{ "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": 6.477593228252779, "learning_rate": 3.2258064516129035e-07, "loss": 1.0563, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.608373175034339, "learning_rate": 6.451612903225807e-07, "loss": 1.0613, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.634153639772746, "learning_rate": 9.67741935483871e-07, "loss": 1.0756, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.37862084848562, "learning_rate": 1.2903225806451614e-06, "loss": 1.0631, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 5.957390327277104, "learning_rate": 1.6129032258064516e-06, "loss": 1.0288, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.905837241210188, "learning_rate": 1.935483870967742e-06, "loss": 1.0503, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.557431049951584, "learning_rate": 2.2580645161290324e-06, "loss": 1.0148, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.213036548620219, "learning_rate": 2.580645161290323e-06, "loss": 1.0155, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.7897167414212856, "learning_rate": 2.903225806451613e-06, "loss": 0.9849, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.573656860264437, "learning_rate": 3.225806451612903e-06, "loss": 0.9848, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.5096206884944565, "learning_rate": 3.548387096774194e-06, "loss": 0.9744, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.881219343914181, "learning_rate": 3.870967741935484e-06, "loss": 0.9566, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.140809829357429, "learning_rate": 4.193548387096774e-06, "loss": 0.9576, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.0674451647752505, "learning_rate": 4.516129032258065e-06, "loss": 0.9521, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.6846684339899123, "learning_rate": 4.838709677419355e-06, "loss": 0.9365, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.8197245143298693, "learning_rate": 5.161290322580646e-06, "loss": 0.9365, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.549815177689368, "learning_rate": 5.483870967741935e-06, "loss": 0.9143, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.1078127846422356, "learning_rate": 5.806451612903226e-06, "loss": 0.8995, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.4960446426494252, "learning_rate": 6.129032258064517e-06, "loss": 0.8751, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.1217910627820942, "learning_rate": 6.451612903225806e-06, "loss": 0.8626, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.0575995477921027, "learning_rate": 6.774193548387097e-06, "loss": 0.8476, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.1876347481852476, "learning_rate": 7.096774193548388e-06, "loss": 0.8376, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.0792000484388882, "learning_rate": 7.4193548387096784e-06, "loss": 0.8326, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.9173316018570816, "learning_rate": 7.741935483870968e-06, "loss": 0.8309, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8941894784261414, "learning_rate": 8.064516129032258e-06, "loss": 0.8183, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.9505584472002754, "learning_rate": 8.387096774193549e-06, "loss": 0.8026, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.8397533157416328, "learning_rate": 8.70967741935484e-06, "loss": 0.8021, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8158313639953463, "learning_rate": 9.03225806451613e-06, "loss": 0.8061, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.9358601686296211, "learning_rate": 9.35483870967742e-06, "loss": 0.79, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7137638891686431, "learning_rate": 9.67741935483871e-06, "loss": 0.7765, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6500899763373091, "learning_rate": 1e-05, "loss": 0.7717, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7281368565795832, "learning_rate": 1.0322580645161291e-05, "loss": 0.7674, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6750805679600209, "learning_rate": 1.0645161290322582e-05, "loss": 0.7755, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.5985301074905576, "learning_rate": 1.096774193548387e-05, "loss": 0.7828, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.730900994547618, "learning_rate": 1.1290322580645164e-05, "loss": 0.7651, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6455085830370394, "learning_rate": 1.1612903225806453e-05, "loss": 0.7613, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5623081301975674, "learning_rate": 1.1935483870967743e-05, "loss": 0.74, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6529040582350412, "learning_rate": 1.2258064516129034e-05, "loss": 0.7407, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5850371407882645, "learning_rate": 1.2580645161290324e-05, "loss": 0.756, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5962933452433633, "learning_rate": 1.2903225806451613e-05, "loss": 0.7658, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.584305925026736, "learning_rate": 1.3225806451612903e-05, "loss": 0.7509, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6085649610320307, "learning_rate": 1.3548387096774194e-05, "loss": 0.7496, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.614555038523388, "learning_rate": 1.3870967741935486e-05, "loss": 0.7421, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5901489682927136, "learning_rate": 1.4193548387096776e-05, "loss": 0.7492, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.5411324799212693, "learning_rate": 1.4516129032258066e-05, "loss": 0.7423, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5577538979102997, "learning_rate": 1.4838709677419357e-05, "loss": 0.7286, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.49874469972677277, "learning_rate": 1.5161290322580646e-05, "loss": 0.7286, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5873644290127196, "learning_rate": 1.5483870967741936e-05, "loss": 0.7212, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5255249648305, "learning_rate": 1.5806451612903226e-05, "loss": 0.7204, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.6044445879575432, "learning_rate": 1.6129032258064517e-05, "loss": 0.7276, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5637677453493457, "learning_rate": 1.6451612903225807e-05, "loss": 0.7322, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.5335539079196651, "learning_rate": 1.6774193548387098e-05, "loss": 0.7215, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.6054503090159665, "learning_rate": 1.7096774193548388e-05, "loss": 0.7356, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.842002101038644, "learning_rate": 1.741935483870968e-05, "loss": 0.722, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.6226292697181102, "learning_rate": 1.774193548387097e-05, "loss": 0.7099, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6272766855138812, "learning_rate": 1.806451612903226e-05, "loss": 0.7114, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6602298097963051, "learning_rate": 1.838709677419355e-05, "loss": 0.7065, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.7505876337838009, "learning_rate": 1.870967741935484e-05, "loss": 0.7058, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5605497951539581, "learning_rate": 1.903225806451613e-05, "loss": 0.708, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5940898322430102, "learning_rate": 1.935483870967742e-05, "loss": 0.705, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.6528165260870716, "learning_rate": 1.967741935483871e-05, "loss": 0.7058, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.549198256150178, "learning_rate": 2e-05, "loss": 0.7182, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6185792651815687, "learning_rate": 2.0322580645161292e-05, "loss": 0.6963, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7042694789335682, "learning_rate": 2.0645161290322582e-05, "loss": 0.7008, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.649024380319142, "learning_rate": 2.0967741935483873e-05, "loss": 0.699, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6059349102826053, "learning_rate": 2.1290322580645163e-05, "loss": 0.6981, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.5943332145149156, "learning_rate": 2.161290322580645e-05, "loss": 0.6954, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.649196549104721, "learning_rate": 2.193548387096774e-05, "loss": 0.6982, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.8542776977677725, "learning_rate": 2.225806451612903e-05, "loss": 0.6987, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.9566391369654852, "learning_rate": 2.2580645161290328e-05, "loss": 0.7125, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.9177407069486693, "learning_rate": 2.2903225806451615e-05, "loss": 0.6981, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.6277205501735237, "learning_rate": 2.3225806451612906e-05, "loss": 0.6992, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.9723010855540931, "learning_rate": 2.3548387096774196e-05, "loss": 0.6951, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.9823516395377273, "learning_rate": 2.3870967741935486e-05, "loss": 0.7022, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.780973865857798, "learning_rate": 2.4193548387096777e-05, "loss": 0.6937, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 1.2755809216901615, "learning_rate": 2.4516129032258067e-05, "loss": 0.7067, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.1210309338812496, "learning_rate": 2.4838709677419358e-05, "loss": 0.6761, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 1.033848189662638, "learning_rate": 2.5161290322580648e-05, "loss": 0.6853, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8947674775245431, "learning_rate": 2.548387096774194e-05, "loss": 0.6839, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.7759697419045672, "learning_rate": 2.5806451612903226e-05, "loss": 0.6942, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.9941555113727018, "learning_rate": 2.6129032258064516e-05, "loss": 0.6873, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.596156061817777, "learning_rate": 2.6451612903225806e-05, "loss": 0.7031, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.7231306876026157, "learning_rate": 2.6774193548387097e-05, "loss": 0.6998, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 1.59912310058348, "learning_rate": 2.7096774193548387e-05, "loss": 0.6877, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.8051085118519008, "learning_rate": 2.7419354838709678e-05, "loss": 0.6906, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.5812574750382369, "learning_rate": 2.774193548387097e-05, "loss": 0.7072, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.8807463024413626, "learning_rate": 2.8064516129032262e-05, "loss": 0.6938, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.674145896730149, "learning_rate": 2.8387096774193552e-05, "loss": 0.6843, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.0557517934996061, "learning_rate": 2.8709677419354843e-05, "loss": 0.6791, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 1.48827685589954, "learning_rate": 2.9032258064516133e-05, "loss": 0.7041, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.3689355915822325, "learning_rate": 2.9354838709677423e-05, "loss": 0.6975, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.9545395137686417, "learning_rate": 2.9677419354838714e-05, "loss": 0.6836, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.2466220401607848, "learning_rate": 3.0000000000000004e-05, "loss": 0.6961, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.0840415341966352, "learning_rate": 3.032258064516129e-05, "loss": 0.684, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.083665297087355, "learning_rate": 3.0645161290322585e-05, "loss": 0.6787, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.2707953301116686, "learning_rate": 3.096774193548387e-05, "loss": 0.6923, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.2395735102181824, "learning_rate": 3.1290322580645166e-05, "loss": 0.6784, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.0677452871894855, "learning_rate": 3.161290322580645e-05, "loss": 0.6771, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.0110972236020281, "learning_rate": 3.193548387096774e-05, "loss": 0.6696, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.5252907113791827, "learning_rate": 3.2258064516129034e-05, "loss": 0.6882, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.0727623253068135, "learning_rate": 3.258064516129033e-05, "loss": 0.6748, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.2132607867575935, "learning_rate": 3.2903225806451614e-05, "loss": 0.6907, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 1.5589326935523051, "learning_rate": 3.322580645161291e-05, "loss": 0.6744, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.9079658718550178, "learning_rate": 3.3548387096774195e-05, "loss": 0.6914, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 2.2007481149305654, "learning_rate": 3.387096774193549e-05, "loss": 0.6748, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.4388628629504885, "learning_rate": 3.4193548387096776e-05, "loss": 0.6768, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 2.008537166910615, "learning_rate": 3.451612903225807e-05, "loss": 0.6829, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.511682926803833, "learning_rate": 3.483870967741936e-05, "loss": 0.6754, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.9031358004300736, "learning_rate": 3.516129032258065e-05, "loss": 0.6793, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.355831941788139, "learning_rate": 3.548387096774194e-05, "loss": 0.6801, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.7308829827650773, "learning_rate": 3.5806451612903225e-05, "loss": 0.6864, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.3668802286515473, "learning_rate": 3.612903225806452e-05, "loss": 0.681, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.5511003367570442, "learning_rate": 3.6451612903225805e-05, "loss": 0.6755, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.2039515307998194, "learning_rate": 3.67741935483871e-05, "loss": 0.6665, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.3736914927601132, "learning_rate": 3.7096774193548386e-05, "loss": 0.6735, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.3361023118216442, "learning_rate": 3.741935483870968e-05, "loss": 0.6797, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.2710339457924351, "learning_rate": 3.7741935483870974e-05, "loss": 0.6903, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.3227409735094156, "learning_rate": 3.806451612903226e-05, "loss": 0.6753, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.2464912034837927, "learning_rate": 3.8387096774193555e-05, "loss": 0.6809, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.0474027729137192, "learning_rate": 3.870967741935484e-05, "loss": 0.6824, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 1.1643818006158473, "learning_rate": 3.9032258064516135e-05, "loss": 0.6771, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.059939668421655, "learning_rate": 3.935483870967742e-05, "loss": 0.68, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7755323289106344, "learning_rate": 3.9677419354838716e-05, "loss": 0.6647, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.7817028409787542, "learning_rate": 4e-05, "loss": 0.6772, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.7614693231795627, "learning_rate": 3.9999920040266474e-05, "loss": 0.6762, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.7563759659928397, "learning_rate": 3.999968016170525e-05, "loss": 0.675, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.2604669751133544, "learning_rate": 3.9999280366234394e-05, "loss": 0.6675, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.1647019378814087, "learning_rate": 3.999872065705065e-05, "loss": 0.6748, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 1.436872361353139, "learning_rate": 3.999800103862945e-05, "loss": 0.6668, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.728572171825493, "learning_rate": 3.9997121516724834e-05, "loss": 0.6635, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.2528032191432512, "learning_rate": 3.999608209836944e-05, "loss": 0.6706, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.1262521934311198, "learning_rate": 3.999488279187443e-05, "loss": 0.6778, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 1.1244123603788096, "learning_rate": 3.9993523606829425e-05, "loss": 0.6656, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.9511626737031691, "learning_rate": 3.9992004554102435e-05, "loss": 0.6724, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7542213323391145, "learning_rate": 3.999032564583976e-05, "loss": 0.667, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.7048344892641571, "learning_rate": 3.998848689546591e-05, "loss": 0.6557, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.8392619777507283, "learning_rate": 3.9986488317683496e-05, "loss": 0.6589, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 1.0141612472863415, "learning_rate": 3.9984329928473067e-05, "loss": 0.6697, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.9741507410185664, "learning_rate": 3.998201174509306e-05, "loss": 0.6653, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.9095164817803185, "learning_rate": 3.997953378607961e-05, "loss": 0.668, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 1.0369548410640146, "learning_rate": 3.9976896071246403e-05, "loss": 0.6623, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 1.4144031792216796, "learning_rate": 3.997409862168454e-05, "loss": 0.6644, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.8035442445462372, "learning_rate": 3.997114145976237e-05, "loss": 0.6541, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 1.0215484886856412, "learning_rate": 3.9968024609125245e-05, "loss": 0.6681, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 1.3161852087522259, "learning_rate": 3.996474809469545e-05, "loss": 0.6752, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.9788860231695952, "learning_rate": 3.996131194267189e-05, "loss": 0.6621, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 1.253923321598977, "learning_rate": 3.995771618052995e-05, "loss": 0.668, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 1.0707026068885621, "learning_rate": 3.9953960837021256e-05, "loss": 0.6711, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 1.2631220147906796, "learning_rate": 3.995004594217343e-05, "loss": 0.6633, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7955150013452147, "learning_rate": 3.994597152728987e-05, "loss": 0.6747, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.8702247720933353, "learning_rate": 3.994173762494947e-05, "loss": 0.6665, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.8493955855602949, "learning_rate": 3.9937344269006424e-05, "loss": 0.6668, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7454044433147579, "learning_rate": 3.993279149458988e-05, "loss": 0.6644, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.9986859786475802, "learning_rate": 3.9928079338103695e-05, "loss": 0.6684, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.7306817543107726, "learning_rate": 3.992320783722616e-05, "loss": 0.6625, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7243013997346882, "learning_rate": 3.991817703090965e-05, "loss": 0.6624, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 1.1510008730767705, "learning_rate": 3.991298695938038e-05, "loss": 0.6622, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.9326885343821749, "learning_rate": 3.9907637664138e-05, "loss": 0.6442, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.632360865920809, "learning_rate": 3.990212918795534e-05, "loss": 0.6582, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.6974692845953296, "learning_rate": 3.9896461574878036e-05, "loss": 0.667, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.7831636411051853, "learning_rate": 3.989063487022416e-05, "loss": 0.6648, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5580737887152741, "learning_rate": 3.9884649120583903e-05, "loss": 0.6568, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.6108262649858266, "learning_rate": 3.987850437381915e-05, "loss": 0.6636, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6850752531642225, "learning_rate": 3.987220067906313e-05, "loss": 0.6659, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.6732406559056014, "learning_rate": 3.986573808672002e-05, "loss": 0.6501, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.6907728940349958, "learning_rate": 3.9859116648464534e-05, "loss": 0.6585, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.8904636522025347, "learning_rate": 3.985233641724152e-05, "loss": 0.6553, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 1.0667349486466484, "learning_rate": 3.984539744726554e-05, "loss": 0.6412, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.630544324283301, "learning_rate": 3.983829979402038e-05, "loss": 0.653, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.6034563196880326, "learning_rate": 3.983104351425871e-05, "loss": 0.6608, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7868450395428561, "learning_rate": 3.982362866600154e-05, "loss": 0.6555, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.598714625401936, "learning_rate": 3.9816055308537806e-05, "loss": 0.649, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.4529523492076498, "learning_rate": 3.980832350242388e-05, "loss": 0.6436, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5230748443190553, "learning_rate": 3.980043330948306e-05, "loss": 0.6627, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.48497393373572806, "learning_rate": 3.9792384792805124e-05, "loss": 0.6554, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.4917817309688444, "learning_rate": 3.978417801674579e-05, "loss": 0.6581, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.4826687873687132, "learning_rate": 3.9775813046926244e-05, "loss": 0.6557, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.4862793796511975, "learning_rate": 3.976728995023254e-05, "loss": 0.6495, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.582866259358297, "learning_rate": 3.975860879481514e-05, "loss": 0.6587, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.6479218934740191, "learning_rate": 3.974976965008833e-05, "loss": 0.6468, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5543635972048198, "learning_rate": 3.9740772586729674e-05, "loss": 0.6404, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.5532086446008052, "learning_rate": 3.973161767667946e-05, "loss": 0.6513, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.5039823462841059, "learning_rate": 3.972230499314009e-05, "loss": 0.6592, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.4341447575434744, "learning_rate": 3.9712834610575545e-05, "loss": 0.6398, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.531106347556286, "learning_rate": 3.9703206604710746e-05, "loss": 0.6489, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.47403810937747815, "learning_rate": 3.969342105253098e-05, "loss": 0.6606, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.4889473663955482, "learning_rate": 3.9683478032281246e-05, "loss": 0.6597, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.5321485177310059, "learning_rate": 3.967337762346568e-05, "loss": 0.6561, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.4455041914054921, "learning_rate": 3.9663119906846885e-05, "loss": 0.6473, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5753234263112805, "learning_rate": 3.965270496444528e-05, "loss": 0.6597, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6416846367009785, "learning_rate": 3.9642132879538465e-05, "loss": 0.6524, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.4276901634283716, "learning_rate": 3.9631403736660566e-05, "loss": 0.6428, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5106614036153407, "learning_rate": 3.962051762160151e-05, "loss": 0.6316, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.48828811164425484, "learning_rate": 3.960947462140638e-05, "loss": 0.6539, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5589446683650268, "learning_rate": 3.959827482437472e-05, "loss": 0.6405, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.5131344211160214, "learning_rate": 3.958691832005981e-05, "loss": 0.6618, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.6098407156514524, "learning_rate": 3.9575405199267944e-05, "loss": 0.6525, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.630118230802271, "learning_rate": 3.956373555405774e-05, "loss": 0.6527, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.4533715607916912, "learning_rate": 3.955190947773937e-05, "loss": 0.6459, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.6538730821706686, "learning_rate": 3.9539927064873824e-05, "loss": 0.6501, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.934205738158969, "learning_rate": 3.952778841127214e-05, "loss": 0.6508, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.9078307133377653, "learning_rate": 3.95154936139947e-05, "loss": 0.6302, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.7498507976781076, "learning_rate": 3.950304277135034e-05, "loss": 0.6527, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 1.0089173037106915, "learning_rate": 3.94904359828957e-05, "loss": 0.6496, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 1.0436713960601793, "learning_rate": 3.94776733494343e-05, "loss": 0.6453, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.7373433495052917, "learning_rate": 3.9464754973015826e-05, "loss": 0.6428, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5677511621559119, "learning_rate": 3.9451680956935275e-05, "loss": 0.6427, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.6524588868146363, "learning_rate": 3.943845140573213e-05, "loss": 0.6589, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.8113935728136296, "learning_rate": 3.942506642518952e-05, "loss": 0.6392, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.7495399332538232, "learning_rate": 3.9411526122333396e-05, "loss": 0.6535, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.569631021956347, "learning_rate": 3.939783060543167e-05, "loss": 0.6545, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5237605113303171, "learning_rate": 3.938397998399333e-05, "loss": 0.6474, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6399416130728933, "learning_rate": 3.936997436876756e-05, "loss": 0.6453, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.494219503133526, "learning_rate": 3.935581387174289e-05, "loss": 0.6551, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.42310683078873934, "learning_rate": 3.9341498606146295e-05, "loss": 0.6366, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.6647544576725289, "learning_rate": 3.932702868644224e-05, "loss": 0.6496, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.7710265543058797, "learning_rate": 3.931240422833181e-05, "loss": 0.6386, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7433398933973411, "learning_rate": 3.9297625348751806e-05, "loss": 0.6509, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.688336500800989, "learning_rate": 3.9282692165873744e-05, "loss": 0.6478, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.66662913530737, "learning_rate": 3.9267604799102945e-05, "loss": 0.6311, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.4672107155451462, "learning_rate": 3.9252363369077615e-05, "loss": 0.638, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5980769538892994, "learning_rate": 3.9236967997667796e-05, "loss": 0.6455, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.7091653258872186, "learning_rate": 3.9221418807974496e-05, "loss": 0.6424, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.7131540146931287, "learning_rate": 3.92057159243286e-05, "loss": 0.6463, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.513290893173061, "learning_rate": 3.9189859472289956e-05, "loss": 0.6376, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.517899047138146, "learning_rate": 3.9173849578646324e-05, "loss": 0.6225, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6105267734893487, "learning_rate": 3.9157686371412395e-05, "loss": 0.6566, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5885695980190451, "learning_rate": 3.914136997982874e-05, "loss": 0.6426, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5773345857829824, "learning_rate": 3.912490053436079e-05, "loss": 0.6383, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5725067863525142, "learning_rate": 3.9108278166697805e-05, "loss": 0.6419, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5046855130790154, "learning_rate": 3.909150300975178e-05, "loss": 0.6291, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.47302202534987353, "learning_rate": 3.907457519765642e-05, "loss": 0.6606, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5660677114446305, "learning_rate": 3.905749486576607e-05, "loss": 0.6452, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6586716168331777, "learning_rate": 3.90402621506546e-05, "loss": 0.6333, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4628339518475785, "learning_rate": 3.902287719011435e-05, "loss": 0.6424, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.4596716600431549, "learning_rate": 3.900534012315499e-05, "loss": 0.6285, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 1.1911531208917865, "learning_rate": 3.8987651090002454e-05, "loss": 0.6309, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.4323416174398744, "learning_rate": 3.896981023209777e-05, "loss": 0.6343, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4871068936539705, "learning_rate": 3.8951817692095966e-05, "loss": 0.6326, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4496552158511434, "learning_rate": 3.893367361386491e-05, "loss": 0.6339, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4866927031465208, "learning_rate": 3.891537814248417e-05, "loss": 0.6457, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.4527342689872624, "learning_rate": 3.889693142424384e-05, "loss": 0.6504, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.43691473341957066, "learning_rate": 3.8878333606643405e-05, "loss": 0.6349, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.48579972869850624, "learning_rate": 3.885958483839049e-05, "loss": 0.6431, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.5924014320157608, "learning_rate": 3.8840685269399786e-05, "loss": 0.6435, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.5759197187995851, "learning_rate": 3.882163505079171e-05, "loss": 0.6335, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.6192249045294064, "learning_rate": 3.880243433489132e-05, "loss": 0.6394, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.6505807262347182, "learning_rate": 3.878308327522702e-05, "loss": 0.5932, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.510963135113173, "learning_rate": 3.876358202652936e-05, "loss": 0.5818, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5692074856413379, "learning_rate": 3.8743930744729835e-05, "loss": 0.5861, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6023402769533283, "learning_rate": 3.8724129586959535e-05, "loss": 0.5907, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.9247123576506604, "learning_rate": 3.870417871154801e-05, "loss": 0.5829, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 1.0883378866261062, "learning_rate": 3.868407827802192e-05, "loss": 0.5856, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.6942259258351299, "learning_rate": 3.8663828447103804e-05, "loss": 0.6028, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.48463012618531254, "learning_rate": 3.8643429380710765e-05, "loss": 0.5937, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5281447954443, "learning_rate": 3.862288124195319e-05, "loss": 0.5993, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.47656911393665535, "learning_rate": 3.8602184195133464e-05, "loss": 0.5872, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5233877225863044, "learning_rate": 3.8581338405744604e-05, "loss": 0.587, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.5258445578909233, "learning_rate": 3.8560344040468996e-05, "loss": 0.5847, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5307486128344715, "learning_rate": 3.853920126717703e-05, "loss": 0.5835, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.48166540705395183, "learning_rate": 3.851791025492574e-05, "loss": 0.5919, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.5009628009210326, "learning_rate": 3.8496471173957515e-05, "loss": 0.5926, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.5256430524093463, "learning_rate": 3.847488419569866e-05, "loss": 0.5921, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.43733353850924916, "learning_rate": 3.8453149492758077e-05, "loss": 0.5949, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.47565052659620805, "learning_rate": 3.8431267238925886e-05, "loss": 0.5946, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.4332855133013182, "learning_rate": 3.840923760917199e-05, "loss": 0.584, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.45464676735543563, "learning_rate": 3.838706077964473e-05, "loss": 0.5874, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.4242071557119854, "learning_rate": 3.836473692766944e-05, "loss": 0.5865, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.4452701715849986, "learning_rate": 3.834226623174705e-05, "loss": 0.5862, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.44953007056883354, "learning_rate": 3.831964887155264e-05, "loss": 0.601, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.37930291379273906, "learning_rate": 3.829688502793403e-05, "loss": 0.5738, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.48104669981313575, "learning_rate": 3.827397488291029e-05, "loss": 0.5861, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.4098867027792675, "learning_rate": 3.8250918619670343e-05, "loss": 0.5849, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.4650722290827814, "learning_rate": 3.822771642257145e-05, "loss": 0.592, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.383152637026104, "learning_rate": 3.820436847713776e-05, "loss": 0.5859, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.47898977047948754, "learning_rate": 3.8180874970058826e-05, "loss": 0.5834, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.4563227246329737, "learning_rate": 3.8157236089188103e-05, "loss": 0.594, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.4312422981339171, "learning_rate": 3.813345202354145e-05, "loss": 0.5965, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.5231479381544224, "learning_rate": 3.810952296329563e-05, "loss": 0.5787, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.5257951129727876, "learning_rate": 3.808544909978676e-05, "loss": 0.5962, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.5837048298828571, "learning_rate": 3.806123062550882e-05, "loss": 0.6026, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.6053752028442583, "learning_rate": 3.803686773411208e-05, "loss": 0.5857, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.6581566067279031, "learning_rate": 3.801236062040158e-05, "loss": 0.5922, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5597021350604087, "learning_rate": 3.798770948033553e-05, "loss": 0.5922, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5383362448703497, "learning_rate": 3.796291451102381e-05, "loss": 0.6074, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.7017256395932311, "learning_rate": 3.793797591072631e-05, "loss": 0.5883, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6344681389512209, "learning_rate": 3.791289387885144e-05, "loss": 0.5868, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4925165357423287, "learning_rate": 3.788766861595443e-05, "loss": 0.5975, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.49157435180119935, "learning_rate": 3.7862300323735835e-05, "loss": 0.588, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5119615344916871, "learning_rate": 3.783678920503983e-05, "loss": 0.59, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.4365865466918359, "learning_rate": 3.781113546385265e-05, "loss": 0.5908, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.46624162514759265, "learning_rate": 3.7785339305300916e-05, "loss": 0.5914, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5891511750472989, "learning_rate": 3.7759400935650025e-05, "loss": 0.5909, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5242655492151053, "learning_rate": 3.77333205623025e-05, "loss": 0.5773, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.5174100838406573, "learning_rate": 3.7707098393796295e-05, "loss": 0.5857, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5426543725114813, "learning_rate": 3.7680734639803185e-05, "loss": 0.6016, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5490277331179183, "learning_rate": 3.765422951112704e-05, "loss": 0.5858, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.4017038611631924, "learning_rate": 3.762758321970216e-05, "loss": 0.5998, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.42969623713566607, "learning_rate": 3.7600795978591584e-05, "loss": 0.5923, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.4578999420395149, "learning_rate": 3.757386800198538e-05, "loss": 0.5814, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.42038847366295296, "learning_rate": 3.7546799505198925e-05, "loss": 0.5922, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.4927326663594715, "learning_rate": 3.7519590704671197e-05, "loss": 0.5897, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.7634682670510429, "learning_rate": 3.749224181796305e-05, "loss": 0.5981, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.6060651265295243, "learning_rate": 3.746475306375545e-05, "loss": 0.5936, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5486492081389972, "learning_rate": 3.743712466184774e-05, "loss": 0.5797, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.585229658231713, "learning_rate": 3.7409356833155885e-05, "loss": 0.5828, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.5698259936186569, "learning_rate": 3.73814497997107e-05, "loss": 0.5953, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.6469266870618808, "learning_rate": 3.7353403784656095e-05, "loss": 0.5899, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.4595976384778677, "learning_rate": 3.732521901224724e-05, "loss": 0.5935, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6970429018921385, "learning_rate": 3.7296895707848844e-05, "loss": 0.5981, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.6820420972052915, "learning_rate": 3.7268434097933275e-05, "loss": 0.5828, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.4651372593497201, "learning_rate": 3.723983441007882e-05, "loss": 0.5937, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5140916553253816, "learning_rate": 3.721109687296781e-05, "loss": 0.5816, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.6024426918159069, "learning_rate": 3.718222171638484e-05, "loss": 0.5907, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.7317715283545044, "learning_rate": 3.715320917121488e-05, "loss": 0.5817, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.44971283065000234, "learning_rate": 3.712405946944149e-05, "loss": 0.5918, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6939847523224308, "learning_rate": 3.709477284414488e-05, "loss": 0.5794, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.61058286396214, "learning_rate": 3.7065349529500136e-05, "loss": 0.5796, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.5009181781118767, "learning_rate": 3.7035789760775305e-05, "loss": 0.583, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.895931558309035, "learning_rate": 3.70060937743295e-05, "loss": 0.5858, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.9613069791398011, "learning_rate": 3.6976261807611045e-05, "loss": 0.5879, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.36196206984580304, "learning_rate": 3.694629409915555e-05, "loss": 0.5827, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6173974966756283, "learning_rate": 3.691619088858401e-05, "loss": 0.5768, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5951741766611666, "learning_rate": 3.68859524166009e-05, "loss": 0.5938, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.395824645933242, "learning_rate": 3.6855578924992226e-05, "loss": 0.5891, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.5844092783060882, "learning_rate": 3.6825070656623626e-05, "loss": 0.5818, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.5447279620615895, "learning_rate": 3.67944278554384e-05, "loss": 0.5961, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4625700664624749, "learning_rate": 3.676365076645557e-05, "loss": 0.5756, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.7695877231139978, "learning_rate": 3.673273963576791e-05, "loss": 0.5908, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6582553066801797, "learning_rate": 3.670169471054001e-05, "loss": 0.5849, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.46082019289435333, "learning_rate": 3.6670516239006254e-05, "loss": 0.6051, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.5657417195857356, "learning_rate": 3.663920447046888e-05, "loss": 0.5884, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.46608736985085514, "learning_rate": 3.6607759655295954e-05, "loss": 0.5807, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5029726891534637, "learning_rate": 3.657618204491937e-05, "loss": 0.5885, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.4495596165407664, "learning_rate": 3.6544471891832875e-05, "loss": 0.5846, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.3878410261449997, "learning_rate": 3.6512629449589983e-05, "loss": 0.5841, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.43597615587216537, "learning_rate": 3.6480654972802045e-05, "loss": 0.5924, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.3888055035169622, "learning_rate": 3.644854871713611e-05, "loss": 0.5921, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.39781755991047896, "learning_rate": 3.6416310939312924e-05, "loss": 0.5825, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.42469353688483713, "learning_rate": 3.638394189710493e-05, "loss": 0.5816, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.44972214755792506, "learning_rate": 3.635144184933412e-05, "loss": 0.5984, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.48010456834262777, "learning_rate": 3.6318811055869994e-05, "loss": 0.5857, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.47269226371714274, "learning_rate": 3.628604977762752e-05, "loss": 0.5857, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.4472277554948365, "learning_rate": 3.6253158276565004e-05, "loss": 0.5881, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.4313846923244479, "learning_rate": 3.6220136815682016e-05, "loss": 0.5848, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.4993824897587496, "learning_rate": 3.618698565901727e-05, "loss": 0.5894, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.7075545799739866, "learning_rate": 3.615370507164654e-05, "loss": 0.5829, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.48584529065381554, "learning_rate": 3.61202953196805e-05, "loss": 0.5906, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.5056915158427379, "learning_rate": 3.6086756670262654e-05, "loss": 0.5811, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.65969257153899, "learning_rate": 3.6053089391567135e-05, "loss": 0.5827, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.5537149353815661, "learning_rate": 3.601929375279662e-05, "loss": 0.6002, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.6120186834923397, "learning_rate": 3.598537002418012e-05, "loss": 0.5893, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.3756055632290216, "learning_rate": 3.5951318476970885e-05, "loss": 0.5793, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.37317115526420075, "learning_rate": 3.591713938344416e-05, "loss": 0.5755, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.5145181523703846, "learning_rate": 3.588283301689507e-05, "loss": 0.5808, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.6266866757774687, "learning_rate": 3.5848399651636424e-05, "loss": 0.5847, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.44859597987833943, "learning_rate": 3.5813839562996473e-05, "loss": 0.5876, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.48817876890673234, "learning_rate": 3.5779153027316775e-05, "loss": 0.5676, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.42680224481619605, "learning_rate": 3.574434032194994e-05, "loss": 0.5905, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.4863600780863088, "learning_rate": 3.5709401725257436e-05, "loss": 0.5909, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.35094415377677035, "learning_rate": 3.5674337516607346e-05, "loss": 0.588, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.41032308501089465, "learning_rate": 3.563914797637216e-05, "loss": 0.5791, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.4638672728197637, "learning_rate": 3.560383338592649e-05, "loss": 0.6032, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.4473661634207172, "learning_rate": 3.556839402764487e-05, "loss": 0.5859, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.4011419156482702, "learning_rate": 3.553283018489946e-05, "loss": 0.58, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.40878948621792033, "learning_rate": 3.54971421420578e-05, "loss": 0.5953, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.40025676903021096, "learning_rate": 3.5461330184480524e-05, "loss": 0.5769, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.51896484034032, "learning_rate": 3.54253945985191e-05, "loss": 0.5766, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4356651019596482, "learning_rate": 3.5389335671513524e-05, "loss": 0.5906, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.40628440976894575, "learning_rate": 3.5353153691789986e-05, "loss": 0.5859, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.43665031973054863, "learning_rate": 3.531684894865866e-05, "loss": 0.5841, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.40001459733312456, "learning_rate": 3.528042173241128e-05, "loss": 0.5868, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4425878838739277, "learning_rate": 3.524387233431892e-05, "loss": 0.5754, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.36732440716998394, "learning_rate": 3.520720104662958e-05, "loss": 0.602, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.4365579685858625, "learning_rate": 3.5170408162565904e-05, "loss": 0.5841, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.43592443411183174, "learning_rate": 3.513349397632281e-05, "loss": 0.574, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.44157554891711326, "learning_rate": 3.5096458783065145e-05, "loss": 0.5835, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.39705807787475933, "learning_rate": 3.505930287892533e-05, "loss": 0.5905, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.476257856512208, "learning_rate": 3.502202656100099e-05, "loss": 0.5923, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5184032257765657, "learning_rate": 3.498463012735256e-05, "loss": 0.5889, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.5234073361731034, "learning_rate": 3.494711387700094e-05, "loss": 0.5928, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.4266633157644462, "learning_rate": 3.490947810992505e-05, "loss": 0.5876, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.4256921828364436, "learning_rate": 3.48717231270595e-05, "loss": 0.5811, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.40863526199400035, "learning_rate": 3.483384923029211e-05, "loss": 0.5967, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.40935269863586743, "learning_rate": 3.479585672246156e-05, "loss": 0.5915, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.43570219163265833, "learning_rate": 3.4757745907354924e-05, "loss": 0.5967, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4130647227219362, "learning_rate": 3.471951708970527e-05, "loss": 0.584, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.3906983105456478, "learning_rate": 3.468117057518921e-05, "loss": 0.5815, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.5591744322067574, "learning_rate": 3.4642706670424426e-05, "loss": 0.581, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.4620756834156378, "learning_rate": 3.460412568296731e-05, "loss": 0.5907, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.43122212359797785, "learning_rate": 3.456542792131039e-05, "loss": 0.5872, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.47974599126765616, "learning_rate": 3.4526613694879936e-05, "loss": 0.5965, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.37614150780037536, "learning_rate": 3.448768331403348e-05, "loss": 0.572, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.39159809985017585, "learning_rate": 3.44486370900573e-05, "loss": 0.5783, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.4719498205789532, "learning_rate": 3.440947533516396e-05, "loss": 0.5898, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.40020635903690216, "learning_rate": 3.4370198362489816e-05, "loss": 0.5843, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.46391831220787255, "learning_rate": 3.43308064860925e-05, "loss": 0.5851, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.36899712158701475, "learning_rate": 3.4291300020948393e-05, "loss": 0.5883, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.47379367739494715, "learning_rate": 3.425167928295015e-05, "loss": 0.5854, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.4976125474093888, "learning_rate": 3.421194458890411e-05, "loss": 0.574, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.49963817386815745, "learning_rate": 3.4172096256527865e-05, "loss": 0.5872, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.4657675363657139, "learning_rate": 3.4132134604447595e-05, "loss": 0.5788, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.5080184845456196, "learning_rate": 3.409205995219561e-05, "loss": 0.5709, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.42654623412596265, "learning_rate": 3.4051872620207765e-05, "loss": 0.5864, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.362465300462791, "learning_rate": 3.40115729298209e-05, "loss": 0.5838, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.4468604606049936, "learning_rate": 3.397116120327025e-05, "loss": 0.5807, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.4081516211317525, "learning_rate": 3.3930637763686916e-05, "loss": 0.5756, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.4013965240688019, "learning_rate": 3.389000293509524e-05, "loss": 0.5774, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.4144301498360425, "learning_rate": 3.3849257042410225e-05, "loss": 0.5637, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.4904041330150964, "learning_rate": 3.380840041143494e-05, "loss": 0.5725, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.3994437365525792, "learning_rate": 3.376743336885792e-05, "loss": 0.5878, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4911276019524593, "learning_rate": 3.372635624225055e-05, "loss": 0.5868, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.49432760071358534, "learning_rate": 3.3685169360064445e-05, "loss": 0.5775, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4193261249958042, "learning_rate": 3.3643873051628804e-05, "loss": 0.5845, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.37031716366612977, "learning_rate": 3.3602467647147814e-05, "loss": 0.5875, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.4295233876351392, "learning_rate": 3.356095347769799e-05, "loss": 0.5913, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.4548291355076105, "learning_rate": 3.351933087522552e-05, "loss": 0.5755, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.5001143264584728, "learning_rate": 3.3477600172543626e-05, "loss": 0.5754, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.39577847191841864, "learning_rate": 3.3435761703329894e-05, "loss": 0.5924, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.4791580122776765, "learning_rate": 3.3393815802123606e-05, "loss": 0.5786, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.5619938618029915, "learning_rate": 3.335176280432308e-05, "loss": 0.5929, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.4275220861957953, "learning_rate": 3.330960304618295e-05, "loss": 0.5788, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4314841149826118, "learning_rate": 3.326733686481153e-05, "loss": 0.5811, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.45761221019935006, "learning_rate": 3.3224964598168084e-05, "loss": 0.5826, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.4495860119756415, "learning_rate": 3.318248658506012e-05, "loss": 0.5773, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.5024976164330925, "learning_rate": 3.313990316514069e-05, "loss": 0.5846, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.39243259470299385, "learning_rate": 3.309721467890571e-05, "loss": 0.5793, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.3635420943381022, "learning_rate": 3.305442146769115e-05, "loss": 0.5851, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.5701863896395498, "learning_rate": 3.30115238736704e-05, "loss": 0.5775, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.45955414817043055, "learning_rate": 3.296852223985148e-05, "loss": 0.5805, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.37025395579997267, "learning_rate": 3.2925416910074315e-05, "loss": 0.5879, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.4501685630968794, "learning_rate": 3.288220822900796e-05, "loss": 0.5761, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.3895616794578641, "learning_rate": 3.283889654214788e-05, "loss": 0.5852, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.3530342161686175, "learning_rate": 3.279548219581317e-05, "loss": 0.5964, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.4445386072001585, "learning_rate": 3.275196553714379e-05, "loss": 0.5893, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.35364661297576705, "learning_rate": 3.270834691409778e-05, "loss": 0.5862, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.47072448850778137, "learning_rate": 3.266462667544849e-05, "loss": 0.5684, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.36259573847755067, "learning_rate": 3.262080517078178e-05, "loss": 0.5775, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.43872881963705596, "learning_rate": 3.257688275049323e-05, "loss": 0.5871, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.5142114923747332, "learning_rate": 3.253285976578535e-05, "loss": 0.5898, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.315034902208789, "learning_rate": 3.2488736568664756e-05, "loss": 0.5821, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.5778380242647284, "learning_rate": 3.244451351193935e-05, "loss": 0.5879, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.41280489951186455, "learning_rate": 3.240019094921551e-05, "loss": 0.5808, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.5133731784599911, "learning_rate": 3.235576923489527e-05, "loss": 0.5662, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.4686813564814689, "learning_rate": 3.2311248724173476e-05, "loss": 0.5839, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.49585506647580746, "learning_rate": 3.226662977303494e-05, "loss": 0.5914, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.5065065583094107, "learning_rate": 3.2221912738251626e-05, "loss": 0.5926, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.44372236063902326, "learning_rate": 3.2177097977379736e-05, "loss": 0.5774, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.464100437408751, "learning_rate": 3.21321858487569e-05, "loss": 0.586, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4881011447564086, "learning_rate": 3.208717671149931e-05, "loss": 0.5733, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.42546135376410105, "learning_rate": 3.204207092549882e-05, "loss": 0.5808, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.3993250653068562, "learning_rate": 3.19968688514201e-05, "loss": 0.5848, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.4290417029071681, "learning_rate": 3.195157085069774e-05, "loss": 0.5774, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.429136101479987, "learning_rate": 3.190617728553332e-05, "loss": 0.5742, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.36307327164735614, "learning_rate": 3.1860688518892606e-05, "loss": 0.5816, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4680960427116546, "learning_rate": 3.181510491450254e-05, "loss": 0.5793, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.4944778485758311, "learning_rate": 3.176942683684842e-05, "loss": 0.5838, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.37490430938156255, "learning_rate": 3.1723654651170934e-05, "loss": 0.5781, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.38163098497903397, "learning_rate": 3.167778872346327e-05, "loss": 0.5774, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.4883131179129975, "learning_rate": 3.163182942046815e-05, "loss": 0.5779, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.4098261034973883, "learning_rate": 3.158577710967494e-05, "loss": 0.5822, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.35559027853758957, "learning_rate": 3.153963215931669e-05, "loss": 0.5698, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.42218981570032543, "learning_rate": 3.14933949383672e-05, "loss": 0.5705, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.3346873222140708, "learning_rate": 3.144706581653805e-05, "loss": 0.5922, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.408495525785712, "learning_rate": 3.140064516427566e-05, "loss": 0.5845, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.3203753585453229, "learning_rate": 3.135413335275833e-05, "loss": 0.5776, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.38765716095372504, "learning_rate": 3.130753075389327e-05, "loss": 0.5717, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.36350627086577225, "learning_rate": 3.1260837740313625e-05, "loss": 0.5858, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.4612900445305953, "learning_rate": 3.121405468537547e-05, "loss": 0.57, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.3738190273132149, "learning_rate": 3.116718196315488e-05, "loss": 0.5797, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4086975238367636, "learning_rate": 3.1120219948444894e-05, "loss": 0.5656, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.33400035963369773, "learning_rate": 3.107316901675252e-05, "loss": 0.5762, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.35508413990894855, "learning_rate": 3.1026029544295745e-05, "loss": 0.5844, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.3897982658250479, "learning_rate": 3.097880190800057e-05, "loss": 0.5833, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.40101747093134793, "learning_rate": 3.093148648549788e-05, "loss": 0.5736, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.3816059667765972, "learning_rate": 3.088408365512055e-05, "loss": 0.5733, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.4635851969052653, "learning_rate": 3.083659379590034e-05, "loss": 0.5818, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.3746271762669072, "learning_rate": 3.0789017287564913e-05, "loss": 0.5808, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.6228339620192107, "learning_rate": 3.074135451053475e-05, "loss": 0.5687, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3759902917186176, "learning_rate": 3.069360584592015e-05, "loss": 0.5749, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.445721260445949, "learning_rate": 3.064577167551816e-05, "loss": 0.5696, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.37346782595656497, "learning_rate": 3.059785238180953e-05, "loss": 0.5832, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.3988639227697271, "learning_rate": 3.054984834795566e-05, "loss": 0.5784, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.38899155955350884, "learning_rate": 3.0501759957795537e-05, "loss": 0.5782, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.3889034521759632, "learning_rate": 3.0453587595842627e-05, "loss": 0.5809, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.34817117015726357, "learning_rate": 3.0405331647281856e-05, "loss": 0.5783, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.3663110954108221, "learning_rate": 3.0356992497966508e-05, "loss": 0.5625, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3623939771298832, "learning_rate": 3.0308570534415137e-05, "loss": 0.5816, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.4140002749710151, "learning_rate": 3.0260066143808467e-05, "loss": 0.5838, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.32808767852537324, "learning_rate": 3.021147971398632e-05, "loss": 0.5714, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.42073545721989564, "learning_rate": 3.0162811633444478e-05, "loss": 0.5828, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.37881858248565364, "learning_rate": 3.0114062291331635e-05, "loss": 0.584, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.3154169964245379, "learning_rate": 3.0065232077446217e-05, "loss": 0.5867, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.34128728119429386, "learning_rate": 3.001632138223332e-05, "loss": 0.5709, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.4616133624203812, "learning_rate": 2.9967330596781565e-05, "loss": 0.529, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.4841655775166307, "learning_rate": 2.9918260112819952e-05, "loss": 0.5073, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5453023624982727, "learning_rate": 2.9869110322714778e-05, "loss": 0.5248, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5249710530830061, "learning_rate": 2.9819881619466447e-05, "loss": 0.5075, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.5616878513713486, "learning_rate": 2.9770574396706364e-05, "loss": 0.5132, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.42834575546183445, "learning_rate": 2.972118904869376e-05, "loss": 0.5251, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.5880593274728451, "learning_rate": 2.9671725970312563e-05, "loss": 0.5125, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.48388561048544, "learning_rate": 2.9622185557068238e-05, "loss": 0.5066, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.49300983869149034, "learning_rate": 2.95725682050846e-05, "loss": 0.4981, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.562659617546423, "learning_rate": 2.9522874311100684e-05, "loss": 0.5139, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.425696942621046, "learning_rate": 2.9473104272467526e-05, "loss": 0.5151, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.5004223781150227, "learning_rate": 2.942325848714505e-05, "loss": 0.5013, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.4562247655853067, "learning_rate": 2.9373337353698804e-05, "loss": 0.5002, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.47760300964364316, "learning_rate": 2.932334127129686e-05, "loss": 0.5155, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.45546594103403903, "learning_rate": 2.9273270639706547e-05, "loss": 0.5026, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.4105144126429356, "learning_rate": 2.922312585929131e-05, "loss": 0.5127, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.34239944004224504, "learning_rate": 2.9172907331007478e-05, "loss": 0.515, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.4662083012002479, "learning_rate": 2.9122615456401053e-05, "loss": 0.515, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.3703117439456717, "learning_rate": 2.9072250637604535e-05, "loss": 0.5096, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3684176846861193, "learning_rate": 2.9021813277333667e-05, "loss": 0.5064, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.41260423166103205, "learning_rate": 2.8971303778884244e-05, "loss": 0.5116, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.29313902649404, "learning_rate": 2.8920722546128863e-05, "loss": 0.5133, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.3723915514270263, "learning_rate": 2.887006998351372e-05, "loss": 0.5219, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3699395052300313, "learning_rate": 2.881934649605535e-05, "loss": 0.5174, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.41069478092283507, "learning_rate": 2.8768552489337408e-05, "loss": 0.5096, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.36688676914617285, "learning_rate": 2.8717688369507425e-05, "loss": 0.5155, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.4195832604000225, "learning_rate": 2.8666754543273535e-05, "loss": 0.5178, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.35684640427520364, "learning_rate": 2.8615751417901273e-05, "loss": 0.517, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3371510304719831, "learning_rate": 2.856467940121025e-05, "loss": 0.5097, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.3815531475295617, "learning_rate": 2.8513538901570964e-05, "loss": 0.5134, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.2923188432959191, "learning_rate": 2.846233032790149e-05, "loss": 0.5119, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.3703235414926014, "learning_rate": 2.84110540896642e-05, "loss": 0.5147, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.305274981618383, "learning_rate": 2.8359710596862555e-05, "loss": 0.5157, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.3660136669015862, "learning_rate": 2.8308300260037734e-05, "loss": 0.5078, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.3281467816819499, "learning_rate": 2.8256823490265424e-05, "loss": 0.5108, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.33657288331500623, "learning_rate": 2.8205280699152515e-05, "loss": 0.5149, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.30969235525444777, "learning_rate": 2.8153672298833777e-05, "loss": 0.5125, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3487088723890818, "learning_rate": 2.8101998701968615e-05, "loss": 0.5128, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.3726914625364127, "learning_rate": 2.805026032173773e-05, "loss": 0.5155, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3605053522938795, "learning_rate": 2.7998457571839832e-05, "loss": 0.5213, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.3354964413307366, "learning_rate": 2.7946590866488322e-05, "loss": 0.5168, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.36010557483768113, "learning_rate": 2.7894660620408e-05, "loss": 0.5144, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.4965059789816826, "learning_rate": 2.784266724883173e-05, "loss": 0.5099, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.33548090423036525, "learning_rate": 2.7790611167497128e-05, "loss": 0.5132, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3925194469909624, "learning_rate": 2.7738492792643224e-05, "loss": 0.5171, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.39046304165012247, "learning_rate": 2.768631254100716e-05, "loss": 0.5126, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.4553151275790691, "learning_rate": 2.7634070829820836e-05, "loss": 0.5261, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.37667643869132705, "learning_rate": 2.7581768076807592e-05, "loss": 0.5154, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.6740557027602709, "learning_rate": 2.7529404700178832e-05, "loss": 0.5255, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.40913671686454595, "learning_rate": 2.7476981118630735e-05, "loss": 0.5236, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.3238551053975326, "learning_rate": 2.742449775134085e-05, "loss": 0.5046, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.3819450089959347, "learning_rate": 2.7371955017964788e-05, "loss": 0.5105, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.41294460126980065, "learning_rate": 2.7319353338632845e-05, "loss": 0.5248, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.33645149060379737, "learning_rate": 2.7266693133946645e-05, "loss": 0.5172, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.36226713122769794, "learning_rate": 2.7213974824975785e-05, "loss": 0.5142, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3876501941232757, "learning_rate": 2.7161198833254464e-05, "loss": 0.5173, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3897100686114734, "learning_rate": 2.7108365580778095e-05, "loss": 0.526, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3222954766324042, "learning_rate": 2.705547548999996e-05, "loss": 0.5089, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.33161211626768006, "learning_rate": 2.7002528983827817e-05, "loss": 0.5022, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.3811120919318282, "learning_rate": 2.6949526485620517e-05, "loss": 0.5121, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3731403818815151, "learning_rate": 2.6896468419184623e-05, "loss": 0.5207, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.35876136856719404, "learning_rate": 2.6843355208771024e-05, "loss": 0.5132, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3696218410090677, "learning_rate": 2.6790187279071536e-05, "loss": 0.5177, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4477433354562586, "learning_rate": 2.67369650552155e-05, "loss": 0.5107, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.337025815351157, "learning_rate": 2.6683688962766407e-05, "loss": 0.5219, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.32575877509837664, "learning_rate": 2.6630359427718468e-05, "loss": 0.5151, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3306654180371296, "learning_rate": 2.6576976876493225e-05, "loss": 0.5112, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.34550128016256226, "learning_rate": 2.652354173593614e-05, "loss": 0.5088, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.3400173981355111, "learning_rate": 2.647005443331317e-05, "loss": 0.5072, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3345996114164319, "learning_rate": 2.6416515396307354e-05, "loss": 0.5154, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3445404249123143, "learning_rate": 2.636292505301542e-05, "loss": 0.5175, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.32490055235506304, "learning_rate": 2.630928383194431e-05, "loss": 0.5157, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3230398827392262, "learning_rate": 2.625559216200781e-05, "loss": 0.5293, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3140245790083967, "learning_rate": 2.620185047252308e-05, "loss": 0.5241, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.3225718179591085, "learning_rate": 2.614805919320723e-05, "loss": 0.5151, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3020248382466392, "learning_rate": 2.6094218754173895e-05, "loss": 0.5108, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.35115106899373644, "learning_rate": 2.60403295859298e-05, "loss": 0.5154, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3416859792967509, "learning_rate": 2.5986392119371297e-05, "loss": 0.5066, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.36514628575055125, "learning_rate": 2.5932406785780928e-05, "loss": 0.5163, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.38449639609933767, "learning_rate": 2.5878374016823987e-05, "loss": 0.5292, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.37794205078470755, "learning_rate": 2.5824294244545045e-05, "loss": 0.5182, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.3611518337000464, "learning_rate": 2.577016790136453e-05, "loss": 0.5214, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.4435281927893701, "learning_rate": 2.5715995420075225e-05, "loss": 0.5165, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.34749053695754195, "learning_rate": 2.5661777233838864e-05, "loss": 0.5246, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.43964414183434614, "learning_rate": 2.5607513776182616e-05, "loss": 0.5132, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3597993812476438, "learning_rate": 2.5553205480995633e-05, "loss": 0.5182, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.39963473928491655, "learning_rate": 2.5498852782525604e-05, "loss": 0.5231, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3341864753714615, "learning_rate": 2.5444456115375252e-05, "loss": 0.5148, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.34493159857194344, "learning_rate": 2.539001591449889e-05, "loss": 0.5187, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.35063789248000937, "learning_rate": 2.53355326151989e-05, "loss": 0.5036, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.33739318698962373, "learning_rate": 2.5281006653122288e-05, "loss": 0.5139, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.33268396308246667, "learning_rate": 2.5226438464257217e-05, "loss": 0.5088, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3343828876347694, "learning_rate": 2.5171828484929447e-05, "loss": 0.5097, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.4027986116968729, "learning_rate": 2.5117177151798934e-05, "loss": 0.513, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.32697185625411995, "learning_rate": 2.506248490185627e-05, "loss": 0.517, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.3824979769729423, "learning_rate": 2.500775217241923e-05, "loss": 0.5265, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3230140092546599, "learning_rate": 2.4952979401129266e-05, "loss": 0.5208, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3794242183500647, "learning_rate": 2.4898167025948e-05, "loss": 0.5072, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.34138351461441213, "learning_rate": 2.4843315485153703e-05, "loss": 0.5176, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.424697460194382, "learning_rate": 2.4788425217337856e-05, "loss": 0.519, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.39537899474735544, "learning_rate": 2.4733496661401572e-05, "loss": 0.5192, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.37669514131772985, "learning_rate": 2.4678530256552114e-05, "loss": 0.5241, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.452705825188183, "learning_rate": 2.46235264422994e-05, "loss": 0.523, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.411396067796578, "learning_rate": 2.4568485658452452e-05, "loss": 0.5262, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.3739120110382456, "learning_rate": 2.451340834511592e-05, "loss": 0.5202, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.4104778261310893, "learning_rate": 2.4458294942686528e-05, "loss": 0.5061, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.42335710364512963, "learning_rate": 2.440314589184958e-05, "loss": 0.5203, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.35577799875859734, "learning_rate": 2.434796163357541e-05, "loss": 0.5159, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3831260351088632, "learning_rate": 2.429274260911588e-05, "loss": 0.5146, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.34851260825090713, "learning_rate": 2.423748926000084e-05, "loss": 0.5144, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3875073822291589, "learning_rate": 2.418220202803459e-05, "loss": 0.5184, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3027398045762043, "learning_rate": 2.412688135529237e-05, "loss": 0.5118, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3387873034662186, "learning_rate": 2.4071527684116807e-05, "loss": 0.5226, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.32506869764923313, "learning_rate": 2.4016141457114372e-05, "loss": 0.5208, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.33898742717876335, "learning_rate": 2.396072311715187e-05, "loss": 0.5348, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3192832415427228, "learning_rate": 2.3905273107352863e-05, "loss": 0.5153, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.33881468140364684, "learning_rate": 2.3849791871094157e-05, "loss": 0.5129, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.2988702775656352, "learning_rate": 2.379427985200223e-05, "loss": 0.5118, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3166042811287194, "learning_rate": 2.373873749394972e-05, "loss": 0.5178, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.33743613141848927, "learning_rate": 2.3683165241051836e-05, "loss": 0.5109, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.33593039507986017, "learning_rate": 2.3627563537662823e-05, "loss": 0.5268, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.32666666932197874, "learning_rate": 2.3571932828372433e-05, "loss": 0.5107, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3279248384996737, "learning_rate": 2.351627355800233e-05, "loss": 0.514, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.30688394578368106, "learning_rate": 2.346058617160256e-05, "loss": 0.5111, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.3174514410609214, "learning_rate": 2.3404871114447976e-05, "loss": 0.5275, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.35843046917161897, "learning_rate": 2.334912883203469e-05, "loss": 0.5245, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.31761658805421217, "learning_rate": 2.3293359770076505e-05, "loss": 0.507, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.37730505855229285, "learning_rate": 2.323756437450136e-05, "loss": 0.5223, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.2876991488953251, "learning_rate": 2.3181743091447754e-05, "loss": 0.5194, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.43820694826958523, "learning_rate": 2.3125896367261164e-05, "loss": 0.5067, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.3210252455000504, "learning_rate": 2.307002464849052e-05, "loss": 0.4954, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.3611829178161809, "learning_rate": 2.30141283818846e-05, "loss": 0.52, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3076954351627943, "learning_rate": 2.2958208014388462e-05, "loss": 0.5138, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3183656954656659, "learning_rate": 2.2902263993139857e-05, "loss": 0.5316, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.36339519548309956, "learning_rate": 2.2846296765465708e-05, "loss": 0.5208, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.2908500596974759, "learning_rate": 2.2790306778878465e-05, "loss": 0.5233, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.3290224881498389, "learning_rate": 2.273429448107257e-05, "loss": 0.5185, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.30100835867522713, "learning_rate": 2.2678260319920868e-05, "loss": 0.506, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.31703736664224635, "learning_rate": 2.262220474347102e-05, "loss": 0.5215, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3487119720895661, "learning_rate": 2.2566128199941918e-05, "loss": 0.5157, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.27776072659428436, "learning_rate": 2.2510031137720104e-05, "loss": 0.5185, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.4236319948963463, "learning_rate": 2.2453914005356206e-05, "loss": 0.5183, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.337570158088462, "learning_rate": 2.2397777251561302e-05, "loss": 0.511, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3486895449018145, "learning_rate": 2.2341621325203393e-05, "loss": 0.5065, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.4075769134124715, "learning_rate": 2.2285446675303764e-05, "loss": 0.5217, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.29461078731562146, "learning_rate": 2.2229253751033423e-05, "loss": 0.52, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.384227184965198, "learning_rate": 2.2173043001709492e-05, "loss": 0.5173, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3361429484659011, "learning_rate": 2.2116814876791627e-05, "loss": 0.506, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.364622190904082, "learning_rate": 2.2060569825878413e-05, "loss": 0.52, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.3430939593263435, "learning_rate": 2.2004308298703777e-05, "loss": 0.5181, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3425518385573039, "learning_rate": 2.1948030745133396e-05, "loss": 0.5123, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3525306359926485, "learning_rate": 2.1891737615161083e-05, "loss": 0.5225, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3253807514584669, "learning_rate": 2.1835429358905218e-05, "loss": 0.5251, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.272620248184193, "learning_rate": 2.17791064266051e-05, "loss": 0.5141, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.3897448104265427, "learning_rate": 2.172276926861741e-05, "loss": 0.5216, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.27304361576786396, "learning_rate": 2.166641833541255e-05, "loss": 0.5238, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3856814917193331, "learning_rate": 2.161005407757109e-05, "loss": 0.5024, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.37523942392409415, "learning_rate": 2.155367694578013e-05, "loss": 0.5182, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.35446335091598064, "learning_rate": 2.1497287390829712e-05, "loss": 0.5162, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.44727181833815416, "learning_rate": 2.1440885863609208e-05, "loss": 0.5077, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.30147042394176127, "learning_rate": 2.1384472815103737e-05, "loss": 0.515, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.4317955311731039, "learning_rate": 2.1328048696390534e-05, "loss": 0.5194, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.2706033193987954, "learning_rate": 2.1271613958635342e-05, "loss": 0.5102, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.4494893834009883, "learning_rate": 2.1215169053088825e-05, "loss": 0.5144, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.33529177865482285, "learning_rate": 2.1158714431082937e-05, "loss": 0.5174, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3911780458419764, "learning_rate": 2.110225054402733e-05, "loss": 0.5255, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.42687652647402174, "learning_rate": 2.1045777843405747e-05, "loss": 0.5333, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.32226126551954215, "learning_rate": 2.09892967807724e-05, "loss": 0.5154, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.4542482842715895, "learning_rate": 2.093280780774835e-05, "loss": 0.5085, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.3031183068856153, "learning_rate": 2.087631137601793e-05, "loss": 0.519, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3949563253337484, "learning_rate": 2.0819807937325104e-05, "loss": 0.5265, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.322802179021318, "learning_rate": 2.0763297943469847e-05, "loss": 0.5097, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.3446515565745692, "learning_rate": 2.070678184630458e-05, "loss": 0.5249, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.36113574022128764, "learning_rate": 2.06502600977305e-05, "loss": 0.5139, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.27760141324099896, "learning_rate": 2.0593733149694008e-05, "loss": 0.5035, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.32441744199378597, "learning_rate": 2.0537201454183074e-05, "loss": 0.526, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.27784622056349606, "learning_rate": 2.0480665463223626e-05, "loss": 0.5234, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.30670238696106455, "learning_rate": 2.042412562887594e-05, "loss": 0.5125, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.256751589287175, "learning_rate": 2.0367582403231033e-05, "loss": 0.5093, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.28304308837631426, "learning_rate": 2.0311036238407023e-05, "loss": 0.5044, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.2651034556215472, "learning_rate": 2.0254487586545534e-05, "loss": 0.515, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.2728132024678006, "learning_rate": 2.0197936899808088e-05, "loss": 0.5121, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.2715664437118818, "learning_rate": 2.0141384630372466e-05, "loss": 0.5275, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.29006534996695105, "learning_rate": 2.0084831230429106e-05, "loss": 0.5074, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.2715703084645425, "learning_rate": 2.0028277152177492e-05, "loss": 0.5107, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.33808189280611106, "learning_rate": 1.9971722847822518e-05, "loss": 0.5195, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.28377220167069384, "learning_rate": 1.99151687695709e-05, "loss": 0.5212, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2974087822429702, "learning_rate": 1.9858615369627537e-05, "loss": 0.521, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.25345214763748103, "learning_rate": 1.9802063100191916e-05, "loss": 0.522, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.28476702561911166, "learning_rate": 1.974551241345447e-05, "loss": 0.5215, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.2732775645954896, "learning_rate": 1.9688963761592984e-05, "loss": 0.5152, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.30057345033886673, "learning_rate": 1.963241759676897e-05, "loss": 0.5059, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.28477720989583605, "learning_rate": 1.9575874371124066e-05, "loss": 0.5156, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.30428593673400045, "learning_rate": 1.951933453677638e-05, "loss": 0.5223, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.2803287115011706, "learning_rate": 1.9462798545816932e-05, "loss": 0.528, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.307966887568033, "learning_rate": 1.9406266850305996e-05, "loss": 0.502, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.30874631303593253, "learning_rate": 1.9349739902269503e-05, "loss": 0.5159, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.33221966034274536, "learning_rate": 1.9293218153695425e-05, "loss": 0.5264, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.33190481688429696, "learning_rate": 1.9236702056530153e-05, "loss": 0.5048, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.3679789233171999, "learning_rate": 1.9180192062674907e-05, "loss": 0.5211, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.2693530749005987, "learning_rate": 1.9123688623982076e-05, "loss": 0.5198, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3572501985860057, "learning_rate": 1.906719219225165e-05, "loss": 0.5071, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.2815225561387077, "learning_rate": 1.9010703219227603e-05, "loss": 0.521, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.3574020017195305, "learning_rate": 1.8954222156594256e-05, "loss": 0.5175, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.2954426841821671, "learning_rate": 1.8897749455972673e-05, "loss": 0.514, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.38069602250970047, "learning_rate": 1.884128556891707e-05, "loss": 0.5242, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.29816800844978636, "learning_rate": 1.878483094691119e-05, "loss": 0.5012, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.3558269679203087, "learning_rate": 1.8728386041364664e-05, "loss": 0.5101, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.284739607636165, "learning_rate": 1.867195130360947e-05, "loss": 0.5108, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.360527356217755, "learning_rate": 1.8615527184896263e-05, "loss": 0.5111, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.2620487669189305, "learning_rate": 1.8559114136390795e-05, "loss": 0.5185, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.30565747331080256, "learning_rate": 1.8502712609170298e-05, "loss": 0.4986, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.28807061886755153, "learning_rate": 1.8446323054219876e-05, "loss": 0.5093, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.3314251105301034, "learning_rate": 1.838994592242891e-05, "loss": 0.5102, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.2880897813656077, "learning_rate": 1.8333581664587453e-05, "loss": 0.5084, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3604693133505654, "learning_rate": 1.8277230731382593e-05, "loss": 0.5075, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.2661195921757332, "learning_rate": 1.82208935733949e-05, "loss": 0.4962, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.3764670243816647, "learning_rate": 1.8164570641094793e-05, "loss": 0.5099, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.27405391736334955, "learning_rate": 1.810826238483892e-05, "loss": 0.5082, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.3010213866388687, "learning_rate": 1.8051969254866608e-05, "loss": 0.5156, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.31169839327737014, "learning_rate": 1.7995691701296226e-05, "loss": 0.5045, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.27814746060436946, "learning_rate": 1.7939430174121593e-05, "loss": 0.5113, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.3144002854577958, "learning_rate": 1.788318512320838e-05, "loss": 0.5166, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.30941437854467874, "learning_rate": 1.782695699829051e-05, "loss": 0.5069, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.3121394353295585, "learning_rate": 1.7770746248966587e-05, "loss": 0.502, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.2759153639196326, "learning_rate": 1.7714553324696243e-05, "loss": 0.4943, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.2831686342453077, "learning_rate": 1.7658378674796614e-05, "loss": 0.5068, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.27361148899114984, "learning_rate": 1.76022227484387e-05, "loss": 0.5079, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.29657890231076645, "learning_rate": 1.7546085994643807e-05, "loss": 0.5182, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.30986591300626304, "learning_rate": 1.7489968862279902e-05, "loss": 0.5177, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.2703513784237585, "learning_rate": 1.743387180005809e-05, "loss": 0.5124, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.2845617700931079, "learning_rate": 1.737779525652899e-05, "loss": 0.5163, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2891995017843707, "learning_rate": 1.732173968007914e-05, "loss": 0.5078, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2769821494127827, "learning_rate": 1.7265705518927437e-05, "loss": 0.5056, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.2919561472971228, "learning_rate": 1.7209693221121542e-05, "loss": 0.5096, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.30070980398958197, "learning_rate": 1.7153703234534302e-05, "loss": 0.5086, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.25925974701217314, "learning_rate": 1.709773600686015e-05, "loss": 0.5094, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.3277989528128114, "learning_rate": 1.7041791985611548e-05, "loss": 0.5281, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.26549392098704644, "learning_rate": 1.69858716181154e-05, "loss": 0.5167, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.3278518412768399, "learning_rate": 1.692997535150948e-05, "loss": 0.5325, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.2997843010845892, "learning_rate": 1.687410363273884e-05, "loss": 0.509, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3237114951915077, "learning_rate": 1.6818256908552257e-05, "loss": 0.5121, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.2869742082802723, "learning_rate": 1.6762435625498646e-05, "loss": 0.5104, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.28031227791124175, "learning_rate": 1.67066402299235e-05, "loss": 0.5175, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.28533564307628956, "learning_rate": 1.6650871167965313e-05, "loss": 0.5159, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.2750552044741209, "learning_rate": 1.6595128885552028e-05, "loss": 0.5228, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.26637816826111926, "learning_rate": 1.653941382839745e-05, "loss": 0.5071, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.4157393882911366, "learning_rate": 1.6483726441997673e-05, "loss": 0.455, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3776702842958225, "learning_rate": 1.642806717162757e-05, "loss": 0.4585, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.4585967836601849, "learning_rate": 1.637243646233718e-05, "loss": 0.4581, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.4700719835342753, "learning_rate": 1.6316834758948174e-05, "loss": 0.4583, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.42666413374739304, "learning_rate": 1.6261262506050282e-05, "loss": 0.465, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.5198168739920576, "learning_rate": 1.620572014799777e-05, "loss": 0.4517, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.38964077495883365, "learning_rate": 1.6150208128905857e-05, "loss": 0.4491, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.49358444941678964, "learning_rate": 1.6094726892647147e-05, "loss": 0.4573, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.36936911372988945, "learning_rate": 1.6039276882848135e-05, "loss": 0.4519, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.47367563496741133, "learning_rate": 1.5983858542885635e-05, "loss": 0.458, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3927225823253957, "learning_rate": 1.5928472315883203e-05, "loss": 0.4489, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.4731205146275457, "learning_rate": 1.5873118644707633e-05, "loss": 0.4423, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.4000470884803812, "learning_rate": 1.5817797971965413e-05, "loss": 0.4492, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.46143520492916246, "learning_rate": 1.576251073999917e-05, "loss": 0.4548, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.36364574045471304, "learning_rate": 1.5707257390884126e-05, "loss": 0.4515, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.4109581358390023, "learning_rate": 1.5652038366424595e-05, "loss": 0.4576, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3758162158235699, "learning_rate": 1.5596854108150424e-05, "loss": 0.4407, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3761937726852865, "learning_rate": 1.5541705057313476e-05, "loss": 0.4488, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3545447110220908, "learning_rate": 1.5486591654884086e-05, "loss": 0.4579, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.38196855536635366, "learning_rate": 1.543151434154755e-05, "loss": 0.4606, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.31351378690195647, "learning_rate": 1.5376473557700615e-05, "loss": 0.4458, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.36921002442121237, "learning_rate": 1.5321469743447893e-05, "loss": 0.4496, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.2871655883425049, "learning_rate": 1.5266503338598434e-05, "loss": 0.448, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.35414087085408336, "learning_rate": 1.5211574782662149e-05, "loss": 0.4459, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.29971648341794377, "learning_rate": 1.5156684514846307e-05, "loss": 0.4436, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3304135177024114, "learning_rate": 1.5101832974052012e-05, "loss": 0.4367, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.31549494331848693, "learning_rate": 1.5047020598870737e-05, "loss": 0.4478, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.3164058103435242, "learning_rate": 1.4992247827580778e-05, "loss": 0.4476, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.34846284121205, "learning_rate": 1.493751509814374e-05, "loss": 0.4473, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.3083678429089962, "learning_rate": 1.4882822848201073e-05, "loss": 0.456, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.3228520268525766, "learning_rate": 1.4828171515070553e-05, "loss": 0.4466, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3063028177624797, "learning_rate": 1.4773561535742793e-05, "loss": 0.458, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.3067909676734137, "learning_rate": 1.4718993346877715e-05, "loss": 0.4256, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.284881474405159, "learning_rate": 1.466446738480111e-05, "loss": 0.4561, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.3160444311447502, "learning_rate": 1.460998408550112e-05, "loss": 0.4525, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.26055871624537125, "learning_rate": 1.4555543884624751e-05, "loss": 0.4463, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.3291039842505353, "learning_rate": 1.4501147217474402e-05, "loss": 0.455, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.27749972240338017, "learning_rate": 1.444679451900437e-05, "loss": 0.4491, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.2917509041504197, "learning_rate": 1.4392486223817397e-05, "loss": 0.4518, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.34205713833921314, "learning_rate": 1.4338222766161143e-05, "loss": 0.4591, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2726625807785195, "learning_rate": 1.4284004579924777e-05, "loss": 0.4425, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.35064572243907566, "learning_rate": 1.4229832098635479e-05, "loss": 0.4459, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.2588372760441889, "learning_rate": 1.4175705755454963e-05, "loss": 0.4373, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.30934510325169856, "learning_rate": 1.412162598317602e-05, "loss": 0.4389, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.27470765725411456, "learning_rate": 1.406759321421907e-05, "loss": 0.4347, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.28303008657313417, "learning_rate": 1.401360788062871e-05, "loss": 0.4624, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.2944851813829043, "learning_rate": 1.3959670414070204e-05, "loss": 0.4405, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.2664471006635906, "learning_rate": 1.3905781245826108e-05, "loss": 0.457, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.30245026109502976, "learning_rate": 1.3851940806792778e-05, "loss": 0.4517, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.25701174353805734, "learning_rate": 1.379814952747693e-05, "loss": 0.4605, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2737012712313101, "learning_rate": 1.3744407837992193e-05, "loss": 0.4419, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2803231022533781, "learning_rate": 1.3690716168055692e-05, "loss": 0.4528, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.2710495064817369, "learning_rate": 1.363707494698459e-05, "loss": 0.4612, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.28340380700128187, "learning_rate": 1.358348460369265e-05, "loss": 0.4531, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2887609934550937, "learning_rate": 1.352994556668684e-05, "loss": 0.4478, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.2961612112611042, "learning_rate": 1.3476458264063865e-05, "loss": 0.4445, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.2837766011233678, "learning_rate": 1.342302312350678e-05, "loss": 0.4514, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.2559345417827772, "learning_rate": 1.3369640572281537e-05, "loss": 0.4674, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.2734635926235582, "learning_rate": 1.3316311037233596e-05, "loss": 0.4395, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.40740167244112435, "learning_rate": 1.326303494478451e-05, "loss": 0.4639, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.24700459519516277, "learning_rate": 1.3209812720928472e-05, "loss": 0.4425, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2863156944750727, "learning_rate": 1.315664479122898e-05, "loss": 0.4508, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.24820213346917622, "learning_rate": 1.3103531580815378e-05, "loss": 0.453, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.24367448737167902, "learning_rate": 1.3050473514379488e-05, "loss": 0.4475, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2807355033299512, "learning_rate": 1.2997471016172188e-05, "loss": 0.4645, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.24649044462710476, "learning_rate": 1.2944524510000042e-05, "loss": 0.4347, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2673166384108523, "learning_rate": 1.2891634419221908e-05, "loss": 0.4575, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.25175322088716195, "learning_rate": 1.2838801166745545e-05, "loss": 0.4614, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.33408992468663923, "learning_rate": 1.2786025175024216e-05, "loss": 0.4575, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.23649251393723955, "learning_rate": 1.2733306866053357e-05, "loss": 0.4593, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.31778167832740273, "learning_rate": 1.2680646661367163e-05, "loss": 0.4454, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.26701851140692656, "learning_rate": 1.2628044982035219e-05, "loss": 0.4389, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.25084277562819024, "learning_rate": 1.2575502248659155e-05, "loss": 0.458, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.27864439663158946, "learning_rate": 1.2523018881369269e-05, "loss": 0.4574, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.24613812791879044, "learning_rate": 1.2470595299821176e-05, "loss": 0.4603, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2792798541926854, "learning_rate": 1.2418231923192416e-05, "loss": 0.4623, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.2667496886792795, "learning_rate": 1.2365929170179165e-05, "loss": 0.4514, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.27069234207868786, "learning_rate": 1.2313687458992848e-05, "loss": 0.444, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.28416047718181975, "learning_rate": 1.2261507207356785e-05, "loss": 0.4489, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.24011912347701475, "learning_rate": 1.220938883250288e-05, "loss": 0.4637, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2669712952791185, "learning_rate": 1.215733275116827e-05, "loss": 0.4517, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.25072917121749133, "learning_rate": 1.2105339379592005e-05, "loss": 0.4529, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.23550530889778828, "learning_rate": 1.2053409133511681e-05, "loss": 0.4558, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.2458087852054663, "learning_rate": 1.2001542428160173e-05, "loss": 0.4508, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2375528075467578, "learning_rate": 1.1949739678262278e-05, "loss": 0.4522, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.2606254562112482, "learning_rate": 1.189800129803139e-05, "loss": 0.4419, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.250896030640026, "learning_rate": 1.1846327701166228e-05, "loss": 0.455, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.25011458189772884, "learning_rate": 1.1794719300847493e-05, "loss": 0.4581, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2740848168292271, "learning_rate": 1.1743176509734582e-05, "loss": 0.4373, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.24356294835955644, "learning_rate": 1.1691699739962275e-05, "loss": 0.4517, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.26387859945134606, "learning_rate": 1.1640289403137456e-05, "loss": 0.4443, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.2793003738860213, "learning_rate": 1.1588945910335802e-05, "loss": 0.4454, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.25561989894710385, "learning_rate": 1.1537669672098517e-05, "loss": 0.4484, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.2787717890278576, "learning_rate": 1.1486461098429036e-05, "loss": 0.4655, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.24529877544713108, "learning_rate": 1.1435320598789747e-05, "loss": 0.4617, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.2565023922318482, "learning_rate": 1.1384248582098736e-05, "loss": 0.4419, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.24848139880195788, "learning_rate": 1.1333245456726467e-05, "loss": 0.4343, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.24541430517811264, "learning_rate": 1.128231163049258e-05, "loss": 0.4516, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.24486741598156228, "learning_rate": 1.123144751066259e-05, "loss": 0.4401, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.25185076135879647, "learning_rate": 1.1180653503944657e-05, "loss": 0.4397, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.2533254341309614, "learning_rate": 1.1129930016486287e-05, "loss": 0.4396, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2408569412424829, "learning_rate": 1.107927745387114e-05, "loss": 0.45, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.32860489705820756, "learning_rate": 1.1028696221115766e-05, "loss": 0.4563, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.24502855621078135, "learning_rate": 1.0978186722666341e-05, "loss": 0.4521, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.2378536898222587, "learning_rate": 1.0927749362395475e-05, "loss": 0.46, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.24207776663976827, "learning_rate": 1.0877384543598954e-05, "loss": 0.4572, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.25274967669227905, "learning_rate": 1.0827092668992529e-05, "loss": 0.457, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.23252078893289102, "learning_rate": 1.077687414070869e-05, "loss": 0.4572, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.25883191614960205, "learning_rate": 1.0726729360293451e-05, "loss": 0.4446, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.23344641240521694, "learning_rate": 1.0676658728703147e-05, "loss": 0.4512, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.22648781082408126, "learning_rate": 1.0626662646301198e-05, "loss": 0.4567, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.24798592788680537, "learning_rate": 1.0576741512854958e-05, "loss": 0.4528, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.21685740119314692, "learning_rate": 1.052689572753247e-05, "loss": 0.4539, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.23000974880631522, "learning_rate": 1.0477125688899328e-05, "loss": 0.4525, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.22892838088926817, "learning_rate": 1.0427431794915406e-05, "loss": 0.4563, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.22446667781781224, "learning_rate": 1.0377814442931769e-05, "loss": 0.4528, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.22753241621329479, "learning_rate": 1.0328274029687439e-05, "loss": 0.4471, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2264130537265349, "learning_rate": 1.0278810951306253e-05, "loss": 0.4489, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.21949374610860034, "learning_rate": 1.0229425603293647e-05, "loss": 0.4545, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.24165789317637376, "learning_rate": 1.0180118380533558e-05, "loss": 0.4459, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2345721998799339, "learning_rate": 1.0130889677285225e-05, "loss": 0.4677, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.23171475450101292, "learning_rate": 1.008173988718005e-05, "loss": 0.4437, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.22909827264391358, "learning_rate": 1.0032669403218439e-05, "loss": 0.4532, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.2251245963841707, "learning_rate": 9.983678617766677e-06, "loss": 0.4432, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.24518714709623374, "learning_rate": 9.934767922553788e-06, "loss": 0.4652, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.23042760056598094, "learning_rate": 9.885937708668371e-06, "loss": 0.4649, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.24758396410262923, "learning_rate": 9.837188366555524e-06, "loss": 0.449, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.2575078392026684, "learning_rate": 9.788520286013691e-06, "loss": 0.4494, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.22328972747881584, "learning_rate": 9.739933856191537e-06, "loss": 0.4627, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2474423547076759, "learning_rate": 9.691429465584866e-06, "loss": 0.4455, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.24738642268387423, "learning_rate": 9.643007502033492e-06, "loss": 0.464, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.25095114478467057, "learning_rate": 9.594668352718152e-06, "loss": 0.4419, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.24673161150701461, "learning_rate": 9.546412404157383e-06, "loss": 0.4431, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.22551271094498476, "learning_rate": 9.498240042204471e-06, "loss": 0.4717, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.2507966029063254, "learning_rate": 9.450151652044339e-06, "loss": 0.4606, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.25178639315815204, "learning_rate": 9.402147618190472e-06, "loss": 0.4545, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.22586898384267323, "learning_rate": 9.354228324481841e-06, "loss": 0.4496, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.23352702490697683, "learning_rate": 9.306394154079852e-06, "loss": 0.4532, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.22581572506843406, "learning_rate": 9.258645489465254e-06, "loss": 0.4642, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.23622662673042696, "learning_rate": 9.21098271243509e-06, "loss": 0.466, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.24312937549056562, "learning_rate": 9.163406204099659e-06, "loss": 0.4523, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.25083625968738366, "learning_rate": 9.115916344879452e-06, "loss": 0.4423, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.22502347862055566, "learning_rate": 9.068513514502126e-06, "loss": 0.4436, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2607204850243803, "learning_rate": 9.021198091999439e-06, "loss": 0.456, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.23638684314050698, "learning_rate": 8.973970455704251e-06, "loss": 0.4514, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.24360972143537568, "learning_rate": 8.926830983247495e-06, "loss": 0.4583, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2499169746529581, "learning_rate": 8.879780051555116e-06, "loss": 0.4537, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.24539883967356227, "learning_rate": 8.83281803684512e-06, "loss": 0.4391, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.21941587801282286, "learning_rate": 8.785945314624532e-06, "loss": 0.4689, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.23075617501502682, "learning_rate": 8.739162259686385e-06, "loss": 0.4557, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.23497186826146652, "learning_rate": 8.692469246106734e-06, "loss": 0.4571, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.24302217512943022, "learning_rate": 8.645866647241677e-06, "loss": 0.4623, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.23577146217213873, "learning_rate": 8.599354835724348e-06, "loss": 0.4424, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.22220358708138846, "learning_rate": 8.552934183461958e-06, "loss": 0.4562, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2303791046790549, "learning_rate": 8.506605061632805e-06, "loss": 0.4264, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.2525427135523463, "learning_rate": 8.460367840683308e-06, "loss": 0.4657, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2271358786255469, "learning_rate": 8.414222890325065e-06, "loss": 0.4579, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.23526798554471276, "learning_rate": 8.368170579531855e-06, "loss": 0.4469, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.46813847062302094, "learning_rate": 8.322211276536733e-06, "loss": 0.4364, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.24845360980356532, "learning_rate": 8.27634534882907e-06, "loss": 0.4568, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.2343873968069309, "learning_rate": 8.230573163151585e-06, "loss": 0.45, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.22625689867009582, "learning_rate": 8.184895085497466e-06, "loss": 0.4567, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.22697445146742837, "learning_rate": 8.139311481107401e-06, "loss": 0.4406, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.22553109283428777, "learning_rate": 8.093822714466686e-06, "loss": 0.4388, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.22904680631318522, "learning_rate": 8.048429149302271e-06, "loss": 0.4583, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.21970334688088589, "learning_rate": 8.003131148579902e-06, "loss": 0.4444, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2310220762840295, "learning_rate": 7.957929074501182e-06, "loss": 0.4506, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.22514288243218744, "learning_rate": 7.912823288500695e-06, "loss": 0.445, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.22353589828917403, "learning_rate": 7.867814151243102e-06, "loss": 0.4486, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2381913385080768, "learning_rate": 7.822902022620267e-06, "loss": 0.4503, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.21924157504960895, "learning_rate": 7.778087261748377e-06, "loss": 0.4538, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.2268264999753015, "learning_rate": 7.733370226965056e-06, "loss": 0.4654, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.23249978374587446, "learning_rate": 7.688751275826527e-06, "loss": 0.4455, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.23667564039245317, "learning_rate": 7.644230765104735e-06, "loss": 0.4565, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.22741875084096377, "learning_rate": 7.599809050784502e-06, "loss": 0.4501, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.24125713649673763, "learning_rate": 7.555486488060661e-06, "loss": 0.4775, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.23032522502645114, "learning_rate": 7.511263431335249e-06, "loss": 0.4527, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.23363329026820367, "learning_rate": 7.467140234214656e-06, "loss": 0.4557, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.241984135020704, "learning_rate": 7.423117249506777e-06, "loss": 0.4472, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.24525282800248444, "learning_rate": 7.379194829218231e-06, "loss": 0.4499, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.233949223871052, "learning_rate": 7.335373324551518e-06, "loss": 0.4533, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.22757939697767546, "learning_rate": 7.291653085902224e-06, "loss": 0.4526, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2324305601461966, "learning_rate": 7.248034462856213e-06, "loss": 0.4576, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.22463299270704437, "learning_rate": 7.20451780418683e-06, "loss": 0.4498, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.21963748102086136, "learning_rate": 7.161103457852128e-06, "loss": 0.4441, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.22057763574226216, "learning_rate": 7.117791770992046e-06, "loss": 0.454, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.22080829689376105, "learning_rate": 7.074583089925688e-06, "loss": 0.4604, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.2576943421458925, "learning_rate": 7.0314777601485155e-06, "loss": 0.4559, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.20969689424186222, "learning_rate": 6.988476126329604e-06, "loss": 0.4563, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.2308070749506109, "learning_rate": 6.945578532308857e-06, "loss": 0.4523, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.23804154810990094, "learning_rate": 6.902785321094301e-06, "loss": 0.4486, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.23915609490554582, "learning_rate": 6.8600968348593115e-06, "loss": 0.4517, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.21384317331479477, "learning_rate": 6.817513414939892e-06, "loss": 0.4583, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.22123707583787539, "learning_rate": 6.775035401831924e-06, "loss": 0.4354, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.23374324694845347, "learning_rate": 6.732663135188473e-06, "loss": 0.4486, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.22048125581703396, "learning_rate": 6.690396953817055e-06, "loss": 0.4403, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.22359729952834725, "learning_rate": 6.648237195676927e-06, "loss": 0.4335, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.22107880014293255, "learning_rate": 6.606184197876395e-06, "loss": 0.4548, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.21387699603514507, "learning_rate": 6.564238296670109e-06, "loss": 0.4463, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.22814859216120242, "learning_rate": 6.52239982745638e-06, "loss": 0.4569, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.21524652598577504, "learning_rate": 6.480669124774484e-06, "loss": 0.4568, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.22009712394087774, "learning_rate": 6.439046522302013e-06, "loss": 0.4428, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.21207340773654598, "learning_rate": 6.397532352852191e-06, "loss": 0.4547, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.23010143825761967, "learning_rate": 6.356126948371202e-06, "loss": 0.4466, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.22722996360484035, "learning_rate": 6.314830639935559e-06, "loss": 0.4525, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2636500930595437, "learning_rate": 6.273643757749448e-06, "loss": 0.4574, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.24120856587304954, "learning_rate": 6.2325666311420856e-06, "loss": 0.4456, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2160453593635134, "learning_rate": 6.1915995885650675e-06, "loss": 0.4493, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.2112351856222027, "learning_rate": 6.150742957589784e-06, "loss": 0.4555, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2322506463483274, "learning_rate": 6.109997064904774e-06, "loss": 0.4528, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2198060408030978, "learning_rate": 6.069362236313092e-06, "loss": 0.4522, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2066215599139907, "learning_rate": 6.0288387967297565e-06, "loss": 0.4551, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2158068649857071, "learning_rate": 5.988427070179108e-06, "loss": 0.4442, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.482441451974355, "learning_rate": 5.948127379792234e-06, "loss": 0.4567, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.2202956949715079, "learning_rate": 5.90794004780439e-06, "loss": 0.4425, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.22335936891631955, "learning_rate": 5.867865395552405e-06, "loss": 0.4481, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.20678619230658424, "learning_rate": 5.8279037434721364e-06, "loss": 0.4376, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.23586837397291524, "learning_rate": 5.788055411095892e-06, "loss": 0.4635, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2233081092755246, "learning_rate": 5.7483207170498625e-06, "loss": 0.4513, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.21949058036278804, "learning_rate": 5.708699979051613e-06, "loss": 0.446, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.23491963577957564, "learning_rate": 5.66919351390751e-06, "loss": 0.4498, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.22928269310760682, "learning_rate": 5.629801637510188e-06, "loss": 0.4484, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.2104592006217001, "learning_rate": 5.590524664836043e-06, "loss": 0.4475, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.21897196379617948, "learning_rate": 5.551362909942708e-06, "loss": 0.445, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.22190976045590668, "learning_rate": 5.51231668596653e-06, "loss": 0.4577, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.20053555792772937, "learning_rate": 5.47338630512007e-06, "loss": 0.4529, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.20656498022105274, "learning_rate": 5.434572078689617e-06, "loss": 0.4532, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.2143693282596957, "learning_rate": 5.395874317032694e-06, "loss": 0.4596, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.23098575795888565, "learning_rate": 5.357293329575573e-06, "loss": 0.432, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.21129003894866485, "learning_rate": 5.318829424810797e-06, "loss": 0.4514, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.21348499515846953, "learning_rate": 5.280482910294728e-06, "loss": 0.4413, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.20539973085032495, "learning_rate": 5.242254092645078e-06, "loss": 0.4567, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2104844075482288, "learning_rate": 5.2041432775384445e-06, "loss": 0.4586, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.21994376860108975, "learning_rate": 5.166150769707892e-06, "loss": 0.45, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.21420754379028742, "learning_rate": 5.128276872940503e-06, "loss": 0.4485, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.21278220300745548, "learning_rate": 5.090521890074953e-06, "loss": 0.4579, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2033517213229406, "learning_rate": 5.0528861229990675e-06, "loss": 0.4458, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.21179214640083543, "learning_rate": 5.015369872647442e-06, "loss": 0.4477, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.20548833835703745, "learning_rate": 4.9779734389990195e-06, "loss": 0.4543, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.20600430505488201, "learning_rate": 4.940697121074675e-06, "loss": 0.458, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.20174488714907438, "learning_rate": 4.903541216934864e-06, "loss": 0.4566, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.22223854367566048, "learning_rate": 4.8665060236772e-06, "loss": 0.4532, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2040059144419156, "learning_rate": 4.829591837434102e-06, "loss": 0.457, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.20635283167263077, "learning_rate": 4.792798953370424e-06, "loss": 0.4592, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.21730848017504034, "learning_rate": 4.756127665681083e-06, "loss": 0.4433, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.24460966325178768, "learning_rate": 4.719578267588725e-06, "loss": 0.4413, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.20967723148024867, "learning_rate": 4.6831510513413525e-06, "loss": 0.4495, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4348783250911853, "learning_rate": 4.6468463082100176e-06, "loss": 0.4091, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.2798248116401278, "learning_rate": 4.610664328486485e-06, "loss": 0.4078, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.3385066950815171, "learning_rate": 4.5746054014809e-06, "loss": 0.4103, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.4833702227317605, "learning_rate": 4.5386698155194766e-06, "loss": 0.4216, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.26745698137752977, "learning_rate": 4.502857857942204e-06, "loss": 0.4036, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3443188337420425, "learning_rate": 4.467169815100549e-06, "loss": 0.4003, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3710778226052755, "learning_rate": 4.431605972355137e-06, "loss": 0.4014, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.2942399796323976, "learning_rate": 4.396166614073516e-06, "loss": 0.4145, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.24594533783336867, "learning_rate": 4.360852023627846e-06, "loss": 0.4048, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3057540627404856, "learning_rate": 4.325662483392656e-06, "loss": 0.403, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.347162533833731, "learning_rate": 4.29059827474257e-06, "loss": 0.4056, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.28008976542009284, "learning_rate": 4.255659678050063e-06, "loss": 0.3978, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.2406943379215898, "learning_rate": 4.22084697268323e-06, "loss": 0.4141, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.28181570617022617, "learning_rate": 4.186160437003535e-06, "loss": 0.407, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.29906175242035915, "learning_rate": 4.151600348363582e-06, "loss": 0.4096, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.2501753845627743, "learning_rate": 4.11716698310493e-06, "loss": 0.4092, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.23462732547357903, "learning_rate": 4.082860616555848e-06, "loss": 0.3827, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.2590008845376222, "learning_rate": 4.048681523029125e-06, "loss": 0.4037, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2626643200230661, "learning_rate": 4.014629975819882e-06, "loss": 0.41, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.23411687655421354, "learning_rate": 3.9807062472033855e-06, "loss": 0.4115, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2205701925751201, "learning_rate": 3.94691060843287e-06, "loss": 0.3977, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.22086957311969663, "learning_rate": 3.913243329737353e-06, "loss": 0.4124, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.247217488473629, "learning_rate": 3.879704680319503e-06, "loss": 0.3881, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2216386962418425, "learning_rate": 3.846294928353471e-06, "loss": 0.4104, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.22209500350984582, "learning_rate": 3.8130143409827345e-06, "loss": 0.4009, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2237883768500585, "learning_rate": 3.7798631843179887e-06, "loss": 0.4114, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2187003900345546, "learning_rate": 3.7468417234349973e-06, "loss": 0.4047, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2121314227244524, "learning_rate": 3.7139502223724823e-06, "loss": 0.4149, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.20533358821093145, "learning_rate": 3.6811889441300095e-06, "loss": 0.4018, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.22312637812595829, "learning_rate": 3.648558150665886e-06, "loss": 0.4135, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.2307176513951624, "learning_rate": 3.616058102895075e-06, "loss": 0.4135, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2019989498714405, "learning_rate": 3.583689060687079e-06, "loss": 0.4098, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.21345582294222495, "learning_rate": 3.5514512828639023e-06, "loss": 0.406, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.23674704920894238, "learning_rate": 3.51934502719796e-06, "loss": 0.4046, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.22951137375823813, "learning_rate": 3.4873705504100185e-06, "loss": 0.3986, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.21608085382067607, "learning_rate": 3.4555281081671345e-06, "loss": 0.3954, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.210900923603534, "learning_rate": 3.4238179550806326e-06, "loss": 0.3877, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.21508999403318155, "learning_rate": 3.3922403447040497e-06, "loss": 0.4115, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.22267603047274837, "learning_rate": 3.3607955295311247e-06, "loss": 0.407, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.21338408755991436, "learning_rate": 3.32948376099375e-06, "loss": 0.4018, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.21044164127728515, "learning_rate": 3.2983052894599976e-06, "loss": 0.3982, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2081506264068293, "learning_rate": 3.2672603642320945e-06, "loss": 0.4252, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2122487146765408, "learning_rate": 3.236349233544438e-06, "loss": 0.3943, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2041338463018291, "learning_rate": 3.205572144561604e-06, "loss": 0.4064, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2108230312928265, "learning_rate": 3.174929343376374e-06, "loss": 0.3887, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2102472090283489, "learning_rate": 3.1444210750077777e-06, "loss": 0.4096, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.21082554471117193, "learning_rate": 3.1140475833991046e-06, "loss": 0.4098, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.21012853817625923, "learning_rate": 3.0838091114159895e-06, "loss": 0.4118, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.20619962835228337, "learning_rate": 3.0537059008444524e-06, "loss": 0.3949, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2027152128572896, "learning_rate": 3.0237381923889563e-06, "loss": 0.4096, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.21853602145933473, "learning_rate": 2.9939062256704997e-06, "loss": 0.4017, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.21625423327724774, "learning_rate": 2.964210239224696e-06, "loss": 0.419, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.2122776230476268, "learning_rate": 2.934650470499869e-06, "loss": 0.4038, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.20036511953726002, "learning_rate": 2.905227155855128e-06, "loss": 0.4025, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2136111776133258, "learning_rate": 2.875940530558519e-06, "loss": 0.4078, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2134392649788091, "learning_rate": 2.8467908287851154e-06, "loss": 0.4212, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.2217143306781957, "learning_rate": 2.8177782836151603e-06, "loss": 0.4011, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.20287291424147902, "learning_rate": 2.7889031270321874e-06, "loss": 0.4211, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.21162096783165363, "learning_rate": 2.760165589921184e-06, "loss": 0.3993, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.20117426243607414, "learning_rate": 2.7315659020667305e-06, "loss": 0.4044, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2051853265446691, "learning_rate": 2.703104292151164e-06, "loss": 0.4117, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.21042666567216145, "learning_rate": 2.6747809877527607e-06, "loss": 0.413, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.20958918489044204, "learning_rate": 2.6465962153439082e-06, "loss": 0.4135, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.20432739638878733, "learning_rate": 2.618550200289303e-06, "loss": 0.4016, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2089540417676064, "learning_rate": 2.59064316684412e-06, "loss": 0.3944, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20740385680255627, "learning_rate": 2.562875338152264e-06, "loss": 0.4022, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2076216036689584, "learning_rate": 2.5352469362445552e-06, "loss": 0.4045, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.20458258296257895, "learning_rate": 2.5077581820369523e-06, "loss": 0.4179, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.20533265033712644, "learning_rate": 2.480409295328803e-06, "loss": 0.4018, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.20199423451280127, "learning_rate": 2.45320049480108e-06, "loss": 0.4076, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.20433506384218147, "learning_rate": 2.4261319980146293e-06, "loss": 0.4098, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.20732174905046666, "learning_rate": 2.399204021408421e-06, "loss": 0.4098, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.20472718636955511, "learning_rate": 2.3724167802978395e-06, "loss": 0.4111, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.19995948924633697, "learning_rate": 2.3457704888729625e-06, "loss": 0.407, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.20733185176802826, "learning_rate": 2.3192653601968162e-06, "loss": 0.4172, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.22272835566432903, "learning_rate": 2.2929016062037057e-06, "loss": 0.4046, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.20964864192361465, "learning_rate": 2.2666794376975055e-06, "loss": 0.4144, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2062667692299166, "learning_rate": 2.24059906434998e-06, "loss": 0.4023, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.20950315381732337, "learning_rate": 2.214660694699091e-06, "loss": 0.4098, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.20147285714758312, "learning_rate": 2.188864536147355e-06, "loss": 0.4192, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.21807633578380572, "learning_rate": 2.1632107949601757e-06, "loss": 0.4077, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.23545618885474334, "learning_rate": 2.137699676264171e-06, "loss": 0.4106, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.21641692168677862, "learning_rate": 2.1123313840455738e-06, "loss": 0.4301, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.20668058039120596, "learning_rate": 2.08710612114857e-06, "loss": 0.3951, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2065953371777538, "learning_rate": 2.0620240892736953e-06, "loss": 0.4068, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.20894996093646703, "learning_rate": 2.0370854889762e-06, "loss": 0.4121, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.20688268050735423, "learning_rate": 2.0122905196644726e-06, "loss": 0.391, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21811826652607536, "learning_rate": 1.987639379598427e-06, "loss": 0.4074, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21487621784762595, "learning_rate": 1.963132265887919e-06, "loss": 0.3981, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.21205227809346344, "learning_rate": 1.9387693744911784e-06, "loss": 0.4009, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.20880581013726845, "learning_rate": 1.9145509002132368e-06, "loss": 0.3992, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.19813492521192766, "learning_rate": 1.8904770367043723e-06, "loss": 0.4086, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.2092587070920211, "learning_rate": 1.8665479764585504e-06, "loss": 0.414, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.20027991485425195, "learning_rate": 1.8427639108118977e-06, "loss": 0.4166, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.20346425597384946, "learning_rate": 1.8191250299411755e-06, "loss": 0.4159, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.20191738388962435, "learning_rate": 1.7956315228622446e-06, "loss": 0.414, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.20900098200656808, "learning_rate": 1.7722835774285553e-06, "loss": 0.4059, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.19746426147719126, "learning_rate": 1.7490813803296624e-06, "loss": 0.4054, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.1909588896589638, "learning_rate": 1.726025117089718e-06, "loss": 0.4138, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.19883895109378735, "learning_rate": 1.70311497206598e-06, "loss": 0.4068, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2100201954164295, "learning_rate": 1.6803511284473638e-06, "loss": 0.3848, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.20852949591402997, "learning_rate": 1.6577337682529538e-06, "loss": 0.4046, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.20787956399272026, "learning_rate": 1.6352630723305617e-06, "loss": 0.4014, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2750605165105917, "learning_rate": 1.612939220355272e-06, "loss": 0.413, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.2050195685263587, "learning_rate": 1.5907623908280112e-06, "loss": 0.3991, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 1.0017359772728263, "learning_rate": 1.568732761074121e-06, "loss": 0.4361, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.21444187111582272, "learning_rate": 1.5468505072419237e-06, "loss": 0.4054, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.20660464711775994, "learning_rate": 1.5251158043013448e-06, "loss": 0.4161, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.20911784721912205, "learning_rate": 1.5035288260424885e-06, "loss": 0.4113, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.1974422293175174, "learning_rate": 1.4820897450742623e-06, "loss": 0.396, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2045814932548567, "learning_rate": 1.4607987328229767e-06, "loss": 0.4053, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.1962010966038764, "learning_rate": 1.4396559595310056e-06, "loss": 0.4189, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.19478506181898866, "learning_rate": 1.4186615942553973e-06, "loss": 0.4145, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.19766441112186983, "learning_rate": 1.3978158048665424e-06, "loss": 0.4039, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.19851945127964898, "learning_rate": 1.3771187580468115e-06, "loss": 0.4046, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.2002584655628957, "learning_rate": 1.3565706192892392e-06, "loss": 0.4124, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.19005904904506515, "learning_rate": 1.3361715528961993e-06, "loss": 0.4031, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.19953802503495796, "learning_rate": 1.3159217219780817e-06, "loss": 0.4081, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.19635686271958577, "learning_rate": 1.2958212884519949e-06, "loss": 0.3904, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.1938857700414822, "learning_rate": 1.2758704130404675e-06, "loss": 0.4002, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.20245589080209406, "learning_rate": 1.2560692552701738e-06, "loss": 0.3941, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.19970539904725576, "learning_rate": 1.2364179734706382e-06, "loss": 0.3962, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.20246560327863203, "learning_rate": 1.2169167247729852e-06, "loss": 0.4084, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2022466510822884, "learning_rate": 1.1975656651086864e-06, "loss": 0.4074, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.19361114530821846, "learning_rate": 1.1783649492082926e-06, "loss": 0.3997, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.19134085168716836, "learning_rate": 1.1593147306002183e-06, "loss": 0.4115, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2121449377364046, "learning_rate": 1.140415161609505e-06, "loss": 0.4129, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.20081652538168707, "learning_rate": 1.121666393356604e-06, "loss": 0.4091, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.20535375620422236, "learning_rate": 1.1030685757561632e-06, "loss": 0.3932, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.20166023506634398, "learning_rate": 1.0846218575158373e-06, "loss": 0.405, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.1903340547771791, "learning_rate": 1.066326386135097e-06, "loss": 0.4026, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.20891500946641642, "learning_rate": 1.0481823079040398e-06, "loss": 0.3915, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.19543244023717174, "learning_rate": 1.0301897679022344e-06, "loss": 0.4012, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.1953412421858172, "learning_rate": 1.0123489099975491e-06, "loss": 0.4002, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.18902001806009017, "learning_rate": 9.9465987684501e-07, "loss": 0.4038, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.2042284754775904, "learning_rate": 9.771228098856534e-07, "loss": 0.3876, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.2007708494103635, "learning_rate": 9.597378493454013e-07, "loss": 0.4185, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.20016775574017728, "learning_rate": 9.425051342339353e-07, "loss": 0.4085, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.19779480198728958, "learning_rate": 9.254248023435864e-07, "loss": 0.4014, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.1981007398696411, "learning_rate": 9.084969902482288e-07, "loss": 0.4232, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.19772365810997924, "learning_rate": 8.917218333021993e-07, "loss": 0.4193, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.20140860518586973, "learning_rate": 8.750994656392109e-07, "loss": 0.3823, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.19563659342473652, "learning_rate": 8.58630020171265e-07, "loss": 0.4147, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.19973833432673113, "learning_rate": 8.423136285876099e-07, "loss": 0.3947, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.1930926109167982, "learning_rate": 8.26150421353682e-07, "loss": 0.3956, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.1954360504979555, "learning_rate": 8.101405277100549e-07, "loss": 0.4216, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.195398263249236, "learning_rate": 7.942840756714077e-07, "loss": 0.3927, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.1928066581838666, "learning_rate": 7.785811920255093e-07, "loss": 0.4188, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.19625336829310186, "learning_rate": 7.630320023322024e-07, "loss": 0.3905, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.19029506355209874, "learning_rate": 7.476366309223903e-07, "loss": 0.4112, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.20268529106872146, "learning_rate": 7.323952008970537e-07, "loss": 0.416, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.19726692212577795, "learning_rate": 7.173078341262618e-07, "loss": 0.3993, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.20174763243837165, "learning_rate": 7.023746512481989e-07, "loss": 0.4043, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.1908692683645128, "learning_rate": 6.875957716681902e-07, "loss": 0.3998, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.1924621046313558, "learning_rate": 6.729713135577687e-07, "loss": 0.4131, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2010157190289527, "learning_rate": 6.585013938537143e-07, "loss": 0.4034, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.20464419966006478, "learning_rate": 6.441861282571115e-07, "loss": 0.4034, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.20106195829671025, "learning_rate": 6.300256312324471e-07, "loss": 0.4034, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.19312593832087646, "learning_rate": 6.160200160066776e-07, "loss": 0.4131, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.20085676754388304, "learning_rate": 6.021693945683327e-07, "loss": 0.3995, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.1937626645330691, "learning_rate": 5.884738776666044e-07, "loss": 0.4053, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.1910384003432906, "learning_rate": 5.749335748104878e-07, "loss": 0.4201, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.19786829469335296, "learning_rate": 5.615485942678778e-07, "loss": 0.4193, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.20156106626423123, "learning_rate": 5.483190430647289e-07, "loss": 0.4203, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.19488653836834066, "learning_rate": 5.352450269841747e-07, "loss": 0.4193, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.19575275709833817, "learning_rate": 5.22326650565701e-07, "loss": 0.426, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.19507445245616178, "learning_rate": 5.095640171043048e-07, "loss": 0.414, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.1908144204738654, "learning_rate": 4.969572286496594e-07, "loss": 0.4031, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.1914994366999489, "learning_rate": 4.845063860053079e-07, "loss": 0.4103, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.1942844099773449, "learning_rate": 4.7221158872785997e-07, "loss": 0.4142, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.19446365754347186, "learning_rate": 4.600729351261857e-07, "loss": 0.3889, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.19807801701490738, "learning_rate": 4.4809052226063355e-07, "loss": 0.4071, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.19276054540675006, "learning_rate": 4.3626444594226046e-07, "loss": 0.4094, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.1918246678513344, "learning_rate": 4.245948007320588e-07, "loss": 0.3917, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.19649906184520557, "learning_rate": 4.130816799401971e-07, "loss": 0.4052, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.19257205916960954, "learning_rate": 4.017251756252827e-07, "loss": 0.4052, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.19703175201229947, "learning_rate": 3.9052537859362473e-07, "loss": 0.4136, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.4757301673547169, "learning_rate": 3.7948237839849687e-07, "loss": 0.4163, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.19459526225740265, "learning_rate": 3.6859626333943797e-07, "loss": 0.3932, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.19200349619598206, "learning_rate": 3.578671204615347e-07, "loss": 0.4044, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.19610850889525644, "learning_rate": 3.472950355547267e-07, "loss": 0.407, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.19992983357431018, "learning_rate": 3.3688009315312244e-07, "loss": 0.3952, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.18399491641876808, "learning_rate": 3.266223765343224e-07, "loss": 0.4153, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.19701691161518392, "learning_rate": 3.16521967718757e-07, "loss": 0.4102, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.1967301695838012, "learning_rate": 3.0657894746902726e-07, "loss": 0.3957, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.20242516942310865, "learning_rate": 2.9679339528925654e-07, "loss": 0.3942, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.19071584387506402, "learning_rate": 2.871653894244597e-07, "loss": 0.4101, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.20002125183919364, "learning_rate": 2.7769500685991266e-07, "loss": 0.412, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.19916162109349958, "learning_rate": 2.683823233205485e-07, "loss": 0.4033, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.19319644474435352, "learning_rate": 2.592274132703287e-07, "loss": 0.3953, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.19064034075347738, "learning_rate": 2.502303499116754e-07, "loss": 0.4107, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.19202101510730182, "learning_rate": 2.413912051848666e-07, "loss": 0.4038, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.19536245831044788, "learning_rate": 2.3271004976746613e-07, "loss": 0.4114, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2005679589915383, "learning_rate": 2.2418695307376393e-07, "loss": 0.4001, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.1915709669875042, "learning_rate": 2.1582198325420968e-07, "loss": 0.4223, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.19831098147137072, "learning_rate": 2.0761520719488447e-07, "loss": 0.4091, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.1935558456855792, "learning_rate": 1.9956669051694798e-07, "loss": 0.4149, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.1966938849027211, "learning_rate": 1.916764975761254e-07, "loss": 0.4069, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.20070759263760735, "learning_rate": 1.839446914621923e-07, "loss": 0.4147, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.1935454595783563, "learning_rate": 1.7637133399845962e-07, "loss": 0.4115, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.1974983667384864, "learning_rate": 1.6895648574129397e-07, "loss": 0.4169, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.19614710665795945, "learning_rate": 1.6170020597962465e-07, "loss": 0.42, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.20666306375929797, "learning_rate": 1.5460255273447078e-07, "loss": 0.4139, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.1926026068889857, "learning_rate": 1.4766358275847715e-07, "loss": 0.4019, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.18994581969116617, "learning_rate": 1.4088335153546573e-07, "loss": 0.4024, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.19905091377939918, "learning_rate": 1.3426191327998496e-07, "loss": 0.4045, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.19495747697180038, "learning_rate": 1.277993209368744e-07, "loss": 0.4105, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.20049236808686596, "learning_rate": 1.214956261808542e-07, "loss": 0.3967, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.19584357183567813, "learning_rate": 1.1535087941609846e-07, "loss": 0.4138, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.19356376320435695, "learning_rate": 1.0936512977583802e-07, "loss": 0.4098, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.192110777888993, "learning_rate": 1.0353842512196732e-07, "loss": 0.411, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.1920643940656442, "learning_rate": 9.787081204466253e-08, "loss": 0.4146, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.18983520468980594, "learning_rate": 9.236233586200627e-08, "loss": 0.4082, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.19624467045583752, "learning_rate": 8.70130406196279e-08, "loss": 0.4047, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.19316738354436583, "learning_rate": 8.182296909035047e-08, "loss": 0.4109, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.19417003641927916, "learning_rate": 7.679216277384439e-08, "loss": 0.4067, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.19712312023373016, "learning_rate": 7.19206618963053e-08, "loss": 0.4028, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.19461383199461244, "learning_rate": 6.720850541012347e-08, "loss": 0.4127, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.2136076364607488, "learning_rate": 6.265573099357714e-08, "loss": 0.3954, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.19164175636345618, "learning_rate": 5.826237505053067e-08, "loss": 0.4101, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.1932592234027784, "learning_rate": 5.4028472710137e-08, "loss": 0.4111, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.19309903926195618, "learning_rate": 4.9954057826571146e-08, "loss": 0.4043, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.19468623926176598, "learning_rate": 4.6039162978743776e-08, "loss": 0.4009, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.1912683213197442, "learning_rate": 4.228381947004812e-08, "loss": 0.384, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.19176624143660354, "learning_rate": 3.868805732811343e-08, "loss": 0.4268, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.18975424670735358, "learning_rate": 3.525190530455636e-08, "loss": 0.3968, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.19473187717389925, "learning_rate": 3.197539087475887e-08, "loss": 0.419, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.19765893141367094, "learning_rate": 2.8858540237641786e-08, "loss": 0.4091, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.19471541586644167, "learning_rate": 2.5901378315458247e-08, "loss": 0.4033, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.1953746586231011, "learning_rate": 2.3103928753598347e-08, "loss": 0.4157, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.18984435400112296, "learning_rate": 2.0466213920393718e-08, "loss": 0.4163, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.1959981939162274, "learning_rate": 1.7988254906942115e-08, "loss": 0.3996, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.1933290706304125, "learning_rate": 1.5670071526936447e-08, "loss": 0.4062, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.19828126987161276, "learning_rate": 1.3511682316509344e-08, "loss": 0.4044, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.1846613009380835, "learning_rate": 1.1513104534086605e-08, "loss": 0.4209, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.21784033162370092, "learning_rate": 9.67435416023843e-09, "loss": 0.4071, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.1913369066895745, "learning_rate": 7.995445897566178e-09, "loss": 0.4037, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.1946010802451154, "learning_rate": 6.476393170578021e-09, "loss": 0.3999, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.19416344024148272, "learning_rate": 5.11720812557348e-09, "loss": 0.4103, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.19911799340163672, "learning_rate": 3.917901630563492e-09, "loss": 0.4067, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.1924615651406477, "learning_rate": 2.878483275170485e-09, "loss": 0.4051, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.19193087409273282, "learning_rate": 1.998961370555108e-09, "loss": 0.4066, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.1905775821471462, "learning_rate": 1.2793429493518361e-09, "loss": 0.4105, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.19114606383721822, "learning_rate": 7.196337656112384e-10, "loss": 0.425, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.1907677748927005, "learning_rate": 3.198382947511292e-10, "loss": 0.3993, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.1895832508887791, "learning_rate": 7.995973352770137e-11, "loss": 0.4068, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19062790631568952, "learning_rate": 0.0, "loss": 0.4009, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 5.446394315196596e+18, "train_loss": 0.5326917097153451, "train_runtime": 29761.0248, "train_samples_per_second": 5.309, "train_steps_per_second": 0.041 } ], "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": 5.446394315196596e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }