.0993080008711075e-06, "loss": 0.861, "step": 13633 }, { "epoch": 0.7963785046728972, "grad_norm": 1.117431640625, "learning_rate": 2.0981484097587734e-06, "loss": 0.7608, "step": 13634 }, { "epoch": 0.7964369158878505, "grad_norm": 1.03434157371521, "learning_rate": 2.0969891014589006e-06, "loss": 0.6112, "step": 13635 }, { "epoch": 0.7964953271028037, "grad_norm": 1.3446030616760254, "learning_rate": 2.095830076012988e-06, "loss": 0.7542, "step": 13636 }, { "epoch": 0.796553738317757, "grad_norm": 1.1842265129089355, "learning_rate": 2.09467133346251e-06, "loss": 0.6743, "step": 13637 }, { "epoch": 0.7966121495327103, "grad_norm": 1.2374500036239624, "learning_rate": 2.0935128738489442e-06, "loss": 0.7436, "step": 13638 }, { "epoch": 0.7966705607476635, "grad_norm": 1.2735776901245117, "learning_rate": 2.0923546972137534e-06, "loss": 0.7559, "step": 13639 }, { "epoch": 0.7967289719626168, "grad_norm": 1.3006696701049805, "learning_rate": 2.0911968035983842e-06, "loss": 1.0036, "step": 13640 }, { "epoch": 0.7967873831775701, "grad_norm": 1.9509737491607666, "learning_rate": 2.0900391930442842e-06, "loss": 0.6037, "step": 13641 }, { "epoch": 0.7968457943925233, "grad_norm": 1.1302231550216675, "learning_rate": 2.08888186559288e-06, "loss": 0.7884, "step": 13642 }, { "epoch": 0.7969042056074767, "grad_norm": 0.9844521284103394, "learning_rate": 2.087724821285595e-06, "loss": 0.6985, "step": 13643 }, { "epoch": 0.7969626168224299, "grad_norm": 1.603103518486023, "learning_rate": 2.086568060163845e-06, "loss": 0.7713, "step": 13644 }, { "epoch": 0.7970210280373832, "grad_norm": 1.3559149503707886, "learning_rate": 2.0854115822690234e-06, "loss": 0.7497, "step": 13645 }, { "epoch": 0.7970794392523365, "grad_norm": 1.0885860919952393, "learning_rate": 2.084255387642529e-06, "loss": 0.7667, "step": 13646 }, { "epoch": 0.7971378504672897, "grad_norm": 1.3139089345932007, "learning_rate": 2.0830994763257352e-06, "loss": 1.0464, "step": 13647 }, { "epoch": 0.797196261682243, "grad_norm": 1.4738531112670898, "learning_rate": 2.0819438483600197e-06, "loss": 0.7885, "step": 13648 }, { "epoch": 0.7972546728971963, "grad_norm": 0.9152523279190063, "learning_rate": 2.080788503786738e-06, "loss": 0.6434, "step": 13649 }, { "epoch": 0.7973130841121495, "grad_norm": 0.9771870970726013, "learning_rate": 2.079633442647242e-06, "loss": 0.6116, "step": 13650 }, { "epoch": 0.7973714953271028, "grad_norm": 1.7150065898895264, "learning_rate": 2.078478664982876e-06, "loss": 0.7186, "step": 13651 }, { "epoch": 0.797429906542056, "grad_norm": 1.2785265445709229, "learning_rate": 2.0773241708349634e-06, "loss": 0.8284, "step": 13652 }, { "epoch": 0.7974883177570093, "grad_norm": 1.0188038349151611, "learning_rate": 2.0761699602448315e-06, "loss": 0.671, "step": 13653 }, { "epoch": 0.7975467289719627, "grad_norm": 0.9965946674346924, "learning_rate": 2.075016033253784e-06, "loss": 0.8058, "step": 13654 }, { "epoch": 0.7976051401869159, "grad_norm": 1.2617231607437134, "learning_rate": 2.073862389903123e-06, "loss": 0.779, "step": 13655 }, { "epoch": 0.7976635514018692, "grad_norm": 1.2180845737457275, "learning_rate": 2.0727090302341424e-06, "loss": 0.7297, "step": 13656 }, { "epoch": 0.7977219626168224, "grad_norm": 1.0066624879837036, "learning_rate": 2.0715559542881148e-06, "loss": 0.8797, "step": 13657 }, { "epoch": 0.7977803738317757, "grad_norm": 1.0698717832565308, "learning_rate": 2.070403162106315e-06, "loss": 0.5539, "step": 13658 }, { "epoch": 0.797838785046729, "grad_norm": 1.1012746095657349, "learning_rate": 2.069250653729996e-06, "loss": 0.8806, "step": 13659 }, { "epoch": 0.7978971962616822, "grad_norm": 1.0889078378677368, "learning_rate": 2.0680984292004125e-06, "loss": 0.8088, "step": 13660 }, { "epoch": 0.7979556074766355, "grad_norm": 1.2386677265167236, "learning_rate": 2.066946488558803e-06, "loss": 0.6968, "step": 13661 }, { "epoch": 0.7980140186915888, "grad_norm": 1.0540236234664917, "learning_rate": 2.0657948318463928e-06, "loss": 0.6915, "step": 13662 }, { "epoch": 0.798072429906542, "grad_norm": 0.9478921294212341, "learning_rate": 2.064643459104405e-06, "loss": 0.6503, "step": 13663 }, { "epoch": 0.7981308411214953, "grad_norm": 0.9805182218551636, "learning_rate": 2.0634923703740462e-06, "loss": 0.6803, "step": 13664 }, { "epoch": 0.7981892523364486, "grad_norm": 0.9146764874458313, "learning_rate": 2.062341565696507e-06, "loss": 0.6831, "step": 13665 }, { "epoch": 0.7982476635514019, "grad_norm": 1.306106686592102, "learning_rate": 2.061191045112988e-06, "loss": 0.848, "step": 13666 }, { "epoch": 0.7983060747663552, "grad_norm": 0.9398171901702881, "learning_rate": 2.0600408086646595e-06, "loss": 0.7063, "step": 13667 }, { "epoch": 0.7983644859813084, "grad_norm": 1.3184462785720825, "learning_rate": 2.0588908563926935e-06, "loss": 0.7791, "step": 13668 }, { "epoch": 0.7984228971962617, "grad_norm": 1.0853073596954346, "learning_rate": 2.057741188338245e-06, "loss": 0.8082, "step": 13669 }, { "epoch": 0.798481308411215, "grad_norm": 1.0626461505889893, "learning_rate": 2.0565918045424584e-06, "loss": 0.8269, "step": 13670 }, { "epoch": 0.7985397196261682, "grad_norm": 1.0139447450637817, "learning_rate": 2.0554427050464742e-06, "loss": 0.61, "step": 13671 }, { "epoch": 0.7985981308411215, "grad_norm": 1.7791731357574463, "learning_rate": 2.054293889891419e-06, "loss": 0.7065, "step": 13672 }, { "epoch": 0.7986565420560747, "grad_norm": 1.3074049949645996, "learning_rate": 2.0531453591184124e-06, "loss": 0.7458, "step": 13673 }, { "epoch": 0.798714953271028, "grad_norm": 0.9048128128051758, "learning_rate": 2.051997112768559e-06, "loss": 0.796, "step": 13674 }, { "epoch": 0.7987733644859814, "grad_norm": 1.000432014465332, "learning_rate": 2.050849150882952e-06, "loss": 0.7677, "step": 13675 }, { "epoch": 0.7988317757009346, "grad_norm": 0.9718784093856812, "learning_rate": 2.049701473502681e-06, "loss": 0.7831, "step": 13676 }, { "epoch": 0.7988901869158879, "grad_norm": 1.0816726684570312, "learning_rate": 2.048554080668822e-06, "loss": 0.7796, "step": 13677 }, { "epoch": 0.7989485981308411, "grad_norm": 1.0407142639160156, "learning_rate": 2.047406972422442e-06, "loss": 0.6876, "step": 13678 }, { "epoch": 0.7990070093457944, "grad_norm": 1.0228279829025269, "learning_rate": 2.0462601488045962e-06, "loss": 0.7171, "step": 13679 }, { "epoch": 0.7990654205607477, "grad_norm": 1.0346752405166626, "learning_rate": 2.0451136098563273e-06, "loss": 0.6044, "step": 13680 }, { "epoch": 0.7991238317757009, "grad_norm": 1.0714852809906006, "learning_rate": 2.0439673556186747e-06, "loss": 0.758, "step": 13681 }, { "epoch": 0.7991822429906542, "grad_norm": 1.2949002981185913, "learning_rate": 2.0428213861326585e-06, "loss": 0.6909, "step": 13682 }, { "epoch": 0.7992406542056075, "grad_norm": 1.2086042165756226, "learning_rate": 2.0416757014392973e-06, "loss": 0.8582, "step": 13683 }, { "epoch": 0.7992990654205607, "grad_norm": 1.2213561534881592, "learning_rate": 2.0405303015795987e-06, "loss": 0.8041, "step": 13684 }, { "epoch": 0.799357476635514, "grad_norm": 1.3886793851852417, "learning_rate": 2.0393851865945504e-06, "loss": 0.7976, "step": 13685 }, { "epoch": 0.7994158878504672, "grad_norm": 1.0466471910476685, "learning_rate": 2.038240356525143e-06, "loss": 0.7532, "step": 13686 }, { "epoch": 0.7994742990654206, "grad_norm": 1.4536938667297363, "learning_rate": 2.0370958114123463e-06, "loss": 0.6814, "step": 13687 }, { "epoch": 0.7995327102803739, "grad_norm": 1.1619220972061157, "learning_rate": 2.0359515512971262e-06, "loss": 0.7123, "step": 13688 }, { "epoch": 0.7995911214953271, "grad_norm": 0.9881994724273682, "learning_rate": 2.034807576220439e-06, "loss": 0.6939, "step": 13689 }, { "epoch": 0.7996495327102804, "grad_norm": 1.8408443927764893, "learning_rate": 2.0336638862232226e-06, "loss": 0.8484, "step": 13690 }, { "epoch": 0.7997079439252337, "grad_norm": 1.4018232822418213, "learning_rate": 2.032520481346417e-06, "loss": 0.7843, "step": 13691 }, { "epoch": 0.7997663551401869, "grad_norm": 1.3682122230529785, "learning_rate": 2.0313773616309397e-06, "loss": 0.8298, "step": 13692 }, { "epoch": 0.7998247663551402, "grad_norm": 1.2170335054397583, "learning_rate": 2.030234527117706e-06, "loss": 0.6958, "step": 13693 }, { "epoch": 0.7998831775700934, "grad_norm": 1.1786394119262695, "learning_rate": 2.0290919778476214e-06, "loss": 0.6977, "step": 13694 }, { "epoch": 0.7999415887850467, "grad_norm": 1.271007776260376, "learning_rate": 2.0279497138615734e-06, "loss": 0.6838, "step": 13695 }, { "epoch": 0.8, "grad_norm": 1.578715205192566, "learning_rate": 2.026807735200449e-06, "loss": 0.8413, "step": 13696 }, { "epoch": 0.8000584112149532, "grad_norm": 1.0781776905059814, "learning_rate": 2.0256660419051177e-06, "loss": 0.7315, "step": 13697 }, { "epoch": 0.8001168224299066, "grad_norm": 1.111570954322815, "learning_rate": 2.024524634016438e-06, "loss": 0.7811, "step": 13698 }, { "epoch": 0.8001752336448598, "grad_norm": 2.0085504055023193, "learning_rate": 2.0233835115752696e-06, "loss": 0.7102, "step": 13699 }, { "epoch": 0.8002336448598131, "grad_norm": 1.3772964477539062, "learning_rate": 2.022242674622449e-06, "loss": 0.8423, "step": 13700 }, { "epoch": 0.8002920560747664, "grad_norm": 1.1343172788619995, "learning_rate": 2.0211021231988103e-06, "loss": 0.8224, "step": 13701 }, { "epoch": 0.8003504672897196, "grad_norm": 1.435976266860962, "learning_rate": 2.019961857345173e-06, "loss": 0.7621, "step": 13702 }, { "epoch": 0.8004088785046729, "grad_norm": 1.6664729118347168, "learning_rate": 2.018821877102345e-06, "loss": 0.7923, "step": 13703 }, { "epoch": 0.8004672897196262, "grad_norm": 1.583851933479309, "learning_rate": 2.017682182511129e-06, "loss": 0.8082, "step": 13704 }, { "epoch": 0.8005257009345794, "grad_norm": 1.459519863128662, "learning_rate": 2.0165427736123177e-06, "loss": 0.9712, "step": 13705 }, { "epoch": 0.8005841121495327, "grad_norm": 1.0919698476791382, "learning_rate": 2.015403650446691e-06, "loss": 0.7216, "step": 13706 }, { "epoch": 0.8006425233644859, "grad_norm": 1.1623796224594116, "learning_rate": 2.014264813055019e-06, "loss": 0.7506, "step": 13707 }, { "epoch": 0.8007009345794392, "grad_norm": 2.6336464881896973, "learning_rate": 2.0131262614780566e-06, "loss": 0.7028, "step": 13708 }, { "epoch": 0.8007593457943926, "grad_norm": 1.3200974464416504, "learning_rate": 2.011987995756557e-06, "loss": 0.8374, "step": 13709 }, { "epoch": 0.8008177570093458, "grad_norm": 1.6928739547729492, "learning_rate": 2.0108500159312582e-06, "loss": 0.7613, "step": 13710 }, { "epoch": 0.8008761682242991, "grad_norm": 0.9251733422279358, "learning_rate": 2.0097123220428938e-06, "loss": 0.6727, "step": 13711 }, { "epoch": 0.8009345794392523, "grad_norm": 1.3422932624816895, "learning_rate": 2.00857491413218e-06, "loss": 0.8755, "step": 13712 }, { "epoch": 0.8009929906542056, "grad_norm": 1.55227530002594, "learning_rate": 2.0074377922398204e-06, "loss": 0.6045, "step": 13713 }, { "epoch": 0.8010514018691589, "grad_norm": 1.518312931060791, "learning_rate": 2.0063009564065206e-06, "loss": 0.8712, "step": 13714 }, { "epoch": 0.8011098130841121, "grad_norm": 2.0456483364105225, "learning_rate": 2.00516440667296e-06, "loss": 0.9717, "step": 13715 }, { "epoch": 0.8011682242990654, "grad_norm": 1.0567893981933594, "learning_rate": 2.004028143079828e-06, "loss": 0.8587, "step": 13716 }, { "epoch": 0.8012266355140187, "grad_norm": 1.3849297761917114, "learning_rate": 2.0028921656677857e-06, "loss": 0.6797, "step": 13717 }, { "epoch": 0.8012850467289719, "grad_norm": 1.9910818338394165, "learning_rate": 2.0017564744774885e-06, "loss": 0.7834, "step": 13718 }, { "epoch": 0.8013434579439253, "grad_norm": 1.028594732284546, "learning_rate": 2.0006210695495885e-06, "loss": 0.5643, "step": 13719 }, { "epoch": 0.8014018691588785, "grad_norm": 0.8611136078834534, "learning_rate": 1.999485950924718e-06, "loss": 0.7309, "step": 13720 }, { "epoch": 0.8014602803738318, "grad_norm": 1.4470897912979126, "learning_rate": 1.9983511186435055e-06, "loss": 0.6476, "step": 13721 }, { "epoch": 0.8015186915887851, "grad_norm": 1.4535740613937378, "learning_rate": 1.99721657274657e-06, "loss": 0.9187, "step": 13722 }, { "epoch": 0.8015771028037383, "grad_norm": 1.1467909812927246, "learning_rate": 1.996082313274513e-06, "loss": 0.6231, "step": 13723 }, { "epoch": 0.8016355140186916, "grad_norm": 1.2266299724578857, "learning_rate": 1.994948340267935e-06, "loss": 0.8716, "step": 13724 }, { "epoch": 0.8016939252336449, "grad_norm": 0.9980427622795105, "learning_rate": 1.9938146537674165e-06, "loss": 0.6192, "step": 13725 }, { "epoch": 0.8017523364485981, "grad_norm": 2.1447062492370605, "learning_rate": 1.9926812538135367e-06, "loss": 0.7054, "step": 13726 }, { "epoch": 0.8018107476635514, "grad_norm": 1.5659762620925903, "learning_rate": 1.9915481404468616e-06, "loss": 0.7995, "step": 13727 }, { "epoch": 0.8018691588785046, "grad_norm": 1.007636308670044, "learning_rate": 1.9904153137079417e-06, "loss": 0.6244, "step": 13728 }, { "epoch": 0.8019275700934579, "grad_norm": 1.7344632148742676, "learning_rate": 1.9892827736373265e-06, "loss": 0.7276, "step": 13729 }, { "epoch": 0.8019859813084113, "grad_norm": 1.2820661067962646, "learning_rate": 1.9881505202755457e-06, "loss": 0.7625, "step": 13730 }, { "epoch": 0.8020443925233645, "grad_norm": 0.9349419474601746, "learning_rate": 1.987018553663125e-06, "loss": 0.5862, "step": 13731 }, { "epoch": 0.8021028037383178, "grad_norm": 1.881911039352417, "learning_rate": 1.9858868738405824e-06, "loss": 0.6979, "step": 13732 }, { "epoch": 0.802161214953271, "grad_norm": 0.9738483428955078, "learning_rate": 1.9847554808484148e-06, "loss": 0.6978, "step": 13733 }, { "epoch": 0.8022196261682243, "grad_norm": 1.4332618713378906, "learning_rate": 1.9836243747271224e-06, "loss": 0.7569, "step": 13734 }, { "epoch": 0.8022780373831776, "grad_norm": 0.9983245730400085, "learning_rate": 1.9824935555171798e-06, "loss": 0.7257, "step": 13735 }, { "epoch": 0.8023364485981308, "grad_norm": 1.1576157808303833, "learning_rate": 1.9813630232590684e-06, "loss": 0.7993, "step": 13736 }, { "epoch": 0.8023948598130841, "grad_norm": 1.381318211555481, "learning_rate": 1.980232777993244e-06, "loss": 0.8287, "step": 13737 }, { "epoch": 0.8024532710280374, "grad_norm": 1.176771879196167, "learning_rate": 1.9791028197601625e-06, "loss": 0.7097, "step": 13738 }, { "epoch": 0.8025116822429906, "grad_norm": 0.8646134734153748, "learning_rate": 1.9779731486002664e-06, "loss": 0.7464, "step": 13739 }, { "epoch": 0.802570093457944, "grad_norm": 1.3431559801101685, "learning_rate": 1.976843764553986e-06, "loss": 0.7321, "step": 13740 }, { "epoch": 0.8026285046728971, "grad_norm": 1.2376383543014526, "learning_rate": 1.97571466766174e-06, "loss": 0.729, "step": 13741 }, { "epoch": 0.8026869158878505, "grad_norm": 1.5917361974716187, "learning_rate": 1.974585857963942e-06, "loss": 0.7891, "step": 13742 }, { "epoch": 0.8027453271028038, "grad_norm": 3.8130903244018555, "learning_rate": 1.9734573355009935e-06, "loss": 0.7278, "step": 13743 }, { "epoch": 0.802803738317757, "grad_norm": 1.4265081882476807, "learning_rate": 1.972329100313286e-06, "loss": 0.6697, "step": 13744 }, { "epoch": 0.8028621495327103, "grad_norm": 0.9238653779029846, "learning_rate": 1.9712011524412e-06, "loss": 0.6969, "step": 13745 }, { "epoch": 0.8029205607476636, "grad_norm": 1.552351951599121, "learning_rate": 1.9700734919251e-06, "loss": 0.9983, "step": 13746 }, { "epoch": 0.8029789719626168, "grad_norm": 1.0415534973144531, "learning_rate": 1.9689461188053527e-06, "loss": 0.6153, "step": 13747 }, { "epoch": 0.8030373831775701, "grad_norm": 1.0179306268692017, "learning_rate": 1.967819033122298e-06, "loss": 0.6125, "step": 13748 }, { "epoch": 0.8030957943925233, "grad_norm": 1.2171564102172852, "learning_rate": 1.9666922349162878e-06, "loss": 0.7815, "step": 13749 }, { "epoch": 0.8031542056074766, "grad_norm": 0.9612230062484741, "learning_rate": 1.965565724227644e-06, "loss": 0.6698, "step": 13750 }, { "epoch": 0.80321261682243, "grad_norm": 1.2130728960037231, "learning_rate": 1.964439501096683e-06, "loss": 0.6295, "step": 13751 }, { "epoch": 0.8032710280373832, "grad_norm": 1.0902448892593384, "learning_rate": 1.9633135655637194e-06, "loss": 0.7348, "step": 13752 }, { "epoch": 0.8033294392523365, "grad_norm": 0.9223734140396118, "learning_rate": 1.962187917669044e-06, "loss": 0.5427, "step": 13753 }, { "epoch": 0.8033878504672897, "grad_norm": 1.1654623746871948, "learning_rate": 1.9610625574529472e-06, "loss": 0.8613, "step": 13754 }, { "epoch": 0.803446261682243, "grad_norm": 1.1377180814743042, "learning_rate": 1.9599374849557108e-06, "loss": 0.8748, "step": 13755 }, { "epoch": 0.8035046728971963, "grad_norm": 1.165856122970581, "learning_rate": 1.958812700217595e-06, "loss": 0.8131, "step": 13756 }, { "epoch": 0.8035630841121495, "grad_norm": 1.2446318864822388, "learning_rate": 1.9576882032788636e-06, "loss": 0.8294, "step": 13757 }, { "epoch": 0.8036214953271028, "grad_norm": 1.051788091659546, "learning_rate": 1.9565639941797553e-06, "loss": 0.7477, "step": 13758 }, { "epoch": 0.8036799065420561, "grad_norm": 1.480481743812561, "learning_rate": 1.9554400729605117e-06, "loss": 0.6982, "step": 13759 }, { "epoch": 0.8037383177570093, "grad_norm": 1.541911005973816, "learning_rate": 1.954316439661359e-06, "loss": 0.7563, "step": 13760 }, { "epoch": 0.8037967289719626, "grad_norm": 1.1045465469360352, "learning_rate": 1.9531930943225086e-06, "loss": 0.7924, "step": 13761 }, { "epoch": 0.8038551401869158, "grad_norm": 0.9524716734886169, "learning_rate": 1.9520700369841706e-06, "loss": 0.7416, "step": 13762 }, { "epoch": 0.8039135514018692, "grad_norm": 1.0315126180648804, "learning_rate": 1.950947267686536e-06, "loss": 0.7413, "step": 13763 }, { "epoch": 0.8039719626168225, "grad_norm": 1.1931425333023071, "learning_rate": 1.9498247864697893e-06, "loss": 0.7736, "step": 13764 }, { "epoch": 0.8040303738317757, "grad_norm": 0.9687777161598206, "learning_rate": 1.9487025933741112e-06, "loss": 0.7933, "step": 13765 }, { "epoch": 0.804088785046729, "grad_norm": 1.3399180173873901, "learning_rate": 1.9475806884396576e-06, "loss": 0.6635, "step": 13766 }, { "epoch": 0.8041471962616823, "grad_norm": 1.066917061805725, "learning_rate": 1.946459071706588e-06, "loss": 0.6456, "step": 13767 }, { "epoch": 0.8042056074766355, "grad_norm": 1.0805747509002686, "learning_rate": 1.945337743215041e-06, "loss": 0.7912, "step": 13768 }, { "epoch": 0.8042640186915888, "grad_norm": 1.1789612770080566, "learning_rate": 1.944216703005155e-06, "loss": 0.7994, "step": 13769 }, { "epoch": 0.804322429906542, "grad_norm": 1.3032281398773193, "learning_rate": 1.9430959511170476e-06, "loss": 0.9075, "step": 13770 }, { "epoch": 0.8043808411214953, "grad_norm": 5.349466800689697, "learning_rate": 1.9419754875908338e-06, "loss": 0.7536, "step": 13771 }, { "epoch": 0.8044392523364486, "grad_norm": 1.1549664735794067, "learning_rate": 1.9408553124666173e-06, "loss": 0.8164, "step": 13772 }, { "epoch": 0.8044976635514018, "grad_norm": 1.0475869178771973, "learning_rate": 1.939735425784486e-06, "loss": 0.7888, "step": 13773 }, { "epoch": 0.8045560747663552, "grad_norm": 1.1235172748565674, "learning_rate": 1.938615827584526e-06, "loss": 0.8952, "step": 13774 }, { "epoch": 0.8046144859813084, "grad_norm": 1.0259324312210083, "learning_rate": 1.937496517906804e-06, "loss": 0.9598, "step": 13775 }, { "epoch": 0.8046728971962617, "grad_norm": 0.9592755436897278, "learning_rate": 1.936377496791382e-06, "loss": 0.7555, "step": 13776 }, { "epoch": 0.804731308411215, "grad_norm": 1.054966926574707, "learning_rate": 1.9352587642783137e-06, "loss": 0.8768, "step": 13777 }, { "epoch": 0.8047897196261682, "grad_norm": 1.059922218322754, "learning_rate": 1.934140320407636e-06, "loss": 0.7591, "step": 13778 }, { "epoch": 0.8048481308411215, "grad_norm": 1.3428466320037842, "learning_rate": 1.9330221652193805e-06, "loss": 0.6351, "step": 13779 }, { "epoch": 0.8049065420560748, "grad_norm": 1.1736035346984863, "learning_rate": 1.9319042987535665e-06, "loss": 0.8026, "step": 13780 }, { "epoch": 0.804964953271028, "grad_norm": 0.833583414554596, "learning_rate": 1.9307867210501975e-06, "loss": 0.5789, "step": 13781 }, { "epoch": 0.8050233644859813, "grad_norm": 1.1753644943237305, "learning_rate": 1.9296694321492828e-06, "loss": 0.7724, "step": 13782 }, { "epoch": 0.8050817757009345, "grad_norm": 1.0560146570205688, "learning_rate": 1.9285524320908022e-06, "loss": 0.7427, "step": 13783 }, { "epoch": 0.8051401869158878, "grad_norm": 1.1532750129699707, "learning_rate": 1.92743572091474e-06, "loss": 0.8239, "step": 13784 }, { "epoch": 0.8051985981308412, "grad_norm": 1.0490273237228394, "learning_rate": 1.9263192986610614e-06, "loss": 0.673, "step": 13785 }, { "epoch": 0.8052570093457944, "grad_norm": 1.1742074489593506, "learning_rate": 1.92520316536972e-06, "loss": 0.7809, "step": 13786 }, { "epoch": 0.8053154205607477, "grad_norm": 1.0934906005859375, "learning_rate": 1.9240873210806676e-06, "loss": 0.6797, "step": 13787 }, { "epoch": 0.805373831775701, "grad_norm": 1.5321552753448486, "learning_rate": 1.92297176583384e-06, "loss": 0.8375, "step": 13788 }, { "epoch": 0.8054322429906542, "grad_norm": 1.3419770002365112, "learning_rate": 1.921856499669166e-06, "loss": 0.7491, "step": 13789 }, { "epoch": 0.8054906542056075, "grad_norm": 1.042520523071289, "learning_rate": 1.9207415226265593e-06, "loss": 0.7757, "step": 13790 }, { "epoch": 0.8055490654205607, "grad_norm": 1.1122369766235352, "learning_rate": 1.9196268347459234e-06, "loss": 0.6583, "step": 13791 }, { "epoch": 0.805607476635514, "grad_norm": 0.8799676299095154, "learning_rate": 1.918512436067156e-06, "loss": 0.5866, "step": 13792 }, { "epoch": 0.8056658878504673, "grad_norm": 1.3047572374343872, "learning_rate": 1.917398326630141e-06, "loss": 0.7053, "step": 13793 }, { "epoch": 0.8057242990654205, "grad_norm": 0.9223652482032776, "learning_rate": 1.9162845064747583e-06, "loss": 0.7274, "step": 13794 }, { "epoch": 0.8057827102803738, "grad_norm": 1.4389832019805908, "learning_rate": 1.915170975640868e-06, "loss": 0.7292, "step": 13795 }, { "epoch": 0.805841121495327, "grad_norm": 1.0950274467468262, "learning_rate": 1.9140577341683218e-06, "loss": 0.8079, "step": 13796 }, { "epoch": 0.8058995327102804, "grad_norm": 1.0446748733520508, "learning_rate": 1.912944782096966e-06, "loss": 0.6938, "step": 13797 }, { "epoch": 0.8059579439252337, "grad_norm": 1.3035439252853394, "learning_rate": 1.9118321194666357e-06, "loss": 0.7919, "step": 13798 }, { "epoch": 0.8060163551401869, "grad_norm": 1.651513695716858, "learning_rate": 1.91071974631715e-06, "loss": 0.7608, "step": 13799 }, { "epoch": 0.8060747663551402, "grad_norm": 1.482832670211792, "learning_rate": 1.909607662688325e-06, "loss": 0.6382, "step": 13800 }, { "epoch": 0.8061331775700935, "grad_norm": 1.0595263242721558, "learning_rate": 1.9084958686199594e-06, "loss": 0.7733, "step": 13801 }, { "epoch": 0.8061915887850467, "grad_norm": 1.0227241516113281, "learning_rate": 1.90738436415185e-06, "loss": 0.698, "step": 13802 }, { "epoch": 0.80625, "grad_norm": 1.1499576568603516, "learning_rate": 1.9062731493237718e-06, "loss": 0.7542, "step": 13803 }, { "epoch": 0.8063084112149532, "grad_norm": 1.1137523651123047, "learning_rate": 1.9051622241754997e-06, "loss": 0.702, "step": 13804 }, { "epoch": 0.8063668224299065, "grad_norm": 1.0360114574432373, "learning_rate": 1.904051588746797e-06, "loss": 0.7249, "step": 13805 }, { "epoch": 0.8064252336448599, "grad_norm": 1.743862271308899, "learning_rate": 1.9029412430774087e-06, "loss": 0.7225, "step": 13806 }, { "epoch": 0.806483644859813, "grad_norm": 1.057793140411377, "learning_rate": 1.9018311872070793e-06, "loss": 0.6735, "step": 13807 }, { "epoch": 0.8065420560747664, "grad_norm": 1.7405630350112915, "learning_rate": 1.9007214211755331e-06, "loss": 0.7682, "step": 13808 }, { "epoch": 0.8066004672897197, "grad_norm": 1.0941569805145264, "learning_rate": 1.8996119450224936e-06, "loss": 0.7204, "step": 13809 }, { "epoch": 0.8066588785046729, "grad_norm": 1.2194724082946777, "learning_rate": 1.8985027587876714e-06, "loss": 0.7483, "step": 13810 }, { "epoch": 0.8067172897196262, "grad_norm": 1.1572457551956177, "learning_rate": 1.8973938625107592e-06, "loss": 0.8125, "step": 13811 }, { "epoch": 0.8067757009345794, "grad_norm": 3.9554805755615234, "learning_rate": 1.8962852562314505e-06, "loss": 0.8198, "step": 13812 }, { "epoch": 0.8068341121495327, "grad_norm": 1.2682784795761108, "learning_rate": 1.8951769399894215e-06, "loss": 0.6929, "step": 13813 }, { "epoch": 0.806892523364486, "grad_norm": 1.1202268600463867, "learning_rate": 1.8940689138243329e-06, "loss": 0.7271, "step": 13814 }, { "epoch": 0.8069509345794392, "grad_norm": 1.4308700561523438, "learning_rate": 1.8929611777758528e-06, "loss": 0.8098, "step": 13815 }, { "epoch": 0.8070093457943925, "grad_norm": 0.9423384070396423, "learning_rate": 1.8918537318836206e-06, "loss": 0.6933, "step": 13816 }, { "epoch": 0.8070677570093457, "grad_norm": 0.9338105320930481, "learning_rate": 1.8907465761872779e-06, "loss": 0.7178, "step": 13817 }, { "epoch": 0.8071261682242991, "grad_norm": 1.2039895057678223, "learning_rate": 1.8896397107264452e-06, "loss": 0.7701, "step": 13818 }, { "epoch": 0.8071845794392524, "grad_norm": 1.2331923246383667, "learning_rate": 1.8885331355407389e-06, "loss": 0.7696, "step": 13819 }, { "epoch": 0.8072429906542056, "grad_norm": 1.1959809064865112, "learning_rate": 1.8874268506697645e-06, "loss": 0.6216, "step": 13820 }, { "epoch": 0.8073014018691589, "grad_norm": 1.197398066520691, "learning_rate": 1.8863208561531176e-06, "loss": 0.8758, "step": 13821 }, { "epoch": 0.8073598130841122, "grad_norm": 1.1250218152999878, "learning_rate": 1.885215152030384e-06, "loss": 0.6977, "step": 13822 }, { "epoch": 0.8074182242990654, "grad_norm": 1.2330442667007446, "learning_rate": 1.8841097383411366e-06, "loss": 0.7794, "step": 13823 }, { "epoch": 0.8074766355140187, "grad_norm": 0.9171233773231506, "learning_rate": 1.8830046151249347e-06, "loss": 0.6012, "step": 13824 }, { "epoch": 0.8075350467289719, "grad_norm": 0.972572922706604, "learning_rate": 1.8818997824213347e-06, "loss": 0.6359, "step": 13825 }, { "epoch": 0.8075934579439252, "grad_norm": 1.389617681503296, "learning_rate": 1.8807952402698793e-06, "loss": 0.7507, "step": 13826 }, { "epoch": 0.8076518691588785, "grad_norm": 0.93155837059021, "learning_rate": 1.8796909887101034e-06, "loss": 0.8632, "step": 13827 }, { "epoch": 0.8077102803738317, "grad_norm": 1.1686593294143677, "learning_rate": 1.8785870277815265e-06, "loss": 0.6997, "step": 13828 }, { "epoch": 0.8077686915887851, "grad_norm": 1.2228529453277588, "learning_rate": 1.8774833575236573e-06, "loss": 0.7756, "step": 13829 }, { "epoch": 0.8078271028037384, "grad_norm": 0.9019112586975098, "learning_rate": 1.8763799779759984e-06, "loss": 0.7532, "step": 13830 }, { "epoch": 0.8078855140186916, "grad_norm": 0.9856263995170593, "learning_rate": 1.8752768891780427e-06, "loss": 0.7913, "step": 13831 }, { "epoch": 0.8079439252336449, "grad_norm": 1.1195530891418457, "learning_rate": 1.8741740911692708e-06, "loss": 0.7164, "step": 13832 }, { "epoch": 0.8080023364485981, "grad_norm": 0.7758342623710632, "learning_rate": 1.8730715839891512e-06, "loss": 0.5059, "step": 13833 }, { "epoch": 0.8080607476635514, "grad_norm": 1.0994253158569336, "learning_rate": 1.8719693676771412e-06, "loss": 0.689, "step": 13834 }, { "epoch": 0.8081191588785047, "grad_norm": 1.3076611757278442, "learning_rate": 1.8708674422726936e-06, "loss": 0.6575, "step": 13835 }, { "epoch": 0.8081775700934579, "grad_norm": 1.188496470451355, "learning_rate": 1.8697658078152436e-06, "loss": 0.7597, "step": 13836 }, { "epoch": 0.8082359813084112, "grad_norm": 1.0837115049362183, "learning_rate": 1.8686644643442198e-06, "loss": 0.8452, "step": 13837 }, { "epoch": 0.8082943925233644, "grad_norm": 1.012439250946045, "learning_rate": 1.8675634118990449e-06, "loss": 0.6858, "step": 13838 }, { "epoch": 0.8083528037383177, "grad_norm": 1.3134512901306152, "learning_rate": 1.8664626505191197e-06, "loss": 0.8052, "step": 13839 }, { "epoch": 0.8084112149532711, "grad_norm": 1.2488738298416138, "learning_rate": 1.865362180243847e-06, "loss": 0.5869, "step": 13840 }, { "epoch": 0.8084696261682243, "grad_norm": 1.1286064386367798, "learning_rate": 1.8642620011126077e-06, "loss": 0.5914, "step": 13841 }, { "epoch": 0.8085280373831776, "grad_norm": 1.1957088708877563, "learning_rate": 1.8631621131647815e-06, "loss": 0.7928, "step": 13842 }, { "epoch": 0.8085864485981309, "grad_norm": 1.5742838382720947, "learning_rate": 1.8620625164397343e-06, "loss": 0.8418, "step": 13843 }, { "epoch": 0.8086448598130841, "grad_norm": 1.121941089630127, "learning_rate": 1.8609632109768194e-06, "loss": 0.8064, "step": 13844 }, { "epoch": 0.8087032710280374, "grad_norm": 1.1747299432754517, "learning_rate": 1.859864196815384e-06, "loss": 0.8201, "step": 13845 }, { "epoch": 0.8087616822429906, "grad_norm": 2.4208972454071045, "learning_rate": 1.8587654739947592e-06, "loss": 0.5957, "step": 13846 }, { "epoch": 0.8088200934579439, "grad_norm": 1.2998321056365967, "learning_rate": 1.857667042554272e-06, "loss": 0.9552, "step": 13847 }, { "epoch": 0.8088785046728972, "grad_norm": 0.9238201379776001, "learning_rate": 1.8565689025332367e-06, "loss": 0.6448, "step": 13848 }, { "epoch": 0.8089369158878504, "grad_norm": 1.1291745901107788, "learning_rate": 1.855471053970952e-06, "loss": 0.7764, "step": 13849 }, { "epoch": 0.8089953271028038, "grad_norm": 0.982313334941864, "learning_rate": 1.8543734969067161e-06, "loss": 0.6649, "step": 13850 }, { "epoch": 0.809053738317757, "grad_norm": 1.1190630197525024, "learning_rate": 1.8532762313798091e-06, "loss": 0.6827, "step": 13851 }, { "epoch": 0.8091121495327103, "grad_norm": 0.8684371113777161, "learning_rate": 1.8521792574294993e-06, "loss": 0.6735, "step": 13852 }, { "epoch": 0.8091705607476636, "grad_norm": 1.522338628768921, "learning_rate": 1.8510825750950512e-06, "loss": 0.7956, "step": 13853 }, { "epoch": 0.8092289719626168, "grad_norm": 1.0979419946670532, "learning_rate": 1.8499861844157163e-06, "loss": 0.7691, "step": 13854 }, { "epoch": 0.8092873831775701, "grad_norm": 1.0991801023483276, "learning_rate": 1.8488900854307367e-06, "loss": 0.7373, "step": 13855 }, { "epoch": 0.8093457943925234, "grad_norm": 1.0610861778259277, "learning_rate": 1.84779427817934e-06, "loss": 0.6952, "step": 13856 }, { "epoch": 0.8094042056074766, "grad_norm": 1.2640814781188965, "learning_rate": 1.8466987627007438e-06, "loss": 0.7768, "step": 13857 }, { "epoch": 0.8094626168224299, "grad_norm": 1.1421641111373901, "learning_rate": 1.8456035390341608e-06, "loss": 0.8922, "step": 13858 }, { "epoch": 0.8095210280373831, "grad_norm": 1.2746495008468628, "learning_rate": 1.8445086072187878e-06, "loss": 0.6798, "step": 13859 }, { "epoch": 0.8095794392523364, "grad_norm": 0.83863365650177, "learning_rate": 1.8434139672938166e-06, "loss": 0.5329, "step": 13860 }, { "epoch": 0.8096378504672898, "grad_norm": 1.177433967590332, "learning_rate": 1.8423196192984227e-06, "loss": 0.6698, "step": 13861 }, { "epoch": 0.809696261682243, "grad_norm": 1.478591799736023, "learning_rate": 1.8412255632717713e-06, "loss": 0.7915, "step": 13862 }, { "epoch": 0.8097546728971963, "grad_norm": 1.0551061630249023, "learning_rate": 1.840131799253021e-06, "loss": 0.7948, "step": 13863 }, { "epoch": 0.8098130841121496, "grad_norm": 1.6539455652236938, "learning_rate": 1.8390383272813194e-06, "loss": 0.8741, "step": 13864 }, { "epoch": 0.8098714953271028, "grad_norm": 1.3460198640823364, "learning_rate": 1.8379451473958043e-06, "loss": 0.8077, "step": 13865 }, { "epoch": 0.8099299065420561, "grad_norm": 1.2794034481048584, "learning_rate": 1.8368522596355986e-06, "loss": 0.7755, "step": 13866 }, { "epoch": 0.8099883177570093, "grad_norm": 0.9014967679977417, "learning_rate": 1.8357596640398157e-06, "loss": 0.7222, "step": 13867 }, { "epoch": 0.8100467289719626, "grad_norm": 1.505821943283081, "learning_rate": 1.8346673606475651e-06, "loss": 0.742, "step": 13868 }, { "epoch": 0.8101051401869159, "grad_norm": 1.005287528038025, "learning_rate": 1.8335753494979359e-06, "loss": 0.6484, "step": 13869 }, { "epoch": 0.8101635514018691, "grad_norm": 1.1809251308441162, "learning_rate": 1.8324836306300142e-06, "loss": 0.6916, "step": 13870 }, { "epoch": 0.8102219626168224, "grad_norm": 1.5534226894378662, "learning_rate": 1.831392204082877e-06, "loss": 0.9223, "step": 13871 }, { "epoch": 0.8102803738317756, "grad_norm": 1.239906907081604, "learning_rate": 1.8303010698955803e-06, "loss": 0.7322, "step": 13872 }, { "epoch": 0.810338785046729, "grad_norm": 1.2488878965377808, "learning_rate": 1.8292102281071834e-06, "loss": 0.6048, "step": 13873 }, { "epoch": 0.8103971962616823, "grad_norm": 1.0467429161071777, "learning_rate": 1.8281196787567212e-06, "loss": 0.8186, "step": 13874 }, { "epoch": 0.8104556074766355, "grad_norm": 1.136246681213379, "learning_rate": 1.8270294218832296e-06, "loss": 0.7545, "step": 13875 }, { "epoch": 0.8105140186915888, "grad_norm": 1.1421154737472534, "learning_rate": 1.8259394575257305e-06, "loss": 0.8128, "step": 13876 }, { "epoch": 0.8105724299065421, "grad_norm": 1.0107890367507935, "learning_rate": 1.8248497857232316e-06, "loss": 0.6792, "step": 13877 }, { "epoch": 0.8106308411214953, "grad_norm": 0.9679694175720215, "learning_rate": 1.823760406514735e-06, "loss": 0.7589, "step": 13878 }, { "epoch": 0.8106892523364486, "grad_norm": 1.596469759941101, "learning_rate": 1.8226713199392286e-06, "loss": 0.8378, "step": 13879 }, { "epoch": 0.8107476635514018, "grad_norm": 1.1343120336532593, "learning_rate": 1.8215825260356912e-06, "loss": 0.8673, "step": 13880 }, { "epoch": 0.8108060747663551, "grad_norm": 1.0302644968032837, "learning_rate": 1.8204940248430958e-06, "loss": 0.864, "step": 13881 }, { "epoch": 0.8108644859813084, "grad_norm": 1.122717022895813, "learning_rate": 1.8194058164003946e-06, "loss": 0.7956, "step": 13882 }, { "epoch": 0.8109228971962616, "grad_norm": 2.520148515701294, "learning_rate": 1.81831790074654e-06, "loss": 0.6709, "step": 13883 }, { "epoch": 0.810981308411215, "grad_norm": 1.0438324213027954, "learning_rate": 1.8172302779204654e-06, "loss": 0.8024, "step": 13884 }, { "epoch": 0.8110397196261683, "grad_norm": 0.9824515581130981, "learning_rate": 1.8161429479611026e-06, "loss": 0.6564, "step": 13885 }, { "epoch": 0.8110981308411215, "grad_norm": 1.015278697013855, "learning_rate": 1.8150559109073607e-06, "loss": 0.7188, "step": 13886 }, { "epoch": 0.8111565420560748, "grad_norm": 1.3233052492141724, "learning_rate": 1.8139691667981508e-06, "loss": 0.8359, "step": 13887 }, { "epoch": 0.811214953271028, "grad_norm": 1.0447065830230713, "learning_rate": 1.8128827156723683e-06, "loss": 0.8077, "step": 13888 }, { "epoch": 0.8112733644859813, "grad_norm": 0.9970792531967163, "learning_rate": 1.8117965575688945e-06, "loss": 0.6961, "step": 13889 }, { "epoch": 0.8113317757009346, "grad_norm": 1.4432951211929321, "learning_rate": 1.8107106925266083e-06, "loss": 0.7741, "step": 13890 }, { "epoch": 0.8113901869158878, "grad_norm": 1.7258977890014648, "learning_rate": 1.8096251205843685e-06, "loss": 0.9595, "step": 13891 }, { "epoch": 0.8114485981308411, "grad_norm": 1.1746124029159546, "learning_rate": 1.8085398417810308e-06, "loss": 0.7109, "step": 13892 }, { "epoch": 0.8115070093457943, "grad_norm": 0.9869093894958496, "learning_rate": 1.8074548561554405e-06, "loss": 0.601, "step": 13893 }, { "epoch": 0.8115654205607477, "grad_norm": 1.066046118736267, "learning_rate": 1.806370163746426e-06, "loss": 0.8576, "step": 13894 }, { "epoch": 0.811623831775701, "grad_norm": 1.0408565998077393, "learning_rate": 1.8052857645928124e-06, "loss": 0.6573, "step": 13895 }, { "epoch": 0.8116822429906542, "grad_norm": 1.3501033782958984, "learning_rate": 1.8042016587334065e-06, "loss": 0.7219, "step": 13896 }, { "epoch": 0.8117406542056075, "grad_norm": 1.624440312385559, "learning_rate": 1.803117846207013e-06, "loss": 0.7597, "step": 13897 }, { "epoch": 0.8117990654205608, "grad_norm": 1.0289771556854248, "learning_rate": 1.8020343270524233e-06, "loss": 0.7353, "step": 13898 }, { "epoch": 0.811857476635514, "grad_norm": 0.9332631826400757, "learning_rate": 1.8009511013084136e-06, "loss": 0.7725, "step": 13899 }, { "epoch": 0.8119158878504673, "grad_norm": 2.207886219024658, "learning_rate": 1.7998681690137564e-06, "loss": 0.7311, "step": 13900 }, { "epoch": 0.8119742990654205, "grad_norm": 1.4267358779907227, "learning_rate": 1.79878553020721e-06, "loss": 0.8089, "step": 13901 }, { "epoch": 0.8120327102803738, "grad_norm": 1.0053486824035645, "learning_rate": 1.7977031849275183e-06, "loss": 0.6793, "step": 13902 }, { "epoch": 0.8120911214953271, "grad_norm": 1.2508820295333862, "learning_rate": 1.796621133213423e-06, "loss": 0.9354, "step": 13903 }, { "epoch": 0.8121495327102803, "grad_norm": 1.3485708236694336, "learning_rate": 1.795539375103652e-06, "loss": 1.0067, "step": 13904 }, { "epoch": 0.8122079439252337, "grad_norm": 1.071248173713684, "learning_rate": 1.7944579106369232e-06, "loss": 0.7872, "step": 13905 }, { "epoch": 0.812266355140187, "grad_norm": 0.8970380425453186, "learning_rate": 1.793376739851941e-06, "loss": 0.7974, "step": 13906 }, { "epoch": 0.8123247663551402, "grad_norm": 1.1548405885696411, "learning_rate": 1.7922958627873987e-06, "loss": 0.7581, "step": 13907 }, { "epoch": 0.8123831775700935, "grad_norm": 1.1000113487243652, "learning_rate": 1.7912152794819848e-06, "loss": 0.8865, "step": 13908 }, { "epoch": 0.8124415887850467, "grad_norm": 1.1413695812225342, "learning_rate": 1.7901349899743759e-06, "loss": 0.6633, "step": 13909 }, { "epoch": 0.8125, "grad_norm": 1.1516298055648804, "learning_rate": 1.789054994303231e-06, "loss": 0.6568, "step": 13910 }, { "epoch": 0.8125584112149533, "grad_norm": 0.9798055291175842, "learning_rate": 1.787975292507208e-06, "loss": 0.7385, "step": 13911 }, { "epoch": 0.8126168224299065, "grad_norm": 1.0686776638031006, "learning_rate": 1.7868958846249474e-06, "loss": 0.6685, "step": 13912 }, { "epoch": 0.8126752336448598, "grad_norm": 1.1242142915725708, "learning_rate": 1.7858167706950835e-06, "loss": 0.6816, "step": 13913 }, { "epoch": 0.812733644859813, "grad_norm": 1.098091959953308, "learning_rate": 1.7847379507562402e-06, "loss": 0.6653, "step": 13914 }, { "epoch": 0.8127920560747663, "grad_norm": 1.4174944162368774, "learning_rate": 1.783659424847025e-06, "loss": 0.7407, "step": 13915 }, { "epoch": 0.8128504672897197, "grad_norm": 1.5859966278076172, "learning_rate": 1.7825811930060444e-06, "loss": 0.863, "step": 13916 }, { "epoch": 0.8129088785046729, "grad_norm": 1.3858126401901245, "learning_rate": 1.7815032552718837e-06, "loss": 0.7964, "step": 13917 }, { "epoch": 0.8129672897196262, "grad_norm": 1.1696041822433472, "learning_rate": 1.7804256116831265e-06, "loss": 0.7945, "step": 13918 }, { "epoch": 0.8130257009345795, "grad_norm": 0.854055643081665, "learning_rate": 1.7793482622783386e-06, "loss": 0.5133, "step": 13919 }, { "epoch": 0.8130841121495327, "grad_norm": 1.1230067014694214, "learning_rate": 1.7782712070960828e-06, "loss": 0.7588, "step": 13920 }, { "epoch": 0.813142523364486, "grad_norm": 1.0505505800247192, "learning_rate": 1.777194446174908e-06, "loss": 0.6883, "step": 13921 }, { "epoch": 0.8132009345794392, "grad_norm": 1.0792961120605469, "learning_rate": 1.776117979553349e-06, "loss": 0.8608, "step": 13922 }, { "epoch": 0.8132593457943925, "grad_norm": 1.3343027830123901, "learning_rate": 1.775041807269936e-06, "loss": 0.7664, "step": 13923 }, { "epoch": 0.8133177570093458, "grad_norm": 0.9374427199363708, "learning_rate": 1.7739659293631828e-06, "loss": 0.7274, "step": 13924 }, { "epoch": 0.813376168224299, "grad_norm": 1.7427921295166016, "learning_rate": 1.7728903458715984e-06, "loss": 0.7742, "step": 13925 }, { "epoch": 0.8134345794392523, "grad_norm": 1.1509298086166382, "learning_rate": 1.77181505683368e-06, "loss": 0.8034, "step": 13926 }, { "epoch": 0.8134929906542057, "grad_norm": 1.3839976787567139, "learning_rate": 1.7707400622879079e-06, "loss": 0.8126, "step": 13927 }, { "epoch": 0.8135514018691589, "grad_norm": 1.3349412679672241, "learning_rate": 1.7696653622727623e-06, "loss": 0.9054, "step": 13928 }, { "epoch": 0.8136098130841122, "grad_norm": 1.1437621116638184, "learning_rate": 1.7685909568267034e-06, "loss": 0.6586, "step": 13929 }, { "epoch": 0.8136682242990654, "grad_norm": 1.344834566116333, "learning_rate": 1.7675168459881853e-06, "loss": 0.9146, "step": 13930 }, { "epoch": 0.8137266355140187, "grad_norm": 1.2093569040298462, "learning_rate": 1.7664430297956547e-06, "loss": 0.6733, "step": 13931 }, { "epoch": 0.813785046728972, "grad_norm": 1.334384560585022, "learning_rate": 1.76536950828754e-06, "loss": 0.8069, "step": 13932 }, { "epoch": 0.8138434579439252, "grad_norm": 1.2223972082138062, "learning_rate": 1.764296281502268e-06, "loss": 0.6946, "step": 13933 }, { "epoch": 0.8139018691588785, "grad_norm": 1.164228081703186, "learning_rate": 1.7632233494782458e-06, "loss": 0.9017, "step": 13934 }, { "epoch": 0.8139602803738317, "grad_norm": 0.919154167175293, "learning_rate": 1.762150712253874e-06, "loss": 0.6655, "step": 13935 }, { "epoch": 0.814018691588785, "grad_norm": 1.039196491241455, "learning_rate": 1.7610783698675438e-06, "loss": 0.6793, "step": 13936 }, { "epoch": 0.8140771028037384, "grad_norm": 1.1016885042190552, "learning_rate": 1.760006322357637e-06, "loss": 0.694, "step": 13937 }, { "epoch": 0.8141355140186916, "grad_norm": 1.1183289289474487, "learning_rate": 1.7589345697625238e-06, "loss": 0.7629, "step": 13938 }, { "epoch": 0.8141939252336449, "grad_norm": 0.8891233801841736, "learning_rate": 1.7578631121205613e-06, "loss": 0.7369, "step": 13939 }, { "epoch": 0.8142523364485982, "grad_norm": 1.358892560005188, "learning_rate": 1.7567919494700946e-06, "loss": 0.8258, "step": 13940 }, { "epoch": 0.8143107476635514, "grad_norm": 1.2701878547668457, "learning_rate": 1.755721081849464e-06, "loss": 0.6949, "step": 13941 }, { "epoch": 0.8143691588785047, "grad_norm": 0.9265058040618896, "learning_rate": 1.7546505092969967e-06, "loss": 0.6842, "step": 13942 }, { "epoch": 0.8144275700934579, "grad_norm": 1.4738712310791016, "learning_rate": 1.753580231851012e-06, "loss": 0.8144, "step": 13943 }, { "epoch": 0.8144859813084112, "grad_norm": 0.8000189065933228, "learning_rate": 1.7525102495498124e-06, "loss": 0.7333, "step": 13944 }, { "epoch": 0.8145443925233645, "grad_norm": 1.163938045501709, "learning_rate": 1.751440562431691e-06, "loss": 0.7269, "step": 13945 }, { "epoch": 0.8146028037383177, "grad_norm": 1.1155017614364624, "learning_rate": 1.7503711705349359e-06, "loss": 0.7454, "step": 13946 }, { "epoch": 0.814661214953271, "grad_norm": 1.1029245853424072, "learning_rate": 1.7493020738978205e-06, "loss": 0.7375, "step": 13947 }, { "epoch": 0.8147196261682244, "grad_norm": 2.063692331314087, "learning_rate": 1.7482332725586115e-06, "loss": 0.9034, "step": 13948 }, { "epoch": 0.8147780373831776, "grad_norm": 0.8993724584579468, "learning_rate": 1.7471647665555603e-06, "loss": 0.6104, "step": 13949 }, { "epoch": 0.8148364485981309, "grad_norm": 1.277579665184021, "learning_rate": 1.746096555926904e-06, "loss": 0.7256, "step": 13950 }, { "epoch": 0.8148948598130841, "grad_norm": 1.2410541772842407, "learning_rate": 1.745028640710883e-06, "loss": 0.6872, "step": 13951 }, { "epoch": 0.8149532710280374, "grad_norm": 1.134013295173645, "learning_rate": 1.7439610209457114e-06, "loss": 0.6672, "step": 13952 }, { "epoch": 0.8150116822429907, "grad_norm": 1.5446817874908447, "learning_rate": 1.7428936966696042e-06, "loss": 0.8848, "step": 13953 }, { "epoch": 0.8150700934579439, "grad_norm": 1.0319561958312988, "learning_rate": 1.741826667920762e-06, "loss": 0.6858, "step": 13954 }, { "epoch": 0.8151285046728972, "grad_norm": 1.2219417095184326, "learning_rate": 1.7407599347373717e-06, "loss": 0.8121, "step": 13955 }, { "epoch": 0.8151869158878504, "grad_norm": 1.3354192972183228, "learning_rate": 1.7396934971576162e-06, "loss": 0.8193, "step": 13956 }, { "epoch": 0.8152453271028037, "grad_norm": 1.2008473873138428, "learning_rate": 1.7386273552196587e-06, "loss": 0.7286, "step": 13957 }, { "epoch": 0.815303738317757, "grad_norm": 0.9860463738441467, "learning_rate": 1.7375615089616605e-06, "loss": 0.7614, "step": 13958 }, { "epoch": 0.8153621495327102, "grad_norm": 1.155007243156433, "learning_rate": 1.7364959584217711e-06, "loss": 0.794, "step": 13959 }, { "epoch": 0.8154205607476636, "grad_norm": 1.1876986026763916, "learning_rate": 1.7354307036381225e-06, "loss": 0.7524, "step": 13960 }, { "epoch": 0.8154789719626169, "grad_norm": 1.140731930732727, "learning_rate": 1.734365744648845e-06, "loss": 0.7094, "step": 13961 }, { "epoch": 0.8155373831775701, "grad_norm": 1.287635326385498, "learning_rate": 1.7333010814920503e-06, "loss": 0.7119, "step": 13962 }, { "epoch": 0.8155957943925234, "grad_norm": 1.2136263847351074, "learning_rate": 1.732236714205845e-06, "loss": 0.7058, "step": 13963 }, { "epoch": 0.8156542056074766, "grad_norm": 1.0570721626281738, "learning_rate": 1.731172642828326e-06, "loss": 0.6626, "step": 13964 }, { "epoch": 0.8157126168224299, "grad_norm": 1.0152587890625, "learning_rate": 1.730108867397573e-06, "loss": 0.7497, "step": 13965 }, { "epoch": 0.8157710280373832, "grad_norm": 1.1001908779144287, "learning_rate": 1.7290453879516634e-06, "loss": 0.818, "step": 13966 }, { "epoch": 0.8158294392523364, "grad_norm": 1.5855367183685303, "learning_rate": 1.7279822045286577e-06, "loss": 0.7554, "step": 13967 }, { "epoch": 0.8158878504672897, "grad_norm": 0.8530321717262268, "learning_rate": 1.7269193171666055e-06, "loss": 0.7465, "step": 13968 }, { "epoch": 0.815946261682243, "grad_norm": 1.2482279539108276, "learning_rate": 1.725856725903551e-06, "loss": 0.575, "step": 13969 }, { "epoch": 0.8160046728971962, "grad_norm": 1.3986124992370605, "learning_rate": 1.7247944307775245e-06, "loss": 0.853, "step": 13970 }, { "epoch": 0.8160630841121496, "grad_norm": 1.6364343166351318, "learning_rate": 1.723732431826548e-06, "loss": 0.7575, "step": 13971 }, { "epoch": 0.8161214953271028, "grad_norm": 1.0298869609832764, "learning_rate": 1.7226707290886302e-06, "loss": 0.7265, "step": 13972 }, { "epoch": 0.8161799065420561, "grad_norm": 0.9511203169822693, "learning_rate": 1.7216093226017672e-06, "loss": 0.6509, "step": 13973 }, { "epoch": 0.8162383177570094, "grad_norm": 1.4226551055908203, "learning_rate": 1.7205482124039486e-06, "loss": 0.7405, "step": 13974 }, { "epoch": 0.8162967289719626, "grad_norm": 1.4060019254684448, "learning_rate": 1.719487398533154e-06, "loss": 0.6935, "step": 13975 }, { "epoch": 0.8163551401869159, "grad_norm": 1.3240774869918823, "learning_rate": 1.718426881027353e-06, "loss": 0.8164, "step": 13976 }, { "epoch": 0.8164135514018691, "grad_norm": 1.1032036542892456, "learning_rate": 1.7173666599244987e-06, "loss": 0.6315, "step": 13977 }, { "epoch": 0.8164719626168224, "grad_norm": 1.192270040512085, "learning_rate": 1.716306735262535e-06, "loss": 0.6753, "step": 13978 }, { "epoch": 0.8165303738317757, "grad_norm": 1.3338325023651123, "learning_rate": 1.7152471070793996e-06, "loss": 0.8228, "step": 13979 }, { "epoch": 0.8165887850467289, "grad_norm": 1.3648916482925415, "learning_rate": 1.7141877754130176e-06, "loss": 0.7599, "step": 13980 }, { "epoch": 0.8166471962616823, "grad_norm": 2.9491987228393555, "learning_rate": 1.7131287403013064e-06, "loss": 0.8061, "step": 13981 }, { "epoch": 0.8167056074766356, "grad_norm": 1.1244468688964844, "learning_rate": 1.7120700017821657e-06, "loss": 0.7877, "step": 13982 }, { "epoch": 0.8167640186915888, "grad_norm": 1.1860706806182861, "learning_rate": 1.7110115598934863e-06, "loss": 0.746, "step": 13983 }, { "epoch": 0.8168224299065421, "grad_norm": 1.3472312688827515, "learning_rate": 1.7099534146731567e-06, "loss": 0.7124, "step": 13984 }, { "epoch": 0.8168808411214953, "grad_norm": 1.1814976930618286, "learning_rate": 1.7088955661590424e-06, "loss": 0.8757, "step": 13985 }, { "epoch": 0.8169392523364486, "grad_norm": 1.1257520914077759, "learning_rate": 1.707838014389007e-06, "loss": 0.6992, "step": 13986 }, { "epoch": 0.8169976635514019, "grad_norm": 1.3083802461624146, "learning_rate": 1.7067807594009033e-06, "loss": 0.638, "step": 13987 }, { "epoch": 0.8170560747663551, "grad_norm": 0.9495070576667786, "learning_rate": 1.7057238012325672e-06, "loss": 0.6796, "step": 13988 }, { "epoch": 0.8171144859813084, "grad_norm": 1.0826388597488403, "learning_rate": 1.7046671399218328e-06, "loss": 0.6907, "step": 13989 }, { "epoch": 0.8171728971962616, "grad_norm": 1.7152454853057861, "learning_rate": 1.7036107755065123e-06, "loss": 0.7692, "step": 13990 }, { "epoch": 0.8172313084112149, "grad_norm": 1.5996187925338745, "learning_rate": 1.7025547080244177e-06, "loss": 0.7394, "step": 13991 }, { "epoch": 0.8172897196261683, "grad_norm": 1.1915475130081177, "learning_rate": 1.7014989375133483e-06, "loss": 0.7939, "step": 13992 }, { "epoch": 0.8173481308411215, "grad_norm": 1.3849520683288574, "learning_rate": 1.7004434640110857e-06, "loss": 0.6545, "step": 13993 }, { "epoch": 0.8174065420560748, "grad_norm": 1.0261911153793335, "learning_rate": 1.6993882875554113e-06, "loss": 0.7423, "step": 13994 }, { "epoch": 0.8174649532710281, "grad_norm": 1.078884243965149, "learning_rate": 1.6983334081840852e-06, "loss": 0.7188, "step": 13995 }, { "epoch": 0.8175233644859813, "grad_norm": 1.1646384000778198, "learning_rate": 1.697278825934864e-06, "loss": 0.7546, "step": 13996 }, { "epoch": 0.8175817757009346, "grad_norm": 1.2929658889770508, "learning_rate": 1.6962245408454958e-06, "loss": 0.7857, "step": 13997 }, { "epoch": 0.8176401869158878, "grad_norm": 1.251044750213623, "learning_rate": 1.695170552953709e-06, "loss": 0.7372, "step": 13998 }, { "epoch": 0.8176985981308411, "grad_norm": 0.9121970534324646, "learning_rate": 1.6941168622972315e-06, "loss": 0.6241, "step": 13999 }, { "epoch": 0.8177570093457944, "grad_norm": 1.2659327983856201, "learning_rate": 1.6930634689137692e-06, "loss": 0.9842, "step": 14000 }, { "epoch": 0.8178154205607476, "grad_norm": 1.0306843519210815, "learning_rate": 1.6920103728410309e-06, "loss": 0.7509, "step": 14001 }, { "epoch": 0.8178738317757009, "grad_norm": 1.2565747499465942, "learning_rate": 1.6909575741167006e-06, "loss": 0.8421, "step": 14002 }, { "epoch": 0.8179322429906543, "grad_norm": 1.3034567832946777, "learning_rate": 1.6899050727784628e-06, "loss": 0.8598, "step": 14003 }, { "epoch": 0.8179906542056075, "grad_norm": 1.552669882774353, "learning_rate": 1.6888528688639882e-06, "loss": 0.8427, "step": 14004 }, { "epoch": 0.8180490654205608, "grad_norm": 0.9638116359710693, "learning_rate": 1.6878009624109315e-06, "loss": 0.8139, "step": 14005 }, { "epoch": 0.818107476635514, "grad_norm": 1.2788605690002441, "learning_rate": 1.6867493534569468e-06, "loss": 0.8238, "step": 14006 }, { "epoch": 0.8181658878504673, "grad_norm": 2.1794745922088623, "learning_rate": 1.6856980420396652e-06, "loss": 0.7103, "step": 14007 }, { "epoch": 0.8182242990654206, "grad_norm": 3.246562957763672, "learning_rate": 1.6846470281967186e-06, "loss": 0.8337, "step": 14008 }, { "epoch": 0.8182827102803738, "grad_norm": 1.0824540853500366, "learning_rate": 1.683596311965725e-06, "loss": 0.791, "step": 14009 }, { "epoch": 0.8183411214953271, "grad_norm": 0.9360554814338684, "learning_rate": 1.6825458933842842e-06, "loss": 0.7361, "step": 14010 }, { "epoch": 0.8183995327102803, "grad_norm": 0.9313424825668335, "learning_rate": 1.6814957724899972e-06, "loss": 0.782, "step": 14011 }, { "epoch": 0.8184579439252336, "grad_norm": 1.5780704021453857, "learning_rate": 1.680445949320444e-06, "loss": 0.7601, "step": 14012 }, { "epoch": 0.818516355140187, "grad_norm": 1.0978858470916748, "learning_rate": 1.679396423913201e-06, "loss": 0.7456, "step": 14013 }, { "epoch": 0.8185747663551401, "grad_norm": 0.9840729236602783, "learning_rate": 1.6783471963058318e-06, "loss": 0.8684, "step": 14014 }, { "epoch": 0.8186331775700935, "grad_norm": 0.8362605571746826, "learning_rate": 1.6772982665358873e-06, "loss": 0.5459, "step": 14015 }, { "epoch": 0.8186915887850468, "grad_norm": 1.2240880727767944, "learning_rate": 1.676249634640912e-06, "loss": 0.7282, "step": 14016 }, { "epoch": 0.81875, "grad_norm": 1.3804038763046265, "learning_rate": 1.6752013006584344e-06, "loss": 0.7954, "step": 14017 }, { "epoch": 0.8188084112149533, "grad_norm": 1.087174415588379, "learning_rate": 1.674153264625974e-06, "loss": 0.633, "step": 14018 }, { "epoch": 0.8188668224299065, "grad_norm": 0.9323582053184509, "learning_rate": 1.6731055265810426e-06, "loss": 0.8201, "step": 14019 }, { "epoch": 0.8189252336448598, "grad_norm": 0.8175744414329529, "learning_rate": 1.6720580865611403e-06, "loss": 0.6107, "step": 14020 }, { "epoch": 0.8189836448598131, "grad_norm": 1.3074443340301514, "learning_rate": 1.6710109446037558e-06, "loss": 0.8155, "step": 14021 }, { "epoch": 0.8190420560747663, "grad_norm": 1.4713020324707031, "learning_rate": 1.6699641007463674e-06, "loss": 0.9298, "step": 14022 }, { "epoch": 0.8191004672897196, "grad_norm": 1.0278507471084595, "learning_rate": 1.668917555026437e-06, "loss": 0.759, "step": 14023 }, { "epoch": 0.819158878504673, "grad_norm": 0.9074605107307434, "learning_rate": 1.6678713074814257e-06, "loss": 0.7475, "step": 14024 }, { "epoch": 0.8192172897196262, "grad_norm": 1.2818148136138916, "learning_rate": 1.6668253581487815e-06, "loss": 0.7311, "step": 14025 }, { "epoch": 0.8192757009345795, "grad_norm": 1.130628228187561, "learning_rate": 1.6657797070659343e-06, "loss": 0.8973, "step": 14026 }, { "epoch": 0.8193341121495327, "grad_norm": 1.7456921339035034, "learning_rate": 1.6647343542703143e-06, "loss": 0.7806, "step": 14027 }, { "epoch": 0.819392523364486, "grad_norm": 1.252397060394287, "learning_rate": 1.6636892997993292e-06, "loss": 0.7088, "step": 14028 }, { "epoch": 0.8194509345794393, "grad_norm": 1.162428617477417, "learning_rate": 1.662644543690386e-06, "loss": 0.6777, "step": 14029 }, { "epoch": 0.8195093457943925, "grad_norm": 1.0463764667510986, "learning_rate": 1.6616000859808778e-06, "loss": 0.6651, "step": 14030 }, { "epoch": 0.8195677570093458, "grad_norm": 1.168914556503296, "learning_rate": 1.6605559267081827e-06, "loss": 0.8502, "step": 14031 }, { "epoch": 0.819626168224299, "grad_norm": 1.375017523765564, "learning_rate": 1.6595120659096776e-06, "loss": 0.7871, "step": 14032 }, { "epoch": 0.8196845794392523, "grad_norm": 2.4147188663482666, "learning_rate": 1.6584685036227167e-06, "loss": 0.738, "step": 14033 }, { "epoch": 0.8197429906542056, "grad_norm": 1.1538546085357666, "learning_rate": 1.6574252398846558e-06, "loss": 0.727, "step": 14034 }, { "epoch": 0.8198014018691588, "grad_norm": 0.9018726944923401, "learning_rate": 1.6563822747328273e-06, "loss": 0.6338, "step": 14035 }, { "epoch": 0.8198598130841122, "grad_norm": 0.7636032104492188, "learning_rate": 1.6553396082045648e-06, "loss": 0.678, "step": 14036 }, { "epoch": 0.8199182242990655, "grad_norm": 1.2907710075378418, "learning_rate": 1.654297240337186e-06, "loss": 0.81, "step": 14037 }, { "epoch": 0.8199766355140187, "grad_norm": 1.177348256111145, "learning_rate": 1.6532551711679933e-06, "loss": 0.6828, "step": 14038 }, { "epoch": 0.820035046728972, "grad_norm": 1.2271684408187866, "learning_rate": 1.6522134007342894e-06, "loss": 0.8265, "step": 14039 }, { "epoch": 0.8200934579439252, "grad_norm": 1.3108927011489868, "learning_rate": 1.6511719290733542e-06, "loss": 0.7441, "step": 14040 }, { "epoch": 0.8201518691588785, "grad_norm": 1.5891185998916626, "learning_rate": 1.6501307562224644e-06, "loss": 0.8772, "step": 14041 }, { "epoch": 0.8202102803738318, "grad_norm": 0.8680116534233093, "learning_rate": 1.6490898822188883e-06, "loss": 0.6003, "step": 14042 }, { "epoch": 0.820268691588785, "grad_norm": 17.265878677368164, "learning_rate": 1.6480493070998738e-06, "loss": 0.7814, "step": 14043 }, { "epoch": 0.8203271028037383, "grad_norm": 1.1043025255203247, "learning_rate": 1.6470090309026676e-06, "loss": 0.738, "step": 14044 }, { "epoch": 0.8203855140186916, "grad_norm": 1.2922917604446411, "learning_rate": 1.645969053664499e-06, "loss": 0.8234, "step": 14045 }, { "epoch": 0.8204439252336448, "grad_norm": 0.862583339214325, "learning_rate": 1.6449293754225903e-06, "loss": 0.6665, "step": 14046 }, { "epoch": 0.8205023364485982, "grad_norm": 2.718653440475464, "learning_rate": 1.6438899962141553e-06, "loss": 0.8309, "step": 14047 }, { "epoch": 0.8205607476635514, "grad_norm": 1.1737289428710938, "learning_rate": 1.6428509160763884e-06, "loss": 0.591, "step": 14048 }, { "epoch": 0.8206191588785047, "grad_norm": 1.4553941488265991, "learning_rate": 1.6418121350464856e-06, "loss": 0.6677, "step": 14049 }, { "epoch": 0.820677570093458, "grad_norm": 1.6621812582015991, "learning_rate": 1.6407736531616214e-06, "loss": 0.7928, "step": 14050 }, { "epoch": 0.8207359813084112, "grad_norm": 1.1296569108963013, "learning_rate": 1.639735470458963e-06, "loss": 0.6668, "step": 14051 }, { "epoch": 0.8207943925233645, "grad_norm": 1.2962416410446167, "learning_rate": 1.6386975869756682e-06, "loss": 0.8883, "step": 14052 }, { "epoch": 0.8208528037383177, "grad_norm": 1.6614362001419067, "learning_rate": 1.6376600027488842e-06, "loss": 0.6742, "step": 14053 }, { "epoch": 0.820911214953271, "grad_norm": 0.9442678689956665, "learning_rate": 1.6366227178157502e-06, "loss": 0.6225, "step": 14054 }, { "epoch": 0.8209696261682243, "grad_norm": 1.4123785495758057, "learning_rate": 1.6355857322133883e-06, "loss": 0.65, "step": 14055 }, { "epoch": 0.8210280373831775, "grad_norm": 1.181886076927185, "learning_rate": 1.6345490459789093e-06, "loss": 0.7847, "step": 14056 }, { "epoch": 0.8210864485981308, "grad_norm": 0.9759467840194702, "learning_rate": 1.633512659149421e-06, "loss": 0.9451, "step": 14057 }, { "epoch": 0.8211448598130842, "grad_norm": 1.1597970724105835, "learning_rate": 1.6324765717620161e-06, "loss": 0.7129, "step": 14058 }, { "epoch": 0.8212032710280374, "grad_norm": 1.058510661125183, "learning_rate": 1.6314407838537783e-06, "loss": 0.6691, "step": 14059 }, { "epoch": 0.8212616822429907, "grad_norm": 0.9615551829338074, "learning_rate": 1.6304052954617777e-06, "loss": 0.7212, "step": 14060 }, { "epoch": 0.8213200934579439, "grad_norm": 1.6424099206924438, "learning_rate": 1.6293701066230715e-06, "loss": 0.7503, "step": 14061 }, { "epoch": 0.8213785046728972, "grad_norm": 1.093017816543579, "learning_rate": 1.6283352173747148e-06, "loss": 0.8734, "step": 14062 }, { "epoch": 0.8214369158878505, "grad_norm": 1.4101992845535278, "learning_rate": 1.6273006277537428e-06, "loss": 0.6815, "step": 14063 }, { "epoch": 0.8214953271028037, "grad_norm": 0.9609736800193787, "learning_rate": 1.6262663377971899e-06, "loss": 0.622, "step": 14064 }, { "epoch": 0.821553738317757, "grad_norm": 1.1706680059432983, "learning_rate": 1.6252323475420717e-06, "loss": 0.6285, "step": 14065 }, { "epoch": 0.8216121495327103, "grad_norm": 0.9866392612457275, "learning_rate": 1.6241986570253898e-06, "loss": 0.6824, "step": 14066 }, { "epoch": 0.8216705607476635, "grad_norm": 0.9978997111320496, "learning_rate": 1.623165266284149e-06, "loss": 0.7311, "step": 14067 }, { "epoch": 0.8217289719626168, "grad_norm": 0.9444178938865662, "learning_rate": 1.6221321753553265e-06, "loss": 0.6448, "step": 14068 }, { "epoch": 0.82178738317757, "grad_norm": 1.1586416959762573, "learning_rate": 1.6210993842759059e-06, "loss": 0.7058, "step": 14069 }, { "epoch": 0.8218457943925234, "grad_norm": 1.0951714515686035, "learning_rate": 1.620066893082848e-06, "loss": 0.7874, "step": 14070 }, { "epoch": 0.8219042056074767, "grad_norm": 1.0410138368606567, "learning_rate": 1.6190347018131036e-06, "loss": 0.7, "step": 14071 }, { "epoch": 0.8219626168224299, "grad_norm": 1.0341932773590088, "learning_rate": 1.6180028105036204e-06, "loss": 0.6466, "step": 14072 }, { "epoch": 0.8220210280373832, "grad_norm": 1.5708709955215454, "learning_rate": 1.6169712191913244e-06, "loss": 0.6934, "step": 14073 }, { "epoch": 0.8220794392523364, "grad_norm": 0.8703538775444031, "learning_rate": 1.6159399279131415e-06, "loss": 0.6996, "step": 14074 }, { "epoch": 0.8221378504672897, "grad_norm": 1.4280872344970703, "learning_rate": 1.6149089367059833e-06, "loss": 0.8052, "step": 14075 }, { "epoch": 0.822196261682243, "grad_norm": 0.9416399598121643, "learning_rate": 1.6138782456067459e-06, "loss": 0.7914, "step": 14076 }, { "epoch": 0.8222546728971962, "grad_norm": 1.2667213678359985, "learning_rate": 1.6128478546523208e-06, "loss": 0.8585, "step": 14077 }, { "epoch": 0.8223130841121495, "grad_norm": 1.0970048904418945, "learning_rate": 1.6118177638795852e-06, "loss": 0.8025, "step": 14078 }, { "epoch": 0.8223714953271029, "grad_norm": 1.1712145805358887, "learning_rate": 1.610787973325405e-06, "loss": 0.7926, "step": 14079 }, { "epoch": 0.822429906542056, "grad_norm": 1.203941822052002, "learning_rate": 1.6097584830266433e-06, "loss": 0.8045, "step": 14080 }, { "epoch": 0.8224883177570094, "grad_norm": 1.504758358001709, "learning_rate": 1.6087292930201393e-06, "loss": 0.8937, "step": 14081 }, { "epoch": 0.8225467289719626, "grad_norm": 0.9323312044143677, "learning_rate": 1.6077004033427334e-06, "loss": 0.6637, "step": 14082 }, { "epoch": 0.8226051401869159, "grad_norm": 1.5728583335876465, "learning_rate": 1.6066718140312488e-06, "loss": 0.7115, "step": 14083 }, { "epoch": 0.8226635514018692, "grad_norm": 1.2262016534805298, "learning_rate": 1.6056435251224955e-06, "loss": 0.6416, "step": 14084 }, { "epoch": 0.8227219626168224, "grad_norm": 1.7711430788040161, "learning_rate": 1.60461553665328e-06, "loss": 0.7761, "step": 14085 }, { "epoch": 0.8227803738317757, "grad_norm": 1.0709879398345947, "learning_rate": 1.6035878486603951e-06, "loss": 0.7962, "step": 14086 }, { "epoch": 0.822838785046729, "grad_norm": 1.2068723440170288, "learning_rate": 1.6025604611806244e-06, "loss": 0.8802, "step": 14087 }, { "epoch": 0.8228971962616822, "grad_norm": 1.2191896438598633, "learning_rate": 1.6015333742507355e-06, "loss": 0.737, "step": 14088 }, { "epoch": 0.8229556074766355, "grad_norm": 1.2102967500686646, "learning_rate": 1.6005065879074866e-06, "loss": 0.7293, "step": 14089 }, { "epoch": 0.8230140186915887, "grad_norm": 1.1424145698547363, "learning_rate": 1.5994801021876304e-06, "loss": 0.762, "step": 14090 }, { "epoch": 0.8230724299065421, "grad_norm": 1.1434892416000366, "learning_rate": 1.5984539171279046e-06, "loss": 0.6986, "step": 14091 }, { "epoch": 0.8231308411214954, "grad_norm": 1.0249309539794922, "learning_rate": 1.5974280327650393e-06, "loss": 0.8041, "step": 14092 }, { "epoch": 0.8231892523364486, "grad_norm": 1.083670735359192, "learning_rate": 1.59640244913575e-06, "loss": 0.7071, "step": 14093 }, { "epoch": 0.8232476635514019, "grad_norm": 0.911450982093811, "learning_rate": 1.5953771662767392e-06, "loss": 0.686, "step": 14094 }, { "epoch": 0.8233060747663551, "grad_norm": 1.1431257724761963, "learning_rate": 1.5943521842247067e-06, "loss": 0.7291, "step": 14095 }, { "epoch": 0.8233644859813084, "grad_norm": 1.5413075685501099, "learning_rate": 1.5933275030163365e-06, "loss": 1.0233, "step": 14096 }, { "epoch": 0.8234228971962617, "grad_norm": 0.9808517694473267, "learning_rate": 1.5923031226883035e-06, "loss": 0.5772, "step": 14097 }, { "epoch": 0.8234813084112149, "grad_norm": 1.1823667287826538, "learning_rate": 1.5912790432772718e-06, "loss": 0.678, "step": 14098 }, { "epoch": 0.8235397196261682, "grad_norm": 1.2217577695846558, "learning_rate": 1.5902552648198876e-06, "loss": 0.8099, "step": 14099 }, { "epoch": 0.8235981308411215, "grad_norm": 1.151654839515686, "learning_rate": 1.5892317873528006e-06, "loss": 0.7252, "step": 14100 }, { "epoch": 0.8236565420560747, "grad_norm": 1.0430563688278198, "learning_rate": 1.5882086109126337e-06, "loss": 0.7127, "step": 14101 }, { "epoch": 0.8237149532710281, "grad_norm": 1.197999358177185, "learning_rate": 1.5871857355360154e-06, "loss": 0.9861, "step": 14102 }, { "epoch": 0.8237733644859813, "grad_norm": 1.0864838361740112, "learning_rate": 1.586163161259552e-06, "loss": 0.8504, "step": 14103 }, { "epoch": 0.8238317757009346, "grad_norm": 1.1168062686920166, "learning_rate": 1.5851408881198382e-06, "loss": 0.7313, "step": 14104 }, { "epoch": 0.8238901869158879, "grad_norm": 1.6785027980804443, "learning_rate": 1.5841189161534665e-06, "loss": 0.871, "step": 14105 }, { "epoch": 0.8239485981308411, "grad_norm": 1.8328174352645874, "learning_rate": 1.5830972453970117e-06, "loss": 0.7293, "step": 14106 }, { "epoch": 0.8240070093457944, "grad_norm": 0.8234586119651794, "learning_rate": 1.582075875887039e-06, "loss": 0.6063, "step": 14107 }, { "epoch": 0.8240654205607477, "grad_norm": 0.9747673869132996, "learning_rate": 1.5810548076601096e-06, "loss": 0.731, "step": 14108 }, { "epoch": 0.8241238317757009, "grad_norm": 0.9873936772346497, "learning_rate": 1.5800340407527604e-06, "loss": 0.7003, "step": 14109 }, { "epoch": 0.8241822429906542, "grad_norm": 1.3887542486190796, "learning_rate": 1.5790135752015323e-06, "loss": 0.8537, "step": 14110 }, { "epoch": 0.8242406542056074, "grad_norm": 0.9924589991569519, "learning_rate": 1.577993411042943e-06, "loss": 0.5636, "step": 14111 }, { "epoch": 0.8242990654205608, "grad_norm": 0.9243835806846619, "learning_rate": 1.5769735483135062e-06, "loss": 0.6469, "step": 14112 }, { "epoch": 0.8243574766355141, "grad_norm": 1.1296967267990112, "learning_rate": 1.5759539870497275e-06, "loss": 0.6973, "step": 14113 }, { "epoch": 0.8244158878504673, "grad_norm": 1.1806765794754028, "learning_rate": 1.5749347272880922e-06, "loss": 0.8355, "step": 14114 }, { "epoch": 0.8244742990654206, "grad_norm": 1.1151833534240723, "learning_rate": 1.5739157690650852e-06, "loss": 0.713, "step": 14115 }, { "epoch": 0.8245327102803738, "grad_norm": 1.3907432556152344, "learning_rate": 1.57289711241717e-06, "loss": 1.0062, "step": 14116 }, { "epoch": 0.8245911214953271, "grad_norm": 1.2650889158248901, "learning_rate": 1.5718787573808104e-06, "loss": 0.751, "step": 14117 }, { "epoch": 0.8246495327102804, "grad_norm": 0.8537628650665283, "learning_rate": 1.5708607039924496e-06, "loss": 0.7281, "step": 14118 }, { "epoch": 0.8247079439252336, "grad_norm": 1.194132685661316, "learning_rate": 1.5698429522885273e-06, "loss": 0.8206, "step": 14119 }, { "epoch": 0.8247663551401869, "grad_norm": 1.2269389629364014, "learning_rate": 1.5688255023054698e-06, "loss": 0.7186, "step": 14120 }, { "epoch": 0.8248247663551402, "grad_norm": 1.0773619413375854, "learning_rate": 1.5678083540796896e-06, "loss": 0.7513, "step": 14121 }, { "epoch": 0.8248831775700934, "grad_norm": 1.5881727933883667, "learning_rate": 1.5667915076475937e-06, "loss": 0.6312, "step": 14122 }, { "epoch": 0.8249415887850468, "grad_norm": 2.818993091583252, "learning_rate": 1.5657749630455742e-06, "loss": 0.8158, "step": 14123 }, { "epoch": 0.825, "grad_norm": 1.003642201423645, "learning_rate": 1.5647587203100134e-06, "loss": 0.6436, "step": 14124 }, { "epoch": 0.8250584112149533, "grad_norm": 1.246327519416809, "learning_rate": 1.5637427794772864e-06, "loss": 0.8201, "step": 14125 }, { "epoch": 0.8251168224299066, "grad_norm": 1.3047823905944824, "learning_rate": 1.5627271405837508e-06, "loss": 0.8765, "step": 14126 }, { "epoch": 0.8251752336448598, "grad_norm": 1.071174144744873, "learning_rate": 1.5617118036657598e-06, "loss": 0.7148, "step": 14127 }, { "epoch": 0.8252336448598131, "grad_norm": 1.0413172245025635, "learning_rate": 1.5606967687596497e-06, "loss": 0.727, "step": 14128 }, { "epoch": 0.8252920560747663, "grad_norm": 1.3297836780548096, "learning_rate": 1.5596820359017507e-06, "loss": 0.8426, "step": 14129 }, { "epoch": 0.8253504672897196, "grad_norm": 17.279430389404297, "learning_rate": 1.5586676051283845e-06, "loss": 0.9762, "step": 14130 }, { "epoch": 0.8254088785046729, "grad_norm": 0.9491896033287048, "learning_rate": 1.5576534764758522e-06, "loss": 0.6489, "step": 14131 }, { "epoch": 0.8254672897196261, "grad_norm": 0.9637270569801331, "learning_rate": 1.5566396499804559e-06, "loss": 0.8549, "step": 14132 }, { "epoch": 0.8255257009345794, "grad_norm": 1.2792332172393799, "learning_rate": 1.5556261256784776e-06, "loss": 0.8056, "step": 14133 }, { "epoch": 0.8255841121495328, "grad_norm": 2.195019006729126, "learning_rate": 1.5546129036061874e-06, "loss": 0.7389, "step": 14134 }, { "epoch": 0.825642523364486, "grad_norm": 1.2705461978912354, "learning_rate": 1.5535999837998594e-06, "loss": 0.7021, "step": 14135 }, { "epoch": 0.8257009345794393, "grad_norm": 1.448197603225708, "learning_rate": 1.5525873662957414e-06, "loss": 0.7569, "step": 14136 }, { "epoch": 0.8257593457943925, "grad_norm": 1.411916971206665, "learning_rate": 1.5515750511300743e-06, "loss": 0.7926, "step": 14137 }, { "epoch": 0.8258177570093458, "grad_norm": 1.1689949035644531, "learning_rate": 1.5505630383390925e-06, "loss": 0.7547, "step": 14138 }, { "epoch": 0.8258761682242991, "grad_norm": 1.0678421258926392, "learning_rate": 1.5495513279590136e-06, "loss": 0.67, "step": 14139 }, { "epoch": 0.8259345794392523, "grad_norm": 1.2988953590393066, "learning_rate": 1.5485399200260486e-06, "loss": 0.7087, "step": 14140 }, { "epoch": 0.8259929906542056, "grad_norm": 1.9658926725387573, "learning_rate": 1.5475288145763989e-06, "loss": 0.8716, "step": 14141 }, { "epoch": 0.8260514018691589, "grad_norm": 1.3440465927124023, "learning_rate": 1.5465180116462486e-06, "loss": 0.8817, "step": 14142 }, { "epoch": 0.8261098130841121, "grad_norm": 1.725529670715332, "learning_rate": 1.5455075112717789e-06, "loss": 0.9314, "step": 14143 }, { "epoch": 0.8261682242990654, "grad_norm": 1.4682583808898926, "learning_rate": 1.5444973134891517e-06, "loss": 0.8219, "step": 14144 }, { "epoch": 0.8262266355140186, "grad_norm": 1.1662249565124512, "learning_rate": 1.5434874183345262e-06, "loss": 0.807, "step": 14145 }, { "epoch": 0.826285046728972, "grad_norm": 1.207795262336731, "learning_rate": 1.5424778258440476e-06, "loss": 0.6544, "step": 14146 }, { "epoch": 0.8263434579439253, "grad_norm": 1.247056484222412, "learning_rate": 1.5414685360538473e-06, "loss": 0.8403, "step": 14147 }, { "epoch": 0.8264018691588785, "grad_norm": 1.048954963684082, "learning_rate": 1.5404595490000506e-06, "loss": 0.7169, "step": 14148 }, { "epoch": 0.8264602803738318, "grad_norm": 1.3277907371520996, "learning_rate": 1.539450864718768e-06, "loss": 0.7121, "step": 14149 }, { "epoch": 0.826518691588785, "grad_norm": 1.219723105430603, "learning_rate": 1.538442483246103e-06, "loss": 0.8195, "step": 14150 }, { "epoch": 0.8265771028037383, "grad_norm": 1.006218671798706, "learning_rate": 1.5374344046181432e-06, "loss": 0.5655, "step": 14151 }, { "epoch": 0.8266355140186916, "grad_norm": 1.5789499282836914, "learning_rate": 1.5364266288709706e-06, "loss": 0.8018, "step": 14152 }, { "epoch": 0.8266939252336448, "grad_norm": 1.454005241394043, "learning_rate": 1.535419156040656e-06, "loss": 0.732, "step": 14153 }, { "epoch": 0.8267523364485981, "grad_norm": 1.0581467151641846, "learning_rate": 1.5344119861632535e-06, "loss": 0.6423, "step": 14154 }, { "epoch": 0.8268107476635514, "grad_norm": 1.1202658414840698, "learning_rate": 1.5334051192748146e-06, "loss": 0.698, "step": 14155 }, { "epoch": 0.8268691588785047, "grad_norm": 1.1048582792282104, "learning_rate": 1.5323985554113697e-06, "loss": 0.7604, "step": 14156 }, { "epoch": 0.826927570093458, "grad_norm": 1.0735681056976318, "learning_rate": 1.5313922946089488e-06, "loss": 0.7126, "step": 14157 }, { "epoch": 0.8269859813084112, "grad_norm": 3.971015691757202, "learning_rate": 1.5303863369035688e-06, "loss": 0.785, "step": 14158 }, { "epoch": 0.8270443925233645, "grad_norm": 1.1752101182937622, "learning_rate": 1.5293806823312286e-06, "loss": 0.7264, "step": 14159 }, { "epoch": 0.8271028037383178, "grad_norm": 1.5176807641983032, "learning_rate": 1.5283753309279247e-06, "loss": 0.8213, "step": 14160 }, { "epoch": 0.827161214953271, "grad_norm": 0.9962044954299927, "learning_rate": 1.5273702827296354e-06, "loss": 0.7607, "step": 14161 }, { "epoch": 0.8272196261682243, "grad_norm": 1.046628713607788, "learning_rate": 1.5263655377723352e-06, "loss": 0.7547, "step": 14162 }, { "epoch": 0.8272780373831776, "grad_norm": 1.1498887538909912, "learning_rate": 1.5253610960919862e-06, "loss": 0.6233, "step": 14163 }, { "epoch": 0.8273364485981308, "grad_norm": 1.642416000366211, "learning_rate": 1.5243569577245331e-06, "loss": 0.9406, "step": 14164 }, { "epoch": 0.8273948598130841, "grad_norm": 1.3104764223098755, "learning_rate": 1.5233531227059195e-06, "loss": 0.7665, "step": 14165 }, { "epoch": 0.8274532710280373, "grad_norm": 1.1489249467849731, "learning_rate": 1.522349591072072e-06, "loss": 0.697, "step": 14166 }, { "epoch": 0.8275116822429907, "grad_norm": 1.1072224378585815, "learning_rate": 1.521346362858901e-06, "loss": 0.7787, "step": 14167 }, { "epoch": 0.827570093457944, "grad_norm": 1.1911228895187378, "learning_rate": 1.520343438102324e-06, "loss": 0.6067, "step": 14168 }, { "epoch": 0.8276285046728972, "grad_norm": 0.9490381479263306, "learning_rate": 1.5193408168382285e-06, "loss": 0.7794, "step": 14169 }, { "epoch": 0.8276869158878505, "grad_norm": 1.3366717100143433, "learning_rate": 1.518338499102503e-06, "loss": 0.6884, "step": 14170 }, { "epoch": 0.8277453271028037, "grad_norm": 1.904003381729126, "learning_rate": 1.5173364849310201e-06, "loss": 0.8025, "step": 14171 }, { "epoch": 0.827803738317757, "grad_norm": 0.9642291069030762, "learning_rate": 1.516334774359639e-06, "loss": 0.706, "step": 14172 }, { "epoch": 0.8278621495327103, "grad_norm": 1.0205484628677368, "learning_rate": 1.5153333674242154e-06, "loss": 0.7433, "step": 14173 }, { "epoch": 0.8279205607476635, "grad_norm": 1.0858275890350342, "learning_rate": 1.5143322641605883e-06, "loss": 0.7447, "step": 14174 }, { "epoch": 0.8279789719626168, "grad_norm": 1.0192084312438965, "learning_rate": 1.5133314646045916e-06, "loss": 0.6606, "step": 14175 }, { "epoch": 0.8280373831775701, "grad_norm": 1.3223294019699097, "learning_rate": 1.5123309687920417e-06, "loss": 0.8559, "step": 14176 }, { "epoch": 0.8280957943925233, "grad_norm": 1.6155503988265991, "learning_rate": 1.5113307767587449e-06, "loss": 0.8514, "step": 14177 }, { "epoch": 0.8281542056074767, "grad_norm": 1.0404914617538452, "learning_rate": 1.510330888540501e-06, "loss": 0.7854, "step": 14178 }, { "epoch": 0.8282126168224299, "grad_norm": 1.4614839553833008, "learning_rate": 1.5093313041730973e-06, "loss": 0.8212, "step": 14179 }, { "epoch": 0.8282710280373832, "grad_norm": 1.1982707977294922, "learning_rate": 1.5083320236923106e-06, "loss": 0.6672, "step": 14180 }, { "epoch": 0.8283294392523365, "grad_norm": 1.9532018899917603, "learning_rate": 1.5073330471339043e-06, "loss": 0.9678, "step": 14181 }, { "epoch": 0.8283878504672897, "grad_norm": 1.1422821283340454, "learning_rate": 1.5063343745336302e-06, "loss": 0.8215, "step": 14182 }, { "epoch": 0.828446261682243, "grad_norm": 1.1316787004470825, "learning_rate": 1.505336005927236e-06, "loss": 0.7971, "step": 14183 }, { "epoch": 0.8285046728971963, "grad_norm": 2.217010974884033, "learning_rate": 1.5043379413504466e-06, "loss": 0.8568, "step": 14184 }, { "epoch": 0.8285630841121495, "grad_norm": 1.9326077699661255, "learning_rate": 1.5033401808389924e-06, "loss": 0.8072, "step": 14185 }, { "epoch": 0.8286214953271028, "grad_norm": 1.2511951923370361, "learning_rate": 1.5023427244285804e-06, "loss": 0.6885, "step": 14186 }, { "epoch": 0.828679906542056, "grad_norm": 1.2923921346664429, "learning_rate": 1.5013455721549063e-06, "loss": 0.8235, "step": 14187 }, { "epoch": 0.8287383177570093, "grad_norm": 0.9243832230567932, "learning_rate": 1.5003487240536663e-06, "loss": 0.6682, "step": 14188 }, { "epoch": 0.8287967289719627, "grad_norm": 1.4409325122833252, "learning_rate": 1.4993521801605305e-06, "loss": 0.8451, "step": 14189 }, { "epoch": 0.8288551401869159, "grad_norm": 1.0110007524490356, "learning_rate": 1.498355940511169e-06, "loss": 0.8785, "step": 14190 }, { "epoch": 0.8289135514018692, "grad_norm": 0.9305717945098877, "learning_rate": 1.4973600051412418e-06, "loss": 0.7777, "step": 14191 }, { "epoch": 0.8289719626168224, "grad_norm": 0.9120109677314758, "learning_rate": 1.4963643740863875e-06, "loss": 0.6713, "step": 14192 }, { "epoch": 0.8290303738317757, "grad_norm": 1.2925329208374023, "learning_rate": 1.4953690473822469e-06, "loss": 0.7721, "step": 14193 }, { "epoch": 0.829088785046729, "grad_norm": 1.3783718347549438, "learning_rate": 1.4943740250644367e-06, "loss": 0.5999, "step": 14194 }, { "epoch": 0.8291471962616822, "grad_norm": 1.2947919368743896, "learning_rate": 1.493379307168573e-06, "loss": 0.9083, "step": 14195 }, { "epoch": 0.8292056074766355, "grad_norm": 1.0921740531921387, "learning_rate": 1.4923848937302587e-06, "loss": 0.813, "step": 14196 }, { "epoch": 0.8292640186915888, "grad_norm": 1.152113914489746, "learning_rate": 1.4913907847850816e-06, "loss": 0.73, "step": 14197 }, { "epoch": 0.829322429906542, "grad_norm": 0.7353931665420532, "learning_rate": 1.4903969803686247e-06, "loss": 0.4977, "step": 14198 }, { "epoch": 0.8293808411214953, "grad_norm": 1.2516835927963257, "learning_rate": 1.4894034805164548e-06, "loss": 0.7582, "step": 14199 }, { "epoch": 0.8294392523364486, "grad_norm": 1.1512138843536377, "learning_rate": 1.4884102852641258e-06, "loss": 0.84, "step": 14200 }, { "epoch": 0.8294976635514019, "grad_norm": 1.116963505744934, "learning_rate": 1.4874173946471947e-06, "loss": 0.7296, "step": 14201 }, { "epoch": 0.8295560747663552, "grad_norm": 1.3927912712097168, "learning_rate": 1.486424808701189e-06, "loss": 0.793, "step": 14202 }, { "epoch": 0.8296144859813084, "grad_norm": 1.073306679725647, "learning_rate": 1.4854325274616388e-06, "loss": 0.6504, "step": 14203 }, { "epoch": 0.8296728971962617, "grad_norm": 1.1353497505187988, "learning_rate": 1.484440550964058e-06, "loss": 0.5864, "step": 14204 }, { "epoch": 0.829731308411215, "grad_norm": 1.155827522277832, "learning_rate": 1.4834488792439461e-06, "loss": 0.6115, "step": 14205 }, { "epoch": 0.8297897196261682, "grad_norm": 1.3705356121063232, "learning_rate": 1.482457512336799e-06, "loss": 0.8499, "step": 14206 }, { "epoch": 0.8298481308411215, "grad_norm": 0.9695997834205627, "learning_rate": 1.4814664502780974e-06, "loss": 0.6833, "step": 14207 }, { "epoch": 0.8299065420560747, "grad_norm": 1.2233829498291016, "learning_rate": 1.4804756931033148e-06, "loss": 0.7695, "step": 14208 }, { "epoch": 0.829964953271028, "grad_norm": 1.6776760816574097, "learning_rate": 1.4794852408479099e-06, "loss": 0.7157, "step": 14209 }, { "epoch": 0.8300233644859814, "grad_norm": 1.0065133571624756, "learning_rate": 1.4784950935473275e-06, "loss": 0.8328, "step": 14210 }, { "epoch": 0.8300817757009346, "grad_norm": 1.2689955234527588, "learning_rate": 1.477505251237008e-06, "loss": 0.7522, "step": 14211 }, { "epoch": 0.8301401869158879, "grad_norm": 1.3576900959014893, "learning_rate": 1.47651571395238e-06, "loss": 0.7197, "step": 14212 }, { "epoch": 0.8301985981308411, "grad_norm": 1.16611647605896, "learning_rate": 1.4755264817288616e-06, "loss": 0.8698, "step": 14213 }, { "epoch": 0.8302570093457944, "grad_norm": 1.514357089996338, "learning_rate": 1.4745375546018547e-06, "loss": 0.7727, "step": 14214 }, { "epoch": 0.8303154205607477, "grad_norm": 1.3676241636276245, "learning_rate": 1.4735489326067532e-06, "loss": 0.7056, "step": 14215 }, { "epoch": 0.8303738317757009, "grad_norm": 1.083673357963562, "learning_rate": 1.472560615778943e-06, "loss": 0.6996, "step": 14216 }, { "epoch": 0.8304322429906542, "grad_norm": 1.0191388130187988, "learning_rate": 1.4715726041537902e-06, "loss": 0.7378, "step": 14217 }, { "epoch": 0.8304906542056075, "grad_norm": 1.3147330284118652, "learning_rate": 1.470584897766666e-06, "loss": 0.8122, "step": 14218 }, { "epoch": 0.8305490654205607, "grad_norm": 1.2813332080841064, "learning_rate": 1.469597496652917e-06, "loss": 0.9011, "step": 14219 }, { "epoch": 0.830607476635514, "grad_norm": 1.091353178024292, "learning_rate": 1.4686104008478807e-06, "loss": 0.807, "step": 14220 }, { "epoch": 0.8306658878504672, "grad_norm": 1.0602880716323853, "learning_rate": 1.467623610386889e-06, "loss": 0.6707, "step": 14221 }, { "epoch": 0.8307242990654206, "grad_norm": 1.2861124277114868, "learning_rate": 1.4666371253052569e-06, "loss": 0.8328, "step": 14222 }, { "epoch": 0.8307827102803739, "grad_norm": 1.31857168674469, "learning_rate": 1.4656509456382927e-06, "loss": 0.7123, "step": 14223 }, { "epoch": 0.8308411214953271, "grad_norm": 1.1641314029693604, "learning_rate": 1.464665071421294e-06, "loss": 0.7794, "step": 14224 }, { "epoch": 0.8308995327102804, "grad_norm": 0.973425567150116, "learning_rate": 1.4636795026895433e-06, "loss": 0.7188, "step": 14225 }, { "epoch": 0.8309579439252337, "grad_norm": 1.1276509761810303, "learning_rate": 1.4626942394783184e-06, "loss": 0.8645, "step": 14226 }, { "epoch": 0.8310163551401869, "grad_norm": 1.1000492572784424, "learning_rate": 1.4617092818228762e-06, "loss": 0.6627, "step": 14227 }, { "epoch": 0.8310747663551402, "grad_norm": 0.9856029748916626, "learning_rate": 1.4607246297584743e-06, "loss": 0.6083, "step": 14228 }, { "epoch": 0.8311331775700934, "grad_norm": 1.0806422233581543, "learning_rate": 1.4597402833203545e-06, "loss": 0.7725, "step": 14229 }, { "epoch": 0.8311915887850467, "grad_norm": 0.9530561566352844, "learning_rate": 1.4587562425437428e-06, "loss": 0.6388, "step": 14230 }, { "epoch": 0.83125, "grad_norm": 1.1208159923553467, "learning_rate": 1.4577725074638638e-06, "loss": 0.7476, "step": 14231 }, { "epoch": 0.8313084112149532, "grad_norm": 0.9901167750358582, "learning_rate": 1.456789078115921e-06, "loss": 0.8377, "step": 14232 }, { "epoch": 0.8313668224299066, "grad_norm": 1.3896511793136597, "learning_rate": 1.4558059545351144e-06, "loss": 0.6197, "step": 14233 }, { "epoch": 0.8314252336448598, "grad_norm": 0.8676019906997681, "learning_rate": 1.4548231367566324e-06, "loss": 0.7506, "step": 14234 }, { "epoch": 0.8314836448598131, "grad_norm": 1.0760310888290405, "learning_rate": 1.4538406248156467e-06, "loss": 0.8804, "step": 14235 }, { "epoch": 0.8315420560747664, "grad_norm": 1.0562694072723389, "learning_rate": 1.452858418747327e-06, "loss": 0.6953, "step": 14236 }, { "epoch": 0.8316004672897196, "grad_norm": 1.0941718816757202, "learning_rate": 1.451876518586821e-06, "loss": 0.751, "step": 14237 }, { "epoch": 0.8316588785046729, "grad_norm": 1.0483148097991943, "learning_rate": 1.4508949243692782e-06, "loss": 0.7007, "step": 14238 }, { "epoch": 0.8317172897196262, "grad_norm": 0.908248782157898, "learning_rate": 1.449913636129825e-06, "loss": 0.5504, "step": 14239 }, { "epoch": 0.8317757009345794, "grad_norm": 1.0362331867218018, "learning_rate": 1.4489326539035842e-06, "loss": 0.7345, "step": 14240 }, { "epoch": 0.8318341121495327, "grad_norm": 1.2157509326934814, "learning_rate": 1.447951977725669e-06, "loss": 0.8227, "step": 14241 }, { "epoch": 0.8318925233644859, "grad_norm": 0.9527712464332581, "learning_rate": 1.4469716076311724e-06, "loss": 0.6441, "step": 14242 }, { "epoch": 0.8319509345794392, "grad_norm": 1.1607921123504639, "learning_rate": 1.4459915436551886e-06, "loss": 0.9428, "step": 14243 }, { "epoch": 0.8320093457943926, "grad_norm": 1.667173981666565, "learning_rate": 1.4450117858327895e-06, "loss": 0.8508, "step": 14244 }, { "epoch": 0.8320677570093458, "grad_norm": 1.2752327919006348, "learning_rate": 1.4440323341990437e-06, "loss": 0.7212, "step": 14245 }, { "epoch": 0.8321261682242991, "grad_norm": 1.3901841640472412, "learning_rate": 1.4430531887890076e-06, "loss": 0.7212, "step": 14246 }, { "epoch": 0.8321845794392523, "grad_norm": 1.1703120470046997, "learning_rate": 1.4420743496377232e-06, "loss": 0.8954, "step": 14247 }, { "epoch": 0.8322429906542056, "grad_norm": 1.065352201461792, "learning_rate": 1.4410958167802259e-06, "loss": 0.7491, "step": 14248 }, { "epoch": 0.8323014018691589, "grad_norm": 1.1712603569030762, "learning_rate": 1.4401175902515375e-06, "loss": 0.8732, "step": 14249 }, { "epoch": 0.8323598130841121, "grad_norm": 2.563704252243042, "learning_rate": 1.4391396700866644e-06, "loss": 0.7226, "step": 14250 }, { "epoch": 0.8324182242990654, "grad_norm": 1.1444971561431885, "learning_rate": 1.4381620563206156e-06, "loss": 0.767, "step": 14251 }, { "epoch": 0.8324766355140187, "grad_norm": 1.013951063156128, "learning_rate": 1.4371847489883762e-06, "loss": 0.6077, "step": 14252 }, { "epoch": 0.8325350467289719, "grad_norm": 0.9900752305984497, "learning_rate": 1.4362077481249237e-06, "loss": 0.6975, "step": 14253 }, { "epoch": 0.8325934579439253, "grad_norm": 1.1321076154708862, "learning_rate": 1.4352310537652281e-06, "loss": 0.9483, "step": 14254 }, { "epoch": 0.8326518691588785, "grad_norm": 0.8609340190887451, "learning_rate": 1.4342546659442414e-06, "loss": 0.7056, "step": 14255 }, { "epoch": 0.8327102803738318, "grad_norm": 1.0937576293945312, "learning_rate": 1.4332785846969132e-06, "loss": 0.798, "step": 14256 }, { "epoch": 0.8327686915887851, "grad_norm": 1.017501711845398, "learning_rate": 1.4323028100581794e-06, "loss": 0.7401, "step": 14257 }, { "epoch": 0.8328271028037383, "grad_norm": 1.1689095497131348, "learning_rate": 1.4313273420629592e-06, "loss": 0.8457, "step": 14258 }, { "epoch": 0.8328855140186916, "grad_norm": 1.1830384731292725, "learning_rate": 1.4303521807461696e-06, "loss": 0.7032, "step": 14259 }, { "epoch": 0.8329439252336449, "grad_norm": 1.095355749130249, "learning_rate": 1.429377326142708e-06, "loss": 0.7343, "step": 14260 }, { "epoch": 0.8330023364485981, "grad_norm": 0.9563770294189453, "learning_rate": 1.4284027782874665e-06, "loss": 0.6836, "step": 14261 }, { "epoch": 0.8330607476635514, "grad_norm": 0.9092307090759277, "learning_rate": 1.4274285372153284e-06, "loss": 0.7931, "step": 14262 }, { "epoch": 0.8331191588785046, "grad_norm": 0.9152425527572632, "learning_rate": 1.426454602961157e-06, "loss": 0.7252, "step": 14263 }, { "epoch": 0.8331775700934579, "grad_norm": 1.1656626462936401, "learning_rate": 1.4254809755598154e-06, "loss": 0.748, "step": 14264 }, { "epoch": 0.8332359813084113, "grad_norm": 1.0547508001327515, "learning_rate": 1.4245076550461445e-06, "loss": 0.6869, "step": 14265 }, { "epoch": 0.8332943925233645, "grad_norm": 0.9574003219604492, "learning_rate": 1.4235346414549833e-06, "loss": 0.6415, "step": 14266 }, { "epoch": 0.8333528037383178, "grad_norm": 1.0310174226760864, "learning_rate": 1.4225619348211594e-06, "loss": 0.7513, "step": 14267 }, { "epoch": 0.833411214953271, "grad_norm": 0.9189668893814087, "learning_rate": 1.4215895351794807e-06, "loss": 0.723, "step": 14268 }, { "epoch": 0.8334696261682243, "grad_norm": 1.1458991765975952, "learning_rate": 1.4206174425647556e-06, "loss": 0.9475, "step": 14269 }, { "epoch": 0.8335280373831776, "grad_norm": 0.9484947919845581, "learning_rate": 1.419645657011771e-06, "loss": 0.6234, "step": 14270 }, { "epoch": 0.8335864485981308, "grad_norm": 1.1480687856674194, "learning_rate": 1.4186741785553116e-06, "loss": 0.7467, "step": 14271 }, { "epoch": 0.8336448598130841, "grad_norm": 1.2792528867721558, "learning_rate": 1.4177030072301446e-06, "loss": 0.7252, "step": 14272 }, { "epoch": 0.8337032710280374, "grad_norm": 1.0006297826766968, "learning_rate": 1.416732143071029e-06, "loss": 0.7396, "step": 14273 }, { "epoch": 0.8337616822429906, "grad_norm": 1.3002198934555054, "learning_rate": 1.415761586112716e-06, "loss": 0.7447, "step": 14274 }, { "epoch": 0.833820093457944, "grad_norm": 0.8093899488449097, "learning_rate": 1.4147913363899379e-06, "loss": 0.6711, "step": 14275 }, { "epoch": 0.8338785046728971, "grad_norm": 1.4396246671676636, "learning_rate": 1.4138213939374246e-06, "loss": 0.9212, "step": 14276 }, { "epoch": 0.8339369158878505, "grad_norm": 1.016757845878601, "learning_rate": 1.4128517587898872e-06, "loss": 0.6991, "step": 14277 }, { "epoch": 0.8339953271028038, "grad_norm": 0.9738282561302185, "learning_rate": 1.4118824309820322e-06, "loss": 0.626, "step": 14278 }, { "epoch": 0.834053738317757, "grad_norm": 1.0298212766647339, "learning_rate": 1.4109134105485534e-06, "loss": 0.6711, "step": 14279 }, { "epoch": 0.8341121495327103, "grad_norm": 1.071266531944275, "learning_rate": 1.4099446975241282e-06, "loss": 0.7865, "step": 14280 }, { "epoch": 0.8341705607476636, "grad_norm": 1.1366623640060425, "learning_rate": 1.4089762919434336e-06, "loss": 0.7073, "step": 14281 }, { "epoch": 0.8342289719626168, "grad_norm": 1.3588886260986328, "learning_rate": 1.408008193841126e-06, "loss": 0.8991, "step": 14282 }, { "epoch": 0.8342873831775701, "grad_norm": 1.0989489555358887, "learning_rate": 1.4070404032518491e-06, "loss": 0.6414, "step": 14283 }, { "epoch": 0.8343457943925233, "grad_norm": 1.009063959121704, "learning_rate": 1.4060729202102518e-06, "loss": 0.6785, "step": 14284 }, { "epoch": 0.8344042056074766, "grad_norm": 1.1557083129882812, "learning_rate": 1.4051057447509531e-06, "loss": 0.7481, "step": 14285 }, { "epoch": 0.83446261682243, "grad_norm": 1.0650469064712524, "learning_rate": 1.4041388769085729e-06, "loss": 0.6699, "step": 14286 }, { "epoch": 0.8345210280373832, "grad_norm": 1.1999027729034424, "learning_rate": 1.4031723167177136e-06, "loss": 0.8714, "step": 14287 }, { "epoch": 0.8345794392523365, "grad_norm": 0.8998681902885437, "learning_rate": 1.4022060642129687e-06, "loss": 0.6253, "step": 14288 }, { "epoch": 0.8346378504672897, "grad_norm": 1.29434335231781, "learning_rate": 1.4012401194289205e-06, "loss": 0.7655, "step": 14289 }, { "epoch": 0.834696261682243, "grad_norm": 1.7121660709381104, "learning_rate": 1.4002744824001436e-06, "loss": 0.6965, "step": 14290 }, { "epoch": 0.8347546728971963, "grad_norm": 1.2743324041366577, "learning_rate": 1.399309153161198e-06, "loss": 0.7632, "step": 14291 }, { "epoch": 0.8348130841121495, "grad_norm": 1.0710989236831665, "learning_rate": 1.398344131746634e-06, "loss": 0.7482, "step": 14292 }, { "epoch": 0.8348714953271028, "grad_norm": 0.9950528144836426, "learning_rate": 1.3973794181909871e-06, "loss": 0.8058, "step": 14293 }, { "epoch": 0.8349299065420561, "grad_norm": 1.0759893655776978, "learning_rate": 1.3964150125287867e-06, "loss": 0.7351, "step": 14294 }, { "epoch": 0.8349883177570093, "grad_norm": 1.3995474576950073, "learning_rate": 1.3954509147945494e-06, "loss": 0.7216, "step": 14295 }, { "epoch": 0.8350467289719626, "grad_norm": 0.8345171809196472, "learning_rate": 1.3944871250227853e-06, "loss": 0.6994, "step": 14296 }, { "epoch": 0.8351051401869158, "grad_norm": 0.9902068972587585, "learning_rate": 1.3935236432479837e-06, "loss": 0.5674, "step": 14297 }, { "epoch": 0.8351635514018692, "grad_norm": 2.7374582290649414, "learning_rate": 1.392560469504628e-06, "loss": 0.9576, "step": 14298 }, { "epoch": 0.8352219626168225, "grad_norm": 1.059504747390747, "learning_rate": 1.3915976038271927e-06, "loss": 0.7416, "step": 14299 }, { "epoch": 0.8352803738317757, "grad_norm": 1.10109543800354, "learning_rate": 1.3906350462501394e-06, "loss": 0.7543, "step": 14300 }, { "epoch": 0.835338785046729, "grad_norm": 1.0371122360229492, "learning_rate": 1.3896727968079216e-06, "loss": 0.7608, "step": 14301 }, { "epoch": 0.8353971962616823, "grad_norm": 1.1635510921478271, "learning_rate": 1.3887108555349748e-06, "loss": 0.8674, "step": 14302 }, { "epoch": 0.8354556074766355, "grad_norm": 0.9805271625518799, "learning_rate": 1.3877492224657264e-06, "loss": 0.845, "step": 14303 }, { "epoch": 0.8355140186915888, "grad_norm": 1.0620030164718628, "learning_rate": 1.3867878976345984e-06, "loss": 0.6647, "step": 14304 }, { "epoch": 0.835572429906542, "grad_norm": 1.342120885848999, "learning_rate": 1.3858268810759923e-06, "loss": 0.6967, "step": 14305 }, { "epoch": 0.8356308411214953, "grad_norm": 1.5845355987548828, "learning_rate": 1.3848661728243062e-06, "loss": 0.7724, "step": 14306 }, { "epoch": 0.8356892523364486, "grad_norm": 1.2127898931503296, "learning_rate": 1.383905772913926e-06, "loss": 0.6272, "step": 14307 }, { "epoch": 0.8357476635514018, "grad_norm": 0.8446322679519653, "learning_rate": 1.3829456813792219e-06, "loss": 0.5572, "step": 14308 }, { "epoch": 0.8358060747663552, "grad_norm": 1.7120625972747803, "learning_rate": 1.3819858982545598e-06, "loss": 0.7546, "step": 14309 }, { "epoch": 0.8358644859813084, "grad_norm": 1.2556698322296143, "learning_rate": 1.3810264235742865e-06, "loss": 0.6124, "step": 14310 }, { "epoch": 0.8359228971962617, "grad_norm": 1.296450138092041, "learning_rate": 1.3800672573727447e-06, "loss": 0.7246, "step": 14311 }, { "epoch": 0.835981308411215, "grad_norm": 1.3704776763916016, "learning_rate": 1.3791083996842658e-06, "loss": 0.7228, "step": 14312 }, { "epoch": 0.8360397196261682, "grad_norm": 1.1227394342422485, "learning_rate": 1.3781498505431635e-06, "loss": 0.6384, "step": 14313 }, { "epoch": 0.8360981308411215, "grad_norm": 1.1850614547729492, "learning_rate": 1.377191609983749e-06, "loss": 0.6652, "step": 14314 }, { "epoch": 0.8361565420560748, "grad_norm": 1.000495195388794, "learning_rate": 1.3762336780403163e-06, "loss": 0.724, "step": 14315 }, { "epoch": 0.836214953271028, "grad_norm": 1.3134392499923706, "learning_rate": 1.3752760547471455e-06, "loss": 0.986, "step": 14316 }, { "epoch": 0.8362733644859813, "grad_norm": 1.4473521709442139, "learning_rate": 1.3743187401385205e-06, "loss": 0.9106, "step": 14317 }, { "epoch": 0.8363317757009345, "grad_norm": 1.3189433813095093, "learning_rate": 1.373361734248697e-06, "loss": 0.8478, "step": 14318 }, { "epoch": 0.8363901869158878, "grad_norm": 0.9985069632530212, "learning_rate": 1.3724050371119324e-06, "loss": 0.593, "step": 14319 }, { "epoch": 0.8364485981308412, "grad_norm": 0.8609564304351807, "learning_rate": 1.3714486487624635e-06, "loss": 0.7975, "step": 14320 }, { "epoch": 0.8365070093457944, "grad_norm": 1.2522605657577515, "learning_rate": 1.3704925692345183e-06, "loss": 0.6252, "step": 14321 }, { "epoch": 0.8365654205607477, "grad_norm": 1.384591817855835, "learning_rate": 1.3695367985623188e-06, "loss": 0.805, "step": 14322 }, { "epoch": 0.836623831775701, "grad_norm": 1.165695309638977, "learning_rate": 1.3685813367800716e-06, "loss": 0.7844, "step": 14323 }, { "epoch": 0.8366822429906542, "grad_norm": 1.1194887161254883, "learning_rate": 1.367626183921975e-06, "loss": 0.7543, "step": 14324 }, { "epoch": 0.8367406542056075, "grad_norm": 0.9913620948791504, "learning_rate": 1.3666713400222143e-06, "loss": 0.7194, "step": 14325 }, { "epoch": 0.8367990654205607, "grad_norm": 1.4752466678619385, "learning_rate": 1.3657168051149606e-06, "loss": 0.8262, "step": 14326 }, { "epoch": 0.836857476635514, "grad_norm": 1.0892301797866821, "learning_rate": 1.3647625792343788e-06, "loss": 0.655, "step": 14327 }, { "epoch": 0.8369158878504673, "grad_norm": 1.275684118270874, "learning_rate": 1.3638086624146218e-06, "loss": 0.78, "step": 14328 }, { "epoch": 0.8369742990654205, "grad_norm": 1.197174310684204, "learning_rate": 1.3628550546898346e-06, "loss": 0.6942, "step": 14329 }, { "epoch": 0.8370327102803738, "grad_norm": 1.2325247526168823, "learning_rate": 1.361901756094144e-06, "loss": 0.6209, "step": 14330 }, { "epoch": 0.837091121495327, "grad_norm": 1.5597141981124878, "learning_rate": 1.3609487666616662e-06, "loss": 0.8349, "step": 14331 }, { "epoch": 0.8371495327102804, "grad_norm": 1.24014413356781, "learning_rate": 1.3599960864265127e-06, "loss": 0.792, "step": 14332 }, { "epoch": 0.8372079439252337, "grad_norm": 1.3150155544281006, "learning_rate": 1.3590437154227799e-06, "loss": 0.806, "step": 14333 }, { "epoch": 0.8372663551401869, "grad_norm": 1.0924588441848755, "learning_rate": 1.3580916536845569e-06, "loss": 0.6609, "step": 14334 }, { "epoch": 0.8373247663551402, "grad_norm": 1.0409669876098633, "learning_rate": 1.3571399012459152e-06, "loss": 0.5864, "step": 14335 }, { "epoch": 0.8373831775700935, "grad_norm": 1.1498342752456665, "learning_rate": 1.3561884581409167e-06, "loss": 0.9081, "step": 14336 }, { "epoch": 0.8374415887850467, "grad_norm": 1.025933027267456, "learning_rate": 1.35523732440362e-06, "loss": 0.762, "step": 14337 }, { "epoch": 0.8375, "grad_norm": 0.952614963054657, "learning_rate": 1.3542865000680604e-06, "loss": 0.5923, "step": 14338 }, { "epoch": 0.8375584112149532, "grad_norm": 1.7315754890441895, "learning_rate": 1.3533359851682714e-06, "loss": 0.9855, "step": 14339 }, { "epoch": 0.8376168224299065, "grad_norm": 1.4397916793823242, "learning_rate": 1.3523857797382755e-06, "loss": 0.7288, "step": 14340 }, { "epoch": 0.8376752336448599, "grad_norm": 0.84550541639328, "learning_rate": 1.3514358838120767e-06, "loss": 0.6462, "step": 14341 }, { "epoch": 0.837733644859813, "grad_norm": 0.9594034552574158, "learning_rate": 1.3504862974236755e-06, "loss": 0.7038, "step": 14342 }, { "epoch": 0.8377920560747664, "grad_norm": 1.4434055089950562, "learning_rate": 1.3495370206070558e-06, "loss": 0.7514, "step": 14343 }, { "epoch": 0.8378504672897197, "grad_norm": 1.8383220434188843, "learning_rate": 1.3485880533961925e-06, "loss": 0.882, "step": 14344 }, { "epoch": 0.8379088785046729, "grad_norm": 1.2167209386825562, "learning_rate": 1.3476393958250544e-06, "loss": 0.9515, "step": 14345 }, { "epoch": 0.8379672897196262, "grad_norm": 0.8489529490470886, "learning_rate": 1.3466910479275885e-06, "loss": 0.6049, "step": 14346 }, { "epoch": 0.8380257009345794, "grad_norm": 1.1720843315124512, "learning_rate": 1.3457430097377421e-06, "loss": 0.7984, "step": 14347 }, { "epoch": 0.8380841121495327, "grad_norm": 0.8464607000350952, "learning_rate": 1.3447952812894415e-06, "loss": 0.7011, "step": 14348 }, { "epoch": 0.838142523364486, "grad_norm": 1.0250039100646973, "learning_rate": 1.3438478626166096e-06, "loss": 0.788, "step": 14349 }, { "epoch": 0.8382009345794392, "grad_norm": 1.2422714233398438, "learning_rate": 1.3429007537531558e-06, "loss": 0.742, "step": 14350 }, { "epoch": 0.8382593457943925, "grad_norm": 0.9783058762550354, "learning_rate": 1.341953954732973e-06, "loss": 0.7983, "step": 14351 }, { "epoch": 0.8383177570093457, "grad_norm": 0.856881856918335, "learning_rate": 1.341007465589954e-06, "loss": 0.6025, "step": 14352 }, { "epoch": 0.8383761682242991, "grad_norm": 1.0191560983657837, "learning_rate": 1.3400612863579687e-06, "loss": 0.7821, "step": 14353 }, { "epoch": 0.8384345794392524, "grad_norm": 1.3695988655090332, "learning_rate": 1.3391154170708864e-06, "loss": 0.7121, "step": 14354 }, { "epoch": 0.8384929906542056, "grad_norm": 0.935605525970459, "learning_rate": 1.3381698577625569e-06, "loss": 0.7057, "step": 14355 }, { "epoch": 0.8385514018691589, "grad_norm": 1.2856824398040771, "learning_rate": 1.3372246084668217e-06, "loss": 0.8616, "step": 14356 }, { "epoch": 0.8386098130841122, "grad_norm": 1.2488744258880615, "learning_rate": 1.3362796692175162e-06, "loss": 0.8405, "step": 14357 }, { "epoch": 0.8386682242990654, "grad_norm": 1.1093199253082275, "learning_rate": 1.3353350400484566e-06, "loss": 0.8333, "step": 14358 }, { "epoch": 0.8387266355140187, "grad_norm": 1.2465018033981323, "learning_rate": 1.3343907209934537e-06, "loss": 0.8842, "step": 14359 }, { "epoch": 0.8387850467289719, "grad_norm": 0.95467209815979, "learning_rate": 1.3334467120863038e-06, "loss": 0.8378, "step": 14360 }, { "epoch": 0.8388434579439252, "grad_norm": 0.9516198039054871, "learning_rate": 1.332503013360794e-06, "loss": 0.7151, "step": 14361 }, { "epoch": 0.8389018691588785, "grad_norm": 1.453863263130188, "learning_rate": 1.3315596248507022e-06, "loss": 1.0618, "step": 14362 }, { "epoch": 0.8389602803738317, "grad_norm": 1.05479896068573, "learning_rate": 1.3306165465897913e-06, "loss": 0.6214, "step": 14363 }, { "epoch": 0.8390186915887851, "grad_norm": 1.1207596063613892, "learning_rate": 1.3296737786118118e-06, "loss": 0.8088, "step": 14364 }, { "epoch": 0.8390771028037384, "grad_norm": 0.8890492916107178, "learning_rate": 1.3287313209505092e-06, "loss": 0.8651, "step": 14365 }, { "epoch": 0.8391355140186916, "grad_norm": 0.9737650156021118, "learning_rate": 1.3277891736396143e-06, "loss": 0.7443, "step": 14366 }, { "epoch": 0.8391939252336449, "grad_norm": 0.9383081793785095, "learning_rate": 1.3268473367128487e-06, "loss": 0.7291, "step": 14367 }, { "epoch": 0.8392523364485981, "grad_norm": 1.0308958292007446, "learning_rate": 1.3259058102039202e-06, "loss": 0.6231, "step": 14368 }, { "epoch": 0.8393107476635514, "grad_norm": 1.2507504224777222, "learning_rate": 1.3249645941465228e-06, "loss": 0.7947, "step": 14369 }, { "epoch": 0.8393691588785047, "grad_norm": 0.9122934341430664, "learning_rate": 1.3240236885743496e-06, "loss": 0.6944, "step": 14370 }, { "epoch": 0.8394275700934579, "grad_norm": 1.7297714948654175, "learning_rate": 1.3230830935210704e-06, "loss": 0.8213, "step": 14371 }, { "epoch": 0.8394859813084112, "grad_norm": 0.9418363571166992, "learning_rate": 1.3221428090203535e-06, "loss": 0.6882, "step": 14372 }, { "epoch": 0.8395443925233644, "grad_norm": 0.8935844302177429, "learning_rate": 1.3212028351058526e-06, "loss": 0.4922, "step": 14373 }, { "epoch": 0.8396028037383177, "grad_norm": 1.6271454095840454, "learning_rate": 1.3202631718112068e-06, "loss": 0.722, "step": 14374 }, { "epoch": 0.8396612149532711, "grad_norm": 1.0067063570022583, "learning_rate": 1.3193238191700509e-06, "loss": 0.7567, "step": 14375 }, { "epoch": 0.8397196261682243, "grad_norm": 1.3683507442474365, "learning_rate": 1.3183847772160007e-06, "loss": 0.9037, "step": 14376 }, { "epoch": 0.8397780373831776, "grad_norm": 1.0128129720687866, "learning_rate": 1.3174460459826687e-06, "loss": 1.0074, "step": 14377 }, { "epoch": 0.8398364485981309, "grad_norm": 1.2153242826461792, "learning_rate": 1.3165076255036524e-06, "loss": 0.7715, "step": 14378 }, { "epoch": 0.8398948598130841, "grad_norm": 1.4635518789291382, "learning_rate": 1.315569515812537e-06, "loss": 0.8563, "step": 14379 }, { "epoch": 0.8399532710280374, "grad_norm": 1.267331600189209, "learning_rate": 1.3146317169429e-06, "loss": 0.6842, "step": 14380 }, { "epoch": 0.8400116822429906, "grad_norm": 1.1528279781341553, "learning_rate": 1.3136942289283028e-06, "loss": 0.6821, "step": 14381 }, { "epoch": 0.8400700934579439, "grad_norm": 0.9132688045501709, "learning_rate": 1.3127570518023002e-06, "loss": 0.6453, "step": 14382 }, { "epoch": 0.8401285046728972, "grad_norm": 1.2161736488342285, "learning_rate": 1.311820185598437e-06, "loss": 0.8483, "step": 14383 }, { "epoch": 0.8401869158878504, "grad_norm": 1.1599940061569214, "learning_rate": 1.3108836303502392e-06, "loss": 0.8122, "step": 14384 }, { "epoch": 0.8402453271028038, "grad_norm": 1.2960916757583618, "learning_rate": 1.3099473860912325e-06, "loss": 0.8927, "step": 14385 }, { "epoch": 0.840303738317757, "grad_norm": 0.994486927986145, "learning_rate": 1.3090114528549202e-06, "loss": 0.661, "step": 14386 }, { "epoch": 0.8403621495327103, "grad_norm": 1.0395654439926147, "learning_rate": 1.3080758306748043e-06, "loss": 0.7256, "step": 14387 }, { "epoch": 0.8404205607476636, "grad_norm": 0.9611790180206299, "learning_rate": 1.3071405195843679e-06, "loss": 0.6676, "step": 14388 }, { "epoch": 0.8404789719626168, "grad_norm": 1.1248505115509033, "learning_rate": 1.3062055196170875e-06, "loss": 0.7222, "step": 14389 }, { "epoch": 0.8405373831775701, "grad_norm": 1.4358019828796387, "learning_rate": 1.305270830806431e-06, "loss": 0.8874, "step": 14390 }, { "epoch": 0.8405957943925234, "grad_norm": 0.8831319808959961, "learning_rate": 1.304336453185845e-06, "loss": 0.5722, "step": 14391 }, { "epoch": 0.8406542056074766, "grad_norm": 2.819486618041992, "learning_rate": 1.3034023867887768e-06, "loss": 0.7205, "step": 14392 }, { "epoch": 0.8407126168224299, "grad_norm": 1.6213096380233765, "learning_rate": 1.3024686316486545e-06, "loss": 0.839, "step": 14393 }, { "epoch": 0.8407710280373831, "grad_norm": 1.270577311515808, "learning_rate": 1.301535187798898e-06, "loss": 0.6837, "step": 14394 }, { "epoch": 0.8408294392523364, "grad_norm": 1.3265914916992188, "learning_rate": 1.300602055272918e-06, "loss": 0.7432, "step": 14395 }, { "epoch": 0.8408878504672898, "grad_norm": 1.2144635915756226, "learning_rate": 1.2996692341041084e-06, "loss": 1.0225, "step": 14396 }, { "epoch": 0.840946261682243, "grad_norm": 1.1339770555496216, "learning_rate": 1.2987367243258607e-06, "loss": 0.6449, "step": 14397 }, { "epoch": 0.8410046728971963, "grad_norm": 1.1474149227142334, "learning_rate": 1.2978045259715433e-06, "loss": 0.6609, "step": 14398 }, { "epoch": 0.8410630841121496, "grad_norm": 1.1306260824203491, "learning_rate": 1.2968726390745245e-06, "loss": 0.6946, "step": 14399 }, { "epoch": 0.8411214953271028, "grad_norm": 1.0863240957260132, "learning_rate": 1.295941063668159e-06, "loss": 0.7512, "step": 14400 }, { "epoch": 0.8411799065420561, "grad_norm": 4.60049295425415, "learning_rate": 1.2950097997857825e-06, "loss": 0.8243, "step": 14401 }, { "epoch": 0.8412383177570093, "grad_norm": 1.3440214395523071, "learning_rate": 1.2940788474607313e-06, "loss": 0.7755, "step": 14402 }, { "epoch": 0.8412967289719626, "grad_norm": 1.3414359092712402, "learning_rate": 1.2931482067263235e-06, "loss": 0.7797, "step": 14403 }, { "epoch": 0.8413551401869159, "grad_norm": 1.3704530000686646, "learning_rate": 1.2922178776158633e-06, "loss": 0.6715, "step": 14404 }, { "epoch": 0.8414135514018691, "grad_norm": 1.1593245267868042, "learning_rate": 1.2912878601626511e-06, "loss": 0.7496, "step": 14405 }, { "epoch": 0.8414719626168224, "grad_norm": 1.1032195091247559, "learning_rate": 1.2903581543999721e-06, "loss": 0.7517, "step": 14406 }, { "epoch": 0.8415303738317756, "grad_norm": 0.9934847354888916, "learning_rate": 1.2894287603611033e-06, "loss": 0.7827, "step": 14407 }, { "epoch": 0.841588785046729, "grad_norm": 0.9702949523925781, "learning_rate": 1.2884996780793068e-06, "loss": 0.5977, "step": 14408 }, { "epoch": 0.8416471962616823, "grad_norm": 1.115332841873169, "learning_rate": 1.2875709075878328e-06, "loss": 0.6274, "step": 14409 }, { "epoch": 0.8417056074766355, "grad_norm": 1.133241891860962, "learning_rate": 1.2866424489199247e-06, "loss": 0.6584, "step": 14410 }, { "epoch": 0.8417640186915888, "grad_norm": 1.2442491054534912, "learning_rate": 1.2857143021088114e-06, "loss": 0.8281, "step": 14411 }, { "epoch": 0.8418224299065421, "grad_norm": 0.9294203519821167, "learning_rate": 1.2847864671877164e-06, "loss": 0.7215, "step": 14412 }, { "epoch": 0.8418808411214953, "grad_norm": 1.2507002353668213, "learning_rate": 1.283858944189843e-06, "loss": 0.737, "step": 14413 }, { "epoch": 0.8419392523364486, "grad_norm": 1.0121009349822998, "learning_rate": 1.2829317331483882e-06, "loss": 0.8356, "step": 14414 }, { "epoch": 0.8419976635514018, "grad_norm": 0.8671683073043823, "learning_rate": 1.2820048340965373e-06, "loss": 0.7276, "step": 14415 }, { "epoch": 0.8420560747663551, "grad_norm": 1.0345666408538818, "learning_rate": 1.2810782470674654e-06, "loss": 0.8205, "step": 14416 }, { "epoch": 0.8421144859813084, "grad_norm": 1.204580545425415, "learning_rate": 1.280151972094339e-06, "loss": 0.7734, "step": 14417 }, { "epoch": 0.8421728971962616, "grad_norm": 1.1437922716140747, "learning_rate": 1.279226009210306e-06, "loss": 0.7925, "step": 14418 }, { "epoch": 0.842231308411215, "grad_norm": 0.7438068389892578, "learning_rate": 1.2783003584485066e-06, "loss": 0.5198, "step": 14419 }, { "epoch": 0.8422897196261683, "grad_norm": 1.0434646606445312, "learning_rate": 1.277375019842073e-06, "loss": 0.6663, "step": 14420 }, { "epoch": 0.8423481308411215, "grad_norm": 1.3882628679275513, "learning_rate": 1.2764499934241214e-06, "loss": 0.8605, "step": 14421 }, { "epoch": 0.8424065420560748, "grad_norm": 0.8788823485374451, "learning_rate": 1.2755252792277606e-06, "loss": 0.6744, "step": 14422 }, { "epoch": 0.842464953271028, "grad_norm": 0.7940089702606201, "learning_rate": 1.2746008772860885e-06, "loss": 0.8461, "step": 14423 }, { "epoch": 0.8425233644859813, "grad_norm": 0.9177830219268799, "learning_rate": 1.2736767876321866e-06, "loss": 0.6658, "step": 14424 }, { "epoch": 0.8425817757009346, "grad_norm": 1.0478500127792358, "learning_rate": 1.2727530102991302e-06, "loss": 0.8692, "step": 14425 }, { "epoch": 0.8426401869158878, "grad_norm": 1.459450125694275, "learning_rate": 1.2718295453199813e-06, "loss": 0.835, "step": 14426 }, { "epoch": 0.8426985981308411, "grad_norm": 0.8933395147323608, "learning_rate": 1.270906392727792e-06, "loss": 0.6508, "step": 14427 }, { "epoch": 0.8427570093457943, "grad_norm": 1.483240008354187, "learning_rate": 1.2699835525556036e-06, "loss": 0.646, "step": 14428 }, { "epoch": 0.8428154205607477, "grad_norm": 1.6656993627548218, "learning_rate": 1.2690610248364433e-06, "loss": 0.7973, "step": 14429 }, { "epoch": 0.842873831775701, "grad_norm": 2.51511812210083, "learning_rate": 1.2681388096033298e-06, "loss": 0.6191, "step": 14430 }, { "epoch": 0.8429322429906542, "grad_norm": 0.879397451877594, "learning_rate": 1.2672169068892692e-06, "loss": 0.735, "step": 14431 }, { "epoch": 0.8429906542056075, "grad_norm": 1.1449601650238037, "learning_rate": 1.2662953167272564e-06, "loss": 0.8203, "step": 14432 }, { "epoch": 0.8430490654205608, "grad_norm": 0.808163583278656, "learning_rate": 1.2653740391502788e-06, "loss": 0.5108, "step": 14433 }, { "epoch": 0.843107476635514, "grad_norm": 1.2688755989074707, "learning_rate": 1.2644530741913064e-06, "loss": 0.7449, "step": 14434 }, { "epoch": 0.8431658878504673, "grad_norm": 1.010035514831543, "learning_rate": 1.2635324218833034e-06, "loss": 0.6674, "step": 14435 }, { "epoch": 0.8432242990654205, "grad_norm": 1.042111873626709, "learning_rate": 1.2626120822592192e-06, "loss": 0.716, "step": 14436 }, { "epoch": 0.8432827102803738, "grad_norm": 0.9952508807182312, "learning_rate": 1.2616920553519917e-06, "loss": 0.8523, "step": 14437 }, { "epoch": 0.8433411214953271, "grad_norm": 0.8866356015205383, "learning_rate": 1.2607723411945516e-06, "loss": 0.5844, "step": 14438 }, { "epoch": 0.8433995327102803, "grad_norm": 1.058646559715271, "learning_rate": 1.2598529398198145e-06, "loss": 0.722, "step": 14439 }, { "epoch": 0.8434579439252337, "grad_norm": 1.0010236501693726, "learning_rate": 1.2589338512606907e-06, "loss": 0.6507, "step": 14440 }, { "epoch": 0.843516355140187, "grad_norm": 0.8775460720062256, "learning_rate": 1.2580150755500708e-06, "loss": 0.7056, "step": 14441 }, { "epoch": 0.8435747663551402, "grad_norm": 2.849593162536621, "learning_rate": 1.2570966127208373e-06, "loss": 0.6167, "step": 14442 }, { "epoch": 0.8436331775700935, "grad_norm": 1.205773949623108, "learning_rate": 1.2561784628058648e-06, "loss": 0.7518, "step": 14443 }, { "epoch": 0.8436915887850467, "grad_norm": 0.9039765000343323, "learning_rate": 1.255260625838015e-06, "loss": 0.7834, "step": 14444 }, { "epoch": 0.84375, "grad_norm": 1.111295461654663, "learning_rate": 1.2543431018501383e-06, "loss": 0.7606, "step": 14445 }, { "epoch": 0.8438084112149533, "grad_norm": 1.1184310913085938, "learning_rate": 1.253425890875073e-06, "loss": 0.7614, "step": 14446 }, { "epoch": 0.8438668224299065, "grad_norm": 1.5541090965270996, "learning_rate": 1.2525089929456436e-06, "loss": 0.7271, "step": 14447 }, { "epoch": 0.8439252336448598, "grad_norm": 1.1420280933380127, "learning_rate": 1.2515924080946695e-06, "loss": 0.6965, "step": 14448 }, { "epoch": 0.843983644859813, "grad_norm": 1.6715948581695557, "learning_rate": 1.2506761363549546e-06, "loss": 0.7351, "step": 14449 }, { "epoch": 0.8440420560747663, "grad_norm": 1.175153136253357, "learning_rate": 1.249760177759296e-06, "loss": 0.7577, "step": 14450 }, { "epoch": 0.8441004672897197, "grad_norm": 1.1364457607269287, "learning_rate": 1.2488445323404742e-06, "loss": 0.7359, "step": 14451 }, { "epoch": 0.8441588785046729, "grad_norm": 1.0297110080718994, "learning_rate": 1.2479292001312581e-06, "loss": 0.7458, "step": 14452 }, { "epoch": 0.8442172897196262, "grad_norm": 1.4192343950271606, "learning_rate": 1.247014181164412e-06, "loss": 0.9429, "step": 14453 }, { "epoch": 0.8442757009345795, "grad_norm": 1.0478904247283936, "learning_rate": 1.246099475472683e-06, "loss": 0.5876, "step": 14454 }, { "epoch": 0.8443341121495327, "grad_norm": 1.3984544277191162, "learning_rate": 1.245185083088808e-06, "loss": 0.751, "step": 14455 }, { "epoch": 0.844392523364486, "grad_norm": 1.170642375946045, "learning_rate": 1.2442710040455187e-06, "loss": 0.7643, "step": 14456 }, { "epoch": 0.8444509345794392, "grad_norm": 1.3435333967208862, "learning_rate": 1.2433572383755244e-06, "loss": 0.8308, "step": 14457 }, { "epoch": 0.8445093457943925, "grad_norm": 1.0951247215270996, "learning_rate": 1.2424437861115345e-06, "loss": 0.6788, "step": 14458 }, { "epoch": 0.8445677570093458, "grad_norm": 1.09073007106781, "learning_rate": 1.2415306472862376e-06, "loss": 0.8861, "step": 14459 }, { "epoch": 0.844626168224299, "grad_norm": 1.5559661388397217, "learning_rate": 1.2406178219323173e-06, "loss": 0.7899, "step": 14460 }, { "epoch": 0.8446845794392523, "grad_norm": 1.0761587619781494, "learning_rate": 1.2397053100824463e-06, "loss": 0.8174, "step": 14461 }, { "epoch": 0.8447429906542057, "grad_norm": 2.04453444480896, "learning_rate": 1.2387931117692808e-06, "loss": 0.8253, "step": 14462 }, { "epoch": 0.8448014018691589, "grad_norm": 1.7361998558044434, "learning_rate": 1.2378812270254726e-06, "loss": 0.7691, "step": 14463 }, { "epoch": 0.8448598130841122, "grad_norm": 0.9765941500663757, "learning_rate": 1.2369696558836541e-06, "loss": 0.8964, "step": 14464 }, { "epoch": 0.8449182242990654, "grad_norm": 1.1229034662246704, "learning_rate": 1.236058398376454e-06, "loss": 0.7569, "step": 14465 }, { "epoch": 0.8449766355140187, "grad_norm": 1.5563780069351196, "learning_rate": 1.2351474545364872e-06, "loss": 0.7532, "step": 14466 }, { "epoch": 0.845035046728972, "grad_norm": 1.475237250328064, "learning_rate": 1.2342368243963554e-06, "loss": 0.8153, "step": 14467 }, { "epoch": 0.8450934579439252, "grad_norm": 1.0814317464828491, "learning_rate": 1.2333265079886524e-06, "loss": 0.7434, "step": 14468 }, { "epoch": 0.8451518691588785, "grad_norm": 0.9686444997787476, "learning_rate": 1.2324165053459559e-06, "loss": 0.7586, "step": 14469 }, { "epoch": 0.8452102803738317, "grad_norm": 1.429958462715149, "learning_rate": 1.2315068165008393e-06, "loss": 0.5963, "step": 14470 }, { "epoch": 0.845268691588785, "grad_norm": 1.0719279050827026, "learning_rate": 1.230597441485858e-06, "loss": 0.8415, "step": 14471 }, { "epoch": 0.8453271028037384, "grad_norm": 1.8709932565689087, "learning_rate": 1.229688380333559e-06, "loss": 0.7412, "step": 14472 }, { "epoch": 0.8453855140186916, "grad_norm": 1.3213945627212524, "learning_rate": 1.2287796330764823e-06, "loss": 0.7961, "step": 14473 }, { "epoch": 0.8454439252336449, "grad_norm": 0.9584086537361145, "learning_rate": 1.2278711997471472e-06, "loss": 0.5605, "step": 14474 }, { "epoch": 0.8455023364485982, "grad_norm": 1.06735360622406, "learning_rate": 1.2269630803780719e-06, "loss": 0.8201, "step": 14475 }, { "epoch": 0.8455607476635514, "grad_norm": 1.1871085166931152, "learning_rate": 1.2260552750017551e-06, "loss": 0.7123, "step": 14476 }, { "epoch": 0.8456191588785047, "grad_norm": 1.336647629737854, "learning_rate": 1.2251477836506875e-06, "loss": 0.7735, "step": 14477 }, { "epoch": 0.8456775700934579, "grad_norm": 1.6603081226348877, "learning_rate": 1.224240606357353e-06, "loss": 0.8608, "step": 14478 }, { "epoch": 0.8457359813084112, "grad_norm": 1.1528325080871582, "learning_rate": 1.2233337431542181e-06, "loss": 0.8701, "step": 14479 }, { "epoch": 0.8457943925233645, "grad_norm": 1.1010040044784546, "learning_rate": 1.2224271940737364e-06, "loss": 0.7263, "step": 14480 }, { "epoch": 0.8458528037383177, "grad_norm": 0.8864266872406006, "learning_rate": 1.2215209591483567e-06, "loss": 0.5924, "step": 14481 }, { "epoch": 0.845911214953271, "grad_norm": 1.291122555732727, "learning_rate": 1.2206150384105142e-06, "loss": 0.9144, "step": 14482 }, { "epoch": 0.8459696261682244, "grad_norm": 0.9238076210021973, "learning_rate": 1.219709431892634e-06, "loss": 0.778, "step": 14483 }, { "epoch": 0.8460280373831776, "grad_norm": 1.8789983987808228, "learning_rate": 1.2188041396271266e-06, "loss": 0.7138, "step": 14484 }, { "epoch": 0.8460864485981309, "grad_norm": 1.246717929840088, "learning_rate": 1.2178991616463908e-06, "loss": 0.7934, "step": 14485 }, { "epoch": 0.8461448598130841, "grad_norm": 0.8695106506347656, "learning_rate": 1.2169944979828197e-06, "loss": 0.6718, "step": 14486 }, { "epoch": 0.8462032710280374, "grad_norm": 0.9877080917358398, "learning_rate": 1.2160901486687892e-06, "loss": 0.7417, "step": 14487 }, { "epoch": 0.8462616822429907, "grad_norm": 1.1114977598190308, "learning_rate": 1.2151861137366673e-06, "loss": 0.8236, "step": 14488 }, { "epoch": 0.8463200934579439, "grad_norm": 1.0805131196975708, "learning_rate": 1.2142823932188131e-06, "loss": 0.8372, "step": 14489 }, { "epoch": 0.8463785046728972, "grad_norm": 1.1509042978286743, "learning_rate": 1.2133789871475665e-06, "loss": 0.7244, "step": 14490 }, { "epoch": 0.8464369158878504, "grad_norm": 1.0570149421691895, "learning_rate": 1.2124758955552652e-06, "loss": 0.7931, "step": 14491 }, { "epoch": 0.8464953271028037, "grad_norm": 1.0690815448760986, "learning_rate": 1.2115731184742274e-06, "loss": 0.7584, "step": 14492 }, { "epoch": 0.846553738317757, "grad_norm": 1.157804012298584, "learning_rate": 1.2106706559367664e-06, "loss": 0.8152, "step": 14493 }, { "epoch": 0.8466121495327102, "grad_norm": 0.9953295588493347, "learning_rate": 1.2097685079751832e-06, "loss": 0.7717, "step": 14494 }, { "epoch": 0.8466705607476636, "grad_norm": 1.2345216274261475, "learning_rate": 1.2088666746217637e-06, "loss": 0.719, "step": 14495 }, { "epoch": 0.8467289719626169, "grad_norm": 1.0505318641662598, "learning_rate": 1.2079651559087868e-06, "loss": 0.7151, "step": 14496 }, { "epoch": 0.8467873831775701, "grad_norm": 1.025835633277893, "learning_rate": 1.2070639518685167e-06, "loss": 0.8536, "step": 14497 }, { "epoch": 0.8468457943925234, "grad_norm": 1.304244875907898, "learning_rate": 1.2061630625332098e-06, "loss": 0.7784, "step": 14498 }, { "epoch": 0.8469042056074766, "grad_norm": 1.2729848623275757, "learning_rate": 1.2052624879351105e-06, "loss": 0.8497, "step": 14499 }, { "epoch": 0.8469626168224299, "grad_norm": 1.2073312997817993, "learning_rate": 1.2043622281064471e-06, "loss": 0.6712, "step": 14500 }, { "epoch": 0.8470210280373832, "grad_norm": 1.257249355316162, "learning_rate": 1.2034622830794452e-06, "loss": 0.6304, "step": 14501 }, { "epoch": 0.8470794392523364, "grad_norm": 1.0169260501861572, "learning_rate": 1.2025626528863098e-06, "loss": 0.7626, "step": 14502 }, { "epoch": 0.8471378504672897, "grad_norm": 1.0069798231124878, "learning_rate": 1.2016633375592435e-06, "loss": 0.9804, "step": 14503 }, { "epoch": 0.847196261682243, "grad_norm": 1.0716934204101562, "learning_rate": 1.200764337130429e-06, "loss": 0.8403, "step": 14504 }, { "epoch": 0.8472546728971962, "grad_norm": 1.1999871730804443, "learning_rate": 1.1998656516320451e-06, "loss": 0.7183, "step": 14505 }, { "epoch": 0.8473130841121496, "grad_norm": 1.1041148900985718, "learning_rate": 1.1989672810962571e-06, "loss": 0.9299, "step": 14506 }, { "epoch": 0.8473714953271028, "grad_norm": 0.8977372646331787, "learning_rate": 1.1980692255552151e-06, "loss": 0.6892, "step": 14507 }, { "epoch": 0.8474299065420561, "grad_norm": 0.8972779512405396, "learning_rate": 1.1971714850410654e-06, "loss": 0.7473, "step": 14508 }, { "epoch": 0.8474883177570094, "grad_norm": 1.1481703519821167, "learning_rate": 1.1962740595859335e-06, "loss": 0.7651, "step": 14509 }, { "epoch": 0.8475467289719626, "grad_norm": 0.8328399658203125, "learning_rate": 1.1953769492219425e-06, "loss": 0.6481, "step": 14510 }, { "epoch": 0.8476051401869159, "grad_norm": 1.0198392868041992, "learning_rate": 1.1944801539812011e-06, "loss": 0.7913, "step": 14511 }, { "epoch": 0.8476635514018691, "grad_norm": 0.9889466762542725, "learning_rate": 1.1935836738958028e-06, "loss": 0.6949, "step": 14512 }, { "epoch": 0.8477219626168224, "grad_norm": 0.9062498807907104, "learning_rate": 1.1926875089978375e-06, "loss": 0.7745, "step": 14513 }, { "epoch": 0.8477803738317757, "grad_norm": 1.0222629308700562, "learning_rate": 1.1917916593193745e-06, "loss": 0.7869, "step": 14514 }, { "epoch": 0.8478387850467289, "grad_norm": 1.3952168226242065, "learning_rate": 1.1908961248924799e-06, "loss": 0.6595, "step": 14515 }, { "epoch": 0.8478971962616823, "grad_norm": 1.0915077924728394, "learning_rate": 1.1900009057492068e-06, "loss": 0.7444, "step": 14516 }, { "epoch": 0.8479556074766356, "grad_norm": 1.2067742347717285, "learning_rate": 1.1891060019215916e-06, "loss": 0.6074, "step": 14517 }, { "epoch": 0.8480140186915888, "grad_norm": 1.480778694152832, "learning_rate": 1.188211413441669e-06, "loss": 0.9203, "step": 14518 }, { "epoch": 0.8480724299065421, "grad_norm": 0.7910964488983154, "learning_rate": 1.187317140341453e-06, "loss": 0.5767, "step": 14519 }, { "epoch": 0.8481308411214953, "grad_norm": 1.0684881210327148, "learning_rate": 1.1864231826529493e-06, "loss": 0.7309, "step": 14520 }, { "epoch": 0.8481892523364486, "grad_norm": 1.5000275373458862, "learning_rate": 1.1855295404081546e-06, "loss": 0.9007, "step": 14521 }, { "epoch": 0.8482476635514019, "grad_norm": 1.286064863204956, "learning_rate": 1.1846362136390531e-06, "loss": 0.7824, "step": 14522 }, { "epoch": 0.8483060747663551, "grad_norm": 1.2416812181472778, "learning_rate": 1.1837432023776208e-06, "loss": 0.711, "step": 14523 }, { "epoch": 0.8483644859813084, "grad_norm": 1.1314983367919922, "learning_rate": 1.182850506655815e-06, "loss": 0.6641, "step": 14524 }, { "epoch": 0.8484228971962616, "grad_norm": 1.344149112701416, "learning_rate": 1.1819581265055857e-06, "loss": 0.7792, "step": 14525 }, { "epoch": 0.8484813084112149, "grad_norm": 1.2667596340179443, "learning_rate": 1.181066061958872e-06, "loss": 0.8286, "step": 14526 }, { "epoch": 0.8485397196261683, "grad_norm": 1.0698806047439575, "learning_rate": 1.180174313047604e-06, "loss": 0.8217, "step": 14527 }, { "epoch": 0.8485981308411215, "grad_norm": 1.0340540409088135, "learning_rate": 1.179282879803697e-06, "loss": 0.7835, "step": 14528 }, { "epoch": 0.8486565420560748, "grad_norm": 1.3323850631713867, "learning_rate": 1.1783917622590568e-06, "loss": 0.7543, "step": 14529 }, { "epoch": 0.8487149532710281, "grad_norm": 1.1382299661636353, "learning_rate": 1.1775009604455722e-06, "loss": 0.8371, "step": 14530 }, { "epoch": 0.8487733644859813, "grad_norm": 0.9132840633392334, "learning_rate": 1.17661047439513e-06, "loss": 0.8112, "step": 14531 }, { "epoch": 0.8488317757009346, "grad_norm": 1.0404974222183228, "learning_rate": 1.1757203041396014e-06, "loss": 0.6953, "step": 14532 }, { "epoch": 0.8488901869158878, "grad_norm": 1.1688321828842163, "learning_rate": 1.1748304497108453e-06, "loss": 0.7516, "step": 14533 }, { "epoch": 0.8489485981308411, "grad_norm": 0.9349194765090942, "learning_rate": 1.1739409111407118e-06, "loss": 0.8993, "step": 14534 }, { "epoch": 0.8490070093457944, "grad_norm": 0.9323481917381287, "learning_rate": 1.1730516884610332e-06, "loss": 0.6369, "step": 14535 }, { "epoch": 0.8490654205607476, "grad_norm": 1.6480629444122314, "learning_rate": 1.1721627817036408e-06, "loss": 0.7855, "step": 14536 }, { "epoch": 0.8491238317757009, "grad_norm": 1.2605037689208984, "learning_rate": 1.1712741909003444e-06, "loss": 0.639, "step": 14537 }, { "epoch": 0.8491822429906543, "grad_norm": 1.122481107711792, "learning_rate": 1.1703859160829512e-06, "loss": 0.7101, "step": 14538 }, { "epoch": 0.8492406542056075, "grad_norm": 0.9577779769897461, "learning_rate": 1.1694979572832521e-06, "loss": 0.7559, "step": 14539 }, { "epoch": 0.8492990654205608, "grad_norm": 1.0185405015945435, "learning_rate": 1.1686103145330262e-06, "loss": 0.7179, "step": 14540 }, { "epoch": 0.849357476635514, "grad_norm": 1.1252433061599731, "learning_rate": 1.167722987864045e-06, "loss": 0.7732, "step": 14541 }, { "epoch": 0.8494158878504673, "grad_norm": 0.9174008369445801, "learning_rate": 1.166835977308064e-06, "loss": 0.8341, "step": 14542 }, { "epoch": 0.8494742990654206, "grad_norm": 1.1512399911880493, "learning_rate": 1.165949282896831e-06, "loss": 0.8032, "step": 14543 }, { "epoch": 0.8495327102803738, "grad_norm": 0.8874152302742004, "learning_rate": 1.1650629046620843e-06, "loss": 0.7747, "step": 14544 }, { "epoch": 0.8495911214953271, "grad_norm": 1.4429749250411987, "learning_rate": 1.1641768426355427e-06, "loss": 0.8492, "step": 14545 }, { "epoch": 0.8496495327102803, "grad_norm": 0.9862958192825317, "learning_rate": 1.1632910968489242e-06, "loss": 0.596, "step": 14546 }, { "epoch": 0.8497079439252336, "grad_norm": 1.313269019126892, "learning_rate": 1.1624056673339245e-06, "loss": 0.635, "step": 14547 }, { "epoch": 0.849766355140187, "grad_norm": 1.223754644393921, "learning_rate": 1.1615205541222375e-06, "loss": 0.799, "step": 14548 }, { "epoch": 0.8498247663551401, "grad_norm": 1.235090970993042, "learning_rate": 1.160635757245544e-06, "loss": 0.7325, "step": 14549 }, { "epoch": 0.8498831775700935, "grad_norm": 1.1239557266235352, "learning_rate": 1.1597512767355058e-06, "loss": 0.7327, "step": 14550 }, { "epoch": 0.8499415887850468, "grad_norm": 1.2686930894851685, "learning_rate": 1.1588671126237838e-06, "loss": 0.7575, "step": 14551 }, { "epoch": 0.85, "grad_norm": 1.3023507595062256, "learning_rate": 1.157983264942022e-06, "loss": 0.8459, "step": 14552 }, { "epoch": 0.8500584112149533, "grad_norm": 1.1017765998840332, "learning_rate": 1.1570997337218492e-06, "loss": 0.8256, "step": 14553 }, { "epoch": 0.8501168224299065, "grad_norm": 0.8506672382354736, "learning_rate": 1.1562165189948925e-06, "loss": 0.8344, "step": 14554 }, { "epoch": 0.8501752336448598, "grad_norm": 1.1054627895355225, "learning_rate": 1.1553336207927612e-06, "loss": 0.7636, "step": 14555 }, { "epoch": 0.8502336448598131, "grad_norm": 0.7915657162666321, "learning_rate": 1.1544510391470575e-06, "loss": 0.6211, "step": 14556 }, { "epoch": 0.8502920560747663, "grad_norm": 1.3817535638809204, "learning_rate": 1.1535687740893665e-06, "loss": 0.8155, "step": 14557 }, { "epoch": 0.8503504672897196, "grad_norm": 1.2024203538894653, "learning_rate": 1.1526868256512647e-06, "loss": 0.7801, "step": 14558 }, { "epoch": 0.850408878504673, "grad_norm": 1.061667799949646, "learning_rate": 1.151805193864317e-06, "loss": 0.6544, "step": 14559 }, { "epoch": 0.8504672897196262, "grad_norm": 1.1399173736572266, "learning_rate": 1.1509238787600806e-06, "loss": 0.7826, "step": 14560 }, { "epoch": 0.8505257009345795, "grad_norm": 1.3276761770248413, "learning_rate": 1.150042880370099e-06, "loss": 0.7973, "step": 14561 }, { "epoch": 0.8505841121495327, "grad_norm": 1.3483775854110718, "learning_rate": 1.1491621987259005e-06, "loss": 0.8984, "step": 14562 }, { "epoch": 0.850642523364486, "grad_norm": 1.0334941148757935, "learning_rate": 1.148281833859005e-06, "loss": 0.665, "step": 14563 }, { "epoch": 0.8507009345794393, "grad_norm": 1.1081963777542114, "learning_rate": 1.1474017858009235e-06, "loss": 0.6579, "step": 14564 }, { "epoch": 0.8507593457943925, "grad_norm": 2.04976749420166, "learning_rate": 1.1465220545831524e-06, "loss": 0.811, "step": 14565 }, { "epoch": 0.8508177570093458, "grad_norm": 0.9388052225112915, "learning_rate": 1.14564264023718e-06, "loss": 0.641, "step": 14566 }, { "epoch": 0.850876168224299, "grad_norm": 1.0208834409713745, "learning_rate": 1.1447635427944791e-06, "loss": 0.7723, "step": 14567 }, { "epoch": 0.8509345794392523, "grad_norm": 0.9885345697402954, "learning_rate": 1.1438847622865125e-06, "loss": 0.769, "step": 14568 }, { "epoch": 0.8509929906542056, "grad_norm": 1.1007232666015625, "learning_rate": 1.1430062987447343e-06, "loss": 0.6536, "step": 14569 }, { "epoch": 0.8510514018691588, "grad_norm": 1.1900129318237305, "learning_rate": 1.14212815220058e-06, "loss": 0.7743, "step": 14570 }, { "epoch": 0.8511098130841122, "grad_norm": 1.0417160987854004, "learning_rate": 1.1412503226854877e-06, "loss": 0.698, "step": 14571 }, { "epoch": 0.8511682242990655, "grad_norm": 1.5377354621887207, "learning_rate": 1.140372810230872e-06, "loss": 0.7953, "step": 14572 }, { "epoch": 0.8512266355140187, "grad_norm": 1.453012228012085, "learning_rate": 1.1394956148681357e-06, "loss": 0.8639, "step": 14573 }, { "epoch": 0.851285046728972, "grad_norm": 1.064186692237854, "learning_rate": 1.1386187366286795e-06, "loss": 0.6789, "step": 14574 }, { "epoch": 0.8513434579439252, "grad_norm": 1.1982795000076294, "learning_rate": 1.1377421755438834e-06, "loss": 0.8122, "step": 14575 }, { "epoch": 0.8514018691588785, "grad_norm": 1.0315147638320923, "learning_rate": 1.1368659316451213e-06, "loss": 0.8014, "step": 14576 }, { "epoch": 0.8514602803738318, "grad_norm": 1.078678846359253, "learning_rate": 1.1359900049637574e-06, "loss": 0.6009, "step": 14577 }, { "epoch": 0.851518691588785, "grad_norm": 0.9196035861968994, "learning_rate": 1.1351143955311373e-06, "loss": 0.723, "step": 14578 }, { "epoch": 0.8515771028037383, "grad_norm": 1.2157540321350098, "learning_rate": 1.1342391033786038e-06, "loss": 0.7893, "step": 14579 }, { "epoch": 0.8516355140186916, "grad_norm": 2.1659095287323, "learning_rate": 1.1333641285374809e-06, "loss": 0.7951, "step": 14580 }, { "epoch": 0.8516939252336448, "grad_norm": 1.0697683095932007, "learning_rate": 1.1324894710390844e-06, "loss": 0.621, "step": 14581 }, { "epoch": 0.8517523364485982, "grad_norm": 1.1376566886901855, "learning_rate": 1.131615130914724e-06, "loss": 0.7362, "step": 14582 }, { "epoch": 0.8518107476635514, "grad_norm": 0.8957938551902771, "learning_rate": 1.1307411081956854e-06, "loss": 0.6293, "step": 14583 }, { "epoch": 0.8518691588785047, "grad_norm": 1.2426323890686035, "learning_rate": 1.1298674029132573e-06, "loss": 0.7843, "step": 14584 }, { "epoch": 0.851927570093458, "grad_norm": 1.353570580482483, "learning_rate": 1.1289940150987044e-06, "loss": 0.9217, "step": 14585 }, { "epoch": 0.8519859813084112, "grad_norm": 1.0604870319366455, "learning_rate": 1.1281209447832908e-06, "loss": 0.7683, "step": 14586 }, { "epoch": 0.8520443925233645, "grad_norm": 0.96388179063797, "learning_rate": 1.1272481919982603e-06, "loss": 0.6864, "step": 14587 }, { "epoch": 0.8521028037383177, "grad_norm": 1.0637919902801514, "learning_rate": 1.1263757567748501e-06, "loss": 0.658, "step": 14588 }, { "epoch": 0.852161214953271, "grad_norm": 0.9264376759529114, "learning_rate": 1.1255036391442887e-06, "loss": 0.7255, "step": 14589 }, { "epoch": 0.8522196261682243, "grad_norm": 1.0707415342330933, "learning_rate": 1.1246318391377853e-06, "loss": 0.797, "step": 14590 }, { "epoch": 0.8522780373831775, "grad_norm": 1.0606170892715454, "learning_rate": 1.1237603567865452e-06, "loss": 0.6377, "step": 14591 }, { "epoch": 0.8523364485981308, "grad_norm": 1.1364089250564575, "learning_rate": 1.1228891921217566e-06, "loss": 0.8378, "step": 14592 }, { "epoch": 0.8523948598130842, "grad_norm": 1.098328709602356, "learning_rate": 1.1220183451746014e-06, "loss": 0.7511, "step": 14593 }, { "epoch": 0.8524532710280374, "grad_norm": 1.588486671447754, "learning_rate": 1.121147815976248e-06, "loss": 0.5598, "step": 14594 }, { "epoch": 0.8525116822429907, "grad_norm": 0.8114290833473206, "learning_rate": 1.1202776045578533e-06, "loss": 0.6483, "step": 14595 }, { "epoch": 0.8525700934579439, "grad_norm": 1.3414620161056519, "learning_rate": 1.1194077109505586e-06, "loss": 0.9796, "step": 14596 }, { "epoch": 0.8526285046728972, "grad_norm": 0.990120530128479, "learning_rate": 1.1185381351855018e-06, "loss": 0.7731, "step": 14597 }, { "epoch": 0.8526869158878505, "grad_norm": 1.3482017517089844, "learning_rate": 1.1176688772938037e-06, "loss": 0.7546, "step": 14598 }, { "epoch": 0.8527453271028037, "grad_norm": 1.2717905044555664, "learning_rate": 1.1167999373065797e-06, "loss": 0.7651, "step": 14599 }, { "epoch": 0.852803738317757, "grad_norm": 1.0160276889801025, "learning_rate": 1.1159313152549266e-06, "loss": 0.8307, "step": 14600 }, { "epoch": 0.8528621495327103, "grad_norm": 1.0411491394042969, "learning_rate": 1.1150630111699312e-06, "loss": 0.8218, "step": 14601 }, { "epoch": 0.8529205607476635, "grad_norm": 1.2096697092056274, "learning_rate": 1.114195025082674e-06, "loss": 0.8274, "step": 14602 }, { "epoch": 0.8529789719626168, "grad_norm": 1.276528239250183, "learning_rate": 1.1133273570242165e-06, "loss": 0.7387, "step": 14603 }, { "epoch": 0.85303738317757, "grad_norm": 1.0534982681274414, "learning_rate": 1.1124600070256185e-06, "loss": 0.7188, "step": 14604 }, { "epoch": 0.8530957943925234, "grad_norm": 1.510728120803833, "learning_rate": 1.1115929751179221e-06, "loss": 0.8352, "step": 14605 }, { "epoch": 0.8531542056074767, "grad_norm": 0.9065031409263611, "learning_rate": 1.1107262613321545e-06, "loss": 0.7373, "step": 14606 }, { "epoch": 0.8532126168224299, "grad_norm": 1.1509833335876465, "learning_rate": 1.1098598656993408e-06, "loss": 0.8896, "step": 14607 }, { "epoch": 0.8532710280373832, "grad_norm": 1.6892879009246826, "learning_rate": 1.1089937882504852e-06, "loss": 0.994, "step": 14608 }, { "epoch": 0.8533294392523364, "grad_norm": 1.0495857000350952, "learning_rate": 1.1081280290165897e-06, "loss": 0.7362, "step": 14609 }, { "epoch": 0.8533878504672897, "grad_norm": 1.4216790199279785, "learning_rate": 1.1072625880286392e-06, "loss": 0.7099, "step": 14610 }, { "epoch": 0.853446261682243, "grad_norm": 1.2308788299560547, "learning_rate": 1.1063974653176057e-06, "loss": 0.9068, "step": 14611 }, { "epoch": 0.8535046728971962, "grad_norm": 1.1384087800979614, "learning_rate": 1.1055326609144567e-06, "loss": 0.8919, "step": 14612 }, { "epoch": 0.8535630841121495, "grad_norm": 0.843838632106781, "learning_rate": 1.1046681748501409e-06, "loss": 0.6242, "step": 14613 }, { "epoch": 0.8536214953271029, "grad_norm": 1.0454840660095215, "learning_rate": 1.1038040071555988e-06, "loss": 0.6953, "step": 14614 }, { "epoch": 0.853679906542056, "grad_norm": 0.9601994752883911, "learning_rate": 1.1029401578617638e-06, "loss": 0.7563, "step": 14615 }, { "epoch": 0.8537383177570094, "grad_norm": 1.5195834636688232, "learning_rate": 1.1020766269995475e-06, "loss": 0.7407, "step": 14616 }, { "epoch": 0.8537967289719626, "grad_norm": 0.9998459219932556, "learning_rate": 1.101213414599861e-06, "loss": 0.8687, "step": 14617 }, { "epoch": 0.8538551401869159, "grad_norm": 1.2725706100463867, "learning_rate": 1.100350520693596e-06, "loss": 0.8283, "step": 14618 }, { "epoch": 0.8539135514018692, "grad_norm": 0.9670023322105408, "learning_rate": 1.0994879453116391e-06, "loss": 0.662, "step": 14619 }, { "epoch": 0.8539719626168224, "grad_norm": 0.9272193312644958, "learning_rate": 1.09862568848486e-06, "loss": 0.6659, "step": 14620 }, { "epoch": 0.8540303738317757, "grad_norm": 1.2931257486343384, "learning_rate": 1.0977637502441197e-06, "loss": 0.7886, "step": 14621 }, { "epoch": 0.854088785046729, "grad_norm": 1.0605552196502686, "learning_rate": 1.0969021306202699e-06, "loss": 0.678, "step": 14622 }, { "epoch": 0.8541471962616822, "grad_norm": 18.039310455322266, "learning_rate": 1.0960408296441437e-06, "loss": 0.8332, "step": 14623 }, { "epoch": 0.8542056074766355, "grad_norm": 1.0602755546569824, "learning_rate": 1.0951798473465747e-06, "loss": 0.7553, "step": 14624 }, { "epoch": 0.8542640186915887, "grad_norm": 1.0608088970184326, "learning_rate": 1.09431918375837e-06, "loss": 0.8109, "step": 14625 }, { "epoch": 0.8543224299065421, "grad_norm": 1.16188383102417, "learning_rate": 1.0934588389103385e-06, "loss": 0.6898, "step": 14626 }, { "epoch": 0.8543808411214954, "grad_norm": 1.1153802871704102, "learning_rate": 1.0925988128332732e-06, "loss": 0.6717, "step": 14627 }, { "epoch": 0.8544392523364486, "grad_norm": 0.8895884156227112, "learning_rate": 1.0917391055579518e-06, "loss": 0.8257, "step": 14628 }, { "epoch": 0.8544976635514019, "grad_norm": 0.9062826037406921, "learning_rate": 1.0908797171151453e-06, "loss": 0.6811, "step": 14629 }, { "epoch": 0.8545560747663551, "grad_norm": 1.0292447805404663, "learning_rate": 1.0900206475356113e-06, "loss": 0.6478, "step": 14630 }, { "epoch": 0.8546144859813084, "grad_norm": 1.082740306854248, "learning_rate": 1.0891618968500962e-06, "loss": 0.6977, "step": 14631 }, { "epoch": 0.8546728971962617, "grad_norm": 0.9232220649719238, "learning_rate": 1.0883034650893376e-06, "loss": 0.8512, "step": 14632 }, { "epoch": 0.8547313084112149, "grad_norm": 1.327024221420288, "learning_rate": 1.0874453522840556e-06, "loss": 0.8069, "step": 14633 }, { "epoch": 0.8547897196261682, "grad_norm": 1.142511010169983, "learning_rate": 1.0865875584649665e-06, "loss": 0.7412, "step": 14634 }, { "epoch": 0.8548481308411215, "grad_norm": 1.1421617269515991, "learning_rate": 1.0857300836627694e-06, "loss": 0.6596, "step": 14635 }, { "epoch": 0.8549065420560747, "grad_norm": 1.6764593124389648, "learning_rate": 1.0848729279081493e-06, "loss": 0.6968, "step": 14636 }, { "epoch": 0.8549649532710281, "grad_norm": 0.9223895072937012, "learning_rate": 1.0840160912317943e-06, "loss": 0.6603, "step": 14637 }, { "epoch": 0.8550233644859813, "grad_norm": 1.1832853555679321, "learning_rate": 1.083159573664363e-06, "loss": 0.8841, "step": 14638 }, { "epoch": 0.8550817757009346, "grad_norm": 1.243798851966858, "learning_rate": 1.0823033752365154e-06, "loss": 0.77, "step": 14639 }, { "epoch": 0.8551401869158879, "grad_norm": 1.1245344877243042, "learning_rate": 1.0814474959788935e-06, "loss": 0.6938, "step": 14640 }, { "epoch": 0.8551985981308411, "grad_norm": 1.3832781314849854, "learning_rate": 1.0805919359221272e-06, "loss": 0.6934, "step": 14641 }, { "epoch": 0.8552570093457944, "grad_norm": 1.2421499490737915, "learning_rate": 1.0797366950968413e-06, "loss": 0.6933, "step": 14642 }, { "epoch": 0.8553154205607477, "grad_norm": 1.140089511871338, "learning_rate": 1.0788817735336443e-06, "loss": 0.6083, "step": 14643 }, { "epoch": 0.8553738317757009, "grad_norm": 1.057133436203003, "learning_rate": 1.0780271712631351e-06, "loss": 0.6995, "step": 14644 }, { "epoch": 0.8554322429906542, "grad_norm": 0.8588012456893921, "learning_rate": 1.0771728883159005e-06, "loss": 0.623, "step": 14645 }, { "epoch": 0.8554906542056074, "grad_norm": 1.035744309425354, "learning_rate": 1.0763189247225136e-06, "loss": 0.6682, "step": 14646 }, { "epoch": 0.8555490654205608, "grad_norm": 2.9432156085968018, "learning_rate": 1.075465280513539e-06, "loss": 0.9428, "step": 14647 }, { "epoch": 0.8556074766355141, "grad_norm": 1.4098643064498901, "learning_rate": 1.0746119557195322e-06, "loss": 0.8865, "step": 14648 }, { "epoch": 0.8556658878504673, "grad_norm": 1.0611430406570435, "learning_rate": 1.07375895037103e-06, "loss": 0.6844, "step": 14649 }, { "epoch": 0.8557242990654206, "grad_norm": 1.0784350633621216, "learning_rate": 1.0729062644985665e-06, "loss": 0.8291, "step": 14650 }, { "epoch": 0.8557827102803738, "grad_norm": 1.1172664165496826, "learning_rate": 1.0720538981326557e-06, "loss": 0.6357, "step": 14651 }, { "epoch": 0.8558411214953271, "grad_norm": 17.312328338623047, "learning_rate": 1.0712018513038068e-06, "loss": 0.8901, "step": 14652 }, { "epoch": 0.8558995327102804, "grad_norm": 1.1136891841888428, "learning_rate": 1.070350124042514e-06, "loss": 0.764, "step": 14653 }, { "epoch": 0.8559579439252336, "grad_norm": 0.9003828167915344, "learning_rate": 1.0694987163792604e-06, "loss": 0.7532, "step": 14654 }, { "epoch": 0.8560163551401869, "grad_norm": 1.053321361541748, "learning_rate": 1.0686476283445224e-06, "loss": 0.6745, "step": 14655 }, { "epoch": 0.8560747663551402, "grad_norm": 0.934893012046814, "learning_rate": 1.0677968599687561e-06, "loss": 0.5931, "step": 14656 }, { "epoch": 0.8561331775700934, "grad_norm": 1.0306857824325562, "learning_rate": 1.0669464112824156e-06, "loss": 0.8416, "step": 14657 }, { "epoch": 0.8561915887850468, "grad_norm": 1.0438220500946045, "learning_rate": 1.0660962823159337e-06, "loss": 0.8922, "step": 14658 }, { "epoch": 0.85625, "grad_norm": 1.0474510192871094, "learning_rate": 1.0652464730997404e-06, "loss": 0.6976, "step": 14659 }, { "epoch": 0.8563084112149533, "grad_norm": 1.3777521848678589, "learning_rate": 1.064396983664253e-06, "loss": 0.7856, "step": 14660 }, { "epoch": 0.8563668224299066, "grad_norm": 1.6244101524353027, "learning_rate": 1.0635478140398703e-06, "loss": 0.6868, "step": 14661 }, { "epoch": 0.8564252336448598, "grad_norm": 0.9590185880661011, "learning_rate": 1.0626989642569896e-06, "loss": 0.7184, "step": 14662 }, { "epoch": 0.8564836448598131, "grad_norm": 1.1366804838180542, "learning_rate": 1.0618504343459868e-06, "loss": 0.8973, "step": 14663 }, { "epoch": 0.8565420560747663, "grad_norm": 1.13162100315094, "learning_rate": 1.0610022243372342e-06, "loss": 0.6589, "step": 14664 }, { "epoch": 0.8566004672897196, "grad_norm": 1.0744554996490479, "learning_rate": 1.060154334261092e-06, "loss": 0.5786, "step": 14665 }, { "epoch": 0.8566588785046729, "grad_norm": 1.0398807525634766, "learning_rate": 1.0593067641479016e-06, "loss": 0.6895, "step": 14666 }, { "epoch": 0.8567172897196261, "grad_norm": 1.267291784286499, "learning_rate": 1.058459514028003e-06, "loss": 0.9258, "step": 14667 }, { "epoch": 0.8567757009345794, "grad_norm": 0.7801699042320251, "learning_rate": 1.0576125839317175e-06, "loss": 0.6295, "step": 14668 }, { "epoch": 0.8568341121495328, "grad_norm": 1.0753719806671143, "learning_rate": 1.0567659738893532e-06, "loss": 0.8799, "step": 14669 }, { "epoch": 0.856892523364486, "grad_norm": 1.0694254636764526, "learning_rate": 1.0559196839312192e-06, "loss": 0.8024, "step": 14670 }, { "epoch": 0.8569509345794393, "grad_norm": 0.9069505333900452, "learning_rate": 1.0550737140875978e-06, "loss": 0.9014, "step": 14671 }, { "epoch": 0.8570093457943925, "grad_norm": 0.9369138479232788, "learning_rate": 1.0542280643887726e-06, "loss": 0.6604, "step": 14672 }, { "epoch": 0.8570677570093458, "grad_norm": 1.266298770904541, "learning_rate": 1.0533827348650061e-06, "loss": 0.7534, "step": 14673 }, { "epoch": 0.8571261682242991, "grad_norm": 1.021729826927185, "learning_rate": 1.052537725546553e-06, "loss": 0.7237, "step": 14674 }, { "epoch": 0.8571845794392523, "grad_norm": 1.2060080766677856, "learning_rate": 1.051693036463657e-06, "loss": 0.7499, "step": 14675 }, { "epoch": 0.8572429906542056, "grad_norm": 1.0578196048736572, "learning_rate": 1.0508486676465513e-06, "loss": 0.9197, "step": 14676 }, { "epoch": 0.8573014018691589, "grad_norm": 1.0142446756362915, "learning_rate": 1.0500046191254577e-06, "loss": 0.7841, "step": 14677 }, { "epoch": 0.8573598130841121, "grad_norm": 1.0753940343856812, "learning_rate": 1.049160890930584e-06, "loss": 0.6609, "step": 14678 }, { "epoch": 0.8574182242990654, "grad_norm": 1.4957165718078613, "learning_rate": 1.048317483092124e-06, "loss": 0.8097, "step": 14679 }, { "epoch": 0.8574766355140186, "grad_norm": 1.0919954776763916, "learning_rate": 1.047474395640269e-06, "loss": 0.7547, "step": 14680 }, { "epoch": 0.857535046728972, "grad_norm": 0.9479002356529236, "learning_rate": 1.0466316286051902e-06, "loss": 0.7447, "step": 14681 }, { "epoch": 0.8575934579439253, "grad_norm": 1.151119589805603, "learning_rate": 1.0457891820170552e-06, "loss": 0.8407, "step": 14682 }, { "epoch": 0.8576518691588785, "grad_norm": 1.1577271223068237, "learning_rate": 1.0449470559060125e-06, "loss": 0.8456, "step": 14683 }, { "epoch": 0.8577102803738318, "grad_norm": 1.029188632965088, "learning_rate": 1.0441052503022009e-06, "loss": 0.6532, "step": 14684 }, { "epoch": 0.857768691588785, "grad_norm": 0.8916462659835815, "learning_rate": 1.0432637652357525e-06, "loss": 0.6623, "step": 14685 }, { "epoch": 0.8578271028037383, "grad_norm": 1.0843515396118164, "learning_rate": 1.04242260073678e-06, "loss": 1.0012, "step": 14686 }, { "epoch": 0.8578855140186916, "grad_norm": 0.9717994332313538, "learning_rate": 1.0415817568353958e-06, "loss": 0.6877, "step": 14687 }, { "epoch": 0.8579439252336448, "grad_norm": 1.3396737575531006, "learning_rate": 1.0407412335616906e-06, "loss": 0.7173, "step": 14688 }, { "epoch": 0.8580023364485981, "grad_norm": 1.1490286588668823, "learning_rate": 1.0399010309457459e-06, "loss": 0.8462, "step": 14689 }, { "epoch": 0.8580607476635514, "grad_norm": 0.9862267971038818, "learning_rate": 1.0390611490176373e-06, "loss": 0.7924, "step": 14690 }, { "epoch": 0.8581191588785047, "grad_norm": 1.1350027322769165, "learning_rate": 1.0382215878074186e-06, "loss": 0.8124, "step": 14691 }, { "epoch": 0.858177570093458, "grad_norm": 1.0214930772781372, "learning_rate": 1.0373823473451427e-06, "loss": 0.5443, "step": 14692 }, { "epoch": 0.8582359813084112, "grad_norm": 0.834163248538971, "learning_rate": 1.0365434276608477e-06, "loss": 0.5611, "step": 14693 }, { "epoch": 0.8582943925233645, "grad_norm": 0.9385734796524048, "learning_rate": 1.035704828784555e-06, "loss": 0.7389, "step": 14694 }, { "epoch": 0.8583528037383178, "grad_norm": 2.6980032920837402, "learning_rate": 1.0348665507462818e-06, "loss": 0.7334, "step": 14695 }, { "epoch": 0.858411214953271, "grad_norm": 1.2712312936782837, "learning_rate": 1.0340285935760286e-06, "loss": 0.7327, "step": 14696 }, { "epoch": 0.8584696261682243, "grad_norm": 1.2641997337341309, "learning_rate": 1.033190957303787e-06, "loss": 0.7655, "step": 14697 }, { "epoch": 0.8585280373831776, "grad_norm": 1.7744474411010742, "learning_rate": 1.0323536419595381e-06, "loss": 0.6955, "step": 14698 }, { "epoch": 0.8585864485981308, "grad_norm": 0.8043378591537476, "learning_rate": 1.0315166475732475e-06, "loss": 0.6609, "step": 14699 }, { "epoch": 0.8586448598130841, "grad_norm": 0.8486257791519165, "learning_rate": 1.0306799741748741e-06, "loss": 0.6036, "step": 14700 }, { "epoch": 0.8587032710280373, "grad_norm": 0.9682250618934631, "learning_rate": 1.0298436217943609e-06, "loss": 0.7071, "step": 14701 }, { "epoch": 0.8587616822429907, "grad_norm": 0.9303827881813049, "learning_rate": 1.0290075904616414e-06, "loss": 0.7297, "step": 14702 }, { "epoch": 0.858820093457944, "grad_norm": 0.9808047413825989, "learning_rate": 1.028171880206642e-06, "loss": 0.6831, "step": 14703 }, { "epoch": 0.8588785046728972, "grad_norm": 0.9166598916053772, "learning_rate": 1.0273364910592675e-06, "loss": 0.8571, "step": 14704 }, { "epoch": 0.8589369158878505, "grad_norm": 0.8247193098068237, "learning_rate": 1.0265014230494208e-06, "loss": 0.6635, "step": 14705 }, { "epoch": 0.8589953271028037, "grad_norm": 0.9786083102226257, "learning_rate": 1.02566667620699e-06, "loss": 0.5824, "step": 14706 }, { "epoch": 0.859053738317757, "grad_norm": 1.597103238105774, "learning_rate": 1.0248322505618459e-06, "loss": 0.7461, "step": 14707 }, { "epoch": 0.8591121495327103, "grad_norm": 1.185689091682434, "learning_rate": 1.0239981461438574e-06, "loss": 0.7994, "step": 14708 }, { "epoch": 0.8591705607476635, "grad_norm": 2.1001055240631104, "learning_rate": 1.023164362982878e-06, "loss": 0.8915, "step": 14709 }, { "epoch": 0.8592289719626168, "grad_norm": 1.0102829933166504, "learning_rate": 1.02233090110875e-06, "loss": 0.7267, "step": 14710 }, { "epoch": 0.8592873831775701, "grad_norm": 1.0394389629364014, "learning_rate": 1.021497760551301e-06, "loss": 0.8196, "step": 14711 }, { "epoch": 0.8593457943925233, "grad_norm": 1.27993905544281, "learning_rate": 1.0206649413403501e-06, "loss": 0.8243, "step": 14712 }, { "epoch": 0.8594042056074767, "grad_norm": 0.9314073920249939, "learning_rate": 1.0198324435057039e-06, "loss": 0.7287, "step": 14713 }, { "epoch": 0.8594626168224299, "grad_norm": 1.3284567594528198, "learning_rate": 1.0190002670771593e-06, "loss": 0.941, "step": 14714 }, { "epoch": 0.8595210280373832, "grad_norm": 1.0697650909423828, "learning_rate": 1.0181684120845026e-06, "loss": 0.8517, "step": 14715 }, { "epoch": 0.8595794392523365, "grad_norm": 0.8995751738548279, "learning_rate": 1.0173368785575043e-06, "loss": 0.7288, "step": 14716 }, { "epoch": 0.8596378504672897, "grad_norm": 1.11558198928833, "learning_rate": 1.0165056665259231e-06, "loss": 0.7256, "step": 14717 }, { "epoch": 0.859696261682243, "grad_norm": 1.1750189065933228, "learning_rate": 1.015674776019513e-06, "loss": 0.7733, "step": 14718 }, { "epoch": 0.8597546728971963, "grad_norm": 1.431841492652893, "learning_rate": 1.0148442070680053e-06, "loss": 0.7764, "step": 14719 }, { "epoch": 0.8598130841121495, "grad_norm": 1.0571688413619995, "learning_rate": 1.0140139597011356e-06, "loss": 0.662, "step": 14720 }, { "epoch": 0.8598714953271028, "grad_norm": 0.960827112197876, "learning_rate": 1.0131840339486143e-06, "loss": 0.6456, "step": 14721 }, { "epoch": 0.859929906542056, "grad_norm": 0.9398359060287476, "learning_rate": 1.0123544298401445e-06, "loss": 0.7541, "step": 14722 }, { "epoch": 0.8599883177570093, "grad_norm": 1.2624740600585938, "learning_rate": 1.0115251474054199e-06, "loss": 0.8468, "step": 14723 }, { "epoch": 0.8600467289719627, "grad_norm": 1.0790210962295532, "learning_rate": 1.0106961866741195e-06, "loss": 0.8667, "step": 14724 }, { "epoch": 0.8601051401869159, "grad_norm": 1.4259852170944214, "learning_rate": 1.0098675476759124e-06, "loss": 0.8668, "step": 14725 }, { "epoch": 0.8601635514018692, "grad_norm": 1.495129108428955, "learning_rate": 1.0090392304404595e-06, "loss": 0.7738, "step": 14726 }, { "epoch": 0.8602219626168224, "grad_norm": 1.1791646480560303, "learning_rate": 1.0082112349974017e-06, "loss": 0.7063, "step": 14727 }, { "epoch": 0.8602803738317757, "grad_norm": 0.9343026280403137, "learning_rate": 1.0073835613763772e-06, "loss": 0.7664, "step": 14728 }, { "epoch": 0.860338785046729, "grad_norm": 1.1445086002349854, "learning_rate": 1.006556209607007e-06, "loss": 0.9597, "step": 14729 }, { "epoch": 0.8603971962616822, "grad_norm": 1.056036114692688, "learning_rate": 1.0057291797189027e-06, "loss": 0.7697, "step": 14730 }, { "epoch": 0.8604556074766355, "grad_norm": 1.0207648277282715, "learning_rate": 1.0049024717416678e-06, "loss": 0.6448, "step": 14731 }, { "epoch": 0.8605140186915888, "grad_norm": 1.5798163414001465, "learning_rate": 1.0040760857048847e-06, "loss": 0.8159, "step": 14732 }, { "epoch": 0.860572429906542, "grad_norm": 1.619307279586792, "learning_rate": 1.003250021638137e-06, "loss": 0.6929, "step": 14733 }, { "epoch": 0.8606308411214953, "grad_norm": 1.2738794088363647, "learning_rate": 1.0024242795709826e-06, "loss": 0.7991, "step": 14734 }, { "epoch": 0.8606892523364486, "grad_norm": 1.1005735397338867, "learning_rate": 1.0015988595329807e-06, "loss": 0.6137, "step": 14735 }, { "epoch": 0.8607476635514019, "grad_norm": 0.9368434548377991, "learning_rate": 1.000773761553674e-06, "loss": 0.6194, "step": 14736 }, { "epoch": 0.8608060747663552, "grad_norm": 0.8248820304870605, "learning_rate": 9.999489856625889e-07, "loss": 0.6823, "step": 14737 }, { "epoch": 0.8608644859813084, "grad_norm": 1.6249295473098755, "learning_rate": 9.991245318892495e-07, "loss": 0.8342, "step": 14738 }, { "epoch": 0.8609228971962617, "grad_norm": 1.092615008354187, "learning_rate": 9.983004002631592e-07, "loss": 0.7494, "step": 14739 }, { "epoch": 0.860981308411215, "grad_norm": 1.2048437595367432, "learning_rate": 9.974765908138184e-07, "loss": 0.7136, "step": 14740 }, { "epoch": 0.8610397196261682, "grad_norm": 1.8783884048461914, "learning_rate": 9.966531035707072e-07, "loss": 0.9052, "step": 14741 }, { "epoch": 0.8610981308411215, "grad_norm": 1.1307393312454224, "learning_rate": 9.95829938563302e-07, "loss": 0.7998, "step": 14742 }, { "epoch": 0.8611565420560747, "grad_norm": 1.1055407524108887, "learning_rate": 9.950070958210657e-07, "loss": 0.694, "step": 14743 }, { "epoch": 0.861214953271028, "grad_norm": 0.9689121842384338, "learning_rate": 9.941845753734437e-07, "loss": 0.6124, "step": 14744 }, { "epoch": 0.8612733644859814, "grad_norm": 0.7868703007698059, "learning_rate": 9.93362377249879e-07, "loss": 0.7838, "step": 14745 }, { "epoch": 0.8613317757009346, "grad_norm": 1.0510179996490479, "learning_rate": 9.925405014797962e-07, "loss": 0.7168, "step": 14746 }, { "epoch": 0.8613901869158879, "grad_norm": 0.9126620888710022, "learning_rate": 9.917189480926104e-07, "loss": 0.8426, "step": 14747 }, { "epoch": 0.8614485981308411, "grad_norm": 0.9405373930931091, "learning_rate": 9.90897717117728e-07, "loss": 0.6736, "step": 14748 }, { "epoch": 0.8615070093457944, "grad_norm": 0.9043285250663757, "learning_rate": 9.900768085845391e-07, "loss": 0.684, "step": 14749 }, { "epoch": 0.8615654205607477, "grad_norm": 1.087433934211731, "learning_rate": 9.892562225224266e-07, "loss": 0.7978, "step": 14750 }, { "epoch": 0.8616238317757009, "grad_norm": 1.0845712423324585, "learning_rate": 9.884359589607585e-07, "loss": 0.6538, "step": 14751 }, { "epoch": 0.8616822429906542, "grad_norm": 1.2053089141845703, "learning_rate": 9.876160179288886e-07, "loss": 0.8488, "step": 14752 }, { "epoch": 0.8617406542056075, "grad_norm": 1.1996780633926392, "learning_rate": 9.867963994561713e-07, "loss": 0.7298, "step": 14753 }, { "epoch": 0.8617990654205607, "grad_norm": 0.9583183526992798, "learning_rate": 9.859771035719357e-07, "loss": 0.68, "step": 14754 }, { "epoch": 0.861857476635514, "grad_norm": 1.2763344049453735, "learning_rate": 9.85158130305508e-07, "loss": 0.87, "step": 14755 }, { "epoch": 0.8619158878504672, "grad_norm": 1.268572211265564, "learning_rate": 9.843394796861983e-07, "loss": 0.9752, "step": 14756 }, { "epoch": 0.8619742990654206, "grad_norm": 1.1613858938217163, "learning_rate": 9.835211517433042e-07, "loss": 0.8189, "step": 14757 }, { "epoch": 0.8620327102803739, "grad_norm": 1.2729127407073975, "learning_rate": 9.827031465061165e-07, "loss": 0.6442, "step": 14758 }, { "epoch": 0.8620911214953271, "grad_norm": 0.791449248790741, "learning_rate": 9.818854640039134e-07, "loss": 0.6073, "step": 14759 }, { "epoch": 0.8621495327102804, "grad_norm": 0.9053583145141602, "learning_rate": 9.810681042659598e-07, "loss": 0.6473, "step": 14760 }, { "epoch": 0.8622079439252337, "grad_norm": 2.5988380908966064, "learning_rate": 9.802510673215083e-07, "loss": 0.8631, "step": 14761 }, { "epoch": 0.8622663551401869, "grad_norm": 1.2679574489593506, "learning_rate": 9.794343531998008e-07, "loss": 0.7061, "step": 14762 }, { "epoch": 0.8623247663551402, "grad_norm": 1.0871641635894775, "learning_rate": 9.786179619300685e-07, "loss": 0.6165, "step": 14763 }, { "epoch": 0.8623831775700934, "grad_norm": 1.1731898784637451, "learning_rate": 9.778018935415333e-07, "loss": 0.7632, "step": 14764 }, { "epoch": 0.8624415887850467, "grad_norm": 0.9859402179718018, "learning_rate": 9.76986148063398e-07, "loss": 0.7823, "step": 14765 }, { "epoch": 0.8625, "grad_norm": 1.153551459312439, "learning_rate": 9.761707255248643e-07, "loss": 0.6785, "step": 14766 }, { "epoch": 0.8625584112149532, "grad_norm": 0.9675017595291138, "learning_rate": 9.75355625955111e-07, "loss": 0.801, "step": 14767 }, { "epoch": 0.8626168224299066, "grad_norm": 1.1164551973342896, "learning_rate": 9.745408493833131e-07, "loss": 0.8627, "step": 14768 }, { "epoch": 0.8626752336448598, "grad_norm": 0.9964213371276855, "learning_rate": 9.737263958386357e-07, "loss": 0.826, "step": 14769 }, { "epoch": 0.8627336448598131, "grad_norm": 0.9668107032775879, "learning_rate": 9.72912265350222e-07, "loss": 0.733, "step": 14770 }, { "epoch": 0.8627920560747664, "grad_norm": 1.0639592409133911, "learning_rate": 9.72098457947217e-07, "loss": 0.746, "step": 14771 }, { "epoch": 0.8628504672897196, "grad_norm": 1.1125696897506714, "learning_rate": 9.712849736587415e-07, "loss": 0.7316, "step": 14772 }, { "epoch": 0.8629088785046729, "grad_norm": 1.0206661224365234, "learning_rate": 9.704718125139157e-07, "loss": 0.6894, "step": 14773 }, { "epoch": 0.8629672897196262, "grad_norm": 1.0108429193496704, "learning_rate": 9.696589745418383e-07, "loss": 0.7911, "step": 14774 }, { "epoch": 0.8630257009345794, "grad_norm": 1.15219247341156, "learning_rate": 9.68846459771604e-07, "loss": 0.7129, "step": 14775 }, { "epoch": 0.8630841121495327, "grad_norm": 1.0064417123794556, "learning_rate": 9.680342682322953e-07, "loss": 0.5338, "step": 14776 }, { "epoch": 0.8631425233644859, "grad_norm": 1.0790879726409912, "learning_rate": 9.67222399952976e-07, "loss": 0.7367, "step": 14777 }, { "epoch": 0.8632009345794392, "grad_norm": 0.9992991089820862, "learning_rate": 9.664108549627094e-07, "loss": 0.7224, "step": 14778 }, { "epoch": 0.8632593457943926, "grad_norm": 1.7396320104599, "learning_rate": 9.655996332905348e-07, "loss": 0.6172, "step": 14779 }, { "epoch": 0.8633177570093458, "grad_norm": 1.2229030132293701, "learning_rate": 9.647887349654906e-07, "loss": 0.744, "step": 14780 }, { "epoch": 0.8633761682242991, "grad_norm": 1.057755470275879, "learning_rate": 9.639781600166e-07, "loss": 0.7802, "step": 14781 }, { "epoch": 0.8634345794392523, "grad_norm": 1.4785887002944946, "learning_rate": 9.631679084728695e-07, "loss": 0.8912, "step": 14782 }, { "epoch": 0.8634929906542056, "grad_norm": 1.1205275058746338, "learning_rate": 9.623579803633042e-07, "loss": 0.7173, "step": 14783 }, { "epoch": 0.8635514018691589, "grad_norm": 1.2599780559539795, "learning_rate": 9.615483757168887e-07, "loss": 0.7319, "step": 14784 }, { "epoch": 0.8636098130841121, "grad_norm": 0.9401422142982483, "learning_rate": 9.60739094562596e-07, "loss": 0.5219, "step": 14785 }, { "epoch": 0.8636682242990654, "grad_norm": 1.253503441810608, "learning_rate": 9.59930136929399e-07, "loss": 0.7597, "step": 14786 }, { "epoch": 0.8637266355140187, "grad_norm": 0.9284231066703796, "learning_rate": 9.59121502846243e-07, "loss": 0.6709, "step": 14787 }, { "epoch": 0.8637850467289719, "grad_norm": 0.9673981666564941, "learning_rate": 9.583131923420764e-07, "loss": 0.6605, "step": 14788 }, { "epoch": 0.8638434579439253, "grad_norm": 1.0158945322036743, "learning_rate": 9.575052054458244e-07, "loss": 0.7012, "step": 14789 }, { "epoch": 0.8639018691588785, "grad_norm": 1.4547260999679565, "learning_rate": 9.566975421864055e-07, "loss": 0.835, "step": 14790 }, { "epoch": 0.8639602803738318, "grad_norm": 1.1623432636260986, "learning_rate": 9.558902025927275e-07, "loss": 0.8228, "step": 14791 }, { "epoch": 0.8640186915887851, "grad_norm": 1.1554133892059326, "learning_rate": 9.55083186693686e-07, "loss": 0.74, "step": 14792 }, { "epoch": 0.8640771028037383, "grad_norm": 0.8862192034721375, "learning_rate": 9.54276494518166e-07, "loss": 0.7388, "step": 14793 }, { "epoch": 0.8641355140186916, "grad_norm": 0.998997151851654, "learning_rate": 9.534701260950385e-07, "loss": 0.6306, "step": 14794 }, { "epoch": 0.8641939252336449, "grad_norm": 0.9488519430160522, "learning_rate": 9.526640814531607e-07, "loss": 0.7614, "step": 14795 }, { "epoch": 0.8642523364485981, "grad_norm": 0.9241781234741211, "learning_rate": 9.518583606213849e-07, "loss": 0.7133, "step": 14796 }, { "epoch": 0.8643107476635514, "grad_norm": 1.0618243217468262, "learning_rate": 9.510529636285471e-07, "loss": 0.7713, "step": 14797 }, { "epoch": 0.8643691588785046, "grad_norm": 1.598375678062439, "learning_rate": 9.502478905034751e-07, "loss": 0.8247, "step": 14798 }, { "epoch": 0.8644275700934579, "grad_norm": 1.2840800285339355, "learning_rate": 9.494431412749816e-07, "loss": 0.8466, "step": 14799 }, { "epoch": 0.8644859813084113, "grad_norm": 1.1393038034439087, "learning_rate": 9.48638715971868e-07, "loss": 0.7464, "step": 14800 }, { "epoch": 0.8645443925233645, "grad_norm": 0.9408765435218811, "learning_rate": 9.478346146229255e-07, "loss": 0.64, "step": 14801 }, { "epoch": 0.8646028037383178, "grad_norm": 0.9617988467216492, "learning_rate": 9.470308372569337e-07, "loss": 0.8526, "step": 14802 }, { "epoch": 0.864661214953271, "grad_norm": 1.3596936464309692, "learning_rate": 9.462273839026625e-07, "loss": 0.955, "step": 14803 }, { "epoch": 0.8647196261682243, "grad_norm": 1.332808494567871, "learning_rate": 9.45424254588867e-07, "loss": 0.743, "step": 14804 }, { "epoch": 0.8647780373831776, "grad_norm": 0.8602466583251953, "learning_rate": 9.446214493442884e-07, "loss": 0.5956, "step": 14805 }, { "epoch": 0.8648364485981308, "grad_norm": 1.0957342386245728, "learning_rate": 9.43818968197664e-07, "loss": 0.7701, "step": 14806 }, { "epoch": 0.8648948598130841, "grad_norm": 1.0420492887496948, "learning_rate": 9.430168111777117e-07, "loss": 0.6561, "step": 14807 }, { "epoch": 0.8649532710280374, "grad_norm": 1.3089295625686646, "learning_rate": 9.422149783131429e-07, "loss": 0.836, "step": 14808 }, { "epoch": 0.8650116822429906, "grad_norm": 0.9880345463752747, "learning_rate": 9.414134696326571e-07, "loss": 0.6393, "step": 14809 }, { "epoch": 0.865070093457944, "grad_norm": 3.307985544204712, "learning_rate": 9.40612285164938e-07, "loss": 0.7125, "step": 14810 }, { "epoch": 0.8651285046728971, "grad_norm": 1.0916264057159424, "learning_rate": 9.398114249386636e-07, "loss": 0.8339, "step": 14811 }, { "epoch": 0.8651869158878505, "grad_norm": 0.8192001581192017, "learning_rate": 9.390108889824933e-07, "loss": 0.7254, "step": 14812 }, { "epoch": 0.8652453271028038, "grad_norm": 1.1520577669143677, "learning_rate": 9.382106773250821e-07, "loss": 0.6694, "step": 14813 }, { "epoch": 0.865303738317757, "grad_norm": 1.053353190422058, "learning_rate": 9.374107899950691e-07, "loss": 0.8058, "step": 14814 }, { "epoch": 0.8653621495327103, "grad_norm": 0.8655158281326294, "learning_rate": 9.366112270210826e-07, "loss": 0.612, "step": 14815 }, { "epoch": 0.8654205607476636, "grad_norm": 1.1237820386886597, "learning_rate": 9.358119884317395e-07, "loss": 0.7423, "step": 14816 }, { "epoch": 0.8654789719626168, "grad_norm": 0.8716915249824524, "learning_rate": 9.350130742556452e-07, "loss": 0.8002, "step": 14817 }, { "epoch": 0.8655373831775701, "grad_norm": 0.992163360118866, "learning_rate": 9.342144845213919e-07, "loss": 0.6895, "step": 14818 }, { "epoch": 0.8655957943925233, "grad_norm": 1.0273044109344482, "learning_rate": 9.334162192575658e-07, "loss": 0.7818, "step": 14819 }, { "epoch": 0.8656542056074766, "grad_norm": 1.2273008823394775, "learning_rate": 9.326182784927329e-07, "loss": 1.0704, "step": 14820 }, { "epoch": 0.86571261682243, "grad_norm": 1.4341720342636108, "learning_rate": 9.318206622554549e-07, "loss": 0.7911, "step": 14821 }, { "epoch": 0.8657710280373832, "grad_norm": 1.2249162197113037, "learning_rate": 9.310233705742777e-07, "loss": 0.6686, "step": 14822 }, { "epoch": 0.8658294392523365, "grad_norm": 1.1606581211090088, "learning_rate": 9.302264034777353e-07, "loss": 0.7001, "step": 14823 }, { "epoch": 0.8658878504672897, "grad_norm": 1.0581461191177368, "learning_rate": 9.294297609943537e-07, "loss": 0.7005, "step": 14824 }, { "epoch": 0.865946261682243, "grad_norm": 1.1069668531417847, "learning_rate": 9.286334431526456e-07, "loss": 0.8444, "step": 14825 }, { "epoch": 0.8660046728971963, "grad_norm": 0.9125787615776062, "learning_rate": 9.278374499811116e-07, "loss": 0.7413, "step": 14826 }, { "epoch": 0.8660630841121495, "grad_norm": 1.2035541534423828, "learning_rate": 9.270417815082411e-07, "loss": 0.7766, "step": 14827 }, { "epoch": 0.8661214953271028, "grad_norm": 0.9400492310523987, "learning_rate": 9.262464377625091e-07, "loss": 0.6526, "step": 14828 }, { "epoch": 0.8661799065420561, "grad_norm": 0.9306803345680237, "learning_rate": 9.254514187723829e-07, "loss": 0.7288, "step": 14829 }, { "epoch": 0.8662383177570093, "grad_norm": 1.257590413093567, "learning_rate": 9.246567245663174e-07, "loss": 0.7809, "step": 14830 }, { "epoch": 0.8662967289719626, "grad_norm": 1.0091816186904907, "learning_rate": 9.238623551727566e-07, "loss": 0.6295, "step": 14831 }, { "epoch": 0.8663551401869158, "grad_norm": 1.3150914907455444, "learning_rate": 9.230683106201299e-07, "loss": 0.6331, "step": 14832 }, { "epoch": 0.8664135514018692, "grad_norm": 1.9333611726760864, "learning_rate": 9.222745909368546e-07, "loss": 0.7738, "step": 14833 }, { "epoch": 0.8664719626168225, "grad_norm": 1.1486153602600098, "learning_rate": 9.214811961513404e-07, "loss": 0.868, "step": 14834 }, { "epoch": 0.8665303738317757, "grad_norm": 1.0298465490341187, "learning_rate": 9.206881262919831e-07, "loss": 0.7519, "step": 14835 }, { "epoch": 0.866588785046729, "grad_norm": 1.1115143299102783, "learning_rate": 9.198953813871692e-07, "loss": 0.8157, "step": 14836 }, { "epoch": 0.8666471962616823, "grad_norm": 1.2644879817962646, "learning_rate": 9.191029614652702e-07, "loss": 0.9004, "step": 14837 }, { "epoch": 0.8667056074766355, "grad_norm": 0.99097740650177, "learning_rate": 9.183108665546458e-07, "loss": 0.788, "step": 14838 }, { "epoch": 0.8667640186915888, "grad_norm": 1.1619313955307007, "learning_rate": 9.175190966836478e-07, "loss": 0.9109, "step": 14839 }, { "epoch": 0.866822429906542, "grad_norm": 1.3413727283477783, "learning_rate": 9.167276518806112e-07, "loss": 0.9475, "step": 14840 }, { "epoch": 0.8668808411214953, "grad_norm": 1.0241758823394775, "learning_rate": 9.159365321738655e-07, "loss": 0.7336, "step": 14841 }, { "epoch": 0.8669392523364486, "grad_norm": 1.0370100736618042, "learning_rate": 9.15145737591725e-07, "loss": 0.7878, "step": 14842 }, { "epoch": 0.8669976635514018, "grad_norm": 0.9277951121330261, "learning_rate": 9.143552681624901e-07, "loss": 0.7048, "step": 14843 }, { "epoch": 0.8670560747663552, "grad_norm": 0.8956868648529053, "learning_rate": 9.135651239144561e-07, "loss": 0.6814, "step": 14844 }, { "epoch": 0.8671144859813084, "grad_norm": 1.0514544248580933, "learning_rate": 9.127753048758992e-07, "loss": 0.7892, "step": 14845 }, { "epoch": 0.8671728971962617, "grad_norm": 1.0536738634109497, "learning_rate": 9.119858110750889e-07, "loss": 0.6389, "step": 14846 }, { "epoch": 0.867231308411215, "grad_norm": 0.9705331325531006, "learning_rate": 9.11196642540284e-07, "loss": 0.8673, "step": 14847 }, { "epoch": 0.8672897196261682, "grad_norm": 1.6519724130630493, "learning_rate": 9.104077992997251e-07, "loss": 0.6342, "step": 14848 }, { "epoch": 0.8673481308411215, "grad_norm": 1.193011999130249, "learning_rate": 9.096192813816495e-07, "loss": 0.8399, "step": 14849 }, { "epoch": 0.8674065420560748, "grad_norm": 1.1498866081237793, "learning_rate": 9.088310888142748e-07, "loss": 0.7017, "step": 14850 }, { "epoch": 0.867464953271028, "grad_norm": 1.2294062376022339, "learning_rate": 9.080432216258139e-07, "loss": 0.7962, "step": 14851 }, { "epoch": 0.8675233644859813, "grad_norm": 0.9582120180130005, "learning_rate": 9.072556798444654e-07, "loss": 0.7094, "step": 14852 }, { "epoch": 0.8675817757009345, "grad_norm": 1.3158038854599, "learning_rate": 9.064684634984123e-07, "loss": 0.5614, "step": 14853 }, { "epoch": 0.8676401869158878, "grad_norm": 1.3165236711502075, "learning_rate": 9.056815726158352e-07, "loss": 0.6752, "step": 14854 }, { "epoch": 0.8676985981308412, "grad_norm": 1.0035444498062134, "learning_rate": 9.048950072248907e-07, "loss": 0.662, "step": 14855 }, { "epoch": 0.8677570093457944, "grad_norm": 1.6128895282745361, "learning_rate": 9.041087673537375e-07, "loss": 0.9223, "step": 14856 }, { "epoch": 0.8678154205607477, "grad_norm": 1.0981734991073608, "learning_rate": 9.033228530305094e-07, "loss": 0.706, "step": 14857 }, { "epoch": 0.867873831775701, "grad_norm": 1.0056921243667603, "learning_rate": 9.025372642833374e-07, "loss": 0.7291, "step": 14858 }, { "epoch": 0.8679322429906542, "grad_norm": 1.0213596820831299, "learning_rate": 9.017520011403413e-07, "loss": 0.8119, "step": 14859 }, { "epoch": 0.8679906542056075, "grad_norm": 0.9096794724464417, "learning_rate": 9.009670636296209e-07, "loss": 0.6609, "step": 14860 }, { "epoch": 0.8680490654205607, "grad_norm": 1.124125599861145, "learning_rate": 9.001824517792734e-07, "loss": 0.6571, "step": 14861 }, { "epoch": 0.868107476635514, "grad_norm": 2.770235776901245, "learning_rate": 8.993981656173778e-07, "loss": 0.6573, "step": 14862 }, { "epoch": 0.8681658878504673, "grad_norm": 0.9566443562507629, "learning_rate": 8.98614205172006e-07, "loss": 0.6879, "step": 14863 }, { "epoch": 0.8682242990654205, "grad_norm": 1.4862806797027588, "learning_rate": 8.978305704712164e-07, "loss": 0.7301, "step": 14864 }, { "epoch": 0.8682827102803738, "grad_norm": 0.9662801623344421, "learning_rate": 8.970472615430548e-07, "loss": 0.7878, "step": 14865 }, { "epoch": 0.868341121495327, "grad_norm": 1.0862699747085571, "learning_rate": 8.962642784155596e-07, "loss": 0.777, "step": 14866 }, { "epoch": 0.8683995327102804, "grad_norm": 2.135540008544922, "learning_rate": 8.954816211167483e-07, "loss": 0.9472, "step": 14867 }, { "epoch": 0.8684579439252337, "grad_norm": 1.959455966949463, "learning_rate": 8.946992896746375e-07, "loss": 0.8196, "step": 14868 }, { "epoch": 0.8685163551401869, "grad_norm": 1.008674144744873, "learning_rate": 8.939172841172272e-07, "loss": 0.7656, "step": 14869 }, { "epoch": 0.8685747663551402, "grad_norm": 0.9193459153175354, "learning_rate": 8.931356044725026e-07, "loss": 0.5341, "step": 14870 }, { "epoch": 0.8686331775700935, "grad_norm": 1.0972304344177246, "learning_rate": 8.923542507684446e-07, "loss": 0.792, "step": 14871 }, { "epoch": 0.8686915887850467, "grad_norm": 1.1137739419937134, "learning_rate": 8.915732230330165e-07, "loss": 0.9063, "step": 14872 }, { "epoch": 0.86875, "grad_norm": 1.3526055812835693, "learning_rate": 8.907925212941692e-07, "loss": 0.7887, "step": 14873 }, { "epoch": 0.8688084112149532, "grad_norm": 1.082840085029602, "learning_rate": 8.900121455798472e-07, "loss": 0.7395, "step": 14874 }, { "epoch": 0.8688668224299065, "grad_norm": 1.4331815242767334, "learning_rate": 8.892320959179823e-07, "loss": 0.7929, "step": 14875 }, { "epoch": 0.8689252336448599, "grad_norm": 1.0504674911499023, "learning_rate": 8.884523723364902e-07, "loss": 0.7403, "step": 14876 }, { "epoch": 0.868983644859813, "grad_norm": 3.401460647583008, "learning_rate": 8.876729748632796e-07, "loss": 0.8429, "step": 14877 }, { "epoch": 0.8690420560747664, "grad_norm": 0.7937279939651489, "learning_rate": 8.868939035262436e-07, "loss": 0.6369, "step": 14878 }, { "epoch": 0.8691004672897197, "grad_norm": 1.5087467432022095, "learning_rate": 8.861151583532657e-07, "loss": 0.8165, "step": 14879 }, { "epoch": 0.8691588785046729, "grad_norm": 0.9465567469596863, "learning_rate": 8.853367393722212e-07, "loss": 0.7001, "step": 14880 }, { "epoch": 0.8692172897196262, "grad_norm": 1.2782865762710571, "learning_rate": 8.845586466109657e-07, "loss": 0.7537, "step": 14881 }, { "epoch": 0.8692757009345794, "grad_norm": 0.9935147166252136, "learning_rate": 8.837808800973524e-07, "loss": 0.8204, "step": 14882 }, { "epoch": 0.8693341121495327, "grad_norm": 1.2261103391647339, "learning_rate": 8.830034398592125e-07, "loss": 0.7362, "step": 14883 }, { "epoch": 0.869392523364486, "grad_norm": 1.266283631324768, "learning_rate": 8.822263259243747e-07, "loss": 0.6948, "step": 14884 }, { "epoch": 0.8694509345794392, "grad_norm": 1.0338228940963745, "learning_rate": 8.814495383206534e-07, "loss": 0.8914, "step": 14885 }, { "epoch": 0.8695093457943925, "grad_norm": 1.035132884979248, "learning_rate": 8.806730770758465e-07, "loss": 0.7022, "step": 14886 }, { "epoch": 0.8695677570093457, "grad_norm": 0.9348704814910889, "learning_rate": 8.798969422177495e-07, "loss": 0.6036, "step": 14887 }, { "epoch": 0.8696261682242991, "grad_norm": 0.7874818444252014, "learning_rate": 8.791211337741345e-07, "loss": 0.6321, "step": 14888 }, { "epoch": 0.8696845794392524, "grad_norm": 1.0667940378189087, "learning_rate": 8.783456517727729e-07, "loss": 0.7264, "step": 14889 }, { "epoch": 0.8697429906542056, "grad_norm": 0.8400567770004272, "learning_rate": 8.775704962414167e-07, "loss": 0.5381, "step": 14890 }, { "epoch": 0.8698014018691589, "grad_norm": 0.8212077617645264, "learning_rate": 8.767956672078104e-07, "loss": 0.718, "step": 14891 }, { "epoch": 0.8698598130841122, "grad_norm": 1.4688986539840698, "learning_rate": 8.760211646996874e-07, "loss": 0.7133, "step": 14892 }, { "epoch": 0.8699182242990654, "grad_norm": 1.4580103158950806, "learning_rate": 8.752469887447645e-07, "loss": 0.7568, "step": 14893 }, { "epoch": 0.8699766355140187, "grad_norm": 1.0618643760681152, "learning_rate": 8.744731393707528e-07, "loss": 0.8706, "step": 14894 }, { "epoch": 0.8700350467289719, "grad_norm": 1.2024037837982178, "learning_rate": 8.736996166053469e-07, "loss": 0.6907, "step": 14895 }, { "epoch": 0.8700934579439252, "grad_norm": 1.0083508491516113, "learning_rate": 8.729264204762311e-07, "loss": 0.709, "step": 14896 }, { "epoch": 0.8701518691588785, "grad_norm": 1.0775294303894043, "learning_rate": 8.721535510110823e-07, "loss": 0.6281, "step": 14897 }, { "epoch": 0.8702102803738317, "grad_norm": 1.4998786449432373, "learning_rate": 8.713810082375573e-07, "loss": 0.9228, "step": 14898 }, { "epoch": 0.8702686915887851, "grad_norm": 6.66680908203125, "learning_rate": 8.706087921833106e-07, "loss": 0.7812, "step": 14899 }, { "epoch": 0.8703271028037384, "grad_norm": 0.8744029402732849, "learning_rate": 8.698369028759767e-07, "loss": 0.5823, "step": 14900 }, { "epoch": 0.8703855140186916, "grad_norm": 1.2519195079803467, "learning_rate": 8.690653403431826e-07, "loss": 0.6659, "step": 14901 }, { "epoch": 0.8704439252336449, "grad_norm": 1.3062193393707275, "learning_rate": 8.682941046125448e-07, "loss": 0.7005, "step": 14902 }, { "epoch": 0.8705023364485981, "grad_norm": 1.196333408355713, "learning_rate": 8.675231957116647e-07, "loss": 0.6707, "step": 14903 }, { "epoch": 0.8705607476635514, "grad_norm": 0.9096260070800781, "learning_rate": 8.667526136681348e-07, "loss": 0.7337, "step": 14904 }, { "epoch": 0.8706191588785047, "grad_norm": 2.2830960750579834, "learning_rate": 8.65982358509535e-07, "loss": 0.8766, "step": 14905 }, { "epoch": 0.8706775700934579, "grad_norm": 1.0144498348236084, "learning_rate": 8.65212430263429e-07, "loss": 0.5576, "step": 14906 }, { "epoch": 0.8707359813084112, "grad_norm": 1.516329050064087, "learning_rate": 8.644428289573781e-07, "loss": 0.6972, "step": 14907 }, { "epoch": 0.8707943925233644, "grad_norm": 1.0707160234451294, "learning_rate": 8.636735546189245e-07, "loss": 0.8175, "step": 14908 }, { "epoch": 0.8708528037383177, "grad_norm": 1.135017991065979, "learning_rate": 8.629046072756031e-07, "loss": 0.8315, "step": 14909 }, { "epoch": 0.8709112149532711, "grad_norm": 1.1944026947021484, "learning_rate": 8.621359869549339e-07, "loss": 0.7903, "step": 14910 }, { "epoch": 0.8709696261682243, "grad_norm": 0.9573450088500977, "learning_rate": 8.613676936844239e-07, "loss": 0.7493, "step": 14911 }, { "epoch": 0.8710280373831776, "grad_norm": 1.1135365962982178, "learning_rate": 8.605997274915734e-07, "loss": 0.6676, "step": 14912 }, { "epoch": 0.8710864485981309, "grad_norm": 1.2540369033813477, "learning_rate": 8.59832088403868e-07, "loss": 0.6667, "step": 14913 }, { "epoch": 0.8711448598130841, "grad_norm": 2.372494697570801, "learning_rate": 8.590647764487825e-07, "loss": 0.9144, "step": 14914 }, { "epoch": 0.8712032710280374, "grad_norm": 1.2974218130111694, "learning_rate": 8.582977916537805e-07, "loss": 0.7019, "step": 14915 }, { "epoch": 0.8712616822429906, "grad_norm": 1.2571041584014893, "learning_rate": 8.575311340463088e-07, "loss": 0.782, "step": 14916 }, { "epoch": 0.8713200934579439, "grad_norm": 1.076600193977356, "learning_rate": 8.56764803653809e-07, "loss": 0.6713, "step": 14917 }, { "epoch": 0.8713785046728972, "grad_norm": 0.9613196849822998, "learning_rate": 8.55998800503709e-07, "loss": 0.7569, "step": 14918 }, { "epoch": 0.8714369158878504, "grad_norm": 1.0550302267074585, "learning_rate": 8.552331246234257e-07, "loss": 0.7836, "step": 14919 }, { "epoch": 0.8714953271028038, "grad_norm": 1.1155418157577515, "learning_rate": 8.544677760403619e-07, "loss": 0.7382, "step": 14920 }, { "epoch": 0.871553738317757, "grad_norm": 2.1770899295806885, "learning_rate": 8.537027547819077e-07, "loss": 0.7679, "step": 14921 }, { "epoch": 0.8716121495327103, "grad_norm": 1.1841251850128174, "learning_rate": 8.529380608754478e-07, "loss": 0.6991, "step": 14922 }, { "epoch": 0.8716705607476636, "grad_norm": 1.278114914894104, "learning_rate": 8.52173694348346e-07, "loss": 0.8107, "step": 14923 }, { "epoch": 0.8717289719626168, "grad_norm": 1.2309069633483887, "learning_rate": 8.514096552279638e-07, "loss": 0.825, "step": 14924 }, { "epoch": 0.8717873831775701, "grad_norm": 1.4122542142868042, "learning_rate": 8.506459435416469e-07, "loss": 0.7559, "step": 14925 }, { "epoch": 0.8718457943925234, "grad_norm": 1.6065138578414917, "learning_rate": 8.498825593167259e-07, "loss": 0.7512, "step": 14926 }, { "epoch": 0.8719042056074766, "grad_norm": 1.1041725873947144, "learning_rate": 8.491195025805254e-07, "loss": 0.7343, "step": 14927 }, { "epoch": 0.8719626168224299, "grad_norm": 2.6165566444396973, "learning_rate": 8.483567733603538e-07, "loss": 0.6229, "step": 14928 }, { "epoch": 0.8720210280373831, "grad_norm": 1.0411338806152344, "learning_rate": 8.4759437168351e-07, "loss": 0.7944, "step": 14929 }, { "epoch": 0.8720794392523364, "grad_norm": 1.0051168203353882, "learning_rate": 8.468322975772836e-07, "loss": 0.805, "step": 14930 }, { "epoch": 0.8721378504672898, "grad_norm": 1.198315978050232, "learning_rate": 8.46070551068946e-07, "loss": 0.7495, "step": 14931 }, { "epoch": 0.872196261682243, "grad_norm": 1.1751432418823242, "learning_rate": 8.453091321857642e-07, "loss": 0.5515, "step": 14932 }, { "epoch": 0.8722546728971963, "grad_norm": 1.0411978960037231, "learning_rate": 8.445480409549855e-07, "loss": 0.7456, "step": 14933 }, { "epoch": 0.8723130841121496, "grad_norm": 1.0550459623336792, "learning_rate": 8.437872774038525e-07, "loss": 0.8417, "step": 14934 }, { "epoch": 0.8723714953271028, "grad_norm": 1.6869804859161377, "learning_rate": 8.430268415595943e-07, "loss": 0.8719, "step": 14935 }, { "epoch": 0.8724299065420561, "grad_norm": 1.029304027557373, "learning_rate": 8.42266733449425e-07, "loss": 0.703, "step": 14936 }, { "epoch": 0.8724883177570093, "grad_norm": 1.1208786964416504, "learning_rate": 8.415069531005526e-07, "loss": 0.8386, "step": 14937 }, { "epoch": 0.8725467289719626, "grad_norm": 1.172155499458313, "learning_rate": 8.407475005401689e-07, "loss": 0.7349, "step": 14938 }, { "epoch": 0.8726051401869159, "grad_norm": 1.2461942434310913, "learning_rate": 8.399883757954507e-07, "loss": 0.8644, "step": 14939 }, { "epoch": 0.8726635514018691, "grad_norm": 1.0443388223648071, "learning_rate": 8.392295788935734e-07, "loss": 0.8928, "step": 14940 }, { "epoch": 0.8727219626168224, "grad_norm": 0.9963073134422302, "learning_rate": 8.384711098616916e-07, "loss": 0.9999, "step": 14941 }, { "epoch": 0.8727803738317756, "grad_norm": 0.9668946266174316, "learning_rate": 8.377129687269548e-07, "loss": 0.5834, "step": 14942 }, { "epoch": 0.872838785046729, "grad_norm": 1.3145753145217896, "learning_rate": 8.369551555164945e-07, "loss": 0.5934, "step": 14943 }, { "epoch": 0.8728971962616823, "grad_norm": 1.434402346611023, "learning_rate": 8.361976702574326e-07, "loss": 0.6655, "step": 14944 }, { "epoch": 0.8729556074766355, "grad_norm": 1.0166513919830322, "learning_rate": 8.354405129768817e-07, "loss": 0.7246, "step": 14945 }, { "epoch": 0.8730140186915888, "grad_norm": 1.15591299533844, "learning_rate": 8.346836837019412e-07, "loss": 0.7063, "step": 14946 }, { "epoch": 0.8730724299065421, "grad_norm": 1.0810588598251343, "learning_rate": 8.339271824596984e-07, "loss": 0.7063, "step": 14947 }, { "epoch": 0.8731308411214953, "grad_norm": 1.5168025493621826, "learning_rate": 8.331710092772294e-07, "loss": 0.7445, "step": 14948 }, { "epoch": 0.8731892523364486, "grad_norm": 1.1225996017456055, "learning_rate": 8.324151641815958e-07, "loss": 0.691, "step": 14949 }, { "epoch": 0.8732476635514018, "grad_norm": 1.2035589218139648, "learning_rate": 8.316596471998506e-07, "loss": 0.8746, "step": 14950 }, { "epoch": 0.8733060747663551, "grad_norm": 1.0480080842971802, "learning_rate": 8.309044583590353e-07, "loss": 0.9395, "step": 14951 }, { "epoch": 0.8733644859813084, "grad_norm": 1.2340948581695557, "learning_rate": 8.301495976861795e-07, "loss": 0.6799, "step": 14952 }, { "epoch": 0.8734228971962616, "grad_norm": 1.183284878730774, "learning_rate": 8.293950652082994e-07, "loss": 0.6412, "step": 14953 }, { "epoch": 0.873481308411215, "grad_norm": 1.0984035730361938, "learning_rate": 8.286408609523977e-07, "loss": 0.8351, "step": 14954 }, { "epoch": 0.8735397196261683, "grad_norm": 0.8654460906982422, "learning_rate": 8.278869849454718e-07, "loss": 0.6449, "step": 14955 }, { "epoch": 0.8735981308411215, "grad_norm": 0.7838064432144165, "learning_rate": 8.27133437214499e-07, "loss": 0.5726, "step": 14956 }, { "epoch": 0.8736565420560748, "grad_norm": 1.1406182050704956, "learning_rate": 8.263802177864522e-07, "loss": 0.9463, "step": 14957 }, { "epoch": 0.873714953271028, "grad_norm": 1.2889599800109863, "learning_rate": 8.256273266882919e-07, "loss": 0.7167, "step": 14958 }, { "epoch": 0.8737733644859813, "grad_norm": 0.8987367749214172, "learning_rate": 8.24874763946959e-07, "loss": 0.6789, "step": 14959 }, { "epoch": 0.8738317757009346, "grad_norm": 1.160323977470398, "learning_rate": 8.241225295893929e-07, "loss": 0.8157, "step": 14960 }, { "epoch": 0.8738901869158878, "grad_norm": 0.8026908040046692, "learning_rate": 8.233706236425132e-07, "loss": 0.6074, "step": 14961 }, { "epoch": 0.8739485981308411, "grad_norm": 1.191770315170288, "learning_rate": 8.226190461332328e-07, "loss": 0.6677, "step": 14962 }, { "epoch": 0.8740070093457943, "grad_norm": 1.0056785345077515, "learning_rate": 8.218677970884526e-07, "loss": 0.8059, "step": 14963 }, { "epoch": 0.8740654205607477, "grad_norm": 1.2362587451934814, "learning_rate": 8.211168765350563e-07, "loss": 0.6991, "step": 14964 }, { "epoch": 0.874123831775701, "grad_norm": 1.0126639604568481, "learning_rate": 8.20366284499925e-07, "loss": 0.7309, "step": 14965 }, { "epoch": 0.8741822429906542, "grad_norm": 1.5555305480957031, "learning_rate": 8.19616021009918e-07, "loss": 0.906, "step": 14966 }, { "epoch": 0.8742406542056075, "grad_norm": 0.8551458716392517, "learning_rate": 8.188660860918895e-07, "loss": 0.6494, "step": 14967 }, { "epoch": 0.8742990654205608, "grad_norm": 1.065011739730835, "learning_rate": 8.181164797726826e-07, "loss": 0.7399, "step": 14968 }, { "epoch": 0.874357476635514, "grad_norm": 1.0518397092819214, "learning_rate": 8.173672020791223e-07, "loss": 0.7333, "step": 14969 }, { "epoch": 0.8744158878504673, "grad_norm": 1.2811392545700073, "learning_rate": 8.166182530380295e-07, "loss": 0.8961, "step": 14970 }, { "epoch": 0.8744742990654205, "grad_norm": 1.3396573066711426, "learning_rate": 8.15869632676205e-07, "loss": 0.6993, "step": 14971 }, { "epoch": 0.8745327102803738, "grad_norm": 0.998997688293457, "learning_rate": 8.151213410204472e-07, "loss": 0.6813, "step": 14972 }, { "epoch": 0.8745911214953271, "grad_norm": 1.3235588073730469, "learning_rate": 8.143733780975349e-07, "loss": 0.6588, "step": 14973 }, { "epoch": 0.8746495327102803, "grad_norm": 0.9811797738075256, "learning_rate": 8.136257439342377e-07, "loss": 0.6903, "step": 14974 }, { "epoch": 0.8747079439252337, "grad_norm": 1.0380115509033203, "learning_rate": 8.128784385573174e-07, "loss": 0.7107, "step": 14975 }, { "epoch": 0.874766355140187, "grad_norm": 1.6508673429489136, "learning_rate": 8.121314619935172e-07, "loss": 0.8145, "step": 14976 }, { "epoch": 0.8748247663551402, "grad_norm": 1.0457926988601685, "learning_rate": 8.113848142695746e-07, "loss": 0.8161, "step": 14977 }, { "epoch": 0.8748831775700935, "grad_norm": 0.9980837106704712, "learning_rate": 8.106384954122093e-07, "loss": 0.7118, "step": 14978 }, { "epoch": 0.8749415887850467, "grad_norm": 1.0507062673568726, "learning_rate": 8.098925054481343e-07, "loss": 0.8698, "step": 14979 }, { "epoch": 0.875, "grad_norm": 1.8663352727890015, "learning_rate": 8.091468444040518e-07, "loss": 0.9124, "step": 14980 }, { "epoch": 0.8750584112149533, "grad_norm": 1.1280874013900757, "learning_rate": 8.084015123066446e-07, "loss": 0.7872, "step": 14981 }, { "epoch": 0.8751168224299065, "grad_norm": 1.2384992837905884, "learning_rate": 8.076565091825916e-07, "loss": 0.9002, "step": 14982 }, { "epoch": 0.8751752336448598, "grad_norm": 1.0283855199813843, "learning_rate": 8.069118350585558e-07, "loss": 0.7154, "step": 14983 }, { "epoch": 0.875233644859813, "grad_norm": 1.3946733474731445, "learning_rate": 8.061674899611893e-07, "loss": 0.7491, "step": 14984 }, { "epoch": 0.8752920560747663, "grad_norm": 1.145157814025879, "learning_rate": 8.054234739171352e-07, "loss": 0.7452, "step": 14985 }, { "epoch": 0.8753504672897197, "grad_norm": 0.9344159364700317, "learning_rate": 8.046797869530187e-07, "loss": 0.8005, "step": 14986 }, { "epoch": 0.8754088785046729, "grad_norm": 1.445095419883728, "learning_rate": 8.03936429095461e-07, "loss": 0.6815, "step": 14987 }, { "epoch": 0.8754672897196262, "grad_norm": 1.4412329196929932, "learning_rate": 8.031934003710639e-07, "loss": 0.8455, "step": 14988 }, { "epoch": 0.8755257009345795, "grad_norm": 0.8681256771087646, "learning_rate": 8.024507008064208e-07, "loss": 0.7108, "step": 14989 }, { "epoch": 0.8755841121495327, "grad_norm": 1.1180058717727661, "learning_rate": 8.017083304281159e-07, "loss": 0.7076, "step": 14990 }, { "epoch": 0.875642523364486, "grad_norm": 0.9909948110580444, "learning_rate": 8.009662892627179e-07, "loss": 0.7034, "step": 14991 }, { "epoch": 0.8757009345794392, "grad_norm": 1.5377085208892822, "learning_rate": 8.002245773367834e-07, "loss": 0.6663, "step": 14992 }, { "epoch": 0.8757593457943925, "grad_norm": 1.276975154876709, "learning_rate": 7.994831946768622e-07, "loss": 0.7596, "step": 14993 }, { "epoch": 0.8758177570093458, "grad_norm": 1.0305628776550293, "learning_rate": 7.987421413094854e-07, "loss": 0.8654, "step": 14994 }, { "epoch": 0.875876168224299, "grad_norm": 0.9965190291404724, "learning_rate": 7.980014172611772e-07, "loss": 0.7214, "step": 14995 }, { "epoch": 0.8759345794392523, "grad_norm": 1.1580078601837158, "learning_rate": 7.97261022558451e-07, "loss": 0.8089, "step": 14996 }, { "epoch": 0.8759929906542057, "grad_norm": 1.3943361043930054, "learning_rate": 7.96520957227801e-07, "loss": 0.7206, "step": 14997 }, { "epoch": 0.8760514018691589, "grad_norm": 1.5963282585144043, "learning_rate": 7.957812212957195e-07, "loss": 0.8165, "step": 14998 }, { "epoch": 0.8761098130841122, "grad_norm": 1.149296760559082, "learning_rate": 7.950418147886785e-07, "loss": 0.7255, "step": 14999 }, { "epoch": 0.8761682242990654, "grad_norm": 0.8763484954833984, "learning_rate": 7.943027377331436e-07, "loss": 0.703, "step": 15000 }, { "epoch": 0.8762266355140187, "grad_norm": 0.98543381690979, "learning_rate": 7.93563990155567e-07, "loss": 0.7637, "step": 15001 }, { "epoch": 0.876285046728972, "grad_norm": 1.0669232606887817, "learning_rate": 7.928255720823885e-07, "loss": 0.7495, "step": 15002 }, { "epoch": 0.8763434579439252, "grad_norm": 1.0350735187530518, "learning_rate": 7.920874835400372e-07, "loss": 0.5826, "step": 15003 }, { "epoch": 0.8764018691588785, "grad_norm": 1.4628428220748901, "learning_rate": 7.913497245549273e-07, "loss": 0.7182, "step": 15004 }, { "epoch": 0.8764602803738317, "grad_norm": 1.092499017715454, "learning_rate": 7.906122951534678e-07, "loss": 0.7741, "step": 15005 }, { "epoch": 0.876518691588785, "grad_norm": 1.0362036228179932, "learning_rate": 7.898751953620476e-07, "loss": 0.5893, "step": 15006 }, { "epoch": 0.8765771028037384, "grad_norm": 1.979213833808899, "learning_rate": 7.891384252070499e-07, "loss": 0.8355, "step": 15007 }, { "epoch": 0.8766355140186916, "grad_norm": 3.8406145572662354, "learning_rate": 7.884019847148461e-07, "loss": 0.6596, "step": 15008 }, { "epoch": 0.8766939252336449, "grad_norm": 1.2231944799423218, "learning_rate": 7.876658739117904e-07, "loss": 0.8437, "step": 15009 }, { "epoch": 0.8767523364485982, "grad_norm": 1.111066460609436, "learning_rate": 7.869300928242318e-07, "loss": 0.7441, "step": 15010 }, { "epoch": 0.8768107476635514, "grad_norm": 1.0390431880950928, "learning_rate": 7.861946414785015e-07, "loss": 0.7538, "step": 15011 }, { "epoch": 0.8768691588785047, "grad_norm": 1.1745834350585938, "learning_rate": 7.854595199009229e-07, "loss": 0.8044, "step": 15012 }, { "epoch": 0.8769275700934579, "grad_norm": 1.0372141599655151, "learning_rate": 7.847247281178083e-07, "loss": 0.6404, "step": 15013 }, { "epoch": 0.8769859813084112, "grad_norm": 1.0275439023971558, "learning_rate": 7.839902661554533e-07, "loss": 0.6772, "step": 15014 }, { "epoch": 0.8770443925233645, "grad_norm": 1.1066992282867432, "learning_rate": 7.83256134040149e-07, "loss": 0.6853, "step": 15015 }, { "epoch": 0.8771028037383177, "grad_norm": 1.0264551639556885, "learning_rate": 7.825223317981645e-07, "loss": 0.8313, "step": 15016 }, { "epoch": 0.877161214953271, "grad_norm": 0.8651648163795471, "learning_rate": 7.817888594557677e-07, "loss": 0.7509, "step": 15017 }, { "epoch": 0.8772196261682244, "grad_norm": 1.118173360824585, "learning_rate": 7.810557170392097e-07, "loss": 0.8727, "step": 15018 }, { "epoch": 0.8772780373831776, "grad_norm": 0.898032009601593, "learning_rate": 7.803229045747274e-07, "loss": 0.7218, "step": 15019 }, { "epoch": 0.8773364485981309, "grad_norm": 0.9275825619697571, "learning_rate": 7.79590422088552e-07, "loss": 0.6094, "step": 15020 }, { "epoch": 0.8773948598130841, "grad_norm": 1.1104811429977417, "learning_rate": 7.78858269606898e-07, "loss": 0.7059, "step": 15021 }, { "epoch": 0.8774532710280374, "grad_norm": 1.171589970588684, "learning_rate": 7.78126447155968e-07, "loss": 0.7195, "step": 15022 }, { "epoch": 0.8775116822429907, "grad_norm": 0.9906176924705505, "learning_rate": 7.773949547619564e-07, "loss": 0.7322, "step": 15023 }, { "epoch": 0.8775700934579439, "grad_norm": 1.054958701133728, "learning_rate": 7.766637924510423e-07, "loss": 0.6716, "step": 15024 }, { "epoch": 0.8776285046728972, "grad_norm": 1.2649613618850708, "learning_rate": 7.759329602493981e-07, "loss": 0.7852, "step": 15025 }, { "epoch": 0.8776869158878504, "grad_norm": 1.1754584312438965, "learning_rate": 7.752024581831774e-07, "loss": 0.6905, "step": 15026 }, { "epoch": 0.8777453271028037, "grad_norm": 1.3026095628738403, "learning_rate": 7.744722862785248e-07, "loss": 0.6564, "step": 15027 }, { "epoch": 0.877803738317757, "grad_norm": 1.1432820558547974, "learning_rate": 7.73742444561576e-07, "loss": 0.7976, "step": 15028 }, { "epoch": 0.8778621495327102, "grad_norm": 1.1513663530349731, "learning_rate": 7.730129330584502e-07, "loss": 0.6369, "step": 15029 }, { "epoch": 0.8779205607476636, "grad_norm": 1.0018855333328247, "learning_rate": 7.722837517952608e-07, "loss": 0.757, "step": 15030 }, { "epoch": 0.8779789719626169, "grad_norm": 1.191785454750061, "learning_rate": 7.715549007981026e-07, "loss": 0.926, "step": 15031 }, { "epoch": 0.8780373831775701, "grad_norm": 1.0003770589828491, "learning_rate": 7.708263800930616e-07, "loss": 0.74, "step": 15032 }, { "epoch": 0.8780957943925234, "grad_norm": 1.1647614240646362, "learning_rate": 7.700981897062121e-07, "loss": 0.8132, "step": 15033 }, { "epoch": 0.8781542056074766, "grad_norm": 1.0210458040237427, "learning_rate": 7.693703296636168e-07, "loss": 0.8137, "step": 15034 }, { "epoch": 0.8782126168224299, "grad_norm": 0.8951756954193115, "learning_rate": 7.686427999913282e-07, "loss": 0.7153, "step": 15035 }, { "epoch": 0.8782710280373832, "grad_norm": 1.0441619157791138, "learning_rate": 7.679156007153843e-07, "loss": 0.6918, "step": 15036 }, { "epoch": 0.8783294392523364, "grad_norm": 1.0596522092819214, "learning_rate": 7.671887318618099e-07, "loss": 0.7763, "step": 15037 }, { "epoch": 0.8783878504672897, "grad_norm": 1.2775585651397705, "learning_rate": 7.664621934566219e-07, "loss": 0.7754, "step": 15038 }, { "epoch": 0.878446261682243, "grad_norm": 1.5760639905929565, "learning_rate": 7.657359855258206e-07, "loss": 0.7067, "step": 15039 }, { "epoch": 0.8785046728971962, "grad_norm": 1.0613625049591064, "learning_rate": 7.650101080954031e-07, "loss": 0.7131, "step": 15040 }, { "epoch": 0.8785630841121496, "grad_norm": 1.1653097867965698, "learning_rate": 7.642845611913463e-07, "loss": 0.8241, "step": 15041 }, { "epoch": 0.8786214953271028, "grad_norm": 1.3354487419128418, "learning_rate": 7.635593448396161e-07, "loss": 0.7852, "step": 15042 }, { "epoch": 0.8786799065420561, "grad_norm": 1.2241969108581543, "learning_rate": 7.628344590661718e-07, "loss": 0.86, "step": 15043 }, { "epoch": 0.8787383177570094, "grad_norm": 1.071298360824585, "learning_rate": 7.621099038969537e-07, "loss": 0.7279, "step": 15044 }, { "epoch": 0.8787967289719626, "grad_norm": 1.3438831567764282, "learning_rate": 7.613856793578955e-07, "loss": 0.8148, "step": 15045 }, { "epoch": 0.8788551401869159, "grad_norm": 1.0597410202026367, "learning_rate": 7.606617854749209e-07, "loss": 0.7016, "step": 15046 }, { "epoch": 0.8789135514018691, "grad_norm": 1.122706413269043, "learning_rate": 7.599382222739349e-07, "loss": 0.7034, "step": 15047 }, { "epoch": 0.8789719626168224, "grad_norm": 1.0723766088485718, "learning_rate": 7.592149897808354e-07, "loss": 0.6224, "step": 15048 }, { "epoch": 0.8790303738317757, "grad_norm": 1.159414529800415, "learning_rate": 7.584920880215075e-07, "loss": 0.8582, "step": 15049 }, { "epoch": 0.8790887850467289, "grad_norm": 0.9492838382720947, "learning_rate": 7.577695170218225e-07, "loss": 0.6518, "step": 15050 }, { "epoch": 0.8791471962616823, "grad_norm": 1.199928879737854, "learning_rate": 7.570472768076464e-07, "loss": 0.7644, "step": 15051 }, { "epoch": 0.8792056074766356, "grad_norm": 1.0243054628372192, "learning_rate": 7.563253674048232e-07, "loss": 0.791, "step": 15052 }, { "epoch": 0.8792640186915888, "grad_norm": 1.368757724761963, "learning_rate": 7.556037888391943e-07, "loss": 0.7727, "step": 15053 }, { "epoch": 0.8793224299065421, "grad_norm": 1.1072964668273926, "learning_rate": 7.548825411365845e-07, "loss": 0.7002, "step": 15054 }, { "epoch": 0.8793808411214953, "grad_norm": 1.0137367248535156, "learning_rate": 7.541616243228056e-07, "loss": 0.7927, "step": 15055 }, { "epoch": 0.8794392523364486, "grad_norm": 0.8866426944732666, "learning_rate": 7.534410384236623e-07, "loss": 0.8178, "step": 15056 }, { "epoch": 0.8794976635514019, "grad_norm": 1.0349559783935547, "learning_rate": 7.527207834649431e-07, "loss": 0.7227, "step": 15057 }, { "epoch": 0.8795560747663551, "grad_norm": 1.0848596096038818, "learning_rate": 7.520008594724292e-07, "loss": 0.8617, "step": 15058 }, { "epoch": 0.8796144859813084, "grad_norm": 1.0015718936920166, "learning_rate": 7.512812664718849e-07, "loss": 0.8129, "step": 15059 }, { "epoch": 0.8796728971962616, "grad_norm": 1.157946228981018, "learning_rate": 7.505620044890638e-07, "loss": 0.8096, "step": 15060 }, { "epoch": 0.8797313084112149, "grad_norm": 0.935853898525238, "learning_rate": 7.498430735497097e-07, "loss": 0.6388, "step": 15061 }, { "epoch": 0.8797897196261683, "grad_norm": 1.0063995122909546, "learning_rate": 7.491244736795544e-07, "loss": 0.7186, "step": 15062 }, { "epoch": 0.8798481308411215, "grad_norm": 0.9385510683059692, "learning_rate": 7.484062049043184e-07, "loss": 0.6249, "step": 15063 }, { "epoch": 0.8799065420560748, "grad_norm": 1.0123759508132935, "learning_rate": 7.476882672497077e-07, "loss": 0.7142, "step": 15064 }, { "epoch": 0.8799649532710281, "grad_norm": 1.0221424102783203, "learning_rate": 7.469706607414151e-07, "loss": 0.6227, "step": 15065 }, { "epoch": 0.8800233644859813, "grad_norm": 1.618913173675537, "learning_rate": 7.462533854051268e-07, "loss": 0.8261, "step": 15066 }, { "epoch": 0.8800817757009346, "grad_norm": 1.0688806772232056, "learning_rate": 7.455364412665145e-07, "loss": 0.8235, "step": 15067 }, { "epoch": 0.8801401869158878, "grad_norm": 1.1024057865142822, "learning_rate": 7.448198283512398e-07, "loss": 0.6424, "step": 15068 }, { "epoch": 0.8801985981308411, "grad_norm": 0.8887762427330017, "learning_rate": 7.441035466849489e-07, "loss": 0.5717, "step": 15069 }, { "epoch": 0.8802570093457944, "grad_norm": 1.2286970615386963, "learning_rate": 7.433875962932757e-07, "loss": 0.8758, "step": 15070 }, { "epoch": 0.8803154205607476, "grad_norm": 1.0989537239074707, "learning_rate": 7.426719772018487e-07, "loss": 0.703, "step": 15071 }, { "epoch": 0.8803738317757009, "grad_norm": 1.1776264905929565, "learning_rate": 7.419566894362751e-07, "loss": 0.7155, "step": 15072 }, { "epoch": 0.8804322429906543, "grad_norm": 1.1298327445983887, "learning_rate": 7.412417330221622e-07, "loss": 0.7192, "step": 15073 }, { "epoch": 0.8804906542056075, "grad_norm": 1.013722538948059, "learning_rate": 7.405271079850951e-07, "loss": 0.797, "step": 15074 }, { "epoch": 0.8805490654205608, "grad_norm": 0.9317429065704346, "learning_rate": 7.3981281435065e-07, "loss": 0.6863, "step": 15075 }, { "epoch": 0.880607476635514, "grad_norm": 1.0815829038619995, "learning_rate": 7.390988521443942e-07, "loss": 0.7757, "step": 15076 }, { "epoch": 0.8806658878504673, "grad_norm": 1.350386142730713, "learning_rate": 7.383852213918785e-07, "loss": 0.8289, "step": 15077 }, { "epoch": 0.8807242990654206, "grad_norm": 0.8864257335662842, "learning_rate": 7.376719221186446e-07, "loss": 0.6312, "step": 15078 }, { "epoch": 0.8807827102803738, "grad_norm": 1.0984283685684204, "learning_rate": 7.369589543502243e-07, "loss": 0.7677, "step": 15079 }, { "epoch": 0.8808411214953271, "grad_norm": 1.1250945329666138, "learning_rate": 7.362463181121327e-07, "loss": 0.7868, "step": 15080 }, { "epoch": 0.8808995327102803, "grad_norm": 0.8950470089912415, "learning_rate": 7.355340134298772e-07, "loss": 0.6556, "step": 15081 }, { "epoch": 0.8809579439252336, "grad_norm": 1.0353310108184814, "learning_rate": 7.348220403289496e-07, "loss": 0.7178, "step": 15082 }, { "epoch": 0.881016355140187, "grad_norm": 1.0342029333114624, "learning_rate": 7.341103988348341e-07, "loss": 0.8296, "step": 15083 }, { "epoch": 0.8810747663551401, "grad_norm": 1.3482099771499634, "learning_rate": 7.333990889730003e-07, "loss": 0.7065, "step": 15084 }, { "epoch": 0.8811331775700935, "grad_norm": 1.0366512537002563, "learning_rate": 7.326881107689044e-07, "loss": 0.7069, "step": 15085 }, { "epoch": 0.8811915887850468, "grad_norm": 0.9738933444023132, "learning_rate": 7.319774642479971e-07, "loss": 0.6873, "step": 15086 }, { "epoch": 0.88125, "grad_norm": 1.156697154045105, "learning_rate": 7.312671494357071e-07, "loss": 0.6997, "step": 15087 }, { "epoch": 0.8813084112149533, "grad_norm": 1.1679325103759766, "learning_rate": 7.305571663574629e-07, "loss": 0.7367, "step": 15088 }, { "epoch": 0.8813668224299065, "grad_norm": 0.9812124371528625, "learning_rate": 7.298475150386708e-07, "loss": 0.5702, "step": 15089 }, { "epoch": 0.8814252336448598, "grad_norm": 0.9665439128875732, "learning_rate": 7.291381955047305e-07, "loss": 0.7448, "step": 15090 }, { "epoch": 0.8814836448598131, "grad_norm": 1.027891755104065, "learning_rate": 7.284292077810328e-07, "loss": 0.7043, "step": 15091 }, { "epoch": 0.8815420560747663, "grad_norm": 1.5875282287597656, "learning_rate": 7.277205518929476e-07, "loss": 0.6604, "step": 15092 }, { "epoch": 0.8816004672897196, "grad_norm": 1.3896527290344238, "learning_rate": 7.27012227865842e-07, "loss": 0.8067, "step": 15093 }, { "epoch": 0.881658878504673, "grad_norm": 1.09806489944458, "learning_rate": 7.263042357250639e-07, "loss": 0.797, "step": 15094 }, { "epoch": 0.8817172897196262, "grad_norm": 1.0702037811279297, "learning_rate": 7.255965754959549e-07, "loss": 0.9012, "step": 15095 }, { "epoch": 0.8817757009345795, "grad_norm": 0.8889684677124023, "learning_rate": 7.248892472038449e-07, "loss": 0.624, "step": 15096 }, { "epoch": 0.8818341121495327, "grad_norm": 1.542461633682251, "learning_rate": 7.241822508740448e-07, "loss": 0.6517, "step": 15097 }, { "epoch": 0.881892523364486, "grad_norm": 1.1261847019195557, "learning_rate": 7.234755865318632e-07, "loss": 0.7579, "step": 15098 }, { "epoch": 0.8819509345794393, "grad_norm": 1.084768533706665, "learning_rate": 7.227692542025877e-07, "loss": 0.7715, "step": 15099 }, { "epoch": 0.8820093457943925, "grad_norm": 1.3221240043640137, "learning_rate": 7.220632539115002e-07, "loss": 0.8122, "step": 15100 }, { "epoch": 0.8820677570093458, "grad_norm": 0.8042049407958984, "learning_rate": 7.213575856838717e-07, "loss": 0.4961, "step": 15101 }, { "epoch": 0.882126168224299, "grad_norm": 1.1188042163848877, "learning_rate": 7.206522495449541e-07, "loss": 0.6941, "step": 15102 }, { "epoch": 0.8821845794392523, "grad_norm": 1.28713059425354, "learning_rate": 7.199472455199952e-07, "loss": 0.6299, "step": 15103 }, { "epoch": 0.8822429906542056, "grad_norm": 0.9711787700653076, "learning_rate": 7.192425736342268e-07, "loss": 0.7048, "step": 15104 }, { "epoch": 0.8823014018691588, "grad_norm": 0.9476049542427063, "learning_rate": 7.185382339128643e-07, "loss": 0.675, "step": 15105 }, { "epoch": 0.8823598130841122, "grad_norm": 1.2308114767074585, "learning_rate": 7.178342263811255e-07, "loss": 0.6966, "step": 15106 }, { "epoch": 0.8824182242990655, "grad_norm": 1.175140380859375, "learning_rate": 7.171305510642024e-07, "loss": 0.842, "step": 15107 }, { "epoch": 0.8824766355140187, "grad_norm": 1.0074377059936523, "learning_rate": 7.164272079872792e-07, "loss": 0.6783, "step": 15108 }, { "epoch": 0.882535046728972, "grad_norm": 1.0984063148498535, "learning_rate": 7.157241971755314e-07, "loss": 0.8759, "step": 15109 }, { "epoch": 0.8825934579439252, "grad_norm": 0.9989508986473083, "learning_rate": 7.150215186541177e-07, "loss": 0.7924, "step": 15110 }, { "epoch": 0.8826518691588785, "grad_norm": 0.7798219323158264, "learning_rate": 7.14319172448189e-07, "loss": 0.663, "step": 15111 }, { "epoch": 0.8827102803738318, "grad_norm": 1.265725016593933, "learning_rate": 7.136171585828844e-07, "loss": 0.8272, "step": 15112 }, { "epoch": 0.882768691588785, "grad_norm": 1.4733401536941528, "learning_rate": 7.129154770833257e-07, "loss": 0.7669, "step": 15113 }, { "epoch": 0.8828271028037383, "grad_norm": 1.1021385192871094, "learning_rate": 7.122141279746297e-07, "loss": 0.7668, "step": 15114 }, { "epoch": 0.8828855140186916, "grad_norm": 1.1054003238677979, "learning_rate": 7.115131112818951e-07, "loss": 0.7165, "step": 15115 }, { "epoch": 0.8829439252336448, "grad_norm": 1.3307539224624634, "learning_rate": 7.108124270302141e-07, "loss": 0.7062, "step": 15116 }, { "epoch": 0.8830023364485982, "grad_norm": 1.0721110105514526, "learning_rate": 7.101120752446666e-07, "loss": 0.8281, "step": 15117 }, { "epoch": 0.8830607476635514, "grad_norm": 1.1350041627883911, "learning_rate": 7.094120559503126e-07, "loss": 0.7151, "step": 15118 }, { "epoch": 0.8831191588785047, "grad_norm": 1.1755722761154175, "learning_rate": 7.087123691722131e-07, "loss": 0.7992, "step": 15119 }, { "epoch": 0.883177570093458, "grad_norm": 1.1553316116333008, "learning_rate": 7.080130149354048e-07, "loss": 0.6579, "step": 15120 }, { "epoch": 0.8832359813084112, "grad_norm": 1.7058912515640259, "learning_rate": 7.07313993264922e-07, "loss": 0.7827, "step": 15121 }, { "epoch": 0.8832943925233645, "grad_norm": 0.9904671311378479, "learning_rate": 7.066153041857793e-07, "loss": 0.6714, "step": 15122 }, { "epoch": 0.8833528037383177, "grad_norm": 1.0444552898406982, "learning_rate": 7.059169477229854e-07, "loss": 0.6722, "step": 15123 }, { "epoch": 0.883411214953271, "grad_norm": 1.2003400325775146, "learning_rate": 7.052189239015373e-07, "loss": 0.7724, "step": 15124 }, { "epoch": 0.8834696261682243, "grad_norm": 0.9901477098464966, "learning_rate": 7.045212327464135e-07, "loss": 0.6893, "step": 15125 }, { "epoch": 0.8835280373831775, "grad_norm": 1.0572295188903809, "learning_rate": 7.038238742825876e-07, "loss": 0.8468, "step": 15126 }, { "epoch": 0.8835864485981308, "grad_norm": 0.9377767443656921, "learning_rate": 7.031268485350173e-07, "loss": 0.838, "step": 15127 }, { "epoch": 0.8836448598130842, "grad_norm": 0.9082649350166321, "learning_rate": 7.024301555286484e-07, "loss": 0.8903, "step": 15128 }, { "epoch": 0.8837032710280374, "grad_norm": 1.1716458797454834, "learning_rate": 7.017337952884206e-07, "loss": 0.7212, "step": 15129 }, { "epoch": 0.8837616822429907, "grad_norm": 1.3313591480255127, "learning_rate": 7.010377678392511e-07, "loss": 0.7135, "step": 15130 }, { "epoch": 0.8838200934579439, "grad_norm": 1.0602965354919434, "learning_rate": 7.003420732060562e-07, "loss": 0.6661, "step": 15131 }, { "epoch": 0.8838785046728972, "grad_norm": 1.0146645307540894, "learning_rate": 6.996467114137317e-07, "loss": 0.7755, "step": 15132 }, { "epoch": 0.8839369158878505, "grad_norm": 0.8782525062561035, "learning_rate": 6.989516824871667e-07, "loss": 0.4973, "step": 15133 }, { "epoch": 0.8839953271028037, "grad_norm": 1.1951887607574463, "learning_rate": 6.982569864512378e-07, "loss": 0.9793, "step": 15134 }, { "epoch": 0.884053738317757, "grad_norm": 1.1881351470947266, "learning_rate": 6.975626233308053e-07, "loss": 0.7743, "step": 15135 }, { "epoch": 0.8841121495327103, "grad_norm": 1.0626585483551025, "learning_rate": 6.968685931507246e-07, "loss": 0.6559, "step": 15136 }, { "epoch": 0.8841705607476635, "grad_norm": 1.0120469331741333, "learning_rate": 6.96174895935835e-07, "loss": 0.671, "step": 15137 }, { "epoch": 0.8842289719626168, "grad_norm": 2.964334487915039, "learning_rate": 6.954815317109587e-07, "loss": 0.7979, "step": 15138 }, { "epoch": 0.88428738317757, "grad_norm": 0.9886335134506226, "learning_rate": 6.947885005009203e-07, "loss": 0.5507, "step": 15139 }, { "epoch": 0.8843457943925234, "grad_norm": 0.9893677234649658, "learning_rate": 6.940958023305177e-07, "loss": 0.5399, "step": 15140 }, { "epoch": 0.8844042056074767, "grad_norm": 0.9252224564552307, "learning_rate": 6.93403437224548e-07, "loss": 0.8387, "step": 15141 }, { "epoch": 0.8844626168224299, "grad_norm": 1.3556307554244995, "learning_rate": 6.927114052077865e-07, "loss": 0.9783, "step": 15142 }, { "epoch": 0.8845210280373832, "grad_norm": 1.1987895965576172, "learning_rate": 6.920197063050038e-07, "loss": 0.6652, "step": 15143 }, { "epoch": 0.8845794392523364, "grad_norm": 1.0009217262268066, "learning_rate": 6.913283405409544e-07, "loss": 0.774, "step": 15144 }, { "epoch": 0.8846378504672897, "grad_norm": 1.0785598754882812, "learning_rate": 6.90637307940385e-07, "loss": 0.7413, "step": 15145 }, { "epoch": 0.884696261682243, "grad_norm": 1.0064446926116943, "learning_rate": 6.899466085280282e-07, "loss": 0.6382, "step": 15146 }, { "epoch": 0.8847546728971962, "grad_norm": 1.0834509134292603, "learning_rate": 6.892562423286042e-07, "loss": 0.6279, "step": 15147 }, { "epoch": 0.8848130841121495, "grad_norm": 1.0653661489486694, "learning_rate": 6.8856620936682e-07, "loss": 0.8189, "step": 15148 }, { "epoch": 0.8848714953271029, "grad_norm": 1.1320477724075317, "learning_rate": 6.878765096673734e-07, "loss": 0.8234, "step": 15149 }, { "epoch": 0.884929906542056, "grad_norm": 1.1899070739746094, "learning_rate": 6.871871432549493e-07, "loss": 0.7813, "step": 15150 }, { "epoch": 0.8849883177570094, "grad_norm": 2.7373592853546143, "learning_rate": 6.864981101542223e-07, "loss": 0.7106, "step": 15151 }, { "epoch": 0.8850467289719626, "grad_norm": 1.0748631954193115, "learning_rate": 6.858094103898516e-07, "loss": 0.8452, "step": 15152 }, { "epoch": 0.8851051401869159, "grad_norm": 1.1369365453720093, "learning_rate": 6.851210439864841e-07, "loss": 0.7937, "step": 15153 }, { "epoch": 0.8851635514018692, "grad_norm": 1.2756588459014893, "learning_rate": 6.844330109687614e-07, "loss": 0.9517, "step": 15154 }, { "epoch": 0.8852219626168224, "grad_norm": 1.2708711624145508, "learning_rate": 6.837453113613035e-07, "loss": 0.6541, "step": 15155 }, { "epoch": 0.8852803738317757, "grad_norm": 1.4885857105255127, "learning_rate": 6.830579451887287e-07, "loss": 0.741, "step": 15156 }, { "epoch": 0.885338785046729, "grad_norm": 1.2146680355072021, "learning_rate": 6.823709124756372e-07, "loss": 0.6338, "step": 15157 }, { "epoch": 0.8853971962616822, "grad_norm": 1.3964101076126099, "learning_rate": 6.81684213246615e-07, "loss": 0.9059, "step": 15158 }, { "epoch": 0.8854556074766355, "grad_norm": 1.1836351156234741, "learning_rate": 6.809978475262425e-07, "loss": 0.7355, "step": 15159 }, { "epoch": 0.8855140186915887, "grad_norm": 2.0664241313934326, "learning_rate": 6.803118153390842e-07, "loss": 0.6905, "step": 15160 }, { "epoch": 0.8855724299065421, "grad_norm": 1.0109308958053589, "learning_rate": 6.796261167096929e-07, "loss": 0.6182, "step": 15161 }, { "epoch": 0.8856308411214954, "grad_norm": 1.729583978652954, "learning_rate": 6.789407516626134e-07, "loss": 0.8268, "step": 15162 }, { "epoch": 0.8856892523364486, "grad_norm": 1.2551400661468506, "learning_rate": 6.782557202223705e-07, "loss": 0.8209, "step": 15163 }, { "epoch": 0.8857476635514019, "grad_norm": 0.9791225790977478, "learning_rate": 6.775710224134869e-07, "loss": 0.7218, "step": 15164 }, { "epoch": 0.8858060747663551, "grad_norm": 1.3941701650619507, "learning_rate": 6.768866582604638e-07, "loss": 0.6968, "step": 15165 }, { "epoch": 0.8858644859813084, "grad_norm": 1.1996737718582153, "learning_rate": 6.762026277877986e-07, "loss": 0.8657, "step": 15166 }, { "epoch": 0.8859228971962617, "grad_norm": 1.0055265426635742, "learning_rate": 6.755189310199728e-07, "loss": 0.8372, "step": 15167 }, { "epoch": 0.8859813084112149, "grad_norm": 1.09498929977417, "learning_rate": 6.748355679814533e-07, "loss": 0.7445, "step": 15168 }, { "epoch": 0.8860397196261682, "grad_norm": 1.0974992513656616, "learning_rate": 6.741525386967018e-07, "loss": 0.8163, "step": 15169 }, { "epoch": 0.8860981308411215, "grad_norm": 0.9369217157363892, "learning_rate": 6.734698431901632e-07, "loss": 0.7612, "step": 15170 }, { "epoch": 0.8861565420560747, "grad_norm": 1.1550018787384033, "learning_rate": 6.72787481486269e-07, "loss": 0.6438, "step": 15171 }, { "epoch": 0.8862149532710281, "grad_norm": 0.947694718837738, "learning_rate": 6.721054536094452e-07, "loss": 0.8465, "step": 15172 }, { "epoch": 0.8862733644859813, "grad_norm": 1.4540499448776245, "learning_rate": 6.714237595841e-07, "loss": 0.8145, "step": 15173 }, { "epoch": 0.8863317757009346, "grad_norm": 1.0708727836608887, "learning_rate": 6.707423994346329e-07, "loss": 0.7795, "step": 15174 }, { "epoch": 0.8863901869158879, "grad_norm": 1.511455774307251, "learning_rate": 6.700613731854289e-07, "loss": 0.6541, "step": 15175 }, { "epoch": 0.8864485981308411, "grad_norm": 0.8194003701210022, "learning_rate": 6.693806808608627e-07, "loss": 0.6909, "step": 15176 }, { "epoch": 0.8865070093457944, "grad_norm": 2.0291786193847656, "learning_rate": 6.687003224852961e-07, "loss": 0.8088, "step": 15177 }, { "epoch": 0.8865654205607477, "grad_norm": 0.8203834891319275, "learning_rate": 6.680202980830807e-07, "loss": 0.6806, "step": 15178 }, { "epoch": 0.8866238317757009, "grad_norm": 1.0644469261169434, "learning_rate": 6.673406076785561e-07, "loss": 0.6859, "step": 15179 }, { "epoch": 0.8866822429906542, "grad_norm": 2.1500794887542725, "learning_rate": 6.66661251296048e-07, "loss": 0.7177, "step": 15180 }, { "epoch": 0.8867406542056074, "grad_norm": 1.0574026107788086, "learning_rate": 6.659822289598683e-07, "loss": 0.8173, "step": 15181 }, { "epoch": 0.8867990654205608, "grad_norm": 1.0424226522445679, "learning_rate": 6.65303540694322e-07, "loss": 0.6648, "step": 15182 }, { "epoch": 0.8868574766355141, "grad_norm": 1.0918998718261719, "learning_rate": 6.646251865236997e-07, "loss": 0.6574, "step": 15183 }, { "epoch": 0.8869158878504673, "grad_norm": 1.2155412435531616, "learning_rate": 6.639471664722819e-07, "loss": 0.8179, "step": 15184 }, { "epoch": 0.8869742990654206, "grad_norm": 1.6322495937347412, "learning_rate": 6.632694805643336e-07, "loss": 0.8808, "step": 15185 }, { "epoch": 0.8870327102803738, "grad_norm": 1.0675361156463623, "learning_rate": 6.625921288241077e-07, "loss": 0.6439, "step": 15186 }, { "epoch": 0.8870911214953271, "grad_norm": 0.9450865387916565, "learning_rate": 6.619151112758515e-07, "loss": 0.6139, "step": 15187 }, { "epoch": 0.8871495327102804, "grad_norm": 1.2592689990997314, "learning_rate": 6.612384279437889e-07, "loss": 0.7934, "step": 15188 }, { "epoch": 0.8872079439252336, "grad_norm": 1.103329062461853, "learning_rate": 6.605620788521472e-07, "loss": 0.6673, "step": 15189 }, { "epoch": 0.8872663551401869, "grad_norm": 0.9565266370773315, "learning_rate": 6.598860640251292e-07, "loss": 0.7424, "step": 15190 }, { "epoch": 0.8873247663551402, "grad_norm": 1.0869483947753906, "learning_rate": 6.59210383486929e-07, "loss": 0.8972, "step": 15191 }, { "epoch": 0.8873831775700934, "grad_norm": 2.1174421310424805, "learning_rate": 6.585350372617317e-07, "loss": 0.7213, "step": 15192 }, { "epoch": 0.8874415887850468, "grad_norm": 1.5777417421340942, "learning_rate": 6.578600253737066e-07, "loss": 0.7935, "step": 15193 }, { "epoch": 0.8875, "grad_norm": 0.8241947889328003, "learning_rate": 6.571853478470136e-07, "loss": 0.7201, "step": 15194 }, { "epoch": 0.8875584112149533, "grad_norm": 1.6232339143753052, "learning_rate": 6.56511004705802e-07, "loss": 0.7926, "step": 15195 }, { "epoch": 0.8876168224299066, "grad_norm": 1.373862385749817, "learning_rate": 6.558369959742029e-07, "loss": 0.6719, "step": 15196 }, { "epoch": 0.8876752336448598, "grad_norm": 1.20009446144104, "learning_rate": 6.551633216763431e-07, "loss": 0.6666, "step": 15197 }, { "epoch": 0.8877336448598131, "grad_norm": 0.9153357148170471, "learning_rate": 6.544899818363315e-07, "loss": 0.589, "step": 15198 }, { "epoch": 0.8877920560747663, "grad_norm": 1.3261330127716064, "learning_rate": 6.538169764782676e-07, "loss": 0.7997, "step": 15199 }, { "epoch": 0.8878504672897196, "grad_norm": 1.6069436073303223, "learning_rate": 6.53144305626241e-07, "loss": 0.6872, "step": 15200 }, { "epoch": 0.8879088785046729, "grad_norm": 2.310271978378296, "learning_rate": 6.524719693043235e-07, "loss": 0.8212, "step": 15201 }, { "epoch": 0.8879672897196261, "grad_norm": 0.8485251069068909, "learning_rate": 6.517999675365827e-07, "loss": 0.6621, "step": 15202 }, { "epoch": 0.8880257009345794, "grad_norm": 1.0830656290054321, "learning_rate": 6.511283003470659e-07, "loss": 0.7881, "step": 15203 }, { "epoch": 0.8880841121495328, "grad_norm": 1.0435736179351807, "learning_rate": 6.504569677598138e-07, "loss": 0.8004, "step": 15204 }, { "epoch": 0.888142523364486, "grad_norm": 1.2138017416000366, "learning_rate": 6.497859697988562e-07, "loss": 0.6432, "step": 15205 }, { "epoch": 0.8882009345794393, "grad_norm": 1.1692447662353516, "learning_rate": 6.49115306488205e-07, "loss": 0.7048, "step": 15206 }, { "epoch": 0.8882593457943925, "grad_norm": 1.035408854484558, "learning_rate": 6.484449778518664e-07, "loss": 0.8356, "step": 15207 }, { "epoch": 0.8883177570093458, "grad_norm": 0.9521222710609436, "learning_rate": 6.477749839138303e-07, "loss": 0.7911, "step": 15208 }, { "epoch": 0.8883761682242991, "grad_norm": 1.8494495153427124, "learning_rate": 6.471053246980774e-07, "loss": 0.719, "step": 15209 }, { "epoch": 0.8884345794392523, "grad_norm": 1.075805902481079, "learning_rate": 6.46436000228573e-07, "loss": 0.5743, "step": 15210 }, { "epoch": 0.8884929906542056, "grad_norm": 0.9599546194076538, "learning_rate": 6.457670105292746e-07, "loss": 0.6918, "step": 15211 }, { "epoch": 0.8885514018691589, "grad_norm": 0.7701308131217957, "learning_rate": 6.450983556241264e-07, "loss": 0.6224, "step": 15212 }, { "epoch": 0.8886098130841121, "grad_norm": 2.44598126411438, "learning_rate": 6.444300355370581e-07, "loss": 0.7949, "step": 15213 }, { "epoch": 0.8886682242990654, "grad_norm": 1.105629801750183, "learning_rate": 6.437620502919917e-07, "loss": 0.7137, "step": 15214 }, { "epoch": 0.8887266355140186, "grad_norm": 1.3100210428237915, "learning_rate": 6.430943999128325e-07, "loss": 0.762, "step": 15215 }, { "epoch": 0.888785046728972, "grad_norm": 1.2349597215652466, "learning_rate": 6.424270844234759e-07, "loss": 0.7478, "step": 15216 }, { "epoch": 0.8888434579439253, "grad_norm": 0.8707235455513, "learning_rate": 6.417601038478082e-07, "loss": 0.5244, "step": 15217 }, { "epoch": 0.8889018691588785, "grad_norm": 0.9917168021202087, "learning_rate": 6.410934582097006e-07, "loss": 0.6381, "step": 15218 }, { "epoch": 0.8889602803738318, "grad_norm": 1.2234513759613037, "learning_rate": 6.404271475330093e-07, "loss": 0.8148, "step": 15219 }, { "epoch": 0.889018691588785, "grad_norm": 1.088449478149414, "learning_rate": 6.397611718415864e-07, "loss": 0.8408, "step": 15220 }, { "epoch": 0.8890771028037383, "grad_norm": 1.0303939580917358, "learning_rate": 6.390955311592617e-07, "loss": 0.6076, "step": 15221 }, { "epoch": 0.8891355140186916, "grad_norm": 1.0104860067367554, "learning_rate": 6.384302255098662e-07, "loss": 0.6517, "step": 15222 }, { "epoch": 0.8891939252336448, "grad_norm": 1.0474331378936768, "learning_rate": 6.377652549172087e-07, "loss": 0.7953, "step": 15223 }, { "epoch": 0.8892523364485981, "grad_norm": 1.2117533683776855, "learning_rate": 6.371006194050877e-07, "loss": 0.78, "step": 15224 }, { "epoch": 0.8893107476635514, "grad_norm": 1.0239118337631226, "learning_rate": 6.364363189972922e-07, "loss": 0.9213, "step": 15225 }, { "epoch": 0.8893691588785047, "grad_norm": 1.1215128898620605, "learning_rate": 6.357723537175964e-07, "loss": 0.8989, "step": 15226 }, { "epoch": 0.889427570093458, "grad_norm": 1.0240478515625, "learning_rate": 6.351087235897646e-07, "loss": 0.7339, "step": 15227 }, { "epoch": 0.8894859813084112, "grad_norm": 0.8936710953712463, "learning_rate": 6.344454286375512e-07, "loss": 0.7757, "step": 15228 }, { "epoch": 0.8895443925233645, "grad_norm": 1.1252232789993286, "learning_rate": 6.337824688846928e-07, "loss": 0.7083, "step": 15229 }, { "epoch": 0.8896028037383178, "grad_norm": 1.165938377380371, "learning_rate": 6.331198443549191e-07, "loss": 0.7685, "step": 15230 }, { "epoch": 0.889661214953271, "grad_norm": 1.1165244579315186, "learning_rate": 6.324575550719437e-07, "loss": 0.7382, "step": 15231 }, { "epoch": 0.8897196261682243, "grad_norm": 1.0518735647201538, "learning_rate": 6.317956010594706e-07, "loss": 0.6842, "step": 15232 }, { "epoch": 0.8897780373831776, "grad_norm": 1.3611183166503906, "learning_rate": 6.311339823411955e-07, "loss": 0.7708, "step": 15233 }, { "epoch": 0.8898364485981308, "grad_norm": 1.1709915399551392, "learning_rate": 6.304726989407939e-07, "loss": 0.7627, "step": 15234 }, { "epoch": 0.8898948598130841, "grad_norm": 1.1718156337738037, "learning_rate": 6.298117508819357e-07, "loss": 0.7899, "step": 15235 }, { "epoch": 0.8899532710280373, "grad_norm": 1.6720325946807861, "learning_rate": 6.291511381882742e-07, "loss": 0.8169, "step": 15236 }, { "epoch": 0.8900116822429907, "grad_norm": 0.8624681234359741, "learning_rate": 6.284908608834561e-07, "loss": 0.5827, "step": 15237 }, { "epoch": 0.890070093457944, "grad_norm": 1.2088656425476074, "learning_rate": 6.278309189911125e-07, "loss": 0.7324, "step": 15238 }, { "epoch": 0.8901285046728972, "grad_norm": 1.5530980825424194, "learning_rate": 6.271713125348621e-07, "loss": 0.827, "step": 15239 }, { "epoch": 0.8901869158878505, "grad_norm": 0.9241769909858704, "learning_rate": 6.265120415383141e-07, "loss": 0.6064, "step": 15240 }, { "epoch": 0.8902453271028037, "grad_norm": 1.0475151538848877, "learning_rate": 6.258531060250616e-07, "loss": 0.787, "step": 15241 }, { "epoch": 0.890303738317757, "grad_norm": 0.8981210589408875, "learning_rate": 6.251945060186915e-07, "loss": 0.7123, "step": 15242 }, { "epoch": 0.8903621495327103, "grad_norm": 1.414214015007019, "learning_rate": 6.245362415427736e-07, "loss": 0.658, "step": 15243 }, { "epoch": 0.8904205607476635, "grad_norm": 1.1387392282485962, "learning_rate": 6.23878312620867e-07, "loss": 0.6798, "step": 15244 }, { "epoch": 0.8904789719626168, "grad_norm": 1.0473970174789429, "learning_rate": 6.232207192765227e-07, "loss": 0.7028, "step": 15245 }, { "epoch": 0.8905373831775701, "grad_norm": 0.9722104668617249, "learning_rate": 6.22563461533272e-07, "loss": 0.6745, "step": 15246 }, { "epoch": 0.8905957943925233, "grad_norm": 0.9215197563171387, "learning_rate": 6.219065394146429e-07, "loss": 0.7175, "step": 15247 }, { "epoch": 0.8906542056074767, "grad_norm": 1.1735575199127197, "learning_rate": 6.21249952944143e-07, "loss": 0.6961, "step": 15248 }, { "epoch": 0.8907126168224299, "grad_norm": 1.3999886512756348, "learning_rate": 6.205937021452746e-07, "loss": 0.8359, "step": 15249 }, { "epoch": 0.8907710280373832, "grad_norm": 1.3421850204467773, "learning_rate": 6.199377870415257e-07, "loss": 0.7555, "step": 15250 }, { "epoch": 0.8908294392523365, "grad_norm": 0.7317811250686646, "learning_rate": 6.192822076563687e-07, "loss": 0.4736, "step": 15251 }, { "epoch": 0.8908878504672897, "grad_norm": 1.0843902826309204, "learning_rate": 6.186269640132725e-07, "loss": 0.889, "step": 15252 }, { "epoch": 0.890946261682243, "grad_norm": 1.10094153881073, "learning_rate": 6.179720561356851e-07, "loss": 0.8025, "step": 15253 }, { "epoch": 0.8910046728971963, "grad_norm": 1.0696667432785034, "learning_rate": 6.17317484047043e-07, "loss": 0.846, "step": 15254 }, { "epoch": 0.8910630841121495, "grad_norm": 1.1440860033035278, "learning_rate": 6.166632477707801e-07, "loss": 0.6502, "step": 15255 }, { "epoch": 0.8911214953271028, "grad_norm": 0.949438214302063, "learning_rate": 6.160093473303086e-07, "loss": 0.7821, "step": 15256 }, { "epoch": 0.891179906542056, "grad_norm": 1.3622785806655884, "learning_rate": 6.153557827490342e-07, "loss": 0.898, "step": 15257 }, { "epoch": 0.8912383177570093, "grad_norm": 1.104336142539978, "learning_rate": 6.147025540503459e-07, "loss": 0.8409, "step": 15258 }, { "epoch": 0.8912967289719627, "grad_norm": 0.8264538049697876, "learning_rate": 6.140496612576241e-07, "loss": 0.7192, "step": 15259 }, { "epoch": 0.8913551401869159, "grad_norm": 1.0840340852737427, "learning_rate": 6.133971043942355e-07, "loss": 0.7378, "step": 15260 }, { "epoch": 0.8914135514018692, "grad_norm": 1.1454334259033203, "learning_rate": 6.127448834835359e-07, "loss": 0.7572, "step": 15261 }, { "epoch": 0.8914719626168224, "grad_norm": 0.9599034190177917, "learning_rate": 6.12092998548871e-07, "loss": 0.669, "step": 15262 }, { "epoch": 0.8915303738317757, "grad_norm": 1.0542782545089722, "learning_rate": 6.114414496135712e-07, "loss": 0.7979, "step": 15263 }, { "epoch": 0.891588785046729, "grad_norm": 0.8197694420814514, "learning_rate": 6.107902367009522e-07, "loss": 0.7128, "step": 15264 }, { "epoch": 0.8916471962616822, "grad_norm": 1.047455072402954, "learning_rate": 6.101393598343253e-07, "loss": 0.6837, "step": 15265 }, { "epoch": 0.8917056074766355, "grad_norm": 0.9615904688835144, "learning_rate": 6.09488819036984e-07, "loss": 0.7782, "step": 15266 }, { "epoch": 0.8917640186915888, "grad_norm": 1.304761290550232, "learning_rate": 6.088386143322134e-07, "loss": 0.8381, "step": 15267 }, { "epoch": 0.891822429906542, "grad_norm": 0.8569644689559937, "learning_rate": 6.081887457432844e-07, "loss": 0.7123, "step": 15268 }, { "epoch": 0.8918808411214953, "grad_norm": 1.2461963891983032, "learning_rate": 6.075392132934532e-07, "loss": 0.6673, "step": 15269 }, { "epoch": 0.8919392523364486, "grad_norm": 0.9281997680664062, "learning_rate": 6.0689001700597e-07, "loss": 0.5739, "step": 15270 }, { "epoch": 0.8919976635514019, "grad_norm": 1.026017427444458, "learning_rate": 6.062411569040682e-07, "loss": 0.7408, "step": 15271 }, { "epoch": 0.8920560747663552, "grad_norm": 2.455324649810791, "learning_rate": 6.055926330109741e-07, "loss": 0.6822, "step": 15272 }, { "epoch": 0.8921144859813084, "grad_norm": 1.331587553024292, "learning_rate": 6.049444453498965e-07, "loss": 0.805, "step": 15273 }, { "epoch": 0.8921728971962617, "grad_norm": 1.0122134685516357, "learning_rate": 6.042965939440337e-07, "loss": 0.7111, "step": 15274 }, { "epoch": 0.892231308411215, "grad_norm": 1.6604567766189575, "learning_rate": 6.036490788165738e-07, "loss": 0.8138, "step": 15275 }, { "epoch": 0.8922897196261682, "grad_norm": 0.8059220910072327, "learning_rate": 6.030018999906906e-07, "loss": 0.5308, "step": 15276 }, { "epoch": 0.8923481308411215, "grad_norm": 1.2766852378845215, "learning_rate": 6.023550574895487e-07, "loss": 0.9394, "step": 15277 }, { "epoch": 0.8924065420560747, "grad_norm": 1.1028006076812744, "learning_rate": 6.017085513362997e-07, "loss": 0.9602, "step": 15278 }, { "epoch": 0.892464953271028, "grad_norm": 1.2220823764801025, "learning_rate": 6.010623815540784e-07, "loss": 0.761, "step": 15279 }, { "epoch": 0.8925233644859814, "grad_norm": 1.0586540699005127, "learning_rate": 6.004165481660174e-07, "loss": 0.7454, "step": 15280 }, { "epoch": 0.8925817757009346, "grad_norm": 0.9994823932647705, "learning_rate": 5.997710511952259e-07, "loss": 0.6183, "step": 15281 }, { "epoch": 0.8926401869158879, "grad_norm": 1.2176754474639893, "learning_rate": 5.991258906648101e-07, "loss": 0.7481, "step": 15282 }, { "epoch": 0.8926985981308411, "grad_norm": 0.8852251172065735, "learning_rate": 5.984810665978613e-07, "loss": 0.7232, "step": 15283 }, { "epoch": 0.8927570093457944, "grad_norm": 1.44011652469635, "learning_rate": 5.978365790174545e-07, "loss": 0.8642, "step": 15284 }, { "epoch": 0.8928154205607477, "grad_norm": 0.9750332832336426, "learning_rate": 5.971924279466601e-07, "loss": 0.7092, "step": 15285 }, { "epoch": 0.8928738317757009, "grad_norm": 1.098145604133606, "learning_rate": 5.965486134085319e-07, "loss": 0.8434, "step": 15286 }, { "epoch": 0.8929322429906542, "grad_norm": 0.7352033257484436, "learning_rate": 5.95905135426108e-07, "loss": 0.5872, "step": 15287 }, { "epoch": 0.8929906542056075, "grad_norm": 0.9698024988174438, "learning_rate": 5.952619940224269e-07, "loss": 0.6726, "step": 15288 }, { "epoch": 0.8930490654205607, "grad_norm": 1.5256774425506592, "learning_rate": 5.946191892205e-07, "loss": 0.7606, "step": 15289 }, { "epoch": 0.893107476635514, "grad_norm": 0.9395383596420288, "learning_rate": 5.939767210433378e-07, "loss": 0.6184, "step": 15290 }, { "epoch": 0.8931658878504672, "grad_norm": 1.0835176706314087, "learning_rate": 5.933345895139342e-07, "loss": 0.9493, "step": 15291 }, { "epoch": 0.8932242990654206, "grad_norm": 1.4059892892837524, "learning_rate": 5.926927946552696e-07, "loss": 0.8643, "step": 15292 }, { "epoch": 0.8932827102803739, "grad_norm": 1.310854196548462, "learning_rate": 5.920513364903136e-07, "loss": 0.6826, "step": 15293 }, { "epoch": 0.8933411214953271, "grad_norm": 1.5071501731872559, "learning_rate": 5.914102150420275e-07, "loss": 0.8806, "step": 15294 }, { "epoch": 0.8933995327102804, "grad_norm": 1.272976279258728, "learning_rate": 5.907694303333567e-07, "loss": 0.8675, "step": 15295 }, { "epoch": 0.8934579439252337, "grad_norm": 1.6516441106796265, "learning_rate": 5.901289823872358e-07, "loss": 0.8214, "step": 15296 }, { "epoch": 0.8935163551401869, "grad_norm": 1.3496636152267456, "learning_rate": 5.894888712265834e-07, "loss": 0.7632, "step": 15297 }, { "epoch": 0.8935747663551402, "grad_norm": 1.1529412269592285, "learning_rate": 5.888490968743122e-07, "loss": 0.7783, "step": 15298 }, { "epoch": 0.8936331775700934, "grad_norm": 1.414583444595337, "learning_rate": 5.882096593533193e-07, "loss": 0.7468, "step": 15299 }, { "epoch": 0.8936915887850467, "grad_norm": 1.0937718152999878, "learning_rate": 5.875705586864922e-07, "loss": 0.7101, "step": 15300 }, { "epoch": 0.89375, "grad_norm": 1.0450119972229004, "learning_rate": 5.869317948967046e-07, "loss": 0.7041, "step": 15301 }, { "epoch": 0.8938084112149532, "grad_norm": 1.050850510597229, "learning_rate": 5.86293368006815e-07, "loss": 0.7869, "step": 15302 }, { "epoch": 0.8938668224299066, "grad_norm": 1.5975805521011353, "learning_rate": 5.856552780396762e-07, "loss": 0.889, "step": 15303 }, { "epoch": 0.8939252336448598, "grad_norm": 1.1963564157485962, "learning_rate": 5.850175250181244e-07, "loss": 0.8814, "step": 15304 }, { "epoch": 0.8939836448598131, "grad_norm": 1.1365418434143066, "learning_rate": 5.843801089649881e-07, "loss": 0.678, "step": 15305 }, { "epoch": 0.8940420560747664, "grad_norm": 1.138365626335144, "learning_rate": 5.837430299030778e-07, "loss": 0.7283, "step": 15306 }, { "epoch": 0.8941004672897196, "grad_norm": 1.019785761833191, "learning_rate": 5.831062878551941e-07, "loss": 0.7814, "step": 15307 }, { "epoch": 0.8941588785046729, "grad_norm": 1.2859383821487427, "learning_rate": 5.8246988284413e-07, "loss": 0.871, "step": 15308 }, { "epoch": 0.8942172897196262, "grad_norm": 1.3895556926727295, "learning_rate": 5.818338148926595e-07, "loss": 0.8194, "step": 15309 }, { "epoch": 0.8942757009345794, "grad_norm": 1.0235384702682495, "learning_rate": 5.811980840235498e-07, "loss": 0.6997, "step": 15310 }, { "epoch": 0.8943341121495327, "grad_norm": 1.3191123008728027, "learning_rate": 5.80562690259554e-07, "loss": 0.7118, "step": 15311 }, { "epoch": 0.8943925233644859, "grad_norm": 1.1883037090301514, "learning_rate": 5.799276336234128e-07, "loss": 0.6915, "step": 15312 }, { "epoch": 0.8944509345794392, "grad_norm": 1.1149035692214966, "learning_rate": 5.792929141378556e-07, "loss": 0.7287, "step": 15313 }, { "epoch": 0.8945093457943926, "grad_norm": 1.020745873451233, "learning_rate": 5.786585318255989e-07, "loss": 0.6142, "step": 15314 }, { "epoch": 0.8945677570093458, "grad_norm": 2.038604497909546, "learning_rate": 5.780244867093465e-07, "loss": 0.7342, "step": 15315 }, { "epoch": 0.8946261682242991, "grad_norm": 1.063924789428711, "learning_rate": 5.77390778811796e-07, "loss": 0.6944, "step": 15316 }, { "epoch": 0.8946845794392523, "grad_norm": 0.885189414024353, "learning_rate": 5.767574081556226e-07, "loss": 0.6028, "step": 15317 }, { "epoch": 0.8947429906542056, "grad_norm": 1.1186226606369019, "learning_rate": 5.761243747634993e-07, "loss": 0.7828, "step": 15318 }, { "epoch": 0.8948014018691589, "grad_norm": 1.1953353881835938, "learning_rate": 5.754916786580789e-07, "loss": 0.753, "step": 15319 }, { "epoch": 0.8948598130841121, "grad_norm": 1.0137765407562256, "learning_rate": 5.748593198620079e-07, "loss": 0.6229, "step": 15320 }, { "epoch": 0.8949182242990654, "grad_norm": 1.492599606513977, "learning_rate": 5.742272983979213e-07, "loss": 0.7673, "step": 15321 }, { "epoch": 0.8949766355140187, "grad_norm": 1.0989583730697632, "learning_rate": 5.735956142884358e-07, "loss": 0.7266, "step": 15322 }, { "epoch": 0.8950350467289719, "grad_norm": 1.6869455575942993, "learning_rate": 5.72964267556162e-07, "loss": 0.8098, "step": 15323 }, { "epoch": 0.8950934579439253, "grad_norm": 1.0720794200897217, "learning_rate": 5.72333258223694e-07, "loss": 0.605, "step": 15324 }, { "epoch": 0.8951518691588785, "grad_norm": 1.2860608100891113, "learning_rate": 5.717025863136194e-07, "loss": 0.6385, "step": 15325 }, { "epoch": 0.8952102803738318, "grad_norm": 1.0825122594833374, "learning_rate": 5.710722518485067e-07, "loss": 0.5932, "step": 15326 }, { "epoch": 0.8952686915887851, "grad_norm": 1.008368968963623, "learning_rate": 5.704422548509181e-07, "loss": 0.8006, "step": 15327 }, { "epoch": 0.8953271028037383, "grad_norm": 1.046233892440796, "learning_rate": 5.69812595343403e-07, "loss": 0.9358, "step": 15328 }, { "epoch": 0.8953855140186916, "grad_norm": 1.1870956420898438, "learning_rate": 5.691832733484937e-07, "loss": 0.7436, "step": 15329 }, { "epoch": 0.8954439252336449, "grad_norm": 2.2135982513427734, "learning_rate": 5.685542888887175e-07, "loss": 0.8233, "step": 15330 }, { "epoch": 0.8955023364485981, "grad_norm": 0.8405144214630127, "learning_rate": 5.67925641986583e-07, "loss": 0.7489, "step": 15331 }, { "epoch": 0.8955607476635514, "grad_norm": 1.1677080392837524, "learning_rate": 5.672973326645914e-07, "loss": 0.7756, "step": 15332 }, { "epoch": 0.8956191588785046, "grad_norm": 1.194402813911438, "learning_rate": 5.666693609452312e-07, "loss": 0.8939, "step": 15333 }, { "epoch": 0.8956775700934579, "grad_norm": 1.007738471031189, "learning_rate": 5.660417268509788e-07, "loss": 0.7677, "step": 15334 }, { "epoch": 0.8957359813084113, "grad_norm": 0.9164053201675415, "learning_rate": 5.65414430404293e-07, "loss": 0.7004, "step": 15335 }, { "epoch": 0.8957943925233645, "grad_norm": 0.9842730760574341, "learning_rate": 5.647874716276281e-07, "loss": 0.7028, "step": 15336 }, { "epoch": 0.8958528037383178, "grad_norm": 1.0583019256591797, "learning_rate": 5.641608505434248e-07, "loss": 0.6492, "step": 15337 }, { "epoch": 0.895911214953271, "grad_norm": 1.34480881690979, "learning_rate": 5.635345671741088e-07, "loss": 0.8343, "step": 15338 }, { "epoch": 0.8959696261682243, "grad_norm": 1.083522915840149, "learning_rate": 5.629086215420965e-07, "loss": 0.6371, "step": 15339 }, { "epoch": 0.8960280373831776, "grad_norm": 0.9789450168609619, "learning_rate": 5.622830136697865e-07, "loss": 0.6272, "step": 15340 }, { "epoch": 0.8960864485981308, "grad_norm": 1.0181084871292114, "learning_rate": 5.616577435795756e-07, "loss": 0.6471, "step": 15341 }, { "epoch": 0.8961448598130841, "grad_norm": 0.9413622617721558, "learning_rate": 5.610328112938379e-07, "loss": 0.7516, "step": 15342 }, { "epoch": 0.8962032710280374, "grad_norm": 1.554133653640747, "learning_rate": 5.604082168349423e-07, "loss": 0.8355, "step": 15343 }, { "epoch": 0.8962616822429906, "grad_norm": 1.1151494979858398, "learning_rate": 5.597839602252453e-07, "loss": 0.7875, "step": 15344 }, { "epoch": 0.896320093457944, "grad_norm": 0.8665045499801636, "learning_rate": 5.591600414870857e-07, "loss": 0.672, "step": 15345 }, { "epoch": 0.8963785046728971, "grad_norm": 1.1940487623214722, "learning_rate": 5.585364606427967e-07, "loss": 0.7846, "step": 15346 }, { "epoch": 0.8964369158878505, "grad_norm": 3.0870954990386963, "learning_rate": 5.57913217714694e-07, "loss": 0.6407, "step": 15347 }, { "epoch": 0.8964953271028038, "grad_norm": 1.237897515296936, "learning_rate": 5.572903127250862e-07, "loss": 0.7214, "step": 15348 }, { "epoch": 0.896553738317757, "grad_norm": 1.060834527015686, "learning_rate": 5.566677456962676e-07, "loss": 0.7442, "step": 15349 }, { "epoch": 0.8966121495327103, "grad_norm": 1.3023161888122559, "learning_rate": 5.560455166505185e-07, "loss": 0.809, "step": 15350 }, { "epoch": 0.8966705607476636, "grad_norm": 1.103871464729309, "learning_rate": 5.55423625610112e-07, "loss": 0.6545, "step": 15351 }, { "epoch": 0.8967289719626168, "grad_norm": 0.9498427510261536, "learning_rate": 5.548020725973013e-07, "loss": 0.6022, "step": 15352 }, { "epoch": 0.8967873831775701, "grad_norm": 1.1099597215652466, "learning_rate": 5.541808576343355e-07, "loss": 0.7187, "step": 15353 }, { "epoch": 0.8968457943925233, "grad_norm": 2.050771713256836, "learning_rate": 5.535599807434488e-07, "loss": 0.7681, "step": 15354 }, { "epoch": 0.8969042056074766, "grad_norm": 0.9918710589408875, "learning_rate": 5.529394419468592e-07, "loss": 0.689, "step": 15355 }, { "epoch": 0.89696261682243, "grad_norm": 0.9612051248550415, "learning_rate": 5.523192412667811e-07, "loss": 0.6117, "step": 15356 }, { "epoch": 0.8970210280373832, "grad_norm": 2.0902135372161865, "learning_rate": 5.516993787254077e-07, "loss": 0.8933, "step": 15357 }, { "epoch": 0.8970794392523365, "grad_norm": 1.0806461572647095, "learning_rate": 5.510798543449269e-07, "loss": 0.7594, "step": 15358 }, { "epoch": 0.8971378504672897, "grad_norm": 1.1780489683151245, "learning_rate": 5.5046066814751e-07, "loss": 0.9011, "step": 15359 }, { "epoch": 0.897196261682243, "grad_norm": 0.9795289039611816, "learning_rate": 5.49841820155319e-07, "loss": 0.624, "step": 15360 }, { "epoch": 0.8972546728971963, "grad_norm": 1.4099992513656616, "learning_rate": 5.492233103905042e-07, "loss": 0.8979, "step": 15361 }, { "epoch": 0.8973130841121495, "grad_norm": 1.0781348943710327, "learning_rate": 5.486051388751989e-07, "loss": 0.688, "step": 15362 }, { "epoch": 0.8973714953271028, "grad_norm": 3.0384039878845215, "learning_rate": 5.479873056315321e-07, "loss": 0.6539, "step": 15363 }, { "epoch": 0.8974299065420561, "grad_norm": 1.066466212272644, "learning_rate": 5.473698106816127e-07, "loss": 0.7372, "step": 15364 }, { "epoch": 0.8974883177570093, "grad_norm": 0.8588409423828125, "learning_rate": 5.467526540475443e-07, "loss": 0.6848, "step": 15365 }, { "epoch": 0.8975467289719626, "grad_norm": 1.1280266046524048, "learning_rate": 5.461358357514135e-07, "loss": 0.6739, "step": 15366 }, { "epoch": 0.8976051401869158, "grad_norm": 1.0646559000015259, "learning_rate": 5.455193558152972e-07, "loss": 0.6627, "step": 15367 }, { "epoch": 0.8976635514018692, "grad_norm": 1.22447669506073, "learning_rate": 5.449032142612609e-07, "loss": 0.7928, "step": 15368 }, { "epoch": 0.8977219626168225, "grad_norm": 1.185652732849121, "learning_rate": 5.442874111113539e-07, "loss": 0.6505, "step": 15369 }, { "epoch": 0.8977803738317757, "grad_norm": 0.7903848886489868, "learning_rate": 5.436719463876173e-07, "loss": 0.5206, "step": 15370 }, { "epoch": 0.897838785046729, "grad_norm": 1.0334380865097046, "learning_rate": 5.430568201120812e-07, "loss": 0.7822, "step": 15371 }, { "epoch": 0.8978971962616823, "grad_norm": 0.9966158866882324, "learning_rate": 5.42442032306757e-07, "loss": 0.9586, "step": 15372 }, { "epoch": 0.8979556074766355, "grad_norm": 0.8496277332305908, "learning_rate": 5.418275829936537e-07, "loss": 0.4757, "step": 15373 }, { "epoch": 0.8980140186915888, "grad_norm": 0.8216811418533325, "learning_rate": 5.412134721947593e-07, "loss": 0.6999, "step": 15374 }, { "epoch": 0.898072429906542, "grad_norm": 0.9518886804580688, "learning_rate": 5.405996999320529e-07, "loss": 0.7289, "step": 15375 }, { "epoch": 0.8981308411214953, "grad_norm": 1.0668063163757324, "learning_rate": 5.399862662275035e-07, "loss": 0.773, "step": 15376 }, { "epoch": 0.8981892523364486, "grad_norm": 1.1122100353240967, "learning_rate": 5.393731711030647e-07, "loss": 0.6084, "step": 15377 }, { "epoch": 0.8982476635514018, "grad_norm": 1.229195475578308, "learning_rate": 5.387604145806824e-07, "loss": 0.8127, "step": 15378 }, { "epoch": 0.8983060747663552, "grad_norm": 1.059600830078125, "learning_rate": 5.381479966822866e-07, "loss": 0.6209, "step": 15379 }, { "epoch": 0.8983644859813084, "grad_norm": 1.2693791389465332, "learning_rate": 5.375359174297922e-07, "loss": 0.843, "step": 15380 }, { "epoch": 0.8984228971962617, "grad_norm": 0.9406533241271973, "learning_rate": 5.369241768451105e-07, "loss": 0.7067, "step": 15381 }, { "epoch": 0.898481308411215, "grad_norm": 1.1100432872772217, "learning_rate": 5.36312774950134e-07, "loss": 0.8517, "step": 15382 }, { "epoch": 0.8985397196261682, "grad_norm": 0.9385004639625549, "learning_rate": 5.357017117667473e-07, "loss": 0.6626, "step": 15383 }, { "epoch": 0.8985981308411215, "grad_norm": 1.0538125038146973, "learning_rate": 5.350909873168186e-07, "loss": 0.8242, "step": 15384 }, { "epoch": 0.8986565420560748, "grad_norm": 1.4677358865737915, "learning_rate": 5.344806016222059e-07, "loss": 0.8309, "step": 15385 }, { "epoch": 0.898714953271028, "grad_norm": 2.229884147644043, "learning_rate": 5.338705547047562e-07, "loss": 0.7561, "step": 15386 }, { "epoch": 0.8987733644859813, "grad_norm": 1.259458065032959, "learning_rate": 5.332608465863054e-07, "loss": 0.7779, "step": 15387 }, { "epoch": 0.8988317757009345, "grad_norm": 0.9707046747207642, "learning_rate": 5.326514772886715e-07, "loss": 0.8089, "step": 15388 }, { "epoch": 0.8988901869158878, "grad_norm": 0.7729038596153259, "learning_rate": 5.320424468336672e-07, "loss": 0.539, "step": 15389 }, { "epoch": 0.8989485981308412, "grad_norm": 0.8932588696479797, "learning_rate": 5.314337552430881e-07, "loss": 0.7801, "step": 15390 }, { "epoch": 0.8990070093457944, "grad_norm": 1.0766440629959106, "learning_rate": 5.308254025387216e-07, "loss": 0.8271, "step": 15391 }, { "epoch": 0.8990654205607477, "grad_norm": 1.0058836936950684, "learning_rate": 5.302173887423389e-07, "loss": 0.9109, "step": 15392 }, { "epoch": 0.899123831775701, "grad_norm": 1.1097376346588135, "learning_rate": 5.296097138757017e-07, "loss": 0.7886, "step": 15393 }, { "epoch": 0.8991822429906542, "grad_norm": 1.0028311014175415, "learning_rate": 5.290023779605624e-07, "loss": 0.6952, "step": 15394 }, { "epoch": 0.8992406542056075, "grad_norm": 1.3524248600006104, "learning_rate": 5.283953810186526e-07, "loss": 0.911, "step": 15395 }, { "epoch": 0.8992990654205607, "grad_norm": 0.9340657591819763, "learning_rate": 5.277887230717027e-07, "loss": 0.8241, "step": 15396 }, { "epoch": 0.899357476635514, "grad_norm": 1.0082473754882812, "learning_rate": 5.271824041414197e-07, "loss": 0.964, "step": 15397 }, { "epoch": 0.8994158878504673, "grad_norm": 0.9428340792655945, "learning_rate": 5.265764242495075e-07, "loss": 0.7954, "step": 15398 }, { "epoch": 0.8994742990654205, "grad_norm": 0.9602389335632324, "learning_rate": 5.259707834176552e-07, "loss": 0.7059, "step": 15399 }, { "epoch": 0.8995327102803738, "grad_norm": 1.0273659229278564, "learning_rate": 5.253654816675368e-07, "loss": 0.6889, "step": 15400 }, { "epoch": 0.899591121495327, "grad_norm": 1.2874335050582886, "learning_rate": 5.247605190208182e-07, "loss": 0.6058, "step": 15401 }, { "epoch": 0.8996495327102804, "grad_norm": 1.0848695039749146, "learning_rate": 5.241558954991499e-07, "loss": 0.803, "step": 15402 }, { "epoch": 0.8997079439252337, "grad_norm": 1.0682181119918823, "learning_rate": 5.235516111241734e-07, "loss": 0.7351, "step": 15403 }, { "epoch": 0.8997663551401869, "grad_norm": 1.009964942932129, "learning_rate": 5.229476659175158e-07, "loss": 0.7338, "step": 15404 }, { "epoch": 0.8998247663551402, "grad_norm": 0.9675905108451843, "learning_rate": 5.223440599007912e-07, "loss": 0.5865, "step": 15405 }, { "epoch": 0.8998831775700935, "grad_norm": 1.2740824222564697, "learning_rate": 5.217407930956064e-07, "loss": 0.8505, "step": 15406 }, { "epoch": 0.8999415887850467, "grad_norm": 1.0539578199386597, "learning_rate": 5.211378655235499e-07, "loss": 0.7418, "step": 15407 }, { "epoch": 0.9, "grad_norm": 1.448386788368225, "learning_rate": 5.205352772062012e-07, "loss": 0.747, "step": 15408 }, { "epoch": 0.9000584112149532, "grad_norm": 1.276166558265686, "learning_rate": 5.199330281651271e-07, "loss": 0.7985, "step": 15409 }, { "epoch": 0.9001168224299065, "grad_norm": 0.8861923813819885, "learning_rate": 5.19331118421883e-07, "loss": 0.7192, "step": 15410 }, { "epoch": 0.9001752336448599, "grad_norm": 1.9420720338821411, "learning_rate": 5.187295479980136e-07, "loss": 0.7857, "step": 15411 }, { "epoch": 0.900233644859813, "grad_norm": 1.0966435670852661, "learning_rate": 5.181283169150486e-07, "loss": 0.7973, "step": 15412 }, { "epoch": 0.9002920560747664, "grad_norm": 0.9325107932090759, "learning_rate": 5.175274251945028e-07, "loss": 0.6835, "step": 15413 }, { "epoch": 0.9003504672897197, "grad_norm": 0.9847521185874939, "learning_rate": 5.169268728578858e-07, "loss": 0.6717, "step": 15414 }, { "epoch": 0.9004088785046729, "grad_norm": 0.9864534735679626, "learning_rate": 5.163266599266914e-07, "loss": 0.7116, "step": 15415 }, { "epoch": 0.9004672897196262, "grad_norm": 0.9785268306732178, "learning_rate": 5.157267864224025e-07, "loss": 0.7156, "step": 15416 }, { "epoch": 0.9005257009345794, "grad_norm": 1.3937324285507202, "learning_rate": 5.151272523664885e-07, "loss": 0.7951, "step": 15417 }, { "epoch": 0.9005841121495327, "grad_norm": 1.2262098789215088, "learning_rate": 5.145280577804046e-07, "loss": 1.0374, "step": 15418 }, { "epoch": 0.900642523364486, "grad_norm": 1.1374300718307495, "learning_rate": 5.139292026855991e-07, "loss": 0.7909, "step": 15419 }, { "epoch": 0.9007009345794392, "grad_norm": 1.6247713565826416, "learning_rate": 5.133306871035038e-07, "loss": 0.6863, "step": 15420 }, { "epoch": 0.9007593457943925, "grad_norm": 1.1253455877304077, "learning_rate": 5.127325110555426e-07, "loss": 0.7367, "step": 15421 }, { "epoch": 0.9008177570093457, "grad_norm": 1.1065863370895386, "learning_rate": 5.121346745631228e-07, "loss": 0.5759, "step": 15422 }, { "epoch": 0.9008761682242991, "grad_norm": 1.1245176792144775, "learning_rate": 5.115371776476397e-07, "loss": 0.8763, "step": 15423 }, { "epoch": 0.9009345794392524, "grad_norm": 0.8977612257003784, "learning_rate": 5.109400203304815e-07, "loss": 0.7216, "step": 15424 }, { "epoch": 0.9009929906542056, "grad_norm": 0.9985150694847107, "learning_rate": 5.103432026330179e-07, "loss": 0.8666, "step": 15425 }, { "epoch": 0.9010514018691589, "grad_norm": 1.0756055116653442, "learning_rate": 5.097467245766107e-07, "loss": 0.7679, "step": 15426 }, { "epoch": 0.9011098130841122, "grad_norm": 0.8349552154541016, "learning_rate": 5.091505861826096e-07, "loss": 0.6451, "step": 15427 }, { "epoch": 0.9011682242990654, "grad_norm": 1.0553168058395386, "learning_rate": 5.085547874723473e-07, "loss": 0.7804, "step": 15428 }, { "epoch": 0.9012266355140187, "grad_norm": 1.108280897140503, "learning_rate": 5.079593284671524e-07, "loss": 0.5989, "step": 15429 }, { "epoch": 0.9012850467289719, "grad_norm": 1.680820107460022, "learning_rate": 5.073642091883313e-07, "loss": 0.8769, "step": 15430 }, { "epoch": 0.9013434579439252, "grad_norm": 0.9197506904602051, "learning_rate": 5.067694296571879e-07, "loss": 0.6333, "step": 15431 }, { "epoch": 0.9014018691588785, "grad_norm": 1.239758849143982, "learning_rate": 5.061749898950097e-07, "loss": 0.6083, "step": 15432 }, { "epoch": 0.9014602803738317, "grad_norm": 0.9807267189025879, "learning_rate": 5.055808899230696e-07, "loss": 0.6826, "step": 15433 }, { "epoch": 0.9015186915887851, "grad_norm": 1.3338676691055298, "learning_rate": 5.049871297626329e-07, "loss": 0.7495, "step": 15434 }, { "epoch": 0.9015771028037384, "grad_norm": 1.1111537218093872, "learning_rate": 5.043937094349493e-07, "loss": 0.7648, "step": 15435 }, { "epoch": 0.9016355140186916, "grad_norm": 1.2822757959365845, "learning_rate": 5.038006289612585e-07, "loss": 0.6604, "step": 15436 }, { "epoch": 0.9016939252336449, "grad_norm": 1.1147804260253906, "learning_rate": 5.032078883627877e-07, "loss": 0.5216, "step": 15437 }, { "epoch": 0.9017523364485981, "grad_norm": 0.8781611323356628, "learning_rate": 5.026154876607503e-07, "loss": 0.5562, "step": 15438 }, { "epoch": 0.9018107476635514, "grad_norm": 1.0618722438812256, "learning_rate": 5.020234268763502e-07, "loss": 0.7885, "step": 15439 }, { "epoch": 0.9018691588785047, "grad_norm": 2.3818700313568115, "learning_rate": 5.014317060307749e-07, "loss": 0.7522, "step": 15440 }, { "epoch": 0.9019275700934579, "grad_norm": 1.1391900777816772, "learning_rate": 5.008403251452054e-07, "loss": 0.6964, "step": 15441 }, { "epoch": 0.9019859813084112, "grad_norm": 1.379591703414917, "learning_rate": 5.002492842408058e-07, "loss": 0.797, "step": 15442 }, { "epoch": 0.9020443925233644, "grad_norm": 0.8429427742958069, "learning_rate": 4.996585833387302e-07, "loss": 0.7409, "step": 15443 }, { "epoch": 0.9021028037383177, "grad_norm": 0.8793429732322693, "learning_rate": 4.990682224601228e-07, "loss": 0.6486, "step": 15444 }, { "epoch": 0.9021612149532711, "grad_norm": 0.9616079926490784, "learning_rate": 4.984782016261092e-07, "loss": 0.7689, "step": 15445 }, { "epoch": 0.9022196261682243, "grad_norm": 1.347670316696167, "learning_rate": 4.978885208578077e-07, "loss": 0.7486, "step": 15446 }, { "epoch": 0.9022780373831776, "grad_norm": 1.7371785640716553, "learning_rate": 4.972991801763239e-07, "loss": 0.856, "step": 15447 }, { "epoch": 0.9023364485981309, "grad_norm": 1.0926045179367065, "learning_rate": 4.967101796027507e-07, "loss": 0.7115, "step": 15448 }, { "epoch": 0.9023948598130841, "grad_norm": 1.1554207801818848, "learning_rate": 4.961215191581692e-07, "loss": 0.8683, "step": 15449 }, { "epoch": 0.9024532710280374, "grad_norm": 1.0924547910690308, "learning_rate": 4.95533198863648e-07, "loss": 0.6811, "step": 15450 }, { "epoch": 0.9025116822429906, "grad_norm": 1.3106850385665894, "learning_rate": 4.949452187402415e-07, "loss": 0.7075, "step": 15451 }, { "epoch": 0.9025700934579439, "grad_norm": 1.2962557077407837, "learning_rate": 4.94357578808995e-07, "loss": 0.7485, "step": 15452 }, { "epoch": 0.9026285046728972, "grad_norm": 1.0890944004058838, "learning_rate": 4.937702790909416e-07, "loss": 0.8202, "step": 15453 }, { "epoch": 0.9026869158878504, "grad_norm": 0.92237389087677, "learning_rate": 4.931833196071012e-07, "loss": 0.6859, "step": 15454 }, { "epoch": 0.9027453271028038, "grad_norm": 1.5490738153457642, "learning_rate": 4.925967003784804e-07, "loss": 0.7677, "step": 15455 }, { "epoch": 0.902803738317757, "grad_norm": 1.4170242547988892, "learning_rate": 4.920104214260745e-07, "loss": 0.7595, "step": 15456 }, { "epoch": 0.9028621495327103, "grad_norm": 1.0343018770217896, "learning_rate": 4.914244827708681e-07, "loss": 0.7186, "step": 15457 }, { "epoch": 0.9029205607476636, "grad_norm": 1.0343252420425415, "learning_rate": 4.908388844338297e-07, "loss": 0.6365, "step": 15458 }, { "epoch": 0.9029789719626168, "grad_norm": 1.0252082347869873, "learning_rate": 4.902536264359203e-07, "loss": 0.8653, "step": 15459 }, { "epoch": 0.9030373831775701, "grad_norm": 1.3207247257232666, "learning_rate": 4.896687087980878e-07, "loss": 0.7693, "step": 15460 }, { "epoch": 0.9030957943925234, "grad_norm": 0.96849125623703, "learning_rate": 4.890841315412643e-07, "loss": 0.6547, "step": 15461 }, { "epoch": 0.9031542056074766, "grad_norm": 0.9937537908554077, "learning_rate": 4.88499894686374e-07, "loss": 0.6476, "step": 15462 }, { "epoch": 0.9032126168224299, "grad_norm": 1.1664690971374512, "learning_rate": 4.879159982543246e-07, "loss": 0.8219, "step": 15463 }, { "epoch": 0.9032710280373831, "grad_norm": 1.1454824209213257, "learning_rate": 4.873324422660175e-07, "loss": 0.6941, "step": 15464 }, { "epoch": 0.9033294392523364, "grad_norm": 1.0784649848937988, "learning_rate": 4.86749226742338e-07, "loss": 0.7786, "step": 15465 }, { "epoch": 0.9033878504672898, "grad_norm": 0.8481408357620239, "learning_rate": 4.86166351704156e-07, "loss": 0.5419, "step": 15466 }, { "epoch": 0.903446261682243, "grad_norm": 1.805382251739502, "learning_rate": 4.855838171723382e-07, "loss": 0.7759, "step": 15467 }, { "epoch": 0.9035046728971963, "grad_norm": 1.1168780326843262, "learning_rate": 4.850016231677302e-07, "loss": 0.5933, "step": 15468 }, { "epoch": 0.9035630841121496, "grad_norm": 1.079418659210205, "learning_rate": 4.844197697111697e-07, "loss": 0.7526, "step": 15469 }, { "epoch": 0.9036214953271028, "grad_norm": 1.7765189409255981, "learning_rate": 4.838382568234845e-07, "loss": 0.667, "step": 15470 }, { "epoch": 0.9036799065420561, "grad_norm": 1.1037724018096924, "learning_rate": 4.832570845254836e-07, "loss": 0.73, "step": 15471 }, { "epoch": 0.9037383177570093, "grad_norm": 1.0754181146621704, "learning_rate": 4.826762528379692e-07, "loss": 0.699, "step": 15472 }, { "epoch": 0.9037967289719626, "grad_norm": 1.1250486373901367, "learning_rate": 4.82095761781729e-07, "loss": 0.7011, "step": 15473 }, { "epoch": 0.9038551401869159, "grad_norm": 1.1017272472381592, "learning_rate": 4.81515611377541e-07, "loss": 0.8224, "step": 15474 }, { "epoch": 0.9039135514018691, "grad_norm": 1.0091780424118042, "learning_rate": 4.809358016461663e-07, "loss": 0.826, "step": 15475 }, { "epoch": 0.9039719626168224, "grad_norm": 0.9614081978797913, "learning_rate": 4.803563326083582e-07, "loss": 0.6913, "step": 15476 }, { "epoch": 0.9040303738317756, "grad_norm": 1.3700350522994995, "learning_rate": 4.797772042848581e-07, "loss": 0.7438, "step": 15477 }, { "epoch": 0.904088785046729, "grad_norm": 0.8259237408638, "learning_rate": 4.791984166963892e-07, "loss": 0.6152, "step": 15478 }, { "epoch": 0.9041471962616823, "grad_norm": 1.2197790145874023, "learning_rate": 4.786199698636707e-07, "loss": 0.7646, "step": 15479 }, { "epoch": 0.9042056074766355, "grad_norm": 1.5129581689834595, "learning_rate": 4.780418638074024e-07, "loss": 0.8412, "step": 15480 }, { "epoch": 0.9042640186915888, "grad_norm": 1.3029181957244873, "learning_rate": 4.77464098548277e-07, "loss": 0.7056, "step": 15481 }, { "epoch": 0.9043224299065421, "grad_norm": 1.535611629486084, "learning_rate": 4.768866741069744e-07, "loss": 0.9714, "step": 15482 }, { "epoch": 0.9043808411214953, "grad_norm": 1.091774344444275, "learning_rate": 4.7630959050415703e-07, "loss": 0.7014, "step": 15483 }, { "epoch": 0.9044392523364486, "grad_norm": 0.8378831744194031, "learning_rate": 4.757328477604839e-07, "loss": 0.7384, "step": 15484 }, { "epoch": 0.9044976635514018, "grad_norm": 1.070254921913147, "learning_rate": 4.7515644589659184e-07, "loss": 0.7146, "step": 15485 }, { "epoch": 0.9045560747663551, "grad_norm": 1.2557477951049805, "learning_rate": 4.7458038493311433e-07, "loss": 0.8116, "step": 15486 }, { "epoch": 0.9046144859813084, "grad_norm": 1.100651741027832, "learning_rate": 4.7400466489066823e-07, "loss": 0.612, "step": 15487 }, { "epoch": 0.9046728971962616, "grad_norm": 2.158904790878296, "learning_rate": 4.7342928578985814e-07, "loss": 0.719, "step": 15488 }, { "epoch": 0.904731308411215, "grad_norm": 0.8856353163719177, "learning_rate": 4.7285424765127877e-07, "loss": 0.637, "step": 15489 }, { "epoch": 0.9047897196261683, "grad_norm": 1.22686767578125, "learning_rate": 4.722795504955102e-07, "loss": 0.7632, "step": 15490 }, { "epoch": 0.9048481308411215, "grad_norm": 1.1638712882995605, "learning_rate": 4.7170519434311946e-07, "loss": 0.9126, "step": 15491 }, { "epoch": 0.9049065420560748, "grad_norm": 1.1295889616012573, "learning_rate": 4.7113117921466557e-07, "loss": 0.8429, "step": 15492 }, { "epoch": 0.904964953271028, "grad_norm": 0.9361625909805298, "learning_rate": 4.705575051306921e-07, "loss": 0.6035, "step": 15493 }, { "epoch": 0.9050233644859813, "grad_norm": 1.0946327447891235, "learning_rate": 4.699841721117315e-07, "loss": 0.712, "step": 15494 }, { "epoch": 0.9050817757009346, "grad_norm": 1.0587586164474487, "learning_rate": 4.694111801783041e-07, "loss": 0.6381, "step": 15495 }, { "epoch": 0.9051401869158878, "grad_norm": 1.3742049932479858, "learning_rate": 4.6883852935091566e-07, "loss": 0.669, "step": 15496 }, { "epoch": 0.9051985981308411, "grad_norm": 1.333124041557312, "learning_rate": 4.6826621965006316e-07, "loss": 0.7211, "step": 15497 }, { "epoch": 0.9052570093457943, "grad_norm": 1.2310150861740112, "learning_rate": 4.6769425109623013e-07, "loss": 0.8793, "step": 15498 }, { "epoch": 0.9053154205607477, "grad_norm": 1.0937602519989014, "learning_rate": 4.6712262370988805e-07, "loss": 0.7496, "step": 15499 }, { "epoch": 0.905373831775701, "grad_norm": 1.3234277963638306, "learning_rate": 4.665513375114961e-07, "loss": 0.8169, "step": 15500 }, { "epoch": 0.9054322429906542, "grad_norm": 1.015620231628418, "learning_rate": 4.6598039252149896e-07, "loss": 0.6824, "step": 15501 }, { "epoch": 0.9054906542056075, "grad_norm": 1.0286736488342285, "learning_rate": 4.654097887603315e-07, "loss": 0.7666, "step": 15502 }, { "epoch": 0.9055490654205608, "grad_norm": 1.2179734706878662, "learning_rate": 4.6483952624841846e-07, "loss": 0.9286, "step": 15503 }, { "epoch": 0.905607476635514, "grad_norm": 1.5502793788909912, "learning_rate": 4.642696050061668e-07, "loss": 0.8385, "step": 15504 }, { "epoch": 0.9056658878504673, "grad_norm": 1.0400984287261963, "learning_rate": 4.6370002505397695e-07, "loss": 0.8303, "step": 15505 }, { "epoch": 0.9057242990654205, "grad_norm": 1.1679117679595947, "learning_rate": 4.6313078641223255e-07, "loss": 0.7053, "step": 15506 }, { "epoch": 0.9057827102803738, "grad_norm": 0.8699294924736023, "learning_rate": 4.625618891013095e-07, "loss": 0.5984, "step": 15507 }, { "epoch": 0.9058411214953271, "grad_norm": 0.9527546167373657, "learning_rate": 4.6199333314156604e-07, "loss": 0.6628, "step": 15508 }, { "epoch": 0.9058995327102803, "grad_norm": 1.1932039260864258, "learning_rate": 4.614251185533525e-07, "loss": 0.8355, "step": 15509 }, { "epoch": 0.9059579439252337, "grad_norm": 1.1219128370285034, "learning_rate": 4.6085724535700594e-07, "loss": 0.7026, "step": 15510 }, { "epoch": 0.906016355140187, "grad_norm": 0.8881827592849731, "learning_rate": 4.6028971357285126e-07, "loss": 0.6705, "step": 15511 }, { "epoch": 0.9060747663551402, "grad_norm": 0.8569638729095459, "learning_rate": 4.5972252322119994e-07, "loss": 0.5854, "step": 15512 }, { "epoch": 0.9061331775700935, "grad_norm": 1.313978910446167, "learning_rate": 4.591556743223513e-07, "loss": 0.7075, "step": 15513 }, { "epoch": 0.9061915887850467, "grad_norm": 0.9924944639205933, "learning_rate": 4.585891668965947e-07, "loss": 0.7356, "step": 15514 }, { "epoch": 0.90625, "grad_norm": 1.5705187320709229, "learning_rate": 4.5802300096420725e-07, "loss": 0.7459, "step": 15515 }, { "epoch": 0.9063084112149533, "grad_norm": 1.421546459197998, "learning_rate": 4.574571765454483e-07, "loss": 0.7724, "step": 15516 }, { "epoch": 0.9063668224299065, "grad_norm": 1.375538945198059, "learning_rate": 4.5689169366057274e-07, "loss": 0.912, "step": 15517 }, { "epoch": 0.9064252336448598, "grad_norm": 1.229906439781189, "learning_rate": 4.563265523298177e-07, "loss": 0.9349, "step": 15518 }, { "epoch": 0.906483644859813, "grad_norm": 1.2463563680648804, "learning_rate": 4.557617525734093e-07, "loss": 0.9638, "step": 15519 }, { "epoch": 0.9065420560747663, "grad_norm": 1.4927818775177002, "learning_rate": 4.5519729441156566e-07, "loss": 0.6938, "step": 15520 }, { "epoch": 0.9066004672897197, "grad_norm": 0.9634555578231812, "learning_rate": 4.5463317786448413e-07, "loss": 0.6781, "step": 15521 }, { "epoch": 0.9066588785046729, "grad_norm": 1.2914881706237793, "learning_rate": 4.540694029523596e-07, "loss": 0.7133, "step": 15522 }, { "epoch": 0.9067172897196262, "grad_norm": 1.0314445495605469, "learning_rate": 4.535059696953681e-07, "loss": 0.8459, "step": 15523 }, { "epoch": 0.9067757009345795, "grad_norm": 1.047530174255371, "learning_rate": 4.5294287811367245e-07, "loss": 0.7122, "step": 15524 }, { "epoch": 0.9068341121495327, "grad_norm": 0.9658904671669006, "learning_rate": 4.5238012822742874e-07, "loss": 0.7863, "step": 15525 }, { "epoch": 0.906892523364486, "grad_norm": 1.2680799961090088, "learning_rate": 4.518177200567786e-07, "loss": 0.7652, "step": 15526 }, { "epoch": 0.9069509345794392, "grad_norm": 0.9553167223930359, "learning_rate": 4.5125565362185155e-07, "loss": 0.6881, "step": 15527 }, { "epoch": 0.9070093457943925, "grad_norm": 1.0536428689956665, "learning_rate": 4.506939289427625e-07, "loss": 0.7615, "step": 15528 }, { "epoch": 0.9070677570093458, "grad_norm": 1.0885690450668335, "learning_rate": 4.501325460396155e-07, "loss": 0.7053, "step": 15529 }, { "epoch": 0.907126168224299, "grad_norm": 0.9022956490516663, "learning_rate": 4.4957150493250336e-07, "loss": 0.6232, "step": 15530 }, { "epoch": 0.9071845794392523, "grad_norm": 1.2817097902297974, "learning_rate": 4.490108056415077e-07, "loss": 0.7311, "step": 15531 }, { "epoch": 0.9072429906542057, "grad_norm": 1.0039262771606445, "learning_rate": 4.484504481866958e-07, "loss": 0.6601, "step": 15532 }, { "epoch": 0.9073014018691589, "grad_norm": 0.9224274158477783, "learning_rate": 4.478904325881228e-07, "loss": 0.8286, "step": 15533 }, { "epoch": 0.9073598130841122, "grad_norm": 1.0525418519973755, "learning_rate": 4.4733075886583043e-07, "loss": 0.6677, "step": 15534 }, { "epoch": 0.9074182242990654, "grad_norm": 1.0404905080795288, "learning_rate": 4.467714270398504e-07, "loss": 0.8071, "step": 15535 }, { "epoch": 0.9074766355140187, "grad_norm": 1.0631543397903442, "learning_rate": 4.4621243713020344e-07, "loss": 0.7488, "step": 15536 }, { "epoch": 0.907535046728972, "grad_norm": 1.0483568906784058, "learning_rate": 4.456537891568957e-07, "loss": 0.7715, "step": 15537 }, { "epoch": 0.9075934579439252, "grad_norm": 6.063716411590576, "learning_rate": 4.450954831399212e-07, "loss": 0.7628, "step": 15538 }, { "epoch": 0.9076518691588785, "grad_norm": 1.4061954021453857, "learning_rate": 4.445375190992607e-07, "loss": 0.7822, "step": 15539 }, { "epoch": 0.9077102803738317, "grad_norm": 1.4215435981750488, "learning_rate": 4.4397989705488697e-07, "loss": 0.7275, "step": 15540 }, { "epoch": 0.907768691588785, "grad_norm": 1.4382213354110718, "learning_rate": 4.4342261702675306e-07, "loss": 0.8866, "step": 15541 }, { "epoch": 0.9078271028037384, "grad_norm": 0.9956925511360168, "learning_rate": 4.428656790348096e-07, "loss": 0.6967, "step": 15542 }, { "epoch": 0.9078855140186916, "grad_norm": 1.1374053955078125, "learning_rate": 4.4230908309898734e-07, "loss": 0.6953, "step": 15543 }, { "epoch": 0.9079439252336449, "grad_norm": 1.0336647033691406, "learning_rate": 4.417528292392059e-07, "loss": 0.6812, "step": 15544 }, { "epoch": 0.9080023364485982, "grad_norm": 0.9855998754501343, "learning_rate": 4.4119691747537717e-07, "loss": 0.8007, "step": 15545 }, { "epoch": 0.9080607476635514, "grad_norm": 0.9696398377418518, "learning_rate": 4.406413478273941e-07, "loss": 0.6895, "step": 15546 }, { "epoch": 0.9081191588785047, "grad_norm": 1.780764102935791, "learning_rate": 4.40086120315143e-07, "loss": 0.8863, "step": 15547 }, { "epoch": 0.9081775700934579, "grad_norm": 1.283500075340271, "learning_rate": 4.395312349584968e-07, "loss": 0.8983, "step": 15548 }, { "epoch": 0.9082359813084112, "grad_norm": 1.1649812459945679, "learning_rate": 4.3897669177731196e-07, "loss": 0.6659, "step": 15549 }, { "epoch": 0.9082943925233645, "grad_norm": 2.3689651489257812, "learning_rate": 4.3842249079143917e-07, "loss": 0.7615, "step": 15550 }, { "epoch": 0.9083528037383177, "grad_norm": 1.4086769819259644, "learning_rate": 4.378686320207115e-07, "loss": 0.7271, "step": 15551 }, { "epoch": 0.908411214953271, "grad_norm": 1.1660429239273071, "learning_rate": 4.37315115484952e-07, "loss": 0.7807, "step": 15552 }, { "epoch": 0.9084696261682244, "grad_norm": 1.0654058456420898, "learning_rate": 4.3676194120397363e-07, "loss": 0.6507, "step": 15553 }, { "epoch": 0.9085280373831776, "grad_norm": 1.8383651971817017, "learning_rate": 4.362091091975729e-07, "loss": 0.8054, "step": 15554 }, { "epoch": 0.9085864485981309, "grad_norm": 2.0646305084228516, "learning_rate": 4.3565661948553606e-07, "loss": 0.733, "step": 15555 }, { "epoch": 0.9086448598130841, "grad_norm": 0.8558652400970459, "learning_rate": 4.351044720876374e-07, "loss": 0.6372, "step": 15556 }, { "epoch": 0.9087032710280374, "grad_norm": 1.0860679149627686, "learning_rate": 4.3455266702363997e-07, "loss": 0.728, "step": 15557 }, { "epoch": 0.9087616822429907, "grad_norm": 0.9980836510658264, "learning_rate": 4.340012043132902e-07, "loss": 0.6919, "step": 15558 }, { "epoch": 0.9088200934579439, "grad_norm": 1.0955737829208374, "learning_rate": 4.334500839763278e-07, "loss": 0.91, "step": 15559 }, { "epoch": 0.9088785046728972, "grad_norm": 1.1765261888504028, "learning_rate": 4.328993060324782e-07, "loss": 0.7572, "step": 15560 }, { "epoch": 0.9089369158878504, "grad_norm": 1.1250745058059692, "learning_rate": 4.3234887050145225e-07, "loss": 0.7317, "step": 15561 }, { "epoch": 0.9089953271028037, "grad_norm": 1.2000094652175903, "learning_rate": 4.3179877740295083e-07, "loss": 0.8673, "step": 15562 }, { "epoch": 0.909053738317757, "grad_norm": 1.2226366996765137, "learning_rate": 4.312490267566616e-07, "loss": 0.7835, "step": 15563 }, { "epoch": 0.9091121495327102, "grad_norm": 1.0015976428985596, "learning_rate": 4.3069961858226093e-07, "loss": 0.801, "step": 15564 }, { "epoch": 0.9091705607476636, "grad_norm": 0.9476168751716614, "learning_rate": 4.3015055289941544e-07, "loss": 0.7607, "step": 15565 }, { "epoch": 0.9092289719626169, "grad_norm": 1.0642099380493164, "learning_rate": 4.2960182972777267e-07, "loss": 0.9382, "step": 15566 }, { "epoch": 0.9092873831775701, "grad_norm": 0.9594845175743103, "learning_rate": 4.2905344908697245e-07, "loss": 0.7415, "step": 15567 }, { "epoch": 0.9093457943925234, "grad_norm": 0.8893963694572449, "learning_rate": 4.2850541099664246e-07, "loss": 0.7112, "step": 15568 }, { "epoch": 0.9094042056074766, "grad_norm": 0.9698365926742554, "learning_rate": 4.2795771547639584e-07, "loss": 0.9044, "step": 15569 }, { "epoch": 0.9094626168224299, "grad_norm": 1.1366130113601685, "learning_rate": 4.2741036254583923e-07, "loss": 0.6698, "step": 15570 }, { "epoch": 0.9095210280373832, "grad_norm": 1.211246371269226, "learning_rate": 4.268633522245591e-07, "loss": 0.8427, "step": 15571 }, { "epoch": 0.9095794392523364, "grad_norm": 0.9756643176078796, "learning_rate": 4.2631668453213316e-07, "loss": 0.7265, "step": 15572 }, { "epoch": 0.9096378504672897, "grad_norm": 1.097618579864502, "learning_rate": 4.2577035948812906e-07, "loss": 0.7555, "step": 15573 }, { "epoch": 0.909696261682243, "grad_norm": 0.7275300621986389, "learning_rate": 4.2522437711209564e-07, "loss": 0.5577, "step": 15574 }, { "epoch": 0.9097546728971962, "grad_norm": 0.738923192024231, "learning_rate": 4.2467873742358057e-07, "loss": 0.8306, "step": 15575 }, { "epoch": 0.9098130841121496, "grad_norm": 0.8740885257720947, "learning_rate": 4.2413344044210933e-07, "loss": 0.7043, "step": 15576 }, { "epoch": 0.9098714953271028, "grad_norm": 1.0190986394882202, "learning_rate": 4.235884861871975e-07, "loss": 0.7709, "step": 15577 }, { "epoch": 0.9099299065420561, "grad_norm": 0.657943069934845, "learning_rate": 4.230438746783516e-07, "loss": 0.5221, "step": 15578 }, { "epoch": 0.9099883177570094, "grad_norm": 1.0415184497833252, "learning_rate": 4.2249960593506056e-07, "loss": 0.7414, "step": 15579 }, { "epoch": 0.9100467289719626, "grad_norm": 0.9879477024078369, "learning_rate": 4.2195567997680654e-07, "loss": 0.6692, "step": 15580 }, { "epoch": 0.9101051401869159, "grad_norm": 1.229673147201538, "learning_rate": 4.214120968230573e-07, "loss": 0.7867, "step": 15581 }, { "epoch": 0.9101635514018691, "grad_norm": 0.9030339121818542, "learning_rate": 4.2086885649326616e-07, "loss": 0.7584, "step": 15582 }, { "epoch": 0.9102219626168224, "grad_norm": 0.995495080947876, "learning_rate": 4.2032595900687755e-07, "loss": 0.7545, "step": 15583 }, { "epoch": 0.9102803738317757, "grad_norm": 1.0543495416641235, "learning_rate": 4.1978340438332156e-07, "loss": 0.7163, "step": 15584 }, { "epoch": 0.9103387850467289, "grad_norm": 1.179701328277588, "learning_rate": 4.192411926420159e-07, "loss": 0.6612, "step": 15585 }, { "epoch": 0.9103971962616823, "grad_norm": 0.9555020332336426, "learning_rate": 4.1869932380236847e-07, "loss": 0.7192, "step": 15586 }, { "epoch": 0.9104556074766356, "grad_norm": 1.1813230514526367, "learning_rate": 4.181577978837714e-07, "loss": 0.7535, "step": 15587 }, { "epoch": 0.9105140186915888, "grad_norm": 0.998336911201477, "learning_rate": 4.1761661490560824e-07, "loss": 0.8237, "step": 15588 }, { "epoch": 0.9105724299065421, "grad_norm": 1.2853355407714844, "learning_rate": 4.170757748872456e-07, "loss": 0.861, "step": 15589 }, { "epoch": 0.9106308411214953, "grad_norm": 1.016668438911438, "learning_rate": 4.1653527784804247e-07, "loss": 0.9033, "step": 15590 }, { "epoch": 0.9106892523364486, "grad_norm": 1.2085505723953247, "learning_rate": 4.159951238073423e-07, "loss": 0.7826, "step": 15591 }, { "epoch": 0.9107476635514019, "grad_norm": 1.2970830202102661, "learning_rate": 4.154553127844785e-07, "loss": 0.8048, "step": 15592 }, { "epoch": 0.9108060747663551, "grad_norm": 1.0274134874343872, "learning_rate": 4.149158447987722e-07, "loss": 0.5894, "step": 15593 }, { "epoch": 0.9108644859813084, "grad_norm": 0.8142416477203369, "learning_rate": 4.143767198695281e-07, "loss": 0.6321, "step": 15594 }, { "epoch": 0.9109228971962616, "grad_norm": 1.170704960823059, "learning_rate": 4.1383793801604623e-07, "loss": 0.815, "step": 15595 }, { "epoch": 0.9109813084112149, "grad_norm": 1.2296974658966064, "learning_rate": 4.132994992576056e-07, "loss": 0.8355, "step": 15596 }, { "epoch": 0.9110397196261683, "grad_norm": 1.3069759607315063, "learning_rate": 4.127614036134797e-07, "loss": 0.7659, "step": 15597 }, { "epoch": 0.9110981308411215, "grad_norm": 1.087578535079956, "learning_rate": 4.122236511029276e-07, "loss": 0.6826, "step": 15598 }, { "epoch": 0.9111565420560748, "grad_norm": 12.628585815429688, "learning_rate": 4.116862417451939e-07, "loss": 0.706, "step": 15599 }, { "epoch": 0.9112149532710281, "grad_norm": 0.9717701077461243, "learning_rate": 4.111491755595154e-07, "loss": 0.6166, "step": 15600 }, { "epoch": 0.9112733644859813, "grad_norm": 1.5646010637283325, "learning_rate": 4.1061245256511227e-07, "loss": 0.6365, "step": 15601 }, { "epoch": 0.9113317757009346, "grad_norm": 1.0668740272521973, "learning_rate": 4.100760727811937e-07, "loss": 0.7989, "step": 15602 }, { "epoch": 0.9113901869158878, "grad_norm": 0.9715229868888855, "learning_rate": 4.095400362269597e-07, "loss": 0.7984, "step": 15603 }, { "epoch": 0.9114485981308411, "grad_norm": 0.9824392795562744, "learning_rate": 4.0900434292159175e-07, "loss": 0.6672, "step": 15604 }, { "epoch": 0.9115070093457944, "grad_norm": 1.1226911544799805, "learning_rate": 4.0846899288426666e-07, "loss": 0.575, "step": 15605 }, { "epoch": 0.9115654205607476, "grad_norm": 1.2077988386154175, "learning_rate": 4.0793398613414247e-07, "loss": 0.8263, "step": 15606 }, { "epoch": 0.9116238317757009, "grad_norm": 1.1821578741073608, "learning_rate": 4.07399322690365e-07, "loss": 0.7022, "step": 15607 }, { "epoch": 0.9116822429906543, "grad_norm": 0.958831250667572, "learning_rate": 4.068650025720755e-07, "loss": 0.6155, "step": 15608 }, { "epoch": 0.9117406542056075, "grad_norm": 0.8698938488960266, "learning_rate": 4.0633102579839433e-07, "loss": 0.7594, "step": 15609 }, { "epoch": 0.9117990654205608, "grad_norm": 1.051773190498352, "learning_rate": 4.057973923884351e-07, "loss": 0.7925, "step": 15610 }, { "epoch": 0.911857476635514, "grad_norm": 1.196473240852356, "learning_rate": 4.0526410236129467e-07, "loss": 0.6519, "step": 15611 }, { "epoch": 0.9119158878504673, "grad_norm": 0.9888662695884705, "learning_rate": 4.0473115573606004e-07, "loss": 0.706, "step": 15612 }, { "epoch": 0.9119742990654206, "grad_norm": 1.201212763786316, "learning_rate": 4.0419855253180706e-07, "loss": 0.7173, "step": 15613 }, { "epoch": 0.9120327102803738, "grad_norm": 1.1560531854629517, "learning_rate": 4.0366629276759715e-07, "loss": 0.7821, "step": 15614 }, { "epoch": 0.9120911214953271, "grad_norm": 1.0883032083511353, "learning_rate": 4.0313437646247954e-07, "loss": 0.8206, "step": 15615 }, { "epoch": 0.9121495327102803, "grad_norm": 0.8658832907676697, "learning_rate": 4.0260280363549454e-07, "loss": 0.6975, "step": 15616 }, { "epoch": 0.9122079439252336, "grad_norm": 1.0614620447158813, "learning_rate": 4.020715743056636e-07, "loss": 0.7822, "step": 15617 }, { "epoch": 0.912266355140187, "grad_norm": 0.9886086583137512, "learning_rate": 4.0154068849200257e-07, "loss": 0.7595, "step": 15618 }, { "epoch": 0.9123247663551401, "grad_norm": 0.9841863512992859, "learning_rate": 4.010101462135119e-07, "loss": 0.6558, "step": 15619 }, { "epoch": 0.9123831775700935, "grad_norm": 1.1552146673202515, "learning_rate": 4.0047994748917854e-07, "loss": 0.8792, "step": 15620 }, { "epoch": 0.9124415887850468, "grad_norm": 0.8569534420967102, "learning_rate": 3.9995009233798065e-07, "loss": 0.5836, "step": 15621 }, { "epoch": 0.9125, "grad_norm": 1.103745698928833, "learning_rate": 3.994205807788809e-07, "loss": 0.7624, "step": 15622 }, { "epoch": 0.9125584112149533, "grad_norm": 1.2506084442138672, "learning_rate": 3.988914128308308e-07, "loss": 0.7371, "step": 15623 }, { "epoch": 0.9126168224299065, "grad_norm": 0.9436774253845215, "learning_rate": 3.9836258851276955e-07, "loss": 0.7944, "step": 15624 }, { "epoch": 0.9126752336448598, "grad_norm": 1.835495114326477, "learning_rate": 3.978341078436243e-07, "loss": 0.787, "step": 15625 }, { "epoch": 0.9127336448598131, "grad_norm": 1.0126861333847046, "learning_rate": 3.9730597084231105e-07, "loss": 0.6662, "step": 15626 }, { "epoch": 0.9127920560747663, "grad_norm": 1.0467873811721802, "learning_rate": 3.9677817752773015e-07, "loss": 0.8146, "step": 15627 }, { "epoch": 0.9128504672897196, "grad_norm": 1.006531000137329, "learning_rate": 3.9625072791877326e-07, "loss": 0.7317, "step": 15628 }, { "epoch": 0.912908878504673, "grad_norm": 0.9816815257072449, "learning_rate": 3.9572362203431633e-07, "loss": 0.7178, "step": 15629 }, { "epoch": 0.9129672897196262, "grad_norm": 0.9984056949615479, "learning_rate": 3.9519685989322656e-07, "loss": 0.7541, "step": 15630 }, { "epoch": 0.9130257009345795, "grad_norm": 1.1873047351837158, "learning_rate": 3.946704415143565e-07, "loss": 0.7842, "step": 15631 }, { "epoch": 0.9130841121495327, "grad_norm": 1.5743242502212524, "learning_rate": 3.941443669165468e-07, "loss": 0.8428, "step": 15632 }, { "epoch": 0.913142523364486, "grad_norm": 1.180530309677124, "learning_rate": 3.9361863611862673e-07, "loss": 0.6435, "step": 15633 }, { "epoch": 0.9132009345794393, "grad_norm": 1.2684199810028076, "learning_rate": 3.9309324913941126e-07, "loss": 0.7823, "step": 15634 }, { "epoch": 0.9132593457943925, "grad_norm": 0.8862615823745728, "learning_rate": 3.925682059977043e-07, "loss": 0.7106, "step": 15635 }, { "epoch": 0.9133177570093458, "grad_norm": 1.3612154722213745, "learning_rate": 3.920435067122996e-07, "loss": 0.7166, "step": 15636 }, { "epoch": 0.913376168224299, "grad_norm": 1.021344542503357, "learning_rate": 3.915191513019745e-07, "loss": 0.7805, "step": 15637 }, { "epoch": 0.9134345794392523, "grad_norm": 0.8553653359413147, "learning_rate": 3.909951397854972e-07, "loss": 0.8517, "step": 15638 }, { "epoch": 0.9134929906542056, "grad_norm": 1.0477782487869263, "learning_rate": 3.9047147218162273e-07, "loss": 0.7887, "step": 15639 }, { "epoch": 0.9135514018691588, "grad_norm": 1.2248862981796265, "learning_rate": 3.899481485090895e-07, "loss": 0.6864, "step": 15640 }, { "epoch": 0.9136098130841122, "grad_norm": 1.2458624839782715, "learning_rate": 3.894251687866335e-07, "loss": 0.6919, "step": 15641 }, { "epoch": 0.9136682242990655, "grad_norm": 0.9340073466300964, "learning_rate": 3.8890253303296877e-07, "loss": 0.6514, "step": 15642 }, { "epoch": 0.9137266355140187, "grad_norm": 1.8446202278137207, "learning_rate": 3.8838024126680364e-07, "loss": 0.8624, "step": 15643 }, { "epoch": 0.913785046728972, "grad_norm": 1.130811095237732, "learning_rate": 3.878582935068287e-07, "loss": 0.722, "step": 15644 }, { "epoch": 0.9138434579439252, "grad_norm": 1.0868110656738281, "learning_rate": 3.8733668977172344e-07, "loss": 0.7801, "step": 15645 }, { "epoch": 0.9139018691588785, "grad_norm": 1.1406915187835693, "learning_rate": 3.8681543008015966e-07, "loss": 0.86, "step": 15646 }, { "epoch": 0.9139602803738318, "grad_norm": 0.9719760417938232, "learning_rate": 3.862945144507924e-07, "loss": 0.8741, "step": 15647 }, { "epoch": 0.914018691588785, "grad_norm": 1.2708717584609985, "learning_rate": 3.8577394290226664e-07, "loss": 0.7609, "step": 15648 }, { "epoch": 0.9140771028037383, "grad_norm": 1.1220072507858276, "learning_rate": 3.852537154532121e-07, "loss": 0.6775, "step": 15649 }, { "epoch": 0.9141355140186916, "grad_norm": 1.0540070533752441, "learning_rate": 3.8473383212224825e-07, "loss": 0.7364, "step": 15650 }, { "epoch": 0.9141939252336448, "grad_norm": 1.041779637336731, "learning_rate": 3.842142929279835e-07, "loss": 0.6392, "step": 15651 }, { "epoch": 0.9142523364485982, "grad_norm": 1.4106323719024658, "learning_rate": 3.836950978890108e-07, "loss": 0.7916, "step": 15652 }, { "epoch": 0.9143107476635514, "grad_norm": 1.2092516422271729, "learning_rate": 3.831762470239153e-07, "loss": 0.8297, "step": 15653 }, { "epoch": 0.9143691588785047, "grad_norm": 1.0657176971435547, "learning_rate": 3.8265774035126437e-07, "loss": 0.7491, "step": 15654 }, { "epoch": 0.914427570093458, "grad_norm": 1.0607573986053467, "learning_rate": 3.821395778896153e-07, "loss": 0.7333, "step": 15655 }, { "epoch": 0.9144859813084112, "grad_norm": 1.0648921728134155, "learning_rate": 3.816217596575156e-07, "loss": 0.5782, "step": 15656 }, { "epoch": 0.9145443925233645, "grad_norm": 1.1678434610366821, "learning_rate": 3.811042856734959e-07, "loss": 0.7517, "step": 15657 }, { "epoch": 0.9146028037383177, "grad_norm": 0.9796395897865295, "learning_rate": 3.8058715595608034e-07, "loss": 0.7774, "step": 15658 }, { "epoch": 0.914661214953271, "grad_norm": 0.9981577396392822, "learning_rate": 3.8007037052377516e-07, "loss": 0.8275, "step": 15659 }, { "epoch": 0.9147196261682243, "grad_norm": 1.024081826210022, "learning_rate": 3.7955392939507564e-07, "loss": 0.7076, "step": 15660 }, { "epoch": 0.9147780373831775, "grad_norm": 1.2908269166946411, "learning_rate": 3.7903783258846694e-07, "loss": 0.7097, "step": 15661 }, { "epoch": 0.9148364485981308, "grad_norm": 1.239818811416626, "learning_rate": 3.785220801224199e-07, "loss": 0.87, "step": 15662 }, { "epoch": 0.9148948598130842, "grad_norm": 1.1572176218032837, "learning_rate": 3.780066720153941e-07, "loss": 0.833, "step": 15663 }, { "epoch": 0.9149532710280374, "grad_norm": 0.8880109786987305, "learning_rate": 3.7749160828583596e-07, "loss": 0.6089, "step": 15664 }, { "epoch": 0.9150116822429907, "grad_norm": 0.9307787418365479, "learning_rate": 3.769768889521808e-07, "loss": 0.6773, "step": 15665 }, { "epoch": 0.9150700934579439, "grad_norm": 1.729288935661316, "learning_rate": 3.764625140328493e-07, "loss": 0.7479, "step": 15666 }, { "epoch": 0.9151285046728972, "grad_norm": 1.8619985580444336, "learning_rate": 3.7594848354625237e-07, "loss": 0.7798, "step": 15667 }, { "epoch": 0.9151869158878505, "grad_norm": 1.0210570096969604, "learning_rate": 3.754347975107864e-07, "loss": 0.6924, "step": 15668 }, { "epoch": 0.9152453271028037, "grad_norm": 0.8308582901954651, "learning_rate": 3.7492145594483773e-07, "loss": 0.733, "step": 15669 }, { "epoch": 0.915303738317757, "grad_norm": 1.060674786567688, "learning_rate": 3.7440845886677844e-07, "loss": 0.826, "step": 15670 }, { "epoch": 0.9153621495327103, "grad_norm": 1.1612093448638916, "learning_rate": 3.7389580629497045e-07, "loss": 0.7217, "step": 15671 }, { "epoch": 0.9154205607476635, "grad_norm": 1.1569862365722656, "learning_rate": 3.7338349824776133e-07, "loss": 0.7299, "step": 15672 }, { "epoch": 0.9154789719626168, "grad_norm": 1.3288382291793823, "learning_rate": 3.7287153474348305e-07, "loss": 0.61, "step": 15673 }, { "epoch": 0.91553738317757, "grad_norm": 1.123814582824707, "learning_rate": 3.723599158004654e-07, "loss": 0.6449, "step": 15674 }, { "epoch": 0.9155957943925234, "grad_norm": 1.0726521015167236, "learning_rate": 3.7184864143701593e-07, "loss": 0.8889, "step": 15675 }, { "epoch": 0.9156542056074767, "grad_norm": 1.149520993232727, "learning_rate": 3.713377116714345e-07, "loss": 0.7031, "step": 15676 }, { "epoch": 0.9157126168224299, "grad_norm": 1.1260371208190918, "learning_rate": 3.708271265220087e-07, "loss": 0.7665, "step": 15677 }, { "epoch": 0.9157710280373832, "grad_norm": 0.9545512795448303, "learning_rate": 3.7031688600700833e-07, "loss": 0.5974, "step": 15678 }, { "epoch": 0.9158294392523364, "grad_norm": 1.0161269903182983, "learning_rate": 3.698069901446999e-07, "loss": 0.7636, "step": 15679 }, { "epoch": 0.9158878504672897, "grad_norm": 0.9482417702674866, "learning_rate": 3.6929743895332995e-07, "loss": 0.7054, "step": 15680 }, { "epoch": 0.915946261682243, "grad_norm": 1.0726512670516968, "learning_rate": 3.687882324511394e-07, "loss": 0.6813, "step": 15681 }, { "epoch": 0.9160046728971962, "grad_norm": 1.3597593307495117, "learning_rate": 3.682793706563492e-07, "loss": 0.6885, "step": 15682 }, { "epoch": 0.9160630841121495, "grad_norm": 0.9258407950401306, "learning_rate": 3.677708535871738e-07, "loss": 0.617, "step": 15683 }, { "epoch": 0.9161214953271029, "grad_norm": 1.2424254417419434, "learning_rate": 3.6726268126181185e-07, "loss": 0.6698, "step": 15684 }, { "epoch": 0.916179906542056, "grad_norm": 0.8582203388214111, "learning_rate": 3.667548536984522e-07, "loss": 0.7259, "step": 15685 }, { "epoch": 0.9162383177570094, "grad_norm": 1.1480824947357178, "learning_rate": 3.662473709152714e-07, "loss": 0.802, "step": 15686 }, { "epoch": 0.9162967289719626, "grad_norm": 0.9388899803161621, "learning_rate": 3.657402329304316e-07, "loss": 0.605, "step": 15687 }, { "epoch": 0.9163551401869159, "grad_norm": 1.0727589130401611, "learning_rate": 3.652334397620827e-07, "loss": 0.8652, "step": 15688 }, { "epoch": 0.9164135514018692, "grad_norm": 2.384159803390503, "learning_rate": 3.6472699142836463e-07, "loss": 0.7476, "step": 15689 }, { "epoch": 0.9164719626168224, "grad_norm": 0.9581326246261597, "learning_rate": 3.6422088794740074e-07, "loss": 0.6906, "step": 15690 }, { "epoch": 0.9165303738317757, "grad_norm": 1.3077408075332642, "learning_rate": 3.637151293373098e-07, "loss": 0.7509, "step": 15691 }, { "epoch": 0.916588785046729, "grad_norm": 0.9705828428268433, "learning_rate": 3.632097156161896e-07, "loss": 0.8536, "step": 15692 }, { "epoch": 0.9166471962616822, "grad_norm": 1.128524661064148, "learning_rate": 3.6270464680212893e-07, "loss": 0.7061, "step": 15693 }, { "epoch": 0.9167056074766355, "grad_norm": 1.5524349212646484, "learning_rate": 3.621999229132067e-07, "loss": 0.8051, "step": 15694 }, { "epoch": 0.9167640186915887, "grad_norm": 0.9517723321914673, "learning_rate": 3.616955439674863e-07, "loss": 0.8703, "step": 15695 }, { "epoch": 0.9168224299065421, "grad_norm": 0.9704836010932922, "learning_rate": 3.6119150998301767e-07, "loss": 0.7205, "step": 15696 }, { "epoch": 0.9168808411214954, "grad_norm": 4.545799732208252, "learning_rate": 3.606878209778453e-07, "loss": 0.9983, "step": 15697 }, { "epoch": 0.9169392523364486, "grad_norm": 1.3333219289779663, "learning_rate": 3.6018447696999134e-07, "loss": 0.7546, "step": 15698 }, { "epoch": 0.9169976635514019, "grad_norm": 1.1831997632980347, "learning_rate": 3.59681477977476e-07, "loss": 0.7557, "step": 15699 }, { "epoch": 0.9170560747663551, "grad_norm": 0.9786374568939209, "learning_rate": 3.5917882401829696e-07, "loss": 0.6004, "step": 15700 }, { "epoch": 0.9171144859813084, "grad_norm": 1.2849781513214111, "learning_rate": 3.586765151104465e-07, "loss": 0.6019, "step": 15701 }, { "epoch": 0.9171728971962617, "grad_norm": 1.0017390251159668, "learning_rate": 3.581745512719048e-07, "loss": 0.7313, "step": 15702 }, { "epoch": 0.9172313084112149, "grad_norm": 0.9417734742164612, "learning_rate": 3.576729325206341e-07, "loss": 0.6651, "step": 15703 }, { "epoch": 0.9172897196261682, "grad_norm": 0.8887593150138855, "learning_rate": 3.5717165887458994e-07, "loss": 0.6109, "step": 15704 }, { "epoch": 0.9173481308411215, "grad_norm": 1.0520641803741455, "learning_rate": 3.566707303517114e-07, "loss": 0.7191, "step": 15705 }, { "epoch": 0.9174065420560747, "grad_norm": 1.1914578676223755, "learning_rate": 3.561701469699286e-07, "loss": 0.627, "step": 15706 }, { "epoch": 0.9174649532710281, "grad_norm": 0.8961916565895081, "learning_rate": 3.556699087471571e-07, "loss": 0.7005, "step": 15707 }, { "epoch": 0.9175233644859813, "grad_norm": 1.279482126235962, "learning_rate": 3.551700157013005e-07, "loss": 0.6958, "step": 15708 }, { "epoch": 0.9175817757009346, "grad_norm": 2.5814082622528076, "learning_rate": 3.546704678502522e-07, "loss": 0.9043, "step": 15709 }, { "epoch": 0.9176401869158879, "grad_norm": 1.0271188020706177, "learning_rate": 3.541712652118878e-07, "loss": 0.6867, "step": 15710 }, { "epoch": 0.9176985981308411, "grad_norm": 1.0909901857376099, "learning_rate": 3.5367240780407764e-07, "loss": 0.8, "step": 15711 }, { "epoch": 0.9177570093457944, "grad_norm": 1.3775461912155151, "learning_rate": 3.531738956446729e-07, "loss": 0.7913, "step": 15712 }, { "epoch": 0.9178154205607477, "grad_norm": 1.1486380100250244, "learning_rate": 3.5267572875151814e-07, "loss": 0.8275, "step": 15713 }, { "epoch": 0.9178738317757009, "grad_norm": 1.057031273841858, "learning_rate": 3.521779071424436e-07, "loss": 0.766, "step": 15714 }, { "epoch": 0.9179322429906542, "grad_norm": 1.0932787656784058, "learning_rate": 3.516804308352628e-07, "loss": 0.757, "step": 15715 }, { "epoch": 0.9179906542056074, "grad_norm": 1.0800379514694214, "learning_rate": 3.5118329984778596e-07, "loss": 0.7477, "step": 15716 }, { "epoch": 0.9180490654205608, "grad_norm": 1.044895887374878, "learning_rate": 3.5068651419780107e-07, "loss": 0.5529, "step": 15717 }, { "epoch": 0.9181074766355141, "grad_norm": 1.1520096063613892, "learning_rate": 3.501900739030906e-07, "loss": 0.7777, "step": 15718 }, { "epoch": 0.9181658878504673, "grad_norm": 1.0058318376541138, "learning_rate": 3.4969397898142355e-07, "loss": 0.7644, "step": 15719 }, { "epoch": 0.9182242990654206, "grad_norm": 1.1224100589752197, "learning_rate": 3.491982294505525e-07, "loss": 0.7985, "step": 15720 }, { "epoch": 0.9182827102803738, "grad_norm": 5.018069267272949, "learning_rate": 3.487028253282243e-07, "loss": 0.5406, "step": 15721 }, { "epoch": 0.9183411214953271, "grad_norm": 0.827215313911438, "learning_rate": 3.4820776663216707e-07, "loss": 0.49, "step": 15722 }, { "epoch": 0.9183995327102804, "grad_norm": 1.005577802658081, "learning_rate": 3.4771305338009766e-07, "loss": 0.6607, "step": 15723 }, { "epoch": 0.9184579439252336, "grad_norm": 0.9406330585479736, "learning_rate": 3.472186855897275e-07, "loss": 0.7166, "step": 15724 }, { "epoch": 0.9185163551401869, "grad_norm": 1.0736371278762817, "learning_rate": 3.467246632787458e-07, "loss": 0.9126, "step": 15725 }, { "epoch": 0.9185747663551402, "grad_norm": 0.9481245875358582, "learning_rate": 3.462309864648372e-07, "loss": 0.6609, "step": 15726 }, { "epoch": 0.9186331775700934, "grad_norm": 1.0434460639953613, "learning_rate": 3.4573765516566883e-07, "loss": 0.8602, "step": 15727 }, { "epoch": 0.9186915887850468, "grad_norm": 1.0574887990951538, "learning_rate": 3.4524466939889644e-07, "loss": 0.7502, "step": 15728 }, { "epoch": 0.91875, "grad_norm": 1.690325379371643, "learning_rate": 3.44752029182166e-07, "loss": 0.7577, "step": 15729 }, { "epoch": 0.9188084112149533, "grad_norm": 1.1216516494750977, "learning_rate": 3.442597345331089e-07, "loss": 0.7054, "step": 15730 }, { "epoch": 0.9188668224299066, "grad_norm": 11.589919090270996, "learning_rate": 3.437677854693444e-07, "loss": 0.8305, "step": 15731 }, { "epoch": 0.9189252336448598, "grad_norm": 1.8278770446777344, "learning_rate": 3.4327618200848066e-07, "loss": 0.6324, "step": 15732 }, { "epoch": 0.9189836448598131, "grad_norm": 1.1456542015075684, "learning_rate": 3.427849241681103e-07, "loss": 0.7316, "step": 15733 }, { "epoch": 0.9190420560747663, "grad_norm": 0.9146674275398254, "learning_rate": 3.42294011965818e-07, "loss": 0.6441, "step": 15734 }, { "epoch": 0.9191004672897196, "grad_norm": 1.3671115636825562, "learning_rate": 3.418034454191743e-07, "loss": 0.5346, "step": 15735 }, { "epoch": 0.9191588785046729, "grad_norm": 1.0723377466201782, "learning_rate": 3.4131322454573404e-07, "loss": 0.7775, "step": 15736 }, { "epoch": 0.9192172897196261, "grad_norm": 1.0920147895812988, "learning_rate": 3.408233493630453e-07, "loss": 0.7527, "step": 15737 }, { "epoch": 0.9192757009345794, "grad_norm": 1.2139583826065063, "learning_rate": 3.403338198886386e-07, "loss": 0.8391, "step": 15738 }, { "epoch": 0.9193341121495328, "grad_norm": 1.2529312372207642, "learning_rate": 3.398446361400365e-07, "loss": 0.8152, "step": 15739 }, { "epoch": 0.919392523364486, "grad_norm": 6.713714122772217, "learning_rate": 3.3935579813474727e-07, "loss": 0.7682, "step": 15740 }, { "epoch": 0.9194509345794393, "grad_norm": 1.2282273769378662, "learning_rate": 3.3886730589026475e-07, "loss": 0.6799, "step": 15741 }, { "epoch": 0.9195093457943925, "grad_norm": 0.9984175562858582, "learning_rate": 3.3837915942407484e-07, "loss": 0.7826, "step": 15742 }, { "epoch": 0.9195677570093458, "grad_norm": 0.9700827598571777, "learning_rate": 3.37891358753647e-07, "loss": 0.7648, "step": 15743 }, { "epoch": 0.9196261682242991, "grad_norm": 0.9272235035896301, "learning_rate": 3.374039038964405e-07, "loss": 0.706, "step": 15744 }, { "epoch": 0.9196845794392523, "grad_norm": 1.0283808708190918, "learning_rate": 3.3691679486990145e-07, "loss": 0.717, "step": 15745 }, { "epoch": 0.9197429906542056, "grad_norm": 1.174871802330017, "learning_rate": 3.364300316914637e-07, "loss": 0.6225, "step": 15746 }, { "epoch": 0.9198014018691589, "grad_norm": 1.1557629108428955, "learning_rate": 3.3594361437854994e-07, "loss": 0.8299, "step": 15747 }, { "epoch": 0.9198598130841121, "grad_norm": 1.2006802558898926, "learning_rate": 3.3545754294856625e-07, "loss": 0.6839, "step": 15748 }, { "epoch": 0.9199182242990654, "grad_norm": 1.1383068561553955, "learning_rate": 3.349718174189143e-07, "loss": 0.7408, "step": 15749 }, { "epoch": 0.9199766355140186, "grad_norm": 1.09794020652771, "learning_rate": 3.3448643780697455e-07, "loss": 0.6809, "step": 15750 }, { "epoch": 0.920035046728972, "grad_norm": 1.0028693675994873, "learning_rate": 3.3400140413011984e-07, "loss": 0.8289, "step": 15751 }, { "epoch": 0.9200934579439253, "grad_norm": 1.7205238342285156, "learning_rate": 3.335167164057118e-07, "loss": 0.7299, "step": 15752 }, { "epoch": 0.9201518691588785, "grad_norm": 1.0481359958648682, "learning_rate": 3.330323746510955e-07, "loss": 0.6731, "step": 15753 }, { "epoch": 0.9202102803738318, "grad_norm": 1.0790753364562988, "learning_rate": 3.32548378883607e-07, "loss": 0.9907, "step": 15754 }, { "epoch": 0.920268691588785, "grad_norm": 1.0686049461364746, "learning_rate": 3.320647291205692e-07, "loss": 0.7916, "step": 15755 }, { "epoch": 0.9203271028037383, "grad_norm": 0.9995871782302856, "learning_rate": 3.3158142537928927e-07, "loss": 0.6683, "step": 15756 }, { "epoch": 0.9203855140186916, "grad_norm": 1.022036075592041, "learning_rate": 3.31098467677069e-07, "loss": 0.7707, "step": 15757 }, { "epoch": 0.9204439252336448, "grad_norm": 0.8495058417320251, "learning_rate": 3.306158560311912e-07, "loss": 0.7286, "step": 15758 }, { "epoch": 0.9205023364485981, "grad_norm": 0.9705651998519897, "learning_rate": 3.3013359045893087e-07, "loss": 0.6541, "step": 15759 }, { "epoch": 0.9205607476635514, "grad_norm": 1.4418696165084839, "learning_rate": 3.296516709775466e-07, "loss": 0.7957, "step": 15760 }, { "epoch": 0.9206191588785047, "grad_norm": 1.2113462686538696, "learning_rate": 3.2917009760428666e-07, "loss": 0.7072, "step": 15761 }, { "epoch": 0.920677570093458, "grad_norm": 1.996307373046875, "learning_rate": 3.286888703563884e-07, "loss": 0.926, "step": 15762 }, { "epoch": 0.9207359813084112, "grad_norm": 1.152509331703186, "learning_rate": 3.2820798925107365e-07, "loss": 0.8696, "step": 15763 }, { "epoch": 0.9207943925233645, "grad_norm": 0.9350481629371643, "learning_rate": 3.277274543055564e-07, "loss": 0.7502, "step": 15764 }, { "epoch": 0.9208528037383178, "grad_norm": 0.9535344243049622, "learning_rate": 3.272472655370318e-07, "loss": 0.624, "step": 15765 }, { "epoch": 0.920911214953271, "grad_norm": 1.1882303953170776, "learning_rate": 3.2676742296268717e-07, "loss": 0.8337, "step": 15766 }, { "epoch": 0.9209696261682243, "grad_norm": 1.2345738410949707, "learning_rate": 3.2628792659969656e-07, "loss": 0.8385, "step": 15767 }, { "epoch": 0.9210280373831776, "grad_norm": 0.9831122756004333, "learning_rate": 3.258087764652218e-07, "loss": 0.6752, "step": 15768 }, { "epoch": 0.9210864485981308, "grad_norm": 0.8105970621109009, "learning_rate": 3.253299725764136e-07, "loss": 0.8826, "step": 15769 }, { "epoch": 0.9211448598130841, "grad_norm": 0.916634738445282, "learning_rate": 3.248515149504061e-07, "loss": 0.8856, "step": 15770 }, { "epoch": 0.9212032710280373, "grad_norm": 1.1799794435501099, "learning_rate": 3.2437340360432333e-07, "loss": 0.6675, "step": 15771 }, { "epoch": 0.9212616822429907, "grad_norm": 0.8662137389183044, "learning_rate": 3.2389563855527826e-07, "loss": 0.6403, "step": 15772 }, { "epoch": 0.921320093457944, "grad_norm": 1.4882107973098755, "learning_rate": 3.234182198203706e-07, "loss": 0.6675, "step": 15773 }, { "epoch": 0.9213785046728972, "grad_norm": 1.6536638736724854, "learning_rate": 3.229411474166888e-07, "loss": 0.6985, "step": 15774 }, { "epoch": 0.9214369158878505, "grad_norm": 0.9443539381027222, "learning_rate": 3.2246442136130597e-07, "loss": 0.569, "step": 15775 }, { "epoch": 0.9214953271028037, "grad_norm": 1.0172098875045776, "learning_rate": 3.2198804167128285e-07, "loss": 0.6251, "step": 15776 }, { "epoch": 0.921553738317757, "grad_norm": 1.6418956518173218, "learning_rate": 3.215120083636725e-07, "loss": 0.8367, "step": 15777 }, { "epoch": 0.9216121495327103, "grad_norm": 0.9375898838043213, "learning_rate": 3.210363214555101e-07, "loss": 0.6669, "step": 15778 }, { "epoch": 0.9216705607476635, "grad_norm": 1.097491979598999, "learning_rate": 3.2056098096382213e-07, "loss": 0.7562, "step": 15779 }, { "epoch": 0.9217289719626168, "grad_norm": 0.9682754874229431, "learning_rate": 3.2008598690562163e-07, "loss": 0.7582, "step": 15780 }, { "epoch": 0.9217873831775701, "grad_norm": 0.9306499361991882, "learning_rate": 3.1961133929790723e-07, "loss": 0.7146, "step": 15781 }, { "epoch": 0.9218457943925233, "grad_norm": 1.0285576581954956, "learning_rate": 3.191370381576697e-07, "loss": 0.6496, "step": 15782 }, { "epoch": 0.9219042056074767, "grad_norm": 1.129278302192688, "learning_rate": 3.1866308350188114e-07, "loss": 0.7734, "step": 15783 }, { "epoch": 0.9219626168224299, "grad_norm": 0.9970203042030334, "learning_rate": 3.181894753475068e-07, "loss": 0.7054, "step": 15784 }, { "epoch": 0.9220210280373832, "grad_norm": 1.0740201473236084, "learning_rate": 3.177162137114975e-07, "loss": 0.6592, "step": 15785 }, { "epoch": 0.9220794392523365, "grad_norm": 1.2058446407318115, "learning_rate": 3.1724329861079096e-07, "loss": 0.6634, "step": 15786 }, { "epoch": 0.9221378504672897, "grad_norm": 1.539178729057312, "learning_rate": 3.167707300623135e-07, "loss": 0.7573, "step": 15787 }, { "epoch": 0.922196261682243, "grad_norm": 1.0214650630950928, "learning_rate": 3.1629850808297946e-07, "loss": 0.8086, "step": 15788 }, { "epoch": 0.9222546728971963, "grad_norm": 1.1732019186019897, "learning_rate": 3.1582663268968636e-07, "loss": 0.8928, "step": 15789 }, { "epoch": 0.9223130841121495, "grad_norm": 0.9656205773353577, "learning_rate": 3.1535510389932745e-07, "loss": 0.7471, "step": 15790 }, { "epoch": 0.9223714953271028, "grad_norm": 1.158500075340271, "learning_rate": 3.1488392172877577e-07, "loss": 0.8143, "step": 15791 }, { "epoch": 0.922429906542056, "grad_norm": 1.4479701519012451, "learning_rate": 3.14413086194898e-07, "loss": 0.728, "step": 15792 }, { "epoch": 0.9224883177570093, "grad_norm": 1.2816499471664429, "learning_rate": 3.139425973145449e-07, "loss": 0.7397, "step": 15793 }, { "epoch": 0.9225467289719627, "grad_norm": 0.990487277507782, "learning_rate": 3.1347245510455317e-07, "loss": 0.7076, "step": 15794 }, { "epoch": 0.9226051401869159, "grad_norm": 1.249996542930603, "learning_rate": 3.1300265958175146e-07, "loss": 0.7711, "step": 15795 }, { "epoch": 0.9226635514018692, "grad_norm": 1.0646048784255981, "learning_rate": 3.125332107629542e-07, "loss": 0.9602, "step": 15796 }, { "epoch": 0.9227219626168224, "grad_norm": 1.113445520401001, "learning_rate": 3.120641086649634e-07, "loss": 0.7588, "step": 15797 }, { "epoch": 0.9227803738317757, "grad_norm": 1.1338438987731934, "learning_rate": 3.11595353304569e-07, "loss": 0.8406, "step": 15798 }, { "epoch": 0.922838785046729, "grad_norm": 0.9904566407203674, "learning_rate": 3.111269446985454e-07, "loss": 0.8462, "step": 15799 }, { "epoch": 0.9228971962616822, "grad_norm": 1.1050376892089844, "learning_rate": 3.1065888286365917e-07, "loss": 0.7139, "step": 15800 }, { "epoch": 0.9229556074766355, "grad_norm": 1.0008102655410767, "learning_rate": 3.1019116781666247e-07, "loss": 0.7459, "step": 15801 }, { "epoch": 0.9230140186915888, "grad_norm": 1.0090830326080322, "learning_rate": 3.0972379957429523e-07, "loss": 0.8413, "step": 15802 }, { "epoch": 0.923072429906542, "grad_norm": 1.0809764862060547, "learning_rate": 3.0925677815328625e-07, "loss": 0.6816, "step": 15803 }, { "epoch": 0.9231308411214953, "grad_norm": 1.1733005046844482, "learning_rate": 3.087901035703467e-07, "loss": 0.5492, "step": 15804 }, { "epoch": 0.9231892523364486, "grad_norm": 1.22207510471344, "learning_rate": 3.0832377584218197e-07, "loss": 0.6408, "step": 15805 }, { "epoch": 0.9232476635514019, "grad_norm": 1.1005706787109375, "learning_rate": 3.0785779498548106e-07, "loss": 0.6841, "step": 15806 }, { "epoch": 0.9233060747663552, "grad_norm": 0.9460370540618896, "learning_rate": 3.0739216101692394e-07, "loss": 0.6551, "step": 15807 }, { "epoch": 0.9233644859813084, "grad_norm": 1.5362149477005005, "learning_rate": 3.06926873953175e-07, "loss": 0.6561, "step": 15808 }, { "epoch": 0.9234228971962617, "grad_norm": 1.1430466175079346, "learning_rate": 3.064619338108843e-07, "loss": 0.6759, "step": 15809 }, { "epoch": 0.923481308411215, "grad_norm": 1.1701430082321167, "learning_rate": 3.059973406066963e-07, "loss": 0.6916, "step": 15810 }, { "epoch": 0.9235397196261682, "grad_norm": 0.8745527863502502, "learning_rate": 3.0553309435723653e-07, "loss": 0.79, "step": 15811 }, { "epoch": 0.9235981308411215, "grad_norm": 0.9309049844741821, "learning_rate": 3.050691950791218e-07, "loss": 0.8596, "step": 15812 }, { "epoch": 0.9236565420560747, "grad_norm": 1.0924805402755737, "learning_rate": 3.0460564278895544e-07, "loss": 0.7055, "step": 15813 }, { "epoch": 0.923714953271028, "grad_norm": 1.1224398612976074, "learning_rate": 3.041424375033275e-07, "loss": 0.7865, "step": 15814 }, { "epoch": 0.9237733644859814, "grad_norm": 1.1540147066116333, "learning_rate": 3.0367957923881695e-07, "loss": 0.9422, "step": 15815 }, { "epoch": 0.9238317757009346, "grad_norm": 0.8908482789993286, "learning_rate": 3.032170680119895e-07, "loss": 0.8129, "step": 15816 }, { "epoch": 0.9238901869158879, "grad_norm": 1.2287791967391968, "learning_rate": 3.027549038393995e-07, "loss": 0.7087, "step": 15817 }, { "epoch": 0.9239485981308411, "grad_norm": 0.9434117078781128, "learning_rate": 3.022930867375873e-07, "loss": 0.7687, "step": 15818 }, { "epoch": 0.9240070093457944, "grad_norm": 1.363230586051941, "learning_rate": 3.018316167230817e-07, "loss": 0.8518, "step": 15819 }, { "epoch": 0.9240654205607477, "grad_norm": 1.5083699226379395, "learning_rate": 3.0137049381239956e-07, "loss": 0.6232, "step": 15820 }, { "epoch": 0.9241238317757009, "grad_norm": 1.3482722043991089, "learning_rate": 3.009097180220444e-07, "loss": 0.7104, "step": 15821 }, { "epoch": 0.9241822429906542, "grad_norm": 1.323616862297058, "learning_rate": 3.0044928936850627e-07, "loss": 0.7909, "step": 15822 }, { "epoch": 0.9242406542056075, "grad_norm": 1.5064237117767334, "learning_rate": 2.999892078682676e-07, "loss": 0.7485, "step": 15823 }, { "epoch": 0.9242990654205607, "grad_norm": 1.1337571144104004, "learning_rate": 2.9952947353779295e-07, "loss": 0.7177, "step": 15824 }, { "epoch": 0.924357476635514, "grad_norm": 1.0776814222335815, "learning_rate": 2.9907008639353583e-07, "loss": 0.6019, "step": 15825 }, { "epoch": 0.9244158878504672, "grad_norm": 1.1367278099060059, "learning_rate": 2.986110464519387e-07, "loss": 0.7463, "step": 15826 }, { "epoch": 0.9244742990654206, "grad_norm": 3.3754849433898926, "learning_rate": 2.9815235372943176e-07, "loss": 0.6852, "step": 15827 }, { "epoch": 0.9245327102803739, "grad_norm": 1.0406718254089355, "learning_rate": 2.9769400824243067e-07, "loss": 0.6661, "step": 15828 }, { "epoch": 0.9245911214953271, "grad_norm": 1.083907961845398, "learning_rate": 2.9723601000734013e-07, "loss": 0.7289, "step": 15829 }, { "epoch": 0.9246495327102804, "grad_norm": 1.2324951887130737, "learning_rate": 2.9677835904055373e-07, "loss": 0.7767, "step": 15830 }, { "epoch": 0.9247079439252337, "grad_norm": 0.9142811894416809, "learning_rate": 2.9632105535844837e-07, "loss": 0.6694, "step": 15831 }, { "epoch": 0.9247663551401869, "grad_norm": 1.0957731008529663, "learning_rate": 2.958640989773942e-07, "loss": 0.7794, "step": 15832 }, { "epoch": 0.9248247663551402, "grad_norm": 1.029441475868225, "learning_rate": 2.954074899137427e-07, "loss": 0.8406, "step": 15833 }, { "epoch": 0.9248831775700934, "grad_norm": 1.090835690498352, "learning_rate": 2.949512281838385e-07, "loss": 0.6747, "step": 15834 }, { "epoch": 0.9249415887850467, "grad_norm": 1.9184733629226685, "learning_rate": 2.9449531380401187e-07, "loss": 0.7038, "step": 15835 }, { "epoch": 0.925, "grad_norm": 1.6619160175323486, "learning_rate": 2.9403974679057866e-07, "loss": 0.8148, "step": 15836 }, { "epoch": 0.9250584112149532, "grad_norm": 0.8626194000244141, "learning_rate": 2.935845271598459e-07, "loss": 0.6961, "step": 15837 }, { "epoch": 0.9251168224299066, "grad_norm": 0.9350965619087219, "learning_rate": 2.9312965492810374e-07, "loss": 0.8314, "step": 15838 }, { "epoch": 0.9251752336448598, "grad_norm": 0.9266983270645142, "learning_rate": 2.926751301116337e-07, "loss": 0.6701, "step": 15839 }, { "epoch": 0.9252336448598131, "grad_norm": 0.9137505888938904, "learning_rate": 2.9222095272670505e-07, "loss": 0.7912, "step": 15840 }, { "epoch": 0.9252920560747664, "grad_norm": 8.886981010437012, "learning_rate": 2.917671227895691e-07, "loss": 0.6695, "step": 15841 }, { "epoch": 0.9253504672897196, "grad_norm": 0.904812216758728, "learning_rate": 2.913136403164729e-07, "loss": 0.63, "step": 15842 }, { "epoch": 0.9254088785046729, "grad_norm": 1.3659029006958008, "learning_rate": 2.9086050532364576e-07, "loss": 0.7882, "step": 15843 }, { "epoch": 0.9254672897196262, "grad_norm": 1.436177134513855, "learning_rate": 2.904077178273035e-07, "loss": 0.626, "step": 15844 }, { "epoch": 0.9255257009345794, "grad_norm": 1.1116530895233154, "learning_rate": 2.899552778436532e-07, "loss": 0.731, "step": 15845 }, { "epoch": 0.9255841121495327, "grad_norm": 1.112192988395691, "learning_rate": 2.8950318538888855e-07, "loss": 0.8465, "step": 15846 }, { "epoch": 0.9256425233644859, "grad_norm": 1.215023159980774, "learning_rate": 2.8905144047918887e-07, "loss": 0.6244, "step": 15847 }, { "epoch": 0.9257009345794392, "grad_norm": 1.1528345346450806, "learning_rate": 2.8860004313072453e-07, "loss": 0.7273, "step": 15848 }, { "epoch": 0.9257593457943926, "grad_norm": 1.1395901441574097, "learning_rate": 2.881489933596482e-07, "loss": 0.9247, "step": 15849 }, { "epoch": 0.9258177570093458, "grad_norm": 1.4610612392425537, "learning_rate": 2.876982911821058e-07, "loss": 0.6975, "step": 15850 }, { "epoch": 0.9258761682242991, "grad_norm": 1.062281608581543, "learning_rate": 2.872479366142289e-07, "loss": 0.8345, "step": 15851 }, { "epoch": 0.9259345794392523, "grad_norm": 1.0550601482391357, "learning_rate": 2.867979296721324e-07, "loss": 0.7136, "step": 15852 }, { "epoch": 0.9259929906542056, "grad_norm": 0.9898030757904053, "learning_rate": 2.863482703719267e-07, "loss": 0.6648, "step": 15853 }, { "epoch": 0.9260514018691589, "grad_norm": 1.0495504140853882, "learning_rate": 2.8589895872970117e-07, "loss": 0.7179, "step": 15854 }, { "epoch": 0.9261098130841121, "grad_norm": 0.7935728430747986, "learning_rate": 2.8544999476153967e-07, "loss": 0.6288, "step": 15855 }, { "epoch": 0.9261682242990654, "grad_norm": 1.4630290269851685, "learning_rate": 2.850013784835115e-07, "loss": 0.7617, "step": 15856 }, { "epoch": 0.9262266355140187, "grad_norm": 1.7488937377929688, "learning_rate": 2.845531099116705e-07, "loss": 0.6967, "step": 15857 }, { "epoch": 0.9262850467289719, "grad_norm": 1.1633905172348022, "learning_rate": 2.841051890620627e-07, "loss": 0.7136, "step": 15858 }, { "epoch": 0.9263434579439253, "grad_norm": 0.9615486264228821, "learning_rate": 2.8365761595071763e-07, "loss": 0.6321, "step": 15859 }, { "epoch": 0.9264018691588785, "grad_norm": 0.9756441712379456, "learning_rate": 2.8321039059365563e-07, "loss": 0.6276, "step": 15860 }, { "epoch": 0.9264602803738318, "grad_norm": 0.9096571803092957, "learning_rate": 2.827635130068829e-07, "loss": 0.7459, "step": 15861 }, { "epoch": 0.9265186915887851, "grad_norm": 1.002113938331604, "learning_rate": 2.823169832063921e-07, "loss": 0.6249, "step": 15862 }, { "epoch": 0.9265771028037383, "grad_norm": 1.1722378730773926, "learning_rate": 2.8187080120816726e-07, "loss": 0.9437, "step": 15863 }, { "epoch": 0.9266355140186916, "grad_norm": 1.1196452379226685, "learning_rate": 2.8142496702817545e-07, "loss": 0.7188, "step": 15864 }, { "epoch": 0.9266939252336449, "grad_norm": 1.3054313659667969, "learning_rate": 2.8097948068237513e-07, "loss": 0.7456, "step": 15865 }, { "epoch": 0.9267523364485981, "grad_norm": 1.2519162893295288, "learning_rate": 2.8053434218670794e-07, "loss": 0.6309, "step": 15866 }, { "epoch": 0.9268107476635514, "grad_norm": 0.9854830503463745, "learning_rate": 2.8008955155710784e-07, "loss": 0.7241, "step": 15867 }, { "epoch": 0.9268691588785046, "grad_norm": 1.0832128524780273, "learning_rate": 2.7964510880949423e-07, "loss": 0.5952, "step": 15868 }, { "epoch": 0.9269275700934579, "grad_norm": 1.2063167095184326, "learning_rate": 2.792010139597734e-07, "loss": 0.6571, "step": 15869 }, { "epoch": 0.9269859813084113, "grad_norm": 1.4307091236114502, "learning_rate": 2.787572670238403e-07, "loss": 0.6779, "step": 15870 }, { "epoch": 0.9270443925233645, "grad_norm": 0.925256073474884, "learning_rate": 2.7831386801757563e-07, "loss": 0.6542, "step": 15871 }, { "epoch": 0.9271028037383178, "grad_norm": 1.1096967458724976, "learning_rate": 2.778708169568489e-07, "loss": 0.7285, "step": 15872 }, { "epoch": 0.927161214953271, "grad_norm": 0.9338879585266113, "learning_rate": 2.7742811385751964e-07, "loss": 0.6249, "step": 15873 }, { "epoch": 0.9272196261682243, "grad_norm": 1.085371494293213, "learning_rate": 2.7698575873542964e-07, "loss": 0.8269, "step": 15874 }, { "epoch": 0.9272780373831776, "grad_norm": 1.287835717201233, "learning_rate": 2.76543751606414e-07, "loss": 0.727, "step": 15875 }, { "epoch": 0.9273364485981308, "grad_norm": 1.068786859512329, "learning_rate": 2.7610209248629004e-07, "loss": 0.8031, "step": 15876 }, { "epoch": 0.9273948598130841, "grad_norm": 0.8662859201431274, "learning_rate": 2.7566078139086515e-07, "loss": 0.5734, "step": 15877 }, { "epoch": 0.9274532710280374, "grad_norm": 0.952142059803009, "learning_rate": 2.7521981833593557e-07, "loss": 0.7181, "step": 15878 }, { "epoch": 0.9275116822429906, "grad_norm": 1.0449470281600952, "learning_rate": 2.74779203337282e-07, "loss": 0.7626, "step": 15879 }, { "epoch": 0.927570093457944, "grad_norm": 0.9040691256523132, "learning_rate": 2.743389364106763e-07, "loss": 0.5887, "step": 15880 }, { "epoch": 0.9276285046728971, "grad_norm": 1.0731831789016724, "learning_rate": 2.7389901757187474e-07, "loss": 0.8529, "step": 15881 }, { "epoch": 0.9276869158878505, "grad_norm": 1.109238624572754, "learning_rate": 2.734594468366214e-07, "loss": 0.617, "step": 15882 }, { "epoch": 0.9277453271028038, "grad_norm": 1.4873180389404297, "learning_rate": 2.7302022422064923e-07, "loss": 0.7487, "step": 15883 }, { "epoch": 0.927803738317757, "grad_norm": 1.1050578355789185, "learning_rate": 2.725813497396801e-07, "loss": 0.861, "step": 15884 }, { "epoch": 0.9278621495327103, "grad_norm": 1.0442492961883545, "learning_rate": 2.7214282340942033e-07, "loss": 0.7431, "step": 15885 }, { "epoch": 0.9279205607476636, "grad_norm": 0.9727123379707336, "learning_rate": 2.7170464524556517e-07, "loss": 0.8772, "step": 15886 }, { "epoch": 0.9279789719626168, "grad_norm": 1.1120061874389648, "learning_rate": 2.712668152637965e-07, "loss": 0.707, "step": 15887 }, { "epoch": 0.9280373831775701, "grad_norm": 1.1261378526687622, "learning_rate": 2.7082933347978515e-07, "loss": 0.6833, "step": 15888 }, { "epoch": 0.9280957943925233, "grad_norm": 0.9907559752464294, "learning_rate": 2.703921999091896e-07, "loss": 0.7312, "step": 15889 }, { "epoch": 0.9281542056074766, "grad_norm": 0.9971461296081543, "learning_rate": 2.699554145676553e-07, "loss": 0.6873, "step": 15890 }, { "epoch": 0.92821261682243, "grad_norm": 1.0044219493865967, "learning_rate": 2.69518977470814e-07, "loss": 0.9227, "step": 15891 }, { "epoch": 0.9282710280373832, "grad_norm": 1.1269760131835938, "learning_rate": 2.6908288863428555e-07, "loss": 0.7743, "step": 15892 }, { "epoch": 0.9283294392523365, "grad_norm": 1.0087120532989502, "learning_rate": 2.6864714807367963e-07, "loss": 0.6672, "step": 15893 }, { "epoch": 0.9283878504672897, "grad_norm": 0.7793200612068176, "learning_rate": 2.6821175580458935e-07, "loss": 0.7356, "step": 15894 }, { "epoch": 0.928446261682243, "grad_norm": 0.992547869682312, "learning_rate": 2.677767118426e-07, "loss": 0.7345, "step": 15895 }, { "epoch": 0.9285046728971963, "grad_norm": 1.1157666444778442, "learning_rate": 2.6734201620328247e-07, "loss": 0.7365, "step": 15896 }, { "epoch": 0.9285630841121495, "grad_norm": 1.1414307355880737, "learning_rate": 2.66907668902191e-07, "loss": 0.742, "step": 15897 }, { "epoch": 0.9286214953271028, "grad_norm": 1.0314123630523682, "learning_rate": 2.6647366995487644e-07, "loss": 0.8852, "step": 15898 }, { "epoch": 0.9286799065420561, "grad_norm": 0.8536046147346497, "learning_rate": 2.6604001937686643e-07, "loss": 0.6906, "step": 15899 }, { "epoch": 0.9287383177570093, "grad_norm": 0.9330580234527588, "learning_rate": 2.6560671718368514e-07, "loss": 0.5639, "step": 15900 }, { "epoch": 0.9287967289719626, "grad_norm": 0.7617489099502563, "learning_rate": 2.651737633908413e-07, "loss": 0.6472, "step": 15901 }, { "epoch": 0.9288551401869158, "grad_norm": 1.2610211372375488, "learning_rate": 2.647411580138282e-07, "loss": 0.6643, "step": 15902 }, { "epoch": 0.9289135514018692, "grad_norm": 1.2032980918884277, "learning_rate": 2.64308901068131e-07, "loss": 0.7971, "step": 15903 }, { "epoch": 0.9289719626168225, "grad_norm": 0.8517290949821472, "learning_rate": 2.638769925692175e-07, "loss": 0.7359, "step": 15904 }, { "epoch": 0.9290303738317757, "grad_norm": 1.0869624614715576, "learning_rate": 2.634454325325497e-07, "loss": 0.8233, "step": 15905 }, { "epoch": 0.929088785046729, "grad_norm": 1.2085508108139038, "learning_rate": 2.6301422097357197e-07, "loss": 0.6626, "step": 15906 }, { "epoch": 0.9291471962616823, "grad_norm": 1.244667887687683, "learning_rate": 2.6258335790771636e-07, "loss": 0.7204, "step": 15907 }, { "epoch": 0.9292056074766355, "grad_norm": 1.0181151628494263, "learning_rate": 2.6215284335040614e-07, "loss": 0.6525, "step": 15908 }, { "epoch": 0.9292640186915888, "grad_norm": 1.2691315412521362, "learning_rate": 2.6172267731704783e-07, "loss": 0.7088, "step": 15909 }, { "epoch": 0.929322429906542, "grad_norm": 0.996822714805603, "learning_rate": 2.6129285982303796e-07, "loss": 0.6881, "step": 15910 }, { "epoch": 0.9293808411214953, "grad_norm": 1.3863022327423096, "learning_rate": 2.608633908837588e-07, "loss": 0.887, "step": 15911 }, { "epoch": 0.9294392523364486, "grad_norm": 1.3761322498321533, "learning_rate": 2.6043427051458346e-07, "loss": 0.7778, "step": 15912 }, { "epoch": 0.9294976635514018, "grad_norm": 1.320830225944519, "learning_rate": 2.600054987308698e-07, "loss": 0.8929, "step": 15913 }, { "epoch": 0.9295560747663552, "grad_norm": 1.2094969749450684, "learning_rate": 2.595770755479643e-07, "loss": 0.7885, "step": 15914 }, { "epoch": 0.9296144859813084, "grad_norm": 1.0469073057174683, "learning_rate": 2.591490009811981e-07, "loss": 0.7763, "step": 15915 }, { "epoch": 0.9296728971962617, "grad_norm": 1.1262229681015015, "learning_rate": 2.587212750458934e-07, "loss": 0.7651, "step": 15916 }, { "epoch": 0.929731308411215, "grad_norm": 1.394884467124939, "learning_rate": 2.5829389775736013e-07, "loss": 0.9539, "step": 15917 }, { "epoch": 0.9297897196261682, "grad_norm": 0.902687132358551, "learning_rate": 2.578668691308939e-07, "loss": 0.7599, "step": 15918 }, { "epoch": 0.9298481308411215, "grad_norm": 0.9303433895111084, "learning_rate": 2.5744018918177905e-07, "loss": 0.6996, "step": 15919 }, { "epoch": 0.9299065420560748, "grad_norm": 0.938042163848877, "learning_rate": 2.5701385792528345e-07, "loss": 0.761, "step": 15920 }, { "epoch": 0.929964953271028, "grad_norm": 1.1488080024719238, "learning_rate": 2.5658787537666927e-07, "loss": 0.7163, "step": 15921 }, { "epoch": 0.9300233644859813, "grad_norm": 0.9161204695701599, "learning_rate": 2.5616224155117997e-07, "loss": 0.5793, "step": 15922 }, { "epoch": 0.9300817757009345, "grad_norm": 1.033577799797058, "learning_rate": 2.5573695646405326e-07, "loss": 0.818, "step": 15923 }, { "epoch": 0.9301401869158878, "grad_norm": 1.0201095342636108, "learning_rate": 2.55312020130507e-07, "loss": 0.7725, "step": 15924 }, { "epoch": 0.9301985981308412, "grad_norm": 1.0099364519119263, "learning_rate": 2.548874325657502e-07, "loss": 0.83, "step": 15925 }, { "epoch": 0.9302570093457944, "grad_norm": 0.999282956123352, "learning_rate": 2.5446319378498064e-07, "loss": 0.6592, "step": 15926 }, { "epoch": 0.9303154205607477, "grad_norm": 1.3327782154083252, "learning_rate": 2.540393038033795e-07, "loss": 0.8873, "step": 15927 }, { "epoch": 0.930373831775701, "grad_norm": 0.9787761569023132, "learning_rate": 2.536157626361202e-07, "loss": 0.6852, "step": 15928 }, { "epoch": 0.9304322429906542, "grad_norm": 1.0441571474075317, "learning_rate": 2.5319257029836287e-07, "loss": 0.7063, "step": 15929 }, { "epoch": 0.9304906542056075, "grad_norm": 1.1203651428222656, "learning_rate": 2.527697268052498e-07, "loss": 0.7033, "step": 15930 }, { "epoch": 0.9305490654205607, "grad_norm": 1.3438472747802734, "learning_rate": 2.523472321719189e-07, "loss": 0.8724, "step": 15931 }, { "epoch": 0.930607476635514, "grad_norm": 1.2434306144714355, "learning_rate": 2.519250864134892e-07, "loss": 0.7416, "step": 15932 }, { "epoch": 0.9306658878504673, "grad_norm": 1.2164433002471924, "learning_rate": 2.5150328954506863e-07, "loss": 0.7414, "step": 15933 }, { "epoch": 0.9307242990654205, "grad_norm": 1.220625638961792, "learning_rate": 2.510818415817573e-07, "loss": 0.858, "step": 15934 }, { "epoch": 0.9307827102803738, "grad_norm": 0.9154638051986694, "learning_rate": 2.506607425386354e-07, "loss": 0.7689, "step": 15935 }, { "epoch": 0.930841121495327, "grad_norm": 1.0916266441345215, "learning_rate": 2.5023999243077747e-07, "loss": 0.8269, "step": 15936 }, { "epoch": 0.9308995327102804, "grad_norm": 0.9192932844161987, "learning_rate": 2.4981959127323927e-07, "loss": 0.7116, "step": 15937 }, { "epoch": 0.9309579439252337, "grad_norm": 1.0249271392822266, "learning_rate": 2.4939953908106885e-07, "loss": 0.7058, "step": 15938 }, { "epoch": 0.9310163551401869, "grad_norm": 0.8597339987754822, "learning_rate": 2.4897983586930185e-07, "loss": 0.8895, "step": 15939 }, { "epoch": 0.9310747663551402, "grad_norm": 0.9949951767921448, "learning_rate": 2.485604816529563e-07, "loss": 0.677, "step": 15940 }, { "epoch": 0.9311331775700935, "grad_norm": 1.0062357187271118, "learning_rate": 2.4814147644704356e-07, "loss": 0.6961, "step": 15941 }, { "epoch": 0.9311915887850467, "grad_norm": 1.021738052368164, "learning_rate": 2.4772282026655826e-07, "loss": 0.6363, "step": 15942 }, { "epoch": 0.93125, "grad_norm": 1.4607617855072021, "learning_rate": 2.4730451312648617e-07, "loss": 0.6901, "step": 15943 }, { "epoch": 0.9313084112149532, "grad_norm": 1.1351221799850464, "learning_rate": 2.468865550417976e-07, "loss": 0.6879, "step": 15944 }, { "epoch": 0.9313668224299065, "grad_norm": 1.0175343751907349, "learning_rate": 2.4646894602745276e-07, "loss": 0.7296, "step": 15945 }, { "epoch": 0.9314252336448599, "grad_norm": 1.2138075828552246, "learning_rate": 2.4605168609839747e-07, "loss": 0.6822, "step": 15946 }, { "epoch": 0.931483644859813, "grad_norm": 1.0541958808898926, "learning_rate": 2.4563477526956534e-07, "loss": 0.6141, "step": 15947 }, { "epoch": 0.9315420560747664, "grad_norm": 1.0455865859985352, "learning_rate": 2.452182135558789e-07, "loss": 0.847, "step": 15948 }, { "epoch": 0.9316004672897197, "grad_norm": 1.09491765499115, "learning_rate": 2.4480200097224514e-07, "loss": 0.792, "step": 15949 }, { "epoch": 0.9316588785046729, "grad_norm": 0.8639258742332458, "learning_rate": 2.443861375335621e-07, "loss": 0.682, "step": 15950 }, { "epoch": 0.9317172897196262, "grad_norm": 1.1770027875900269, "learning_rate": 2.439706232547145e-07, "loss": 0.7697, "step": 15951 }, { "epoch": 0.9317757009345794, "grad_norm": 1.0173888206481934, "learning_rate": 2.435554581505728e-07, "loss": 0.8616, "step": 15952 }, { "epoch": 0.9318341121495327, "grad_norm": 0.746152400970459, "learning_rate": 2.431406422359961e-07, "loss": 0.6388, "step": 15953 }, { "epoch": 0.931892523364486, "grad_norm": 0.9822349548339844, "learning_rate": 2.427261755258303e-07, "loss": 0.7463, "step": 15954 }, { "epoch": 0.9319509345794392, "grad_norm": 0.985464870929718, "learning_rate": 2.423120580349114e-07, "loss": 0.6749, "step": 15955 }, { "epoch": 0.9320093457943925, "grad_norm": 1.094270944595337, "learning_rate": 2.4189828977805975e-07, "loss": 0.6901, "step": 15956 }, { "epoch": 0.9320677570093457, "grad_norm": 1.0783727169036865, "learning_rate": 2.4148487077008456e-07, "loss": 0.6102, "step": 15957 }, { "epoch": 0.9321261682242991, "grad_norm": 2.0196611881256104, "learning_rate": 2.4107180102578066e-07, "loss": 0.8593, "step": 15958 }, { "epoch": 0.9321845794392524, "grad_norm": 0.9514081478118896, "learning_rate": 2.4065908055993514e-07, "loss": 0.7599, "step": 15959 }, { "epoch": 0.9322429906542056, "grad_norm": 1.0066808462142944, "learning_rate": 2.4024670938731733e-07, "loss": 0.6879, "step": 15960 }, { "epoch": 0.9323014018691589, "grad_norm": 1.052126407623291, "learning_rate": 2.3983468752268646e-07, "loss": 0.7247, "step": 15961 }, { "epoch": 0.9323598130841122, "grad_norm": 1.0320566892623901, "learning_rate": 2.394230149807908e-07, "loss": 0.7079, "step": 15962 }, { "epoch": 0.9324182242990654, "grad_norm": 0.8899078369140625, "learning_rate": 2.390116917763619e-07, "loss": 0.6947, "step": 15963 }, { "epoch": 0.9324766355140187, "grad_norm": 1.1042922735214233, "learning_rate": 2.386007179241234e-07, "loss": 0.6994, "step": 15964 }, { "epoch": 0.9325350467289719, "grad_norm": 15.31710147857666, "learning_rate": 2.3819009343878375e-07, "loss": 0.7367, "step": 15965 }, { "epoch": 0.9325934579439252, "grad_norm": 1.1284102201461792, "learning_rate": 2.3777981833503772e-07, "loss": 0.7024, "step": 15966 }, { "epoch": 0.9326518691588785, "grad_norm": 1.1520520448684692, "learning_rate": 2.3736989262757247e-07, "loss": 0.7936, "step": 15967 }, { "epoch": 0.9327102803738317, "grad_norm": 1.8674122095108032, "learning_rate": 2.3696031633105632e-07, "loss": 0.77, "step": 15968 }, { "epoch": 0.9327686915887851, "grad_norm": 1.0839589834213257, "learning_rate": 2.3655108946015082e-07, "loss": 0.8259, "step": 15969 }, { "epoch": 0.9328271028037384, "grad_norm": 1.450698971748352, "learning_rate": 2.3614221202950094e-07, "loss": 0.8289, "step": 15970 }, { "epoch": 0.9328855140186916, "grad_norm": 1.0547388792037964, "learning_rate": 2.3573368405374054e-07, "loss": 0.6138, "step": 15971 }, { "epoch": 0.9329439252336449, "grad_norm": 1.052871823310852, "learning_rate": 2.3532550554749346e-07, "loss": 0.6301, "step": 15972 }, { "epoch": 0.9330023364485981, "grad_norm": 1.226783037185669, "learning_rate": 2.3491767652536578e-07, "loss": 0.7734, "step": 15973 }, { "epoch": 0.9330607476635514, "grad_norm": 1.0028353929519653, "learning_rate": 2.3451019700195477e-07, "loss": 0.703, "step": 15974 }, { "epoch": 0.9331191588785047, "grad_norm": 1.6490107774734497, "learning_rate": 2.3410306699184537e-07, "loss": 0.9268, "step": 15975 }, { "epoch": 0.9331775700934579, "grad_norm": 1.0990452766418457, "learning_rate": 2.3369628650960928e-07, "loss": 0.676, "step": 15976 }, { "epoch": 0.9332359813084112, "grad_norm": 0.9975166916847229, "learning_rate": 2.3328985556980266e-07, "loss": 0.7934, "step": 15977 }, { "epoch": 0.9332943925233644, "grad_norm": 1.276540994644165, "learning_rate": 2.3288377418697382e-07, "loss": 0.7786, "step": 15978 }, { "epoch": 0.9333528037383177, "grad_norm": 1.187934160232544, "learning_rate": 2.3247804237565897e-07, "loss": 0.8704, "step": 15979 }, { "epoch": 0.9334112149532711, "grad_norm": 0.9187748432159424, "learning_rate": 2.3207266015037532e-07, "loss": 0.6754, "step": 15980 }, { "epoch": 0.9334696261682243, "grad_norm": 1.0312469005584717, "learning_rate": 2.3166762752563466e-07, "loss": 0.6853, "step": 15981 }, { "epoch": 0.9335280373831776, "grad_norm": 1.0613819360733032, "learning_rate": 2.31262944515932e-07, "loss": 0.6947, "step": 15982 }, { "epoch": 0.9335864485981309, "grad_norm": 1.1377735137939453, "learning_rate": 2.3085861113575136e-07, "loss": 0.7062, "step": 15983 }, { "epoch": 0.9336448598130841, "grad_norm": 0.8789286017417908, "learning_rate": 2.3045462739956448e-07, "loss": 0.7084, "step": 15984 }, { "epoch": 0.9337032710280374, "grad_norm": 1.1272270679473877, "learning_rate": 2.3005099332182977e-07, "loss": 0.7993, "step": 15985 }, { "epoch": 0.9337616822429906, "grad_norm": 1.002899169921875, "learning_rate": 2.2964770891699572e-07, "loss": 0.6966, "step": 15986 }, { "epoch": 0.9338200934579439, "grad_norm": 1.1346545219421387, "learning_rate": 2.2924477419949186e-07, "loss": 0.6506, "step": 15987 }, { "epoch": 0.9338785046728972, "grad_norm": 1.0373018980026245, "learning_rate": 2.2884218918374334e-07, "loss": 0.7098, "step": 15988 }, { "epoch": 0.9339369158878504, "grad_norm": 1.0033866167068481, "learning_rate": 2.2843995388415752e-07, "loss": 0.8293, "step": 15989 }, { "epoch": 0.9339953271028038, "grad_norm": 1.2212961912155151, "learning_rate": 2.2803806831512953e-07, "loss": 0.9319, "step": 15990 }, { "epoch": 0.934053738317757, "grad_norm": 1.1369030475616455, "learning_rate": 2.2763653249104566e-07, "loss": 0.7836, "step": 15991 }, { "epoch": 0.9341121495327103, "grad_norm": 1.231727957725525, "learning_rate": 2.2723534642627555e-07, "loss": 0.7456, "step": 15992 }, { "epoch": 0.9341705607476636, "grad_norm": 1.1772907972335815, "learning_rate": 2.2683451013517765e-07, "loss": 0.9592, "step": 15993 }, { "epoch": 0.9342289719626168, "grad_norm": 1.1737194061279297, "learning_rate": 2.2643402363209832e-07, "loss": 0.7082, "step": 15994 }, { "epoch": 0.9342873831775701, "grad_norm": 1.0148496627807617, "learning_rate": 2.2603388693137163e-07, "loss": 0.6725, "step": 15995 }, { "epoch": 0.9343457943925234, "grad_norm": 1.6797139644622803, "learning_rate": 2.2563410004731946e-07, "loss": 0.748, "step": 15996 }, { "epoch": 0.9344042056074766, "grad_norm": 1.0572843551635742, "learning_rate": 2.2523466299424924e-07, "loss": 0.7664, "step": 15997 }, { "epoch": 0.9344626168224299, "grad_norm": 1.0933821201324463, "learning_rate": 2.2483557578645732e-07, "loss": 0.6742, "step": 15998 }, { "epoch": 0.9345210280373831, "grad_norm": 1.0308845043182373, "learning_rate": 2.2443683843822672e-07, "loss": 0.8095, "step": 15999 }, { "epoch": 0.9345794392523364, "grad_norm": 0.963616669178009, "learning_rate": 2.2403845096382937e-07, "loss": 0.6469, "step": 16000 }, { "epoch": 0.9346378504672898, "grad_norm": 1.440463662147522, "learning_rate": 2.2364041337752497e-07, "loss": 0.9244, "step": 16001 }, { "epoch": 0.934696261682243, "grad_norm": 0.975688099861145, "learning_rate": 2.2324272569355875e-07, "loss": 0.7108, "step": 16002 }, { "epoch": 0.9347546728971963, "grad_norm": 0.9465233683586121, "learning_rate": 2.228453879261616e-07, "loss": 0.7504, "step": 16003 }, { "epoch": 0.9348130841121496, "grad_norm": 1.0857675075531006, "learning_rate": 2.2244840008955658e-07, "loss": 0.7358, "step": 16004 }, { "epoch": 0.9348714953271028, "grad_norm": 1.1750444173812866, "learning_rate": 2.2205176219795345e-07, "loss": 0.6691, "step": 16005 }, { "epoch": 0.9349299065420561, "grad_norm": 1.054364800453186, "learning_rate": 2.2165547426554635e-07, "loss": 0.7483, "step": 16006 }, { "epoch": 0.9349883177570093, "grad_norm": 1.5160443782806396, "learning_rate": 2.2125953630652065e-07, "loss": 0.8169, "step": 16007 }, { "epoch": 0.9350467289719626, "grad_norm": 1.011536955833435, "learning_rate": 2.2086394833504386e-07, "loss": 0.8204, "step": 16008 }, { "epoch": 0.9351051401869159, "grad_norm": 1.1472694873809814, "learning_rate": 2.2046871036527806e-07, "loss": 0.9608, "step": 16009 }, { "epoch": 0.9351635514018691, "grad_norm": 1.1530725955963135, "learning_rate": 2.200738224113641e-07, "loss": 0.7085, "step": 16010 }, { "epoch": 0.9352219626168224, "grad_norm": 0.9086293578147888, "learning_rate": 2.196792844874418e-07, "loss": 0.6856, "step": 16011 }, { "epoch": 0.9352803738317756, "grad_norm": 1.0263410806655884, "learning_rate": 2.1928509660762763e-07, "loss": 0.8189, "step": 16012 }, { "epoch": 0.935338785046729, "grad_norm": 1.3708535432815552, "learning_rate": 2.1889125878603036e-07, "loss": 0.8055, "step": 16013 }, { "epoch": 0.9353971962616823, "grad_norm": 0.9669449329376221, "learning_rate": 2.184977710367464e-07, "loss": 0.705, "step": 16014 }, { "epoch": 0.9354556074766355, "grad_norm": 0.9428446888923645, "learning_rate": 2.181046333738579e-07, "loss": 0.8369, "step": 16015 }, { "epoch": 0.9355140186915888, "grad_norm": 0.9121053814888, "learning_rate": 2.177118458114369e-07, "loss": 0.8488, "step": 16016 }, { "epoch": 0.9355724299065421, "grad_norm": 1.0500566959381104, "learning_rate": 2.1731940836354105e-07, "loss": 0.7074, "step": 16017 }, { "epoch": 0.9356308411214953, "grad_norm": 1.1914277076721191, "learning_rate": 2.1692732104421578e-07, "loss": 0.6536, "step": 16018 }, { "epoch": 0.9356892523364486, "grad_norm": 1.005713939666748, "learning_rate": 2.165355838674943e-07, "loss": 0.8876, "step": 16019 }, { "epoch": 0.9357476635514018, "grad_norm": 1.1087416410446167, "learning_rate": 2.161441968473965e-07, "loss": 0.7251, "step": 16020 }, { "epoch": 0.9358060747663551, "grad_norm": 0.9798194169998169, "learning_rate": 2.1575315999793124e-07, "loss": 0.7191, "step": 16021 }, { "epoch": 0.9358644859813084, "grad_norm": 1.0168075561523438, "learning_rate": 2.153624733330939e-07, "loss": 0.6857, "step": 16022 }, { "epoch": 0.9359228971962616, "grad_norm": 1.3096047639846802, "learning_rate": 2.149721368668667e-07, "loss": 0.8045, "step": 16023 }, { "epoch": 0.935981308411215, "grad_norm": 0.9819285273551941, "learning_rate": 2.1458215061322173e-07, "loss": 0.7285, "step": 16024 }, { "epoch": 0.9360397196261683, "grad_norm": 1.2496726512908936, "learning_rate": 2.1419251458611456e-07, "loss": 0.8342, "step": 16025 }, { "epoch": 0.9360981308411215, "grad_norm": 1.1853986978530884, "learning_rate": 2.1380322879949177e-07, "loss": 0.9716, "step": 16026 }, { "epoch": 0.9361565420560748, "grad_norm": 1.1322648525238037, "learning_rate": 2.1341429326728557e-07, "loss": 0.8408, "step": 16027 }, { "epoch": 0.936214953271028, "grad_norm": 0.9940947890281677, "learning_rate": 2.1302570800341594e-07, "loss": 0.6818, "step": 16028 }, { "epoch": 0.9362733644859813, "grad_norm": 1.2606574296951294, "learning_rate": 2.1263747302179283e-07, "loss": 0.759, "step": 16029 }, { "epoch": 0.9363317757009346, "grad_norm": 1.4558168649673462, "learning_rate": 2.122495883363096e-07, "loss": 0.8259, "step": 16030 }, { "epoch": 0.9363901869158878, "grad_norm": 1.547472596168518, "learning_rate": 2.1186205396084848e-07, "loss": 0.7551, "step": 16031 }, { "epoch": 0.9364485981308411, "grad_norm": 0.9275422096252441, "learning_rate": 2.1147486990928056e-07, "loss": 0.6534, "step": 16032 }, { "epoch": 0.9365070093457943, "grad_norm": 0.898323655128479, "learning_rate": 2.1108803619546258e-07, "loss": 0.6965, "step": 16033 }, { "epoch": 0.9365654205607477, "grad_norm": 1.0196566581726074, "learning_rate": 2.1070155283324123e-07, "loss": 0.7434, "step": 16034 }, { "epoch": 0.936623831775701, "grad_norm": 1.9025133848190308, "learning_rate": 2.1031541983644877e-07, "loss": 0.8836, "step": 16035 }, { "epoch": 0.9366822429906542, "grad_norm": 1.392653226852417, "learning_rate": 2.099296372189019e-07, "loss": 0.681, "step": 16036 }, { "epoch": 0.9367406542056075, "grad_norm": 0.9867384433746338, "learning_rate": 2.0954420499441185e-07, "loss": 0.7918, "step": 16037 }, { "epoch": 0.9367990654205608, "grad_norm": 1.1320929527282715, "learning_rate": 2.091591231767709e-07, "loss": 0.8626, "step": 16038 }, { "epoch": 0.936857476635514, "grad_norm": 0.9983057379722595, "learning_rate": 2.0877439177976355e-07, "loss": 0.7529, "step": 16039 }, { "epoch": 0.9369158878504673, "grad_norm": 1.0636810064315796, "learning_rate": 2.0839001081715882e-07, "loss": 0.7546, "step": 16040 }, { "epoch": 0.9369742990654205, "grad_norm": 1.0392011404037476, "learning_rate": 2.0800598030271345e-07, "loss": 0.842, "step": 16041 }, { "epoch": 0.9370327102803738, "grad_norm": 1.0317264795303345, "learning_rate": 2.0762230025017204e-07, "loss": 0.7758, "step": 16042 }, { "epoch": 0.9370911214953271, "grad_norm": 1.0909092426300049, "learning_rate": 2.0723897067326582e-07, "loss": 0.6988, "step": 16043 }, { "epoch": 0.9371495327102803, "grad_norm": 1.105527400970459, "learning_rate": 2.0685599158571823e-07, "loss": 0.7522, "step": 16044 }, { "epoch": 0.9372079439252337, "grad_norm": 1.1020593643188477, "learning_rate": 2.0647336300123277e-07, "loss": 0.6832, "step": 16045 }, { "epoch": 0.937266355140187, "grad_norm": 1.132648229598999, "learning_rate": 2.0609108493350517e-07, "loss": 0.7696, "step": 16046 }, { "epoch": 0.9373247663551402, "grad_norm": 0.9675635099411011, "learning_rate": 2.0570915739621779e-07, "loss": 0.6358, "step": 16047 }, { "epoch": 0.9373831775700935, "grad_norm": 1.0355536937713623, "learning_rate": 2.0532758040303748e-07, "loss": 0.7809, "step": 16048 }, { "epoch": 0.9374415887850467, "grad_norm": 1.2760560512542725, "learning_rate": 2.0494635396762442e-07, "loss": 0.984, "step": 16049 }, { "epoch": 0.9375, "grad_norm": 0.8245740532875061, "learning_rate": 2.0456547810362214e-07, "loss": 0.6316, "step": 16050 }, { "epoch": 0.9375584112149533, "grad_norm": 0.9989327788352966, "learning_rate": 2.04184952824662e-07, "loss": 0.7521, "step": 16051 }, { "epoch": 0.9376168224299065, "grad_norm": 1.5403110980987549, "learning_rate": 2.0380477814436306e-07, "loss": 0.6579, "step": 16052 }, { "epoch": 0.9376752336448598, "grad_norm": 1.047805905342102, "learning_rate": 2.0342495407633223e-07, "loss": 0.6713, "step": 16053 }, { "epoch": 0.937733644859813, "grad_norm": 1.1566849946975708, "learning_rate": 2.0304548063416308e-07, "loss": 0.7947, "step": 16054 }, { "epoch": 0.9377920560747663, "grad_norm": 1.1344133615493774, "learning_rate": 2.0266635783143806e-07, "loss": 0.7007, "step": 16055 }, { "epoch": 0.9378504672897197, "grad_norm": 0.8311440944671631, "learning_rate": 2.0228758568172636e-07, "loss": 0.6064, "step": 16056 }, { "epoch": 0.9379088785046729, "grad_norm": 0.8874115943908691, "learning_rate": 2.0190916419858486e-07, "loss": 0.6783, "step": 16057 }, { "epoch": 0.9379672897196262, "grad_norm": 1.1086853742599487, "learning_rate": 2.01531093395555e-07, "loss": 0.8612, "step": 16058 }, { "epoch": 0.9380257009345795, "grad_norm": 0.9514637589454651, "learning_rate": 2.0115337328617146e-07, "loss": 0.7913, "step": 16059 }, { "epoch": 0.9380841121495327, "grad_norm": 0.959039568901062, "learning_rate": 2.0077600388395015e-07, "loss": 0.906, "step": 16060 }, { "epoch": 0.938142523364486, "grad_norm": 1.4258763790130615, "learning_rate": 2.003989852023991e-07, "loss": 0.6626, "step": 16061 }, { "epoch": 0.9382009345794392, "grad_norm": 1.133846402168274, "learning_rate": 2.000223172550131e-07, "loss": 0.8206, "step": 16062 }, { "epoch": 0.9382593457943925, "grad_norm": 1.425790786743164, "learning_rate": 1.9964600005527024e-07, "loss": 0.6714, "step": 16063 }, { "epoch": 0.9383177570093458, "grad_norm": 1.0831907987594604, "learning_rate": 1.99270033616642e-07, "loss": 0.6952, "step": 16064 }, { "epoch": 0.938376168224299, "grad_norm": 1.4515936374664307, "learning_rate": 1.9889441795258314e-07, "loss": 0.7168, "step": 16065 }, { "epoch": 0.9384345794392523, "grad_norm": 1.0096311569213867, "learning_rate": 1.9851915307653623e-07, "loss": 0.7873, "step": 16066 }, { "epoch": 0.9384929906542057, "grad_norm": 1.2124264240264893, "learning_rate": 1.9814423900193502e-07, "loss": 0.696, "step": 16067 }, { "epoch": 0.9385514018691589, "grad_norm": 0.9228163361549377, "learning_rate": 1.977696757421954e-07, "loss": 0.7106, "step": 16068 }, { "epoch": 0.9386098130841122, "grad_norm": 0.9199626445770264, "learning_rate": 1.9739546331072555e-07, "loss": 0.6726, "step": 16069 }, { "epoch": 0.9386682242990654, "grad_norm": 0.8922380208969116, "learning_rate": 1.970216017209159e-07, "loss": 0.6775, "step": 16070 }, { "epoch": 0.9387266355140187, "grad_norm": 1.271533727645874, "learning_rate": 1.9664809098614901e-07, "loss": 0.8205, "step": 16071 }, { "epoch": 0.938785046728972, "grad_norm": 0.9842879176139832, "learning_rate": 1.9627493111979313e-07, "loss": 0.9644, "step": 16072 }, { "epoch": 0.9388434579439252, "grad_norm": 1.0166831016540527, "learning_rate": 1.9590212213520421e-07, "loss": 0.6146, "step": 16073 }, { "epoch": 0.9389018691588785, "grad_norm": 1.1422069072723389, "learning_rate": 1.955296640457227e-07, "loss": 0.8532, "step": 16074 }, { "epoch": 0.9389602803738317, "grad_norm": 0.9329562187194824, "learning_rate": 1.951575568646835e-07, "loss": 0.6876, "step": 16075 }, { "epoch": 0.939018691588785, "grad_norm": 1.2037948369979858, "learning_rate": 1.947858006053993e-07, "loss": 0.8361, "step": 16076 }, { "epoch": 0.9390771028037384, "grad_norm": 1.0558037757873535, "learning_rate": 1.9441439528118057e-07, "loss": 0.7031, "step": 16077 }, { "epoch": 0.9391355140186916, "grad_norm": 0.9474529027938843, "learning_rate": 1.9404334090531774e-07, "loss": 0.8525, "step": 16078 }, { "epoch": 0.9391939252336449, "grad_norm": 1.0922101736068726, "learning_rate": 1.9367263749109022e-07, "loss": 0.7478, "step": 16079 }, { "epoch": 0.9392523364485982, "grad_norm": 0.9546911716461182, "learning_rate": 1.933022850517674e-07, "loss": 0.7764, "step": 16080 }, { "epoch": 0.9393107476635514, "grad_norm": 1.0852152109146118, "learning_rate": 1.9293228360060424e-07, "loss": 0.8246, "step": 16081 }, { "epoch": 0.9393691588785047, "grad_norm": 0.92950439453125, "learning_rate": 1.9256263315084235e-07, "loss": 0.6815, "step": 16082 }, { "epoch": 0.9394275700934579, "grad_norm": 1.145294189453125, "learning_rate": 1.9219333371571224e-07, "loss": 0.6832, "step": 16083 }, { "epoch": 0.9394859813084112, "grad_norm": 1.0748385190963745, "learning_rate": 1.9182438530843117e-07, "loss": 0.6643, "step": 16084 }, { "epoch": 0.9395443925233645, "grad_norm": 1.5977095365524292, "learning_rate": 1.9145578794220632e-07, "loss": 0.7791, "step": 16085 }, { "epoch": 0.9396028037383177, "grad_norm": 1.2365562915802002, "learning_rate": 1.9108754163022602e-07, "loss": 0.7481, "step": 16086 }, { "epoch": 0.939661214953271, "grad_norm": 0.9750254154205322, "learning_rate": 1.9071964638567198e-07, "loss": 0.6069, "step": 16087 }, { "epoch": 0.9397196261682244, "grad_norm": 0.9654688835144043, "learning_rate": 1.9035210222171252e-07, "loss": 0.5877, "step": 16088 }, { "epoch": 0.9397780373831776, "grad_norm": 1.393401026725769, "learning_rate": 1.8998490915150048e-07, "loss": 0.637, "step": 16089 }, { "epoch": 0.9398364485981309, "grad_norm": 1.3592466115951538, "learning_rate": 1.8961806718818087e-07, "loss": 0.8276, "step": 16090 }, { "epoch": 0.9398948598130841, "grad_norm": 0.8826543688774109, "learning_rate": 1.8925157634487879e-07, "loss": 0.7843, "step": 16091 }, { "epoch": 0.9399532710280374, "grad_norm": 0.9963127970695496, "learning_rate": 1.888854366347148e-07, "loss": 0.8558, "step": 16092 }, { "epoch": 0.9400116822429907, "grad_norm": 1.1682014465332031, "learning_rate": 1.8851964807079072e-07, "loss": 0.9016, "step": 16093 }, { "epoch": 0.9400700934579439, "grad_norm": 1.0874419212341309, "learning_rate": 1.8815421066620044e-07, "loss": 0.6794, "step": 16094 }, { "epoch": 0.9401285046728972, "grad_norm": 1.1251453161239624, "learning_rate": 1.8778912443402242e-07, "loss": 0.7638, "step": 16095 }, { "epoch": 0.9401869158878504, "grad_norm": 1.1546056270599365, "learning_rate": 1.8742438938732287e-07, "loss": 0.722, "step": 16096 }, { "epoch": 0.9402453271028037, "grad_norm": 1.0353878736495972, "learning_rate": 1.8706000553915693e-07, "loss": 0.7187, "step": 16097 }, { "epoch": 0.940303738317757, "grad_norm": 1.0454840660095215, "learning_rate": 1.8669597290256413e-07, "loss": 0.7955, "step": 16098 }, { "epoch": 0.9403621495327102, "grad_norm": 1.110964298248291, "learning_rate": 1.863322914905752e-07, "loss": 0.9261, "step": 16099 }, { "epoch": 0.9404205607476636, "grad_norm": 0.9410340189933777, "learning_rate": 1.8596896131620746e-07, "loss": 0.7425, "step": 16100 }, { "epoch": 0.9404789719626169, "grad_norm": 0.9340097308158875, "learning_rate": 1.8560598239246275e-07, "loss": 0.614, "step": 16101 }, { "epoch": 0.9405373831775701, "grad_norm": 0.8719614148139954, "learning_rate": 1.852433547323329e-07, "loss": 0.5869, "step": 16102 }, { "epoch": 0.9405957943925234, "grad_norm": 1.043225646018982, "learning_rate": 1.8488107834879754e-07, "loss": 0.7962, "step": 16103 }, { "epoch": 0.9406542056074766, "grad_norm": 1.338833212852478, "learning_rate": 1.8451915325482072e-07, "loss": 0.7521, "step": 16104 }, { "epoch": 0.9407126168224299, "grad_norm": 1.1889179944992065, "learning_rate": 1.8415757946335766e-07, "loss": 0.8239, "step": 16105 }, { "epoch": 0.9407710280373832, "grad_norm": 1.1753281354904175, "learning_rate": 1.837963569873491e-07, "loss": 0.8211, "step": 16106 }, { "epoch": 0.9408294392523364, "grad_norm": 1.002153754234314, "learning_rate": 1.834354858397236e-07, "loss": 0.7883, "step": 16107 }, { "epoch": 0.9408878504672897, "grad_norm": 1.5038022994995117, "learning_rate": 1.8307496603339636e-07, "loss": 0.7975, "step": 16108 }, { "epoch": 0.940946261682243, "grad_norm": 1.3449714183807373, "learning_rate": 1.827147975812693e-07, "loss": 0.7774, "step": 16109 }, { "epoch": 0.9410046728971962, "grad_norm": 1.1861895322799683, "learning_rate": 1.8235498049623656e-07, "loss": 0.7324, "step": 16110 }, { "epoch": 0.9410630841121496, "grad_norm": 1.6436858177185059, "learning_rate": 1.819955147911734e-07, "loss": 0.6946, "step": 16111 }, { "epoch": 0.9411214953271028, "grad_norm": 1.0792640447616577, "learning_rate": 1.8163640047894615e-07, "loss": 0.809, "step": 16112 }, { "epoch": 0.9411799065420561, "grad_norm": 1.253129482269287, "learning_rate": 1.81277637572409e-07, "loss": 0.6591, "step": 16113 }, { "epoch": 0.9412383177570094, "grad_norm": 1.1841446161270142, "learning_rate": 1.8091922608439948e-07, "loss": 0.9067, "step": 16114 }, { "epoch": 0.9412967289719626, "grad_norm": 1.0348889827728271, "learning_rate": 1.805611660277473e-07, "loss": 0.7765, "step": 16115 }, { "epoch": 0.9413551401869159, "grad_norm": 1.1347590684890747, "learning_rate": 1.8020345741526778e-07, "loss": 0.7781, "step": 16116 }, { "epoch": 0.9414135514018691, "grad_norm": 2.5070693492889404, "learning_rate": 1.7984610025976401e-07, "loss": 0.6914, "step": 16117 }, { "epoch": 0.9414719626168224, "grad_norm": 0.962024986743927, "learning_rate": 1.7948909457402464e-07, "loss": 0.7827, "step": 16118 }, { "epoch": 0.9415303738317757, "grad_norm": 1.0548477172851562, "learning_rate": 1.791324403708272e-07, "loss": 0.8125, "step": 16119 }, { "epoch": 0.9415887850467289, "grad_norm": 1.7514598369598389, "learning_rate": 1.7877613766293712e-07, "loss": 0.9556, "step": 16120 }, { "epoch": 0.9416471962616823, "grad_norm": 1.127839207649231, "learning_rate": 1.7842018646310634e-07, "loss": 0.8014, "step": 16121 }, { "epoch": 0.9417056074766356, "grad_norm": 0.8717969655990601, "learning_rate": 1.780645867840758e-07, "loss": 0.6465, "step": 16122 }, { "epoch": 0.9417640186915888, "grad_norm": 0.9242432713508606, "learning_rate": 1.7770933863857197e-07, "loss": 0.6104, "step": 16123 }, { "epoch": 0.9418224299065421, "grad_norm": 1.1692835092544556, "learning_rate": 1.7735444203930808e-07, "loss": 0.7605, "step": 16124 }, { "epoch": 0.9418808411214953, "grad_norm": 1.6369953155517578, "learning_rate": 1.7699989699898833e-07, "loss": 0.5565, "step": 16125 }, { "epoch": 0.9419392523364486, "grad_norm": 0.999554455280304, "learning_rate": 1.7664570353030042e-07, "loss": 0.6622, "step": 16126 }, { "epoch": 0.9419976635514019, "grad_norm": 0.7484918236732483, "learning_rate": 1.7629186164592083e-07, "loss": 0.5848, "step": 16127 }, { "epoch": 0.9420560747663551, "grad_norm": 0.9595639109611511, "learning_rate": 1.759383713585161e-07, "loss": 0.744, "step": 16128 }, { "epoch": 0.9421144859813084, "grad_norm": 1.0188184976577759, "learning_rate": 1.7558523268073612e-07, "loss": 0.8814, "step": 16129 }, { "epoch": 0.9421728971962616, "grad_norm": 0.9868970513343811, "learning_rate": 1.752324456252208e-07, "loss": 0.6809, "step": 16130 }, { "epoch": 0.9422313084112149, "grad_norm": 1.2322782278060913, "learning_rate": 1.7488001020459445e-07, "loss": 0.6559, "step": 16131 }, { "epoch": 0.9422897196261683, "grad_norm": 1.0156793594360352, "learning_rate": 1.7452792643147364e-07, "loss": 0.7686, "step": 16132 }, { "epoch": 0.9423481308411215, "grad_norm": 1.0306272506713867, "learning_rate": 1.7417619431845945e-07, "loss": 0.7438, "step": 16133 }, { "epoch": 0.9424065420560748, "grad_norm": 1.1112782955169678, "learning_rate": 1.7382481387813954e-07, "loss": 0.7444, "step": 16134 }, { "epoch": 0.9424649532710281, "grad_norm": 1.170648217201233, "learning_rate": 1.7347378512309053e-07, "loss": 0.7888, "step": 16135 }, { "epoch": 0.9425233644859813, "grad_norm": 1.03425931930542, "learning_rate": 1.7312310806587463e-07, "loss": 0.7535, "step": 16136 }, { "epoch": 0.9425817757009346, "grad_norm": 0.9610525965690613, "learning_rate": 1.7277278271904506e-07, "loss": 0.7561, "step": 16137 }, { "epoch": 0.9426401869158878, "grad_norm": 1.0418001413345337, "learning_rate": 1.7242280909513964e-07, "loss": 0.8143, "step": 16138 }, { "epoch": 0.9426985981308411, "grad_norm": 1.0781688690185547, "learning_rate": 1.7207318720668276e-07, "loss": 0.7974, "step": 16139 }, { "epoch": 0.9427570093457944, "grad_norm": 1.0558435916900635, "learning_rate": 1.7172391706618885e-07, "loss": 0.7585, "step": 16140 }, { "epoch": 0.9428154205607476, "grad_norm": 1.0494511127471924, "learning_rate": 1.7137499868615792e-07, "loss": 0.7882, "step": 16141 }, { "epoch": 0.9428738317757009, "grad_norm": 0.9391425251960754, "learning_rate": 1.7102643207907777e-07, "loss": 0.7253, "step": 16142 }, { "epoch": 0.9429322429906543, "grad_norm": 3.2374515533447266, "learning_rate": 1.7067821725742507e-07, "loss": 0.8822, "step": 16143 }, { "epoch": 0.9429906542056075, "grad_norm": 1.002871036529541, "learning_rate": 1.7033035423366095e-07, "loss": 0.8548, "step": 16144 }, { "epoch": 0.9430490654205608, "grad_norm": 1.0650417804718018, "learning_rate": 1.6998284302023772e-07, "loss": 0.6812, "step": 16145 }, { "epoch": 0.943107476635514, "grad_norm": 0.956540584564209, "learning_rate": 1.6963568362959203e-07, "loss": 0.6947, "step": 16146 }, { "epoch": 0.9431658878504673, "grad_norm": 1.196148157119751, "learning_rate": 1.6928887607414733e-07, "loss": 0.6499, "step": 16147 }, { "epoch": 0.9432242990654206, "grad_norm": 0.939255952835083, "learning_rate": 1.6894242036631813e-07, "loss": 0.5905, "step": 16148 }, { "epoch": 0.9432827102803738, "grad_norm": 0.9283651113510132, "learning_rate": 1.6859631651850449e-07, "loss": 0.6475, "step": 16149 }, { "epoch": 0.9433411214953271, "grad_norm": 1.1227095127105713, "learning_rate": 1.682505645430932e-07, "loss": 0.6936, "step": 16150 }, { "epoch": 0.9433995327102803, "grad_norm": 1.1698648929595947, "learning_rate": 1.6790516445245764e-07, "loss": 0.731, "step": 16151 }, { "epoch": 0.9434579439252336, "grad_norm": 0.9580638408660889, "learning_rate": 1.675601162589613e-07, "loss": 0.6937, "step": 16152 }, { "epoch": 0.943516355140187, "grad_norm": 1.355688214302063, "learning_rate": 1.6721541997495318e-07, "loss": 0.645, "step": 16153 }, { "epoch": 0.9435747663551401, "grad_norm": 0.9521311521530151, "learning_rate": 1.6687107561277004e-07, "loss": 0.7204, "step": 16154 }, { "epoch": 0.9436331775700935, "grad_norm": 1.3268043994903564, "learning_rate": 1.6652708318473765e-07, "loss": 0.8785, "step": 16155 }, { "epoch": 0.9436915887850468, "grad_norm": 1.057605266571045, "learning_rate": 1.661834427031661e-07, "loss": 0.8094, "step": 16156 }, { "epoch": 0.94375, "grad_norm": 1.0893969535827637, "learning_rate": 1.6584015418035447e-07, "loss": 0.7793, "step": 16157 }, { "epoch": 0.9438084112149533, "grad_norm": 1.068726897239685, "learning_rate": 1.6549721762859073e-07, "loss": 0.7426, "step": 16158 }, { "epoch": 0.9438668224299065, "grad_norm": 1.0304036140441895, "learning_rate": 1.6515463306014722e-07, "loss": 0.6758, "step": 16159 }, { "epoch": 0.9439252336448598, "grad_norm": 1.0659658908843994, "learning_rate": 1.648124004872864e-07, "loss": 0.8044, "step": 16160 }, { "epoch": 0.9439836448598131, "grad_norm": 1.2556346654891968, "learning_rate": 1.6447051992225627e-07, "loss": 0.7347, "step": 16161 }, { "epoch": 0.9440420560747663, "grad_norm": 0.9830771684646606, "learning_rate": 1.6412899137729256e-07, "loss": 0.6449, "step": 16162 }, { "epoch": 0.9441004672897196, "grad_norm": 0.9744923114776611, "learning_rate": 1.6378781486462103e-07, "loss": 0.8309, "step": 16163 }, { "epoch": 0.944158878504673, "grad_norm": 1.008226752281189, "learning_rate": 1.6344699039644973e-07, "loss": 0.7539, "step": 16164 }, { "epoch": 0.9442172897196262, "grad_norm": 0.9893105626106262, "learning_rate": 1.631065179849778e-07, "loss": 0.6801, "step": 16165 }, { "epoch": 0.9442757009345795, "grad_norm": 0.986290693283081, "learning_rate": 1.627663976423932e-07, "loss": 0.7402, "step": 16166 }, { "epoch": 0.9443341121495327, "grad_norm": 1.0141805410385132, "learning_rate": 1.6242662938086628e-07, "loss": 0.7052, "step": 16167 }, { "epoch": 0.944392523364486, "grad_norm": 0.8976566791534424, "learning_rate": 1.620872132125595e-07, "loss": 0.7818, "step": 16168 }, { "epoch": 0.9444509345794393, "grad_norm": 0.9077064990997314, "learning_rate": 1.6174814914961867e-07, "loss": 0.809, "step": 16169 }, { "epoch": 0.9445093457943925, "grad_norm": 0.9495959281921387, "learning_rate": 1.614094372041808e-07, "loss": 0.7199, "step": 16170 }, { "epoch": 0.9445677570093458, "grad_norm": 0.8972055912017822, "learning_rate": 1.6107107738836835e-07, "loss": 0.5501, "step": 16171 }, { "epoch": 0.944626168224299, "grad_norm": 1.223881483078003, "learning_rate": 1.607330697142906e-07, "loss": 0.8076, "step": 16172 }, { "epoch": 0.9446845794392523, "grad_norm": 2.4402518272399902, "learning_rate": 1.603954141940467e-07, "loss": 0.9633, "step": 16173 }, { "epoch": 0.9447429906542056, "grad_norm": 1.1781648397445679, "learning_rate": 1.6005811083972034e-07, "loss": 0.7776, "step": 16174 }, { "epoch": 0.9448014018691588, "grad_norm": 1.0698741674423218, "learning_rate": 1.5972115966338408e-07, "loss": 0.7042, "step": 16175 }, { "epoch": 0.9448598130841122, "grad_norm": 1.017405390739441, "learning_rate": 1.5938456067709719e-07, "loss": 0.5933, "step": 16176 }, { "epoch": 0.9449182242990655, "grad_norm": 0.9478548765182495, "learning_rate": 1.5904831389290776e-07, "loss": 0.5781, "step": 16177 }, { "epoch": 0.9449766355140187, "grad_norm": 0.7930877804756165, "learning_rate": 1.5871241932284953e-07, "loss": 0.5907, "step": 16178 }, { "epoch": 0.945035046728972, "grad_norm": 1.12066650390625, "learning_rate": 1.58376876978944e-07, "loss": 0.7157, "step": 16179 }, { "epoch": 0.9450934579439252, "grad_norm": 0.9689181447029114, "learning_rate": 1.5804168687320264e-07, "loss": 0.7001, "step": 16180 }, { "epoch": 0.9451518691588785, "grad_norm": 0.9237520694732666, "learning_rate": 1.5770684901761924e-07, "loss": 0.7263, "step": 16181 }, { "epoch": 0.9452102803738318, "grad_norm": 1.165960669517517, "learning_rate": 1.573723634241786e-07, "loss": 0.8079, "step": 16182 }, { "epoch": 0.945268691588785, "grad_norm": 0.9051730036735535, "learning_rate": 1.570382301048534e-07, "loss": 0.8142, "step": 16183 }, { "epoch": 0.9453271028037383, "grad_norm": 1.025564432144165, "learning_rate": 1.56704449071603e-07, "loss": 0.7894, "step": 16184 }, { "epoch": 0.9453855140186916, "grad_norm": 1.0769386291503906, "learning_rate": 1.563710203363711e-07, "loss": 0.8043, "step": 16185 }, { "epoch": 0.9454439252336448, "grad_norm": 1.320077657699585, "learning_rate": 1.560379439110926e-07, "loss": 0.7664, "step": 16186 }, { "epoch": 0.9455023364485982, "grad_norm": 0.9106393456459045, "learning_rate": 1.5570521980768806e-07, "loss": 0.6701, "step": 16187 }, { "epoch": 0.9455607476635514, "grad_norm": 1.0012584924697876, "learning_rate": 1.5537284803806786e-07, "loss": 0.7843, "step": 16188 }, { "epoch": 0.9456191588785047, "grad_norm": 1.3138840198516846, "learning_rate": 1.5504082861412695e-07, "loss": 0.6674, "step": 16189 }, { "epoch": 0.945677570093458, "grad_norm": 0.9087039828300476, "learning_rate": 1.5470916154774583e-07, "loss": 0.7339, "step": 16190 }, { "epoch": 0.9457359813084112, "grad_norm": 1.1467111110687256, "learning_rate": 1.543778468507995e-07, "loss": 0.7109, "step": 16191 }, { "epoch": 0.9457943925233645, "grad_norm": 0.9403256177902222, "learning_rate": 1.540468845351417e-07, "loss": 0.6505, "step": 16192 }, { "epoch": 0.9458528037383177, "grad_norm": 1.3942511081695557, "learning_rate": 1.5371627461262085e-07, "loss": 0.8098, "step": 16193 }, { "epoch": 0.945911214953271, "grad_norm": 2.6678528785705566, "learning_rate": 1.5338601709506852e-07, "loss": 0.7167, "step": 16194 }, { "epoch": 0.9459696261682243, "grad_norm": 1.0295878648757935, "learning_rate": 1.5305611199430415e-07, "loss": 0.7057, "step": 16195 }, { "epoch": 0.9460280373831775, "grad_norm": 1.2488704919815063, "learning_rate": 1.527265593221372e-07, "loss": 0.8105, "step": 16196 }, { "epoch": 0.9460864485981308, "grad_norm": 0.9674345850944519, "learning_rate": 1.5239735909036046e-07, "loss": 0.9939, "step": 16197 }, { "epoch": 0.9461448598130842, "grad_norm": 0.9800649881362915, "learning_rate": 1.5206851131075673e-07, "loss": 0.73, "step": 16198 }, { "epoch": 0.9462032710280374, "grad_norm": 1.1992881298065186, "learning_rate": 1.5174001599509768e-07, "loss": 0.7297, "step": 16199 }, { "epoch": 0.9462616822429907, "grad_norm": 0.9013485312461853, "learning_rate": 1.5141187315513728e-07, "loss": 0.5848, "step": 16200 }, { "epoch": 0.9463200934579439, "grad_norm": 1.0542956590652466, "learning_rate": 1.5108408280262276e-07, "loss": 0.6343, "step": 16201 }, { "epoch": 0.9463785046728972, "grad_norm": 4.305258274078369, "learning_rate": 1.5075664494928365e-07, "loss": 0.8069, "step": 16202 }, { "epoch": 0.9464369158878505, "grad_norm": 1.1969780921936035, "learning_rate": 1.5042955960684057e-07, "loss": 0.73, "step": 16203 }, { "epoch": 0.9464953271028037, "grad_norm": 0.9237452745437622, "learning_rate": 1.5010282678699973e-07, "loss": 0.772, "step": 16204 }, { "epoch": 0.946553738317757, "grad_norm": 1.000414490699768, "learning_rate": 1.4977644650145505e-07, "loss": 0.8935, "step": 16205 }, { "epoch": 0.9466121495327103, "grad_norm": 0.9721969366073608, "learning_rate": 1.4945041876188836e-07, "loss": 0.7358, "step": 16206 }, { "epoch": 0.9466705607476635, "grad_norm": 1.025490403175354, "learning_rate": 1.491247435799681e-07, "loss": 0.7738, "step": 16207 }, { "epoch": 0.9467289719626168, "grad_norm": 0.9790714979171753, "learning_rate": 1.4879942096735045e-07, "loss": 0.594, "step": 16208 }, { "epoch": 0.94678738317757, "grad_norm": 1.0389842987060547, "learning_rate": 1.4847445093567836e-07, "loss": 0.8615, "step": 16209 }, { "epoch": 0.9468457943925234, "grad_norm": 1.2955467700958252, "learning_rate": 1.4814983349658362e-07, "loss": 0.8318, "step": 16210 }, { "epoch": 0.9469042056074767, "grad_norm": 1.4334443807601929, "learning_rate": 1.4782556866168362e-07, "loss": 0.7635, "step": 16211 }, { "epoch": 0.9469626168224299, "grad_norm": 1.227264404296875, "learning_rate": 1.4750165644258463e-07, "loss": 0.7927, "step": 16212 }, { "epoch": 0.9470210280373832, "grad_norm": 1.277108907699585, "learning_rate": 1.471780968508796e-07, "loss": 0.7998, "step": 16213 }, { "epoch": 0.9470794392523364, "grad_norm": 1.7004326581954956, "learning_rate": 1.4685488989814812e-07, "loss": 0.7279, "step": 16214 }, { "epoch": 0.9471378504672897, "grad_norm": 0.9433217644691467, "learning_rate": 1.4653203559595986e-07, "loss": 0.7479, "step": 16215 }, { "epoch": 0.947196261682243, "grad_norm": 1.1417921781539917, "learning_rate": 1.462095339558678e-07, "loss": 0.8178, "step": 16216 }, { "epoch": 0.9472546728971962, "grad_norm": 0.8852009773254395, "learning_rate": 1.4588738498941601e-07, "loss": 0.718, "step": 16217 }, { "epoch": 0.9473130841121495, "grad_norm": 0.9213322997093201, "learning_rate": 1.455655887081342e-07, "loss": 0.6609, "step": 16218 }, { "epoch": 0.9473714953271029, "grad_norm": 1.1444145441055298, "learning_rate": 1.452441451235387e-07, "loss": 0.594, "step": 16219 }, { "epoch": 0.947429906542056, "grad_norm": 0.9337638020515442, "learning_rate": 1.4492305424713583e-07, "loss": 0.7322, "step": 16220 }, { "epoch": 0.9474883177570094, "grad_norm": 1.6631865501403809, "learning_rate": 1.4460231609041642e-07, "loss": 0.7542, "step": 16221 }, { "epoch": 0.9475467289719626, "grad_norm": 1.1310290098190308, "learning_rate": 1.4428193066485906e-07, "loss": 0.8207, "step": 16222 }, { "epoch": 0.9476051401869159, "grad_norm": 0.8778349757194519, "learning_rate": 1.439618979819335e-07, "loss": 0.8161, "step": 16223 }, { "epoch": 0.9476635514018692, "grad_norm": 1.1520391702651978, "learning_rate": 1.4364221805309052e-07, "loss": 0.8088, "step": 16224 }, { "epoch": 0.9477219626168224, "grad_norm": 2.816460371017456, "learning_rate": 1.4332289088977324e-07, "loss": 0.6969, "step": 16225 }, { "epoch": 0.9477803738317757, "grad_norm": 0.8884315490722656, "learning_rate": 1.430039165034114e-07, "loss": 0.7042, "step": 16226 }, { "epoch": 0.947838785046729, "grad_norm": 1.262274146080017, "learning_rate": 1.4268529490542027e-07, "loss": 0.8432, "step": 16227 }, { "epoch": 0.9478971962616822, "grad_norm": 0.8971129655838013, "learning_rate": 1.423670261072041e-07, "loss": 0.9012, "step": 16228 }, { "epoch": 0.9479556074766355, "grad_norm": 1.0461198091506958, "learning_rate": 1.4204911012015377e-07, "loss": 0.8005, "step": 16229 }, { "epoch": 0.9480140186915887, "grad_norm": 1.0098049640655518, "learning_rate": 1.4173154695564571e-07, "loss": 0.6749, "step": 16230 }, { "epoch": 0.9480724299065421, "grad_norm": 1.1252923011779785, "learning_rate": 1.4141433662504867e-07, "loss": 0.8592, "step": 16231 }, { "epoch": 0.9481308411214954, "grad_norm": 1.0332543849945068, "learning_rate": 1.4109747913971462e-07, "loss": 0.7187, "step": 16232 }, { "epoch": 0.9481892523364486, "grad_norm": 1.0543164014816284, "learning_rate": 1.407809745109845e-07, "loss": 0.756, "step": 16233 }, { "epoch": 0.9482476635514019, "grad_norm": 0.8871446251869202, "learning_rate": 1.4046482275018592e-07, "loss": 0.7138, "step": 16234 }, { "epoch": 0.9483060747663551, "grad_norm": 0.8111009001731873, "learning_rate": 1.4014902386863316e-07, "loss": 0.6936, "step": 16235 }, { "epoch": 0.9483644859813084, "grad_norm": 1.0690953731536865, "learning_rate": 1.398335778776305e-07, "loss": 0.7985, "step": 16236 }, { "epoch": 0.9484228971962617, "grad_norm": 1.1239116191864014, "learning_rate": 1.3951848478846673e-07, "loss": 0.7077, "step": 16237 }, { "epoch": 0.9484813084112149, "grad_norm": 1.3376491069793701, "learning_rate": 1.3920374461242058e-07, "loss": 0.871, "step": 16238 }, { "epoch": 0.9485397196261682, "grad_norm": 1.040858507156372, "learning_rate": 1.3888935736075638e-07, "loss": 0.788, "step": 16239 }, { "epoch": 0.9485981308411215, "grad_norm": 0.9819738864898682, "learning_rate": 1.385753230447251e-07, "loss": 0.6881, "step": 16240 }, { "epoch": 0.9486565420560747, "grad_norm": 1.925621509552002, "learning_rate": 1.3826164167556666e-07, "loss": 0.6418, "step": 16241 }, { "epoch": 0.9487149532710281, "grad_norm": 1.0634509325027466, "learning_rate": 1.3794831326450987e-07, "loss": 0.6881, "step": 16242 }, { "epoch": 0.9487733644859813, "grad_norm": 1.0533233880996704, "learning_rate": 1.3763533782276572e-07, "loss": 0.6911, "step": 16243 }, { "epoch": 0.9488317757009346, "grad_norm": 0.9351534843444824, "learning_rate": 1.3732271536153864e-07, "loss": 0.8489, "step": 16244 }, { "epoch": 0.9488901869158879, "grad_norm": 1.0299204587936401, "learning_rate": 1.3701044589201517e-07, "loss": 0.8537, "step": 16245 }, { "epoch": 0.9489485981308411, "grad_norm": 1.062464714050293, "learning_rate": 1.366985294253731e-07, "loss": 0.7718, "step": 16246 }, { "epoch": 0.9490070093457944, "grad_norm": 1.1156073808670044, "learning_rate": 1.3638696597277678e-07, "loss": 0.5923, "step": 16247 }, { "epoch": 0.9490654205607477, "grad_norm": 1.045811653137207, "learning_rate": 1.360757555453751e-07, "loss": 0.8183, "step": 16248 }, { "epoch": 0.9491238317757009, "grad_norm": 0.8974459767341614, "learning_rate": 1.3576489815430915e-07, "loss": 0.6176, "step": 16249 }, { "epoch": 0.9491822429906542, "grad_norm": 1.0686768293380737, "learning_rate": 1.3545439381070223e-07, "loss": 0.6254, "step": 16250 }, { "epoch": 0.9492406542056074, "grad_norm": 0.9865218997001648, "learning_rate": 1.3514424252566993e-07, "loss": 0.6963, "step": 16251 }, { "epoch": 0.9492990654205608, "grad_norm": 2.4935083389282227, "learning_rate": 1.3483444431031001e-07, "loss": 0.8539, "step": 16252 }, { "epoch": 0.9493574766355141, "grad_norm": 1.1057953834533691, "learning_rate": 1.3452499917571248e-07, "loss": 0.7185, "step": 16253 }, { "epoch": 0.9494158878504673, "grad_norm": 0.8374361395835876, "learning_rate": 1.3421590713295296e-07, "loss": 0.7558, "step": 16254 }, { "epoch": 0.9494742990654206, "grad_norm": 0.9897329807281494, "learning_rate": 1.3390716819309147e-07, "loss": 0.5896, "step": 16255 }, { "epoch": 0.9495327102803738, "grad_norm": 1.1078585386276245, "learning_rate": 1.3359878236718027e-07, "loss": 0.8162, "step": 16256 }, { "epoch": 0.9495911214953271, "grad_norm": 1.1995240449905396, "learning_rate": 1.332907496662561e-07, "loss": 0.6743, "step": 16257 }, { "epoch": 0.9496495327102804, "grad_norm": 1.3048428297042847, "learning_rate": 1.3298307010134237e-07, "loss": 0.7729, "step": 16258 }, { "epoch": 0.9497079439252336, "grad_norm": 1.0056979656219482, "learning_rate": 1.3267574368345247e-07, "loss": 0.901, "step": 16259 }, { "epoch": 0.9497663551401869, "grad_norm": 0.9136040210723877, "learning_rate": 1.3236877042358654e-07, "loss": 0.8786, "step": 16260 }, { "epoch": 0.9498247663551402, "grad_norm": 0.9727734923362732, "learning_rate": 1.3206215033273018e-07, "loss": 0.7047, "step": 16261 }, { "epoch": 0.9498831775700934, "grad_norm": 1.0854252576828003, "learning_rate": 1.3175588342185796e-07, "loss": 0.7046, "step": 16262 }, { "epoch": 0.9499415887850468, "grad_norm": 1.1347107887268066, "learning_rate": 1.3144996970193003e-07, "loss": 0.844, "step": 16263 }, { "epoch": 0.95, "grad_norm": 1.1318279504776, "learning_rate": 1.311444091838965e-07, "loss": 0.6881, "step": 16264 }, { "epoch": 0.9500584112149533, "grad_norm": 1.4792193174362183, "learning_rate": 1.3083920187869415e-07, "loss": 0.7403, "step": 16265 }, { "epoch": 0.9501168224299066, "grad_norm": 0.9698911905288696, "learning_rate": 1.305343477972465e-07, "loss": 0.6873, "step": 16266 }, { "epoch": 0.9501752336448598, "grad_norm": 0.8272458910942078, "learning_rate": 1.302298469504637e-07, "loss": 0.6135, "step": 16267 }, { "epoch": 0.9502336448598131, "grad_norm": 1.2484389543533325, "learning_rate": 1.299256993492426e-07, "loss": 0.7911, "step": 16268 }, { "epoch": 0.9502920560747663, "grad_norm": 1.0917185544967651, "learning_rate": 1.2962190500447114e-07, "loss": 0.8074, "step": 16269 }, { "epoch": 0.9503504672897196, "grad_norm": 1.0385247468948364, "learning_rate": 1.2931846392702174e-07, "loss": 0.6551, "step": 16270 }, { "epoch": 0.9504088785046729, "grad_norm": 0.9943380355834961, "learning_rate": 1.290153761277546e-07, "loss": 0.823, "step": 16271 }, { "epoch": 0.9504672897196261, "grad_norm": 0.8499191999435425, "learning_rate": 1.2871264161751885e-07, "loss": 0.7815, "step": 16272 }, { "epoch": 0.9505257009345794, "grad_norm": 1.1111127138137817, "learning_rate": 1.2841026040714578e-07, "loss": 0.8574, "step": 16273 }, { "epoch": 0.9505841121495328, "grad_norm": 1.0030734539031982, "learning_rate": 1.281082325074612e-07, "loss": 0.6928, "step": 16274 }, { "epoch": 0.950642523364486, "grad_norm": 1.0251487493515015, "learning_rate": 1.2780655792927422e-07, "loss": 0.6838, "step": 16275 }, { "epoch": 0.9507009345794393, "grad_norm": 0.9150238633155823, "learning_rate": 1.2750523668338177e-07, "loss": 0.6522, "step": 16276 }, { "epoch": 0.9507593457943925, "grad_norm": 1.2384508848190308, "learning_rate": 1.2720426878056746e-07, "loss": 0.6012, "step": 16277 }, { "epoch": 0.9508177570093458, "grad_norm": 1.0707000494003296, "learning_rate": 1.2690365423160377e-07, "loss": 0.88, "step": 16278 }, { "epoch": 0.9508761682242991, "grad_norm": 1.198171854019165, "learning_rate": 1.26603393047251e-07, "loss": 0.8066, "step": 16279 }, { "epoch": 0.9509345794392523, "grad_norm": 0.8854765295982361, "learning_rate": 1.2630348523825385e-07, "loss": 0.7386, "step": 16280 }, { "epoch": 0.9509929906542056, "grad_norm": 1.1780179738998413, "learning_rate": 1.2600393081534712e-07, "loss": 0.7282, "step": 16281 }, { "epoch": 0.9510514018691589, "grad_norm": 0.9488474726676941, "learning_rate": 1.257047297892522e-07, "loss": 0.6886, "step": 16282 }, { "epoch": 0.9511098130841121, "grad_norm": 1.2969516515731812, "learning_rate": 1.2540588217067717e-07, "loss": 0.6387, "step": 16283 }, { "epoch": 0.9511682242990654, "grad_norm": 1.2336381673812866, "learning_rate": 1.2510738797031908e-07, "loss": 0.5046, "step": 16284 }, { "epoch": 0.9512266355140186, "grad_norm": 1.1195099353790283, "learning_rate": 1.2480924719885934e-07, "loss": 0.7072, "step": 16285 }, { "epoch": 0.951285046728972, "grad_norm": 0.836975634098053, "learning_rate": 1.2451145986697056e-07, "loss": 0.4882, "step": 16286 }, { "epoch": 0.9513434579439253, "grad_norm": 1.6092170476913452, "learning_rate": 1.2421402598530974e-07, "loss": 0.7447, "step": 16287 }, { "epoch": 0.9514018691588785, "grad_norm": 1.219735026359558, "learning_rate": 1.2391694556452173e-07, "loss": 0.7983, "step": 16288 }, { "epoch": 0.9514602803738318, "grad_norm": 1.1996132135391235, "learning_rate": 1.236202186152413e-07, "loss": 0.7899, "step": 16289 }, { "epoch": 0.951518691588785, "grad_norm": 0.8642480969429016, "learning_rate": 1.233238451480856e-07, "loss": 0.8274, "step": 16290 }, { "epoch": 0.9515771028037383, "grad_norm": 1.144650936126709, "learning_rate": 1.2302782517366384e-07, "loss": 0.8072, "step": 16291 }, { "epoch": 0.9516355140186916, "grad_norm": 0.9955563545227051, "learning_rate": 1.2273215870257093e-07, "loss": 0.9526, "step": 16292 }, { "epoch": 0.9516939252336448, "grad_norm": 0.9190866351127625, "learning_rate": 1.2243684574538838e-07, "loss": 0.7417, "step": 16293 }, { "epoch": 0.9517523364485981, "grad_norm": 0.840903103351593, "learning_rate": 1.2214188631268554e-07, "loss": 0.7284, "step": 16294 }, { "epoch": 0.9518107476635514, "grad_norm": 1.1784517765045166, "learning_rate": 1.2184728041501946e-07, "loss": 0.7224, "step": 16295 }, { "epoch": 0.9518691588785047, "grad_norm": 0.924247682094574, "learning_rate": 1.2155302806293513e-07, "loss": 0.7348, "step": 16296 }, { "epoch": 0.951927570093458, "grad_norm": 1.051936388015747, "learning_rate": 1.2125912926696181e-07, "loss": 0.6391, "step": 16297 }, { "epoch": 0.9519859813084112, "grad_norm": 1.0304443836212158, "learning_rate": 1.2096558403761893e-07, "loss": 0.6965, "step": 16298 }, { "epoch": 0.9520443925233645, "grad_norm": 1.440182089805603, "learning_rate": 1.2067239238541585e-07, "loss": 0.9297, "step": 16299 }, { "epoch": 0.9521028037383178, "grad_norm": 1.1735126972198486, "learning_rate": 1.203795543208419e-07, "loss": 0.868, "step": 16300 }, { "epoch": 0.952161214953271, "grad_norm": 0.9896398186683655, "learning_rate": 1.200870698543799e-07, "loss": 0.9078, "step": 16301 }, { "epoch": 0.9522196261682243, "grad_norm": 0.9019108414649963, "learning_rate": 1.1979493899649809e-07, "loss": 0.797, "step": 16302 }, { "epoch": 0.9522780373831776, "grad_norm": 1.2791310548782349, "learning_rate": 1.1950316175765142e-07, "loss": 0.7417, "step": 16303 }, { "epoch": 0.9523364485981308, "grad_norm": 1.355660319328308, "learning_rate": 1.1921173814828378e-07, "loss": 0.6585, "step": 16304 }, { "epoch": 0.9523948598130841, "grad_norm": 0.7940183877944946, "learning_rate": 1.1892066817882464e-07, "loss": 0.7523, "step": 16305 }, { "epoch": 0.9524532710280373, "grad_norm": 1.5354413986206055, "learning_rate": 1.1862995185969117e-07, "loss": 0.718, "step": 16306 }, { "epoch": 0.9525116822429907, "grad_norm": 0.94560307264328, "learning_rate": 1.1833958920128952e-07, "loss": 0.6481, "step": 16307 }, { "epoch": 0.952570093457944, "grad_norm": 0.9942413568496704, "learning_rate": 1.1804958021401025e-07, "loss": 0.697, "step": 16308 }, { "epoch": 0.9526285046728972, "grad_norm": 1.0646451711654663, "learning_rate": 1.1775992490823507e-07, "loss": 0.7949, "step": 16309 }, { "epoch": 0.9526869158878505, "grad_norm": 0.9563323259353638, "learning_rate": 1.1747062329433012e-07, "loss": 0.7603, "step": 16310 }, { "epoch": 0.9527453271028037, "grad_norm": 0.9718140959739685, "learning_rate": 1.1718167538264935e-07, "loss": 0.7195, "step": 16311 }, { "epoch": 0.952803738317757, "grad_norm": 1.4693785905838013, "learning_rate": 1.1689308118353448e-07, "loss": 0.6611, "step": 16312 }, { "epoch": 0.9528621495327103, "grad_norm": 1.0096474885940552, "learning_rate": 1.1660484070731282e-07, "loss": 0.676, "step": 16313 }, { "epoch": 0.9529205607476635, "grad_norm": 1.1871343851089478, "learning_rate": 1.1631695396430387e-07, "loss": 0.7134, "step": 16314 }, { "epoch": 0.9529789719626168, "grad_norm": 0.9972364902496338, "learning_rate": 1.160294209648094e-07, "loss": 0.7608, "step": 16315 }, { "epoch": 0.9530373831775701, "grad_norm": 0.8769331574440002, "learning_rate": 1.1574224171912118e-07, "loss": 0.6598, "step": 16316 }, { "epoch": 0.9530957943925233, "grad_norm": 1.0356485843658447, "learning_rate": 1.1545541623751766e-07, "loss": 0.9091, "step": 16317 }, { "epoch": 0.9531542056074767, "grad_norm": 1.0085724592208862, "learning_rate": 1.1516894453026283e-07, "loss": 0.6299, "step": 16318 }, { "epoch": 0.9532126168224299, "grad_norm": 1.112489104270935, "learning_rate": 1.1488282660761075e-07, "loss": 0.7665, "step": 16319 }, { "epoch": 0.9532710280373832, "grad_norm": 1.0241715908050537, "learning_rate": 1.1459706247980318e-07, "loss": 0.8664, "step": 16320 }, { "epoch": 0.9533294392523365, "grad_norm": 0.9619700908660889, "learning_rate": 1.143116521570653e-07, "loss": 0.6419, "step": 16321 }, { "epoch": 0.9533878504672897, "grad_norm": 2.2064568996429443, "learning_rate": 1.140265956496145e-07, "loss": 0.8079, "step": 16322 }, { "epoch": 0.953446261682243, "grad_norm": 2.052845001220703, "learning_rate": 1.1374189296765037e-07, "loss": 0.7077, "step": 16323 }, { "epoch": 0.9535046728971963, "grad_norm": 0.8358929753303528, "learning_rate": 1.1345754412136478e-07, "loss": 0.6541, "step": 16324 }, { "epoch": 0.9535630841121495, "grad_norm": 1.169005274772644, "learning_rate": 1.1317354912093514e-07, "loss": 0.8483, "step": 16325 }, { "epoch": 0.9536214953271028, "grad_norm": 1.0459851026535034, "learning_rate": 1.1288990797652444e-07, "loss": 0.8625, "step": 16326 }, { "epoch": 0.953679906542056, "grad_norm": 1.2728760242462158, "learning_rate": 1.1260662069828455e-07, "loss": 0.7534, "step": 16327 }, { "epoch": 0.9537383177570093, "grad_norm": 1.1386420726776123, "learning_rate": 1.1232368729635512e-07, "loss": 0.8283, "step": 16328 }, { "epoch": 0.9537967289719627, "grad_norm": 0.9055522084236145, "learning_rate": 1.1204110778086253e-07, "loss": 0.672, "step": 16329 }, { "epoch": 0.9538551401869159, "grad_norm": 2.4350497722625732, "learning_rate": 1.1175888216191977e-07, "loss": 0.873, "step": 16330 }, { "epoch": 0.9539135514018692, "grad_norm": 1.032412052154541, "learning_rate": 1.1147701044962766e-07, "loss": 0.72, "step": 16331 }, { "epoch": 0.9539719626168224, "grad_norm": 0.973706066608429, "learning_rate": 1.1119549265407593e-07, "loss": 0.6737, "step": 16332 }, { "epoch": 0.9540303738317757, "grad_norm": 1.0318955183029175, "learning_rate": 1.109143287853387e-07, "loss": 0.7458, "step": 16333 }, { "epoch": 0.954088785046729, "grad_norm": 0.9988892674446106, "learning_rate": 1.1063351885348129e-07, "loss": 0.7401, "step": 16334 }, { "epoch": 0.9541471962616822, "grad_norm": 0.8474841117858887, "learning_rate": 1.1035306286855119e-07, "loss": 0.7327, "step": 16335 }, { "epoch": 0.9542056074766355, "grad_norm": 0.8782574534416199, "learning_rate": 1.1007296084058816e-07, "loss": 0.667, "step": 16336 }, { "epoch": 0.9542640186915888, "grad_norm": 1.079864501953125, "learning_rate": 1.0979321277961753e-07, "loss": 0.8149, "step": 16337 }, { "epoch": 0.954322429906542, "grad_norm": 0.951583981513977, "learning_rate": 1.0951381869564903e-07, "loss": 0.8271, "step": 16338 }, { "epoch": 0.9543808411214953, "grad_norm": 0.8714501857757568, "learning_rate": 1.0923477859868581e-07, "loss": 0.7567, "step": 16339 }, { "epoch": 0.9544392523364486, "grad_norm": 0.84125816822052, "learning_rate": 1.0895609249871098e-07, "loss": 0.7492, "step": 16340 }, { "epoch": 0.9544976635514019, "grad_norm": 1.0587283372879028, "learning_rate": 1.086777604057021e-07, "loss": 0.7127, "step": 16341 }, { "epoch": 0.9545560747663552, "grad_norm": 1.2187552452087402, "learning_rate": 1.0839978232962122e-07, "loss": 0.7802, "step": 16342 }, { "epoch": 0.9546144859813084, "grad_norm": 0.9315153956413269, "learning_rate": 1.0812215828041372e-07, "loss": 0.6513, "step": 16343 }, { "epoch": 0.9546728971962617, "grad_norm": 1.0733256340026855, "learning_rate": 1.0784488826802054e-07, "loss": 0.6471, "step": 16344 }, { "epoch": 0.954731308411215, "grad_norm": 0.9129416942596436, "learning_rate": 1.0756797230236149e-07, "loss": 0.6584, "step": 16345 }, { "epoch": 0.9547897196261682, "grad_norm": 1.0526162385940552, "learning_rate": 1.0729141039334979e-07, "loss": 0.6865, "step": 16346 }, { "epoch": 0.9548481308411215, "grad_norm": 1.0192314386367798, "learning_rate": 1.0701520255088193e-07, "loss": 0.9298, "step": 16347 }, { "epoch": 0.9549065420560747, "grad_norm": 1.2377818822860718, "learning_rate": 1.067393487848456e-07, "loss": 0.8255, "step": 16348 }, { "epoch": 0.954964953271028, "grad_norm": 1.0925655364990234, "learning_rate": 1.0646384910511287e-07, "loss": 0.8088, "step": 16349 }, { "epoch": 0.9550233644859814, "grad_norm": 0.9282565712928772, "learning_rate": 1.0618870352154475e-07, "loss": 0.6439, "step": 16350 }, { "epoch": 0.9550817757009346, "grad_norm": 0.971472442150116, "learning_rate": 1.0591391204398783e-07, "loss": 0.6749, "step": 16351 }, { "epoch": 0.9551401869158879, "grad_norm": 1.2493611574172974, "learning_rate": 1.0563947468227642e-07, "loss": 0.6596, "step": 16352 }, { "epoch": 0.9551985981308411, "grad_norm": 1.019905686378479, "learning_rate": 1.0536539144623492e-07, "loss": 0.7667, "step": 16353 }, { "epoch": 0.9552570093457944, "grad_norm": 0.7482194304466248, "learning_rate": 1.0509166234567214e-07, "loss": 0.604, "step": 16354 }, { "epoch": 0.9553154205607477, "grad_norm": 0.9805108904838562, "learning_rate": 1.0481828739038469e-07, "loss": 0.6621, "step": 16355 }, { "epoch": 0.9553738317757009, "grad_norm": 0.9231734871864319, "learning_rate": 1.0454526659015585e-07, "loss": 0.6262, "step": 16356 }, { "epoch": 0.9554322429906542, "grad_norm": 1.0286105871200562, "learning_rate": 1.0427259995475891e-07, "loss": 0.7484, "step": 16357 }, { "epoch": 0.9554906542056075, "grad_norm": 1.0516407489776611, "learning_rate": 1.0400028749395274e-07, "loss": 1.0759, "step": 16358 }, { "epoch": 0.9555490654205607, "grad_norm": 0.9944918751716614, "learning_rate": 1.0372832921748289e-07, "loss": 0.5841, "step": 16359 }, { "epoch": 0.955607476635514, "grad_norm": 1.256849765777588, "learning_rate": 1.0345672513508265e-07, "loss": 0.6689, "step": 16360 }, { "epoch": 0.9556658878504672, "grad_norm": 1.2106478214263916, "learning_rate": 1.0318547525647316e-07, "loss": 0.7283, "step": 16361 }, { "epoch": 0.9557242990654206, "grad_norm": 1.183085560798645, "learning_rate": 1.029145795913633e-07, "loss": 0.7284, "step": 16362 }, { "epoch": 0.9557827102803739, "grad_norm": 0.9097614288330078, "learning_rate": 1.0264403814944756e-07, "loss": 0.8403, "step": 16363 }, { "epoch": 0.9558411214953271, "grad_norm": 1.2771742343902588, "learning_rate": 1.023738509404093e-07, "loss": 0.7488, "step": 16364 }, { "epoch": 0.9558995327102804, "grad_norm": 1.124677300453186, "learning_rate": 1.0210401797391967e-07, "loss": 0.6065, "step": 16365 }, { "epoch": 0.9559579439252337, "grad_norm": 1.075721263885498, "learning_rate": 1.0183453925963427e-07, "loss": 0.6958, "step": 16366 }, { "epoch": 0.9560163551401869, "grad_norm": 0.8493913412094116, "learning_rate": 1.0156541480719984e-07, "loss": 0.7713, "step": 16367 }, { "epoch": 0.9560747663551402, "grad_norm": 1.55417001247406, "learning_rate": 1.0129664462624644e-07, "loss": 0.8064, "step": 16368 }, { "epoch": 0.9561331775700934, "grad_norm": 0.9793537855148315, "learning_rate": 1.0102822872639529e-07, "loss": 0.8899, "step": 16369 }, { "epoch": 0.9561915887850467, "grad_norm": 1.0016909837722778, "learning_rate": 1.0076016711725311e-07, "loss": 0.9286, "step": 16370 }, { "epoch": 0.95625, "grad_norm": 0.8907613158226013, "learning_rate": 1.0049245980841226e-07, "loss": 0.7476, "step": 16371 }, { "epoch": 0.9563084112149532, "grad_norm": 0.8764791488647461, "learning_rate": 1.0022510680945618e-07, "loss": 0.6907, "step": 16372 }, { "epoch": 0.9563668224299066, "grad_norm": 0.8980743885040283, "learning_rate": 9.995810812995166e-08, "loss": 0.8241, "step": 16373 }, { "epoch": 0.9564252336448598, "grad_norm": 1.0335264205932617, "learning_rate": 9.96914637794566e-08, "loss": 0.6682, "step": 16374 }, { "epoch": 0.9564836448598131, "grad_norm": 1.0810048580169678, "learning_rate": 9.942517376751448e-08, "loss": 0.733, "step": 16375 }, { "epoch": 0.9565420560747664, "grad_norm": 0.9242236614227295, "learning_rate": 9.915923810365436e-08, "loss": 0.7614, "step": 16376 }, { "epoch": 0.9566004672897196, "grad_norm": 0.8987413048744202, "learning_rate": 9.889365679739526e-08, "loss": 0.7816, "step": 16377 }, { "epoch": 0.9566588785046729, "grad_norm": 1.1843937635421753, "learning_rate": 9.862842985824184e-08, "loss": 0.7564, "step": 16378 }, { "epoch": 0.9567172897196262, "grad_norm": 4.267534255981445, "learning_rate": 9.836355729568758e-08, "loss": 0.7941, "step": 16379 }, { "epoch": 0.9567757009345794, "grad_norm": 1.1142361164093018, "learning_rate": 9.80990391192116e-08, "loss": 0.8601, "step": 16380 }, { "epoch": 0.9568341121495327, "grad_norm": 1.1095637083053589, "learning_rate": 9.783487533828074e-08, "loss": 0.946, "step": 16381 }, { "epoch": 0.9568925233644859, "grad_norm": 1.5772321224212646, "learning_rate": 9.757106596235188e-08, "loss": 0.7617, "step": 16382 }, { "epoch": 0.9569509345794392, "grad_norm": 1.0712080001831055, "learning_rate": 9.730761100086639e-08, "loss": 0.743, "step": 16383 }, { "epoch": 0.9570093457943926, "grad_norm": 1.0820661783218384, "learning_rate": 9.704451046325114e-08, "loss": 0.7882, "step": 16384 }, { "epoch": 0.9570677570093458, "grad_norm": 1.093308687210083, "learning_rate": 9.678176435892417e-08, "loss": 0.9529, "step": 16385 }, { "epoch": 0.9571261682242991, "grad_norm": 0.8522695899009705, "learning_rate": 9.651937269728905e-08, "loss": 0.7509, "step": 16386 }, { "epoch": 0.9571845794392523, "grad_norm": 1.0374603271484375, "learning_rate": 9.62573354877383e-08, "loss": 0.9516, "step": 16387 }, { "epoch": 0.9572429906542056, "grad_norm": 1.2235466241836548, "learning_rate": 9.599565273964995e-08, "loss": 0.9253, "step": 16388 }, { "epoch": 0.9573014018691589, "grad_norm": 1.0002394914627075, "learning_rate": 9.573432446238762e-08, "loss": 0.928, "step": 16389 }, { "epoch": 0.9573598130841121, "grad_norm": 1.0350396633148193, "learning_rate": 9.547335066530605e-08, "loss": 0.815, "step": 16390 }, { "epoch": 0.9574182242990654, "grad_norm": 1.5946238040924072, "learning_rate": 9.521273135774667e-08, "loss": 0.7177, "step": 16391 }, { "epoch": 0.9574766355140187, "grad_norm": 0.9209709167480469, "learning_rate": 9.495246654903533e-08, "loss": 0.7234, "step": 16392 }, { "epoch": 0.9575350467289719, "grad_norm": 1.3415520191192627, "learning_rate": 9.469255624848906e-08, "loss": 0.7261, "step": 16393 }, { "epoch": 0.9575934579439253, "grad_norm": 1.071346402168274, "learning_rate": 9.443300046540815e-08, "loss": 0.735, "step": 16394 }, { "epoch": 0.9576518691588785, "grad_norm": 1.2546876668930054, "learning_rate": 9.417379920908409e-08, "loss": 0.7293, "step": 16395 }, { "epoch": 0.9577102803738318, "grad_norm": 1.0748156309127808, "learning_rate": 9.391495248879168e-08, "loss": 0.751, "step": 16396 }, { "epoch": 0.9577686915887851, "grad_norm": 0.9307128190994263, "learning_rate": 9.365646031379683e-08, "loss": 0.7773, "step": 16397 }, { "epoch": 0.9578271028037383, "grad_norm": 1.4294321537017822, "learning_rate": 9.339832269335103e-08, "loss": 0.8433, "step": 16398 }, { "epoch": 0.9578855140186916, "grad_norm": 1.1196880340576172, "learning_rate": 9.314053963669245e-08, "loss": 0.7307, "step": 16399 }, { "epoch": 0.9579439252336449, "grad_norm": 5.200107097625732, "learning_rate": 9.288311115304926e-08, "loss": 0.7607, "step": 16400 }, { "epoch": 0.9580023364485981, "grad_norm": 0.9073560237884521, "learning_rate": 9.262603725163189e-08, "loss": 0.6183, "step": 16401 }, { "epoch": 0.9580607476635514, "grad_norm": 1.0705080032348633, "learning_rate": 9.236931794164295e-08, "loss": 0.7831, "step": 16402 }, { "epoch": 0.9581191588785046, "grad_norm": 1.6820372343063354, "learning_rate": 9.211295323227176e-08, "loss": 0.6396, "step": 16403 }, { "epoch": 0.9581775700934579, "grad_norm": 1.1577403545379639, "learning_rate": 9.185694313269211e-08, "loss": 0.7956, "step": 16404 }, { "epoch": 0.9582359813084113, "grad_norm": 0.9048067927360535, "learning_rate": 9.160128765206666e-08, "loss": 0.7115, "step": 16405 }, { "epoch": 0.9582943925233645, "grad_norm": 0.9671370983123779, "learning_rate": 9.134598679954699e-08, "loss": 0.6418, "step": 16406 }, { "epoch": 0.9583528037383178, "grad_norm": 1.2994810342788696, "learning_rate": 9.109104058426799e-08, "loss": 0.7987, "step": 16407 }, { "epoch": 0.958411214953271, "grad_norm": 2.2653486728668213, "learning_rate": 9.083644901535793e-08, "loss": 0.7755, "step": 16408 }, { "epoch": 0.9584696261682243, "grad_norm": 1.1284708976745605, "learning_rate": 9.058221210192509e-08, "loss": 0.9255, "step": 16409 }, { "epoch": 0.9585280373831776, "grad_norm": 1.1785361766815186, "learning_rate": 9.032832985307105e-08, "loss": 0.7748, "step": 16410 }, { "epoch": 0.9585864485981308, "grad_norm": 1.1051414012908936, "learning_rate": 9.00748022778819e-08, "loss": 0.8075, "step": 16411 }, { "epoch": 0.9586448598130841, "grad_norm": 1.0314375162124634, "learning_rate": 8.982162938543149e-08, "loss": 1.0233, "step": 16412 }, { "epoch": 0.9587032710280374, "grad_norm": 1.0005930662155151, "learning_rate": 8.956881118478033e-08, "loss": 0.9063, "step": 16413 }, { "epoch": 0.9587616822429906, "grad_norm": 1.0651850700378418, "learning_rate": 8.931634768497788e-08, "loss": 0.7101, "step": 16414 }, { "epoch": 0.958820093457944, "grad_norm": 0.971287190914154, "learning_rate": 8.906423889506133e-08, "loss": 0.7993, "step": 16415 }, { "epoch": 0.9588785046728971, "grad_norm": 1.2325674295425415, "learning_rate": 8.881248482405125e-08, "loss": 0.675, "step": 16416 }, { "epoch": 0.9589369158878505, "grad_norm": 1.2114149332046509, "learning_rate": 8.856108548095821e-08, "loss": 0.6876, "step": 16417 }, { "epoch": 0.9589953271028038, "grad_norm": 1.059341311454773, "learning_rate": 8.831004087478168e-08, "loss": 0.6634, "step": 16418 }, { "epoch": 0.959053738317757, "grad_norm": 1.4855574369430542, "learning_rate": 8.805935101450447e-08, "loss": 0.8535, "step": 16419 }, { "epoch": 0.9591121495327103, "grad_norm": 0.7587547302246094, "learning_rate": 8.780901590910162e-08, "loss": 0.5693, "step": 16420 }, { "epoch": 0.9591705607476636, "grad_norm": 0.9776155948638916, "learning_rate": 8.755903556753265e-08, "loss": 0.6322, "step": 16421 }, { "epoch": 0.9592289719626168, "grad_norm": 1.016216516494751, "learning_rate": 8.730940999874149e-08, "loss": 0.733, "step": 16422 }, { "epoch": 0.9592873831775701, "grad_norm": 1.8438855409622192, "learning_rate": 8.706013921166434e-08, "loss": 0.7341, "step": 16423 }, { "epoch": 0.9593457943925233, "grad_norm": 1.2420144081115723, "learning_rate": 8.681122321522296e-08, "loss": 0.8413, "step": 16424 }, { "epoch": 0.9594042056074766, "grad_norm": 1.2268953323364258, "learning_rate": 8.656266201832687e-08, "loss": 0.7592, "step": 16425 }, { "epoch": 0.95946261682243, "grad_norm": 1.866661787033081, "learning_rate": 8.631445562987007e-08, "loss": 0.7841, "step": 16426 }, { "epoch": 0.9595210280373832, "grad_norm": 1.0139780044555664, "learning_rate": 8.606660405873768e-08, "loss": 0.8236, "step": 16427 }, { "epoch": 0.9595794392523365, "grad_norm": 1.1432814598083496, "learning_rate": 8.581910731380039e-08, "loss": 0.7377, "step": 16428 }, { "epoch": 0.9596378504672897, "grad_norm": 0.9729796051979065, "learning_rate": 8.557196540391555e-08, "loss": 0.6663, "step": 16429 }, { "epoch": 0.959696261682243, "grad_norm": 1.1499998569488525, "learning_rate": 8.532517833792942e-08, "loss": 0.7271, "step": 16430 }, { "epoch": 0.9597546728971963, "grad_norm": 0.915715754032135, "learning_rate": 8.507874612467382e-08, "loss": 0.7156, "step": 16431 }, { "epoch": 0.9598130841121495, "grad_norm": 1.7817360162734985, "learning_rate": 8.483266877296947e-08, "loss": 0.7097, "step": 16432 }, { "epoch": 0.9598714953271028, "grad_norm": 0.9560425281524658, "learning_rate": 8.458694629162267e-08, "loss": 0.7784, "step": 16433 }, { "epoch": 0.9599299065420561, "grad_norm": 1.0980039834976196, "learning_rate": 8.43415786894286e-08, "loss": 0.8309, "step": 16434 }, { "epoch": 0.9599883177570093, "grad_norm": 1.236159086227417, "learning_rate": 8.409656597516913e-08, "loss": 0.7577, "step": 16435 }, { "epoch": 0.9600467289719626, "grad_norm": 1.1753723621368408, "learning_rate": 8.38519081576139e-08, "loss": 0.7731, "step": 16436 }, { "epoch": 0.9601051401869158, "grad_norm": 1.2192893028259277, "learning_rate": 8.360760524551814e-08, "loss": 0.6688, "step": 16437 }, { "epoch": 0.9601635514018692, "grad_norm": 1.0740008354187012, "learning_rate": 8.336365724762707e-08, "loss": 0.936, "step": 16438 }, { "epoch": 0.9602219626168225, "grad_norm": 1.1749428510665894, "learning_rate": 8.312006417267038e-08, "loss": 0.6693, "step": 16439 }, { "epoch": 0.9602803738317757, "grad_norm": 1.0558182001113892, "learning_rate": 8.287682602936776e-08, "loss": 0.8081, "step": 16440 }, { "epoch": 0.960338785046729, "grad_norm": 1.015061378479004, "learning_rate": 8.263394282642445e-08, "loss": 0.7336, "step": 16441 }, { "epoch": 0.9603971962616823, "grad_norm": 1.05629301071167, "learning_rate": 8.239141457253131e-08, "loss": 0.6903, "step": 16442 }, { "epoch": 0.9604556074766355, "grad_norm": 1.006253719329834, "learning_rate": 8.214924127637247e-08, "loss": 0.7056, "step": 16443 }, { "epoch": 0.9605140186915888, "grad_norm": 0.8831316232681274, "learning_rate": 8.190742294661214e-08, "loss": 0.8194, "step": 16444 }, { "epoch": 0.960572429906542, "grad_norm": 2.6557538509368896, "learning_rate": 8.166595959190671e-08, "loss": 0.5963, "step": 16445 }, { "epoch": 0.9606308411214953, "grad_norm": 1.0398451089859009, "learning_rate": 8.142485122089816e-08, "loss": 0.77, "step": 16446 }, { "epoch": 0.9606892523364486, "grad_norm": 1.2728633880615234, "learning_rate": 8.118409784221515e-08, "loss": 0.7219, "step": 16447 }, { "epoch": 0.9607476635514018, "grad_norm": 0.9971694946289062, "learning_rate": 8.094369946447633e-08, "loss": 0.9431, "step": 16448 }, { "epoch": 0.9608060747663552, "grad_norm": 1.0860308408737183, "learning_rate": 8.070365609628372e-08, "loss": 0.7283, "step": 16449 }, { "epoch": 0.9608644859813084, "grad_norm": 1.0607107877731323, "learning_rate": 8.046396774622933e-08, "loss": 0.7213, "step": 16450 }, { "epoch": 0.9609228971962617, "grad_norm": 0.8142647743225098, "learning_rate": 8.022463442289074e-08, "loss": 0.8259, "step": 16451 }, { "epoch": 0.960981308411215, "grad_norm": 1.0440549850463867, "learning_rate": 7.998565613483556e-08, "loss": 0.7777, "step": 16452 }, { "epoch": 0.9610397196261682, "grad_norm": 0.7991484999656677, "learning_rate": 7.974703289061691e-08, "loss": 0.651, "step": 16453 }, { "epoch": 0.9610981308411215, "grad_norm": 1.0888816118240356, "learning_rate": 7.950876469877467e-08, "loss": 0.6166, "step": 16454 }, { "epoch": 0.9611565420560748, "grad_norm": 1.1208535432815552, "learning_rate": 7.927085156783643e-08, "loss": 0.7161, "step": 16455 }, { "epoch": 0.961214953271028, "grad_norm": 1.0850821733474731, "learning_rate": 7.903329350631649e-08, "loss": 0.733, "step": 16456 }, { "epoch": 0.9612733644859813, "grad_norm": 1.007594108581543, "learning_rate": 7.87960905227192e-08, "loss": 0.6771, "step": 16457 }, { "epoch": 0.9613317757009345, "grad_norm": 1.0607072114944458, "learning_rate": 7.855924262553328e-08, "loss": 0.8138, "step": 16458 }, { "epoch": 0.9613901869158878, "grad_norm": 0.9345342516899109, "learning_rate": 7.832274982323418e-08, "loss": 0.9442, "step": 16459 }, { "epoch": 0.9614485981308412, "grad_norm": 1.0174953937530518, "learning_rate": 7.808661212428848e-08, "loss": 0.723, "step": 16460 }, { "epoch": 0.9615070093457944, "grad_norm": 0.9301005601882935, "learning_rate": 7.785082953714718e-08, "loss": 0.7555, "step": 16461 }, { "epoch": 0.9615654205607477, "grad_norm": 0.9635090231895447, "learning_rate": 7.761540207024798e-08, "loss": 0.6056, "step": 16462 }, { "epoch": 0.961623831775701, "grad_norm": 1.3144155740737915, "learning_rate": 7.738032973201748e-08, "loss": 0.688, "step": 16463 }, { "epoch": 0.9616822429906542, "grad_norm": 1.0558394193649292, "learning_rate": 7.714561253086894e-08, "loss": 0.7188, "step": 16464 }, { "epoch": 0.9617406542056075, "grad_norm": 1.024694561958313, "learning_rate": 7.691125047520454e-08, "loss": 0.8674, "step": 16465 }, { "epoch": 0.9617990654205607, "grad_norm": 1.2014329433441162, "learning_rate": 7.667724357341089e-08, "loss": 0.7192, "step": 16466 }, { "epoch": 0.961857476635514, "grad_norm": 1.2713794708251953, "learning_rate": 7.644359183386241e-08, "loss": 0.6734, "step": 16467 }, { "epoch": 0.9619158878504673, "grad_norm": 0.8969206213951111, "learning_rate": 7.621029526492241e-08, "loss": 0.6944, "step": 16468 }, { "epoch": 0.9619742990654205, "grad_norm": 1.08560049533844, "learning_rate": 7.597735387494198e-08, "loss": 0.7466, "step": 16469 }, { "epoch": 0.9620327102803738, "grad_norm": 1.0407885313034058, "learning_rate": 7.57447676722567e-08, "loss": 0.6844, "step": 16470 }, { "epoch": 0.962091121495327, "grad_norm": 1.850433111190796, "learning_rate": 7.551253666519209e-08, "loss": 0.7536, "step": 16471 }, { "epoch": 0.9621495327102804, "grad_norm": 1.1929938793182373, "learning_rate": 7.528066086205821e-08, "loss": 0.7372, "step": 16472 }, { "epoch": 0.9622079439252337, "grad_norm": 0.9278514981269836, "learning_rate": 7.504914027115617e-08, "loss": 0.7169, "step": 16473 }, { "epoch": 0.9622663551401869, "grad_norm": 1.1316279172897339, "learning_rate": 7.481797490077048e-08, "loss": 0.8966, "step": 16474 }, { "epoch": 0.9623247663551402, "grad_norm": 1.0789140462875366, "learning_rate": 7.45871647591756e-08, "loss": 0.83, "step": 16475 }, { "epoch": 0.9623831775700935, "grad_norm": 1.0342090129852295, "learning_rate": 7.435670985463272e-08, "loss": 0.851, "step": 16476 }, { "epoch": 0.9624415887850467, "grad_norm": 1.1118932962417603, "learning_rate": 7.412661019538858e-08, "loss": 0.6779, "step": 16477 }, { "epoch": 0.9625, "grad_norm": 1.1382982730865479, "learning_rate": 7.389686578967991e-08, "loss": 0.7106, "step": 16478 }, { "epoch": 0.9625584112149532, "grad_norm": 1.4145489931106567, "learning_rate": 7.366747664572904e-08, "loss": 0.8804, "step": 16479 }, { "epoch": 0.9626168224299065, "grad_norm": 1.1637096405029297, "learning_rate": 7.343844277174494e-08, "loss": 0.8816, "step": 16480 }, { "epoch": 0.9626752336448599, "grad_norm": 1.0500061511993408, "learning_rate": 7.320976417592773e-08, "loss": 0.6366, "step": 16481 }, { "epoch": 0.962733644859813, "grad_norm": 0.9995824694633484, "learning_rate": 7.298144086645865e-08, "loss": 0.6912, "step": 16482 }, { "epoch": 0.9627920560747664, "grad_norm": 1.11471688747406, "learning_rate": 7.275347285151113e-08, "loss": 0.6672, "step": 16483 }, { "epoch": 0.9628504672897197, "grad_norm": 1.0953831672668457, "learning_rate": 7.252586013924423e-08, "loss": 0.7417, "step": 16484 }, { "epoch": 0.9629088785046729, "grad_norm": 0.9087370038032532, "learning_rate": 7.229860273780364e-08, "loss": 0.6841, "step": 16485 }, { "epoch": 0.9629672897196262, "grad_norm": 0.9244865775108337, "learning_rate": 7.20717006553251e-08, "loss": 0.814, "step": 16486 }, { "epoch": 0.9630257009345794, "grad_norm": 1.0133817195892334, "learning_rate": 7.184515389992652e-08, "loss": 0.668, "step": 16487 }, { "epoch": 0.9630841121495327, "grad_norm": 1.037129521369934, "learning_rate": 7.161896247971922e-08, "loss": 0.7773, "step": 16488 }, { "epoch": 0.963142523364486, "grad_norm": 0.8064497113227844, "learning_rate": 7.139312640279562e-08, "loss": 0.5884, "step": 16489 }, { "epoch": 0.9632009345794392, "grad_norm": 1.0237805843353271, "learning_rate": 7.116764567724144e-08, "loss": 0.694, "step": 16490 }, { "epoch": 0.9632593457943925, "grad_norm": 0.9422010779380798, "learning_rate": 7.094252031112581e-08, "loss": 0.6514, "step": 16491 }, { "epoch": 0.9633177570093457, "grad_norm": 2.23109769821167, "learning_rate": 7.07177503125045e-08, "loss": 0.7267, "step": 16492 }, { "epoch": 0.9633761682242991, "grad_norm": 3.7056431770324707, "learning_rate": 7.049333568942441e-08, "loss": 0.7389, "step": 16493 }, { "epoch": 0.9634345794392524, "grad_norm": 1.1415927410125732, "learning_rate": 7.026927644991688e-08, "loss": 0.8501, "step": 16494 }, { "epoch": 0.9634929906542056, "grad_norm": 1.099382758140564, "learning_rate": 7.004557260200107e-08, "loss": 0.8774, "step": 16495 }, { "epoch": 0.9635514018691589, "grad_norm": 1.1018707752227783, "learning_rate": 6.982222415368167e-08, "loss": 0.5426, "step": 16496 }, { "epoch": 0.9636098130841122, "grad_norm": 0.8801037669181824, "learning_rate": 6.959923111295563e-08, "loss": 0.6747, "step": 16497 }, { "epoch": 0.9636682242990654, "grad_norm": 1.0040230751037598, "learning_rate": 6.937659348780212e-08, "loss": 0.6437, "step": 16498 }, { "epoch": 0.9637266355140187, "grad_norm": 1.6622085571289062, "learning_rate": 6.915431128619032e-08, "loss": 0.7676, "step": 16499 }, { "epoch": 0.9637850467289719, "grad_norm": 1.2141220569610596, "learning_rate": 6.893238451607387e-08, "loss": 0.7384, "step": 16500 }, { "epoch": 0.9638434579439252, "grad_norm": 1.1903188228607178, "learning_rate": 6.871081318539863e-08, "loss": 0.8605, "step": 16501 }, { "epoch": 0.9639018691588785, "grad_norm": 1.3160868883132935, "learning_rate": 6.84895973020927e-08, "loss": 0.9703, "step": 16502 }, { "epoch": 0.9639602803738317, "grad_norm": 1.1273378133773804, "learning_rate": 6.82687368740742e-08, "loss": 0.7704, "step": 16503 }, { "epoch": 0.9640186915887851, "grad_norm": 1.1347438097000122, "learning_rate": 6.804823190924792e-08, "loss": 0.824, "step": 16504 }, { "epoch": 0.9640771028037384, "grad_norm": 1.0118441581726074, "learning_rate": 6.782808241550642e-08, "loss": 0.708, "step": 16505 }, { "epoch": 0.9641355140186916, "grad_norm": 0.9722208976745605, "learning_rate": 6.760828840072675e-08, "loss": 0.547, "step": 16506 }, { "epoch": 0.9641939252336449, "grad_norm": 0.9784893989562988, "learning_rate": 6.738884987277816e-08, "loss": 0.7563, "step": 16507 }, { "epoch": 0.9642523364485981, "grad_norm": 1.010029673576355, "learning_rate": 6.716976683951438e-08, "loss": 0.8191, "step": 16508 }, { "epoch": 0.9643107476635514, "grad_norm": 0.9131863713264465, "learning_rate": 6.695103930877466e-08, "loss": 0.6549, "step": 16509 }, { "epoch": 0.9643691588785047, "grad_norm": 1.0978455543518066, "learning_rate": 6.673266728838834e-08, "loss": 0.739, "step": 16510 }, { "epoch": 0.9644275700934579, "grad_norm": 1.2475311756134033, "learning_rate": 6.651465078617136e-08, "loss": 0.7491, "step": 16511 }, { "epoch": 0.9644859813084112, "grad_norm": 1.1151700019836426, "learning_rate": 6.629698980992527e-08, "loss": 0.7173, "step": 16512 }, { "epoch": 0.9645443925233644, "grad_norm": 0.9185647964477539, "learning_rate": 6.607968436744272e-08, "loss": 0.7323, "step": 16513 }, { "epoch": 0.9646028037383177, "grad_norm": 0.9620065689086914, "learning_rate": 6.586273446649972e-08, "loss": 0.6769, "step": 16514 }, { "epoch": 0.9646612149532711, "grad_norm": 1.0235161781311035, "learning_rate": 6.564614011486114e-08, "loss": 0.679, "step": 16515 }, { "epoch": 0.9647196261682243, "grad_norm": 1.0273202657699585, "learning_rate": 6.54299013202786e-08, "loss": 0.6224, "step": 16516 }, { "epoch": 0.9647780373831776, "grad_norm": 3.021362066268921, "learning_rate": 6.521401809049254e-08, "loss": 0.728, "step": 16517 }, { "epoch": 0.9648364485981309, "grad_norm": 0.8897334933280945, "learning_rate": 6.499849043322903e-08, "loss": 0.7078, "step": 16518 }, { "epoch": 0.9648948598130841, "grad_norm": 0.9852925539016724, "learning_rate": 6.478331835620189e-08, "loss": 0.6399, "step": 16519 }, { "epoch": 0.9649532710280374, "grad_norm": 1.2320693731307983, "learning_rate": 6.456850186711271e-08, "loss": 0.654, "step": 16520 }, { "epoch": 0.9650116822429906, "grad_norm": 1.3886138200759888, "learning_rate": 6.435404097364984e-08, "loss": 0.7473, "step": 16521 }, { "epoch": 0.9650700934579439, "grad_norm": 0.8773228526115417, "learning_rate": 6.413993568348709e-08, "loss": 0.7423, "step": 16522 }, { "epoch": 0.9651285046728972, "grad_norm": 0.8689234256744385, "learning_rate": 6.392618600429057e-08, "loss": 0.5621, "step": 16523 }, { "epoch": 0.9651869158878504, "grad_norm": 1.5119953155517578, "learning_rate": 6.371279194370861e-08, "loss": 0.673, "step": 16524 }, { "epoch": 0.9652453271028038, "grad_norm": 1.1072852611541748, "learning_rate": 6.349975350937843e-08, "loss": 0.7417, "step": 16525 }, { "epoch": 0.965303738317757, "grad_norm": 1.2402427196502686, "learning_rate": 6.328707070892615e-08, "loss": 0.8108, "step": 16526 }, { "epoch": 0.9653621495327103, "grad_norm": 0.8419666290283203, "learning_rate": 6.307474354996234e-08, "loss": 0.6652, "step": 16527 }, { "epoch": 0.9654205607476636, "grad_norm": 1.0826411247253418, "learning_rate": 6.286277204008761e-08, "loss": 0.6755, "step": 16528 }, { "epoch": 0.9654789719626168, "grad_norm": 0.9824995994567871, "learning_rate": 6.265115618688811e-08, "loss": 0.7058, "step": 16529 }, { "epoch": 0.9655373831775701, "grad_norm": 1.083387017250061, "learning_rate": 6.243989599793666e-08, "loss": 0.8014, "step": 16530 }, { "epoch": 0.9655957943925234, "grad_norm": 1.0043346881866455, "learning_rate": 6.22289914807972e-08, "loss": 0.6459, "step": 16531 }, { "epoch": 0.9656542056074766, "grad_norm": 1.1288093328475952, "learning_rate": 6.201844264301483e-08, "loss": 0.7818, "step": 16532 }, { "epoch": 0.9657126168224299, "grad_norm": 1.0217311382293701, "learning_rate": 6.180824949212794e-08, "loss": 0.7226, "step": 16533 }, { "epoch": 0.9657710280373831, "grad_norm": 1.0654829740524292, "learning_rate": 6.15984120356572e-08, "loss": 0.6674, "step": 16534 }, { "epoch": 0.9658294392523364, "grad_norm": 0.9451408386230469, "learning_rate": 6.138893028111437e-08, "loss": 0.696, "step": 16535 }, { "epoch": 0.9658878504672898, "grad_norm": 0.8887020349502563, "learning_rate": 6.117980423599679e-08, "loss": 0.6962, "step": 16536 }, { "epoch": 0.965946261682243, "grad_norm": 1.2203725576400757, "learning_rate": 6.097103390778847e-08, "loss": 0.924, "step": 16537 }, { "epoch": 0.9660046728971963, "grad_norm": 1.2352299690246582, "learning_rate": 6.076261930396232e-08, "loss": 0.8116, "step": 16538 }, { "epoch": 0.9660630841121496, "grad_norm": 1.2785093784332275, "learning_rate": 6.055456043197683e-08, "loss": 0.8445, "step": 16539 }, { "epoch": 0.9661214953271028, "grad_norm": 0.8907394409179688, "learning_rate": 6.034685729927825e-08, "loss": 0.7795, "step": 16540 }, { "epoch": 0.9661799065420561, "grad_norm": 1.1477694511413574, "learning_rate": 6.013950991330286e-08, "loss": 0.6696, "step": 16541 }, { "epoch": 0.9662383177570093, "grad_norm": 1.1640374660491943, "learning_rate": 5.993251828146918e-08, "loss": 0.7333, "step": 16542 }, { "epoch": 0.9662967289719626, "grad_norm": 1.3980247974395752, "learning_rate": 5.972588241118571e-08, "loss": 0.7559, "step": 16543 }, { "epoch": 0.9663551401869159, "grad_norm": 1.3701581954956055, "learning_rate": 5.951960230984988e-08, "loss": 0.8641, "step": 16544 }, { "epoch": 0.9664135514018691, "grad_norm": 0.9511581063270569, "learning_rate": 5.9313677984841334e-08, "loss": 0.6973, "step": 16545 }, { "epoch": 0.9664719626168224, "grad_norm": 1.0585383176803589, "learning_rate": 5.910810944353418e-08, "loss": 0.8182, "step": 16546 }, { "epoch": 0.9665303738317756, "grad_norm": 1.0049127340316772, "learning_rate": 5.890289669328475e-08, "loss": 0.7246, "step": 16547 }, { "epoch": 0.966588785046729, "grad_norm": 1.113680124282837, "learning_rate": 5.8698039741436066e-08, "loss": 0.8231, "step": 16548 }, { "epoch": 0.9666471962616823, "grad_norm": 1.2283337116241455, "learning_rate": 5.8493538595321145e-08, "loss": 0.7935, "step": 16549 }, { "epoch": 0.9667056074766355, "grad_norm": 1.1173479557037354, "learning_rate": 5.8289393262258576e-08, "loss": 0.8976, "step": 16550 }, { "epoch": 0.9667640186915888, "grad_norm": 0.8969032168388367, "learning_rate": 5.808560374955585e-08, "loss": 0.833, "step": 16551 }, { "epoch": 0.9668224299065421, "grad_norm": 1.2234960794448853, "learning_rate": 5.788217006450714e-08, "loss": 0.5701, "step": 16552 }, { "epoch": 0.9668808411214953, "grad_norm": 0.9673880934715271, "learning_rate": 5.767909221439105e-08, "loss": 0.7094, "step": 16553 }, { "epoch": 0.9669392523364486, "grad_norm": 0.8560855388641357, "learning_rate": 5.747637020647845e-08, "loss": 0.9172, "step": 16554 }, { "epoch": 0.9669976635514018, "grad_norm": 0.7798063158988953, "learning_rate": 5.727400404802352e-08, "loss": 0.5848, "step": 16555 }, { "epoch": 0.9670560747663551, "grad_norm": 1.2091463804244995, "learning_rate": 5.707199374627048e-08, "loss": 0.6058, "step": 16556 }, { "epoch": 0.9671144859813084, "grad_norm": 1.4464553594589233, "learning_rate": 5.6870339308446874e-08, "loss": 0.7893, "step": 16557 }, { "epoch": 0.9671728971962616, "grad_norm": 1.17125403881073, "learning_rate": 5.666904074177248e-08, "loss": 0.8567, "step": 16558 }, { "epoch": 0.967231308411215, "grad_norm": 0.9321736097335815, "learning_rate": 5.646809805345155e-08, "loss": 0.6328, "step": 16559 }, { "epoch": 0.9672897196261683, "grad_norm": 0.8890886902809143, "learning_rate": 5.6267511250673866e-08, "loss": 0.7863, "step": 16560 }, { "epoch": 0.9673481308411215, "grad_norm": 0.9989510774612427, "learning_rate": 5.606728034062148e-08, "loss": 0.7656, "step": 16561 }, { "epoch": 0.9674065420560748, "grad_norm": 1.2156214714050293, "learning_rate": 5.586740533045865e-08, "loss": 0.7073, "step": 16562 }, { "epoch": 0.967464953271028, "grad_norm": 0.8893871903419495, "learning_rate": 5.566788622733965e-08, "loss": 0.6777, "step": 16563 }, { "epoch": 0.9675233644859813, "grad_norm": 1.2390319108963013, "learning_rate": 5.5468723038405446e-08, "loss": 0.8141, "step": 16564 }, { "epoch": 0.9675817757009346, "grad_norm": 0.7693612575531006, "learning_rate": 5.5269915770784776e-08, "loss": 0.6374, "step": 16565 }, { "epoch": 0.9676401869158878, "grad_norm": 1.1277929544448853, "learning_rate": 5.507146443159306e-08, "loss": 0.735, "step": 16566 }, { "epoch": 0.9676985981308411, "grad_norm": 1.065076231956482, "learning_rate": 5.4873369027931275e-08, "loss": 0.8925, "step": 16567 }, { "epoch": 0.9677570093457943, "grad_norm": 1.0054653882980347, "learning_rate": 5.467562956689154e-08, "loss": 0.7072, "step": 16568 }, { "epoch": 0.9678154205607477, "grad_norm": 1.5433205366134644, "learning_rate": 5.447824605555041e-08, "loss": 0.7964, "step": 16569 }, { "epoch": 0.967873831775701, "grad_norm": 1.3352645635604858, "learning_rate": 5.428121850097112e-08, "loss": 0.7125, "step": 16570 }, { "epoch": 0.9679322429906542, "grad_norm": 0.9282044768333435, "learning_rate": 5.4084546910206926e-08, "loss": 0.7948, "step": 16571 }, { "epoch": 0.9679906542056075, "grad_norm": 1.0517911911010742, "learning_rate": 5.388823129029663e-08, "loss": 0.6574, "step": 16572 }, { "epoch": 0.9680490654205608, "grad_norm": 0.8315090537071228, "learning_rate": 5.369227164826574e-08, "loss": 0.8157, "step": 16573 }, { "epoch": 0.968107476635514, "grad_norm": 0.8714753985404968, "learning_rate": 5.3496667991128626e-08, "loss": 0.7399, "step": 16574 }, { "epoch": 0.9681658878504673, "grad_norm": 0.7775312662124634, "learning_rate": 5.330142032588637e-08, "loss": 0.5779, "step": 16575 }, { "epoch": 0.9682242990654205, "grad_norm": 1.3152797222137451, "learning_rate": 5.310652865952559e-08, "loss": 0.563, "step": 16576 }, { "epoch": 0.9682827102803738, "grad_norm": 2.0711443424224854, "learning_rate": 5.2911992999022946e-08, "loss": 0.5728, "step": 16577 }, { "epoch": 0.9683411214953271, "grad_norm": 1.2386916875839233, "learning_rate": 5.271781335133952e-08, "loss": 0.7548, "step": 16578 }, { "epoch": 0.9683995327102803, "grad_norm": 1.0535063743591309, "learning_rate": 5.252398972342643e-08, "loss": 0.7874, "step": 16579 }, { "epoch": 0.9684579439252337, "grad_norm": 1.0587222576141357, "learning_rate": 5.2330522122220336e-08, "loss": 0.6658, "step": 16580 }, { "epoch": 0.968516355140187, "grad_norm": 0.8644222617149353, "learning_rate": 5.213741055464572e-08, "loss": 0.7122, "step": 16581 }, { "epoch": 0.9685747663551402, "grad_norm": 1.2355483770370483, "learning_rate": 5.1944655027613696e-08, "loss": 0.9209, "step": 16582 }, { "epoch": 0.9686331775700935, "grad_norm": 5.7341742515563965, "learning_rate": 5.1752255548023214e-08, "loss": 0.7381, "step": 16583 }, { "epoch": 0.9686915887850467, "grad_norm": 1.4879876375198364, "learning_rate": 5.156021212276097e-08, "loss": 0.8809, "step": 16584 }, { "epoch": 0.96875, "grad_norm": 2.6883769035339355, "learning_rate": 5.1368524758700357e-08, "loss": 0.81, "step": 16585 }, { "epoch": 0.9688084112149533, "grad_norm": 0.9215119481086731, "learning_rate": 5.117719346270145e-08, "loss": 0.7917, "step": 16586 }, { "epoch": 0.9688668224299065, "grad_norm": 1.1311419010162354, "learning_rate": 5.098621824161209e-08, "loss": 0.7254, "step": 16587 }, { "epoch": 0.9689252336448598, "grad_norm": 0.9806286096572876, "learning_rate": 5.079559910226795e-08, "loss": 0.8564, "step": 16588 }, { "epoch": 0.968983644859813, "grad_norm": 0.8635913133621216, "learning_rate": 5.06053360514902e-08, "loss": 0.8994, "step": 16589 }, { "epoch": 0.9690420560747663, "grad_norm": 1.0032334327697754, "learning_rate": 5.04154290960901e-08, "loss": 0.7446, "step": 16590 }, { "epoch": 0.9691004672897197, "grad_norm": 1.2609845399856567, "learning_rate": 5.022587824286329e-08, "loss": 0.9142, "step": 16591 }, { "epoch": 0.9691588785046729, "grad_norm": 0.9934520721435547, "learning_rate": 5.0036683498594365e-08, "loss": 0.8451, "step": 16592 }, { "epoch": 0.9692172897196262, "grad_norm": 1.9909366369247437, "learning_rate": 4.9847844870055674e-08, "loss": 0.8279, "step": 16593 }, { "epoch": 0.9692757009345795, "grad_norm": 1.2369389533996582, "learning_rate": 4.9659362364004036e-08, "loss": 0.6656, "step": 16594 }, { "epoch": 0.9693341121495327, "grad_norm": 1.0412688255310059, "learning_rate": 4.9471235987186287e-08, "loss": 0.7408, "step": 16595 }, { "epoch": 0.969392523364486, "grad_norm": 1.0216418504714966, "learning_rate": 4.9283465746335915e-08, "loss": 0.7458, "step": 16596 }, { "epoch": 0.9694509345794392, "grad_norm": 1.0242570638656616, "learning_rate": 4.90960516481731e-08, "loss": 0.7206, "step": 16597 }, { "epoch": 0.9695093457943925, "grad_norm": 0.8358325958251953, "learning_rate": 4.890899369940472e-08, "loss": 0.6461, "step": 16598 }, { "epoch": 0.9695677570093458, "grad_norm": 1.0434421300888062, "learning_rate": 4.8722291906727615e-08, "loss": 0.7412, "step": 16599 }, { "epoch": 0.969626168224299, "grad_norm": 1.1558887958526611, "learning_rate": 4.853594627682201e-08, "loss": 0.7175, "step": 16600 }, { "epoch": 0.9696845794392523, "grad_norm": 0.9376499652862549, "learning_rate": 4.8349956816358124e-08, "loss": 0.5866, "step": 16601 }, { "epoch": 0.9697429906542057, "grad_norm": 1.2311846017837524, "learning_rate": 4.8164323531992854e-08, "loss": 0.8474, "step": 16602 }, { "epoch": 0.9698014018691589, "grad_norm": 2.0206825733184814, "learning_rate": 4.797904643036977e-08, "loss": 0.7509, "step": 16603 }, { "epoch": 0.9698598130841122, "grad_norm": 1.5081911087036133, "learning_rate": 4.7794125518120235e-08, "loss": 0.6558, "step": 16604 }, { "epoch": 0.9699182242990654, "grad_norm": 0.8821950554847717, "learning_rate": 4.76095608018623e-08, "loss": 0.7545, "step": 16605 }, { "epoch": 0.9699766355140187, "grad_norm": 0.9441689848899841, "learning_rate": 4.7425352288202883e-08, "loss": 0.7064, "step": 16606 }, { "epoch": 0.970035046728972, "grad_norm": 0.84527987241745, "learning_rate": 4.7241499983733394e-08, "loss": 0.7578, "step": 16607 }, { "epoch": 0.9700934579439252, "grad_norm": 1.1103472709655762, "learning_rate": 4.705800389503412e-08, "loss": 0.8106, "step": 16608 }, { "epoch": 0.9701518691588785, "grad_norm": 1.0100295543670654, "learning_rate": 4.6874864028674247e-08, "loss": 0.7311, "step": 16609 }, { "epoch": 0.9702102803738317, "grad_norm": 1.0499427318572998, "learning_rate": 4.6692080391207425e-08, "loss": 0.7915, "step": 16610 }, { "epoch": 0.970268691588785, "grad_norm": 1.3892194032669067, "learning_rate": 4.650965298917398e-08, "loss": 0.687, "step": 16611 }, { "epoch": 0.9703271028037384, "grad_norm": 1.0798219442367554, "learning_rate": 4.632758182910646e-08, "loss": 0.6453, "step": 16612 }, { "epoch": 0.9703855140186916, "grad_norm": 1.0926992893218994, "learning_rate": 4.6145866917517436e-08, "loss": 0.6736, "step": 16613 }, { "epoch": 0.9704439252336449, "grad_norm": 1.719644546508789, "learning_rate": 4.596450826091392e-08, "loss": 0.7329, "step": 16614 }, { "epoch": 0.9705023364485982, "grad_norm": 0.839188814163208, "learning_rate": 4.578350586578628e-08, "loss": 0.7362, "step": 16615 }, { "epoch": 0.9705607476635514, "grad_norm": 1.0093574523925781, "learning_rate": 4.560285973861045e-08, "loss": 0.6998, "step": 16616 }, { "epoch": 0.9706191588785047, "grad_norm": 0.9388003349304199, "learning_rate": 4.5422569885853474e-08, "loss": 0.6856, "step": 16617 }, { "epoch": 0.9706775700934579, "grad_norm": 0.9668912887573242, "learning_rate": 4.524263631396908e-08, "loss": 0.8299, "step": 16618 }, { "epoch": 0.9707359813084112, "grad_norm": 1.3067471981048584, "learning_rate": 4.506305902939545e-08, "loss": 0.6536, "step": 16619 }, { "epoch": 0.9707943925233645, "grad_norm": 1.3512190580368042, "learning_rate": 4.488383803856078e-08, "loss": 0.8547, "step": 16620 }, { "epoch": 0.9708528037383177, "grad_norm": 0.7705370783805847, "learning_rate": 4.4704973347878824e-08, "loss": 0.6581, "step": 16621 }, { "epoch": 0.970911214953271, "grad_norm": 1.0799176692962646, "learning_rate": 4.452646496375112e-08, "loss": 0.7509, "step": 16622 }, { "epoch": 0.9709696261682244, "grad_norm": 1.0063589811325073, "learning_rate": 4.4348312892567024e-08, "loss": 0.7349, "step": 16623 }, { "epoch": 0.9710280373831776, "grad_norm": 1.275887370109558, "learning_rate": 4.417051714070364e-08, "loss": 0.7882, "step": 16624 }, { "epoch": 0.9710864485981309, "grad_norm": 0.9958932399749756, "learning_rate": 4.399307771452366e-08, "loss": 0.8366, "step": 16625 }, { "epoch": 0.9711448598130841, "grad_norm": 0.9810906052589417, "learning_rate": 4.3815994620377556e-08, "loss": 0.8678, "step": 16626 }, { "epoch": 0.9712032710280374, "grad_norm": 2.552100896835327, "learning_rate": 4.3639267864603594e-08, "loss": 0.7828, "step": 16627 }, { "epoch": 0.9712616822429907, "grad_norm": 0.958914041519165, "learning_rate": 4.34628974535245e-08, "loss": 0.8428, "step": 16628 }, { "epoch": 0.9713200934579439, "grad_norm": 1.351359248161316, "learning_rate": 4.328688339345743e-08, "loss": 0.7075, "step": 16629 }, { "epoch": 0.9713785046728972, "grad_norm": 1.1217706203460693, "learning_rate": 4.3111225690698475e-08, "loss": 0.5971, "step": 16630 }, { "epoch": 0.9714369158878504, "grad_norm": 1.2741482257843018, "learning_rate": 4.293592435153593e-08, "loss": 0.7796, "step": 16631 }, { "epoch": 0.9714953271028037, "grad_norm": 2.690387010574341, "learning_rate": 4.276097938224255e-08, "loss": 0.7724, "step": 16632 }, { "epoch": 0.971553738317757, "grad_norm": 1.0083140134811401, "learning_rate": 4.258639078908111e-08, "loss": 0.744, "step": 16633 }, { "epoch": 0.9716121495327102, "grad_norm": 1.0061709880828857, "learning_rate": 4.2412158578299946e-08, "loss": 0.6983, "step": 16634 }, { "epoch": 0.9716705607476636, "grad_norm": 0.9470275044441223, "learning_rate": 4.2238282756135176e-08, "loss": 0.8195, "step": 16635 }, { "epoch": 0.9717289719626169, "grad_norm": 0.9929304718971252, "learning_rate": 4.20647633288096e-08, "loss": 0.7362, "step": 16636 }, { "epoch": 0.9717873831775701, "grad_norm": 0.9063149094581604, "learning_rate": 4.1891600302533805e-08, "loss": 0.777, "step": 16637 }, { "epoch": 0.9718457943925234, "grad_norm": 0.9061160087585449, "learning_rate": 4.1718793683505066e-08, "loss": 0.504, "step": 16638 }, { "epoch": 0.9719042056074766, "grad_norm": 0.9111661911010742, "learning_rate": 4.154634347790731e-08, "loss": 0.7678, "step": 16639 }, { "epoch": 0.9719626168224299, "grad_norm": 1.0471030473709106, "learning_rate": 4.137424969191561e-08, "loss": 0.7284, "step": 16640 }, { "epoch": 0.9720210280373832, "grad_norm": 1.257222294807434, "learning_rate": 4.120251233168615e-08, "loss": 0.7134, "step": 16641 }, { "epoch": 0.9720794392523364, "grad_norm": 0.8806679844856262, "learning_rate": 4.1031131403367344e-08, "loss": 0.7675, "step": 16642 }, { "epoch": 0.9721378504672897, "grad_norm": 1.256040334701538, "learning_rate": 4.086010691309206e-08, "loss": 0.6616, "step": 16643 }, { "epoch": 0.972196261682243, "grad_norm": 0.9768819212913513, "learning_rate": 4.0689438866982064e-08, "loss": 0.7674, "step": 16644 }, { "epoch": 0.9722546728971962, "grad_norm": 0.8980096578598022, "learning_rate": 4.051912727114582e-08, "loss": 0.6654, "step": 16645 }, { "epoch": 0.9723130841121496, "grad_norm": 1.1411409378051758, "learning_rate": 4.034917213167733e-08, "loss": 0.8409, "step": 16646 }, { "epoch": 0.9723714953271028, "grad_norm": 2.696553945541382, "learning_rate": 4.017957345466172e-08, "loss": 0.7377, "step": 16647 }, { "epoch": 0.9724299065420561, "grad_norm": 1.3235472440719604, "learning_rate": 4.001033124616749e-08, "loss": 0.609, "step": 16648 }, { "epoch": 0.9724883177570094, "grad_norm": 0.8481469750404358, "learning_rate": 3.9841445512251995e-08, "loss": 0.569, "step": 16649 }, { "epoch": 0.9725467289719626, "grad_norm": 0.7840811610221863, "learning_rate": 3.967291625896041e-08, "loss": 0.636, "step": 16650 }, { "epoch": 0.9726051401869159, "grad_norm": 1.2887617349624634, "learning_rate": 3.950474349232458e-08, "loss": 0.7688, "step": 16651 }, { "epoch": 0.9726635514018691, "grad_norm": 1.0023224353790283, "learning_rate": 3.933692721836302e-08, "loss": 0.7305, "step": 16652 }, { "epoch": 0.9727219626168224, "grad_norm": 1.1113144159317017, "learning_rate": 3.916946744308203e-08, "loss": 0.6011, "step": 16653 }, { "epoch": 0.9727803738317757, "grad_norm": 1.229365587234497, "learning_rate": 3.9002364172474607e-08, "loss": 0.7508, "step": 16654 }, { "epoch": 0.9728387850467289, "grad_norm": 1.0430384874343872, "learning_rate": 3.883561741252262e-08, "loss": 0.9235, "step": 16655 }, { "epoch": 0.9728971962616823, "grad_norm": 0.9951326251029968, "learning_rate": 3.866922716919241e-08, "loss": 0.9186, "step": 16656 }, { "epoch": 0.9729556074766356, "grad_norm": 0.8307605981826782, "learning_rate": 3.8503193448441447e-08, "loss": 0.8827, "step": 16657 }, { "epoch": 0.9730140186915888, "grad_norm": 1.2970341444015503, "learning_rate": 3.833751625621052e-08, "loss": 0.6571, "step": 16658 }, { "epoch": 0.9730724299065421, "grad_norm": 1.1148406267166138, "learning_rate": 3.817219559843044e-08, "loss": 0.7987, "step": 16659 }, { "epoch": 0.9731308411214953, "grad_norm": 1.1291977167129517, "learning_rate": 3.800723148101759e-08, "loss": 0.6987, "step": 16660 }, { "epoch": 0.9731892523364486, "grad_norm": 2.1169486045837402, "learning_rate": 3.784262390987503e-08, "loss": 0.9067, "step": 16661 }, { "epoch": 0.9732476635514019, "grad_norm": 0.9196640849113464, "learning_rate": 3.767837289089582e-08, "loss": 0.6397, "step": 16662 }, { "epoch": 0.9733060747663551, "grad_norm": 1.1498090028762817, "learning_rate": 3.751447842995748e-08, "loss": 0.8509, "step": 16663 }, { "epoch": 0.9733644859813084, "grad_norm": 1.0051257610321045, "learning_rate": 3.7350940532926425e-08, "loss": 0.8786, "step": 16664 }, { "epoch": 0.9734228971962616, "grad_norm": 1.520997166633606, "learning_rate": 3.718775920565687e-08, "loss": 0.6413, "step": 16665 }, { "epoch": 0.9734813084112149, "grad_norm": 1.1145509481430054, "learning_rate": 3.702493445398747e-08, "loss": 0.7794, "step": 16666 }, { "epoch": 0.9735397196261683, "grad_norm": 1.1142348051071167, "learning_rate": 3.686246628374579e-08, "loss": 0.668, "step": 16667 }, { "epoch": 0.9735981308411215, "grad_norm": 1.038894534111023, "learning_rate": 3.6700354700748284e-08, "loss": 0.7408, "step": 16668 }, { "epoch": 0.9736565420560748, "grad_norm": 1.2148529291152954, "learning_rate": 3.653859971079587e-08, "loss": 0.7054, "step": 16669 }, { "epoch": 0.9737149532710281, "grad_norm": 1.0730187892913818, "learning_rate": 3.637720131967726e-08, "loss": 0.8024, "step": 16670 }, { "epoch": 0.9737733644859813, "grad_norm": 1.070719838142395, "learning_rate": 3.621615953317115e-08, "loss": 0.7581, "step": 16671 }, { "epoch": 0.9738317757009346, "grad_norm": 0.9237644672393799, "learning_rate": 3.605547435703849e-08, "loss": 0.7665, "step": 16672 }, { "epoch": 0.9738901869158878, "grad_norm": 1.1244829893112183, "learning_rate": 3.589514579703357e-08, "loss": 0.7657, "step": 16673 }, { "epoch": 0.9739485981308411, "grad_norm": 0.8734045028686523, "learning_rate": 3.57351738588918e-08, "loss": 0.7019, "step": 16674 }, { "epoch": 0.9740070093457944, "grad_norm": 0.7842587232589722, "learning_rate": 3.5575558548339714e-08, "loss": 0.7343, "step": 16675 }, { "epoch": 0.9740654205607476, "grad_norm": 0.9580525159835815, "learning_rate": 3.541629987109052e-08, "loss": 0.8162, "step": 16676 }, { "epoch": 0.9741238317757009, "grad_norm": 1.0439910888671875, "learning_rate": 3.525739783284299e-08, "loss": 0.7256, "step": 16677 }, { "epoch": 0.9741822429906543, "grad_norm": 0.8291963934898376, "learning_rate": 3.50988524392859e-08, "loss": 0.6324, "step": 16678 }, { "epoch": 0.9742406542056075, "grad_norm": 1.0690724849700928, "learning_rate": 3.49406636960925e-08, "loss": 0.6792, "step": 16679 }, { "epoch": 0.9742990654205608, "grad_norm": 1.1145706176757812, "learning_rate": 3.478283160892604e-08, "loss": 0.8618, "step": 16680 }, { "epoch": 0.974357476635514, "grad_norm": 1.0122095346450806, "learning_rate": 3.46253561834331e-08, "loss": 0.7258, "step": 16681 }, { "epoch": 0.9744158878504673, "grad_norm": 1.0929605960845947, "learning_rate": 3.44682374252514e-08, "loss": 0.8125, "step": 16682 }, { "epoch": 0.9744742990654206, "grad_norm": 1.0612465143203735, "learning_rate": 3.431147534000423e-08, "loss": 0.7909, "step": 16683 }, { "epoch": 0.9745327102803738, "grad_norm": 0.859883189201355, "learning_rate": 3.4155069933301535e-08, "loss": 0.6268, "step": 16684 }, { "epoch": 0.9745911214953271, "grad_norm": 1.0159190893173218, "learning_rate": 3.399902121074217e-08, "loss": 0.8213, "step": 16685 }, { "epoch": 0.9746495327102803, "grad_norm": 0.9746846556663513, "learning_rate": 3.3843329177909447e-08, "loss": 0.7848, "step": 16686 }, { "epoch": 0.9747079439252336, "grad_norm": 1.1254570484161377, "learning_rate": 3.3687993840377794e-08, "loss": 0.8016, "step": 16687 }, { "epoch": 0.974766355140187, "grad_norm": 1.0911935567855835, "learning_rate": 3.3533015203705e-08, "loss": 0.7208, "step": 16688 }, { "epoch": 0.9748247663551401, "grad_norm": 1.1654376983642578, "learning_rate": 3.337839327343995e-08, "loss": 0.7695, "step": 16689 }, { "epoch": 0.9748831775700935, "grad_norm": 1.13788902759552, "learning_rate": 3.322412805511488e-08, "loss": 0.7755, "step": 16690 }, { "epoch": 0.9749415887850468, "grad_norm": 1.2176471948623657, "learning_rate": 3.307021955425094e-08, "loss": 0.7574, "step": 16691 }, { "epoch": 0.975, "grad_norm": 0.911449134349823, "learning_rate": 3.291666777635705e-08, "loss": 0.6854, "step": 16692 }, { "epoch": 0.9750584112149533, "grad_norm": 1.089856505393982, "learning_rate": 3.276347272692992e-08, "loss": 0.6891, "step": 16693 }, { "epoch": 0.9751168224299065, "grad_norm": 1.1577318906784058, "learning_rate": 3.261063441145185e-08, "loss": 0.7791, "step": 16694 }, { "epoch": 0.9751752336448598, "grad_norm": 0.8581148982048035, "learning_rate": 3.245815283539178e-08, "loss": 0.6288, "step": 16695 }, { "epoch": 0.9752336448598131, "grad_norm": 0.9427124857902527, "learning_rate": 3.230602800420979e-08, "loss": 0.7421, "step": 16696 }, { "epoch": 0.9752920560747663, "grad_norm": 1.0564793348312378, "learning_rate": 3.2154259923347086e-08, "loss": 0.8412, "step": 16697 }, { "epoch": 0.9753504672897196, "grad_norm": 0.9673711061477661, "learning_rate": 3.200284859823932e-08, "loss": 0.6913, "step": 16698 }, { "epoch": 0.975408878504673, "grad_norm": 1.2428452968597412, "learning_rate": 3.185179403430216e-08, "loss": 0.721, "step": 16699 }, { "epoch": 0.9754672897196262, "grad_norm": 0.8418024182319641, "learning_rate": 3.170109623694351e-08, "loss": 0.7552, "step": 16700 }, { "epoch": 0.9755257009345795, "grad_norm": 1.0784244537353516, "learning_rate": 3.155075521155793e-08, "loss": 0.6005, "step": 16701 }, { "epoch": 0.9755841121495327, "grad_norm": 1.1469142436981201, "learning_rate": 3.140077096352445e-08, "loss": 0.6598, "step": 16702 }, { "epoch": 0.975642523364486, "grad_norm": 1.0146723985671997, "learning_rate": 3.125114349821212e-08, "loss": 0.6496, "step": 16703 }, { "epoch": 0.9757009345794393, "grad_norm": 1.074518084526062, "learning_rate": 3.110187282097554e-08, "loss": 0.5184, "step": 16704 }, { "epoch": 0.9757593457943925, "grad_norm": 1.0943772792816162, "learning_rate": 3.095295893715822e-08, "loss": 0.7814, "step": 16705 }, { "epoch": 0.9758177570093458, "grad_norm": 1.1355105638504028, "learning_rate": 3.080440185208922e-08, "loss": 0.6582, "step": 16706 }, { "epoch": 0.975876168224299, "grad_norm": 0.9344711303710938, "learning_rate": 3.06562015710854e-08, "loss": 0.751, "step": 16707 }, { "epoch": 0.9759345794392523, "grad_norm": 1.0834014415740967, "learning_rate": 3.050835809945141e-08, "loss": 0.8366, "step": 16708 }, { "epoch": 0.9759929906542056, "grad_norm": 1.0505486726760864, "learning_rate": 3.0360871442477457e-08, "loss": 0.631, "step": 16709 }, { "epoch": 0.9760514018691588, "grad_norm": 0.9775967001914978, "learning_rate": 3.021374160544377e-08, "loss": 0.5772, "step": 16710 }, { "epoch": 0.9761098130841122, "grad_norm": 1.149606466293335, "learning_rate": 3.006696859361613e-08, "loss": 0.7584, "step": 16711 }, { "epoch": 0.9761682242990655, "grad_norm": 1.0503698587417603, "learning_rate": 2.9920552412245896e-08, "loss": 0.7866, "step": 16712 }, { "epoch": 0.9762266355140187, "grad_norm": 0.9822115898132324, "learning_rate": 2.9774493066574428e-08, "loss": 0.6909, "step": 16713 }, { "epoch": 0.976285046728972, "grad_norm": 1.116265892982483, "learning_rate": 2.9628790561829767e-08, "loss": 0.8448, "step": 16714 }, { "epoch": 0.9763434579439252, "grad_norm": 0.9576584696769714, "learning_rate": 2.9483444903227743e-08, "loss": 0.7424, "step": 16715 }, { "epoch": 0.9764018691588785, "grad_norm": 0.9011003971099854, "learning_rate": 2.9338456095967527e-08, "loss": 0.7309, "step": 16716 }, { "epoch": 0.9764602803738318, "grad_norm": 1.0447043180465698, "learning_rate": 2.9193824145239413e-08, "loss": 0.7449, "step": 16717 }, { "epoch": 0.976518691588785, "grad_norm": 1.0889204740524292, "learning_rate": 2.904954905622148e-08, "loss": 0.745, "step": 16718 }, { "epoch": 0.9765771028037383, "grad_norm": 1.1066495180130005, "learning_rate": 2.8905630834075162e-08, "loss": 0.744, "step": 16719 }, { "epoch": 0.9766355140186916, "grad_norm": 1.2501847743988037, "learning_rate": 2.876206948395299e-08, "loss": 0.7003, "step": 16720 }, { "epoch": 0.9766939252336448, "grad_norm": 0.9580166935920715, "learning_rate": 2.861886501099198e-08, "loss": 0.7422, "step": 16721 }, { "epoch": 0.9767523364485982, "grad_norm": 1.163811206817627, "learning_rate": 2.8476017420319134e-08, "loss": 0.7551, "step": 16722 }, { "epoch": 0.9768107476635514, "grad_norm": 2.4419291019439697, "learning_rate": 2.833352671704481e-08, "loss": 0.8201, "step": 16723 }, { "epoch": 0.9768691588785047, "grad_norm": 0.8742854595184326, "learning_rate": 2.8191392906270488e-08, "loss": 0.6366, "step": 16724 }, { "epoch": 0.976927570093458, "grad_norm": 0.934825599193573, "learning_rate": 2.80496159930832e-08, "loss": 0.7131, "step": 16725 }, { "epoch": 0.9769859813084112, "grad_norm": 1.372103214263916, "learning_rate": 2.7908195982557785e-08, "loss": 0.648, "step": 16726 }, { "epoch": 0.9770443925233645, "grad_norm": 0.9769640564918518, "learning_rate": 2.7767132879752413e-08, "loss": 0.6315, "step": 16727 }, { "epoch": 0.9771028037383177, "grad_norm": 0.8981100916862488, "learning_rate": 2.762642668971971e-08, "loss": 0.7337, "step": 16728 }, { "epoch": 0.977161214953271, "grad_norm": 0.8480190634727478, "learning_rate": 2.748607741749454e-08, "loss": 0.657, "step": 16729 }, { "epoch": 0.9772196261682243, "grad_norm": 1.133623719215393, "learning_rate": 2.7346085068098437e-08, "loss": 0.8175, "step": 16730 }, { "epoch": 0.9772780373831775, "grad_norm": 1.519742727279663, "learning_rate": 2.7206449646544063e-08, "loss": 0.6607, "step": 16731 }, { "epoch": 0.9773364485981308, "grad_norm": 1.0940325260162354, "learning_rate": 2.706717115782853e-08, "loss": 1.0482, "step": 16732 }, { "epoch": 0.9773948598130842, "grad_norm": 1.00478196144104, "learning_rate": 2.692824960693452e-08, "loss": 0.6798, "step": 16733 }, { "epoch": 0.9774532710280374, "grad_norm": 1.1707661151885986, "learning_rate": 2.678968499883694e-08, "loss": 0.6791, "step": 16734 }, { "epoch": 0.9775116822429907, "grad_norm": 0.8076099753379822, "learning_rate": 2.6651477338494047e-08, "loss": 0.7588, "step": 16735 }, { "epoch": 0.9775700934579439, "grad_norm": 0.9899171590805054, "learning_rate": 2.6513626630852995e-08, "loss": 0.7832, "step": 16736 }, { "epoch": 0.9776285046728972, "grad_norm": 1.7927947044372559, "learning_rate": 2.6376132880846506e-08, "loss": 0.9491, "step": 16737 }, { "epoch": 0.9776869158878505, "grad_norm": 1.5631903409957886, "learning_rate": 2.6238996093395087e-08, "loss": 0.7288, "step": 16738 }, { "epoch": 0.9777453271028037, "grad_norm": 1.5968167781829834, "learning_rate": 2.6102216273409252e-08, "loss": 0.7594, "step": 16739 }, { "epoch": 0.977803738317757, "grad_norm": 1.063804268836975, "learning_rate": 2.596579342578176e-08, "loss": 0.6864, "step": 16740 }, { "epoch": 0.9778621495327103, "grad_norm": 0.84610915184021, "learning_rate": 2.5829727555397587e-08, "loss": 0.6638, "step": 16741 }, { "epoch": 0.9779205607476635, "grad_norm": 0.9364253878593445, "learning_rate": 2.5694018667125066e-08, "loss": 0.6018, "step": 16742 }, { "epoch": 0.9779789719626168, "grad_norm": 0.9377590417861938, "learning_rate": 2.5558666765822525e-08, "loss": 0.618, "step": 16743 }, { "epoch": 0.97803738317757, "grad_norm": 0.9314764738082886, "learning_rate": 2.5423671856332764e-08, "loss": 0.8435, "step": 16744 }, { "epoch": 0.9780957943925234, "grad_norm": 1.0367534160614014, "learning_rate": 2.5289033943488582e-08, "loss": 0.6471, "step": 16745 }, { "epoch": 0.9781542056074767, "grad_norm": 1.4281013011932373, "learning_rate": 2.515475303210835e-08, "loss": 0.735, "step": 16746 }, { "epoch": 0.9782126168224299, "grad_norm": 1.0656862258911133, "learning_rate": 2.5020829126998215e-08, "loss": 0.8428, "step": 16747 }, { "epoch": 0.9782710280373832, "grad_norm": 0.9674203395843506, "learning_rate": 2.4887262232951015e-08, "loss": 0.8392, "step": 16748 }, { "epoch": 0.9783294392523364, "grad_norm": 0.9496752619743347, "learning_rate": 2.4754052354747372e-08, "loss": 0.9157, "step": 16749 }, { "epoch": 0.9783878504672897, "grad_norm": 1.0126553773880005, "learning_rate": 2.462119949715569e-08, "loss": 0.7641, "step": 16750 }, { "epoch": 0.978446261682243, "grad_norm": 0.945097804069519, "learning_rate": 2.4488703664929946e-08, "loss": 0.6736, "step": 16751 }, { "epoch": 0.9785046728971962, "grad_norm": 0.8479959964752197, "learning_rate": 2.4356564862811905e-08, "loss": 0.6393, "step": 16752 }, { "epoch": 0.9785630841121495, "grad_norm": 1.0048454999923706, "learning_rate": 2.4224783095532224e-08, "loss": 0.8845, "step": 16753 }, { "epoch": 0.9786214953271029, "grad_norm": 0.9319868683815002, "learning_rate": 2.4093358367807128e-08, "loss": 0.7229, "step": 16754 }, { "epoch": 0.978679906542056, "grad_norm": 1.181880235671997, "learning_rate": 2.396229068433842e-08, "loss": 0.702, "step": 16755 }, { "epoch": 0.9787383177570094, "grad_norm": 1.0641720294952393, "learning_rate": 2.3831580049820112e-08, "loss": 0.818, "step": 16756 }, { "epoch": 0.9787967289719626, "grad_norm": 1.0431478023529053, "learning_rate": 2.3701226468928472e-08, "loss": 0.6664, "step": 16757 }, { "epoch": 0.9788551401869159, "grad_norm": 1.3668341636657715, "learning_rate": 2.3571229946329766e-08, "loss": 0.7221, "step": 16758 }, { "epoch": 0.9789135514018692, "grad_norm": 1.556179404258728, "learning_rate": 2.3441590486676935e-08, "loss": 0.7413, "step": 16759 }, { "epoch": 0.9789719626168224, "grad_norm": 0.9958625435829163, "learning_rate": 2.3312308094607382e-08, "loss": 0.891, "step": 16760 }, { "epoch": 0.9790303738317757, "grad_norm": 1.1711100339889526, "learning_rate": 2.318338277475185e-08, "loss": 0.6707, "step": 16761 }, { "epoch": 0.979088785046729, "grad_norm": 1.0180634260177612, "learning_rate": 2.3054814531722204e-08, "loss": 0.8381, "step": 16762 }, { "epoch": 0.9791471962616822, "grad_norm": 1.367998719215393, "learning_rate": 2.2926603370121426e-08, "loss": 0.8403, "step": 16763 }, { "epoch": 0.9792056074766355, "grad_norm": 0.8927919864654541, "learning_rate": 2.279874929453696e-08, "loss": 0.7759, "step": 16764 }, { "epoch": 0.9792640186915887, "grad_norm": 0.7783681154251099, "learning_rate": 2.2671252309545146e-08, "loss": 0.555, "step": 16765 }, { "epoch": 0.9793224299065421, "grad_norm": 0.9924765229225159, "learning_rate": 2.2544112419710105e-08, "loss": 0.7134, "step": 16766 }, { "epoch": 0.9793808411214954, "grad_norm": 0.8506832122802734, "learning_rate": 2.241732962958154e-08, "loss": 0.6697, "step": 16767 }, { "epoch": 0.9794392523364486, "grad_norm": 1.0005383491516113, "learning_rate": 2.229090394369693e-08, "loss": 0.6924, "step": 16768 }, { "epoch": 0.9794976635514019, "grad_norm": 0.7983598113059998, "learning_rate": 2.216483536658154e-08, "loss": 0.6885, "step": 16769 }, { "epoch": 0.9795560747663551, "grad_norm": 1.0546520948410034, "learning_rate": 2.2039123902746208e-08, "loss": 0.5832, "step": 16770 }, { "epoch": 0.9796144859813084, "grad_norm": 1.156821846961975, "learning_rate": 2.1913769556691777e-08, "loss": 0.7913, "step": 16771 }, { "epoch": 0.9796728971962617, "grad_norm": 0.8826673626899719, "learning_rate": 2.1788772332904662e-08, "loss": 0.6591, "step": 16772 }, { "epoch": 0.9797313084112149, "grad_norm": 2.196014642715454, "learning_rate": 2.166413223585795e-08, "loss": 0.7481, "step": 16773 }, { "epoch": 0.9797897196261682, "grad_norm": 0.9915060997009277, "learning_rate": 2.1539849270013624e-08, "loss": 0.7024, "step": 16774 }, { "epoch": 0.9798481308411215, "grad_norm": 0.8440448641777039, "learning_rate": 2.1415923439818132e-08, "loss": 0.7253, "step": 16775 }, { "epoch": 0.9799065420560747, "grad_norm": 0.9320748448371887, "learning_rate": 2.1292354749707922e-08, "loss": 0.7955, "step": 16776 }, { "epoch": 0.9799649532710281, "grad_norm": 1.0347919464111328, "learning_rate": 2.1169143204105015e-08, "loss": 0.701, "step": 16777 }, { "epoch": 0.9800233644859813, "grad_norm": 0.7696197628974915, "learning_rate": 2.1046288807420324e-08, "loss": 0.7517, "step": 16778 }, { "epoch": 0.9800817757009346, "grad_norm": 1.2301334142684937, "learning_rate": 2.0923791564050333e-08, "loss": 0.7633, "step": 16779 }, { "epoch": 0.9801401869158879, "grad_norm": 1.3357758522033691, "learning_rate": 2.0801651478379315e-08, "loss": 0.7871, "step": 16780 }, { "epoch": 0.9801985981308411, "grad_norm": 0.9533833265304565, "learning_rate": 2.0679868554778216e-08, "loss": 0.8146, "step": 16781 }, { "epoch": 0.9802570093457944, "grad_norm": 2.516291618347168, "learning_rate": 2.0558442797605772e-08, "loss": 0.7984, "step": 16782 }, { "epoch": 0.9803154205607477, "grad_norm": 0.9435281753540039, "learning_rate": 2.0437374211209614e-08, "loss": 0.7851, "step": 16783 }, { "epoch": 0.9803738317757009, "grad_norm": 0.9645581841468811, "learning_rate": 2.0316662799920727e-08, "loss": 0.5535, "step": 16784 }, { "epoch": 0.9804322429906542, "grad_norm": 1.0058352947235107, "learning_rate": 2.0196308568060098e-08, "loss": 0.5974, "step": 16785 }, { "epoch": 0.9804906542056074, "grad_norm": 0.9536961317062378, "learning_rate": 2.0076311519935386e-08, "loss": 0.5752, "step": 16786 }, { "epoch": 0.9805490654205608, "grad_norm": 1.1959809064865112, "learning_rate": 1.995667165984094e-08, "loss": 0.7597, "step": 16787 }, { "epoch": 0.9806074766355141, "grad_norm": 0.9428026080131531, "learning_rate": 1.983738899206e-08, "loss": 0.6053, "step": 16788 }, { "epoch": 0.9806658878504673, "grad_norm": 1.0722932815551758, "learning_rate": 1.9718463520861375e-08, "loss": 0.7884, "step": 16789 }, { "epoch": 0.9807242990654206, "grad_norm": 1.1194593906402588, "learning_rate": 1.9599895250500544e-08, "loss": 0.8073, "step": 16790 }, { "epoch": 0.9807827102803738, "grad_norm": 1.088313102722168, "learning_rate": 1.9481684185221893e-08, "loss": 0.7496, "step": 16791 }, { "epoch": 0.9808411214953271, "grad_norm": 1.157806634902954, "learning_rate": 1.9363830329255374e-08, "loss": 0.9448, "step": 16792 }, { "epoch": 0.9808995327102804, "grad_norm": 0.9213449954986572, "learning_rate": 1.9246333686819828e-08, "loss": 0.5982, "step": 16793 }, { "epoch": 0.9809579439252336, "grad_norm": 1.2466875314712524, "learning_rate": 1.9129194262121897e-08, "loss": 0.7674, "step": 16794 }, { "epoch": 0.9810163551401869, "grad_norm": 1.254253625869751, "learning_rate": 1.901241205935156e-08, "loss": 0.8142, "step": 16795 }, { "epoch": 0.9810747663551402, "grad_norm": 1.1074148416519165, "learning_rate": 1.8895987082689916e-08, "loss": 0.7204, "step": 16796 }, { "epoch": 0.9811331775700934, "grad_norm": 1.106946587562561, "learning_rate": 1.877991933630252e-08, "loss": 0.8853, "step": 16797 }, { "epoch": 0.9811915887850468, "grad_norm": 0.8181654214859009, "learning_rate": 1.8664208824346054e-08, "loss": 0.6201, "step": 16798 }, { "epoch": 0.98125, "grad_norm": 0.891864001750946, "learning_rate": 1.8548855550959423e-08, "loss": 0.5972, "step": 16799 }, { "epoch": 0.9813084112149533, "grad_norm": 1.0320459604263306, "learning_rate": 1.8433859520272656e-08, "loss": 0.7829, "step": 16800 }, { "epoch": 0.9813668224299066, "grad_norm": 1.0932947397232056, "learning_rate": 1.8319220736401356e-08, "loss": 0.8809, "step": 16801 }, { "epoch": 0.9814252336448598, "grad_norm": 0.897712230682373, "learning_rate": 1.8204939203447792e-08, "loss": 0.6254, "step": 16802 }, { "epoch": 0.9814836448598131, "grad_norm": 1.06667160987854, "learning_rate": 1.8091014925503136e-08, "loss": 0.7619, "step": 16803 }, { "epoch": 0.9815420560747663, "grad_norm": 1.355875849723816, "learning_rate": 1.797744790664302e-08, "loss": 0.8609, "step": 16804 }, { "epoch": 0.9816004672897196, "grad_norm": 0.9262607097625732, "learning_rate": 1.7864238150934187e-08, "loss": 0.6285, "step": 16805 }, { "epoch": 0.9816588785046729, "grad_norm": 1.0406854152679443, "learning_rate": 1.7751385662427845e-08, "loss": 0.8171, "step": 16806 }, { "epoch": 0.9817172897196261, "grad_norm": 1.1009043455123901, "learning_rate": 1.763889044516298e-08, "loss": 0.8575, "step": 16807 }, { "epoch": 0.9817757009345794, "grad_norm": 6.210715293884277, "learning_rate": 1.7526752503165267e-08, "loss": 0.688, "step": 16808 }, { "epoch": 0.9818341121495328, "grad_norm": 0.8154770135879517, "learning_rate": 1.741497184044927e-08, "loss": 0.5978, "step": 16809 }, { "epoch": 0.981892523364486, "grad_norm": 1.1009526252746582, "learning_rate": 1.730354846101401e-08, "loss": 0.891, "step": 16810 }, { "epoch": 0.9819509345794393, "grad_norm": 1.0582164525985718, "learning_rate": 1.7192482368849626e-08, "loss": 0.8236, "step": 16811 }, { "epoch": 0.9820093457943925, "grad_norm": 1.0046175718307495, "learning_rate": 1.7081773567929616e-08, "loss": 0.7413, "step": 16812 }, { "epoch": 0.9820677570093458, "grad_norm": 1.2136949300765991, "learning_rate": 1.6971422062217468e-08, "loss": 0.8017, "step": 16813 }, { "epoch": 0.9821261682242991, "grad_norm": 1.0411659479141235, "learning_rate": 1.6861427855661138e-08, "loss": 0.8502, "step": 16814 }, { "epoch": 0.9821845794392523, "grad_norm": 1.1062560081481934, "learning_rate": 1.675179095219859e-08, "loss": 0.9369, "step": 16815 }, { "epoch": 0.9822429906542056, "grad_norm": 1.062013864517212, "learning_rate": 1.6642511355754455e-08, "loss": 0.6711, "step": 16816 }, { "epoch": 0.9823014018691589, "grad_norm": 0.9573757648468018, "learning_rate": 1.653358907023783e-08, "loss": 0.665, "step": 16817 }, { "epoch": 0.9823598130841121, "grad_norm": 1.1271342039108276, "learning_rate": 1.6425024099548938e-08, "loss": 0.8499, "step": 16818 }, { "epoch": 0.9824182242990654, "grad_norm": 1.113617181777954, "learning_rate": 1.6316816447572435e-08, "loss": 0.8629, "step": 16819 }, { "epoch": 0.9824766355140186, "grad_norm": 1.4493244886398315, "learning_rate": 1.62089661181819e-08, "loss": 0.7663, "step": 16820 }, { "epoch": 0.982535046728972, "grad_norm": 1.8399993181228638, "learning_rate": 1.6101473115236465e-08, "loss": 0.6783, "step": 16821 }, { "epoch": 0.9825934579439253, "grad_norm": 0.9212207794189453, "learning_rate": 1.5994337442584164e-08, "loss": 0.8342, "step": 16822 }, { "epoch": 0.9826518691588785, "grad_norm": 0.9355335235595703, "learning_rate": 1.588755910405859e-08, "loss": 0.7004, "step": 16823 }, { "epoch": 0.9827102803738318, "grad_norm": 1.0087306499481201, "learning_rate": 1.5781138103482252e-08, "loss": 0.6917, "step": 16824 }, { "epoch": 0.982768691588785, "grad_norm": 1.1885902881622314, "learning_rate": 1.567507444466432e-08, "loss": 0.835, "step": 16825 }, { "epoch": 0.9828271028037383, "grad_norm": 0.9157543182373047, "learning_rate": 1.5569368131399533e-08, "loss": 0.701, "step": 16826 }, { "epoch": 0.9828855140186916, "grad_norm": 1.299084186553955, "learning_rate": 1.5464019167472643e-08, "loss": 0.8308, "step": 16827 }, { "epoch": 0.9829439252336448, "grad_norm": 0.9493553638458252, "learning_rate": 1.535902755665286e-08, "loss": 0.5888, "step": 16828 }, { "epoch": 0.9830023364485981, "grad_norm": 0.9021158218383789, "learning_rate": 1.5254393302699398e-08, "loss": 0.7469, "step": 16829 }, { "epoch": 0.9830607476635514, "grad_norm": 0.9974688291549683, "learning_rate": 1.515011640935482e-08, "loss": 0.625, "step": 16830 }, { "epoch": 0.9831191588785047, "grad_norm": 1.5136499404907227, "learning_rate": 1.5046196880353914e-08, "loss": 0.8232, "step": 16831 }, { "epoch": 0.983177570093458, "grad_norm": 1.031072974205017, "learning_rate": 1.4942634719414817e-08, "loss": 0.7596, "step": 16832 }, { "epoch": 0.9832359813084112, "grad_norm": 0.8062739372253418, "learning_rate": 1.4839429930243455e-08, "loss": 0.5976, "step": 16833 }, { "epoch": 0.9832943925233645, "grad_norm": 0.8487931489944458, "learning_rate": 1.4736582516534648e-08, "loss": 0.7149, "step": 16834 }, { "epoch": 0.9833528037383178, "grad_norm": 1.176181435585022, "learning_rate": 1.4634092481968786e-08, "loss": 0.7892, "step": 16835 }, { "epoch": 0.983411214953271, "grad_norm": 0.9650798439979553, "learning_rate": 1.4531959830214048e-08, "loss": 0.7497, "step": 16836 }, { "epoch": 0.9834696261682243, "grad_norm": 1.1027870178222656, "learning_rate": 1.4430184564926397e-08, "loss": 0.7747, "step": 16837 }, { "epoch": 0.9835280373831776, "grad_norm": 1.046033501625061, "learning_rate": 1.4328766689748475e-08, "loss": 0.6272, "step": 16838 }, { "epoch": 0.9835864485981308, "grad_norm": 0.8353573679924011, "learning_rate": 1.4227706208309599e-08, "loss": 0.5887, "step": 16839 }, { "epoch": 0.9836448598130841, "grad_norm": 1.0517866611480713, "learning_rate": 1.4127003124225768e-08, "loss": 0.648, "step": 16840 }, { "epoch": 0.9837032710280373, "grad_norm": 1.0703208446502686, "learning_rate": 1.4026657441104097e-08, "loss": 0.6931, "step": 16841 }, { "epoch": 0.9837616822429907, "grad_norm": 1.1219156980514526, "learning_rate": 1.3926669162532824e-08, "loss": 0.5742, "step": 16842 }, { "epoch": 0.983820093457944, "grad_norm": 1.0154119729995728, "learning_rate": 1.382703829209242e-08, "loss": 0.6379, "step": 16843 }, { "epoch": 0.9838785046728972, "grad_norm": 1.6973263025283813, "learning_rate": 1.3727764833348923e-08, "loss": 0.837, "step": 16844 }, { "epoch": 0.9839369158878505, "grad_norm": 0.9566998481750488, "learning_rate": 1.3628848789853932e-08, "loss": 0.6816, "step": 16845 }, { "epoch": 0.9839953271028037, "grad_norm": 1.1661008596420288, "learning_rate": 1.3530290165149062e-08, "loss": 0.7695, "step": 16846 }, { "epoch": 0.984053738317757, "grad_norm": 1.1441360712051392, "learning_rate": 1.3432088962761491e-08, "loss": 0.9257, "step": 16847 }, { "epoch": 0.9841121495327103, "grad_norm": 0.9743410348892212, "learning_rate": 1.3334245186206185e-08, "loss": 0.7115, "step": 16848 }, { "epoch": 0.9841705607476635, "grad_norm": 1.0035037994384766, "learning_rate": 1.3236758838983676e-08, "loss": 0.7929, "step": 16849 }, { "epoch": 0.9842289719626168, "grad_norm": 0.8540350794792175, "learning_rate": 1.3139629924584508e-08, "loss": 0.7178, "step": 16850 }, { "epoch": 0.9842873831775701, "grad_norm": 0.9691110849380493, "learning_rate": 1.3042858446483675e-08, "loss": 0.6527, "step": 16851 }, { "epoch": 0.9843457943925233, "grad_norm": 1.1720573902130127, "learning_rate": 1.2946444408146185e-08, "loss": 0.7554, "step": 16852 }, { "epoch": 0.9844042056074767, "grad_norm": 1.0745632648468018, "learning_rate": 1.2850387813022614e-08, "loss": 0.6477, "step": 16853 }, { "epoch": 0.9844626168224299, "grad_norm": 0.9872539043426514, "learning_rate": 1.2754688664549098e-08, "loss": 0.6107, "step": 16854 }, { "epoch": 0.9845210280373832, "grad_norm": 1.049479603767395, "learning_rate": 1.2659346966152897e-08, "loss": 0.849, "step": 16855 }, { "epoch": 0.9845794392523365, "grad_norm": 0.9069527983665466, "learning_rate": 1.2564362721245726e-08, "loss": 0.6664, "step": 16856 }, { "epoch": 0.9846378504672897, "grad_norm": 0.9268089532852173, "learning_rate": 1.246973593322598e-08, "loss": 0.6558, "step": 16857 }, { "epoch": 0.984696261682243, "grad_norm": 0.9410732984542847, "learning_rate": 1.2375466605482057e-08, "loss": 0.6228, "step": 16858 }, { "epoch": 0.9847546728971963, "grad_norm": 1.109079360961914, "learning_rate": 1.2281554741386815e-08, "loss": 0.6418, "step": 16859 }, { "epoch": 0.9848130841121495, "grad_norm": 1.1065338850021362, "learning_rate": 1.2188000344300898e-08, "loss": 0.7197, "step": 16860 }, { "epoch": 0.9848714953271028, "grad_norm": 0.9673901200294495, "learning_rate": 1.2094803417574963e-08, "loss": 0.8475, "step": 16861 }, { "epoch": 0.984929906542056, "grad_norm": 0.8149331212043762, "learning_rate": 1.2001963964543006e-08, "loss": 0.7428, "step": 16862 }, { "epoch": 0.9849883177570093, "grad_norm": 0.9693228602409363, "learning_rate": 1.1909481988527927e-08, "loss": 0.7369, "step": 16863 }, { "epoch": 0.9850467289719627, "grad_norm": 1.3228602409362793, "learning_rate": 1.1817357492839298e-08, "loss": 0.8075, "step": 16864 }, { "epoch": 0.9851051401869159, "grad_norm": 1.0568197965621948, "learning_rate": 1.1725590480774485e-08, "loss": 0.7802, "step": 16865 }, { "epoch": 0.9851635514018692, "grad_norm": 1.0164135694503784, "learning_rate": 1.1634180955618635e-08, "loss": 0.7005, "step": 16866 }, { "epoch": 0.9852219626168224, "grad_norm": 1.1915034055709839, "learning_rate": 1.1543128920643575e-08, "loss": 0.7148, "step": 16867 }, { "epoch": 0.9852803738317757, "grad_norm": 0.9975236058235168, "learning_rate": 1.1452434379106703e-08, "loss": 0.7037, "step": 16868 }, { "epoch": 0.985338785046729, "grad_norm": 0.9767571091651917, "learning_rate": 1.1362097334255418e-08, "loss": 0.7563, "step": 16869 }, { "epoch": 0.9853971962616822, "grad_norm": 1.1388332843780518, "learning_rate": 1.1272117789321579e-08, "loss": 0.8768, "step": 16870 }, { "epoch": 0.9854556074766355, "grad_norm": 1.2335598468780518, "learning_rate": 1.1182495747527056e-08, "loss": 0.7509, "step": 16871 }, { "epoch": 0.9855140186915888, "grad_norm": 1.0340464115142822, "learning_rate": 1.109323121207817e-08, "loss": 0.7481, "step": 16872 }, { "epoch": 0.985572429906542, "grad_norm": 1.579132318496704, "learning_rate": 1.1004324186170145e-08, "loss": 0.7694, "step": 16873 }, { "epoch": 0.9856308411214953, "grad_norm": 0.9648385047912598, "learning_rate": 1.0915774672985991e-08, "loss": 0.6333, "step": 16874 }, { "epoch": 0.9856892523364486, "grad_norm": 0.9855012893676758, "learning_rate": 1.082758267569428e-08, "loss": 0.677, "step": 16875 }, { "epoch": 0.9857476635514019, "grad_norm": 1.0359313488006592, "learning_rate": 1.0739748197451383e-08, "loss": 0.8086, "step": 16876 }, { "epoch": 0.9858060747663552, "grad_norm": 0.9559612274169922, "learning_rate": 1.0652271241400336e-08, "loss": 0.6412, "step": 16877 }, { "epoch": 0.9858644859813084, "grad_norm": 1.2450486421585083, "learning_rate": 1.056515181067308e-08, "loss": 0.6909, "step": 16878 }, { "epoch": 0.9859228971962617, "grad_norm": 1.0726100206375122, "learning_rate": 1.0478389908387122e-08, "loss": 0.7184, "step": 16879 }, { "epoch": 0.985981308411215, "grad_norm": 1.162131428718567, "learning_rate": 1.0391985537647752e-08, "loss": 0.8118, "step": 16880 }, { "epoch": 0.9860397196261682, "grad_norm": 4.033780097961426, "learning_rate": 1.0305938701548057e-08, "loss": 0.6788, "step": 16881 }, { "epoch": 0.9860981308411215, "grad_norm": 0.8826360106468201, "learning_rate": 1.0220249403166682e-08, "loss": 0.6906, "step": 16882 }, { "epoch": 0.9861565420560747, "grad_norm": 0.8069177269935608, "learning_rate": 1.0134917645570064e-08, "loss": 0.725, "step": 16883 }, { "epoch": 0.986214953271028, "grad_norm": 0.8451555967330933, "learning_rate": 1.0049943431814646e-08, "loss": 0.605, "step": 16884 }, { "epoch": 0.9862733644859814, "grad_norm": 1.2150098085403442, "learning_rate": 9.96532676494022e-09, "loss": 0.8262, "step": 16885 }, { "epoch": 0.9863317757009346, "grad_norm": 1.0626753568649292, "learning_rate": 9.881067647974362e-09, "loss": 0.7362, "step": 16886 }, { "epoch": 0.9863901869158879, "grad_norm": 1.189378023147583, "learning_rate": 9.797166083934662e-09, "loss": 0.6632, "step": 16887 }, { "epoch": 0.9864485981308411, "grad_norm": 1.0089510679244995, "learning_rate": 9.713622075822049e-09, "loss": 0.7099, "step": 16888 }, { "epoch": 0.9865070093457944, "grad_norm": 0.8800655007362366, "learning_rate": 9.630435626628576e-09, "loss": 0.568, "step": 16889 }, { "epoch": 0.9865654205607477, "grad_norm": 1.1607049703598022, "learning_rate": 9.54760673932964e-09, "loss": 0.9846, "step": 16890 }, { "epoch": 0.9866238317757009, "grad_norm": 1.0633296966552734, "learning_rate": 9.465135416891757e-09, "loss": 0.869, "step": 16891 }, { "epoch": 0.9866822429906542, "grad_norm": 1.0742218494415283, "learning_rate": 9.38302166226479e-09, "loss": 0.7168, "step": 16892 }, { "epoch": 0.9867406542056075, "grad_norm": 1.0698779821395874, "learning_rate": 9.30126547838861e-09, "loss": 0.6732, "step": 16893 }, { "epoch": 0.9867990654205607, "grad_norm": 0.9815187454223633, "learning_rate": 9.219866868189763e-09, "loss": 0.8157, "step": 16894 }, { "epoch": 0.986857476635514, "grad_norm": 0.9996920228004456, "learning_rate": 9.138825834580367e-09, "loss": 0.6416, "step": 16895 }, { "epoch": 0.9869158878504672, "grad_norm": 1.1002689599990845, "learning_rate": 9.058142380461433e-09, "loss": 0.7835, "step": 16896 }, { "epoch": 0.9869742990654206, "grad_norm": 1.156554937362671, "learning_rate": 8.97781650872176e-09, "loss": 0.8189, "step": 16897 }, { "epoch": 0.9870327102803739, "grad_norm": 1.0510834455490112, "learning_rate": 8.897848222234606e-09, "loss": 0.7528, "step": 16898 }, { "epoch": 0.9870911214953271, "grad_norm": 1.1352216005325317, "learning_rate": 8.818237523862127e-09, "loss": 0.8678, "step": 16899 }, { "epoch": 0.9871495327102804, "grad_norm": 1.1529550552368164, "learning_rate": 8.738984416455377e-09, "loss": 0.812, "step": 16900 }, { "epoch": 0.9872079439252337, "grad_norm": 1.729652762413025, "learning_rate": 8.660088902848752e-09, "loss": 0.8036, "step": 16901 }, { "epoch": 0.9872663551401869, "grad_norm": 1.8719149827957153, "learning_rate": 8.581550985867771e-09, "loss": 0.9737, "step": 16902 }, { "epoch": 0.9873247663551402, "grad_norm": 1.1165117025375366, "learning_rate": 8.503370668321298e-09, "loss": 0.7001, "step": 16903 }, { "epoch": 0.9873831775700934, "grad_norm": 1.1518800258636475, "learning_rate": 8.425547953009317e-09, "loss": 0.7657, "step": 16904 }, { "epoch": 0.9874415887850467, "grad_norm": 1.2486279010772705, "learning_rate": 8.348082842717375e-09, "loss": 0.6618, "step": 16905 }, { "epoch": 0.9875, "grad_norm": 0.9559652805328369, "learning_rate": 8.270975340216592e-09, "loss": 0.9122, "step": 16906 }, { "epoch": 0.9875584112149532, "grad_norm": 1.0073752403259277, "learning_rate": 8.19422544826698e-09, "loss": 0.7166, "step": 16907 }, { "epoch": 0.9876168224299066, "grad_norm": 1.1602622270584106, "learning_rate": 8.117833169616341e-09, "loss": 0.8554, "step": 16908 }, { "epoch": 0.9876752336448598, "grad_norm": 0.9431392550468445, "learning_rate": 8.041798506998044e-09, "loss": 0.748, "step": 16909 }, { "epoch": 0.9877336448598131, "grad_norm": 0.9540731906890869, "learning_rate": 7.966121463134357e-09, "loss": 0.7159, "step": 16910 }, { "epoch": 0.9877920560747664, "grad_norm": 0.9880461692810059, "learning_rate": 7.890802040732004e-09, "loss": 0.6993, "step": 16911 }, { "epoch": 0.9878504672897196, "grad_norm": 1.0146288871765137, "learning_rate": 7.815840242487716e-09, "loss": 0.8012, "step": 16912 }, { "epoch": 0.9879088785046729, "grad_norm": 1.314103603363037, "learning_rate": 7.741236071084901e-09, "loss": 0.7715, "step": 16913 }, { "epoch": 0.9879672897196262, "grad_norm": 0.9325464963912964, "learning_rate": 7.666989529193647e-09, "loss": 0.5897, "step": 16914 }, { "epoch": 0.9880257009345794, "grad_norm": 0.9788021445274353, "learning_rate": 7.593100619470716e-09, "loss": 0.7865, "step": 16915 }, { "epoch": 0.9880841121495327, "grad_norm": 1.372725248336792, "learning_rate": 7.519569344560662e-09, "loss": 0.74, "step": 16916 }, { "epoch": 0.9881425233644859, "grad_norm": 1.3651353120803833, "learning_rate": 7.446395707094711e-09, "loss": 0.9399, "step": 16917 }, { "epoch": 0.9882009345794392, "grad_norm": 1.315297245979309, "learning_rate": 7.3735797096929905e-09, "loss": 0.6596, "step": 16918 }, { "epoch": 0.9882593457943926, "grad_norm": 1.0322543382644653, "learning_rate": 7.301121354962304e-09, "loss": 0.7776, "step": 16919 }, { "epoch": 0.9883177570093458, "grad_norm": 1.0762165784835815, "learning_rate": 7.229020645493912e-09, "loss": 0.6585, "step": 16920 }, { "epoch": 0.9883761682242991, "grad_norm": 0.942630410194397, "learning_rate": 7.157277583869082e-09, "loss": 0.5868, "step": 16921 }, { "epoch": 0.9884345794392523, "grad_norm": 0.9381847977638245, "learning_rate": 7.0858921726557616e-09, "loss": 0.7826, "step": 16922 }, { "epoch": 0.9884929906542056, "grad_norm": 1.2513656616210938, "learning_rate": 7.014864414408573e-09, "loss": 0.8361, "step": 16923 }, { "epoch": 0.9885514018691589, "grad_norm": 0.9258195757865906, "learning_rate": 6.944194311669928e-09, "loss": 0.6918, "step": 16924 }, { "epoch": 0.9886098130841121, "grad_norm": 1.0342485904693604, "learning_rate": 6.873881866970023e-09, "loss": 0.8385, "step": 16925 }, { "epoch": 0.9886682242990654, "grad_norm": 1.1429572105407715, "learning_rate": 6.8039270828235135e-09, "loss": 0.8267, "step": 16926 }, { "epoch": 0.9887266355140187, "grad_norm": 1.3997358083724976, "learning_rate": 6.734329961735064e-09, "loss": 0.7667, "step": 16927 }, { "epoch": 0.9887850467289719, "grad_norm": 0.8902899622917175, "learning_rate": 6.665090506196015e-09, "loss": 0.7575, "step": 16928 }, { "epoch": 0.9888434579439253, "grad_norm": 1.5475794076919556, "learning_rate": 6.5962087186843825e-09, "loss": 0.797, "step": 16929 }, { "epoch": 0.9889018691588785, "grad_norm": 1.0668132305145264, "learning_rate": 6.527684601664863e-09, "loss": 0.755, "step": 16930 }, { "epoch": 0.9889602803738318, "grad_norm": 0.8827822804450989, "learning_rate": 6.4595181575910496e-09, "loss": 0.854, "step": 16931 }, { "epoch": 0.9890186915887851, "grad_norm": 1.0090620517730713, "learning_rate": 6.391709388900991e-09, "loss": 0.6875, "step": 16932 }, { "epoch": 0.9890771028037383, "grad_norm": 1.0314278602600098, "learning_rate": 6.324258298022745e-09, "loss": 0.8613, "step": 16933 }, { "epoch": 0.9891355140186916, "grad_norm": 0.8555394411087036, "learning_rate": 6.257164887371048e-09, "loss": 0.6556, "step": 16934 }, { "epoch": 0.9891939252336449, "grad_norm": 0.8446992039680481, "learning_rate": 6.190429159346201e-09, "loss": 0.6849, "step": 16935 }, { "epoch": 0.9892523364485981, "grad_norm": 1.209008812904358, "learning_rate": 6.124051116336294e-09, "loss": 0.8515, "step": 16936 }, { "epoch": 0.9893107476635514, "grad_norm": 1.187135934829712, "learning_rate": 6.058030760718314e-09, "loss": 0.8147, "step": 16937 }, { "epoch": 0.9893691588785046, "grad_norm": 0.8667489886283875, "learning_rate": 5.9923680948537064e-09, "loss": 0.7161, "step": 16938 }, { "epoch": 0.9894275700934579, "grad_norm": 1.1830084323883057, "learning_rate": 5.927063121093923e-09, "loss": 0.8228, "step": 16939 }, { "epoch": 0.9894859813084113, "grad_norm": 1.0679835081100464, "learning_rate": 5.862115841775984e-09, "loss": 0.8601, "step": 16940 }, { "epoch": 0.9895443925233645, "grad_norm": 0.9913726449012756, "learning_rate": 5.7975262592246954e-09, "loss": 0.7951, "step": 16941 }, { "epoch": 0.9896028037383178, "grad_norm": 1.239965796470642, "learning_rate": 5.733294375750431e-09, "loss": 0.9763, "step": 16942 }, { "epoch": 0.989661214953271, "grad_norm": 0.929278552532196, "learning_rate": 5.669420193653574e-09, "loss": 0.7653, "step": 16943 }, { "epoch": 0.9897196261682243, "grad_norm": 1.0002186298370361, "learning_rate": 5.605903715218963e-09, "loss": 0.6185, "step": 16944 }, { "epoch": 0.9897780373831776, "grad_norm": 1.1388558149337769, "learning_rate": 5.542744942720335e-09, "loss": 0.8291, "step": 16945 }, { "epoch": 0.9898364485981308, "grad_norm": 0.7771191000938416, "learning_rate": 5.479943878418104e-09, "loss": 0.5894, "step": 16946 }, { "epoch": 0.9898948598130841, "grad_norm": 1.3604867458343506, "learning_rate": 5.417500524561581e-09, "loss": 0.897, "step": 16947 }, { "epoch": 0.9899532710280374, "grad_norm": 0.9857936501502991, "learning_rate": 5.355414883383425e-09, "loss": 0.7399, "step": 16948 }, { "epoch": 0.9900116822429906, "grad_norm": 1.5778435468673706, "learning_rate": 5.293686957106303e-09, "loss": 0.8791, "step": 16949 }, { "epoch": 0.990070093457944, "grad_norm": 1.2445122003555298, "learning_rate": 5.232316747940669e-09, "loss": 0.7779, "step": 16950 }, { "epoch": 0.9901285046728971, "grad_norm": 1.2517529726028442, "learning_rate": 5.171304258081433e-09, "loss": 0.7772, "step": 16951 }, { "epoch": 0.9901869158878505, "grad_norm": 0.8774611949920654, "learning_rate": 5.1106494897124045e-09, "loss": 0.697, "step": 16952 }, { "epoch": 0.9902453271028038, "grad_norm": 0.9399831295013428, "learning_rate": 5.05035244500629e-09, "loss": 0.7345, "step": 16953 }, { "epoch": 0.990303738317757, "grad_norm": 1.2777425050735474, "learning_rate": 4.990413126119142e-09, "loss": 0.744, "step": 16954 }, { "epoch": 0.9903621495327103, "grad_norm": 0.9109071493148804, "learning_rate": 4.930831535197023e-09, "loss": 0.7846, "step": 16955 }, { "epoch": 0.9904205607476636, "grad_norm": 1.241400122642517, "learning_rate": 4.871607674371559e-09, "loss": 0.8084, "step": 16956 }, { "epoch": 0.9904789719626168, "grad_norm": 0.9762248396873474, "learning_rate": 4.812741545764388e-09, "loss": 0.7708, "step": 16957 }, { "epoch": 0.9905373831775701, "grad_norm": 0.9205275177955627, "learning_rate": 4.754233151480492e-09, "loss": 0.6868, "step": 16958 }, { "epoch": 0.9905957943925233, "grad_norm": 1.0011059045791626, "learning_rate": 4.696082493614862e-09, "loss": 0.8307, "step": 16959 }, { "epoch": 0.9906542056074766, "grad_norm": 0.8292074799537659, "learning_rate": 4.6382895742491665e-09, "loss": 0.6676, "step": 16960 }, { "epoch": 0.99071261682243, "grad_norm": 1.2624708414077759, "learning_rate": 4.58085439544953e-09, "loss": 0.6428, "step": 16961 }, { "epoch": 0.9907710280373832, "grad_norm": 1.042297601699829, "learning_rate": 4.5237769592743066e-09, "loss": 0.7963, "step": 16962 }, { "epoch": 0.9908294392523365, "grad_norm": 0.8247860074043274, "learning_rate": 4.4670572677651955e-09, "loss": 0.6462, "step": 16963 }, { "epoch": 0.9908878504672897, "grad_norm": 0.9974175095558167, "learning_rate": 4.410695322952796e-09, "loss": 0.6254, "step": 16964 }, { "epoch": 0.990946261682243, "grad_norm": 0.9335569739341736, "learning_rate": 4.354691126853272e-09, "loss": 0.7309, "step": 16965 }, { "epoch": 0.9910046728971963, "grad_norm": 2.0952768325805664, "learning_rate": 4.2990446814705764e-09, "loss": 0.8694, "step": 16966 }, { "epoch": 0.9910630841121495, "grad_norm": 1.018936038017273, "learning_rate": 4.24375598879867e-09, "loss": 0.6948, "step": 16967 }, { "epoch": 0.9911214953271028, "grad_norm": 0.9772422909736633, "learning_rate": 4.18882505081486e-09, "loss": 0.8433, "step": 16968 }, { "epoch": 0.9911799065420561, "grad_norm": 0.8553386330604553, "learning_rate": 4.13425186948535e-09, "loss": 0.6513, "step": 16969 }, { "epoch": 0.9912383177570093, "grad_norm": 1.1808130741119385, "learning_rate": 4.080036446763025e-09, "loss": 0.7432, "step": 16970 }, { "epoch": 0.9912967289719626, "grad_norm": 1.198904275894165, "learning_rate": 4.026178784589663e-09, "loss": 0.6702, "step": 16971 }, { "epoch": 0.9913551401869158, "grad_norm": 1.1178151369094849, "learning_rate": 3.972678884890391e-09, "loss": 0.8989, "step": 16972 }, { "epoch": 0.9914135514018692, "grad_norm": 0.8712788820266724, "learning_rate": 3.919536749582564e-09, "loss": 0.7581, "step": 16973 }, { "epoch": 0.9914719626168225, "grad_norm": 0.9870116710662842, "learning_rate": 3.866752380566885e-09, "loss": 0.7601, "step": 16974 }, { "epoch": 0.9915303738317757, "grad_norm": 1.0578818321228027, "learning_rate": 3.814325779731842e-09, "loss": 0.6206, "step": 16975 }, { "epoch": 0.991588785046729, "grad_norm": 1.7542991638183594, "learning_rate": 3.7622569489559335e-09, "loss": 0.7098, "step": 16976 }, { "epoch": 0.9916471962616823, "grad_norm": 1.092268943786621, "learning_rate": 3.7105458901010027e-09, "loss": 0.7492, "step": 16977 }, { "epoch": 0.9917056074766355, "grad_norm": 1.0212715864181519, "learning_rate": 3.659192605017792e-09, "loss": 0.8849, "step": 16978 }, { "epoch": 0.9917640186915888, "grad_norm": 1.376038908958435, "learning_rate": 3.60819709554594e-09, "loss": 0.6353, "step": 16979 }, { "epoch": 0.991822429906542, "grad_norm": 0.9910879731178284, "learning_rate": 3.557559363508434e-09, "loss": 0.7614, "step": 16980 }, { "epoch": 0.9918808411214953, "grad_norm": 1.5091735124588013, "learning_rate": 3.5072794107193774e-09, "loss": 0.7448, "step": 16981 }, { "epoch": 0.9919392523364486, "grad_norm": 1.0813182592391968, "learning_rate": 3.4573572389773325e-09, "loss": 0.6552, "step": 16982 }, { "epoch": 0.9919976635514018, "grad_norm": 1.150738000869751, "learning_rate": 3.4077928500686473e-09, "loss": 0.9343, "step": 16983 }, { "epoch": 0.9920560747663552, "grad_norm": 1.0547847747802734, "learning_rate": 3.3585862457685693e-09, "loss": 0.841, "step": 16984 }, { "epoch": 0.9921144859813084, "grad_norm": 0.8816803097724915, "learning_rate": 3.3097374278379113e-09, "loss": 0.7465, "step": 16985 }, { "epoch": 0.9921728971962617, "grad_norm": 1.0788159370422363, "learning_rate": 3.2612463980241647e-09, "loss": 0.7701, "step": 16986 }, { "epoch": 0.992231308411215, "grad_norm": 1.0541223287582397, "learning_rate": 3.2131131580637186e-09, "loss": 0.6952, "step": 16987 }, { "epoch": 0.9922897196261682, "grad_norm": 0.8529942035675049, "learning_rate": 3.165337709679639e-09, "loss": 0.7509, "step": 16988 }, { "epoch": 0.9923481308411215, "grad_norm": 0.955718994140625, "learning_rate": 3.1179200545794484e-09, "loss": 0.7214, "step": 16989 }, { "epoch": 0.9924065420560748, "grad_norm": 1.0990263223648071, "learning_rate": 3.0708601944628992e-09, "loss": 0.7208, "step": 16990 }, { "epoch": 0.992464953271028, "grad_norm": 1.0219932794570923, "learning_rate": 3.024158131014199e-09, "loss": 0.6606, "step": 16991 }, { "epoch": 0.9925233644859813, "grad_norm": 1.0062785148620605, "learning_rate": 2.977813865903123e-09, "loss": 0.9264, "step": 16992 }, { "epoch": 0.9925817757009345, "grad_norm": 1.1099363565444946, "learning_rate": 2.931827400789455e-09, "loss": 0.8968, "step": 16993 }, { "epoch": 0.9926401869158878, "grad_norm": 0.9427039623260498, "learning_rate": 2.8861987373185464e-09, "loss": 0.7473, "step": 16994 }, { "epoch": 0.9926985981308412, "grad_norm": 0.9406134486198425, "learning_rate": 2.8409278771235337e-09, "loss": 0.7774, "step": 16995 }, { "epoch": 0.9927570093457944, "grad_norm": 1.5567213296890259, "learning_rate": 2.7960148218264538e-09, "loss": 0.8485, "step": 16996 }, { "epoch": 0.9928154205607477, "grad_norm": 1.1069904565811157, "learning_rate": 2.7514595730315784e-09, "loss": 0.6528, "step": 16997 }, { "epoch": 0.992873831775701, "grad_norm": 1.2484350204467773, "learning_rate": 2.707262132336519e-09, "loss": 0.7215, "step": 16998 }, { "epoch": 0.9929322429906542, "grad_norm": 1.0818299055099487, "learning_rate": 2.6634225013211223e-09, "loss": 0.7367, "step": 16999 }, { "epoch": 0.9929906542056075, "grad_norm": 0.966221809387207, "learning_rate": 2.619940681555244e-09, "loss": 0.8149, "step": 17000 }, { "epoch": 0.9930490654205607, "grad_norm": 1.0705623626708984, "learning_rate": 2.5768166745954173e-09, "loss": 0.692, "step": 17001 }, { "epoch": 0.993107476635514, "grad_norm": 1.4712029695510864, "learning_rate": 2.534050481984851e-09, "loss": 0.846, "step": 17002 }, { "epoch": 0.9931658878504673, "grad_norm": 1.0340876579284668, "learning_rate": 2.4916421052534333e-09, "loss": 0.9301, "step": 17003 }, { "epoch": 0.9932242990654205, "grad_norm": 3.9819815158843994, "learning_rate": 2.4495915459210596e-09, "loss": 0.8694, "step": 17004 }, { "epoch": 0.9932827102803738, "grad_norm": 1.1397144794464111, "learning_rate": 2.407898805489861e-09, "loss": 0.7703, "step": 17005 }, { "epoch": 0.993341121495327, "grad_norm": 1.097338318824768, "learning_rate": 2.3665638854541982e-09, "loss": 0.716, "step": 17006 }, { "epoch": 0.9933995327102804, "grad_norm": 1.0778495073318481, "learning_rate": 2.3255867872928885e-09, "loss": 0.7036, "step": 17007 }, { "epoch": 0.9934579439252337, "grad_norm": 0.9746605753898621, "learning_rate": 2.2849675124714255e-09, "loss": 0.7663, "step": 17008 }, { "epoch": 0.9935163551401869, "grad_norm": 1.0325896739959717, "learning_rate": 2.244706062445312e-09, "loss": 0.697, "step": 17009 }, { "epoch": 0.9935747663551402, "grad_norm": 1.1176458597183228, "learning_rate": 2.204802438655618e-09, "loss": 0.7721, "step": 17010 }, { "epoch": 0.9936331775700935, "grad_norm": 1.0679736137390137, "learning_rate": 2.165256642528979e-09, "loss": 0.8994, "step": 17011 }, { "epoch": 0.9936915887850467, "grad_norm": 0.8074257373809814, "learning_rate": 2.12606867548093e-09, "loss": 0.5449, "step": 17012 }, { "epoch": 0.99375, "grad_norm": 1.045777678489685, "learning_rate": 2.0872385389147932e-09, "loss": 0.696, "step": 17013 }, { "epoch": 0.9938084112149532, "grad_norm": 0.9448073506355286, "learning_rate": 2.048766234220567e-09, "loss": 0.6087, "step": 17014 }, { "epoch": 0.9938668224299065, "grad_norm": 0.9565726518630981, "learning_rate": 2.010651762774929e-09, "loss": 0.7179, "step": 17015 }, { "epoch": 0.9939252336448599, "grad_norm": 0.926578938961029, "learning_rate": 1.9728951259423425e-09, "loss": 0.8608, "step": 17016 }, { "epoch": 0.993983644859813, "grad_norm": 1.0288773775100708, "learning_rate": 1.935496325072839e-09, "loss": 0.7643, "step": 17017 }, { "epoch": 0.9940420560747664, "grad_norm": 1.0785636901855469, "learning_rate": 1.898455361505347e-09, "loss": 0.6448, "step": 17018 }, { "epoch": 0.9941004672897197, "grad_norm": 0.9163280725479126, "learning_rate": 1.8617722365665835e-09, "loss": 0.7626, "step": 17019 }, { "epoch": 0.9941588785046729, "grad_norm": 1.0206085443496704, "learning_rate": 1.8254469515688322e-09, "loss": 0.7107, "step": 17020 }, { "epoch": 0.9942172897196262, "grad_norm": 1.2342538833618164, "learning_rate": 1.7894795078121641e-09, "loss": 0.7525, "step": 17021 }, { "epoch": 0.9942757009345794, "grad_norm": 1.1525192260742188, "learning_rate": 1.7538699065844377e-09, "loss": 0.7123, "step": 17022 }, { "epoch": 0.9943341121495327, "grad_norm": 0.9633213877677917, "learning_rate": 1.7186181491590791e-09, "loss": 0.7695, "step": 17023 }, { "epoch": 0.994392523364486, "grad_norm": 1.2099608182907104, "learning_rate": 1.6837242367995221e-09, "loss": 0.6543, "step": 17024 }, { "epoch": 0.9944509345794392, "grad_norm": 0.9148221611976624, "learning_rate": 1.649188170752547e-09, "loss": 0.7233, "step": 17025 }, { "epoch": 0.9945093457943925, "grad_norm": 1.044470191001892, "learning_rate": 1.6150099522549423e-09, "loss": 0.842, "step": 17026 }, { "epoch": 0.9945677570093457, "grad_norm": 1.1465988159179688, "learning_rate": 1.5811895825301738e-09, "loss": 0.6669, "step": 17027 }, { "epoch": 0.9946261682242991, "grad_norm": 1.1031774282455444, "learning_rate": 1.5477270627894947e-09, "loss": 0.7301, "step": 17028 }, { "epoch": 0.9946845794392524, "grad_norm": 1.2414700984954834, "learning_rate": 1.5146223942297256e-09, "loss": 0.7878, "step": 17029 }, { "epoch": 0.9947429906542056, "grad_norm": 1.187204360961914, "learning_rate": 1.4818755780354744e-09, "loss": 0.8213, "step": 17030 }, { "epoch": 0.9948014018691589, "grad_norm": 0.7505767345428467, "learning_rate": 1.4494866153780263e-09, "loss": 0.6723, "step": 17031 }, { "epoch": 0.9948598130841122, "grad_norm": 1.0330873727798462, "learning_rate": 1.4174555074186746e-09, "loss": 0.6934, "step": 17032 }, { "epoch": 0.9949182242990654, "grad_norm": 0.9139130115509033, "learning_rate": 1.3857822553031697e-09, "loss": 0.7125, "step": 17033 }, { "epoch": 0.9949766355140187, "grad_norm": 0.9404715299606323, "learning_rate": 1.3544668601639388e-09, "loss": 0.6516, "step": 17034 }, { "epoch": 0.9950350467289719, "grad_norm": 1.048620581626892, "learning_rate": 1.3235093231234174e-09, "loss": 0.7375, "step": 17035 }, { "epoch": 0.9950934579439252, "grad_norm": 1.0539442300796509, "learning_rate": 1.292909645287388e-09, "loss": 0.9156, "step": 17036 }, { "epoch": 0.9951518691588785, "grad_norm": 1.3696550130844116, "learning_rate": 1.2626678277538607e-09, "loss": 0.8386, "step": 17037 }, { "epoch": 0.9952102803738317, "grad_norm": 0.9678943157196045, "learning_rate": 1.2327838716030827e-09, "loss": 0.71, "step": 17038 }, { "epoch": 0.9952686915887851, "grad_norm": 1.3789132833480835, "learning_rate": 1.203257777905309e-09, "loss": 0.8437, "step": 17039 }, { "epoch": 0.9953271028037384, "grad_norm": 0.9661613702774048, "learning_rate": 1.174089547717472e-09, "loss": 0.612, "step": 17040 }, { "epoch": 0.9953855140186916, "grad_norm": 1.1104917526245117, "learning_rate": 1.145279182083181e-09, "loss": 0.7704, "step": 17041 }, { "epoch": 0.9954439252336449, "grad_norm": 1.4981229305267334, "learning_rate": 1.1168266820327234e-09, "loss": 0.8155, "step": 17042 }, { "epoch": 0.9955023364485981, "grad_norm": 2.2897627353668213, "learning_rate": 1.0887320485863939e-09, "loss": 0.7734, "step": 17043 }, { "epoch": 0.9955607476635514, "grad_norm": 0.8540969491004944, "learning_rate": 1.0609952827489445e-09, "loss": 0.6771, "step": 17044 }, { "epoch": 0.9956191588785047, "grad_norm": 1.0355675220489502, "learning_rate": 1.0336163855129143e-09, "loss": 0.7457, "step": 17045 }, { "epoch": 0.9956775700934579, "grad_norm": 1.0376659631729126, "learning_rate": 1.0065953578586306e-09, "loss": 0.7395, "step": 17046 }, { "epoch": 0.9957359813084112, "grad_norm": 1.0865299701690674, "learning_rate": 9.799322007519874e-10, "loss": 0.8504, "step": 17047 }, { "epoch": 0.9957943925233644, "grad_norm": 1.5018129348754883, "learning_rate": 9.536269151477762e-10, "loss": 0.7742, "step": 17048 }, { "epoch": 0.9958528037383177, "grad_norm": 1.0889474153518677, "learning_rate": 9.276795019885765e-10, "loss": 0.7383, "step": 17049 }, { "epoch": 0.9959112149532711, "grad_norm": 0.7904438376426697, "learning_rate": 9.020899622014245e-10, "loss": 0.65, "step": 17050 }, { "epoch": 0.9959696261682243, "grad_norm": 0.8915912508964539, "learning_rate": 8.768582967033645e-10, "loss": 0.5986, "step": 17051 }, { "epoch": 0.9960280373831776, "grad_norm": 1.0648080110549927, "learning_rate": 8.519845063970078e-10, "loss": 0.8612, "step": 17052 }, { "epoch": 0.9960864485981309, "grad_norm": 1.3980913162231445, "learning_rate": 8.274685921727532e-10, "loss": 0.7518, "step": 17053 }, { "epoch": 0.9961448598130841, "grad_norm": 1.0167056322097778, "learning_rate": 8.033105549087872e-10, "loss": 0.7602, "step": 17054 }, { "epoch": 0.9962032710280374, "grad_norm": 1.0246182680130005, "learning_rate": 7.79510395467753e-10, "loss": 0.6692, "step": 17055 }, { "epoch": 0.9962616822429906, "grad_norm": 1.0205484628677368, "learning_rate": 7.560681147034122e-10, "loss": 0.7452, "step": 17056 }, { "epoch": 0.9963200934579439, "grad_norm": 0.9204261898994446, "learning_rate": 7.32983713453983e-10, "loss": 0.903, "step": 17057 }, { "epoch": 0.9963785046728972, "grad_norm": 1.0866520404815674, "learning_rate": 7.102571925454715e-10, "loss": 0.5696, "step": 17058 }, { "epoch": 0.9964369158878504, "grad_norm": 0.9336875081062317, "learning_rate": 6.878885527905609e-10, "loss": 0.778, "step": 17059 }, { "epoch": 0.9964953271028038, "grad_norm": 2.6144611835479736, "learning_rate": 6.658777949919426e-10, "loss": 0.7559, "step": 17060 }, { "epoch": 0.996553738317757, "grad_norm": 0.8860598802566528, "learning_rate": 6.442249199367645e-10, "loss": 0.6045, "step": 17061 }, { "epoch": 0.9966121495327103, "grad_norm": 0.9717853665351868, "learning_rate": 6.229299283977419e-10, "loss": 0.6362, "step": 17062 }, { "epoch": 0.9966705607476636, "grad_norm": 1.0941731929779053, "learning_rate": 6.019928211398185e-10, "loss": 0.6415, "step": 17063 }, { "epoch": 0.9967289719626168, "grad_norm": 1.2187328338623047, "learning_rate": 5.814135989112846e-10, "loss": 0.7326, "step": 17064 }, { "epoch": 0.9967873831775701, "grad_norm": 0.9937381148338318, "learning_rate": 5.611922624493283e-10, "loss": 0.6538, "step": 17065 }, { "epoch": 0.9968457943925234, "grad_norm": 0.9317790269851685, "learning_rate": 5.413288124767047e-10, "loss": 0.794, "step": 17066 }, { "epoch": 0.9969042056074766, "grad_norm": 1.9862250089645386, "learning_rate": 5.218232497039566e-10, "loss": 0.7075, "step": 17067 }, { "epoch": 0.9969626168224299, "grad_norm": 0.9933493137359619, "learning_rate": 5.026755748305245e-10, "loss": 0.7372, "step": 17068 }, { "epoch": 0.9970210280373831, "grad_norm": 1.07268488407135, "learning_rate": 4.838857885414161e-10, "loss": 0.7933, "step": 17069 }, { "epoch": 0.9970794392523364, "grad_norm": 1.0123765468597412, "learning_rate": 4.654538915083162e-10, "loss": 0.7605, "step": 17070 }, { "epoch": 0.9971378504672898, "grad_norm": 1.1164467334747314, "learning_rate": 4.4737988439069733e-10, "loss": 0.563, "step": 17071 }, { "epoch": 0.997196261682243, "grad_norm": 1.08077073097229, "learning_rate": 4.2966376783804e-10, "loss": 0.7864, "step": 17072 }, { "epoch": 0.9972546728971963, "grad_norm": 0.8775122165679932, "learning_rate": 4.123055424809508e-10, "loss": 0.6687, "step": 17073 }, { "epoch": 0.9973130841121496, "grad_norm": 1.1815600395202637, "learning_rate": 3.953052089433751e-10, "loss": 0.6641, "step": 17074 }, { "epoch": 0.9973714953271028, "grad_norm": 0.9281100034713745, "learning_rate": 3.786627678314947e-10, "loss": 0.7253, "step": 17075 }, { "epoch": 0.9974299065420561, "grad_norm": 1.0599029064178467, "learning_rate": 3.623782197437198e-10, "loss": 0.8327, "step": 17076 }, { "epoch": 0.9974883177570093, "grad_norm": 1.2499513626098633, "learning_rate": 3.4645156525958677e-10, "loss": 0.7689, "step": 17077 }, { "epoch": 0.9975467289719626, "grad_norm": 1.0823653936386108, "learning_rate": 3.308828049519708e-10, "loss": 0.7256, "step": 17078 }, { "epoch": 0.9976051401869159, "grad_norm": 0.998157799243927, "learning_rate": 3.156719393770935e-10, "loss": 0.7594, "step": 17079 }, { "epoch": 0.9976635514018691, "grad_norm": 1.238188624382019, "learning_rate": 3.0081896907896423e-10, "loss": 0.8343, "step": 17080 }, { "epoch": 0.9977219626168224, "grad_norm": 0.9987694621086121, "learning_rate": 2.863238945893798e-10, "loss": 0.7149, "step": 17081 }, { "epoch": 0.9977803738317756, "grad_norm": 1.0918023586273193, "learning_rate": 2.721867164268144e-10, "loss": 0.7606, "step": 17082 }, { "epoch": 0.997838785046729, "grad_norm": 0.9887135028839111, "learning_rate": 2.584074350986399e-10, "loss": 0.7274, "step": 17083 }, { "epoch": 0.9978971962616823, "grad_norm": 1.2985767126083374, "learning_rate": 2.4498605109668503e-10, "loss": 0.902, "step": 17084 }, { "epoch": 0.9979556074766355, "grad_norm": 0.9149218201637268, "learning_rate": 2.319225649005663e-10, "loss": 0.68, "step": 17085 }, { "epoch": 0.9980140186915888, "grad_norm": 1.1382081508636475, "learning_rate": 2.1921697697990796e-10, "loss": 0.8434, "step": 17086 }, { "epoch": 0.9980724299065421, "grad_norm": 1.5208513736724854, "learning_rate": 2.0686928778879123e-10, "loss": 0.7029, "step": 17087 }, { "epoch": 0.9981308411214953, "grad_norm": 1.1367311477661133, "learning_rate": 1.9487949776797466e-10, "loss": 0.8455, "step": 17088 }, { "epoch": 0.9981892523364486, "grad_norm": 0.865196704864502, "learning_rate": 1.8324760734822477e-10, "loss": 0.6535, "step": 17089 }, { "epoch": 0.9982476635514018, "grad_norm": 1.0229508876800537, "learning_rate": 1.7197361694365477e-10, "loss": 0.8318, "step": 17090 }, { "epoch": 0.9983060747663551, "grad_norm": 1.3415167331695557, "learning_rate": 1.6105752696060628e-10, "loss": 0.7406, "step": 17091 }, { "epoch": 0.9983644859813084, "grad_norm": 1.0203936100006104, "learning_rate": 1.5049933778765735e-10, "loss": 0.6278, "step": 17092 }, { "epoch": 0.9984228971962616, "grad_norm": 0.9119949340820312, "learning_rate": 1.4029904980339404e-10, "loss": 0.7647, "step": 17093 }, { "epoch": 0.998481308411215, "grad_norm": 0.990648627281189, "learning_rate": 1.304566633730797e-10, "loss": 0.6129, "step": 17094 }, { "epoch": 0.9985397196261683, "grad_norm": 0.9792044758796692, "learning_rate": 1.2097217884865507e-10, "loss": 0.4823, "step": 17095 }, { "epoch": 0.9985981308411215, "grad_norm": 0.940704882144928, "learning_rate": 1.1184559656984839e-10, "loss": 0.6758, "step": 17096 }, { "epoch": 0.9986565420560748, "grad_norm": 0.9013988375663757, "learning_rate": 1.030769168630652e-10, "loss": 0.5886, "step": 17097 }, { "epoch": 0.998714953271028, "grad_norm": 0.9758431315422058, "learning_rate": 9.466614004138841e-11, "loss": 0.7844, "step": 17098 }, { "epoch": 0.9987733644859813, "grad_norm": 0.7598319053649902, "learning_rate": 8.66132664079089e-11, "loss": 0.7088, "step": 17099 }, { "epoch": 0.9988317757009346, "grad_norm": 1.2870280742645264, "learning_rate": 7.891829624906422e-11, "loss": 0.8619, "step": 17100 }, { "epoch": 0.9988901869158878, "grad_norm": 1.174659252166748, "learning_rate": 7.158122984129989e-11, "loss": 0.6983, "step": 17101 }, { "epoch": 0.9989485981308411, "grad_norm": 1.0326818227767944, "learning_rate": 6.460206744551834e-11, "loss": 0.6489, "step": 17102 }, { "epoch": 0.9990070093457943, "grad_norm": 1.3222006559371948, "learning_rate": 5.798080931374017e-11, "loss": 0.9135, "step": 17103 }, { "epoch": 0.9990654205607477, "grad_norm": 0.9758809804916382, "learning_rate": 5.1717455681332684e-11, "loss": 0.6397, "step": 17104 }, { "epoch": 0.999123831775701, "grad_norm": 0.9778735637664795, "learning_rate": 4.581200677367115e-11, "loss": 0.9576, "step": 17105 }, { "epoch": 0.9991822429906542, "grad_norm": 1.6286513805389404, "learning_rate": 4.026446280169793e-11, "loss": 0.7331, "step": 17106 }, { "epoch": 0.9992406542056075, "grad_norm": 0.9268882870674133, "learning_rate": 3.5074823963032744e-11, "loss": 0.6861, "step": 17107 }, { "epoch": 0.9992990654205608, "grad_norm": 1.252060890197754, "learning_rate": 3.0243090444193046e-11, "loss": 0.7902, "step": 17108 }, { "epoch": 0.999357476635514, "grad_norm": 1.0261578559875488, "learning_rate": 2.576926241837363e-11, "loss": 0.6788, "step": 17109 }, { "epoch": 0.9994158878504673, "grad_norm": 1.204297661781311, "learning_rate": 2.1653340045446615e-11, "loss": 0.8479, "step": 17110 }, { "epoch": 0.9994742990654205, "grad_norm": 0.92666095495224, "learning_rate": 1.7895323471961433e-11, "loss": 0.581, "step": 17111 }, { "epoch": 0.9995327102803738, "grad_norm": 1.2255587577819824, "learning_rate": 1.4495212834475525e-11, "loss": 0.7368, "step": 17112 }, { "epoch": 0.9995911214953271, "grad_norm": 1.4310369491577148, "learning_rate": 1.1453008251782748e-11, "loss": 0.9117, "step": 17113 }, { "epoch": 0.9996495327102803, "grad_norm": 1.018444299697876, "learning_rate": 8.768709834905409e-12, "loss": 0.6664, "step": 17114 }, { "epoch": 0.9997079439252337, "grad_norm": 0.9221544861793518, "learning_rate": 6.4423176793226846e-12, "loss": 0.6979, "step": 17115 }, { "epoch": 0.999766355140187, "grad_norm": 1.0017166137695312, "learning_rate": 4.4738318683013036e-12, "loss": 0.8271, "step": 17116 }, { "epoch": 0.9998247663551402, "grad_norm": 1.2902287244796753, "learning_rate": 2.863252472895539e-12, "loss": 0.7542, "step": 17117 }, { "epoch": 0.9998831775700935, "grad_norm": 1.0570790767669678, "learning_rate": 1.6105795497267652e-12, "loss": 0.8504, "step": 17118 }, { "epoch": 0.9999415887850467, "grad_norm": 1.2856327295303345, "learning_rate": 7.158131443141258e-13, "loss": 0.9707, "step": 17119 }, { "epoch": 1.0, "grad_norm": 1.0304148197174072, "learning_rate": 1.78953287743866e-13, "loss": 0.8253, "step": 17120 }, { "epoch": 1.0, "step": 17120, "total_flos": 1.6053657882955298e+20, "train_loss": 0.8368375787581099, "train_runtime": 214699.8673, "train_samples_per_second": 2.552, "train_steps_per_second": 0.08 } ], "logging_steps": 1.0, "max_steps": 17120, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.6053657882955298e+20, "train_batch_size": 1, "trial_name": null, "trial_params": null }