{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 7.503084713970782, "learning_rate": 3.2258064516129035e-07, "loss": 1.1378, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 7.514736403667072, "learning_rate": 6.451612903225807e-07, "loss": 1.1866, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.798409960072311, "learning_rate": 9.67741935483871e-07, "loss": 1.1989, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 7.897880481370664, "learning_rate": 1.2903225806451614e-06, "loss": 1.2099, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 7.138357703065381, "learning_rate": 1.6129032258064516e-06, "loss": 1.1351, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.743193137108209, "learning_rate": 1.935483870967742e-06, "loss": 1.0948, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.966458103750349, "learning_rate": 2.2580645161290324e-06, "loss": 1.1132, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 5.463755006671124, "learning_rate": 2.580645161290323e-06, "loss": 1.0993, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 3.2103603587160903, "learning_rate": 2.903225806451613e-06, "loss": 1.0509, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.7154689836659656, "learning_rate": 3.225806451612903e-06, "loss": 1.0017, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.4606075068928757, "learning_rate": 3.548387096774194e-06, "loss": 1.0248, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.357474525162542, "learning_rate": 3.870967741935484e-06, "loss": 0.9936, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.47595324759215, "learning_rate": 4.193548387096774e-06, "loss": 1.0052, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.20336755465853, "learning_rate": 4.516129032258065e-06, "loss": 0.9464, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.051392158558194, "learning_rate": 4.838709677419355e-06, "loss": 0.9433, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.0210222780174707, "learning_rate": 5.161290322580646e-06, "loss": 0.9037, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.9224001853922474, "learning_rate": 5.483870967741935e-06, "loss": 0.9107, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.765680934528235, "learning_rate": 5.806451612903226e-06, "loss": 0.9008, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.4292697828752847, "learning_rate": 6.129032258064517e-06, "loss": 0.8984, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 2.039865398046408, "learning_rate": 6.451612903225806e-06, "loss": 0.853, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.713672291300877, "learning_rate": 6.774193548387097e-06, "loss": 0.8554, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.6569604217553489, "learning_rate": 7.096774193548388e-06, "loss": 0.8649, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.6276445336780074, "learning_rate": 7.4193548387096784e-06, "loss": 0.8295, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.6593974859456029, "learning_rate": 7.741935483870968e-06, "loss": 0.8464, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.2685811716932058, "learning_rate": 8.064516129032258e-06, "loss": 0.8237, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.1587027560182672, "learning_rate": 8.387096774193549e-06, "loss": 0.8278, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.1824843029776155, "learning_rate": 8.70967741935484e-06, "loss": 0.8142, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.1318642179998892, "learning_rate": 9.03225806451613e-06, "loss": 0.814, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.044257893716117, "learning_rate": 9.35483870967742e-06, "loss": 0.8057, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.0147522821814636, "learning_rate": 9.67741935483871e-06, "loss": 0.7981, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 1.0895239478528396, "learning_rate": 1e-05, "loss": 0.8113, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.9676228324112952, "learning_rate": 1.0322580645161291e-05, "loss": 0.8297, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.8576992425152197, "learning_rate": 1.0645161290322582e-05, "loss": 0.8017, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.9050315930918111, "learning_rate": 1.096774193548387e-05, "loss": 0.7743, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.8489890757076628, "learning_rate": 1.1290322580645164e-05, "loss": 0.7396, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.8345399880533599, "learning_rate": 1.1612903225806453e-05, "loss": 0.7861, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.9094266656676647, "learning_rate": 1.1935483870967743e-05, "loss": 0.7735, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.7665588051442778, "learning_rate": 1.2258064516129034e-05, "loss": 0.7739, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.7813096965685901, "learning_rate": 1.2580645161290324e-05, "loss": 0.7596, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.9022644305231784, "learning_rate": 1.2903225806451613e-05, "loss": 0.8202, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7920588138052854, "learning_rate": 1.3225806451612903e-05, "loss": 0.7643, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.8337950966733882, "learning_rate": 1.3548387096774194e-05, "loss": 0.7392, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.8018917800745686, "learning_rate": 1.3870967741935486e-05, "loss": 0.7833, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.873853755723303, "learning_rate": 1.4193548387096776e-05, "loss": 0.7634, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.7437388042229468, "learning_rate": 1.4516129032258066e-05, "loss": 0.7387, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.8302666326690332, "learning_rate": 1.4838709677419357e-05, "loss": 0.7513, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.8385945798299679, "learning_rate": 1.5161290322580646e-05, "loss": 0.7559, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.8425080272526984, "learning_rate": 1.5483870967741936e-05, "loss": 0.7413, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.8476220948118279, "learning_rate": 1.5806451612903226e-05, "loss": 0.7789, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.8898908060888648, "learning_rate": 1.6129032258064517e-05, "loss": 0.7599, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.9479752199638628, "learning_rate": 1.6451612903225807e-05, "loss": 0.7655, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.7844725583945985, "learning_rate": 1.6774193548387098e-05, "loss": 0.7487, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.8016191191180528, "learning_rate": 1.7096774193548388e-05, "loss": 0.7387, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.8029340274434809, "learning_rate": 1.741935483870968e-05, "loss": 0.7406, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7944806910259237, "learning_rate": 1.774193548387097e-05, "loss": 0.7526, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.7466417656983905, "learning_rate": 1.806451612903226e-05, "loss": 0.7409, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.7900460242198514, "learning_rate": 1.838709677419355e-05, "loss": 0.7499, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.7281240011051396, "learning_rate": 1.870967741935484e-05, "loss": 0.726, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.8539979067777076, "learning_rate": 1.903225806451613e-05, "loss": 0.7345, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.720838143015573, "learning_rate": 1.935483870967742e-05, "loss": 0.7274, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.9042186324582473, "learning_rate": 1.967741935483871e-05, "loss": 0.7248, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.7803205309817628, "learning_rate": 2e-05, "loss": 0.7311, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.9061917508408353, "learning_rate": 2.0322580645161292e-05, "loss": 0.7343, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.8769045903819416, "learning_rate": 2.0645161290322582e-05, "loss": 0.7452, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.8263308924061519, "learning_rate": 2.0967741935483873e-05, "loss": 0.7461, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 1.2282839617608687, "learning_rate": 2.1290322580645163e-05, "loss": 0.7621, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.8068501478008052, "learning_rate": 2.161290322580645e-05, "loss": 0.7312, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 1.3196707039534552, "learning_rate": 2.193548387096774e-05, "loss": 0.7337, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.9288671465452273, "learning_rate": 2.225806451612903e-05, "loss": 0.7256, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.3934460386361143, "learning_rate": 2.2580645161290328e-05, "loss": 0.7326, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 1.1048997986093254, "learning_rate": 2.2903225806451615e-05, "loss": 0.7118, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 1.185694114601632, "learning_rate": 2.3225806451612906e-05, "loss": 0.7238, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 1.0964117028097276, "learning_rate": 2.3548387096774196e-05, "loss": 0.7334, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.9826085148141172, "learning_rate": 2.3870967741935486e-05, "loss": 0.753, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.9557923911406768, "learning_rate": 2.4193548387096777e-05, "loss": 0.7111, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.9117674431126678, "learning_rate": 2.4516129032258067e-05, "loss": 0.7272, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.8106637740280904, "learning_rate": 2.4838709677419358e-05, "loss": 0.7424, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.8411245261643929, "learning_rate": 2.5161290322580648e-05, "loss": 0.7107, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8718447080294116, "learning_rate": 2.548387096774194e-05, "loss": 0.7205, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.7869858768598513, "learning_rate": 2.5806451612903226e-05, "loss": 0.7493, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.8047022303536817, "learning_rate": 2.6129032258064516e-05, "loss": 0.7458, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.743769808249303, "learning_rate": 2.6451612903225806e-05, "loss": 0.7236, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8500304587544085, "learning_rate": 2.6774193548387097e-05, "loss": 0.731, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.8717676214001009, "learning_rate": 2.7096774193548387e-05, "loss": 0.7222, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.8484835943107905, "learning_rate": 2.7419354838709678e-05, "loss": 0.7362, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.8208753143010263, "learning_rate": 2.774193548387097e-05, "loss": 0.7468, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7813284358670587, "learning_rate": 2.8064516129032262e-05, "loss": 0.7271, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.8111078298043992, "learning_rate": 2.8387096774193552e-05, "loss": 0.7324, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.7346035852600786, "learning_rate": 2.8709677419354843e-05, "loss": 0.6911, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.9305236385531354, "learning_rate": 2.9032258064516133e-05, "loss": 0.7069, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.7147781210564377, "learning_rate": 2.9354838709677423e-05, "loss": 0.7012, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.0627283756067116, "learning_rate": 2.9677419354838714e-05, "loss": 0.6948, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.74497667585685, "learning_rate": 3.0000000000000004e-05, "loss": 0.7233, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.9967539138388996, "learning_rate": 3.032258064516129e-05, "loss": 0.6803, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.0140979491520121, "learning_rate": 3.0645161290322585e-05, "loss": 0.7379, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.843922372946162, "learning_rate": 3.096774193548387e-05, "loss": 0.7445, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.8144103146454966, "learning_rate": 3.1290322580645166e-05, "loss": 0.7355, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.9355487569083951, "learning_rate": 3.161290322580645e-05, "loss": 0.7006, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.8477507976311596, "learning_rate": 3.193548387096774e-05, "loss": 0.7278, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.9800504591011133, "learning_rate": 3.2258064516129034e-05, "loss": 0.7362, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.9952295961616786, "learning_rate": 3.258064516129033e-05, "loss": 0.7414, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.8298212188407171, "learning_rate": 3.2903225806451614e-05, "loss": 0.7157, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.9846902103926153, "learning_rate": 3.322580645161291e-05, "loss": 0.7318, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.86032566313432, "learning_rate": 3.3548387096774195e-05, "loss": 0.7615, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.8602938155918123, "learning_rate": 3.387096774193549e-05, "loss": 0.7362, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.0607743582730986, "learning_rate": 3.4193548387096776e-05, "loss": 0.7099, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.7864840665525412, "learning_rate": 3.451612903225807e-05, "loss": 0.7242, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.0057308206184927, "learning_rate": 3.483870967741936e-05, "loss": 0.7396, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9965626676920889, "learning_rate": 3.516129032258065e-05, "loss": 0.7497, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.8044873206043468, "learning_rate": 3.548387096774194e-05, "loss": 0.6934, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.9614611282697613, "learning_rate": 3.5806451612903225e-05, "loss": 0.75, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8155759262836069, "learning_rate": 3.612903225806452e-05, "loss": 0.7463, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.7781799223795876, "learning_rate": 3.6451612903225805e-05, "loss": 0.755, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.8370819864539909, "learning_rate": 3.67741935483871e-05, "loss": 0.693, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.7093715304693179, "learning_rate": 3.7096774193548386e-05, "loss": 0.6982, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.8242850547431189, "learning_rate": 3.741935483870968e-05, "loss": 0.7097, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.7503423377527173, "learning_rate": 3.7741935483870974e-05, "loss": 0.7123, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.7970414784742299, "learning_rate": 3.806451612903226e-05, "loss": 0.7352, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.79416125117298, "learning_rate": 3.8387096774193555e-05, "loss": 0.708, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.7901521463641622, "learning_rate": 3.870967741935484e-05, "loss": 0.7317, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.9075458303696281, "learning_rate": 3.9032258064516135e-05, "loss": 0.7824, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.7171932937737137, "learning_rate": 3.935483870967742e-05, "loss": 0.7223, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.8494488237784494, "learning_rate": 3.9677419354838716e-05, "loss": 0.7078, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.8876555384118522, "learning_rate": 4e-05, "loss": 0.7141, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.8781269326148973, "learning_rate": 3.9999920040266474e-05, "loss": 0.7045, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.9536273573069767, "learning_rate": 3.999968016170525e-05, "loss": 0.7141, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.8689484886000522, "learning_rate": 3.9999280366234394e-05, "loss": 0.7442, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.8569610427008477, "learning_rate": 3.999872065705065e-05, "loss": 0.7232, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.92449501194472, "learning_rate": 3.999800103862945e-05, "loss": 0.726, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.8454576800997607, "learning_rate": 3.9997121516724834e-05, "loss": 0.705, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.8721849391594905, "learning_rate": 3.999608209836944e-05, "loss": 0.713, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.7708170056276964, "learning_rate": 3.999488279187443e-05, "loss": 0.7515, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.9743005311692512, "learning_rate": 3.9993523606829425e-05, "loss": 0.7173, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7310647386213173, "learning_rate": 3.9992004554102435e-05, "loss": 0.7152, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.8371909589051477, "learning_rate": 3.999032564583976e-05, "loss": 0.7508, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.9818120236929883, "learning_rate": 3.998848689546591e-05, "loss": 0.7357, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.8749344160217039, "learning_rate": 3.9986488317683496e-05, "loss": 0.7542, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.7652516654354116, "learning_rate": 3.9984329928473067e-05, "loss": 0.735, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.7316889440613997, "learning_rate": 3.998201174509306e-05, "loss": 0.7217, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.7566042198585932, "learning_rate": 3.997953378607961e-05, "loss": 0.7008, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.7155569441096521, "learning_rate": 3.9976896071246403e-05, "loss": 0.7287, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.721842470299914, "learning_rate": 3.997409862168454e-05, "loss": 0.7277, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.8477513306264948, "learning_rate": 3.997114145976237e-05, "loss": 0.7303, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.7246344392354322, "learning_rate": 3.9968024609125245e-05, "loss": 0.7282, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7855559977049402, "learning_rate": 3.996474809469545e-05, "loss": 0.7247, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.789446164485517, "learning_rate": 3.996131194267189e-05, "loss": 0.7514, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.7315221146396573, "learning_rate": 3.995771618052995e-05, "loss": 0.7149, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.7746756108590115, "learning_rate": 3.9953960837021256e-05, "loss": 0.7222, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.8835978131274552, "learning_rate": 3.995004594217343e-05, "loss": 0.7345, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7291898046881454, "learning_rate": 3.994597152728987e-05, "loss": 0.6955, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.8440947157426881, "learning_rate": 3.994173762494947e-05, "loss": 0.6881, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.8767354477574277, "learning_rate": 3.9937344269006424e-05, "loss": 0.7091, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7348441619560454, "learning_rate": 3.993279149458988e-05, "loss": 0.7382, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.6172477096329974, "learning_rate": 3.9928079338103695e-05, "loss": 0.6793, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.7529066537789875, "learning_rate": 3.992320783722616e-05, "loss": 0.706, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.6617903003559731, "learning_rate": 3.991817703090965e-05, "loss": 0.7442, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.7958397826787119, "learning_rate": 3.991298695938038e-05, "loss": 0.7282, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6925128234069009, "learning_rate": 3.9907637664138e-05, "loss": 0.699, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.723313864752648, "learning_rate": 3.990212918795534e-05, "loss": 0.6949, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.7715229040006584, "learning_rate": 3.9896461574878036e-05, "loss": 0.6986, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6425285739086375, "learning_rate": 3.989063487022416e-05, "loss": 0.724, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.7549032172303133, "learning_rate": 3.9884649120583903e-05, "loss": 0.706, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.8043377820911355, "learning_rate": 3.987850437381915e-05, "loss": 0.7348, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6758390035747324, "learning_rate": 3.987220067906313e-05, "loss": 0.6998, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.8729698686867833, "learning_rate": 3.986573808672002e-05, "loss": 0.7111, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6518367627530275, "learning_rate": 3.9859116648464534e-05, "loss": 0.7332, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.7464160064114018, "learning_rate": 3.985233641724152e-05, "loss": 0.7383, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7102752930466575, "learning_rate": 3.984539744726554e-05, "loss": 0.7026, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6693743306909408, "learning_rate": 3.983829979402038e-05, "loss": 0.7352, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.7367364159071617, "learning_rate": 3.983104351425871e-05, "loss": 0.7329, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7038543513509129, "learning_rate": 3.982362866600154e-05, "loss": 0.7067, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.6498682158348038, "learning_rate": 3.9816055308537806e-05, "loss": 0.7075, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.8207697277770131, "learning_rate": 3.980832350242388e-05, "loss": 0.7385, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.597102378514704, "learning_rate": 3.980043330948306e-05, "loss": 0.7268, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.7477131040891922, "learning_rate": 3.9792384792805124e-05, "loss": 0.6996, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.6078718991064413, "learning_rate": 3.978417801674579e-05, "loss": 0.7106, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.6642376386375441, "learning_rate": 3.9775813046926244e-05, "loss": 0.7166, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6991344633603604, "learning_rate": 3.976728995023254e-05, "loss": 0.7141, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6670194415695312, "learning_rate": 3.975860879481514e-05, "loss": 0.7243, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.7883389236409916, "learning_rate": 3.974976965008833e-05, "loss": 0.7268, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.6933234837192257, "learning_rate": 3.9740772586729674e-05, "loss": 0.7229, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.8022132568744594, "learning_rate": 3.973161767667946e-05, "loss": 0.6986, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.7561047352055063, "learning_rate": 3.972230499314009e-05, "loss": 0.7314, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.7241947024468693, "learning_rate": 3.9712834610575545e-05, "loss": 0.7182, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.7925779471479256, "learning_rate": 3.9703206604710746e-05, "loss": 0.735, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.6355957139526814, "learning_rate": 3.969342105253098e-05, "loss": 0.6906, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.7902097299662549, "learning_rate": 3.9683478032281246e-05, "loss": 0.7065, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.6470084347571323, "learning_rate": 3.967337762346568e-05, "loss": 0.6791, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.7060064701849832, "learning_rate": 3.9663119906846885e-05, "loss": 0.7048, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.7143220395487808, "learning_rate": 3.965270496444528e-05, "loss": 0.709, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6271098518991463, "learning_rate": 3.9642132879538465e-05, "loss": 0.7077, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.7120814335184248, "learning_rate": 3.9631403736660566e-05, "loss": 0.7034, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.6254435569179084, "learning_rate": 3.962051762160151e-05, "loss": 0.7207, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.6699264317073158, "learning_rate": 3.960947462140638e-05, "loss": 0.6762, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.7137515119940933, "learning_rate": 3.959827482437472e-05, "loss": 0.705, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.8498103089559972, "learning_rate": 3.958691832005981e-05, "loss": 0.6853, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.828106979384943, "learning_rate": 3.9575405199267944e-05, "loss": 0.7154, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.9995509238940671, "learning_rate": 3.956373555405774e-05, "loss": 0.7274, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.9428524684177987, "learning_rate": 3.955190947773937e-05, "loss": 0.7193, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.9268073697762673, "learning_rate": 3.9539927064873824e-05, "loss": 0.7365, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.8033575777168859, "learning_rate": 3.952778841127214e-05, "loss": 0.7573, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.8064560286778566, "learning_rate": 3.95154936139947e-05, "loss": 0.6991, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.7076300350513784, "learning_rate": 3.950304277135034e-05, "loss": 0.6994, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.7893631695006703, "learning_rate": 3.94904359828957e-05, "loss": 0.7142, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.7207475337668579, "learning_rate": 3.94776733494343e-05, "loss": 0.7041, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.7243475809052301, "learning_rate": 3.9464754973015826e-05, "loss": 0.7025, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.6806592922216583, "learning_rate": 3.9451680956935275e-05, "loss": 0.7042, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.6391722846469379, "learning_rate": 3.943845140573213e-05, "loss": 0.6874, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.6367528231894845, "learning_rate": 3.942506642518952e-05, "loss": 0.7003, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.6808587975672579, "learning_rate": 3.9411526122333396e-05, "loss": 0.7018, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.7859981176067001, "learning_rate": 3.939783060543167e-05, "loss": 0.6783, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.6090591808367701, "learning_rate": 3.938397998399333e-05, "loss": 0.7363, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6310934926937574, "learning_rate": 3.936997436876756e-05, "loss": 0.6615, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.693519613676404, "learning_rate": 3.935581387174289e-05, "loss": 0.7218, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.6609893369467876, "learning_rate": 3.9341498606146295e-05, "loss": 0.7116, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.6479039513732231, "learning_rate": 3.932702868644224e-05, "loss": 0.7351, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.6434777304597135, "learning_rate": 3.931240422833181e-05, "loss": 0.7051, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5937847002805944, "learning_rate": 3.9297625348751806e-05, "loss": 0.7354, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.6845593817154572, "learning_rate": 3.9282692165873744e-05, "loss": 0.6883, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.6171918163358955, "learning_rate": 3.9267604799102945e-05, "loss": 0.7295, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.719015730659809, "learning_rate": 3.9252363369077615e-05, "loss": 0.6898, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.6874534422156943, "learning_rate": 3.9236967997667796e-05, "loss": 0.7029, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.7145040943365062, "learning_rate": 3.9221418807974496e-05, "loss": 0.7094, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.7304783555363966, "learning_rate": 3.92057159243286e-05, "loss": 0.7137, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.6703404348970633, "learning_rate": 3.9189859472289956e-05, "loss": 0.7205, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6456334843749909, "learning_rate": 3.9173849578646324e-05, "loss": 0.6514, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6297462008784189, "learning_rate": 3.9157686371412395e-05, "loss": 0.6757, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.6941238336501455, "learning_rate": 3.914136997982874e-05, "loss": 0.7064, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5852924944837691, "learning_rate": 3.912490053436079e-05, "loss": 0.6832, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.606643755574863, "learning_rate": 3.9108278166697805e-05, "loss": 0.7258, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.6612603259399625, "learning_rate": 3.909150300975178e-05, "loss": 0.691, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.6061629315254736, "learning_rate": 3.907457519765642e-05, "loss": 0.7214, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5651435342441211, "learning_rate": 3.905749486576607e-05, "loss": 0.6839, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6557524252925451, "learning_rate": 3.90402621506546e-05, "loss": 0.7108, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.625054893235283, "learning_rate": 3.902287719011435e-05, "loss": 0.6909, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.6281349360182332, "learning_rate": 3.900534012315499e-05, "loss": 0.6936, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.6566475638768139, "learning_rate": 3.8987651090002454e-05, "loss": 0.6861, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.6178524939759333, "learning_rate": 3.896981023209777e-05, "loss": 0.6646, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.6124082889964377, "learning_rate": 3.8951817692095966e-05, "loss": 0.6853, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.6895877533777828, "learning_rate": 3.893367361386491e-05, "loss": 0.7004, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.5700234145055577, "learning_rate": 3.891537814248417e-05, "loss": 0.7045, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.6646951749468317, "learning_rate": 3.889693142424384e-05, "loss": 0.7047, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5931067412447493, "learning_rate": 3.8878333606643405e-05, "loss": 0.7194, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6009301720708553, "learning_rate": 3.885958483839049e-05, "loss": 0.7032, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.5958303722730084, "learning_rate": 3.8840685269399786e-05, "loss": 0.7139, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.587388294528334, "learning_rate": 3.882163505079171e-05, "loss": 0.7063, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.5884532344866329, "learning_rate": 3.880243433489132e-05, "loss": 0.7354, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.7475352379810443, "learning_rate": 3.878308327522702e-05, "loss": 0.5264, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.5857476818801367, "learning_rate": 3.876358202652936e-05, "loss": 0.5434, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.7345124797477577, "learning_rate": 3.8743930744729835e-05, "loss": 0.5203, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.7039537037101731, "learning_rate": 3.8724129586959535e-05, "loss": 0.5276, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.715284395522371, "learning_rate": 3.870417871154801e-05, "loss": 0.5219, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.667673131144657, "learning_rate": 3.868407827802192e-05, "loss": 0.5231, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.736881292238405, "learning_rate": 3.8663828447103804e-05, "loss": 0.5206, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.8091277633431571, "learning_rate": 3.8643429380710765e-05, "loss": 0.5014, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6912726303367818, "learning_rate": 3.862288124195319e-05, "loss": 0.5364, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.7226243359721346, "learning_rate": 3.8602184195133464e-05, "loss": 0.553, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.6982947840874775, "learning_rate": 3.8581338405744604e-05, "loss": 0.5051, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.7112063406703065, "learning_rate": 3.8560344040468996e-05, "loss": 0.5487, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.6182325464352314, "learning_rate": 3.853920126717703e-05, "loss": 0.525, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6086333433890887, "learning_rate": 3.851791025492574e-05, "loss": 0.5161, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.6886521258131968, "learning_rate": 3.8496471173957515e-05, "loss": 0.5118, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.6208825938053485, "learning_rate": 3.847488419569866e-05, "loss": 0.5227, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.623652455283092, "learning_rate": 3.8453149492758077e-05, "loss": 0.5178, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6605770503357135, "learning_rate": 3.8431267238925886e-05, "loss": 0.5338, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.648801897079242, "learning_rate": 3.840923760917199e-05, "loss": 0.5084, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.7141707444202106, "learning_rate": 3.838706077964473e-05, "loss": 0.5277, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.6268280924553036, "learning_rate": 3.836473692766944e-05, "loss": 0.5038, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.7649769185272268, "learning_rate": 3.834226623174705e-05, "loss": 0.5193, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.6640534996201588, "learning_rate": 3.831964887155264e-05, "loss": 0.5424, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6752206237805792, "learning_rate": 3.829688502793403e-05, "loss": 0.5197, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5823765654775982, "learning_rate": 3.827397488291029e-05, "loss": 0.51, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.7804075666182979, "learning_rate": 3.8250918619670343e-05, "loss": 0.5095, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.6300150476224112, "learning_rate": 3.822771642257145e-05, "loss": 0.5341, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.7689174229835268, "learning_rate": 3.820436847713776e-05, "loss": 0.5216, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.6339590644541069, "learning_rate": 3.8180874970058826e-05, "loss": 0.5053, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.7018021665834273, "learning_rate": 3.8157236089188103e-05, "loss": 0.5481, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.7430793396915135, "learning_rate": 3.813345202354145e-05, "loss": 0.5239, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6839166235008501, "learning_rate": 3.810952296329563e-05, "loss": 0.5684, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.7801501853320245, "learning_rate": 3.808544909978676e-05, "loss": 0.5052, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.7602625661190782, "learning_rate": 3.806123062550882e-05, "loss": 0.5152, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.7396791733031446, "learning_rate": 3.803686773411208e-05, "loss": 0.5436, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.7870078225130587, "learning_rate": 3.801236062040158e-05, "loss": 0.556, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.6818962485737703, "learning_rate": 3.798770948033553e-05, "loss": 0.5476, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.623911941045672, "learning_rate": 3.796291451102381e-05, "loss": 0.5225, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6359829385084218, "learning_rate": 3.793797591072631e-05, "loss": 0.5256, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.7320422330224942, "learning_rate": 3.791289387885144e-05, "loss": 0.5664, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.6822547795817898, "learning_rate": 3.788766861595443e-05, "loss": 0.5182, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.7081653071786916, "learning_rate": 3.7862300323735835e-05, "loss": 0.5317, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.7085981001212123, "learning_rate": 3.783678920503983e-05, "loss": 0.5175, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.6614874096686921, "learning_rate": 3.781113546385265e-05, "loss": 0.5048, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.7121254516495977, "learning_rate": 3.7785339305300916e-05, "loss": 0.5298, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6162235566013169, "learning_rate": 3.7759400935650025e-05, "loss": 0.5338, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.7172991857816773, "learning_rate": 3.77333205623025e-05, "loss": 0.5183, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.7071963847205278, "learning_rate": 3.7707098393796295e-05, "loss": 0.5413, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.6625494594008674, "learning_rate": 3.7680734639803185e-05, "loss": 0.5222, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.7927577586391457, "learning_rate": 3.765422951112704e-05, "loss": 0.5196, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.7580924998275257, "learning_rate": 3.762758321970216e-05, "loss": 0.5305, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.6616838437494079, "learning_rate": 3.7600795978591584e-05, "loss": 0.5268, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.6393581265462479, "learning_rate": 3.757386800198538e-05, "loss": 0.5147, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.7256458080488165, "learning_rate": 3.7546799505198925e-05, "loss": 0.5451, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.599641369003468, "learning_rate": 3.7519590704671197e-05, "loss": 0.5129, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5810093456248244, "learning_rate": 3.749224181796305e-05, "loss": 0.5172, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.6526148967242799, "learning_rate": 3.746475306375545e-05, "loss": 0.5495, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.623882331153199, "learning_rate": 3.743712466184774e-05, "loss": 0.5391, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.6139695428611707, "learning_rate": 3.7409356833155885e-05, "loss": 0.5211, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.604402869898663, "learning_rate": 3.73814497997107e-05, "loss": 0.5481, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.5624165463788785, "learning_rate": 3.7353403784656095e-05, "loss": 0.5283, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5471203607953365, "learning_rate": 3.732521901224724e-05, "loss": 0.5274, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6090345769597764, "learning_rate": 3.7296895707848844e-05, "loss": 0.5436, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.6406993872043024, "learning_rate": 3.7268434097933275e-05, "loss": 0.5176, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.6266465014943312, "learning_rate": 3.723983441007882e-05, "loss": 0.5467, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.6083414346579429, "learning_rate": 3.721109687296781e-05, "loss": 0.5433, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.722637408415419, "learning_rate": 3.718222171638484e-05, "loss": 0.5366, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.6137847439755949, "learning_rate": 3.715320917121488e-05, "loss": 0.5417, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.6122509730864788, "learning_rate": 3.712405946944149e-05, "loss": 0.5259, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.5788921156890839, "learning_rate": 3.709477284414488e-05, "loss": 0.5329, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.6530622556020588, "learning_rate": 3.7065349529500136e-05, "loss": 0.5261, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.6777412440505384, "learning_rate": 3.7035789760775305e-05, "loss": 0.5082, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.6773333253566755, "learning_rate": 3.70060937743295e-05, "loss": 0.5014, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.6659696229401596, "learning_rate": 3.6976261807611045e-05, "loss": 0.5281, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.8076336511101275, "learning_rate": 3.694629409915555e-05, "loss": 0.5345, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6102669945115623, "learning_rate": 3.691619088858401e-05, "loss": 0.5321, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.733905798320624, "learning_rate": 3.68859524166009e-05, "loss": 0.5118, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.6683499274709993, "learning_rate": 3.6855578924992226e-05, "loss": 0.5313, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.6876156324203561, "learning_rate": 3.6825070656623626e-05, "loss": 0.5195, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.6526306703671276, "learning_rate": 3.67944278554384e-05, "loss": 0.5315, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.6691239693940889, "learning_rate": 3.676365076645557e-05, "loss": 0.5353, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.7765152516209141, "learning_rate": 3.673273963576791e-05, "loss": 0.5126, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6324138860889217, "learning_rate": 3.670169471054001e-05, "loss": 0.5404, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.7258198922920748, "learning_rate": 3.6670516239006254e-05, "loss": 0.4979, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.656973625761326, "learning_rate": 3.663920447046888e-05, "loss": 0.5234, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.7528529304236594, "learning_rate": 3.6607759655295954e-05, "loss": 0.5268, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.6361317254833092, "learning_rate": 3.657618204491937e-05, "loss": 0.5246, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.7066803689727427, "learning_rate": 3.6544471891832875e-05, "loss": 0.5461, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.6160463032125189, "learning_rate": 3.6512629449589983e-05, "loss": 0.5012, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.6219032040011402, "learning_rate": 3.6480654972802045e-05, "loss": 0.5325, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5988053209658053, "learning_rate": 3.644854871713611e-05, "loss": 0.5505, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.5835687891728812, "learning_rate": 3.6416310939312924e-05, "loss": 0.509, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.7089147344671378, "learning_rate": 3.638394189710493e-05, "loss": 0.5273, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.6012888157698852, "learning_rate": 3.635144184933412e-05, "loss": 0.5481, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.69369838292736, "learning_rate": 3.6318811055869994e-05, "loss": 0.53, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.6374606086253978, "learning_rate": 3.628604977762752e-05, "loss": 0.5278, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.6214982424345575, "learning_rate": 3.6253158276565004e-05, "loss": 0.5339, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.6856792115440937, "learning_rate": 3.6220136815682016e-05, "loss": 0.5296, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.594711575024524, "learning_rate": 3.618698565901727e-05, "loss": 0.5093, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.5867941721965445, "learning_rate": 3.615370507164654e-05, "loss": 0.5204, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.6377279932659109, "learning_rate": 3.61202953196805e-05, "loss": 0.5254, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5716978641813245, "learning_rate": 3.6086756670262654e-05, "loss": 0.537, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.5823237927419597, "learning_rate": 3.6053089391567135e-05, "loss": 0.5413, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.6729504224842892, "learning_rate": 3.601929375279662e-05, "loss": 0.5281, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.652302299083827, "learning_rate": 3.598537002418012e-05, "loss": 0.5346, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.6140236338273932, "learning_rate": 3.5951318476970885e-05, "loss": 0.5374, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.6124583116549397, "learning_rate": 3.591713938344416e-05, "loss": 0.5176, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.6610579588420917, "learning_rate": 3.588283301689507e-05, "loss": 0.522, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.5534209708982859, "learning_rate": 3.5848399651636424e-05, "loss": 0.5289, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.6194666371274304, "learning_rate": 3.5813839562996473e-05, "loss": 0.5422, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5794932459932489, "learning_rate": 3.5779153027316775e-05, "loss": 0.5159, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.6001667526881548, "learning_rate": 3.574434032194994e-05, "loss": 0.549, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.6104638421949645, "learning_rate": 3.5709401725257436e-05, "loss": 0.5157, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.5467260163512961, "learning_rate": 3.5674337516607346e-05, "loss": 0.5245, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.6051077050823367, "learning_rate": 3.563914797637216e-05, "loss": 0.5324, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.5788834412969202, "learning_rate": 3.560383338592649e-05, "loss": 0.5402, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5489228846889389, "learning_rate": 3.556839402764487e-05, "loss": 0.543, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.5985262037427298, "learning_rate": 3.553283018489946e-05, "loss": 0.541, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5815042825131398, "learning_rate": 3.54971421420578e-05, "loss": 0.5216, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5923540843747548, "learning_rate": 3.5461330184480524e-05, "loss": 0.5381, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.6101006933606852, "learning_rate": 3.54253945985191e-05, "loss": 0.5051, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.5882451324011925, "learning_rate": 3.5389335671513524e-05, "loss": 0.5137, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.5695717875729274, "learning_rate": 3.5353153691789986e-05, "loss": 0.5265, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.6879767939217664, "learning_rate": 3.531684894865866e-05, "loss": 0.5341, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5873025531276886, "learning_rate": 3.528042173241128e-05, "loss": 0.5375, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.7030178820893247, "learning_rate": 3.524387233431892e-05, "loss": 0.5383, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.6643274448456234, "learning_rate": 3.520720104662958e-05, "loss": 0.5509, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.6392741932644332, "learning_rate": 3.5170408162565904e-05, "loss": 0.5368, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.7078185138964181, "learning_rate": 3.513349397632281e-05, "loss": 0.5191, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.6651257367155959, "learning_rate": 3.5096458783065145e-05, "loss": 0.5449, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.7040197762158421, "learning_rate": 3.505930287892533e-05, "loss": 0.5109, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.6145301307161043, "learning_rate": 3.502202656100099e-05, "loss": 0.5484, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.6921324271983895, "learning_rate": 3.498463012735256e-05, "loss": 0.5678, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.6575232114076228, "learning_rate": 3.494711387700094e-05, "loss": 0.5603, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.6994552553284334, "learning_rate": 3.490947810992505e-05, "loss": 0.5184, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.8325616350720443, "learning_rate": 3.48717231270595e-05, "loss": 0.5322, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.6803735635928142, "learning_rate": 3.483384923029211e-05, "loss": 0.5277, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.8516699727266813, "learning_rate": 3.479585672246156e-05, "loss": 0.5296, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.647447843456564, "learning_rate": 3.4757745907354924e-05, "loss": 0.5573, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.6715777407188551, "learning_rate": 3.471951708970527e-05, "loss": 0.5221, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.6063843707376345, "learning_rate": 3.468117057518921e-05, "loss": 0.5444, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.6078175152265067, "learning_rate": 3.4642706670424426e-05, "loss": 0.5328, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.550153899328264, "learning_rate": 3.460412568296731e-05, "loss": 0.5142, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.6377922708276933, "learning_rate": 3.456542792131039e-05, "loss": 0.5314, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.6702787620784393, "learning_rate": 3.4526613694879936e-05, "loss": 0.5338, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.6043724783186759, "learning_rate": 3.448768331403348e-05, "loss": 0.559, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.6571944477508626, "learning_rate": 3.44486370900573e-05, "loss": 0.5423, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.5766462785105411, "learning_rate": 3.440947533516396e-05, "loss": 0.5571, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.6128895162839355, "learning_rate": 3.4370198362489816e-05, "loss": 0.5148, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.6508531022718609, "learning_rate": 3.43308064860925e-05, "loss": 0.5301, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.6176433133792352, "learning_rate": 3.4291300020948393e-05, "loss": 0.552, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.6696690397798402, "learning_rate": 3.425167928295015e-05, "loss": 0.5409, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.6144949007813604, "learning_rate": 3.421194458890411e-05, "loss": 0.5527, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.7517806228372966, "learning_rate": 3.4172096256527865e-05, "loss": 0.5272, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5126868147654445, "learning_rate": 3.4132134604447595e-05, "loss": 0.5231, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.6482034339863253, "learning_rate": 3.409205995219561e-05, "loss": 0.522, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.563021831857288, "learning_rate": 3.4051872620207765e-05, "loss": 0.5319, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.5592972863901554, "learning_rate": 3.40115729298209e-05, "loss": 0.5456, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.5778358932444784, "learning_rate": 3.397116120327025e-05, "loss": 0.5172, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.5252489783090837, "learning_rate": 3.3930637763686916e-05, "loss": 0.5352, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.6043467673017621, "learning_rate": 3.389000293509524e-05, "loss": 0.5408, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5716040387626918, "learning_rate": 3.3849257042410225e-05, "loss": 0.5356, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5718734082886112, "learning_rate": 3.380840041143494e-05, "loss": 0.5143, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.5360189915443374, "learning_rate": 3.376743336885792e-05, "loss": 0.527, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.6182358286223409, "learning_rate": 3.372635624225055e-05, "loss": 0.5551, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.5506548626282562, "learning_rate": 3.3685169360064445e-05, "loss": 0.5453, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.6107750715323886, "learning_rate": 3.3643873051628804e-05, "loss": 0.5281, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.6045854404380002, "learning_rate": 3.3602467647147814e-05, "loss": 0.5209, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.5732971911584241, "learning_rate": 3.356095347769799e-05, "loss": 0.5122, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.570793661860563, "learning_rate": 3.351933087522552e-05, "loss": 0.5215, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.6940930459289444, "learning_rate": 3.3477600172543626e-05, "loss": 0.5296, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.559463076255443, "learning_rate": 3.3435761703329894e-05, "loss": 0.5327, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.6135521655480165, "learning_rate": 3.3393815802123606e-05, "loss": 0.5556, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.6008244860349252, "learning_rate": 3.335176280432308e-05, "loss": 0.545, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.6169440806806187, "learning_rate": 3.330960304618295e-05, "loss": 0.5497, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.6685123062494358, "learning_rate": 3.326733686481153e-05, "loss": 0.5478, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.7071595198224563, "learning_rate": 3.3224964598168084e-05, "loss": 0.5547, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.7705173153616546, "learning_rate": 3.318248658506012e-05, "loss": 0.5318, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.688052672457196, "learning_rate": 3.313990316514069e-05, "loss": 0.5066, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.7517573381554166, "learning_rate": 3.309721467890571e-05, "loss": 0.5291, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.6556792275391402, "learning_rate": 3.305442146769115e-05, "loss": 0.5334, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.6860371126171132, "learning_rate": 3.30115238736704e-05, "loss": 0.5396, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.6311525730369751, "learning_rate": 3.296852223985148e-05, "loss": 0.5469, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.7080588503422912, "learning_rate": 3.2925416910074315e-05, "loss": 0.5342, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.6267590458505319, "learning_rate": 3.288220822900796e-05, "loss": 0.5318, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.6224697056075468, "learning_rate": 3.283889654214788e-05, "loss": 0.5179, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.7405839211054104, "learning_rate": 3.279548219581317e-05, "loss": 0.538, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.60062480622906, "learning_rate": 3.275196553714379e-05, "loss": 0.5474, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.5992703354346884, "learning_rate": 3.270834691409778e-05, "loss": 0.5193, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.6763011095565484, "learning_rate": 3.266462667544849e-05, "loss": 0.5221, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.530374680188966, "learning_rate": 3.262080517078178e-05, "loss": 0.5371, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.6311375331573383, "learning_rate": 3.257688275049323e-05, "loss": 0.5375, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.56280946497409, "learning_rate": 3.253285976578535e-05, "loss": 0.5351, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.556511516031865, "learning_rate": 3.2488736568664756e-05, "loss": 0.5293, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.6056719183251374, "learning_rate": 3.244451351193935e-05, "loss": 0.5597, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.5739533001383411, "learning_rate": 3.240019094921551e-05, "loss": 0.5072, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.565349918643837, "learning_rate": 3.235576923489527e-05, "loss": 0.533, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.5646902320426321, "learning_rate": 3.2311248724173476e-05, "loss": 0.5495, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5843220392918449, "learning_rate": 3.226662977303494e-05, "loss": 0.5324, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.606093886230053, "learning_rate": 3.2221912738251626e-05, "loss": 0.5463, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.5513620663507773, "learning_rate": 3.2177097977379736e-05, "loss": 0.5491, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.5846209901045546, "learning_rate": 3.21321858487569e-05, "loss": 0.5303, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.573339941981363, "learning_rate": 3.208717671149931e-05, "loss": 0.5098, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.5475708379338693, "learning_rate": 3.204207092549882e-05, "loss": 0.5299, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.618306180605629, "learning_rate": 3.19968688514201e-05, "loss": 0.5239, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.6046552007602204, "learning_rate": 3.195157085069774e-05, "loss": 0.5327, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.5290706752599156, "learning_rate": 3.190617728553332e-05, "loss": 0.5536, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.6098373387055225, "learning_rate": 3.1860688518892606e-05, "loss": 0.5524, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.5350589652497721, "learning_rate": 3.181510491450254e-05, "loss": 0.5433, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.6349148418438577, "learning_rate": 3.176942683684842e-05, "loss": 0.5522, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.5729216159460156, "learning_rate": 3.1723654651170934e-05, "loss": 0.5434, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.5293255778259038, "learning_rate": 3.167778872346327e-05, "loss": 0.5229, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.5963951463128808, "learning_rate": 3.163182942046815e-05, "loss": 0.5117, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.6279740841558932, "learning_rate": 3.158577710967494e-05, "loss": 0.538, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.5321871849927238, "learning_rate": 3.153963215931669e-05, "loss": 0.5239, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.6343810339737647, "learning_rate": 3.14933949383672e-05, "loss": 0.5269, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.5358697136231547, "learning_rate": 3.144706581653805e-05, "loss": 0.5161, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.5978800040677577, "learning_rate": 3.140064516427566e-05, "loss": 0.5187, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.6156373857648589, "learning_rate": 3.135413335275833e-05, "loss": 0.5394, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.5753157189489878, "learning_rate": 3.130753075389327e-05, "loss": 0.5427, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.526429143037595, "learning_rate": 3.1260837740313625e-05, "loss": 0.5295, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.5994904135484854, "learning_rate": 3.121405468537547e-05, "loss": 0.5356, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.5518347503215179, "learning_rate": 3.116718196315488e-05, "loss": 0.5402, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.5527785587490572, "learning_rate": 3.1120219948444894e-05, "loss": 0.5364, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.579890304605503, "learning_rate": 3.107316901675252e-05, "loss": 0.5509, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.5654112675035332, "learning_rate": 3.1026029544295745e-05, "loss": 0.5234, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.5234118546570086, "learning_rate": 3.097880190800057e-05, "loss": 0.5378, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.5552991663452111, "learning_rate": 3.093148648549788e-05, "loss": 0.515, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.5243037418713938, "learning_rate": 3.088408365512055e-05, "loss": 0.5283, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.5241674323360308, "learning_rate": 3.083659379590034e-05, "loss": 0.5267, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.516975798173691, "learning_rate": 3.0789017287564913e-05, "loss": 0.5034, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.5191899164312418, "learning_rate": 3.074135451053475e-05, "loss": 0.5326, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.529201173009504, "learning_rate": 3.069360584592015e-05, "loss": 0.5187, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.5788745743273508, "learning_rate": 3.064577167551816e-05, "loss": 0.5329, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.4749016338573348, "learning_rate": 3.059785238180953e-05, "loss": 0.5151, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.5599214540329618, "learning_rate": 3.054984834795566e-05, "loss": 0.5282, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.5250849058392344, "learning_rate": 3.0501759957795537e-05, "loss": 0.5279, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.5091579614781796, "learning_rate": 3.0453587595842627e-05, "loss": 0.4889, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.5615944789737569, "learning_rate": 3.0405331647281856e-05, "loss": 0.5424, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.47781324585768165, "learning_rate": 3.0356992497966508e-05, "loss": 0.5, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.5341884156105516, "learning_rate": 3.0308570534415137e-05, "loss": 0.5372, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.5723368156625396, "learning_rate": 3.0260066143808467e-05, "loss": 0.5233, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.5216372246042125, "learning_rate": 3.021147971398632e-05, "loss": 0.5272, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.5948666522287946, "learning_rate": 3.0162811633444478e-05, "loss": 0.5255, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.5457796810343587, "learning_rate": 3.0114062291331635e-05, "loss": 0.5465, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.5345788757531656, "learning_rate": 3.0065232077446217e-05, "loss": 0.525, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.5402483761001352, "learning_rate": 3.001632138223332e-05, "loss": 0.4903, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.8370540253467881, "learning_rate": 2.9967330596781565e-05, "loss": 0.3554, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.5723919809055511, "learning_rate": 2.9918260112819952e-05, "loss": 0.3281, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 1.1970633955568557, "learning_rate": 2.9869110322714778e-05, "loss": 0.3312, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.7183331402239959, "learning_rate": 2.9819881619466447e-05, "loss": 0.3211, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.5881181361707728, "learning_rate": 2.9770574396706364e-05, "loss": 0.3572, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.6809921581543961, "learning_rate": 2.972118904869376e-05, "loss": 0.324, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.6059545887270257, "learning_rate": 2.9671725970312563e-05, "loss": 0.3156, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.6015258547662944, "learning_rate": 2.9622185557068238e-05, "loss": 0.3519, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.629715898192647, "learning_rate": 2.95725682050846e-05, "loss": 0.3465, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.614218872836685, "learning_rate": 2.9522874311100684e-05, "loss": 0.3454, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.6048629369463657, "learning_rate": 2.9473104272467526e-05, "loss": 0.3202, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.5838091494702548, "learning_rate": 2.942325848714505e-05, "loss": 0.3556, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.576602975050897, "learning_rate": 2.9373337353698804e-05, "loss": 0.3406, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.540491264296789, "learning_rate": 2.932334127129686e-05, "loss": 0.3362, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.5421623317571762, "learning_rate": 2.9273270639706547e-05, "loss": 0.3195, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.5359252757463964, "learning_rate": 2.922312585929131e-05, "loss": 0.3174, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.5339144778910648, "learning_rate": 2.9172907331007478e-05, "loss": 0.3593, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.523135603014697, "learning_rate": 2.9122615456401053e-05, "loss": 0.3049, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.5614960814088049, "learning_rate": 2.9072250637604535e-05, "loss": 0.3346, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.49641263837078725, "learning_rate": 2.9021813277333667e-05, "loss": 0.3326, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.512017882624528, "learning_rate": 2.8971303778884244e-05, "loss": 0.328, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.5220760198711194, "learning_rate": 2.8920722546128863e-05, "loss": 0.334, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.5024154616987289, "learning_rate": 2.887006998351372e-05, "loss": 0.3342, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.515812441329668, "learning_rate": 2.881934649605535e-05, "loss": 0.3265, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.5246751935796083, "learning_rate": 2.8768552489337408e-05, "loss": 0.3431, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.5005350914659278, "learning_rate": 2.8717688369507425e-05, "loss": 0.3304, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.5275778884172317, "learning_rate": 2.8666754543273535e-05, "loss": 0.3333, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.525854841406369, "learning_rate": 2.8615751417901273e-05, "loss": 0.3216, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.5049679133606946, "learning_rate": 2.856467940121025e-05, "loss": 0.3417, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.5703160794225238, "learning_rate": 2.8513538901570964e-05, "loss": 0.3212, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.5322510488195569, "learning_rate": 2.846233032790149e-05, "loss": 0.3155, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.5473508492226393, "learning_rate": 2.84110540896642e-05, "loss": 0.3388, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.5687868049286398, "learning_rate": 2.8359710596862555e-05, "loss": 0.3154, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.5012680125163681, "learning_rate": 2.8308300260037734e-05, "loss": 0.3357, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.5091682947008935, "learning_rate": 2.8256823490265424e-05, "loss": 0.3321, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.49818713345656096, "learning_rate": 2.8205280699152515e-05, "loss": 0.3102, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.49555456304992057, "learning_rate": 2.8153672298833777e-05, "loss": 0.3297, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.5338312957692373, "learning_rate": 2.8101998701968615e-05, "loss": 0.3121, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.5254136520654095, "learning_rate": 2.805026032173773e-05, "loss": 0.3335, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.49743407427655234, "learning_rate": 2.7998457571839832e-05, "loss": 0.3243, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.5342824581940084, "learning_rate": 2.7946590866488322e-05, "loss": 0.3531, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.49538761511778595, "learning_rate": 2.7894660620408e-05, "loss": 0.3279, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.47031741237986624, "learning_rate": 2.784266724883173e-05, "loss": 0.3252, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.5183282101054323, "learning_rate": 2.7790611167497128e-05, "loss": 0.3198, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.4976174091003971, "learning_rate": 2.7738492792643224e-05, "loss": 0.3342, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.4954481627101152, "learning_rate": 2.768631254100716e-05, "loss": 0.3231, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.47345695361480344, "learning_rate": 2.7634070829820836e-05, "loss": 0.3418, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.48724256612299033, "learning_rate": 2.7581768076807592e-05, "loss": 0.3211, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.47883613157453825, "learning_rate": 2.7529404700178832e-05, "loss": 0.3418, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.4707033311913104, "learning_rate": 2.7476981118630735e-05, "loss": 0.3315, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.5123374309754372, "learning_rate": 2.742449775134085e-05, "loss": 0.3149, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.4630558550782716, "learning_rate": 2.7371955017964788e-05, "loss": 0.3282, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.47423845584547775, "learning_rate": 2.7319353338632845e-05, "loss": 0.331, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.4973777284331617, "learning_rate": 2.7266693133946645e-05, "loss": 0.3101, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.5208916144982474, "learning_rate": 2.7213974824975785e-05, "loss": 0.3319, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.47425934893488353, "learning_rate": 2.7161198833254464e-05, "loss": 0.3376, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.49761588010596186, "learning_rate": 2.7108365580778095e-05, "loss": 0.3376, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.4762520666635183, "learning_rate": 2.705547548999996e-05, "loss": 0.3351, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.46417629714477954, "learning_rate": 2.7002528983827817e-05, "loss": 0.3396, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.5004279465696304, "learning_rate": 2.6949526485620517e-05, "loss": 0.3205, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.5314821730259571, "learning_rate": 2.6896468419184623e-05, "loss": 0.3245, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.5266104243015365, "learning_rate": 2.6843355208771024e-05, "loss": 0.3063, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.5393398109680346, "learning_rate": 2.6790187279071536e-05, "loss": 0.3274, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4873216998527796, "learning_rate": 2.67369650552155e-05, "loss": 0.3467, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.5474491790667803, "learning_rate": 2.6683688962766407e-05, "loss": 0.3461, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.5387197893641015, "learning_rate": 2.6630359427718468e-05, "loss": 0.341, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.5403756006257261, "learning_rate": 2.6576976876493225e-05, "loss": 0.331, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.4717881661148858, "learning_rate": 2.652354173593614e-05, "loss": 0.3327, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.5511887463879174, "learning_rate": 2.647005443331317e-05, "loss": 0.3149, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.4715488717350994, "learning_rate": 2.6416515396307354e-05, "loss": 0.3105, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.5404220907074297, "learning_rate": 2.636292505301542e-05, "loss": 0.3586, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.46006475369634864, "learning_rate": 2.630928383194431e-05, "loss": 0.3301, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.5065496941376492, "learning_rate": 2.625559216200781e-05, "loss": 0.34, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5280978461115334, "learning_rate": 2.620185047252308e-05, "loss": 0.3095, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.49397184616732553, "learning_rate": 2.614805919320723e-05, "loss": 0.3248, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.5647176630120868, "learning_rate": 2.6094218754173895e-05, "loss": 0.3383, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.4846336912895961, "learning_rate": 2.60403295859298e-05, "loss": 0.3443, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.48834667016418554, "learning_rate": 2.5986392119371297e-05, "loss": 0.3328, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.4872744651448236, "learning_rate": 2.5932406785780928e-05, "loss": 0.3259, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.5087455060050856, "learning_rate": 2.5878374016823987e-05, "loss": 0.3286, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.49744872001367374, "learning_rate": 2.5824294244545045e-05, "loss": 0.3291, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.48084715081396967, "learning_rate": 2.577016790136453e-05, "loss": 0.3295, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.5159842401883064, "learning_rate": 2.5715995420075225e-05, "loss": 0.3365, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.49307487339045347, "learning_rate": 2.5661777233838864e-05, "loss": 0.3379, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.4986759192784846, "learning_rate": 2.5607513776182616e-05, "loss": 0.3211, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.48739704453825294, "learning_rate": 2.5553205480995633e-05, "loss": 0.3482, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.5683290056944069, "learning_rate": 2.5498852782525604e-05, "loss": 0.3056, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.4706729829811111, "learning_rate": 2.5444456115375252e-05, "loss": 0.3404, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.5254825228830048, "learning_rate": 2.539001591449889e-05, "loss": 0.3369, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.4572723888888725, "learning_rate": 2.53355326151989e-05, "loss": 0.337, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.48444081675400275, "learning_rate": 2.5281006653122288e-05, "loss": 0.3253, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.4611021576732986, "learning_rate": 2.5226438464257217e-05, "loss": 0.3529, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.4981132506086002, "learning_rate": 2.5171828484929447e-05, "loss": 0.345, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.49546471579963985, "learning_rate": 2.5117177151798934e-05, "loss": 0.3451, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.49681322900992286, "learning_rate": 2.506248490185627e-05, "loss": 0.3568, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.47030276008128863, "learning_rate": 2.500775217241923e-05, "loss": 0.3574, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4938102501175609, "learning_rate": 2.4952979401129266e-05, "loss": 0.3252, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.48044605996419143, "learning_rate": 2.4898167025948e-05, "loss": 0.345, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.5395586889680485, "learning_rate": 2.4843315485153703e-05, "loss": 0.3473, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.46234447716627336, "learning_rate": 2.4788425217337856e-05, "loss": 0.3626, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.5504330236499386, "learning_rate": 2.4733496661401572e-05, "loss": 0.3528, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.5077518637297062, "learning_rate": 2.4678530256552114e-05, "loss": 0.329, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.49579769302645055, "learning_rate": 2.46235264422994e-05, "loss": 0.3413, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.5294930103727967, "learning_rate": 2.4568485658452452e-05, "loss": 0.3278, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.5493066938745109, "learning_rate": 2.451340834511592e-05, "loss": 0.3247, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.5262766228730021, "learning_rate": 2.4458294942686528e-05, "loss": 0.3374, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.5657111734327022, "learning_rate": 2.440314589184958e-05, "loss": 0.3439, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.5500839702363732, "learning_rate": 2.434796163357541e-05, "loss": 0.3358, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.4916864478473294, "learning_rate": 2.429274260911588e-05, "loss": 0.3457, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.5533780895525882, "learning_rate": 2.423748926000084e-05, "loss": 0.3206, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.502955214398862, "learning_rate": 2.418220202803459e-05, "loss": 0.3332, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.4970638455809185, "learning_rate": 2.412688135529237e-05, "loss": 0.3327, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.4950029907678577, "learning_rate": 2.4071527684116807e-05, "loss": 0.3206, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.48958301971642637, "learning_rate": 2.4016141457114372e-05, "loss": 0.3377, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.5158837523758278, "learning_rate": 2.396072311715187e-05, "loss": 0.3243, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.5296618915974622, "learning_rate": 2.3905273107352863e-05, "loss": 0.332, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.4992757652321288, "learning_rate": 2.3849791871094157e-05, "loss": 0.3359, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.5592566183739585, "learning_rate": 2.379427985200223e-05, "loss": 0.3248, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.48133387023199853, "learning_rate": 2.373873749394972e-05, "loss": 0.3407, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.546697203713786, "learning_rate": 2.3683165241051836e-05, "loss": 0.3279, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.5272129592951604, "learning_rate": 2.3627563537662823e-05, "loss": 0.3331, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.5154241291304232, "learning_rate": 2.3571932828372433e-05, "loss": 0.3315, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.5141216589563646, "learning_rate": 2.351627355800233e-05, "loss": 0.3317, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.47953054299849385, "learning_rate": 2.346058617160256e-05, "loss": 0.3318, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.481872097177863, "learning_rate": 2.3404871114447976e-05, "loss": 0.3209, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.49342460631103663, "learning_rate": 2.334912883203469e-05, "loss": 0.3162, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.48261009892499757, "learning_rate": 2.3293359770076505e-05, "loss": 0.347, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.5187859767166771, "learning_rate": 2.323756437450136e-05, "loss": 0.3513, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.4747172213456704, "learning_rate": 2.3181743091447754e-05, "loss": 0.3493, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.4473569575354934, "learning_rate": 2.3125896367261164e-05, "loss": 0.3426, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.524780246849897, "learning_rate": 2.307002464849052e-05, "loss": 0.3507, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.49458835592226386, "learning_rate": 2.30141283818846e-05, "loss": 0.3446, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.48317553800160473, "learning_rate": 2.2958208014388462e-05, "loss": 0.3164, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.503742168168242, "learning_rate": 2.2902263993139857e-05, "loss": 0.3338, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.4728144786832284, "learning_rate": 2.2846296765465708e-05, "loss": 0.3449, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.470524663794513, "learning_rate": 2.2790306778878465e-05, "loss": 0.3505, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.46941250169382004, "learning_rate": 2.273429448107257e-05, "loss": 0.3591, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.5077552370919319, "learning_rate": 2.2678260319920868e-05, "loss": 0.3191, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.4716855682377734, "learning_rate": 2.262220474347102e-05, "loss": 0.3192, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.5062901102714612, "learning_rate": 2.2566128199941918e-05, "loss": 0.3296, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.511963698471579, "learning_rate": 2.2510031137720104e-05, "loss": 0.3503, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.4637712009062845, "learning_rate": 2.2453914005356206e-05, "loss": 0.2939, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.5115287809164624, "learning_rate": 2.2397777251561302e-05, "loss": 0.3284, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.4599731370475623, "learning_rate": 2.2341621325203393e-05, "loss": 0.3283, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.49225959487481874, "learning_rate": 2.2285446675303764e-05, "loss": 0.3128, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.469300765446498, "learning_rate": 2.2229253751033423e-05, "loss": 0.344, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.49947537398097497, "learning_rate": 2.2173043001709492e-05, "loss": 0.3417, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.4950022423549299, "learning_rate": 2.2116814876791627e-05, "loss": 0.3522, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.4760294984149365, "learning_rate": 2.2060569825878413e-05, "loss": 0.3439, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.5145243861805093, "learning_rate": 2.2004308298703777e-05, "loss": 0.3277, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.5052880502118302, "learning_rate": 2.1948030745133396e-05, "loss": 0.32, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.5001708363356894, "learning_rate": 2.1891737615161083e-05, "loss": 0.3567, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.4876675001881101, "learning_rate": 2.1835429358905218e-05, "loss": 0.3355, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.4587965972727132, "learning_rate": 2.17791064266051e-05, "loss": 0.3491, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.49586474470097575, "learning_rate": 2.172276926861741e-05, "loss": 0.3272, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.4837478605962673, "learning_rate": 2.166641833541255e-05, "loss": 0.3443, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.4957320447098207, "learning_rate": 2.161005407757109e-05, "loss": 0.3167, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.45088865757974705, "learning_rate": 2.155367694578013e-05, "loss": 0.3309, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.46451699203597235, "learning_rate": 2.1497287390829712e-05, "loss": 0.3569, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.4646378044402168, "learning_rate": 2.1440885863609208e-05, "loss": 0.3238, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.5191775527216521, "learning_rate": 2.1384472815103737e-05, "loss": 0.3324, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.45465349589867093, "learning_rate": 2.1328048696390534e-05, "loss": 0.3347, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.443469501922114, "learning_rate": 2.1271613958635342e-05, "loss": 0.3231, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.5077820624637123, "learning_rate": 2.1215169053088825e-05, "loss": 0.323, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.4580855066732975, "learning_rate": 2.1158714431082937e-05, "loss": 0.3764, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.47162859130123364, "learning_rate": 2.110225054402733e-05, "loss": 0.3263, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.5000216215613755, "learning_rate": 2.1045777843405747e-05, "loss": 0.3332, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.4783023896063614, "learning_rate": 2.09892967807724e-05, "loss": 0.3382, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.4827737932582892, "learning_rate": 2.093280780774835e-05, "loss": 0.3455, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.47500773231434035, "learning_rate": 2.087631137601793e-05, "loss": 0.3182, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.5216100983438419, "learning_rate": 2.0819807937325104e-05, "loss": 0.3479, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.48929652850646, "learning_rate": 2.0763297943469847e-05, "loss": 0.3313, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.4716787260621783, "learning_rate": 2.070678184630458e-05, "loss": 0.3375, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.4975891624583721, "learning_rate": 2.06502600977305e-05, "loss": 0.3326, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.49604849169816906, "learning_rate": 2.0593733149694008e-05, "loss": 0.338, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.5046023258601783, "learning_rate": 2.0537201454183074e-05, "loss": 0.3409, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.5201910010301043, "learning_rate": 2.0480665463223626e-05, "loss": 0.3396, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.49817381238618996, "learning_rate": 2.042412562887594e-05, "loss": 0.3326, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.4792931266084221, "learning_rate": 2.0367582403231033e-05, "loss": 0.3329, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.4823255728165161, "learning_rate": 2.0311036238407023e-05, "loss": 0.3482, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.4704074437732296, "learning_rate": 2.0254487586545534e-05, "loss": 0.3121, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.47940745431004245, "learning_rate": 2.0197936899808088e-05, "loss": 0.3354, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.5252619600277885, "learning_rate": 2.0141384630372466e-05, "loss": 0.3265, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.4936324872118898, "learning_rate": 2.0084831230429106e-05, "loss": 0.3236, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.5055680356709664, "learning_rate": 2.0028277152177492e-05, "loss": 0.3463, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.5046800226549845, "learning_rate": 1.9971722847822518e-05, "loss": 0.331, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.4857605567726913, "learning_rate": 1.99151687695709e-05, "loss": 0.3205, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.5163077441301966, "learning_rate": 1.9858615369627537e-05, "loss": 0.3312, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.4721496886525335, "learning_rate": 1.9802063100191916e-05, "loss": 0.338, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.4829118850180982, "learning_rate": 1.974551241345447e-05, "loss": 0.3253, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.5073774138863909, "learning_rate": 1.9688963761592984e-05, "loss": 0.3386, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.5119020316128142, "learning_rate": 1.963241759676897e-05, "loss": 0.3419, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.49671460645547727, "learning_rate": 1.9575874371124066e-05, "loss": 0.3431, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.4914797873177092, "learning_rate": 1.951933453677638e-05, "loss": 0.3133, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.4780383461802953, "learning_rate": 1.9462798545816932e-05, "loss": 0.3583, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.506757074741534, "learning_rate": 1.9406266850305996e-05, "loss": 0.3386, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.4990148636301147, "learning_rate": 1.9349739902269503e-05, "loss": 0.3488, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.46476408553669046, "learning_rate": 1.9293218153695425e-05, "loss": 0.3243, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.5172416784282152, "learning_rate": 1.9236702056530153e-05, "loss": 0.3235, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.49669202718855887, "learning_rate": 1.9180192062674907e-05, "loss": 0.3392, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.48238125637161366, "learning_rate": 1.9123688623982076e-05, "loss": 0.3322, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.45539648114587483, "learning_rate": 1.906719219225165e-05, "loss": 0.3105, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.46193725725843393, "learning_rate": 1.9010703219227603e-05, "loss": 0.3268, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.46625023738898613, "learning_rate": 1.8954222156594256e-05, "loss": 0.3189, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.45878882855276654, "learning_rate": 1.8897749455972673e-05, "loss": 0.3401, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.4491517876406701, "learning_rate": 1.884128556891707e-05, "loss": 0.3009, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.4703009311327303, "learning_rate": 1.878483094691119e-05, "loss": 0.3282, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.467158164321104, "learning_rate": 1.8728386041364664e-05, "loss": 0.315, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.4496902950737971, "learning_rate": 1.867195130360947e-05, "loss": 0.3465, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.4609736068925936, "learning_rate": 1.8615527184896263e-05, "loss": 0.3301, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.44281959561321105, "learning_rate": 1.8559114136390795e-05, "loss": 0.3327, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.4451568336822499, "learning_rate": 1.8502712609170298e-05, "loss": 0.3579, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.44949502555677034, "learning_rate": 1.8446323054219876e-05, "loss": 0.3387, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.4361265763358363, "learning_rate": 1.838994592242891e-05, "loss": 0.3133, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.4749961801617851, "learning_rate": 1.8333581664587453e-05, "loss": 0.3199, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.48382242396920255, "learning_rate": 1.8277230731382593e-05, "loss": 0.3382, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.4625439419945996, "learning_rate": 1.82208935733949e-05, "loss": 0.3251, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.5039899775040781, "learning_rate": 1.8164570641094793e-05, "loss": 0.3088, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.49163498187190613, "learning_rate": 1.810826238483892e-05, "loss": 0.3333, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.46614329026786805, "learning_rate": 1.8051969254866608e-05, "loss": 0.349, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.49661899652478064, "learning_rate": 1.7995691701296226e-05, "loss": 0.3205, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.4749817508013223, "learning_rate": 1.7939430174121593e-05, "loss": 0.3355, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.4366425573244486, "learning_rate": 1.788318512320838e-05, "loss": 0.3364, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.5145276608580025, "learning_rate": 1.782695699829051e-05, "loss": 0.3143, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.4961381981364813, "learning_rate": 1.7770746248966587e-05, "loss": 0.311, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.45046579745436477, "learning_rate": 1.7714553324696243e-05, "loss": 0.3285, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.4582630958555004, "learning_rate": 1.7658378674796614e-05, "loss": 0.3116, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.48668717255708355, "learning_rate": 1.76022227484387e-05, "loss": 0.3364, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.5030684118917551, "learning_rate": 1.7546085994643807e-05, "loss": 0.3177, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.4473891920649738, "learning_rate": 1.7489968862279902e-05, "loss": 0.3438, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.47231673487461984, "learning_rate": 1.743387180005809e-05, "loss": 0.3206, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.4577505616930684, "learning_rate": 1.737779525652899e-05, "loss": 0.3034, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.45806427464894234, "learning_rate": 1.732173968007914e-05, "loss": 0.331, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.4560244954964555, "learning_rate": 1.7265705518927437e-05, "loss": 0.3036, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.4516699986677799, "learning_rate": 1.7209693221121542e-05, "loss": 0.3384, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.46872276558524867, "learning_rate": 1.7153703234534302e-05, "loss": 0.343, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.4629522428824425, "learning_rate": 1.709773600686015e-05, "loss": 0.3258, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.4739969621276263, "learning_rate": 1.7041791985611548e-05, "loss": 0.3357, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.43895125282528263, "learning_rate": 1.69858716181154e-05, "loss": 0.3266, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.46287698633579377, "learning_rate": 1.692997535150948e-05, "loss": 0.3399, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.4515921149263306, "learning_rate": 1.687410363273884e-05, "loss": 0.3312, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.4669820607485952, "learning_rate": 1.6818256908552257e-05, "loss": 0.3317, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.44071265412172295, "learning_rate": 1.6762435625498646e-05, "loss": 0.3561, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.43781017203867445, "learning_rate": 1.67066402299235e-05, "loss": 0.3278, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.45361876297894377, "learning_rate": 1.6650871167965313e-05, "loss": 0.328, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.48081892980711227, "learning_rate": 1.6595128885552028e-05, "loss": 0.3299, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.4269455807711529, "learning_rate": 1.653941382839745e-05, "loss": 0.3123, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.6297055479424422, "learning_rate": 1.6483726441997673e-05, "loss": 0.2153, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.46839605924264455, "learning_rate": 1.642806717162757e-05, "loss": 0.1831, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.4159941997931357, "learning_rate": 1.637243646233718e-05, "loss": 0.2006, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.7261156876305139, "learning_rate": 1.6316834758948174e-05, "loss": 0.2227, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.6438692266084866, "learning_rate": 1.6261262506050282e-05, "loss": 0.2072, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4821239553244664, "learning_rate": 1.620572014799777e-05, "loss": 0.2079, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.5231933782468665, "learning_rate": 1.6150208128905857e-05, "loss": 0.1954, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.5200285249260065, "learning_rate": 1.6094726892647147e-05, "loss": 0.1968, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.47079285396825854, "learning_rate": 1.6039276882848135e-05, "loss": 0.2225, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.41652451026170223, "learning_rate": 1.5983858542885635e-05, "loss": 0.187, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.45066807824611815, "learning_rate": 1.5928472315883203e-05, "loss": 0.2046, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.4539849927818501, "learning_rate": 1.5873118644707633e-05, "loss": 0.1838, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.4424224847637963, "learning_rate": 1.5817797971965413e-05, "loss": 0.1801, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.4370779455155397, "learning_rate": 1.576251073999917e-05, "loss": 0.1957, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.4282708029036534, "learning_rate": 1.5707257390884126e-05, "loss": 0.1888, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.40646316817814426, "learning_rate": 1.5652038366424595e-05, "loss": 0.193, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.4256986108405515, "learning_rate": 1.5596854108150424e-05, "loss": 0.2075, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.41330823575576126, "learning_rate": 1.5541705057313476e-05, "loss": 0.2062, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3738881016902634, "learning_rate": 1.5486591654884086e-05, "loss": 0.2054, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3801992413699325, "learning_rate": 1.543151434154755e-05, "loss": 0.2156, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.4039300273538362, "learning_rate": 1.5376473557700615e-05, "loss": 0.2085, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.41267554700042397, "learning_rate": 1.5321469743447893e-05, "loss": 0.2218, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.3850283956361666, "learning_rate": 1.5266503338598434e-05, "loss": 0.2011, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3754805023385069, "learning_rate": 1.5211574782662149e-05, "loss": 0.1916, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.39116249282664195, "learning_rate": 1.5156684514846307e-05, "loss": 0.1601, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3932420672377604, "learning_rate": 1.5101832974052012e-05, "loss": 0.1955, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3721900464818656, "learning_rate": 1.5047020598870737e-05, "loss": 0.2122, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.3927394720309413, "learning_rate": 1.4992247827580778e-05, "loss": 0.1613, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.3841378462507044, "learning_rate": 1.493751509814374e-05, "loss": 0.2022, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.38280866878200037, "learning_rate": 1.4882822848201073e-05, "loss": 0.1706, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.38599532751719523, "learning_rate": 1.4828171515070553e-05, "loss": 0.1943, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.38734992966524745, "learning_rate": 1.4773561535742793e-05, "loss": 0.2154, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.38994660274230786, "learning_rate": 1.4718993346877715e-05, "loss": 0.1943, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.38531403057768654, "learning_rate": 1.466446738480111e-05, "loss": 0.194, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.37523619479884, "learning_rate": 1.460998408550112e-05, "loss": 0.1924, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3873906248806855, "learning_rate": 1.4555543884624751e-05, "loss": 0.1875, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.3845366445564327, "learning_rate": 1.4501147217474402e-05, "loss": 0.1805, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.3604571642295657, "learning_rate": 1.444679451900437e-05, "loss": 0.2131, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.38749385657893226, "learning_rate": 1.4392486223817397e-05, "loss": 0.1858, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.35149660953846595, "learning_rate": 1.4338222766161143e-05, "loss": 0.2055, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.3705637051557086, "learning_rate": 1.4284004579924777e-05, "loss": 0.2036, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.35140800713673, "learning_rate": 1.4229832098635479e-05, "loss": 0.2052, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.36751068634423706, "learning_rate": 1.4175705755454963e-05, "loss": 0.1949, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.37158770064236896, "learning_rate": 1.412162598317602e-05, "loss": 0.1955, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.3934323267094357, "learning_rate": 1.406759321421907e-05, "loss": 0.2082, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3798717634948698, "learning_rate": 1.401360788062871e-05, "loss": 0.2066, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.38530765405449563, "learning_rate": 1.3959670414070204e-05, "loss": 0.2084, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.3830424318728972, "learning_rate": 1.3905781245826108e-05, "loss": 0.2179, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.4046639583883586, "learning_rate": 1.3851940806792778e-05, "loss": 0.2076, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.38144019500310006, "learning_rate": 1.379814952747693e-05, "loss": 0.1686, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.3725318443414517, "learning_rate": 1.3744407837992193e-05, "loss": 0.2007, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.40563478063209774, "learning_rate": 1.3690716168055692e-05, "loss": 0.2034, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.38517450046425517, "learning_rate": 1.363707494698459e-05, "loss": 0.1974, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.3673068551856819, "learning_rate": 1.358348460369265e-05, "loss": 0.2003, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.3768649200498471, "learning_rate": 1.352994556668684e-05, "loss": 0.1975, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3773897605593575, "learning_rate": 1.3476458264063865e-05, "loss": 0.2003, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.37582300109861, "learning_rate": 1.342302312350678e-05, "loss": 0.1891, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3729993657499021, "learning_rate": 1.3369640572281537e-05, "loss": 0.2076, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.38817779781201045, "learning_rate": 1.3316311037233596e-05, "loss": 0.1925, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.3718672036808722, "learning_rate": 1.326303494478451e-05, "loss": 0.2056, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3678823908961312, "learning_rate": 1.3209812720928472e-05, "loss": 0.1827, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.37064254897889154, "learning_rate": 1.315664479122898e-05, "loss": 0.2245, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.3819270656656433, "learning_rate": 1.3103531580815378e-05, "loss": 0.1949, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.37399328045895375, "learning_rate": 1.3050473514379488e-05, "loss": 0.1896, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.36387718878597375, "learning_rate": 1.2997471016172188e-05, "loss": 0.2102, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.3757286444605972, "learning_rate": 1.2944524510000042e-05, "loss": 0.1983, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.3673150373605365, "learning_rate": 1.2891634419221908e-05, "loss": 0.239, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.37192002323391, "learning_rate": 1.2838801166745545e-05, "loss": 0.1939, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.36333664047884845, "learning_rate": 1.2786025175024216e-05, "loss": 0.1937, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.3709950079506895, "learning_rate": 1.2733306866053357e-05, "loss": 0.1999, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.36098012471372565, "learning_rate": 1.2680646661367163e-05, "loss": 0.2085, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.3730864411726241, "learning_rate": 1.2628044982035219e-05, "loss": 0.1912, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.384315105520461, "learning_rate": 1.2575502248659155e-05, "loss": 0.2169, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.3791119120528298, "learning_rate": 1.2523018881369269e-05, "loss": 0.2253, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.3611397711653572, "learning_rate": 1.2470595299821176e-05, "loss": 0.2261, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.3642687182946547, "learning_rate": 1.2418231923192416e-05, "loss": 0.2205, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.3647500482888314, "learning_rate": 1.2365929170179165e-05, "loss": 0.1996, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.3509065912134241, "learning_rate": 1.2313687458992848e-05, "loss": 0.1942, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.3601330803490684, "learning_rate": 1.2261507207356785e-05, "loss": 0.2132, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.372612526751339, "learning_rate": 1.220938883250288e-05, "loss": 0.2043, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.36109750412089164, "learning_rate": 1.215733275116827e-05, "loss": 0.1927, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.379598843520547, "learning_rate": 1.2105339379592005e-05, "loss": 0.181, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.3729522659887599, "learning_rate": 1.2053409133511681e-05, "loss": 0.204, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.3792320705644984, "learning_rate": 1.2001542428160173e-05, "loss": 0.1957, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.36137035929836236, "learning_rate": 1.1949739678262278e-05, "loss": 0.1924, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.3751669031045978, "learning_rate": 1.189800129803139e-05, "loss": 0.186, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3646698916982813, "learning_rate": 1.1846327701166228e-05, "loss": 0.2035, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.37820560645322665, "learning_rate": 1.1794719300847493e-05, "loss": 0.1865, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.36514744444771646, "learning_rate": 1.1743176509734582e-05, "loss": 0.217, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.3538536280484441, "learning_rate": 1.1691699739962275e-05, "loss": 0.1687, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.3688384227710825, "learning_rate": 1.1640289403137456e-05, "loss": 0.1822, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.3691436883266543, "learning_rate": 1.1588945910335802e-05, "loss": 0.1923, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.3606659187354787, "learning_rate": 1.1537669672098517e-05, "loss": 0.2001, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.3742262283905678, "learning_rate": 1.1486461098429036e-05, "loss": 0.1972, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.3577843560548615, "learning_rate": 1.1435320598789747e-05, "loss": 0.1896, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.3635941375321294, "learning_rate": 1.1384248582098736e-05, "loss": 0.1914, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.37638219631560227, "learning_rate": 1.1333245456726467e-05, "loss": 0.1742, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.37669870132389305, "learning_rate": 1.128231163049258e-05, "loss": 0.1946, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.36844316898295293, "learning_rate": 1.123144751066259e-05, "loss": 0.1924, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.3837551580232965, "learning_rate": 1.1180653503944657e-05, "loss": 0.1971, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.3696144570304401, "learning_rate": 1.1129930016486287e-05, "loss": 0.1818, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.3607518722138112, "learning_rate": 1.107927745387114e-05, "loss": 0.1749, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.3763356887620164, "learning_rate": 1.1028696221115766e-05, "loss": 0.2022, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.37072539461098986, "learning_rate": 1.0978186722666341e-05, "loss": 0.1923, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.37929314924413027, "learning_rate": 1.0927749362395475e-05, "loss": 0.194, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.37229519194012617, "learning_rate": 1.0877384543598954e-05, "loss": 0.2099, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.3708722357971854, "learning_rate": 1.0827092668992529e-05, "loss": 0.2187, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.3709895442582374, "learning_rate": 1.077687414070869e-05, "loss": 0.1962, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.3670823745600483, "learning_rate": 1.0726729360293451e-05, "loss": 0.1932, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.3669787573809928, "learning_rate": 1.0676658728703147e-05, "loss": 0.2039, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.3756912821064759, "learning_rate": 1.0626662646301198e-05, "loss": 0.198, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.37193065874143283, "learning_rate": 1.0576741512854958e-05, "loss": 0.1905, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.36415294264452314, "learning_rate": 1.052689572753247e-05, "loss": 0.1787, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.35166612434115824, "learning_rate": 1.0477125688899328e-05, "loss": 0.1786, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.3777099725422198, "learning_rate": 1.0427431794915406e-05, "loss": 0.2024, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.3837009935223371, "learning_rate": 1.0377814442931769e-05, "loss": 0.1976, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.37523033424943303, "learning_rate": 1.0328274029687439e-05, "loss": 0.2274, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.36208373146976447, "learning_rate": 1.0278810951306253e-05, "loss": 0.1788, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.35123013870452047, "learning_rate": 1.0229425603293647e-05, "loss": 0.2173, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.3799537798759065, "learning_rate": 1.0180118380533558e-05, "loss": 0.1936, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.3716963979357198, "learning_rate": 1.0130889677285225e-05, "loss": 0.2008, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.3680974398421337, "learning_rate": 1.008173988718005e-05, "loss": 0.1888, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.38304654972393787, "learning_rate": 1.0032669403218439e-05, "loss": 0.1938, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.3594783484833636, "learning_rate": 9.983678617766677e-06, "loss": 0.2, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.3573869647647205, "learning_rate": 9.934767922553788e-06, "loss": 0.2027, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.35993216567396824, "learning_rate": 9.885937708668371e-06, "loss": 0.2043, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.3738716070291188, "learning_rate": 9.837188366555524e-06, "loss": 0.1915, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.36059247736508665, "learning_rate": 9.788520286013691e-06, "loss": 0.1964, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.35731064252509265, "learning_rate": 9.739933856191537e-06, "loss": 0.1995, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.3587230520088784, "learning_rate": 9.691429465584866e-06, "loss": 0.1947, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.3590487907037134, "learning_rate": 9.643007502033492e-06, "loss": 0.1952, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.3588493714624752, "learning_rate": 9.594668352718152e-06, "loss": 0.2066, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.37420823030480715, "learning_rate": 9.546412404157383e-06, "loss": 0.1922, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.37132572522561247, "learning_rate": 9.498240042204471e-06, "loss": 0.2037, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.3535855594495089, "learning_rate": 9.450151652044339e-06, "loss": 0.1936, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.3651037283649901, "learning_rate": 9.402147618190472e-06, "loss": 0.1809, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.35938147744830534, "learning_rate": 9.354228324481841e-06, "loss": 0.2069, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.3505977962084287, "learning_rate": 9.306394154079852e-06, "loss": 0.2081, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.34743647232778724, "learning_rate": 9.258645489465254e-06, "loss": 0.2277, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.37747268611978396, "learning_rate": 9.21098271243509e-06, "loss": 0.2051, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.3663339304603016, "learning_rate": 9.163406204099659e-06, "loss": 0.1851, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.34362648673547075, "learning_rate": 9.115916344879452e-06, "loss": 0.2098, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.36109225753295304, "learning_rate": 9.068513514502126e-06, "loss": 0.2095, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.3456638089894803, "learning_rate": 9.021198091999439e-06, "loss": 0.1956, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.3712182825493914, "learning_rate": 8.973970455704251e-06, "loss": 0.1979, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.37928189560214615, "learning_rate": 8.926830983247495e-06, "loss": 0.1851, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.3499678653873567, "learning_rate": 8.879780051555116e-06, "loss": 0.2135, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.3769636601794443, "learning_rate": 8.83281803684512e-06, "loss": 0.2203, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.3580573645371336, "learning_rate": 8.785945314624532e-06, "loss": 0.1774, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.3603250471425499, "learning_rate": 8.739162259686385e-06, "loss": 0.1967, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.350534237064728, "learning_rate": 8.692469246106734e-06, "loss": 0.2047, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.3482256313390303, "learning_rate": 8.645866647241677e-06, "loss": 0.1929, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.3663748146044602, "learning_rate": 8.599354835724348e-06, "loss": 0.1972, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.3681713496113816, "learning_rate": 8.552934183461958e-06, "loss": 0.2129, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.36871920113515555, "learning_rate": 8.506605061632805e-06, "loss": 0.1776, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.3611158868985794, "learning_rate": 8.460367840683308e-06, "loss": 0.1934, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.3672954873287425, "learning_rate": 8.414222890325065e-06, "loss": 0.1933, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.36291676525979594, "learning_rate": 8.368170579531855e-06, "loss": 0.2095, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.37351719966240804, "learning_rate": 8.322211276536733e-06, "loss": 0.1895, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.3385772362073074, "learning_rate": 8.27634534882907e-06, "loss": 0.1819, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.35349682520195747, "learning_rate": 8.230573163151585e-06, "loss": 0.1771, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.3422378548454463, "learning_rate": 8.184895085497466e-06, "loss": 0.1893, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.36284233753151895, "learning_rate": 8.139311481107401e-06, "loss": 0.1756, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.36226888521460293, "learning_rate": 8.093822714466686e-06, "loss": 0.2028, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.35361260079338114, "learning_rate": 8.048429149302271e-06, "loss": 0.2214, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.3786476078095374, "learning_rate": 8.003131148579902e-06, "loss": 0.1764, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.3377045095077082, "learning_rate": 7.957929074501182e-06, "loss": 0.2067, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.35973176416537095, "learning_rate": 7.912823288500695e-06, "loss": 0.1874, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.35917758985019477, "learning_rate": 7.867814151243102e-06, "loss": 0.1966, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.36861787843960386, "learning_rate": 7.822902022620267e-06, "loss": 0.2039, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.34900905499461293, "learning_rate": 7.778087261748377e-06, "loss": 0.1905, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.3724316162383524, "learning_rate": 7.733370226965056e-06, "loss": 0.1768, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.3678341354072597, "learning_rate": 7.688751275826527e-06, "loss": 0.1904, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.35210040019159283, "learning_rate": 7.644230765104735e-06, "loss": 0.1996, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.3624031622957777, "learning_rate": 7.599809050784502e-06, "loss": 0.2092, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.3687338492757552, "learning_rate": 7.555486488060661e-06, "loss": 0.1804, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.3569451484913687, "learning_rate": 7.511263431335249e-06, "loss": 0.1762, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.3566983930296276, "learning_rate": 7.467140234214656e-06, "loss": 0.1971, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.3565395572971753, "learning_rate": 7.423117249506777e-06, "loss": 0.2036, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.3621774346599598, "learning_rate": 7.379194829218231e-06, "loss": 0.1812, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.34378960191250535, "learning_rate": 7.335373324551518e-06, "loss": 0.1816, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.3524133439253753, "learning_rate": 7.291653085902224e-06, "loss": 0.1813, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.3532167425466447, "learning_rate": 7.248034462856213e-06, "loss": 0.1988, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.3694427366477642, "learning_rate": 7.20451780418683e-06, "loss": 0.1975, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.35760724151254836, "learning_rate": 7.161103457852128e-06, "loss": 0.1954, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.3453907983133146, "learning_rate": 7.117791770992046e-06, "loss": 0.1808, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.35735286234203967, "learning_rate": 7.074583089925688e-06, "loss": 0.2102, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.3572580218216876, "learning_rate": 7.0314777601485155e-06, "loss": 0.2247, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.33914487541361876, "learning_rate": 6.988476126329604e-06, "loss": 0.1769, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.35529423127524873, "learning_rate": 6.945578532308857e-06, "loss": 0.1829, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.35907436485523786, "learning_rate": 6.902785321094301e-06, "loss": 0.1628, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.3660837293317618, "learning_rate": 6.8600968348593115e-06, "loss": 0.1879, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.3621486356045032, "learning_rate": 6.817513414939892e-06, "loss": 0.2096, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.3515662060253304, "learning_rate": 6.775035401831924e-06, "loss": 0.1988, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.35104022575657784, "learning_rate": 6.732663135188473e-06, "loss": 0.2171, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.3435681462841542, "learning_rate": 6.690396953817055e-06, "loss": 0.1912, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.3452355934758874, "learning_rate": 6.648237195676927e-06, "loss": 0.1902, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.35884598710754934, "learning_rate": 6.606184197876395e-06, "loss": 0.1847, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.3583093668975487, "learning_rate": 6.564238296670109e-06, "loss": 0.1765, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.3551925381815991, "learning_rate": 6.52239982745638e-06, "loss": 0.2167, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.35263104913974896, "learning_rate": 6.480669124774484e-06, "loss": 0.2197, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.3672941401320676, "learning_rate": 6.439046522302013e-06, "loss": 0.2073, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.3578227666983529, "learning_rate": 6.397532352852191e-06, "loss": 0.1868, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.365094143323376, "learning_rate": 6.356126948371202e-06, "loss": 0.1991, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.35099121458538507, "learning_rate": 6.314830639935559e-06, "loss": 0.2066, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.3614551932018863, "learning_rate": 6.273643757749448e-06, "loss": 0.1817, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.35714587183618834, "learning_rate": 6.2325666311420856e-06, "loss": 0.1898, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.34842145453751433, "learning_rate": 6.1915995885650675e-06, "loss": 0.2109, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.3601724104861907, "learning_rate": 6.150742957589784e-06, "loss": 0.1734, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.35171909571044735, "learning_rate": 6.109997064904774e-06, "loss": 0.2011, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.3602494565550743, "learning_rate": 6.069362236313092e-06, "loss": 0.1766, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.34719489762018974, "learning_rate": 6.0288387967297565e-06, "loss": 0.2052, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.3522979131032433, "learning_rate": 5.988427070179108e-06, "loss": 0.179, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.3557168460866029, "learning_rate": 5.948127379792234e-06, "loss": 0.1846, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.3613886861588536, "learning_rate": 5.90794004780439e-06, "loss": 0.1946, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.3514243003258766, "learning_rate": 5.867865395552405e-06, "loss": 0.2087, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.3436190808512137, "learning_rate": 5.8279037434721364e-06, "loss": 0.2093, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.3591363995545283, "learning_rate": 5.788055411095892e-06, "loss": 0.1971, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.355813241093957, "learning_rate": 5.7483207170498625e-06, "loss": 0.1923, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.3454158519557989, "learning_rate": 5.708699979051613e-06, "loss": 0.196, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.3552829842859885, "learning_rate": 5.66919351390751e-06, "loss": 0.1841, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.3395200288994955, "learning_rate": 5.629801637510188e-06, "loss": 0.19, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.34497074777620534, "learning_rate": 5.590524664836043e-06, "loss": 0.1802, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.34987085437365056, "learning_rate": 5.551362909942708e-06, "loss": 0.18, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.34555416449203236, "learning_rate": 5.51231668596653e-06, "loss": 0.1756, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.34181975428498373, "learning_rate": 5.47338630512007e-06, "loss": 0.1948, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.3353054309242631, "learning_rate": 5.434572078689617e-06, "loss": 0.2116, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.34169691702346017, "learning_rate": 5.395874317032694e-06, "loss": 0.2065, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.35694053291465183, "learning_rate": 5.357293329575573e-06, "loss": 0.1845, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.3611293217821771, "learning_rate": 5.318829424810797e-06, "loss": 0.2063, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.3529574597374424, "learning_rate": 5.280482910294728e-06, "loss": 0.1754, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.3451721982489699, "learning_rate": 5.242254092645078e-06, "loss": 0.1894, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.34762707458632996, "learning_rate": 5.2041432775384445e-06, "loss": 0.2105, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.35189023576638134, "learning_rate": 5.166150769707892e-06, "loss": 0.2178, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.3490139297000119, "learning_rate": 5.128276872940503e-06, "loss": 0.1911, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.34117442976672635, "learning_rate": 5.090521890074953e-06, "loss": 0.1913, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.3513975518777398, "learning_rate": 5.0528861229990675e-06, "loss": 0.177, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.3544322045213146, "learning_rate": 5.015369872647442e-06, "loss": 0.1912, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.3513530401816818, "learning_rate": 4.9779734389990195e-06, "loss": 0.2014, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.34988263311445233, "learning_rate": 4.940697121074675e-06, "loss": 0.1916, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.34746395365564775, "learning_rate": 4.903541216934864e-06, "loss": 0.1938, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.3513051586457687, "learning_rate": 4.8665060236772e-06, "loss": 0.1836, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.36118214821308525, "learning_rate": 4.829591837434102e-06, "loss": 0.1794, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.3413248212970705, "learning_rate": 4.792798953370424e-06, "loss": 0.2113, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.3377940075252558, "learning_rate": 4.756127665681083e-06, "loss": 0.1697, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.35957699354774847, "learning_rate": 4.719578267588725e-06, "loss": 0.1728, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.33799573950560907, "learning_rate": 4.6831510513413525e-06, "loss": 0.1777, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.438348598796331, "learning_rate": 4.6468463082100176e-06, "loss": 0.1357, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.37095021803059985, "learning_rate": 4.610664328486485e-06, "loss": 0.1391, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.3273870775490377, "learning_rate": 4.5746054014809e-06, "loss": 0.1306, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.27713165810220913, "learning_rate": 4.5386698155194766e-06, "loss": 0.1305, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.26128145392663876, "learning_rate": 4.502857857942204e-06, "loss": 0.1381, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.2873749386054502, "learning_rate": 4.467169815100549e-06, "loss": 0.1118, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.39680589321195187, "learning_rate": 4.431605972355137e-06, "loss": 0.1363, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.3534949247067103, "learning_rate": 4.396166614073516e-06, "loss": 0.125, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.3441249915275684, "learning_rate": 4.360852023627846e-06, "loss": 0.1371, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.33328316357034893, "learning_rate": 4.325662483392656e-06, "loss": 0.128, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.30384697344964706, "learning_rate": 4.29059827474257e-06, "loss": 0.1317, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.30220169623822063, "learning_rate": 4.255659678050063e-06, "loss": 0.145, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.291369026652043, "learning_rate": 4.22084697268323e-06, "loss": 0.113, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.3146717227668513, "learning_rate": 4.186160437003535e-06, "loss": 0.1439, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.3195007210674804, "learning_rate": 4.151600348363582e-06, "loss": 0.1349, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.2959340110010029, "learning_rate": 4.11716698310493e-06, "loss": 0.1346, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.2763642432051348, "learning_rate": 4.082860616555848e-06, "loss": 0.1393, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.2572037699331177, "learning_rate": 4.048681523029125e-06, "loss": 0.1323, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.26006485615275643, "learning_rate": 4.014629975819882e-06, "loss": 0.1172, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.29721204797692735, "learning_rate": 3.9807062472033855e-06, "loss": 0.1495, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.29688765016665597, "learning_rate": 3.94691060843287e-06, "loss": 0.1521, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.27316008199567043, "learning_rate": 3.913243329737353e-06, "loss": 0.1506, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.28703211836301307, "learning_rate": 3.879704680319503e-06, "loss": 0.1277, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2518513315308959, "learning_rate": 3.846294928353471e-06, "loss": 0.1262, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.2550909655502703, "learning_rate": 3.8130143409827345e-06, "loss": 0.1106, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2646064536127757, "learning_rate": 3.7798631843179887e-06, "loss": 0.1287, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2721462517156476, "learning_rate": 3.7468417234349973e-06, "loss": 0.1428, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.26936796836561844, "learning_rate": 3.7139502223724823e-06, "loss": 0.1342, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.26984039792692427, "learning_rate": 3.6811889441300095e-06, "loss": 0.1352, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2535440095824866, "learning_rate": 3.648558150665886e-06, "loss": 0.1401, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.2648867167749498, "learning_rate": 3.616058102895075e-06, "loss": 0.145, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2653063201167017, "learning_rate": 3.583689060687079e-06, "loss": 0.1094, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.2626727046245209, "learning_rate": 3.5514512828639023e-06, "loss": 0.1279, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.26400841523701507, "learning_rate": 3.51934502719796e-06, "loss": 0.1134, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.2700124990051463, "learning_rate": 3.4873705504100185e-06, "loss": 0.1412, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.24234418217467693, "learning_rate": 3.4555281081671345e-06, "loss": 0.1421, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.2735582543199166, "learning_rate": 3.4238179550806326e-06, "loss": 0.1124, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.253049860977114, "learning_rate": 3.3922403447040497e-06, "loss": 0.1365, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.2617267008631451, "learning_rate": 3.3607955295311247e-06, "loss": 0.1311, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2533622281046341, "learning_rate": 3.32948376099375e-06, "loss": 0.1377, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.2534139463198206, "learning_rate": 3.2983052894599976e-06, "loss": 0.1231, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2679828690319068, "learning_rate": 3.2672603642320945e-06, "loss": 0.1517, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.24906960023656913, "learning_rate": 3.236349233544438e-06, "loss": 0.1072, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.255505569477485, "learning_rate": 3.205572144561604e-06, "loss": 0.1492, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.25990387558566036, "learning_rate": 3.174929343376374e-06, "loss": 0.1289, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.252658241985562, "learning_rate": 3.1444210750077777e-06, "loss": 0.1364, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.26479463413479176, "learning_rate": 3.1140475833991046e-06, "loss": 0.1466, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.25786374902493275, "learning_rate": 3.0838091114159895e-06, "loss": 0.1256, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2629009964848642, "learning_rate": 3.0537059008444524e-06, "loss": 0.1344, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2579569305798692, "learning_rate": 3.0237381923889563e-06, "loss": 0.1212, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.2715271862316935, "learning_rate": 2.9939062256704997e-06, "loss": 0.1487, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.25583755118073853, "learning_rate": 2.964210239224696e-06, "loss": 0.151, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.26574322060888445, "learning_rate": 2.934650470499869e-06, "loss": 0.1336, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.27689827622929924, "learning_rate": 2.905227155855128e-06, "loss": 0.1437, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2612608017982772, "learning_rate": 2.875940530558519e-06, "loss": 0.1359, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2651776695588487, "learning_rate": 2.8467908287851154e-06, "loss": 0.1394, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.27178359292686205, "learning_rate": 2.8177782836151603e-06, "loss": 0.1668, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2508443808585579, "learning_rate": 2.7889031270321874e-06, "loss": 0.1053, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2530722624255237, "learning_rate": 2.760165589921184e-06, "loss": 0.1291, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.2711011143242254, "learning_rate": 2.7315659020667305e-06, "loss": 0.1535, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.24787966767873526, "learning_rate": 2.703104292151164e-06, "loss": 0.1356, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.2593382413999313, "learning_rate": 2.6747809877527607e-06, "loss": 0.1449, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.2607752302333738, "learning_rate": 2.6465962153439082e-06, "loss": 0.144, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.27670257355889755, "learning_rate": 2.618550200289303e-06, "loss": 0.1488, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2662537532254528, "learning_rate": 2.59064316684412e-06, "loss": 0.1333, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.2430334685225239, "learning_rate": 2.562875338152264e-06, "loss": 0.1205, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.25340840595348413, "learning_rate": 2.5352469362445552e-06, "loss": 0.1365, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.259025469266269, "learning_rate": 2.5077581820369523e-06, "loss": 0.1301, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.2590369136519642, "learning_rate": 2.480409295328803e-06, "loss": 0.1358, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.26990664211640775, "learning_rate": 2.45320049480108e-06, "loss": 0.1245, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.2655581641849704, "learning_rate": 2.4261319980146293e-06, "loss": 0.1723, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.24559543500516984, "learning_rate": 2.399204021408421e-06, "loss": 0.1218, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.2788467774743768, "learning_rate": 2.3724167802978395e-06, "loss": 0.1351, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.26153588200131656, "learning_rate": 2.3457704888729625e-06, "loss": 0.1366, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.26286789620520495, "learning_rate": 2.3192653601968162e-06, "loss": 0.1388, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.2659723466924362, "learning_rate": 2.2929016062037057e-06, "loss": 0.1324, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2612720292161416, "learning_rate": 2.2666794376975055e-06, "loss": 0.136, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.28158741039602864, "learning_rate": 2.24059906434998e-06, "loss": 0.1439, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.25208937819761684, "learning_rate": 2.214660694699091e-06, "loss": 0.117, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.2529815106165656, "learning_rate": 2.188864536147355e-06, "loss": 0.1256, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2613676451957394, "learning_rate": 2.1632107949601757e-06, "loss": 0.1366, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2577795624643999, "learning_rate": 2.137699676264171e-06, "loss": 0.1321, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.27526554744889964, "learning_rate": 2.1123313840455738e-06, "loss": 0.1216, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.27500210383339263, "learning_rate": 2.08710612114857e-06, "loss": 0.1413, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2522963606004267, "learning_rate": 2.0620240892736953e-06, "loss": 0.1184, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.2516150503399994, "learning_rate": 2.0370854889762e-06, "loss": 0.1422, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.26408729997403657, "learning_rate": 2.0122905196644726e-06, "loss": 0.1335, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.25386379620056737, "learning_rate": 1.987639379598427e-06, "loss": 0.141, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.26096727509834705, "learning_rate": 1.963132265887919e-06, "loss": 0.1409, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.26427842510956606, "learning_rate": 1.9387693744911784e-06, "loss": 0.1518, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.26225064116327423, "learning_rate": 1.9145509002132368e-06, "loss": 0.1411, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.27238574432283064, "learning_rate": 1.8904770367043723e-06, "loss": 0.1304, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.25990694293551087, "learning_rate": 1.8665479764585504e-06, "loss": 0.1436, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2658406421051845, "learning_rate": 1.8427639108118977e-06, "loss": 0.1265, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.25439776463459673, "learning_rate": 1.8191250299411755e-06, "loss": 0.1314, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.26190503448556984, "learning_rate": 1.7956315228622446e-06, "loss": 0.1262, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.27795632384277297, "learning_rate": 1.7722835774285553e-06, "loss": 0.1158, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2582863478435432, "learning_rate": 1.7490813803296624e-06, "loss": 0.1177, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2602636364612598, "learning_rate": 1.726025117089718e-06, "loss": 0.1536, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2619525230600161, "learning_rate": 1.70311497206598e-06, "loss": 0.1509, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2781931218622196, "learning_rate": 1.6803511284473638e-06, "loss": 0.1429, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.24487321897959816, "learning_rate": 1.6577337682529538e-06, "loss": 0.1377, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2645424944539655, "learning_rate": 1.6352630723305617e-06, "loss": 0.1309, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2580631955983937, "learning_rate": 1.612939220355272e-06, "loss": 0.1356, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.2493082385544422, "learning_rate": 1.5907623908280112e-06, "loss": 0.1262, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2542522928917543, "learning_rate": 1.568732761074121e-06, "loss": 0.1242, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.26483230714564965, "learning_rate": 1.5468505072419237e-06, "loss": 0.1255, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.25005956263432527, "learning_rate": 1.5251158043013448e-06, "loss": 0.1332, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.25938862465324825, "learning_rate": 1.5035288260424885e-06, "loss": 0.1314, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.26998451472939566, "learning_rate": 1.4820897450742623e-06, "loss": 0.137, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.25251476136723594, "learning_rate": 1.4607987328229767e-06, "loss": 0.1374, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.27268662502698815, "learning_rate": 1.4396559595310056e-06, "loss": 0.1389, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.25724662933447556, "learning_rate": 1.4186615942553973e-06, "loss": 0.1303, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2657458151146082, "learning_rate": 1.3978158048665424e-06, "loss": 0.1217, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2709485706222144, "learning_rate": 1.3771187580468115e-06, "loss": 0.12, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.258817862104, "learning_rate": 1.3565706192892392e-06, "loss": 0.1598, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.25610580197053956, "learning_rate": 1.3361715528961993e-06, "loss": 0.1427, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2659615809206235, "learning_rate": 1.3159217219780817e-06, "loss": 0.1426, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.25595507810419993, "learning_rate": 1.2958212884519949e-06, "loss": 0.1436, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.2489212827653562, "learning_rate": 1.2758704130404675e-06, "loss": 0.145, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.2568392385141406, "learning_rate": 1.2560692552701738e-06, "loss": 0.1305, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2601266455388917, "learning_rate": 1.2364179734706382e-06, "loss": 0.1251, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.2590779541373279, "learning_rate": 1.2169167247729852e-06, "loss": 0.1523, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2594453316013502, "learning_rate": 1.1975656651086864e-06, "loss": 0.1216, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.2419501796029935, "learning_rate": 1.1783649492082926e-06, "loss": 0.115, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.2703037640309789, "learning_rate": 1.1593147306002183e-06, "loss": 0.1545, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.25010953619507437, "learning_rate": 1.140415161609505e-06, "loss": 0.1527, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2516295776289254, "learning_rate": 1.121666393356604e-06, "loss": 0.1153, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2630219886863523, "learning_rate": 1.1030685757561632e-06, "loss": 0.1274, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.25706034526954896, "learning_rate": 1.0846218575158373e-06, "loss": 0.1252, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.2544322413541361, "learning_rate": 1.066326386135097e-06, "loss": 0.1329, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.2520362034055363, "learning_rate": 1.0481823079040398e-06, "loss": 0.132, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.2636121368183263, "learning_rate": 1.0301897679022344e-06, "loss": 0.1444, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.2645010278844527, "learning_rate": 1.0123489099975491e-06, "loss": 0.1293, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.27023494943220233, "learning_rate": 9.9465987684501e-07, "loss": 0.1369, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.2667612733572703, "learning_rate": 9.771228098856534e-07, "loss": 0.1378, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.25087553705456234, "learning_rate": 9.597378493454013e-07, "loss": 0.1295, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.2604818134964904, "learning_rate": 9.425051342339353e-07, "loss": 0.1461, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.250712910726447, "learning_rate": 9.254248023435864e-07, "loss": 0.1253, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.25152811783578854, "learning_rate": 9.084969902482288e-07, "loss": 0.1086, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.26616187801701413, "learning_rate": 8.917218333021993e-07, "loss": 0.1421, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2622414814649481, "learning_rate": 8.750994656392109e-07, "loss": 0.1399, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2501437919942646, "learning_rate": 8.58630020171265e-07, "loss": 0.1281, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2667169247463386, "learning_rate": 8.423136285876099e-07, "loss": 0.1218, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.2541515150777066, "learning_rate": 8.26150421353682e-07, "loss": 0.1329, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2616885865809659, "learning_rate": 8.101405277100549e-07, "loss": 0.1329, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2596911451421428, "learning_rate": 7.942840756714077e-07, "loss": 0.1305, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.26093355954543485, "learning_rate": 7.785811920255093e-07, "loss": 0.1297, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.2578333181497124, "learning_rate": 7.630320023322024e-07, "loss": 0.1201, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.25430017563649937, "learning_rate": 7.476366309223903e-07, "loss": 0.1268, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.26047862595628113, "learning_rate": 7.323952008970537e-07, "loss": 0.1328, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.26018474241367084, "learning_rate": 7.173078341262618e-07, "loss": 0.1279, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.24655113581327776, "learning_rate": 7.023746512481989e-07, "loss": 0.1196, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2540276287636465, "learning_rate": 6.875957716681902e-07, "loss": 0.1433, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.27359448967402344, "learning_rate": 6.729713135577687e-07, "loss": 0.1288, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2452729814939689, "learning_rate": 6.585013938537143e-07, "loss": 0.1164, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2621546660010788, "learning_rate": 6.441861282571115e-07, "loss": 0.1182, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.25740655929692324, "learning_rate": 6.300256312324471e-07, "loss": 0.1357, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.25416994079006977, "learning_rate": 6.160200160066776e-07, "loss": 0.1384, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.25426378419688456, "learning_rate": 6.021693945683327e-07, "loss": 0.1242, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.26169659119317645, "learning_rate": 5.884738776666044e-07, "loss": 0.1063, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.26728556462154246, "learning_rate": 5.749335748104878e-07, "loss": 0.1399, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.25530203048439665, "learning_rate": 5.615485942678778e-07, "loss": 0.1313, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.25191061481476407, "learning_rate": 5.483190430647289e-07, "loss": 0.1416, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.2689376292343316, "learning_rate": 5.352450269841747e-07, "loss": 0.1264, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.25041657445549964, "learning_rate": 5.22326650565701e-07, "loss": 0.1402, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.26628658295828517, "learning_rate": 5.095640171043048e-07, "loss": 0.1435, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.25679349020840475, "learning_rate": 4.969572286496594e-07, "loss": 0.1259, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.26453162237945593, "learning_rate": 4.845063860053079e-07, "loss": 0.1614, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2616008544555472, "learning_rate": 4.7221158872785997e-07, "loss": 0.1506, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.24586286718379338, "learning_rate": 4.600729351261857e-07, "loss": 0.1523, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.2535411766832979, "learning_rate": 4.4809052226063355e-07, "loss": 0.1268, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.2461408372031414, "learning_rate": 4.3626444594226046e-07, "loss": 0.1283, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.25465800347381323, "learning_rate": 4.245948007320588e-07, "loss": 0.134, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.2574088314136807, "learning_rate": 4.130816799401971e-07, "loss": 0.1416, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.25820582320758045, "learning_rate": 4.017251756252827e-07, "loss": 0.163, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.2505321957333137, "learning_rate": 3.9052537859362473e-07, "loss": 0.149, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.25453828058538136, "learning_rate": 3.7948237839849687e-07, "loss": 0.1192, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.25732893682612534, "learning_rate": 3.6859626333943797e-07, "loss": 0.1164, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.25438043563022494, "learning_rate": 3.578671204615347e-07, "loss": 0.1215, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.25803480870263656, "learning_rate": 3.472950355547267e-07, "loss": 0.1233, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.2473702724969912, "learning_rate": 3.3688009315312244e-07, "loss": 0.1201, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2552472583859445, "learning_rate": 3.266223765343224e-07, "loss": 0.1666, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2745623720673783, "learning_rate": 3.16521967718757e-07, "loss": 0.141, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.2748604692186058, "learning_rate": 3.0657894746902726e-07, "loss": 0.1536, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.2570434025876586, "learning_rate": 2.9679339528925654e-07, "loss": 0.1286, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.25625807407014234, "learning_rate": 2.871653894244597e-07, "loss": 0.1429, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2631244754423487, "learning_rate": 2.7769500685991266e-07, "loss": 0.122, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2689297183574733, "learning_rate": 2.683823233205485e-07, "loss": 0.1694, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.2654363397313229, "learning_rate": 2.592274132703287e-07, "loss": 0.1353, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.2536785851128983, "learning_rate": 2.502303499116754e-07, "loss": 0.14, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.24718244111650509, "learning_rate": 2.413912051848666e-07, "loss": 0.1443, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.24890454125957157, "learning_rate": 2.3271004976746613e-07, "loss": 0.1329, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.24272356784764462, "learning_rate": 2.2418695307376393e-07, "loss": 0.1204, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2747699961346376, "learning_rate": 2.1582198325420968e-07, "loss": 0.1571, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.2693099486331662, "learning_rate": 2.0761520719488447e-07, "loss": 0.1454, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.24972283253942934, "learning_rate": 1.9956669051694798e-07, "loss": 0.1556, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.24883944696504784, "learning_rate": 1.916764975761254e-07, "loss": 0.1245, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2537692066941293, "learning_rate": 1.839446914621923e-07, "loss": 0.1477, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.2556463899200499, "learning_rate": 1.7637133399845962e-07, "loss": 0.1237, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.26025947711084924, "learning_rate": 1.6895648574129397e-07, "loss": 0.1305, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2422393124033866, "learning_rate": 1.6170020597962465e-07, "loss": 0.1474, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.25562317910259347, "learning_rate": 1.5460255273447078e-07, "loss": 0.144, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.2556223674183599, "learning_rate": 1.4766358275847715e-07, "loss": 0.1619, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.26194276027327934, "learning_rate": 1.4088335153546573e-07, "loss": 0.1198, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.25543618785158234, "learning_rate": 1.3426191327998496e-07, "loss": 0.1278, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.2634294812569942, "learning_rate": 1.277993209368744e-07, "loss": 0.1404, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.24940273169001895, "learning_rate": 1.214956261808542e-07, "loss": 0.1516, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.2641629487953847, "learning_rate": 1.1535087941609846e-07, "loss": 0.1242, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.2667530931715464, "learning_rate": 1.0936512977583802e-07, "loss": 0.1301, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.25653038769054304, "learning_rate": 1.0353842512196732e-07, "loss": 0.139, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.26123208726790614, "learning_rate": 9.787081204466253e-08, "loss": 0.1285, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2537129048601822, "learning_rate": 9.236233586200627e-08, "loss": 0.1575, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2674282423068482, "learning_rate": 8.70130406196279e-08, "loss": 0.1442, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.25031402734950076, "learning_rate": 8.182296909035047e-08, "loss": 0.1307, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.24220403656092152, "learning_rate": 7.679216277384439e-08, "loss": 0.1174, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2675022764449438, "learning_rate": 7.19206618963053e-08, "loss": 0.1359, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.2538775209757523, "learning_rate": 6.720850541012347e-08, "loss": 0.1234, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.2616830841545958, "learning_rate": 6.265573099357714e-08, "loss": 0.1403, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.2566037712307084, "learning_rate": 5.826237505053067e-08, "loss": 0.1495, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.25346210877754966, "learning_rate": 5.4028472710137e-08, "loss": 0.1411, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.27079889128849255, "learning_rate": 4.9954057826571146e-08, "loss": 0.1228, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2592821841217003, "learning_rate": 4.6039162978743776e-08, "loss": 0.1189, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.24906195802395298, "learning_rate": 4.228381947004812e-08, "loss": 0.1284, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.2537211698196386, "learning_rate": 3.868805732811343e-08, "loss": 0.1221, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.25246647685585516, "learning_rate": 3.525190530455636e-08, "loss": 0.1397, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.25189172420702965, "learning_rate": 3.197539087475887e-08, "loss": 0.1144, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2528481009995213, "learning_rate": 2.8858540237641786e-08, "loss": 0.1616, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.24439266448377606, "learning_rate": 2.5901378315458247e-08, "loss": 0.1304, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.2687766443800683, "learning_rate": 2.3103928753598347e-08, "loss": 0.1176, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.24411898352949382, "learning_rate": 2.0466213920393718e-08, "loss": 0.1207, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.2606143696147874, "learning_rate": 1.7988254906942115e-08, "loss": 0.1228, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.2551134567274531, "learning_rate": 1.5670071526936447e-08, "loss": 0.1508, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.24781230550095149, "learning_rate": 1.3511682316509344e-08, "loss": 0.1426, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.24967196674981623, "learning_rate": 1.1513104534086605e-08, "loss": 0.1632, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.2507524156523311, "learning_rate": 9.67435416023843e-09, "loss": 0.1322, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.25913721155493763, "learning_rate": 7.995445897566178e-09, "loss": 0.1292, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.26096803024177423, "learning_rate": 6.476393170578021e-09, "loss": 0.1458, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.2572772129005751, "learning_rate": 5.11720812557348e-09, "loss": 0.1336, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.25210898423979733, "learning_rate": 3.917901630563492e-09, "loss": 0.1471, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2706813064783282, "learning_rate": 2.878483275170485e-09, "loss": 0.1247, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.24615566532555366, "learning_rate": 1.998961370555108e-09, "loss": 0.1255, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.25258520218960223, "learning_rate": 1.2793429493518361e-09, "loss": 0.1113, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2662625196743994, "learning_rate": 7.196337656112384e-10, "loss": 0.1433, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.2402988707628465, "learning_rate": 3.198382947511292e-10, "loss": 0.1308, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.2586135864479596, "learning_rate": 7.995973352770137e-11, "loss": 0.1281, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.24472141664727523, "learning_rate": 0.0, "loss": 0.114, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.3001654329461965e+18, "train_loss": 0.38927515587705347, "train_runtime": 17662.1505, "train_samples_per_second": 8.945, "train_steps_per_second": 0.07 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 1.3001654329461965e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }