{ "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": 6.755417348699791, "learning_rate": 3.2258064516129035e-07, "loss": 0.7945, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.712909205345919, "learning_rate": 6.451612903225807e-07, "loss": 0.7833, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.543553390592576, "learning_rate": 9.67741935483871e-07, "loss": 0.7815, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.993319935023763, "learning_rate": 1.2903225806451614e-06, "loss": 0.8169, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.45034768931133, "learning_rate": 1.6129032258064516e-06, "loss": 0.7945, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.232781887623522, "learning_rate": 1.935483870967742e-06, "loss": 0.7836, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.1198555682459315, "learning_rate": 2.2580645161290324e-06, "loss": 0.7475, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.595179027033085, "learning_rate": 2.580645161290323e-06, "loss": 0.7178, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.9159295878491727, "learning_rate": 2.903225806451613e-06, "loss": 0.686, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.5476725526005035, "learning_rate": 3.225806451612903e-06, "loss": 0.6517, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.4356332553851576, "learning_rate": 3.548387096774194e-06, "loss": 0.656, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.4392185745087995, "learning_rate": 3.870967741935484e-06, "loss": 0.6396, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.8146318192336865, "learning_rate": 4.193548387096774e-06, "loss": 0.6496, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.6985460108694252, "learning_rate": 4.516129032258065e-06, "loss": 0.6335, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.542771178337796, "learning_rate": 4.838709677419355e-06, "loss": 0.626, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.8751099637962443, "learning_rate": 5.161290322580646e-06, "loss": 0.5545, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.6861760678626925, "learning_rate": 5.483870967741935e-06, "loss": 0.5603, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.2287825896377087, "learning_rate": 5.806451612903226e-06, "loss": 0.5442, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.8067072525051522, "learning_rate": 6.129032258064517e-06, "loss": 0.5348, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.312735114632986, "learning_rate": 6.451612903225806e-06, "loss": 0.5241, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.3879528811245239, "learning_rate": 6.774193548387097e-06, "loss": 0.5046, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.6486907457904547, "learning_rate": 7.096774193548388e-06, "loss": 0.5125, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.4933269936413396, "learning_rate": 7.4193548387096784e-06, "loss": 0.4981, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.0886019260731639, "learning_rate": 7.741935483870968e-06, "loss": 0.4986, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8208334225446161, "learning_rate": 8.064516129032258e-06, "loss": 0.5081, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.0957681957429308, "learning_rate": 8.387096774193549e-06, "loss": 0.4767, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.9891565947101272, "learning_rate": 8.70967741935484e-06, "loss": 0.4782, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.7686316504000658, "learning_rate": 9.03225806451613e-06, "loss": 0.4755, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7677747525602447, "learning_rate": 9.35483870967742e-06, "loss": 0.4722, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7216625896794943, "learning_rate": 9.67741935483871e-06, "loss": 0.4641, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.7309937629594347, "learning_rate": 1e-05, "loss": 0.4473, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.8324847328344963, "learning_rate": 1.0322580645161291e-05, "loss": 0.4582, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7781252398270365, "learning_rate": 1.0645161290322582e-05, "loss": 0.4638, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.6042057107237141, "learning_rate": 1.096774193548387e-05, "loss": 0.4357, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.790056447669648, "learning_rate": 1.1290322580645164e-05, "loss": 0.4611, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6408310320789117, "learning_rate": 1.1612903225806453e-05, "loss": 0.4419, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.5384832898800204, "learning_rate": 1.1935483870967743e-05, "loss": 0.4287, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.5959057482889285, "learning_rate": 1.2258064516129034e-05, "loss": 0.4604, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.672922384686366, "learning_rate": 1.2580645161290324e-05, "loss": 0.428, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6335463515282312, "learning_rate": 1.2903225806451613e-05, "loss": 0.4079, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.6405439902388644, "learning_rate": 1.3225806451612903e-05, "loss": 0.4277, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6398117048972151, "learning_rate": 1.3548387096774194e-05, "loss": 0.4063, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.633791412432481, "learning_rate": 1.3870967741935486e-05, "loss": 0.4351, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6307042636155802, "learning_rate": 1.4193548387096776e-05, "loss": 0.4184, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.5451591573821788, "learning_rate": 1.4516129032258066e-05, "loss": 0.414, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.6519664774412253, "learning_rate": 1.4838709677419357e-05, "loss": 0.4349, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.4874482760801229, "learning_rate": 1.5161290322580646e-05, "loss": 0.4404, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.604898301098291, "learning_rate": 1.5483870967741936e-05, "loss": 0.4449, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5571164375802647, "learning_rate": 1.5806451612903226e-05, "loss": 0.4157, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.4744886496805684, "learning_rate": 1.6129032258064517e-05, "loss": 0.4189, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5235853242142384, "learning_rate": 1.6451612903225807e-05, "loss": 0.4151, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.5300935336870748, "learning_rate": 1.6774193548387098e-05, "loss": 0.4145, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.48100252030550245, "learning_rate": 1.7096774193548388e-05, "loss": 0.4167, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5346675448050163, "learning_rate": 1.741935483870968e-05, "loss": 0.4117, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.4981419760081804, "learning_rate": 1.774193548387097e-05, "loss": 0.4189, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6598680337472163, "learning_rate": 1.806451612903226e-05, "loss": 0.4159, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6126311276276901, "learning_rate": 1.838709677419355e-05, "loss": 0.4076, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.589347511968846, "learning_rate": 1.870967741935484e-05, "loss": 0.4206, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5952150641497727, "learning_rate": 1.903225806451613e-05, "loss": 0.4072, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5836289677263679, "learning_rate": 1.935483870967742e-05, "loss": 0.4145, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5740312760277768, "learning_rate": 1.967741935483871e-05, "loss": 0.4123, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.6290323548370004, "learning_rate": 2e-05, "loss": 0.4219, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5597858001641445, "learning_rate": 2.0322580645161292e-05, "loss": 0.4019, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.6571165652219018, "learning_rate": 2.0645161290322582e-05, "loss": 0.3927, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.6956771253469622, "learning_rate": 2.0967741935483873e-05, "loss": 0.4045, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.527068244076508, "learning_rate": 2.1290322580645163e-05, "loss": 0.4022, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.6230652276169771, "learning_rate": 2.161290322580645e-05, "loss": 0.4088, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.6297136810807468, "learning_rate": 2.193548387096774e-05, "loss": 0.4009, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.6338563890509386, "learning_rate": 2.225806451612903e-05, "loss": 0.4033, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.5038743182796402, "learning_rate": 2.2580645161290328e-05, "loss": 0.4038, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.6347730933702843, "learning_rate": 2.2903225806451615e-05, "loss": 0.4044, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.5881950818249323, "learning_rate": 2.3225806451612906e-05, "loss": 0.3976, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.6850788950830541, "learning_rate": 2.3548387096774196e-05, "loss": 0.399, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6253177129704952, "learning_rate": 2.3870967741935486e-05, "loss": 0.3876, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.6167458970936193, "learning_rate": 2.4193548387096777e-05, "loss": 0.4041, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.5949525885659228, "learning_rate": 2.4516129032258067e-05, "loss": 0.4112, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.6549678254469554, "learning_rate": 2.4838709677419358e-05, "loss": 0.3844, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.8741312276051013, "learning_rate": 2.5161290322580648e-05, "loss": 0.4148, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7158278338062114, "learning_rate": 2.548387096774194e-05, "loss": 0.3801, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.6795396983213223, "learning_rate": 2.5806451612903226e-05, "loss": 0.4017, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.6115038501037927, "learning_rate": 2.6129032258064516e-05, "loss": 0.3935, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.6566688348876698, "learning_rate": 2.6451612903225806e-05, "loss": 0.3956, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.9146349579030219, "learning_rate": 2.6774193548387097e-05, "loss": 0.4062, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.872946034842334, "learning_rate": 2.7096774193548387e-05, "loss": 0.412, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.5136926057483998, "learning_rate": 2.7419354838709678e-05, "loss": 0.3945, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7184728093387329, "learning_rate": 2.774193548387097e-05, "loss": 0.3859, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7206550110721986, "learning_rate": 2.8064516129032262e-05, "loss": 0.4145, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.804405431657358, "learning_rate": 2.8387096774193552e-05, "loss": 0.394, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.6179749080086973, "learning_rate": 2.8709677419354843e-05, "loss": 0.4017, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7110676807137664, "learning_rate": 2.9032258064516133e-05, "loss": 0.3846, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.5594995712843723, "learning_rate": 2.9354838709677423e-05, "loss": 0.3756, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.616393440443513, "learning_rate": 2.9677419354838714e-05, "loss": 0.3951, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.7064829136030256, "learning_rate": 3.0000000000000004e-05, "loss": 0.4018, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.5509981684709913, "learning_rate": 3.032258064516129e-05, "loss": 0.3943, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.5953284356262639, "learning_rate": 3.0645161290322585e-05, "loss": 0.3823, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.6612911030218687, "learning_rate": 3.096774193548387e-05, "loss": 0.3857, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.6118569228698735, "learning_rate": 3.1290322580645166e-05, "loss": 0.4094, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.554255598052319, "learning_rate": 3.161290322580645e-05, "loss": 0.4043, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.7673223749680972, "learning_rate": 3.193548387096774e-05, "loss": 0.4031, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.7864228126946654, "learning_rate": 3.2258064516129034e-05, "loss": 0.3823, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.772509363636162, "learning_rate": 3.258064516129033e-05, "loss": 0.4073, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.731267988801205, "learning_rate": 3.2903225806451614e-05, "loss": 0.3991, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.708167100594103, "learning_rate": 3.322580645161291e-05, "loss": 0.3758, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.6907017871255756, "learning_rate": 3.3548387096774195e-05, "loss": 0.3836, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.7104002978078597, "learning_rate": 3.387096774193549e-05, "loss": 0.4062, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.9236264328686119, "learning_rate": 3.4193548387096776e-05, "loss": 0.4055, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.7530336774530603, "learning_rate": 3.451612903225807e-05, "loss": 0.3792, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.6931572259052723, "learning_rate": 3.483870967741936e-05, "loss": 0.3749, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9000068927267706, "learning_rate": 3.516129032258065e-05, "loss": 0.4128, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.6517949829724201, "learning_rate": 3.548387096774194e-05, "loss": 0.3913, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.6083295512198353, "learning_rate": 3.5806451612903225e-05, "loss": 0.3969, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.7156386990848301, "learning_rate": 3.612903225806452e-05, "loss": 0.3816, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.6544637299629203, "learning_rate": 3.6451612903225805e-05, "loss": 0.3985, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.6158697093537401, "learning_rate": 3.67741935483871e-05, "loss": 0.3967, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.746086568316179, "learning_rate": 3.7096774193548386e-05, "loss": 0.3921, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.6853959604491591, "learning_rate": 3.741935483870968e-05, "loss": 0.3889, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.7300637684286888, "learning_rate": 3.7741935483870974e-05, "loss": 0.3805, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 0.552567528105839, "learning_rate": 3.806451612903226e-05, "loss": 0.3691, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 0.6263213137705046, "learning_rate": 3.8387096774193555e-05, "loss": 0.3885, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.6594383880737251, "learning_rate": 3.870967741935484e-05, "loss": 0.3676, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.5969511167735385, "learning_rate": 3.9032258064516135e-05, "loss": 0.3874, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.6181792674128528, "learning_rate": 3.935483870967742e-05, "loss": 0.3949, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.6985100480633836, "learning_rate": 3.9677419354838716e-05, "loss": 0.3862, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.668283437354844, "learning_rate": 4e-05, "loss": 0.3833, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.5123951627422177, "learning_rate": 3.9999920040266474e-05, "loss": 0.3861, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.6969585880898048, "learning_rate": 3.999968016170525e-05, "loss": 0.3838, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.5949564385967117, "learning_rate": 3.9999280366234394e-05, "loss": 0.3853, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.6739685751453015, "learning_rate": 3.999872065705065e-05, "loss": 0.3828, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.6598686193297033, "learning_rate": 3.999800103862945e-05, "loss": 0.3876, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.6339825594159186, "learning_rate": 3.9997121516724834e-05, "loss": 0.4017, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.6589552618450356, "learning_rate": 3.999608209836944e-05, "loss": 0.3879, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.486473234310688, "learning_rate": 3.999488279187443e-05, "loss": 0.3847, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.6361377265508726, "learning_rate": 3.9993523606829425e-05, "loss": 0.3992, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.5725225977381627, "learning_rate": 3.9992004554102435e-05, "loss": 0.3765, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.5004677407469004, "learning_rate": 3.999032564583976e-05, "loss": 0.3887, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.5600293289035149, "learning_rate": 3.998848689546591e-05, "loss": 0.3858, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.5325918486068432, "learning_rate": 3.9986488317683496e-05, "loss": 0.3831, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.589827148672302, "learning_rate": 3.9984329928473067e-05, "loss": 0.3859, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.5477984241998892, "learning_rate": 3.998201174509306e-05, "loss": 0.3769, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.5722490433487333, "learning_rate": 3.997953378607961e-05, "loss": 0.3818, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.48706804442676493, "learning_rate": 3.9976896071246403e-05, "loss": 0.3941, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.5316266648599492, "learning_rate": 3.997409862168454e-05, "loss": 0.3699, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.5026298387306514, "learning_rate": 3.997114145976237e-05, "loss": 0.3783, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.5474848533674711, "learning_rate": 3.9968024609125245e-05, "loss": 0.3911, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.5402724291312393, "learning_rate": 3.996474809469545e-05, "loss": 0.3855, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.38960732136282294, "learning_rate": 3.996131194267189e-05, "loss": 0.3763, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.5001606142503882, "learning_rate": 3.995771618052995e-05, "loss": 0.37, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.43650892217944887, "learning_rate": 3.9953960837021256e-05, "loss": 0.3851, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.5259111450796966, "learning_rate": 3.995004594217343e-05, "loss": 0.368, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.5317427810591795, "learning_rate": 3.994597152728987e-05, "loss": 0.3638, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6527707119887709, "learning_rate": 3.994173762494947e-05, "loss": 0.3837, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.4260369705168573, "learning_rate": 3.9937344269006424e-05, "loss": 0.3676, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.6017762129443496, "learning_rate": 3.993279149458988e-05, "loss": 0.3924, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.501766827008628, "learning_rate": 3.9928079338103695e-05, "loss": 0.3899, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.5677176072908553, "learning_rate": 3.992320783722616e-05, "loss": 0.3835, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.5237779709186631, "learning_rate": 3.991817703090965e-05, "loss": 0.3864, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6192107708122521, "learning_rate": 3.991298695938038e-05, "loss": 0.3789, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.5410741385057695, "learning_rate": 3.9907637664138e-05, "loss": 0.3707, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6390426586546276, "learning_rate": 3.990212918795534e-05, "loss": 0.3841, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.5795718749504484, "learning_rate": 3.9896461574878036e-05, "loss": 0.3697, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.5502908867013396, "learning_rate": 3.989063487022416e-05, "loss": 0.3777, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.6840189018167698, "learning_rate": 3.9884649120583903e-05, "loss": 0.3724, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.5312417508260869, "learning_rate": 3.987850437381915e-05, "loss": 0.3665, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6594512533953235, "learning_rate": 3.987220067906313e-05, "loss": 0.3975, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.8393210213532102, "learning_rate": 3.986573808672002e-05, "loss": 0.4011, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.5984367753577844, "learning_rate": 3.9859116648464534e-05, "loss": 0.3808, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5582675587309203, "learning_rate": 3.985233641724152e-05, "loss": 0.3839, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7724696775712642, "learning_rate": 3.984539744726554e-05, "loss": 0.3761, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.40976894551061915, "learning_rate": 3.983829979402038e-05, "loss": 0.3797, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.5327669337241707, "learning_rate": 3.983104351425871e-05, "loss": 0.3619, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.562523639679183, "learning_rate": 3.982362866600154e-05, "loss": 0.3591, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.41693097920712907, "learning_rate": 3.9816055308537806e-05, "loss": 0.3826, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.7096049641580542, "learning_rate": 3.980832350242388e-05, "loss": 0.3781, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5466760147076989, "learning_rate": 3.980043330948306e-05, "loss": 0.3838, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.44697826931593226, "learning_rate": 3.9792384792805124e-05, "loss": 0.3805, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5205886608680221, "learning_rate": 3.978417801674579e-05, "loss": 0.3677, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.4704009525444477, "learning_rate": 3.9775813046926244e-05, "loss": 0.3742, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.5141303484671288, "learning_rate": 3.976728995023254e-05, "loss": 0.383, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6208412686799271, "learning_rate": 3.975860879481514e-05, "loss": 0.3641, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.4484568395351859, "learning_rate": 3.974976965008833e-05, "loss": 0.3839, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5007737937454938, "learning_rate": 3.9740772586729674e-05, "loss": 0.3671, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.4127502979837837, "learning_rate": 3.973161767667946e-05, "loss": 0.3823, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.4901565687108072, "learning_rate": 3.972230499314009e-05, "loss": 0.3829, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.48366594309293054, "learning_rate": 3.9712834610575545e-05, "loss": 0.3814, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.44058624055321555, "learning_rate": 3.9703206604710746e-05, "loss": 0.3763, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.4176261493286557, "learning_rate": 3.969342105253098e-05, "loss": 0.3696, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.41836419601990144, "learning_rate": 3.9683478032281246e-05, "loss": 0.3785, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.4375757926749219, "learning_rate": 3.967337762346568e-05, "loss": 0.3669, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.4206455659484227, "learning_rate": 3.9663119906846885e-05, "loss": 0.367, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.4321668323363726, "learning_rate": 3.965270496444528e-05, "loss": 0.3792, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.4417452240448929, "learning_rate": 3.9642132879538465e-05, "loss": 0.3526, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.3979362018437697, "learning_rate": 3.9631403736660566e-05, "loss": 0.3792, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5093029149810189, "learning_rate": 3.962051762160151e-05, "loss": 0.382, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.38476805862663105, "learning_rate": 3.960947462140638e-05, "loss": 0.3614, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.536213143504002, "learning_rate": 3.959827482437472e-05, "loss": 0.3616, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.38497244146891446, "learning_rate": 3.958691832005981e-05, "loss": 0.3913, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5577097469716411, "learning_rate": 3.9575405199267944e-05, "loss": 0.3662, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.4620268295393993, "learning_rate": 3.956373555405774e-05, "loss": 0.3869, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.5416017037827816, "learning_rate": 3.955190947773937e-05, "loss": 0.373, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.41189852005277805, "learning_rate": 3.9539927064873824e-05, "loss": 0.3543, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.5927841195357465, "learning_rate": 3.952778841127214e-05, "loss": 0.3722, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.4275695579065861, "learning_rate": 3.95154936139947e-05, "loss": 0.3862, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.6082033278474935, "learning_rate": 3.950304277135034e-05, "loss": 0.3801, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.4457521837529489, "learning_rate": 3.94904359828957e-05, "loss": 0.3746, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5304118591653925, "learning_rate": 3.94776733494343e-05, "loss": 0.3722, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.42981604230904674, "learning_rate": 3.9464754973015826e-05, "loss": 0.3699, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.46540932639541516, "learning_rate": 3.9451680956935275e-05, "loss": 0.3784, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.4271974371117413, "learning_rate": 3.943845140573213e-05, "loss": 0.3616, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.557931555669109, "learning_rate": 3.942506642518952e-05, "loss": 0.39, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.4556823246604565, "learning_rate": 3.9411526122333396e-05, "loss": 0.3813, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.4960003447456358, "learning_rate": 3.939783060543167e-05, "loss": 0.3687, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.4836911777434884, "learning_rate": 3.938397998399333e-05, "loss": 0.3744, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.533069417567158, "learning_rate": 3.936997436876756e-05, "loss": 0.3767, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.43436233418770287, "learning_rate": 3.935581387174289e-05, "loss": 0.3765, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.44376353791941553, "learning_rate": 3.9341498606146295e-05, "loss": 0.3549, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.40700846328168905, "learning_rate": 3.932702868644224e-05, "loss": 0.3788, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.4869418823146371, "learning_rate": 3.931240422833181e-05, "loss": 0.377, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.42768080555785, "learning_rate": 3.9297625348751806e-05, "loss": 0.3969, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.41640619699257425, "learning_rate": 3.9282692165873744e-05, "loss": 0.3732, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.4771947182105158, "learning_rate": 3.9267604799102945e-05, "loss": 0.3761, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.3675791496702074, "learning_rate": 3.9252363369077615e-05, "loss": 0.349, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.448253436206787, "learning_rate": 3.9236967997667796e-05, "loss": 0.3596, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.39475240775254067, "learning_rate": 3.9221418807974496e-05, "loss": 0.3803, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.4409459448403289, "learning_rate": 3.92057159243286e-05, "loss": 0.3768, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.3961420871883123, "learning_rate": 3.9189859472289956e-05, "loss": 0.3781, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.43680678902018905, "learning_rate": 3.9173849578646324e-05, "loss": 0.3664, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.38702847203815566, "learning_rate": 3.9157686371412395e-05, "loss": 0.3701, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.35810815068205354, "learning_rate": 3.914136997982874e-05, "loss": 0.3655, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.4136680159433635, "learning_rate": 3.912490053436079e-05, "loss": 0.3658, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.4385422117011922, "learning_rate": 3.9108278166697805e-05, "loss": 0.3686, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.3888750531801617, "learning_rate": 3.909150300975178e-05, "loss": 0.371, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4309945081847793, "learning_rate": 3.907457519765642e-05, "loss": 0.3663, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.4470793083363246, "learning_rate": 3.905749486576607e-05, "loss": 0.358, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.4446109364525744, "learning_rate": 3.90402621506546e-05, "loss": 0.3619, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.4916836617105671, "learning_rate": 3.902287719011435e-05, "loss": 0.3634, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.5113858812498225, "learning_rate": 3.900534012315499e-05, "loss": 0.3591, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.45417281564875905, "learning_rate": 3.8987651090002454e-05, "loss": 0.3709, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.46190785604647616, "learning_rate": 3.896981023209777e-05, "loss": 0.3777, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.4803703906300371, "learning_rate": 3.8951817692095966e-05, "loss": 0.3717, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4931914789760214, "learning_rate": 3.893367361386491e-05, "loss": 0.3626, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.36477106484068506, "learning_rate": 3.891537814248417e-05, "loss": 0.3597, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.44379375258011766, "learning_rate": 3.889693142424384e-05, "loss": 0.3743, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.37764856204863706, "learning_rate": 3.8878333606643405e-05, "loss": 0.3543, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.47531471675466264, "learning_rate": 3.885958483839049e-05, "loss": 0.3607, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.4040129009068098, "learning_rate": 3.8840685269399786e-05, "loss": 0.3698, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.49631134384764247, "learning_rate": 3.882163505079171e-05, "loss": 0.3523, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.41825999665421043, "learning_rate": 3.880243433489132e-05, "loss": 0.369, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5436010142472042, "learning_rate": 3.878308327522702e-05, "loss": 0.3215, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.4475986015436142, "learning_rate": 3.876358202652936e-05, "loss": 0.3093, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.460897202355817, "learning_rate": 3.8743930744729835e-05, "loss": 0.3108, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.5237041783466839, "learning_rate": 3.8724129586959535e-05, "loss": 0.2926, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.4590879143782289, "learning_rate": 3.870417871154801e-05, "loss": 0.3085, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.4229490461054704, "learning_rate": 3.868407827802192e-05, "loss": 0.3173, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.4085474301510787, "learning_rate": 3.8663828447103804e-05, "loss": 0.3004, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.46148328575443803, "learning_rate": 3.8643429380710765e-05, "loss": 0.3193, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.43833310810203213, "learning_rate": 3.862288124195319e-05, "loss": 0.3137, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.4750273920306575, "learning_rate": 3.8602184195133464e-05, "loss": 0.3249, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.4544228680223262, "learning_rate": 3.8581338405744604e-05, "loss": 0.3185, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.47358950302942787, "learning_rate": 3.8560344040468996e-05, "loss": 0.323, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.4260746714506929, "learning_rate": 3.853920126717703e-05, "loss": 0.2953, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.4902068327006535, "learning_rate": 3.851791025492574e-05, "loss": 0.3183, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 4.8123105167282985, "learning_rate": 3.8496471173957515e-05, "loss": 0.3038, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.7175827860193005, "learning_rate": 3.847488419569866e-05, "loss": 0.3257, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5482748810727847, "learning_rate": 3.8453149492758077e-05, "loss": 0.2986, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6209173565108534, "learning_rate": 3.8431267238925886e-05, "loss": 0.3053, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5425853502344645, "learning_rate": 3.840923760917199e-05, "loss": 0.3156, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.590037449616156, "learning_rate": 3.838706077964473e-05, "loss": 0.3051, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.46658517436102576, "learning_rate": 3.836473692766944e-05, "loss": 0.3104, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5774609646875604, "learning_rate": 3.834226623174705e-05, "loss": 0.3308, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.48324326220790587, "learning_rate": 3.831964887155264e-05, "loss": 0.3003, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.584473397353077, "learning_rate": 3.829688502793403e-05, "loss": 0.3347, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.42860818785698496, "learning_rate": 3.827397488291029e-05, "loss": 0.3158, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.49860230345189044, "learning_rate": 3.8250918619670343e-05, "loss": 0.3057, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.4182787491539937, "learning_rate": 3.822771642257145e-05, "loss": 0.2976, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.4550183190838626, "learning_rate": 3.820436847713776e-05, "loss": 0.3016, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.39794700354822005, "learning_rate": 3.8180874970058826e-05, "loss": 0.3055, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.44930785249730304, "learning_rate": 3.8157236089188103e-05, "loss": 0.3069, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.40970894529711976, "learning_rate": 3.813345202354145e-05, "loss": 0.3016, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.405072578292478, "learning_rate": 3.810952296329563e-05, "loss": 0.2963, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.411867279810857, "learning_rate": 3.808544909978676e-05, "loss": 0.2977, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.4294608520522923, "learning_rate": 3.806123062550882e-05, "loss": 0.3095, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.40743235700199876, "learning_rate": 3.803686773411208e-05, "loss": 0.3217, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.42358853727539886, "learning_rate": 3.801236062040158e-05, "loss": 0.324, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.3856397616786516, "learning_rate": 3.798770948033553e-05, "loss": 0.304, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4175093487412353, "learning_rate": 3.796291451102381e-05, "loss": 0.3162, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.4003379048738828, "learning_rate": 3.793797591072631e-05, "loss": 0.307, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.37679427632044243, "learning_rate": 3.791289387885144e-05, "loss": 0.3105, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4142002447795737, "learning_rate": 3.788766861595443e-05, "loss": 0.3055, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.38710657440969143, "learning_rate": 3.7862300323735835e-05, "loss": 0.3165, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.41751606420378934, "learning_rate": 3.783678920503983e-05, "loss": 0.322, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.3963206837813157, "learning_rate": 3.781113546385265e-05, "loss": 0.3143, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.44584226368089525, "learning_rate": 3.7785339305300916e-05, "loss": 0.3041, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.36896493583435663, "learning_rate": 3.7759400935650025e-05, "loss": 0.3116, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.4622681940576291, "learning_rate": 3.77333205623025e-05, "loss": 0.3277, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.39715510598772374, "learning_rate": 3.7707098393796295e-05, "loss": 0.2958, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.4067829848818273, "learning_rate": 3.7680734639803185e-05, "loss": 0.2972, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.3967047809393824, "learning_rate": 3.765422951112704e-05, "loss": 0.3161, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.41125177575829486, "learning_rate": 3.762758321970216e-05, "loss": 0.2984, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.33301764575601944, "learning_rate": 3.7600795978591584e-05, "loss": 0.2968, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.40958654229681213, "learning_rate": 3.757386800198538e-05, "loss": 0.3137, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.3727676816659605, "learning_rate": 3.7546799505198925e-05, "loss": 0.3166, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.359721701767147, "learning_rate": 3.7519590704671197e-05, "loss": 0.296, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.3598619506209118, "learning_rate": 3.749224181796305e-05, "loss": 0.3009, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.36935232572793797, "learning_rate": 3.746475306375545e-05, "loss": 0.3174, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.3723932475373353, "learning_rate": 3.743712466184774e-05, "loss": 0.3147, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.35905442420533046, "learning_rate": 3.7409356833155885e-05, "loss": 0.3114, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4376206843511305, "learning_rate": 3.73814497997107e-05, "loss": 0.3255, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.389218357665662, "learning_rate": 3.7353403784656095e-05, "loss": 0.3228, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.3963374573248822, "learning_rate": 3.732521901224724e-05, "loss": 0.3098, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.3840274953849808, "learning_rate": 3.7296895707848844e-05, "loss": 0.3101, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.46379317681816923, "learning_rate": 3.7268434097933275e-05, "loss": 0.3044, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.3939634220084408, "learning_rate": 3.723983441007882e-05, "loss": 0.3097, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.4492969358869629, "learning_rate": 3.721109687296781e-05, "loss": 0.3138, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.35815890335374756, "learning_rate": 3.718222171638484e-05, "loss": 0.3164, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.35630453296036624, "learning_rate": 3.715320917121488e-05, "loss": 0.3276, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.370783649263609, "learning_rate": 3.712405946944149e-05, "loss": 0.3071, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.36977404076408527, "learning_rate": 3.709477284414488e-05, "loss": 0.3205, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.3834802798034566, "learning_rate": 3.7065349529500136e-05, "loss": 0.3099, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.3763091543219123, "learning_rate": 3.7035789760775305e-05, "loss": 0.3054, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.400281569494053, "learning_rate": 3.70060937743295e-05, "loss": 0.3113, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.3331502873482162, "learning_rate": 3.6976261807611045e-05, "loss": 0.3009, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.40337601229444175, "learning_rate": 3.694629409915555e-05, "loss": 0.3054, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.38896453066114556, "learning_rate": 3.691619088858401e-05, "loss": 0.3045, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.3685145886086403, "learning_rate": 3.68859524166009e-05, "loss": 0.2931, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.4165169070093089, "learning_rate": 3.6855578924992226e-05, "loss": 0.32, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.3885027677065347, "learning_rate": 3.6825070656623626e-05, "loss": 0.3035, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.454851898217124, "learning_rate": 3.67944278554384e-05, "loss": 0.3084, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.40077500968244273, "learning_rate": 3.676365076645557e-05, "loss": 0.3105, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.3607258318802067, "learning_rate": 3.673273963576791e-05, "loss": 0.3223, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.3696257357147633, "learning_rate": 3.670169471054001e-05, "loss": 0.3047, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.4206192506582285, "learning_rate": 3.6670516239006254e-05, "loss": 0.3131, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4249782127102773, "learning_rate": 3.663920447046888e-05, "loss": 0.3245, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.3792294539251222, "learning_rate": 3.6607759655295954e-05, "loss": 0.3072, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.39291255968292693, "learning_rate": 3.657618204491937e-05, "loss": 0.3158, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.3907042380715031, "learning_rate": 3.6544471891832875e-05, "loss": 0.2929, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.3518467643453036, "learning_rate": 3.6512629449589983e-05, "loss": 0.3131, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.41402757615516617, "learning_rate": 3.6480654972802045e-05, "loss": 0.3284, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.3440639581782692, "learning_rate": 3.644854871713611e-05, "loss": 0.3114, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.39521871278225207, "learning_rate": 3.6416310939312924e-05, "loss": 0.3236, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.35428334660941774, "learning_rate": 3.638394189710493e-05, "loss": 0.3209, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.3601671447018256, "learning_rate": 3.635144184933412e-05, "loss": 0.3083, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.3171876529052187, "learning_rate": 3.6318811055869994e-05, "loss": 0.2953, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.35002318876692645, "learning_rate": 3.628604977762752e-05, "loss": 0.3175, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.3466626435217876, "learning_rate": 3.6253158276565004e-05, "loss": 0.3107, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.3734216980112617, "learning_rate": 3.6220136815682016e-05, "loss": 0.2863, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.43466642560706314, "learning_rate": 3.618698565901727e-05, "loss": 0.3161, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.3941397692413274, "learning_rate": 3.615370507164654e-05, "loss": 0.3221, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.42466097995159097, "learning_rate": 3.61202953196805e-05, "loss": 0.3265, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.4605554258989173, "learning_rate": 3.6086756670262654e-05, "loss": 0.3375, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.35842757929661395, "learning_rate": 3.6053089391567135e-05, "loss": 0.3027, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.3993588958451766, "learning_rate": 3.601929375279662e-05, "loss": 0.3115, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.3833610558556566, "learning_rate": 3.598537002418012e-05, "loss": 0.3245, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.41899103589786946, "learning_rate": 3.5951318476970885e-05, "loss": 0.3057, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.3637281550116784, "learning_rate": 3.591713938344416e-05, "loss": 0.3133, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.4092566705473945, "learning_rate": 3.588283301689507e-05, "loss": 0.2941, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.45572025110156444, "learning_rate": 3.5848399651636424e-05, "loss": 0.3246, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.36262540307457536, "learning_rate": 3.5813839562996473e-05, "loss": 0.3079, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.4114042477171729, "learning_rate": 3.5779153027316775e-05, "loss": 0.3128, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.38762494157390703, "learning_rate": 3.574434032194994e-05, "loss": 0.3207, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.43401577898556654, "learning_rate": 3.5709401725257436e-05, "loss": 0.3316, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4186954971522113, "learning_rate": 3.5674337516607346e-05, "loss": 0.3016, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5400963658158756, "learning_rate": 3.563914797637216e-05, "loss": 0.3173, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.39806578963353234, "learning_rate": 3.560383338592649e-05, "loss": 0.3151, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5203569854687553, "learning_rate": 3.556839402764487e-05, "loss": 0.3232, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.39156623850610045, "learning_rate": 3.553283018489946e-05, "loss": 0.3225, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5268977491701088, "learning_rate": 3.54971421420578e-05, "loss": 0.3161, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.401233486703687, "learning_rate": 3.5461330184480524e-05, "loss": 0.3077, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4592282836087439, "learning_rate": 3.54253945985191e-05, "loss": 0.331, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4381535313764886, "learning_rate": 3.5389335671513524e-05, "loss": 0.3272, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.3950292232428719, "learning_rate": 3.5353153691789986e-05, "loss": 0.2993, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.44141378869512443, "learning_rate": 3.531684894865866e-05, "loss": 0.3173, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4263269552418421, "learning_rate": 3.528042173241128e-05, "loss": 0.3284, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.3774184953391704, "learning_rate": 3.524387233431892e-05, "loss": 0.3298, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.35967700731409824, "learning_rate": 3.520720104662958e-05, "loss": 0.3009, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.39281126952798073, "learning_rate": 3.5170408162565904e-05, "loss": 0.3074, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.35377511636583914, "learning_rate": 3.513349397632281e-05, "loss": 0.3062, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.38074946348802036, "learning_rate": 3.5096458783065145e-05, "loss": 0.3218, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.4057671739342926, "learning_rate": 3.505930287892533e-05, "loss": 0.3193, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.3411975550732986, "learning_rate": 3.502202656100099e-05, "loss": 0.3177, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.46094013020848407, "learning_rate": 3.498463012735256e-05, "loss": 0.3046, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.3251607517509953, "learning_rate": 3.494711387700094e-05, "loss": 0.3134, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.46158506368557545, "learning_rate": 3.490947810992505e-05, "loss": 0.3028, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.35832848978405296, "learning_rate": 3.48717231270595e-05, "loss": 0.3054, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.40365450748977594, "learning_rate": 3.483384923029211e-05, "loss": 0.3049, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.3811744008880752, "learning_rate": 3.479585672246156e-05, "loss": 0.3235, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.35037046094162816, "learning_rate": 3.4757745907354924e-05, "loss": 0.3004, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4253287898437073, "learning_rate": 3.471951708970527e-05, "loss": 0.3193, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.35836061252251744, "learning_rate": 3.468117057518921e-05, "loss": 0.3143, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.4224909206636071, "learning_rate": 3.4642706670424426e-05, "loss": 0.3163, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.3976751522132013, "learning_rate": 3.460412568296731e-05, "loss": 0.306, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.43419701342965494, "learning_rate": 3.456542792131039e-05, "loss": 0.3134, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.35363129648612013, "learning_rate": 3.4526613694879936e-05, "loss": 0.3068, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.4429762399142217, "learning_rate": 3.448768331403348e-05, "loss": 0.3228, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.3858590948567384, "learning_rate": 3.44486370900573e-05, "loss": 0.3215, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.3885479372895316, "learning_rate": 3.440947533516396e-05, "loss": 0.3068, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.40288406368519725, "learning_rate": 3.4370198362489816e-05, "loss": 0.3094, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.3137092241626408, "learning_rate": 3.43308064860925e-05, "loss": 0.2906, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.3965327537962948, "learning_rate": 3.4291300020948393e-05, "loss": 0.3002, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.3193325006600475, "learning_rate": 3.425167928295015e-05, "loss": 0.3194, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.44321117052016074, "learning_rate": 3.421194458890411e-05, "loss": 0.318, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.3373423322125795, "learning_rate": 3.4172096256527865e-05, "loss": 0.3263, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.34330485971504354, "learning_rate": 3.4132134604447595e-05, "loss": 0.3116, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.3276836807130435, "learning_rate": 3.409205995219561e-05, "loss": 0.2818, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.3743311352187326, "learning_rate": 3.4051872620207765e-05, "loss": 0.3188, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.3239680573607507, "learning_rate": 3.40115729298209e-05, "loss": 0.295, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.35085832948680545, "learning_rate": 3.397116120327025e-05, "loss": 0.3046, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.3546706352848645, "learning_rate": 3.3930637763686916e-05, "loss": 0.3019, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.4219603993401056, "learning_rate": 3.389000293509524e-05, "loss": 0.315, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.3859184051573508, "learning_rate": 3.3849257042410225e-05, "loss": 0.3277, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.3630619996921531, "learning_rate": 3.380840041143494e-05, "loss": 0.3113, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.3426689190245307, "learning_rate": 3.376743336885792e-05, "loss": 0.3101, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.34968443366963936, "learning_rate": 3.372635624225055e-05, "loss": 0.3083, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.35285927612051227, "learning_rate": 3.3685169360064445e-05, "loss": 0.3183, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4091954749929655, "learning_rate": 3.3643873051628804e-05, "loss": 0.3211, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.3821474993132987, "learning_rate": 3.3602467647147814e-05, "loss": 0.3096, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.33980618683617003, "learning_rate": 3.356095347769799e-05, "loss": 0.3009, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.3604118304715944, "learning_rate": 3.351933087522552e-05, "loss": 0.3042, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.3507490250757823, "learning_rate": 3.3477600172543626e-05, "loss": 0.3015, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.38750990451829725, "learning_rate": 3.3435761703329894e-05, "loss": 0.317, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.3978472762593145, "learning_rate": 3.3393815802123606e-05, "loss": 0.3041, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.3819933968241246, "learning_rate": 3.335176280432308e-05, "loss": 0.3122, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.39232864465667083, "learning_rate": 3.330960304618295e-05, "loss": 0.3061, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.3949623188184136, "learning_rate": 3.326733686481153e-05, "loss": 0.3353, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.38808014951288283, "learning_rate": 3.3224964598168084e-05, "loss": 0.3107, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.3886744119801081, "learning_rate": 3.318248658506012e-05, "loss": 0.2997, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.4832474177435718, "learning_rate": 3.313990316514069e-05, "loss": 0.3252, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.39113951628525084, "learning_rate": 3.309721467890571e-05, "loss": 0.3139, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.42787021240671796, "learning_rate": 3.305442146769115e-05, "loss": 0.2935, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.36053689438805997, "learning_rate": 3.30115238736704e-05, "loss": 0.3151, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.35242223330792566, "learning_rate": 3.296852223985148e-05, "loss": 0.3126, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3621686863120339, "learning_rate": 3.2925416910074315e-05, "loss": 0.3204, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.38489381741996465, "learning_rate": 3.288220822900796e-05, "loss": 0.3197, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.36024406772592965, "learning_rate": 3.283889654214788e-05, "loss": 0.3183, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.37246530832646285, "learning_rate": 3.279548219581317e-05, "loss": 0.3228, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.3684142074245011, "learning_rate": 3.275196553714379e-05, "loss": 0.3091, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.3491827113944078, "learning_rate": 3.270834691409778e-05, "loss": 0.3039, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.3402866250619368, "learning_rate": 3.266462667544849e-05, "loss": 0.3086, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.3381663993739286, "learning_rate": 3.262080517078178e-05, "loss": 0.3128, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.3572292203363572, "learning_rate": 3.257688275049323e-05, "loss": 0.3036, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.35180615476757304, "learning_rate": 3.253285976578535e-05, "loss": 0.3151, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.40044862000604853, "learning_rate": 3.2488736568664756e-05, "loss": 0.3074, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.33912884930482745, "learning_rate": 3.244451351193935e-05, "loss": 0.3212, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.3699272107738753, "learning_rate": 3.240019094921551e-05, "loss": 0.3167, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.30863975609001726, "learning_rate": 3.235576923489527e-05, "loss": 0.3137, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.39499748576462373, "learning_rate": 3.2311248724173476e-05, "loss": 0.3051, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.3206472359915483, "learning_rate": 3.226662977303494e-05, "loss": 0.3098, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.3410878153219857, "learning_rate": 3.2221912738251626e-05, "loss": 0.3221, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.33848594541119603, "learning_rate": 3.2177097977379736e-05, "loss": 0.3063, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.3139429128737981, "learning_rate": 3.21321858487569e-05, "loss": 0.3057, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.31589045838737695, "learning_rate": 3.208717671149931e-05, "loss": 0.311, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.35204016274278277, "learning_rate": 3.204207092549882e-05, "loss": 0.3314, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.3448746693655694, "learning_rate": 3.19968688514201e-05, "loss": 0.3074, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.31184618059529184, "learning_rate": 3.195157085069774e-05, "loss": 0.3058, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.3729328939631633, "learning_rate": 3.190617728553332e-05, "loss": 0.3019, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.3462541924125286, "learning_rate": 3.1860688518892606e-05, "loss": 0.3047, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.3301675760554136, "learning_rate": 3.181510491450254e-05, "loss": 0.3191, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.3987733331590893, "learning_rate": 3.176942683684842e-05, "loss": 0.3164, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.40428834614025044, "learning_rate": 3.1723654651170934e-05, "loss": 0.3221, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.39395083364668243, "learning_rate": 3.167778872346327e-05, "loss": 0.3108, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.47351151131338354, "learning_rate": 3.163182942046815e-05, "loss": 0.313, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.34287800962098963, "learning_rate": 3.158577710967494e-05, "loss": 0.3234, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.44494786202917624, "learning_rate": 3.153963215931669e-05, "loss": 0.3042, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.43968196274586435, "learning_rate": 3.14933949383672e-05, "loss": 0.3134, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.3602865980158681, "learning_rate": 3.144706581653805e-05, "loss": 0.2923, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.402384077491387, "learning_rate": 3.140064516427566e-05, "loss": 0.3097, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.44537948735691646, "learning_rate": 3.135413335275833e-05, "loss": 0.3223, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.33934862881195255, "learning_rate": 3.130753075389327e-05, "loss": 0.3042, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.47375430541363095, "learning_rate": 3.1260837740313625e-05, "loss": 0.3105, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.3225052062219731, "learning_rate": 3.121405468537547e-05, "loss": 0.2974, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.46847427254906737, "learning_rate": 3.116718196315488e-05, "loss": 0.2957, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4060791458855451, "learning_rate": 3.1120219948444894e-05, "loss": 0.314, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.3867675658894724, "learning_rate": 3.107316901675252e-05, "loss": 0.2882, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.43079219401478225, "learning_rate": 3.1026029544295745e-05, "loss": 0.3124, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.3344884025273699, "learning_rate": 3.097880190800057e-05, "loss": 0.3187, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3659967402916039, "learning_rate": 3.093148648549788e-05, "loss": 0.2955, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4010242883715558, "learning_rate": 3.088408365512055e-05, "loss": 0.2984, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.3382882137072033, "learning_rate": 3.083659379590034e-05, "loss": 0.2938, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.378332164445827, "learning_rate": 3.0789017287564913e-05, "loss": 0.3088, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.3364994184196296, "learning_rate": 3.074135451053475e-05, "loss": 0.3131, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.34439669179970606, "learning_rate": 3.069360584592015e-05, "loss": 0.3076, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.35546482033697907, "learning_rate": 3.064577167551816e-05, "loss": 0.3163, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.35945532689123916, "learning_rate": 3.059785238180953e-05, "loss": 0.3148, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.35100291144332885, "learning_rate": 3.054984834795566e-05, "loss": 0.3191, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.32811609620155313, "learning_rate": 3.0501759957795537e-05, "loss": 0.3151, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.3484786624789004, "learning_rate": 3.0453587595842627e-05, "loss": 0.3008, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.3671154808973987, "learning_rate": 3.0405331647281856e-05, "loss": 0.3014, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.31970109381567013, "learning_rate": 3.0356992497966508e-05, "loss": 0.3003, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3264693802592578, "learning_rate": 3.0308570534415137e-05, "loss": 0.2911, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.32110493361191655, "learning_rate": 3.0260066143808467e-05, "loss": 0.315, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.30064791197216406, "learning_rate": 3.021147971398632e-05, "loss": 0.3121, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.3666236874388868, "learning_rate": 3.0162811633444478e-05, "loss": 0.3034, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.3033193039688193, "learning_rate": 3.0114062291331635e-05, "loss": 0.3037, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.33655854480218345, "learning_rate": 3.0065232077446217e-05, "loss": 0.3131, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.3568578240116604, "learning_rate": 3.001632138223332e-05, "loss": 0.2908, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.4433361640451042, "learning_rate": 2.9967330596781565e-05, "loss": 0.2428, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.4023317873888134, "learning_rate": 2.9918260112819952e-05, "loss": 0.2333, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5499062409406879, "learning_rate": 2.9869110322714778e-05, "loss": 0.2316, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.3841321658253715, "learning_rate": 2.9819881619466447e-05, "loss": 0.2285, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.4091409951299339, "learning_rate": 2.9770574396706364e-05, "loss": 0.2454, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.35632800597893066, "learning_rate": 2.972118904869376e-05, "loss": 0.2329, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.37960559722076204, "learning_rate": 2.9671725970312563e-05, "loss": 0.2532, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.3761811161475915, "learning_rate": 2.9622185557068238e-05, "loss": 0.2388, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.40962224289815186, "learning_rate": 2.95725682050846e-05, "loss": 0.2491, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.31873013042419174, "learning_rate": 2.9522874311100684e-05, "loss": 0.241, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.3761577154327195, "learning_rate": 2.9473104272467526e-05, "loss": 0.2265, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.36332436941612084, "learning_rate": 2.942325848714505e-05, "loss": 0.2411, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.3477721178930633, "learning_rate": 2.9373337353698804e-05, "loss": 0.2292, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.35485895685458196, "learning_rate": 2.932334127129686e-05, "loss": 0.2354, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.34860327508685496, "learning_rate": 2.9273270639706547e-05, "loss": 0.2355, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.33440258564666653, "learning_rate": 2.922312585929131e-05, "loss": 0.2278, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.3099466358316786, "learning_rate": 2.9172907331007478e-05, "loss": 0.2459, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.3245777518668227, "learning_rate": 2.9122615456401053e-05, "loss": 0.2199, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.40111829531055326, "learning_rate": 2.9072250637604535e-05, "loss": 0.2229, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.3127906680707385, "learning_rate": 2.9021813277333667e-05, "loss": 0.2332, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.3928880679892195, "learning_rate": 2.8971303778884244e-05, "loss": 0.2434, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.36464375011444344, "learning_rate": 2.8920722546128863e-05, "loss": 0.2143, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.33321124141312103, "learning_rate": 2.887006998351372e-05, "loss": 0.2376, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3795571847133325, "learning_rate": 2.881934649605535e-05, "loss": 0.2401, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.3545052087069631, "learning_rate": 2.8768552489337408e-05, "loss": 0.2383, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.3335678919822856, "learning_rate": 2.8717688369507425e-05, "loss": 0.2251, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.36343766950305006, "learning_rate": 2.8666754543273535e-05, "loss": 0.2308, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.35746030497271464, "learning_rate": 2.8615751417901273e-05, "loss": 0.2211, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.3213202865483303, "learning_rate": 2.856467940121025e-05, "loss": 0.2116, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.34553312517734464, "learning_rate": 2.8513538901570964e-05, "loss": 0.2469, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.33714556770922705, "learning_rate": 2.846233032790149e-05, "loss": 0.2293, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.354486721561669, "learning_rate": 2.84110540896642e-05, "loss": 0.2482, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.3470326302222043, "learning_rate": 2.8359710596862555e-05, "loss": 0.2331, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.3442328125487303, "learning_rate": 2.8308300260037734e-05, "loss": 0.2324, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.2924947483877256, "learning_rate": 2.8256823490265424e-05, "loss": 0.2191, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3302830774572229, "learning_rate": 2.8205280699152515e-05, "loss": 0.2235, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.2991152485218698, "learning_rate": 2.8153672298833777e-05, "loss": 0.2331, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.28733298653098793, "learning_rate": 2.8101998701968615e-05, "loss": 0.2217, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.30717947550397406, "learning_rate": 2.805026032173773e-05, "loss": 0.2459, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.30214922831652, "learning_rate": 2.7998457571839832e-05, "loss": 0.2411, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.3187108149501721, "learning_rate": 2.7946590866488322e-05, "loss": 0.2463, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.34606026133232376, "learning_rate": 2.7894660620408e-05, "loss": 0.2352, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.3095282748996774, "learning_rate": 2.784266724883173e-05, "loss": 0.2247, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3501023971144448, "learning_rate": 2.7790611167497128e-05, "loss": 0.2279, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3755389229916841, "learning_rate": 2.7738492792643224e-05, "loss": 0.2381, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.35835301174040785, "learning_rate": 2.768631254100716e-05, "loss": 0.2376, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.4110723895213824, "learning_rate": 2.7634070829820836e-05, "loss": 0.2178, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.36802273169269417, "learning_rate": 2.7581768076807592e-05, "loss": 0.2249, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.41163589508304266, "learning_rate": 2.7529404700178832e-05, "loss": 0.2496, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.34237189726373435, "learning_rate": 2.7476981118630735e-05, "loss": 0.2424, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.38313425497519876, "learning_rate": 2.742449775134085e-05, "loss": 0.2376, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.34351835480899595, "learning_rate": 2.7371955017964788e-05, "loss": 0.2425, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.2994795947073237, "learning_rate": 2.7319353338632845e-05, "loss": 0.2299, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3355140256068489, "learning_rate": 2.7266693133946645e-05, "loss": 0.2363, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.30752713720648495, "learning_rate": 2.7213974824975785e-05, "loss": 0.2186, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.32251639444445385, "learning_rate": 2.7161198833254464e-05, "loss": 0.2196, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3068153365909663, "learning_rate": 2.7108365580778095e-05, "loss": 0.2538, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.3315093403588732, "learning_rate": 2.705547548999996e-05, "loss": 0.2288, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.29221692724538645, "learning_rate": 2.7002528983827817e-05, "loss": 0.2357, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.31502070627792617, "learning_rate": 2.6949526485620517e-05, "loss": 0.2502, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.30053138355603565, "learning_rate": 2.6896468419184623e-05, "loss": 0.224, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.2956878576570166, "learning_rate": 2.6843355208771024e-05, "loss": 0.2402, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3470942031427508, "learning_rate": 2.6790187279071536e-05, "loss": 0.2484, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.2859252760756639, "learning_rate": 2.67369650552155e-05, "loss": 0.236, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.34080174366053356, "learning_rate": 2.6683688962766407e-05, "loss": 0.2561, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.30916776171746907, "learning_rate": 2.6630359427718468e-05, "loss": 0.2369, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.34401154442432025, "learning_rate": 2.6576976876493225e-05, "loss": 0.2342, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.30945106965840924, "learning_rate": 2.652354173593614e-05, "loss": 0.2427, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.3611148785228481, "learning_rate": 2.647005443331317e-05, "loss": 0.2337, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.31170861879805245, "learning_rate": 2.6416515396307354e-05, "loss": 0.246, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3365267742613875, "learning_rate": 2.636292505301542e-05, "loss": 0.2439, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.3358352562576256, "learning_rate": 2.630928383194431e-05, "loss": 0.2329, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.3280755376969633, "learning_rate": 2.625559216200781e-05, "loss": 0.2253, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3460321406615258, "learning_rate": 2.620185047252308e-05, "loss": 0.2361, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.3055562372128386, "learning_rate": 2.614805919320723e-05, "loss": 0.2246, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.33460772076338485, "learning_rate": 2.6094218754173895e-05, "loss": 0.2419, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.31391916868517183, "learning_rate": 2.60403295859298e-05, "loss": 0.2305, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.33341031677912625, "learning_rate": 2.5986392119371297e-05, "loss": 0.2355, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.3148083219736533, "learning_rate": 2.5932406785780928e-05, "loss": 0.2442, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.30416531551593806, "learning_rate": 2.5878374016823987e-05, "loss": 0.2346, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.3190183761223846, "learning_rate": 2.5824294244545045e-05, "loss": 0.2148, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.3236490147466715, "learning_rate": 2.577016790136453e-05, "loss": 0.2252, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3148897661192727, "learning_rate": 2.5715995420075225e-05, "loss": 0.2305, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.31973484569649535, "learning_rate": 2.5661777233838864e-05, "loss": 0.2448, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.32260292272237817, "learning_rate": 2.5607513776182616e-05, "loss": 0.2273, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3379953903974987, "learning_rate": 2.5553205480995633e-05, "loss": 0.2291, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.3160295043871309, "learning_rate": 2.5498852782525604e-05, "loss": 0.237, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3052672251426915, "learning_rate": 2.5444456115375252e-05, "loss": 0.2408, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.32502116550834537, "learning_rate": 2.539001591449889e-05, "loss": 0.2283, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.30498099513992394, "learning_rate": 2.53355326151989e-05, "loss": 0.237, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3381988062171586, "learning_rate": 2.5281006653122288e-05, "loss": 0.2411, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3262159888634597, "learning_rate": 2.5226438464257217e-05, "loss": 0.2432, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3547796986197636, "learning_rate": 2.5171828484929447e-05, "loss": 0.2554, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.33315484443373544, "learning_rate": 2.5117177151798934e-05, "loss": 0.2349, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.35269459859340374, "learning_rate": 2.506248490185627e-05, "loss": 0.2452, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.3083855021239448, "learning_rate": 2.500775217241923e-05, "loss": 0.2455, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3541605574828685, "learning_rate": 2.4952979401129266e-05, "loss": 0.2363, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.309917878581204, "learning_rate": 2.4898167025948e-05, "loss": 0.2461, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.3473475510240337, "learning_rate": 2.4843315485153703e-05, "loss": 0.2475, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.2842902159500661, "learning_rate": 2.4788425217337856e-05, "loss": 0.2341, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.2840680484727294, "learning_rate": 2.4733496661401572e-05, "loss": 0.2468, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.3102627884034951, "learning_rate": 2.4678530256552114e-05, "loss": 0.2451, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.2958114753414242, "learning_rate": 2.46235264422994e-05, "loss": 0.235, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.3284933046900823, "learning_rate": 2.4568485658452452e-05, "loss": 0.2394, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.29102838846311607, "learning_rate": 2.451340834511592e-05, "loss": 0.2487, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.30333575415393454, "learning_rate": 2.4458294942686528e-05, "loss": 0.2163, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.3156528172646564, "learning_rate": 2.440314589184958e-05, "loss": 0.2416, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.32716931709499203, "learning_rate": 2.434796163357541e-05, "loss": 0.2321, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3367598882083625, "learning_rate": 2.429274260911588e-05, "loss": 0.2299, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.31077897790776676, "learning_rate": 2.423748926000084e-05, "loss": 0.239, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3102767493385943, "learning_rate": 2.418220202803459e-05, "loss": 0.2376, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.29438165984847614, "learning_rate": 2.412688135529237e-05, "loss": 0.229, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.28435007403848794, "learning_rate": 2.4071527684116807e-05, "loss": 0.2122, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.28191325590145216, "learning_rate": 2.4016141457114372e-05, "loss": 0.2353, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.30777146416917356, "learning_rate": 2.396072311715187e-05, "loss": 0.247, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3284794088166263, "learning_rate": 2.3905273107352863e-05, "loss": 0.2253, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.2832492634215161, "learning_rate": 2.3849791871094157e-05, "loss": 0.2337, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.3166332817951689, "learning_rate": 2.379427985200223e-05, "loss": 0.2375, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3019357003818665, "learning_rate": 2.373873749394972e-05, "loss": 0.2341, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.27353141493216354, "learning_rate": 2.3683165241051836e-05, "loss": 0.2344, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.3175961696979079, "learning_rate": 2.3627563537662823e-05, "loss": 0.2422, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.2875417179503328, "learning_rate": 2.3571932828372433e-05, "loss": 0.243, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.2857111174268744, "learning_rate": 2.351627355800233e-05, "loss": 0.2424, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.32663773424597975, "learning_rate": 2.346058617160256e-05, "loss": 0.2353, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.2941143085240875, "learning_rate": 2.3404871114447976e-05, "loss": 0.2343, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.29504028705443447, "learning_rate": 2.334912883203469e-05, "loss": 0.2321, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.309572638061337, "learning_rate": 2.3293359770076505e-05, "loss": 0.207, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.3257385215291722, "learning_rate": 2.323756437450136e-05, "loss": 0.2666, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.28894988488173134, "learning_rate": 2.3181743091447754e-05, "loss": 0.2427, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.3249872422156381, "learning_rate": 2.3125896367261164e-05, "loss": 0.2422, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.3236240983372909, "learning_rate": 2.307002464849052e-05, "loss": 0.2568, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.2964419820399586, "learning_rate": 2.30141283818846e-05, "loss": 0.2348, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.2967645094474366, "learning_rate": 2.2958208014388462e-05, "loss": 0.2476, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.28752390789743326, "learning_rate": 2.2902263993139857e-05, "loss": 0.2333, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.3064862603244527, "learning_rate": 2.2846296765465708e-05, "loss": 0.2413, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3201496302377686, "learning_rate": 2.2790306778878465e-05, "loss": 0.2352, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.2778599083161683, "learning_rate": 2.273429448107257e-05, "loss": 0.2436, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.30955770047495795, "learning_rate": 2.2678260319920868e-05, "loss": 0.2314, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.2824864052476337, "learning_rate": 2.262220474347102e-05, "loss": 0.24, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.30944591203804633, "learning_rate": 2.2566128199941918e-05, "loss": 0.2301, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.297432693129808, "learning_rate": 2.2510031137720104e-05, "loss": 0.2355, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.3091358708516224, "learning_rate": 2.2453914005356206e-05, "loss": 0.2415, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.3327876817726298, "learning_rate": 2.2397777251561302e-05, "loss": 0.2434, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.290301586679535, "learning_rate": 2.2341621325203393e-05, "loss": 0.2481, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.30960212453947517, "learning_rate": 2.2285446675303764e-05, "loss": 0.2365, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.31263650340840193, "learning_rate": 2.2229253751033423e-05, "loss": 0.2518, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.3089889640271253, "learning_rate": 2.2173043001709492e-05, "loss": 0.2598, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.29105332660786737, "learning_rate": 2.2116814876791627e-05, "loss": 0.2447, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.28412736730544697, "learning_rate": 2.2060569825878413e-05, "loss": 0.2494, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.32197556025236485, "learning_rate": 2.2004308298703777e-05, "loss": 0.2343, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.31316437874813696, "learning_rate": 2.1948030745133396e-05, "loss": 0.2254, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.31491225798309197, "learning_rate": 2.1891737615161083e-05, "loss": 0.2475, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3214024972618688, "learning_rate": 2.1835429358905218e-05, "loss": 0.233, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3289080242406129, "learning_rate": 2.17791064266051e-05, "loss": 0.2317, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.2955602230314971, "learning_rate": 2.172276926861741e-05, "loss": 0.2398, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.30861807569921834, "learning_rate": 2.166641833541255e-05, "loss": 0.2358, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3077384611206183, "learning_rate": 2.161005407757109e-05, "loss": 0.2221, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.28845385136148655, "learning_rate": 2.155367694578013e-05, "loss": 0.2393, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.336435077413178, "learning_rate": 2.1497287390829712e-05, "loss": 0.2502, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.29132655933337875, "learning_rate": 2.1440885863609208e-05, "loss": 0.2293, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.28441084075636747, "learning_rate": 2.1384472815103737e-05, "loss": 0.227, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3047950095398952, "learning_rate": 2.1328048696390534e-05, "loss": 0.2439, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.28938567090884426, "learning_rate": 2.1271613958635342e-05, "loss": 0.2319, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.29445939313176306, "learning_rate": 2.1215169053088825e-05, "loss": 0.2321, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.3246039745232674, "learning_rate": 2.1158714431082937e-05, "loss": 0.2393, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.2814016846188971, "learning_rate": 2.110225054402733e-05, "loss": 0.2431, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.3176286218762792, "learning_rate": 2.1045777843405747e-05, "loss": 0.2315, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.3047058646246194, "learning_rate": 2.09892967807724e-05, "loss": 0.231, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.31345499514502756, "learning_rate": 2.093280780774835e-05, "loss": 0.2278, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.29564185376267726, "learning_rate": 2.087631137601793e-05, "loss": 0.2395, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.33373906391542085, "learning_rate": 2.0819807937325104e-05, "loss": 0.2522, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.3274290442431136, "learning_rate": 2.0763297943469847e-05, "loss": 0.2444, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.2862993341429448, "learning_rate": 2.070678184630458e-05, "loss": 0.2465, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.32161120609935445, "learning_rate": 2.06502600977305e-05, "loss": 0.2227, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3138628343032399, "learning_rate": 2.0593733149694008e-05, "loss": 0.2545, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.30720475638445843, "learning_rate": 2.0537201454183074e-05, "loss": 0.2121, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3135984311139862, "learning_rate": 2.0480665463223626e-05, "loss": 0.2314, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.33759546804119184, "learning_rate": 2.042412562887594e-05, "loss": 0.2207, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.2849026701785313, "learning_rate": 2.0367582403231033e-05, "loss": 0.2316, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.35382431985644797, "learning_rate": 2.0311036238407023e-05, "loss": 0.2314, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.33882611489988046, "learning_rate": 2.0254487586545534e-05, "loss": 0.2529, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.2809459915410016, "learning_rate": 2.0197936899808088e-05, "loss": 0.2291, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.34482810282410215, "learning_rate": 2.0141384630372466e-05, "loss": 0.2543, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.32448641092649605, "learning_rate": 2.0084831230429106e-05, "loss": 0.2412, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.28815762512870563, "learning_rate": 2.0028277152177492e-05, "loss": 0.2287, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3302470696450384, "learning_rate": 1.9971722847822518e-05, "loss": 0.2292, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.2866447369588692, "learning_rate": 1.99151687695709e-05, "loss": 0.2517, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2835365880241254, "learning_rate": 1.9858615369627537e-05, "loss": 0.2291, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.2976878124257098, "learning_rate": 1.9802063100191916e-05, "loss": 0.2212, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.3310971408486803, "learning_rate": 1.974551241345447e-05, "loss": 0.2563, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.2818751229817867, "learning_rate": 1.9688963761592984e-05, "loss": 0.2368, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3156826057317011, "learning_rate": 1.963241759676897e-05, "loss": 0.2316, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.3197392358561073, "learning_rate": 1.9575874371124066e-05, "loss": 0.2273, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.2869964173900364, "learning_rate": 1.951933453677638e-05, "loss": 0.2373, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.33706883742514704, "learning_rate": 1.9462798545816932e-05, "loss": 0.2346, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.2993349188253821, "learning_rate": 1.9406266850305996e-05, "loss": 0.2278, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.28505733707457076, "learning_rate": 1.9349739902269503e-05, "loss": 0.2437, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.32860528518060217, "learning_rate": 1.9293218153695425e-05, "loss": 0.2316, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2793067684928013, "learning_rate": 1.9236702056530153e-05, "loss": 0.2445, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.29228722892055115, "learning_rate": 1.9180192062674907e-05, "loss": 0.2173, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.3348466029472901, "learning_rate": 1.9123688623982076e-05, "loss": 0.2474, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.2739497925919673, "learning_rate": 1.906719219225165e-05, "loss": 0.2405, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.33947471129004636, "learning_rate": 1.9010703219227603e-05, "loss": 0.2317, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.31303900399363294, "learning_rate": 1.8954222156594256e-05, "loss": 0.2464, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.2930283678499677, "learning_rate": 1.8897749455972673e-05, "loss": 0.2318, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.32722897400126544, "learning_rate": 1.884128556891707e-05, "loss": 0.2291, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.33025878174172274, "learning_rate": 1.878483094691119e-05, "loss": 0.225, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.2936107505203344, "learning_rate": 1.8728386041364664e-05, "loss": 0.2182, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.30495283742640833, "learning_rate": 1.867195130360947e-05, "loss": 0.2573, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.2872116625171875, "learning_rate": 1.8615527184896263e-05, "loss": 0.2399, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.29245746043164544, "learning_rate": 1.8559114136390795e-05, "loss": 0.2369, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.33160674707649357, "learning_rate": 1.8502712609170298e-05, "loss": 0.2432, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.29865348503496875, "learning_rate": 1.8446323054219876e-05, "loss": 0.2262, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.34891645381064934, "learning_rate": 1.838994592242891e-05, "loss": 0.2211, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.2905969016226092, "learning_rate": 1.8333581664587453e-05, "loss": 0.2537, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.2834249798725762, "learning_rate": 1.8277230731382593e-05, "loss": 0.2313, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.30245759124865257, "learning_rate": 1.82208935733949e-05, "loss": 0.2336, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.3042030742190677, "learning_rate": 1.8164570641094793e-05, "loss": 0.2255, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.2981928043137251, "learning_rate": 1.810826238483892e-05, "loss": 0.2223, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.28939297560587723, "learning_rate": 1.8051969254866608e-05, "loss": 0.2349, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.28543681129720433, "learning_rate": 1.7995691701296226e-05, "loss": 0.2394, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.28145213286284204, "learning_rate": 1.7939430174121593e-05, "loss": 0.242, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.27893571441541326, "learning_rate": 1.788318512320838e-05, "loss": 0.2406, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.2894878295430241, "learning_rate": 1.782695699829051e-05, "loss": 0.2261, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.2862817293604907, "learning_rate": 1.7770746248966587e-05, "loss": 0.2265, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.2889280950397141, "learning_rate": 1.7714553324696243e-05, "loss": 0.2292, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3126972120294891, "learning_rate": 1.7658378674796614e-05, "loss": 0.2344, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3204005827161708, "learning_rate": 1.76022227484387e-05, "loss": 0.2318, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.28505149455217565, "learning_rate": 1.7546085994643807e-05, "loss": 0.2481, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.2892672630481782, "learning_rate": 1.7489968862279902e-05, "loss": 0.2345, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.2759171850450664, "learning_rate": 1.743387180005809e-05, "loss": 0.255, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.2675105245770148, "learning_rate": 1.737779525652899e-05, "loss": 0.25, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2939746556024564, "learning_rate": 1.732173968007914e-05, "loss": 0.237, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2773613619033846, "learning_rate": 1.7265705518927437e-05, "loss": 0.2367, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.30084428659427975, "learning_rate": 1.7209693221121542e-05, "loss": 0.2345, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.2729902803926609, "learning_rate": 1.7153703234534302e-05, "loss": 0.2421, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.2720178815745043, "learning_rate": 1.709773600686015e-05, "loss": 0.2419, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.305840746902569, "learning_rate": 1.7041791985611548e-05, "loss": 0.2132, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.2997669467156857, "learning_rate": 1.69858716181154e-05, "loss": 0.2385, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.2881195339336446, "learning_rate": 1.692997535150948e-05, "loss": 0.2344, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.299831512546405, "learning_rate": 1.687410363273884e-05, "loss": 0.2213, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.2931674036090629, "learning_rate": 1.6818256908552257e-05, "loss": 0.2274, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.2794081531909957, "learning_rate": 1.6762435625498646e-05, "loss": 0.2357, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3084606400901018, "learning_rate": 1.67066402299235e-05, "loss": 0.2375, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.2996203377269903, "learning_rate": 1.6650871167965313e-05, "loss": 0.2275, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.2842698768655462, "learning_rate": 1.6595128885552028e-05, "loss": 0.2299, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.28807443683086154, "learning_rate": 1.653941382839745e-05, "loss": 0.2128, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.40906381343486575, "learning_rate": 1.6483726441997673e-05, "loss": 0.1899, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.2824453121780795, "learning_rate": 1.642806717162757e-05, "loss": 0.1787, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.497611999490887, "learning_rate": 1.637243646233718e-05, "loss": 0.179, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.3746387476332064, "learning_rate": 1.6316834758948174e-05, "loss": 0.167, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.31679594314930803, "learning_rate": 1.6261262506050282e-05, "loss": 0.1732, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4084185453933994, "learning_rate": 1.620572014799777e-05, "loss": 0.1529, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.30909478349339503, "learning_rate": 1.6150208128905857e-05, "loss": 0.1664, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.29632533929217164, "learning_rate": 1.6094726892647147e-05, "loss": 0.1832, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.2998655642318166, "learning_rate": 1.6039276882848135e-05, "loss": 0.1659, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.318892213261456, "learning_rate": 1.5983858542885635e-05, "loss": 0.1893, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.30653487855666733, "learning_rate": 1.5928472315883203e-05, "loss": 0.1612, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.28047096898997903, "learning_rate": 1.5873118644707633e-05, "loss": 0.1769, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.2841468369762907, "learning_rate": 1.5817797971965413e-05, "loss": 0.169, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.3155221298432844, "learning_rate": 1.576251073999917e-05, "loss": 0.1884, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.2905336938377469, "learning_rate": 1.5707257390884126e-05, "loss": 0.1624, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.29815506509479633, "learning_rate": 1.5652038366424595e-05, "loss": 0.1688, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.28031126016768737, "learning_rate": 1.5596854108150424e-05, "loss": 0.1686, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.29389631007577993, "learning_rate": 1.5541705057313476e-05, "loss": 0.1893, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.27450932228395425, "learning_rate": 1.5486591654884086e-05, "loss": 0.1726, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.25965016710238753, "learning_rate": 1.543151434154755e-05, "loss": 0.1835, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.26585568098507556, "learning_rate": 1.5376473557700615e-05, "loss": 0.1577, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.2772062196260817, "learning_rate": 1.5321469743447893e-05, "loss": 0.1676, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.2614416508399522, "learning_rate": 1.5266503338598434e-05, "loss": 0.1683, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.27393592165968067, "learning_rate": 1.5211574782662149e-05, "loss": 0.1688, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.27619431538329836, "learning_rate": 1.5156684514846307e-05, "loss": 0.1607, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2686986308591095, "learning_rate": 1.5101832974052012e-05, "loss": 0.1644, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.2704120793151719, "learning_rate": 1.5047020598870737e-05, "loss": 0.1716, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2691925293807838, "learning_rate": 1.4992247827580778e-05, "loss": 0.151, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.25950125173711364, "learning_rate": 1.493751509814374e-05, "loss": 0.2009, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.2795502498842019, "learning_rate": 1.4882822848201073e-05, "loss": 0.1688, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.2693227737855042, "learning_rate": 1.4828171515070553e-05, "loss": 0.154, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.30214709697861325, "learning_rate": 1.4773561535742793e-05, "loss": 0.1722, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.2883689554912084, "learning_rate": 1.4718993346877715e-05, "loss": 0.1608, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.27629560183019486, "learning_rate": 1.466446738480111e-05, "loss": 0.1651, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.28065379267112056, "learning_rate": 1.460998408550112e-05, "loss": 0.1753, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.2709561150039, "learning_rate": 1.4555543884624751e-05, "loss": 0.166, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.2818034100574091, "learning_rate": 1.4501147217474402e-05, "loss": 0.159, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.2720476884347945, "learning_rate": 1.444679451900437e-05, "loss": 0.1573, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.29685470143305603, "learning_rate": 1.4392486223817397e-05, "loss": 0.1541, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.29255023257505625, "learning_rate": 1.4338222766161143e-05, "loss": 0.1733, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.27726152871178905, "learning_rate": 1.4284004579924777e-05, "loss": 0.1728, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.2811222875725589, "learning_rate": 1.4229832098635479e-05, "loss": 0.1711, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.26897527249585446, "learning_rate": 1.4175705755454963e-05, "loss": 0.1512, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2777903374383638, "learning_rate": 1.412162598317602e-05, "loss": 0.1712, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.26457039331106474, "learning_rate": 1.406759321421907e-05, "loss": 0.1731, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.26019218769843255, "learning_rate": 1.401360788062871e-05, "loss": 0.1665, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.2768074395560011, "learning_rate": 1.3959670414070204e-05, "loss": 0.1704, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.2763538727454471, "learning_rate": 1.3905781245826108e-05, "loss": 0.1741, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.2619000147703128, "learning_rate": 1.3851940806792778e-05, "loss": 0.1705, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.28067256326652024, "learning_rate": 1.379814952747693e-05, "loss": 0.1537, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2735803916208602, "learning_rate": 1.3744407837992193e-05, "loss": 0.1729, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2681789096447215, "learning_rate": 1.3690716168055692e-05, "loss": 0.1746, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.271621383293506, "learning_rate": 1.363707494698459e-05, "loss": 0.1695, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.27919851500830406, "learning_rate": 1.358348460369265e-05, "loss": 0.1783, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2711841464673936, "learning_rate": 1.352994556668684e-05, "loss": 0.1754, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.2596550150261182, "learning_rate": 1.3476458264063865e-05, "loss": 0.176, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.27720372921084024, "learning_rate": 1.342302312350678e-05, "loss": 0.1605, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.27043328135791794, "learning_rate": 1.3369640572281537e-05, "loss": 0.1647, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.2662920853526842, "learning_rate": 1.3316311037233596e-05, "loss": 0.1777, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.27438138098675535, "learning_rate": 1.326303494478451e-05, "loss": 0.1597, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.2870275881893215, "learning_rate": 1.3209812720928472e-05, "loss": 0.1696, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2733818755107387, "learning_rate": 1.315664479122898e-05, "loss": 0.1663, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.2743565603576047, "learning_rate": 1.3103531580815378e-05, "loss": 0.1725, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.26792835127218717, "learning_rate": 1.3050473514379488e-05, "loss": 0.1667, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2821506013858874, "learning_rate": 1.2997471016172188e-05, "loss": 0.1697, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.27857659063930607, "learning_rate": 1.2944524510000042e-05, "loss": 0.175, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.272759708978221, "learning_rate": 1.2891634419221908e-05, "loss": 0.1808, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.26743335544320207, "learning_rate": 1.2838801166745545e-05, "loss": 0.1485, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.27782992719181043, "learning_rate": 1.2786025175024216e-05, "loss": 0.1648, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.2987532137451538, "learning_rate": 1.2733306866053357e-05, "loss": 0.1596, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2702142307583867, "learning_rate": 1.2680646661367163e-05, "loss": 0.1737, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.2733458439667509, "learning_rate": 1.2628044982035219e-05, "loss": 0.1616, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.2963618713500968, "learning_rate": 1.2575502248659155e-05, "loss": 0.1826, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.27059709027076373, "learning_rate": 1.2523018881369269e-05, "loss": 0.1643, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2531605734279313, "learning_rate": 1.2470595299821176e-05, "loss": 0.1684, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.25689446641132185, "learning_rate": 1.2418231923192416e-05, "loss": 0.1598, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.2656584718626031, "learning_rate": 1.2365929170179165e-05, "loss": 0.1719, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.2545477224788141, "learning_rate": 1.2313687458992848e-05, "loss": 0.1846, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.2890545080363901, "learning_rate": 1.2261507207356785e-05, "loss": 0.1682, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.27112563480743246, "learning_rate": 1.220938883250288e-05, "loss": 0.1699, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2726691871223523, "learning_rate": 1.215733275116827e-05, "loss": 0.1645, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.27098955381215173, "learning_rate": 1.2105339379592005e-05, "loss": 0.1582, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.2555760897240028, "learning_rate": 1.2053409133511681e-05, "loss": 0.1623, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.27653842877973983, "learning_rate": 1.2001542428160173e-05, "loss": 0.168, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2809840121159054, "learning_rate": 1.1949739678262278e-05, "loss": 0.1974, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.2550007867282225, "learning_rate": 1.189800129803139e-05, "loss": 0.1861, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.2635724890657941, "learning_rate": 1.1846327701166228e-05, "loss": 0.1707, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.26246140050620287, "learning_rate": 1.1794719300847493e-05, "loss": 0.1723, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2624293915902128, "learning_rate": 1.1743176509734582e-05, "loss": 0.1762, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2571984864868593, "learning_rate": 1.1691699739962275e-05, "loss": 0.1931, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.26386481250954896, "learning_rate": 1.1640289403137456e-05, "loss": 0.1507, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.28287557348260234, "learning_rate": 1.1588945910335802e-05, "loss": 0.175, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.26534696167113003, "learning_rate": 1.1537669672098517e-05, "loss": 0.1768, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.2759840047996793, "learning_rate": 1.1486461098429036e-05, "loss": 0.1632, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.26869099285738013, "learning_rate": 1.1435320598789747e-05, "loss": 0.1471, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.26639800355955, "learning_rate": 1.1384248582098736e-05, "loss": 0.1673, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.29081534289511374, "learning_rate": 1.1333245456726467e-05, "loss": 0.1764, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.267996292175234, "learning_rate": 1.128231163049258e-05, "loss": 0.1892, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2615791457243424, "learning_rate": 1.123144751066259e-05, "loss": 0.1534, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.27616525655996843, "learning_rate": 1.1180653503944657e-05, "loss": 0.1499, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.28060320288218993, "learning_rate": 1.1129930016486287e-05, "loss": 0.1612, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.26491161750656, "learning_rate": 1.107927745387114e-05, "loss": 0.17, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.26432407676109676, "learning_rate": 1.1028696221115766e-05, "loss": 0.1697, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.28783755099040276, "learning_rate": 1.0978186722666341e-05, "loss": 0.1753, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.27130655451665225, "learning_rate": 1.0927749362395475e-05, "loss": 0.1778, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.26283080654914537, "learning_rate": 1.0877384543598954e-05, "loss": 0.1732, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2609378477723971, "learning_rate": 1.0827092668992529e-05, "loss": 0.1742, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.27057560570509226, "learning_rate": 1.077687414070869e-05, "loss": 0.1517, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.2658204482989287, "learning_rate": 1.0726729360293451e-05, "loss": 0.1641, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.26446979693692685, "learning_rate": 1.0676658728703147e-05, "loss": 0.1674, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.2742832793668281, "learning_rate": 1.0626662646301198e-05, "loss": 0.1652, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2563013643883041, "learning_rate": 1.0576741512854958e-05, "loss": 0.1661, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2753991540716498, "learning_rate": 1.052689572753247e-05, "loss": 0.1628, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.27365721025233364, "learning_rate": 1.0477125688899328e-05, "loss": 0.1656, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.257530750935716, "learning_rate": 1.0427431794915406e-05, "loss": 0.1737, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.27873837122967354, "learning_rate": 1.0377814442931769e-05, "loss": 0.1494, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2662670342792835, "learning_rate": 1.0328274029687439e-05, "loss": 0.162, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.26342562495214916, "learning_rate": 1.0278810951306253e-05, "loss": 0.1609, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.2611159079851167, "learning_rate": 1.0229425603293647e-05, "loss": 0.1743, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.26813352893861997, "learning_rate": 1.0180118380533558e-05, "loss": 0.1651, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2696648054530292, "learning_rate": 1.0130889677285225e-05, "loss": 0.1638, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.27209735531721274, "learning_rate": 1.008173988718005e-05, "loss": 0.1586, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.25706437322368164, "learning_rate": 1.0032669403218439e-05, "loss": 0.1502, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.25542238419195396, "learning_rate": 9.983678617766677e-06, "loss": 0.1768, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2744447725596377, "learning_rate": 9.934767922553788e-06, "loss": 0.1595, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.271655209852879, "learning_rate": 9.885937708668371e-06, "loss": 0.172, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.2697302159500377, "learning_rate": 9.837188366555524e-06, "loss": 0.1527, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.268712141510508, "learning_rate": 9.788520286013691e-06, "loss": 0.1528, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2567596414547175, "learning_rate": 9.739933856191537e-06, "loss": 0.1695, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.28691548987273247, "learning_rate": 9.691429465584866e-06, "loss": 0.1636, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.2726358857115839, "learning_rate": 9.643007502033492e-06, "loss": 0.167, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.2566798829508941, "learning_rate": 9.594668352718152e-06, "loss": 0.1793, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.2687957954119701, "learning_rate": 9.546412404157383e-06, "loss": 0.1566, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.26480495511706, "learning_rate": 9.498240042204471e-06, "loss": 0.1595, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.26509476974645996, "learning_rate": 9.450151652044339e-06, "loss": 0.1645, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2557499969006691, "learning_rate": 9.402147618190472e-06, "loss": 0.1528, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.27018429777869746, "learning_rate": 9.354228324481841e-06, "loss": 0.1516, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.26451600176685436, "learning_rate": 9.306394154079852e-06, "loss": 0.1792, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.2593889531622899, "learning_rate": 9.258645489465254e-06, "loss": 0.1808, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.26417236309355624, "learning_rate": 9.21098271243509e-06, "loss": 0.1853, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.2584239472139293, "learning_rate": 9.163406204099659e-06, "loss": 0.1639, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.25018157371853306, "learning_rate": 9.115916344879452e-06, "loss": 0.1837, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2717579343318098, "learning_rate": 9.068513514502126e-06, "loss": 0.1797, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.26372673574411304, "learning_rate": 9.021198091999439e-06, "loss": 0.1661, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.24885771547926577, "learning_rate": 8.973970455704251e-06, "loss": 0.1745, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.25668833928279494, "learning_rate": 8.926830983247495e-06, "loss": 0.162, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.260494828027864, "learning_rate": 8.879780051555116e-06, "loss": 0.1702, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.25878556510050166, "learning_rate": 8.83281803684512e-06, "loss": 0.17, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.23947609197270636, "learning_rate": 8.785945314624532e-06, "loss": 0.1722, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.2606565165486, "learning_rate": 8.739162259686385e-06, "loss": 0.1735, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2644150525885513, "learning_rate": 8.692469246106734e-06, "loss": 0.1741, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.2678648300271928, "learning_rate": 8.645866647241677e-06, "loss": 0.163, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2554596734114639, "learning_rate": 8.599354835724348e-06, "loss": 0.1754, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.2626070521366938, "learning_rate": 8.552934183461958e-06, "loss": 0.1562, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2623743479852856, "learning_rate": 8.506605061632805e-06, "loss": 0.1726, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.28426711205792504, "learning_rate": 8.460367840683308e-06, "loss": 0.1716, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.25201517520450845, "learning_rate": 8.414222890325065e-06, "loss": 0.1749, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2543180842571872, "learning_rate": 8.368170579531855e-06, "loss": 0.1611, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.26651590321803387, "learning_rate": 8.322211276536733e-06, "loss": 0.1729, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.27068809017055173, "learning_rate": 8.27634534882907e-06, "loss": 0.1615, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.25455210697077213, "learning_rate": 8.230573163151585e-06, "loss": 0.1766, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.25433005581273865, "learning_rate": 8.184895085497466e-06, "loss": 0.171, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.27482400127862666, "learning_rate": 8.139311481107401e-06, "loss": 0.1673, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.2596278679716073, "learning_rate": 8.093822714466686e-06, "loss": 0.1808, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2558874093331776, "learning_rate": 8.048429149302271e-06, "loss": 0.1591, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.24586463249242835, "learning_rate": 8.003131148579902e-06, "loss": 0.1619, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2527269158941475, "learning_rate": 7.957929074501182e-06, "loss": 0.1702, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.2520024452115848, "learning_rate": 7.912823288500695e-06, "loss": 0.1619, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.25475081352338225, "learning_rate": 7.867814151243102e-06, "loss": 0.1673, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2566718193069829, "learning_rate": 7.822902022620267e-06, "loss": 0.1628, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.2496135923974516, "learning_rate": 7.778087261748377e-06, "loss": 0.1596, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.25512070114740737, "learning_rate": 7.733370226965056e-06, "loss": 0.1476, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2541159782263659, "learning_rate": 7.688751275826527e-06, "loss": 0.1544, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2485350780184823, "learning_rate": 7.644230765104735e-06, "loss": 0.1704, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.2573872762020573, "learning_rate": 7.599809050784502e-06, "loss": 0.1777, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2516924465353467, "learning_rate": 7.555486488060661e-06, "loss": 0.1827, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.26237345193920986, "learning_rate": 7.511263431335249e-06, "loss": 0.1457, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.2645447808596802, "learning_rate": 7.467140234214656e-06, "loss": 0.1525, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.2576721997658637, "learning_rate": 7.423117249506777e-06, "loss": 0.1623, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.26669470207843493, "learning_rate": 7.379194829218231e-06, "loss": 0.1587, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.26993041748757474, "learning_rate": 7.335373324551518e-06, "loss": 0.1684, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.2619466180518437, "learning_rate": 7.291653085902224e-06, "loss": 0.1681, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2486245136822617, "learning_rate": 7.248034462856213e-06, "loss": 0.1562, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.2626938757090845, "learning_rate": 7.20451780418683e-06, "loss": 0.1563, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2788057605627071, "learning_rate": 7.161103457852128e-06, "loss": 0.1688, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.26161622450316613, "learning_rate": 7.117791770992046e-06, "loss": 0.1535, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.24879602373820148, "learning_rate": 7.074583089925688e-06, "loss": 0.1513, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.25777642397403505, "learning_rate": 7.0314777601485155e-06, "loss": 0.1666, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.260116975150845, "learning_rate": 6.988476126329604e-06, "loss": 0.1637, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.2596722061774956, "learning_rate": 6.945578532308857e-06, "loss": 0.1629, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.2625897813012122, "learning_rate": 6.902785321094301e-06, "loss": 0.1692, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.2606341383074568, "learning_rate": 6.8600968348593115e-06, "loss": 0.1672, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2544869826953956, "learning_rate": 6.817513414939892e-06, "loss": 0.1658, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.26018696894908006, "learning_rate": 6.775035401831924e-06, "loss": 0.1547, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.25860375023702065, "learning_rate": 6.732663135188473e-06, "loss": 0.156, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.26361794521247356, "learning_rate": 6.690396953817055e-06, "loss": 0.1562, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.26378021114974387, "learning_rate": 6.648237195676927e-06, "loss": 0.1762, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.27491047618506176, "learning_rate": 6.606184197876395e-06, "loss": 0.1859, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.2536304004812812, "learning_rate": 6.564238296670109e-06, "loss": 0.1621, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2646799548449149, "learning_rate": 6.52239982745638e-06, "loss": 0.1546, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.257354407540962, "learning_rate": 6.480669124774484e-06, "loss": 0.1714, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.25764829353992724, "learning_rate": 6.439046522302013e-06, "loss": 0.1737, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.2474576987352541, "learning_rate": 6.397532352852191e-06, "loss": 0.1627, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.24798960505649542, "learning_rate": 6.356126948371202e-06, "loss": 0.1803, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.2497500228369188, "learning_rate": 6.314830639935559e-06, "loss": 0.1628, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2573301445407768, "learning_rate": 6.273643757749448e-06, "loss": 0.1543, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.25394444943719724, "learning_rate": 6.2325666311420856e-06, "loss": 0.1649, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.26902969486038825, "learning_rate": 6.1915995885650675e-06, "loss": 0.1714, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.26278579857984435, "learning_rate": 6.150742957589784e-06, "loss": 0.1617, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.24547980168302802, "learning_rate": 6.109997064904774e-06, "loss": 0.16, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2504133176340798, "learning_rate": 6.069362236313092e-06, "loss": 0.1592, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2483606083210631, "learning_rate": 6.0288387967297565e-06, "loss": 0.1755, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.252813044810782, "learning_rate": 5.988427070179108e-06, "loss": 0.1504, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.24446284504140078, "learning_rate": 5.948127379792234e-06, "loss": 0.1521, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.2607951408962352, "learning_rate": 5.90794004780439e-06, "loss": 0.1505, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.24902878029543318, "learning_rate": 5.867865395552405e-06, "loss": 0.1649, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.25577762140967164, "learning_rate": 5.8279037434721364e-06, "loss": 0.1619, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.25514908830352057, "learning_rate": 5.788055411095892e-06, "loss": 0.1606, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2613708949211013, "learning_rate": 5.7483207170498625e-06, "loss": 0.1577, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.25646573526041205, "learning_rate": 5.708699979051613e-06, "loss": 0.1853, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.25036314295460904, "learning_rate": 5.66919351390751e-06, "loss": 0.1634, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.25420636418754766, "learning_rate": 5.629801637510188e-06, "loss": 0.1698, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.24925956905387875, "learning_rate": 5.590524664836043e-06, "loss": 0.1703, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.25111752483680455, "learning_rate": 5.551362909942708e-06, "loss": 0.1742, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.25961978126194435, "learning_rate": 5.51231668596653e-06, "loss": 0.1514, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.24530453906677524, "learning_rate": 5.47338630512007e-06, "loss": 0.1617, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.23613533536689982, "learning_rate": 5.434572078689617e-06, "loss": 0.1648, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.24832430370292236, "learning_rate": 5.395874317032694e-06, "loss": 0.1553, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.24652367849209886, "learning_rate": 5.357293329575573e-06, "loss": 0.1752, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.25556135573813493, "learning_rate": 5.318829424810797e-06, "loss": 0.1582, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.2370366490276146, "learning_rate": 5.280482910294728e-06, "loss": 0.177, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.2502085554445127, "learning_rate": 5.242254092645078e-06, "loss": 0.1425, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.25553644465623987, "learning_rate": 5.2041432775384445e-06, "loss": 0.1734, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.24742294125933267, "learning_rate": 5.166150769707892e-06, "loss": 0.1522, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.24312123055074003, "learning_rate": 5.128276872940503e-06, "loss": 0.1682, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.25458238498624086, "learning_rate": 5.090521890074953e-06, "loss": 0.1636, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.25407420280764254, "learning_rate": 5.0528861229990675e-06, "loss": 0.1524, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.24804146125818594, "learning_rate": 5.015369872647442e-06, "loss": 0.1453, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2512250570873918, "learning_rate": 4.9779734389990195e-06, "loss": 0.1662, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.29421564563448505, "learning_rate": 4.940697121074675e-06, "loss": 0.1705, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.2523326556856082, "learning_rate": 4.903541216934864e-06, "loss": 0.1699, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.25927181233365076, "learning_rate": 4.8665060236772e-06, "loss": 0.1658, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2486682807446523, "learning_rate": 4.829591837434102e-06, "loss": 0.1515, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.2487538077857195, "learning_rate": 4.792798953370424e-06, "loss": 0.1669, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.24564489889556462, "learning_rate": 4.756127665681083e-06, "loss": 0.1695, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.24738255387441052, "learning_rate": 4.719578267588725e-06, "loss": 0.1784, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.24892530459420842, "learning_rate": 4.6831510513413525e-06, "loss": 0.1628, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.31942349364205885, "learning_rate": 4.6468463082100176e-06, "loss": 0.1502, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.26777156483928366, "learning_rate": 4.610664328486485e-06, "loss": 0.1229, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.23591517150838334, "learning_rate": 4.5746054014809e-06, "loss": 0.1213, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.23894935093444875, "learning_rate": 4.5386698155194766e-06, "loss": 0.1226, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.30030639642070633, "learning_rate": 4.502857857942204e-06, "loss": 0.1138, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3557454838338256, "learning_rate": 4.467169815100549e-06, "loss": 0.1316, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.2972640694167174, "learning_rate": 4.431605972355137e-06, "loss": 0.1119, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.2556721797100097, "learning_rate": 4.396166614073516e-06, "loss": 0.1333, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.24891043159581755, "learning_rate": 4.360852023627846e-06, "loss": 0.1217, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.2743102133141931, "learning_rate": 4.325662483392656e-06, "loss": 0.1143, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2605357160569034, "learning_rate": 4.29059827474257e-06, "loss": 0.128, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.246693225672493, "learning_rate": 4.255659678050063e-06, "loss": 0.112, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.2478827414793634, "learning_rate": 4.22084697268323e-06, "loss": 0.1164, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.22094925470689794, "learning_rate": 4.186160437003535e-06, "loss": 0.1081, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.21443173838041574, "learning_rate": 4.151600348363582e-06, "loss": 0.1187, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.26014205522907186, "learning_rate": 4.11716698310493e-06, "loss": 0.1333, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.26402857446967914, "learning_rate": 4.082860616555848e-06, "loss": 0.1275, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.22454221695628304, "learning_rate": 4.048681523029125e-06, "loss": 0.1234, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.22687327354727352, "learning_rate": 4.014629975819882e-06, "loss": 0.1024, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.20737848036071888, "learning_rate": 3.9807062472033855e-06, "loss": 0.1251, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.21712510213750869, "learning_rate": 3.94691060843287e-06, "loss": 0.1176, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.2218862851040934, "learning_rate": 3.913243329737353e-06, "loss": 0.1161, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.22761165093011132, "learning_rate": 3.879704680319503e-06, "loss": 0.1372, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.23015285349401976, "learning_rate": 3.846294928353471e-06, "loss": 0.1359, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.22856446231181635, "learning_rate": 3.8130143409827345e-06, "loss": 0.1235, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2139366293613454, "learning_rate": 3.7798631843179887e-06, "loss": 0.1133, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.22952799609932906, "learning_rate": 3.7468417234349973e-06, "loss": 0.1129, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.21391178825308244, "learning_rate": 3.7139502223724823e-06, "loss": 0.1253, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2254605462128369, "learning_rate": 3.6811889441300095e-06, "loss": 0.1289, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.21063858168132013, "learning_rate": 3.648558150665886e-06, "loss": 0.1205, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.21785551219952895, "learning_rate": 3.616058102895075e-06, "loss": 0.1112, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.20930148346229874, "learning_rate": 3.583689060687079e-06, "loss": 0.1238, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.20915228634086205, "learning_rate": 3.5514512828639023e-06, "loss": 0.1222, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.21181908899863647, "learning_rate": 3.51934502719796e-06, "loss": 0.1207, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.20930992482063523, "learning_rate": 3.4873705504100185e-06, "loss": 0.1381, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.21305111184501022, "learning_rate": 3.4555281081671345e-06, "loss": 0.1171, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.21352291903054899, "learning_rate": 3.4238179550806326e-06, "loss": 0.12, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.2147981562779905, "learning_rate": 3.3922403447040497e-06, "loss": 0.1141, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.22442681082056268, "learning_rate": 3.3607955295311247e-06, "loss": 0.1351, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2152419451451552, "learning_rate": 3.32948376099375e-06, "loss": 0.1335, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.21895206464139624, "learning_rate": 3.2983052894599976e-06, "loss": 0.1084, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2151988190654966, "learning_rate": 3.2672603642320945e-06, "loss": 0.1065, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.22802856496159205, "learning_rate": 3.236349233544438e-06, "loss": 0.1295, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2112868336561774, "learning_rate": 3.205572144561604e-06, "loss": 0.1237, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2224644379384643, "learning_rate": 3.174929343376374e-06, "loss": 0.1152, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2267766591472218, "learning_rate": 3.1444210750077777e-06, "loss": 0.1258, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.218717141552164, "learning_rate": 3.1140475833991046e-06, "loss": 0.1268, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.21104505759045034, "learning_rate": 3.0838091114159895e-06, "loss": 0.1399, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.21991713933946339, "learning_rate": 3.0537059008444524e-06, "loss": 0.1275, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.20666472757237114, "learning_rate": 3.0237381923889563e-06, "loss": 0.128, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.22148172494687574, "learning_rate": 2.9939062256704997e-06, "loss": 0.1396, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.20974192160638067, "learning_rate": 2.964210239224696e-06, "loss": 0.1033, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.21679185011396385, "learning_rate": 2.934650470499869e-06, "loss": 0.1151, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2155603808280965, "learning_rate": 2.905227155855128e-06, "loss": 0.1286, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.22445191207757859, "learning_rate": 2.875940530558519e-06, "loss": 0.134, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2137506879684848, "learning_rate": 2.8467908287851154e-06, "loss": 0.1295, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.23468670949581413, "learning_rate": 2.8177782836151603e-06, "loss": 0.1317, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.21372123955335506, "learning_rate": 2.7889031270321874e-06, "loss": 0.1316, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.21618368892756754, "learning_rate": 2.760165589921184e-06, "loss": 0.1231, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.21364995525221495, "learning_rate": 2.7315659020667305e-06, "loss": 0.129, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21596365057918546, "learning_rate": 2.703104292151164e-06, "loss": 0.1281, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.21996272049468957, "learning_rate": 2.6747809877527607e-06, "loss": 0.1394, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.20384150347731297, "learning_rate": 2.6465962153439082e-06, "loss": 0.126, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.21163643439151636, "learning_rate": 2.618550200289303e-06, "loss": 0.1279, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.21180676304800938, "learning_rate": 2.59064316684412e-06, "loss": 0.1199, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20616928448772917, "learning_rate": 2.562875338152264e-06, "loss": 0.129, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.21081498390501674, "learning_rate": 2.5352469362445552e-06, "loss": 0.1279, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.21956449143283505, "learning_rate": 2.5077581820369523e-06, "loss": 0.1175, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.22064290650021712, "learning_rate": 2.480409295328803e-06, "loss": 0.1195, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.22861936747292155, "learning_rate": 2.45320049480108e-06, "loss": 0.1014, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.21428350812596936, "learning_rate": 2.4261319980146293e-06, "loss": 0.1405, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.22089585033151277, "learning_rate": 2.399204021408421e-06, "loss": 0.1231, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.21095546167319348, "learning_rate": 2.3724167802978395e-06, "loss": 0.1392, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.21143142677638188, "learning_rate": 2.3457704888729625e-06, "loss": 0.1281, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.21268149663594052, "learning_rate": 2.3192653601968162e-06, "loss": 0.1335, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.21445722698069772, "learning_rate": 2.2929016062037057e-06, "loss": 0.1278, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.21642763972301443, "learning_rate": 2.2666794376975055e-06, "loss": 0.1359, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2141800486567437, "learning_rate": 2.24059906434998e-06, "loss": 0.1158, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.21203090176842976, "learning_rate": 2.214660694699091e-06, "loss": 0.116, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.20385825582687697, "learning_rate": 2.188864536147355e-06, "loss": 0.1336, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.20997599410886966, "learning_rate": 2.1632107949601757e-06, "loss": 0.1016, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2147942542872831, "learning_rate": 2.137699676264171e-06, "loss": 0.1094, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.2093341664768131, "learning_rate": 2.1123313840455738e-06, "loss": 0.1325, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.21968856874343337, "learning_rate": 2.08710612114857e-06, "loss": 0.1285, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2112401839716934, "learning_rate": 2.0620240892736953e-06, "loss": 0.1248, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.20788404664499507, "learning_rate": 2.0370854889762e-06, "loss": 0.1195, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.21084170362196833, "learning_rate": 2.0122905196644726e-06, "loss": 0.1457, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21100849246948736, "learning_rate": 1.987639379598427e-06, "loss": 0.1204, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21071121540702759, "learning_rate": 1.963132265887919e-06, "loss": 0.1311, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20738133653369817, "learning_rate": 1.9387693744911784e-06, "loss": 0.1226, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.20488560970810948, "learning_rate": 1.9145509002132368e-06, "loss": 0.1229, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.21609755411472256, "learning_rate": 1.8904770367043723e-06, "loss": 0.1303, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.2193488642884422, "learning_rate": 1.8665479764585504e-06, "loss": 0.1122, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.21251177731719156, "learning_rate": 1.8427639108118977e-06, "loss": 0.1169, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2166469997262382, "learning_rate": 1.8191250299411755e-06, "loss": 0.129, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.21899962488883384, "learning_rate": 1.7956315228622446e-06, "loss": 0.129, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.21238925379684245, "learning_rate": 1.7722835774285553e-06, "loss": 0.11, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2147978637318225, "learning_rate": 1.7490813803296624e-06, "loss": 0.1169, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.22110009523630453, "learning_rate": 1.726025117089718e-06, "loss": 0.122, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2163187982799811, "learning_rate": 1.70311497206598e-06, "loss": 0.1281, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.21568703813901566, "learning_rate": 1.6803511284473638e-06, "loss": 0.12, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.21096062982242092, "learning_rate": 1.6577337682529538e-06, "loss": 0.1124, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.20515038519691475, "learning_rate": 1.6352630723305617e-06, "loss": 0.1075, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.20984093292154496, "learning_rate": 1.612939220355272e-06, "loss": 0.1495, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.20956464812020328, "learning_rate": 1.5907623908280112e-06, "loss": 0.1223, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.20472691017789235, "learning_rate": 1.568732761074121e-06, "loss": 0.1379, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.21971778506810752, "learning_rate": 1.5468505072419237e-06, "loss": 0.1318, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.21798191778313478, "learning_rate": 1.5251158043013448e-06, "loss": 0.1205, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.209915691341249, "learning_rate": 1.5035288260424885e-06, "loss": 0.1352, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.21786504053239977, "learning_rate": 1.4820897450742623e-06, "loss": 0.1152, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.21106072697176653, "learning_rate": 1.4607987328229767e-06, "loss": 0.144, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.2073022389866306, "learning_rate": 1.4396559595310056e-06, "loss": 0.1015, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.21728314444874455, "learning_rate": 1.4186615942553973e-06, "loss": 0.1199, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.20957919966733776, "learning_rate": 1.3978158048665424e-06, "loss": 0.13, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.20751295478910425, "learning_rate": 1.3771187580468115e-06, "loss": 0.1292, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.22330201196299737, "learning_rate": 1.3565706192892392e-06, "loss": 0.1333, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.20848093280421567, "learning_rate": 1.3361715528961993e-06, "loss": 0.1555, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.21145932198127332, "learning_rate": 1.3159217219780817e-06, "loss": 0.1184, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.20896251232305257, "learning_rate": 1.2958212884519949e-06, "loss": 0.1145, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.21381126114477858, "learning_rate": 1.2758704130404675e-06, "loss": 0.1351, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.21918795226522203, "learning_rate": 1.2560692552701738e-06, "loss": 0.1281, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2173651283777034, "learning_rate": 1.2364179734706382e-06, "loss": 0.1346, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.20978583049043933, "learning_rate": 1.2169167247729852e-06, "loss": 0.1213, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.20235649192441343, "learning_rate": 1.1975656651086864e-06, "loss": 0.118, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.2123171536229055, "learning_rate": 1.1783649492082926e-06, "loss": 0.12, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.220829291466672, "learning_rate": 1.1593147306002183e-06, "loss": 0.1171, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2083320089970205, "learning_rate": 1.140415161609505e-06, "loss": 0.1188, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.20825244488477257, "learning_rate": 1.121666393356604e-06, "loss": 0.1137, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2137204116823938, "learning_rate": 1.1030685757561632e-06, "loss": 0.1254, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.22954659415965253, "learning_rate": 1.0846218575158373e-06, "loss": 0.1057, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.2210302055191104, "learning_rate": 1.066326386135097e-06, "loss": 0.1198, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.20692667033229573, "learning_rate": 1.0481823079040398e-06, "loss": 0.1167, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.2106022276336113, "learning_rate": 1.0301897679022344e-06, "loss": 0.1253, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.22027222481284497, "learning_rate": 1.0123489099975491e-06, "loss": 0.1238, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2078117159265004, "learning_rate": 9.9465987684501e-07, "loss": 0.1312, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.20823417406257916, "learning_rate": 9.771228098856534e-07, "loss": 0.1182, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.20864916685503143, "learning_rate": 9.597378493454013e-07, "loss": 0.1347, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.21464703897172666, "learning_rate": 9.425051342339353e-07, "loss": 0.1199, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.20453995974537767, "learning_rate": 9.254248023435864e-07, "loss": 0.1345, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.20252355494009303, "learning_rate": 9.084969902482288e-07, "loss": 0.1258, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.20871388313753875, "learning_rate": 8.917218333021993e-07, "loss": 0.131, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.20937956764383317, "learning_rate": 8.750994656392109e-07, "loss": 0.1195, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.20853329905146623, "learning_rate": 8.58630020171265e-07, "loss": 0.1112, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.20893383510016408, "learning_rate": 8.423136285876099e-07, "loss": 0.1306, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.19739450196287664, "learning_rate": 8.26150421353682e-07, "loss": 0.1173, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.20958759613279745, "learning_rate": 8.101405277100549e-07, "loss": 0.121, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2147522569221904, "learning_rate": 7.942840756714077e-07, "loss": 0.1108, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.2126815343885609, "learning_rate": 7.785811920255093e-07, "loss": 0.1215, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.21079675345442556, "learning_rate": 7.630320023322024e-07, "loss": 0.1195, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.20871990849830874, "learning_rate": 7.476366309223903e-07, "loss": 0.1196, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.207315501308871, "learning_rate": 7.323952008970537e-07, "loss": 0.1283, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.20877214780717365, "learning_rate": 7.173078341262618e-07, "loss": 0.1243, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.20526040943617874, "learning_rate": 7.023746512481989e-07, "loss": 0.1232, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.20681610992046895, "learning_rate": 6.875957716681902e-07, "loss": 0.1305, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.22347026998427783, "learning_rate": 6.729713135577687e-07, "loss": 0.1229, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2042370951712124, "learning_rate": 6.585013938537143e-07, "loss": 0.1349, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.20567184925209234, "learning_rate": 6.441861282571115e-07, "loss": 0.1339, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.21443496806057918, "learning_rate": 6.300256312324471e-07, "loss": 0.1079, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.20941661461765465, "learning_rate": 6.160200160066776e-07, "loss": 0.1055, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.2240962336388919, "learning_rate": 6.021693945683327e-07, "loss": 0.11, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.21684598420675613, "learning_rate": 5.884738776666044e-07, "loss": 0.1047, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.20573294639901, "learning_rate": 5.749335748104878e-07, "loss": 0.1261, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.21222358173533767, "learning_rate": 5.615485942678778e-07, "loss": 0.1257, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.21372304613909068, "learning_rate": 5.483190430647289e-07, "loss": 0.128, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.2059382495471441, "learning_rate": 5.352450269841747e-07, "loss": 0.1326, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.2131367970615392, "learning_rate": 5.22326650565701e-07, "loss": 0.1289, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.21781326181671448, "learning_rate": 5.095640171043048e-07, "loss": 0.1148, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.20811541774269696, "learning_rate": 4.969572286496594e-07, "loss": 0.117, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.19750440542809294, "learning_rate": 4.845063860053079e-07, "loss": 0.1387, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2112055064291213, "learning_rate": 4.7221158872785997e-07, "loss": 0.1257, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.21343626694886328, "learning_rate": 4.600729351261857e-07, "loss": 0.1255, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.20650982259882325, "learning_rate": 4.4809052226063355e-07, "loss": 0.1206, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.2002389709498157, "learning_rate": 4.3626444594226046e-07, "loss": 0.1256, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.21580514700608824, "learning_rate": 4.245948007320588e-07, "loss": 0.1261, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.21779632779426686, "learning_rate": 4.130816799401971e-07, "loss": 0.12, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.21352405771792288, "learning_rate": 4.017251756252827e-07, "loss": 0.1124, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.21807214106996617, "learning_rate": 3.9052537859362473e-07, "loss": 0.1287, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2037828328303551, "learning_rate": 3.7948237839849687e-07, "loss": 0.1161, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.20478180590786857, "learning_rate": 3.6859626333943797e-07, "loss": 0.1096, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.20885647305782098, "learning_rate": 3.578671204615347e-07, "loss": 0.1185, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.21345496257224314, "learning_rate": 3.472950355547267e-07, "loss": 0.1145, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.21177812834032064, "learning_rate": 3.3688009315312244e-07, "loss": 0.1264, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.20030175481470158, "learning_rate": 3.266223765343224e-07, "loss": 0.1395, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.20640321888150792, "learning_rate": 3.16521967718757e-07, "loss": 0.1151, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.20658838331856244, "learning_rate": 3.0657894746902726e-07, "loss": 0.1295, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.21721916440422429, "learning_rate": 2.9679339528925654e-07, "loss": 0.1132, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.21141084456284923, "learning_rate": 2.871653894244597e-07, "loss": 0.0949, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2124773255059769, "learning_rate": 2.7769500685991266e-07, "loss": 0.1292, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.21578639331787564, "learning_rate": 2.683823233205485e-07, "loss": 0.1262, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.20997885757952264, "learning_rate": 2.592274132703287e-07, "loss": 0.1025, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.21060176523320812, "learning_rate": 2.502303499116754e-07, "loss": 0.1211, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.2109775884525756, "learning_rate": 2.413912051848666e-07, "loss": 0.1234, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.21040620985357372, "learning_rate": 2.3271004976746613e-07, "loss": 0.1197, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.20379471254497133, "learning_rate": 2.2418695307376393e-07, "loss": 0.1248, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2170037656531913, "learning_rate": 2.1582198325420968e-07, "loss": 0.1007, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.21433400132875877, "learning_rate": 2.0761520719488447e-07, "loss": 0.1039, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.21449798090755115, "learning_rate": 1.9956669051694798e-07, "loss": 0.1317, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.21530362572038825, "learning_rate": 1.916764975761254e-07, "loss": 0.1091, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.20295938988179296, "learning_rate": 1.839446914621923e-07, "loss": 0.1198, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.19588262268987433, "learning_rate": 1.7637133399845962e-07, "loss": 0.131, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.2019968865854273, "learning_rate": 1.6895648574129397e-07, "loss": 0.1274, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.2148791820673642, "learning_rate": 1.6170020597962465e-07, "loss": 0.1313, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.2097794374775826, "learning_rate": 1.5460255273447078e-07, "loss": 0.119, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.20014671865215578, "learning_rate": 1.4766358275847715e-07, "loss": 0.1266, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.20992567293785655, "learning_rate": 1.4088335153546573e-07, "loss": 0.1301, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.21954728930095768, "learning_rate": 1.3426191327998496e-07, "loss": 0.1173, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.20813165048570514, "learning_rate": 1.277993209368744e-07, "loss": 0.1036, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.20454581574877218, "learning_rate": 1.214956261808542e-07, "loss": 0.1325, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.21061963983891674, "learning_rate": 1.1535087941609846e-07, "loss": 0.1223, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.21824701581257025, "learning_rate": 1.0936512977583802e-07, "loss": 0.1107, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.20999277704750635, "learning_rate": 1.0353842512196732e-07, "loss": 0.1148, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.19728945289328964, "learning_rate": 9.787081204466253e-08, "loss": 0.1269, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.2147360081482255, "learning_rate": 9.236233586200627e-08, "loss": 0.1125, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.21240148666965925, "learning_rate": 8.70130406196279e-08, "loss": 0.1241, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.21228294905383, "learning_rate": 8.182296909035047e-08, "loss": 0.1173, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.2152480388685142, "learning_rate": 7.679216277384439e-08, "loss": 0.1257, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2098132904431249, "learning_rate": 7.19206618963053e-08, "loss": 0.1273, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.22076700227173607, "learning_rate": 6.720850541012347e-08, "loss": 0.1128, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.21825403088180928, "learning_rate": 6.265573099357714e-08, "loss": 0.1234, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.20039547283380613, "learning_rate": 5.826237505053067e-08, "loss": 0.1275, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.215131528358084, "learning_rate": 5.4028472710137e-08, "loss": 0.0946, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.20738362076294908, "learning_rate": 4.9954057826571146e-08, "loss": 0.1488, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.20852128218386812, "learning_rate": 4.6039162978743776e-08, "loss": 0.1319, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.21312705984525412, "learning_rate": 4.228381947004812e-08, "loss": 0.1208, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.20807155184444726, "learning_rate": 3.868805732811343e-08, "loss": 0.1248, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.20765392329098262, "learning_rate": 3.525190530455636e-08, "loss": 0.1305, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.21321217719480084, "learning_rate": 3.197539087475887e-08, "loss": 0.1282, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.20667487505712112, "learning_rate": 2.8858540237641786e-08, "loss": 0.1506, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.20607894444068384, "learning_rate": 2.5901378315458247e-08, "loss": 0.1277, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.20236566979677426, "learning_rate": 2.3103928753598347e-08, "loss": 0.1213, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.204276454975288, "learning_rate": 2.0466213920393718e-08, "loss": 0.1355, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.20938826101881486, "learning_rate": 1.7988254906942115e-08, "loss": 0.1124, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.20892096394054915, "learning_rate": 1.5670071526936447e-08, "loss": 0.1224, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2098691445625237, "learning_rate": 1.3511682316509344e-08, "loss": 0.1312, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.21467393695221487, "learning_rate": 1.1513104534086605e-08, "loss": 0.1381, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.20364222574906682, "learning_rate": 9.67435416023843e-09, "loss": 0.116, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.22610692052186598, "learning_rate": 7.995445897566178e-09, "loss": 0.1269, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.2077530036324998, "learning_rate": 6.476393170578021e-09, "loss": 0.1415, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.20831759786167559, "learning_rate": 5.11720812557348e-09, "loss": 0.1283, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.2069270319044804, "learning_rate": 3.917901630563492e-09, "loss": 0.1239, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.20931839756801565, "learning_rate": 2.878483275170485e-09, "loss": 0.1136, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.20151130712217835, "learning_rate": 1.998961370555108e-09, "loss": 0.1391, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.206654767651102, "learning_rate": 1.2793429493518361e-09, "loss": 0.116, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.20801480061638436, "learning_rate": 7.196337656112384e-10, "loss": 0.109, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.20547457396515767, "learning_rate": 3.198382947511292e-10, "loss": 0.1088, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.22123102431960742, "learning_rate": 7.995973352770137e-11, "loss": 0.1086, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19109251318731058, "learning_rate": 0.0, "loss": 0.1222, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 1.8655542516698317e+18, "train_loss": 0.25057385399756643, "train_runtime": 23036.2207, "train_samples_per_second": 6.859, "train_steps_per_second": 0.054 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.8655542516698317e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }