{ "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": 19.252690333895718, "learning_rate": 3.2258064516129035e-07, "loss": 1.5398, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 20.663350076782777, "learning_rate": 6.451612903225807e-07, "loss": 1.5912, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 20.371611221884226, "learning_rate": 9.67741935483871e-07, "loss": 1.5867, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 19.102673131593875, "learning_rate": 1.2903225806451614e-06, "loss": 1.5648, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 16.306366499808306, "learning_rate": 1.6129032258064516e-06, "loss": 1.5045, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 15.455186992980694, "learning_rate": 1.935483870967742e-06, "loss": 1.4907, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 10.707068394079926, "learning_rate": 2.2580645161290324e-06, "loss": 1.3959, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 9.302222370065241, "learning_rate": 2.580645161290323e-06, "loss": 1.3527, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 6.647668227651483, "learning_rate": 2.903225806451613e-06, "loss": 1.2642, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 6.015177202155665, "learning_rate": 3.225806451612903e-06, "loss": 1.2418, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 6.007798616149883, "learning_rate": 3.548387096774194e-06, "loss": 1.2458, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 6.0827429085756, "learning_rate": 3.870967741935484e-06, "loss": 1.1547, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 5.942647275293415, "learning_rate": 4.193548387096774e-06, "loss": 1.1416, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 5.306067246435418, "learning_rate": 4.516129032258065e-06, "loss": 1.0704, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 4.3047180694877865, "learning_rate": 4.838709677419355e-06, "loss": 1.054, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 4.302493528076327, "learning_rate": 5.161290322580646e-06, "loss": 0.9839, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 4.459931354606749, "learning_rate": 5.483870967741935e-06, "loss": 0.9473, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 3.6891622508081947, "learning_rate": 5.806451612903226e-06, "loss": 0.9157, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.6395177391560902, "learning_rate": 6.129032258064517e-06, "loss": 0.8839, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 2.3720719900520213, "learning_rate": 6.451612903225806e-06, "loss": 0.8637, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 2.436962440759414, "learning_rate": 6.774193548387097e-06, "loss": 0.8485, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 2.3585836819886334, "learning_rate": 7.096774193548388e-06, "loss": 0.8484, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 2.2202924175433028, "learning_rate": 7.4193548387096784e-06, "loss": 0.8115, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 2.0303293756796457, "learning_rate": 7.741935483870968e-06, "loss": 0.8164, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.8950517992682068, "learning_rate": 8.064516129032258e-06, "loss": 0.7943, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.8012695604115716, "learning_rate": 8.387096774193549e-06, "loss": 0.7712, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.7396295887742894, "learning_rate": 8.70967741935484e-06, "loss": 0.7646, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.6223943827905778, "learning_rate": 9.03225806451613e-06, "loss": 0.75, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.6830281220669803, "learning_rate": 9.35483870967742e-06, "loss": 0.7262, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.6465055693195758, "learning_rate": 9.67741935483871e-06, "loss": 0.7187, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 1.6302853694115946, "learning_rate": 1e-05, "loss": 0.7121, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 1.3061221351832184, "learning_rate": 1.0322580645161291e-05, "loss": 0.7056, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 1.6384527080698876, "learning_rate": 1.0645161290322582e-05, "loss": 0.6903, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 1.578924447871375, "learning_rate": 1.096774193548387e-05, "loss": 0.69, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 1.757968825189834, "learning_rate": 1.1290322580645164e-05, "loss": 0.6972, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 1.5908667756702672, "learning_rate": 1.1612903225806453e-05, "loss": 0.6863, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 1.3949703645903508, "learning_rate": 1.1935483870967743e-05, "loss": 0.6985, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 1.343623724409516, "learning_rate": 1.2258064516129034e-05, "loss": 0.6608, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 1.363193970813858, "learning_rate": 1.2580645161290324e-05, "loss": 0.6703, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 1.3035507933511965, "learning_rate": 1.2903225806451613e-05, "loss": 0.6628, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 1.260254141822417, "learning_rate": 1.3225806451612903e-05, "loss": 0.666, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 1.5308707613223154, "learning_rate": 1.3548387096774194e-05, "loss": 0.6514, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 1.2747219376489975, "learning_rate": 1.3870967741935486e-05, "loss": 0.6649, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 1.4007832754522314, "learning_rate": 1.4193548387096776e-05, "loss": 0.6605, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 1.4337263616649656, "learning_rate": 1.4516129032258066e-05, "loss": 0.6435, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 1.4541864333004642, "learning_rate": 1.4838709677419357e-05, "loss": 0.6668, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 1.3363304007525354, "learning_rate": 1.5161290322580646e-05, "loss": 0.635, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 1.3140906796352145, "learning_rate": 1.5483870967741936e-05, "loss": 0.634, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 1.4309930421149337, "learning_rate": 1.5806451612903226e-05, "loss": 0.639, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 1.347045124172305, "learning_rate": 1.6129032258064517e-05, "loss": 0.6358, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 1.600930069126479, "learning_rate": 1.6451612903225807e-05, "loss": 0.6487, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 1.3747273214170475, "learning_rate": 1.6774193548387098e-05, "loss": 0.641, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 1.1502584858426133, "learning_rate": 1.7096774193548388e-05, "loss": 0.624, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 1.2504506721469526, "learning_rate": 1.741935483870968e-05, "loss": 0.6351, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 1.197253539048471, "learning_rate": 1.774193548387097e-05, "loss": 0.64, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 1.4437850038477895, "learning_rate": 1.806451612903226e-05, "loss": 0.624, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 1.464312914858835, "learning_rate": 1.838709677419355e-05, "loss": 0.6248, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 1.39437966270147, "learning_rate": 1.870967741935484e-05, "loss": 0.6369, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 1.3857899031770697, "learning_rate": 1.903225806451613e-05, "loss": 0.6212, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 1.3325241639322163, "learning_rate": 1.935483870967742e-05, "loss": 0.6282, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 1.4281439509994878, "learning_rate": 1.967741935483871e-05, "loss": 0.6392, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 1.5578434393780047, "learning_rate": 2e-05, "loss": 0.6408, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 1.4851475286224665, "learning_rate": 2.0322580645161292e-05, "loss": 0.6271, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 1.4584919938673395, "learning_rate": 2.0645161290322582e-05, "loss": 0.6195, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 1.5145466938895973, "learning_rate": 2.0967741935483873e-05, "loss": 0.6142, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 1.425010977536689, "learning_rate": 2.1290322580645163e-05, "loss": 0.5945, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 1.848726028006648, "learning_rate": 2.161290322580645e-05, "loss": 0.6173, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 1.566638539054292, "learning_rate": 2.193548387096774e-05, "loss": 0.6016, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 2.3283244969345884, "learning_rate": 2.225806451612903e-05, "loss": 0.6362, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.5765131987140097, "learning_rate": 2.2580645161290328e-05, "loss": 0.6096, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 2.5101207112396247, "learning_rate": 2.2903225806451615e-05, "loss": 0.6084, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 2.16477194092853, "learning_rate": 2.3225806451612906e-05, "loss": 0.6178, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 1.6464720550843386, "learning_rate": 2.3548387096774196e-05, "loss": 0.6133, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 1.7108236121825897, "learning_rate": 2.3870967741935486e-05, "loss": 0.6279, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 1.4894239365286213, "learning_rate": 2.4193548387096777e-05, "loss": 0.6075, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 2.1021810772301395, "learning_rate": 2.4516129032258067e-05, "loss": 0.6007, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.9332251803536973, "learning_rate": 2.4838709677419358e-05, "loss": 0.6259, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 2.3903787760930677, "learning_rate": 2.5161290322580648e-05, "loss": 0.5969, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 2.483224244605866, "learning_rate": 2.548387096774194e-05, "loss": 0.6151, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.7336423423779876, "learning_rate": 2.5806451612903226e-05, "loss": 0.6063, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 1.4273954783482588, "learning_rate": 2.6129032258064516e-05, "loss": 0.5954, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.5375648023456348, "learning_rate": 2.6451612903225806e-05, "loss": 0.5892, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 1.545954690438218, "learning_rate": 2.6774193548387097e-05, "loss": 0.6071, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 1.3746913746878344, "learning_rate": 2.7096774193548387e-05, "loss": 0.6035, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.9287257483329883, "learning_rate": 2.7419354838709678e-05, "loss": 0.6088, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.794648879568071, "learning_rate": 2.774193548387097e-05, "loss": 0.607, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 1.6918351424811273, "learning_rate": 2.8064516129032262e-05, "loss": 0.6098, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.7819680078315199, "learning_rate": 2.8387096774193552e-05, "loss": 0.5814, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.3867535569713194, "learning_rate": 2.8709677419354843e-05, "loss": 0.6017, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 1.8741212401546816, "learning_rate": 2.9032258064516133e-05, "loss": 0.6072, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.6011616931247574, "learning_rate": 2.9354838709677423e-05, "loss": 0.5929, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.783294409882658, "learning_rate": 2.9677419354838714e-05, "loss": 0.592, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.7334629034398874, "learning_rate": 3.0000000000000004e-05, "loss": 0.6106, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.6258139426267784, "learning_rate": 3.032258064516129e-05, "loss": 0.6086, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.6783900104581309, "learning_rate": 3.0645161290322585e-05, "loss": 0.609, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.4766338520278153, "learning_rate": 3.096774193548387e-05, "loss": 0.5865, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.6390433240193816, "learning_rate": 3.1290322580645166e-05, "loss": 0.5852, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.3739428608439217, "learning_rate": 3.161290322580645e-05, "loss": 0.6113, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.357150137803902, "learning_rate": 3.193548387096774e-05, "loss": 0.5817, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.2777774619997113, "learning_rate": 3.2258064516129034e-05, "loss": 0.5744, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.4721808021776113, "learning_rate": 3.258064516129033e-05, "loss": 0.59, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.493813096563891, "learning_rate": 3.2903225806451614e-05, "loss": 0.6057, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 1.3471630361239595, "learning_rate": 3.322580645161291e-05, "loss": 0.5966, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.2875627643860585, "learning_rate": 3.3548387096774195e-05, "loss": 0.597, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.3402829632236375, "learning_rate": 3.387096774193549e-05, "loss": 0.6147, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.2122699825728709, "learning_rate": 3.4193548387096776e-05, "loss": 0.6053, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 1.501571827643135, "learning_rate": 3.451612903225807e-05, "loss": 0.5909, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.6604639106788837, "learning_rate": 3.483870967741936e-05, "loss": 0.6057, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.3317944903670385, "learning_rate": 3.516129032258065e-05, "loss": 0.5946, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.5843845500585516, "learning_rate": 3.548387096774194e-05, "loss": 0.588, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.3066431312098925, "learning_rate": 3.5806451612903225e-05, "loss": 0.6008, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.803729853878925, "learning_rate": 3.612903225806452e-05, "loss": 0.6032, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.4992245065895273, "learning_rate": 3.6451612903225805e-05, "loss": 0.5707, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.4518060144659903, "learning_rate": 3.67741935483871e-05, "loss": 0.5949, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.7752316481041326, "learning_rate": 3.7096774193548386e-05, "loss": 0.6156, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.0831032941902359, "learning_rate": 3.741935483870968e-05, "loss": 0.5931, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.7266629000663023, "learning_rate": 3.7741935483870974e-05, "loss": 0.6048, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.3129202868998309, "learning_rate": 3.806451612903226e-05, "loss": 0.5911, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.7103331091320308, "learning_rate": 3.8387096774193555e-05, "loss": 0.6031, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.4159123650466923, "learning_rate": 3.870967741935484e-05, "loss": 0.6157, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 1.351326731355493, "learning_rate": 3.9032258064516135e-05, "loss": 0.5934, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.3094335060258255, "learning_rate": 3.935483870967742e-05, "loss": 0.5982, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 1.4694185450549135, "learning_rate": 3.9677419354838716e-05, "loss": 0.5851, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.1239031716399466, "learning_rate": 4e-05, "loss": 0.6044, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.487585702130256, "learning_rate": 3.9999920040266474e-05, "loss": 0.6116, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.3935443138810815, "learning_rate": 3.999968016170525e-05, "loss": 0.5971, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.5062374456876135, "learning_rate": 3.9999280366234394e-05, "loss": 0.5992, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.331199177972978, "learning_rate": 3.999872065705065e-05, "loss": 0.6062, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 1.7819675948460216, "learning_rate": 3.999800103862945e-05, "loss": 0.6087, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 1.4970366868522864, "learning_rate": 3.9997121516724834e-05, "loss": 0.5969, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.7895897922784059, "learning_rate": 3.999608209836944e-05, "loss": 0.5839, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.428284986860102, "learning_rate": 3.999488279187443e-05, "loss": 0.5994, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 1.8882477963976625, "learning_rate": 3.9993523606829425e-05, "loss": 0.6067, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 1.3350045937407493, "learning_rate": 3.9992004554102435e-05, "loss": 0.5921, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 1.4135060953445788, "learning_rate": 3.999032564583976e-05, "loss": 0.6094, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.4314901032327882, "learning_rate": 3.998848689546591e-05, "loss": 0.5931, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 1.252627273088662, "learning_rate": 3.9986488317683496e-05, "loss": 0.5652, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 1.3245938713311187, "learning_rate": 3.9984329928473067e-05, "loss": 0.5909, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 1.4758899253974749, "learning_rate": 3.998201174509306e-05, "loss": 0.6075, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 1.2650882466267581, "learning_rate": 3.997953378607961e-05, "loss": 0.5972, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 1.7780522112482566, "learning_rate": 3.9976896071246403e-05, "loss": 0.592, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 1.1335864320539917, "learning_rate": 3.997409862168454e-05, "loss": 0.6007, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.4033278994977476, "learning_rate": 3.997114145976237e-05, "loss": 0.5923, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 1.0039548894112955, "learning_rate": 3.9968024609125245e-05, "loss": 0.5753, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 1.4350696355283838, "learning_rate": 3.996474809469545e-05, "loss": 0.6054, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 1.0861523221105096, "learning_rate": 3.996131194267189e-05, "loss": 0.587, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 1.4540884551062692, "learning_rate": 3.995771618052995e-05, "loss": 0.5993, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 1.2840891682218025, "learning_rate": 3.9953960837021256e-05, "loss": 0.5894, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 1.3094317527566666, "learning_rate": 3.995004594217343e-05, "loss": 0.6029, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 1.3534788824507544, "learning_rate": 3.994597152728987e-05, "loss": 0.5811, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.9601913630980977, "learning_rate": 3.994173762494947e-05, "loss": 0.5746, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 1.1525283401582833, "learning_rate": 3.9937344269006424e-05, "loss": 0.5971, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 1.0413243348749088, "learning_rate": 3.993279149458988e-05, "loss": 0.6012, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 1.0869426167755298, "learning_rate": 3.9928079338103695e-05, "loss": 0.59, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 1.1308096441484963, "learning_rate": 3.992320783722616e-05, "loss": 0.5987, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 1.0609728538152996, "learning_rate": 3.991817703090965e-05, "loss": 0.5785, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 1.0826598671408691, "learning_rate": 3.991298695938038e-05, "loss": 0.5941, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 1.1794854883434855, "learning_rate": 3.9907637664138e-05, "loss": 0.5732, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.9663435343024572, "learning_rate": 3.990212918795534e-05, "loss": 0.5756, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.9806482303617245, "learning_rate": 3.9896461574878036e-05, "loss": 0.6001, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 1.1031581883766512, "learning_rate": 3.989063487022416e-05, "loss": 0.5829, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 1.065899422417949, "learning_rate": 3.9884649120583903e-05, "loss": 0.5835, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 1.4241936866107814, "learning_rate": 3.987850437381915e-05, "loss": 0.5868, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 1.0906654881876812, "learning_rate": 3.987220067906313e-05, "loss": 0.5837, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 1.4451080578228355, "learning_rate": 3.986573808672002e-05, "loss": 0.5885, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 1.132505509114762, "learning_rate": 3.9859116648464534e-05, "loss": 0.5995, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 1.2788983354496268, "learning_rate": 3.985233641724152e-05, "loss": 0.5832, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 1.1235922128684501, "learning_rate": 3.984539744726554e-05, "loss": 0.5879, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 1.2200012928424624, "learning_rate": 3.983829979402038e-05, "loss": 0.5841, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 1.1835831821996403, "learning_rate": 3.983104351425871e-05, "loss": 0.5857, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 1.0806886557782693, "learning_rate": 3.982362866600154e-05, "loss": 0.5823, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 1.0076585643599554, "learning_rate": 3.9816055308537806e-05, "loss": 0.594, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 1.1012569097284057, "learning_rate": 3.980832350242388e-05, "loss": 0.5683, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.9088467190254645, "learning_rate": 3.980043330948306e-05, "loss": 0.5857, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.9051033234192355, "learning_rate": 3.9792384792805124e-05, "loss": 0.5677, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 1.0624651946647163, "learning_rate": 3.978417801674579e-05, "loss": 0.5918, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 1.0841492440522504, "learning_rate": 3.9775813046926244e-05, "loss": 0.5928, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 1.0214260567498237, "learning_rate": 3.976728995023254e-05, "loss": 0.5823, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 1.077311333874838, "learning_rate": 3.975860879481514e-05, "loss": 0.5794, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 1.0911225285967823, "learning_rate": 3.974976965008833e-05, "loss": 0.5888, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.9282566924284943, "learning_rate": 3.9740772586729674e-05, "loss": 0.5995, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 1.0686148766819332, "learning_rate": 3.973161767667946e-05, "loss": 0.5712, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.9387340699888678, "learning_rate": 3.972230499314009e-05, "loss": 0.6034, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.9302371225232643, "learning_rate": 3.9712834610575545e-05, "loss": 0.5731, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 1.0355959725969266, "learning_rate": 3.9703206604710746e-05, "loss": 0.5717, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 1.183874855659692, "learning_rate": 3.969342105253098e-05, "loss": 0.6037, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.9721214244117907, "learning_rate": 3.9683478032281246e-05, "loss": 0.5757, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 1.139571209984775, "learning_rate": 3.967337762346568e-05, "loss": 0.5904, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.9618215797743831, "learning_rate": 3.9663119906846885e-05, "loss": 0.5697, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 1.050531086197253, "learning_rate": 3.965270496444528e-05, "loss": 0.5709, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.9439092808836409, "learning_rate": 3.9642132879538465e-05, "loss": 0.5776, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 1.00772701542615, "learning_rate": 3.9631403736660566e-05, "loss": 0.5695, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.9809804540451803, "learning_rate": 3.962051762160151e-05, "loss": 0.5819, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 1.1700699987359613, "learning_rate": 3.960947462140638e-05, "loss": 0.576, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.9513101286618271, "learning_rate": 3.959827482437472e-05, "loss": 0.5877, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 1.1461985143684827, "learning_rate": 3.958691832005981e-05, "loss": 0.5721, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 1.1030614619906545, "learning_rate": 3.9575405199267944e-05, "loss": 0.5741, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 1.374279185412321, "learning_rate": 3.956373555405774e-05, "loss": 0.5766, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 1.1420162376559932, "learning_rate": 3.955190947773937e-05, "loss": 0.6004, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 1.3359861156047337, "learning_rate": 3.9539927064873824e-05, "loss": 0.5804, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 1.0651016739811217, "learning_rate": 3.952778841127214e-05, "loss": 0.5969, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 1.0933528346918173, "learning_rate": 3.95154936139947e-05, "loss": 0.5983, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 1.0485485196235214, "learning_rate": 3.950304277135034e-05, "loss": 0.5703, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 1.1044733220189855, "learning_rate": 3.94904359828957e-05, "loss": 0.5914, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.9005884140089929, "learning_rate": 3.94776733494343e-05, "loss": 0.5588, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.9277126175071697, "learning_rate": 3.9464754973015826e-05, "loss": 0.5555, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.9351465236989579, "learning_rate": 3.9451680956935275e-05, "loss": 0.574, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.8504777345823327, "learning_rate": 3.943845140573213e-05, "loss": 0.5872, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.918501236565003, "learning_rate": 3.942506642518952e-05, "loss": 0.5895, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.8567664901985884, "learning_rate": 3.9411526122333396e-05, "loss": 0.5807, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.9029510861639635, "learning_rate": 3.939783060543167e-05, "loss": 0.5772, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 1.0249239550636557, "learning_rate": 3.938397998399333e-05, "loss": 0.5744, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.8831730005703099, "learning_rate": 3.936997436876756e-05, "loss": 0.574, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.9687730569480353, "learning_rate": 3.935581387174289e-05, "loss": 0.5626, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.9975997034565769, "learning_rate": 3.9341498606146295e-05, "loss": 0.5687, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.9401080944598412, "learning_rate": 3.932702868644224e-05, "loss": 0.5809, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.9808697532306243, "learning_rate": 3.931240422833181e-05, "loss": 0.5674, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7666991355042834, "learning_rate": 3.9297625348751806e-05, "loss": 0.5731, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.9926794227420196, "learning_rate": 3.9282692165873744e-05, "loss": 0.5787, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.7303494162806105, "learning_rate": 3.9267604799102945e-05, "loss": 0.5843, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.9466843475405502, "learning_rate": 3.9252363369077615e-05, "loss": 0.5744, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.8762773373191212, "learning_rate": 3.9236967997667796e-05, "loss": 0.5626, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.832747543627582, "learning_rate": 3.9221418807974496e-05, "loss": 0.583, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.8702346995982627, "learning_rate": 3.92057159243286e-05, "loss": 0.591, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.8101399047517628, "learning_rate": 3.9189859472289956e-05, "loss": 0.5704, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.7466952995531614, "learning_rate": 3.9173849578646324e-05, "loss": 0.5653, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.8197403936930032, "learning_rate": 3.9157686371412395e-05, "loss": 0.5709, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.8637683375675744, "learning_rate": 3.914136997982874e-05, "loss": 0.5723, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.905379624546444, "learning_rate": 3.912490053436079e-05, "loss": 0.5831, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.8646688699008898, "learning_rate": 3.9108278166697805e-05, "loss": 0.5705, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.9580739846784586, "learning_rate": 3.909150300975178e-05, "loss": 0.5634, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.8109018067471367, "learning_rate": 3.907457519765642e-05, "loss": 0.5629, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.9925600073429315, "learning_rate": 3.905749486576607e-05, "loss": 0.5632, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.8171350649099841, "learning_rate": 3.90402621506546e-05, "loss": 0.5719, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.7787892621805041, "learning_rate": 3.902287719011435e-05, "loss": 0.5657, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.85676285023483, "learning_rate": 3.900534012315499e-05, "loss": 0.5518, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.7611248645643034, "learning_rate": 3.8987651090002454e-05, "loss": 0.5679, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7629056594488097, "learning_rate": 3.896981023209777e-05, "loss": 0.5533, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.9661119997426296, "learning_rate": 3.8951817692095966e-05, "loss": 0.568, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.7892337488270639, "learning_rate": 3.893367361386491e-05, "loss": 0.5597, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 1.3567434669606306, "learning_rate": 3.891537814248417e-05, "loss": 0.5691, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.858724109076416, "learning_rate": 3.889693142424384e-05, "loss": 0.5592, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 1.040841206416966, "learning_rate": 3.8878333606643405e-05, "loss": 0.551, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 1.1863258673251504, "learning_rate": 3.885958483839049e-05, "loss": 0.5762, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.9091789675573673, "learning_rate": 3.8840685269399786e-05, "loss": 0.5556, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.9418021109163665, "learning_rate": 3.882163505079171e-05, "loss": 0.574, "step": 246 }, { "epoch": 1.0, "grad_norm": 1.009598898285874, "learning_rate": 3.880243433489132e-05, "loss": 0.5582, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.7386488139593856, "learning_rate": 3.878308327522702e-05, "loss": 0.5138, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.8761737712568454, "learning_rate": 3.876358202652936e-05, "loss": 0.5166, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.71522322251874, "learning_rate": 3.8743930744729835e-05, "loss": 0.5191, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.8969618442632727, "learning_rate": 3.8724129586959535e-05, "loss": 0.5198, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 1.1564145617793653, "learning_rate": 3.870417871154801e-05, "loss": 0.5035, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.7017885969457458, "learning_rate": 3.868407827802192e-05, "loss": 0.5176, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.9875409453803451, "learning_rate": 3.8663828447103804e-05, "loss": 0.5274, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.7844996173625557, "learning_rate": 3.8643429380710765e-05, "loss": 0.5043, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.8573617593571987, "learning_rate": 3.862288124195319e-05, "loss": 0.5099, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.870302647022531, "learning_rate": 3.8602184195133464e-05, "loss": 0.5143, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.8594960933908071, "learning_rate": 3.8581338405744604e-05, "loss": 0.5105, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.844614487680458, "learning_rate": 3.8560344040468996e-05, "loss": 0.5223, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.7289504156925073, "learning_rate": 3.853920126717703e-05, "loss": 0.5265, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.8128343045960369, "learning_rate": 3.851791025492574e-05, "loss": 0.5077, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.8404165073643822, "learning_rate": 3.8496471173957515e-05, "loss": 0.5252, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.8030885337572248, "learning_rate": 3.847488419569866e-05, "loss": 0.4905, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.8076363783760453, "learning_rate": 3.8453149492758077e-05, "loss": 0.5172, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.7723675864820486, "learning_rate": 3.8431267238925886e-05, "loss": 0.5077, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.74485212842674, "learning_rate": 3.840923760917199e-05, "loss": 0.5108, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.724777419812081, "learning_rate": 3.838706077964473e-05, "loss": 0.5157, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.7535468958403376, "learning_rate": 3.836473692766944e-05, "loss": 0.5027, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.8030541263099834, "learning_rate": 3.834226623174705e-05, "loss": 0.5268, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.6776265103023278, "learning_rate": 3.831964887155264e-05, "loss": 0.517, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.7940461404579646, "learning_rate": 3.829688502793403e-05, "loss": 0.5057, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.6966856677224769, "learning_rate": 3.827397488291029e-05, "loss": 0.5171, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.7985002616954955, "learning_rate": 3.8250918619670343e-05, "loss": 0.493, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.7677621545788159, "learning_rate": 3.822771642257145e-05, "loss": 0.5375, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.8676435636459676, "learning_rate": 3.820436847713776e-05, "loss": 0.5045, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.7305275519311488, "learning_rate": 3.8180874970058826e-05, "loss": 0.5128, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.8903098439986853, "learning_rate": 3.8157236089188103e-05, "loss": 0.5155, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.6600948311814908, "learning_rate": 3.813345202354145e-05, "loss": 0.5112, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.7739309421664086, "learning_rate": 3.810952296329563e-05, "loss": 0.5267, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.768225572402607, "learning_rate": 3.808544909978676e-05, "loss": 0.512, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.7710352172395056, "learning_rate": 3.806123062550882e-05, "loss": 0.5346, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.703450540769814, "learning_rate": 3.803686773411208e-05, "loss": 0.5141, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.8389770881495797, "learning_rate": 3.801236062040158e-05, "loss": 0.5165, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.7192004517212598, "learning_rate": 3.798770948033553e-05, "loss": 0.519, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.7349710964569492, "learning_rate": 3.796291451102381e-05, "loss": 0.5125, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6582534583788864, "learning_rate": 3.793797591072631e-05, "loss": 0.5081, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.7677606344242857, "learning_rate": 3.791289387885144e-05, "loss": 0.5025, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.7114854248091468, "learning_rate": 3.788766861595443e-05, "loss": 0.5146, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.6917495272911155, "learning_rate": 3.7862300323735835e-05, "loss": 0.4935, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.7187766984465079, "learning_rate": 3.783678920503983e-05, "loss": 0.5109, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.6683847834651816, "learning_rate": 3.781113546385265e-05, "loss": 0.5012, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.7829723273471675, "learning_rate": 3.7785339305300916e-05, "loss": 0.5272, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.7446054061240619, "learning_rate": 3.7759400935650025e-05, "loss": 0.4972, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.6947833118232376, "learning_rate": 3.77333205623025e-05, "loss": 0.496, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.968114408518206, "learning_rate": 3.7707098393796295e-05, "loss": 0.5031, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.8174163371364065, "learning_rate": 3.7680734639803185e-05, "loss": 0.5064, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.9726443596059957, "learning_rate": 3.765422951112704e-05, "loss": 0.5377, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.7864935549617391, "learning_rate": 3.762758321970216e-05, "loss": 0.5193, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.8713081250383852, "learning_rate": 3.7600795978591584e-05, "loss": 0.5094, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.6794276123933063, "learning_rate": 3.757386800198538e-05, "loss": 0.5032, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.9281998155118928, "learning_rate": 3.7546799505198925e-05, "loss": 0.5147, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.7462891863680089, "learning_rate": 3.7519590704671197e-05, "loss": 0.5009, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.8964457463237635, "learning_rate": 3.749224181796305e-05, "loss": 0.503, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.7070431339221076, "learning_rate": 3.746475306375545e-05, "loss": 0.5139, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.7788890935620858, "learning_rate": 3.743712466184774e-05, "loss": 0.5151, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.7019452617660829, "learning_rate": 3.7409356833155885e-05, "loss": 0.4993, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.6985236092356045, "learning_rate": 3.73814497997107e-05, "loss": 0.5084, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.833327287033315, "learning_rate": 3.7353403784656095e-05, "loss": 0.5231, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.7091663319585678, "learning_rate": 3.732521901224724e-05, "loss": 0.5253, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.8586474115133234, "learning_rate": 3.7296895707848844e-05, "loss": 0.5021, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.7341552026776824, "learning_rate": 3.7268434097933275e-05, "loss": 0.5084, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.7390086575075017, "learning_rate": 3.723983441007882e-05, "loss": 0.516, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.7066127521928709, "learning_rate": 3.721109687296781e-05, "loss": 0.5067, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.7464149173457072, "learning_rate": 3.718222171638484e-05, "loss": 0.5118, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.7301416789787818, "learning_rate": 3.715320917121488e-05, "loss": 0.5011, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.8107178507702602, "learning_rate": 3.712405946944149e-05, "loss": 0.5257, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6748262559553972, "learning_rate": 3.709477284414488e-05, "loss": 0.5232, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.75242955765086, "learning_rate": 3.7065349529500136e-05, "loss": 0.506, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.8079700996603434, "learning_rate": 3.7035789760775305e-05, "loss": 0.519, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.7279137330914217, "learning_rate": 3.70060937743295e-05, "loss": 0.5172, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.7935631297431146, "learning_rate": 3.6976261807611045e-05, "loss": 0.5086, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.7417605328105408, "learning_rate": 3.694629409915555e-05, "loss": 0.4917, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.6270376423996491, "learning_rate": 3.691619088858401e-05, "loss": 0.522, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.6520269852387204, "learning_rate": 3.68859524166009e-05, "loss": 0.517, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.7217646566138646, "learning_rate": 3.6855578924992226e-05, "loss": 0.5052, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.6884714143997652, "learning_rate": 3.6825070656623626e-05, "loss": 0.5192, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.6955920297233061, "learning_rate": 3.67944278554384e-05, "loss": 0.5117, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.7314079288692376, "learning_rate": 3.676365076645557e-05, "loss": 0.4925, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.7207289957695537, "learning_rate": 3.673273963576791e-05, "loss": 0.5115, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.6783586907789179, "learning_rate": 3.670169471054001e-05, "loss": 0.5159, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.766599809943206, "learning_rate": 3.6670516239006254e-05, "loss": 0.5146, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.7366035313602693, "learning_rate": 3.663920447046888e-05, "loss": 0.4968, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.897706716561883, "learning_rate": 3.6607759655295954e-05, "loss": 0.5136, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.7308688438951336, "learning_rate": 3.657618204491937e-05, "loss": 0.5149, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.8023596880571328, "learning_rate": 3.6544471891832875e-05, "loss": 0.5051, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.7204964189569963, "learning_rate": 3.6512629449589983e-05, "loss": 0.5168, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.6730669903927128, "learning_rate": 3.6480654972802045e-05, "loss": 0.5215, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.7838108498051364, "learning_rate": 3.644854871713611e-05, "loss": 0.5071, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.6382041855133499, "learning_rate": 3.6416310939312924e-05, "loss": 0.5174, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.6452867584480547, "learning_rate": 3.638394189710493e-05, "loss": 0.5175, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.6933948144963639, "learning_rate": 3.635144184933412e-05, "loss": 0.4949, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.7534488871274349, "learning_rate": 3.6318811055869994e-05, "loss": 0.5254, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.715430280727421, "learning_rate": 3.628604977762752e-05, "loss": 0.5085, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.9422602225199317, "learning_rate": 3.6253158276565004e-05, "loss": 0.5073, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.836641760033025, "learning_rate": 3.6220136815682016e-05, "loss": 0.5016, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 1.003232451048981, "learning_rate": 3.618698565901727e-05, "loss": 0.5271, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.7879312929779251, "learning_rate": 3.615370507164654e-05, "loss": 0.4989, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.6729285483582397, "learning_rate": 3.61202953196805e-05, "loss": 0.5081, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.7265138016158843, "learning_rate": 3.6086756670262654e-05, "loss": 0.4868, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.7926898413871319, "learning_rate": 3.6053089391567135e-05, "loss": 0.5153, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.7364503647512103, "learning_rate": 3.601929375279662e-05, "loss": 0.5189, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.6715274849630171, "learning_rate": 3.598537002418012e-05, "loss": 0.5153, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.8041965563915681, "learning_rate": 3.5951318476970885e-05, "loss": 0.5181, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.7385257759582193, "learning_rate": 3.591713938344416e-05, "loss": 0.5205, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.6319202492978194, "learning_rate": 3.588283301689507e-05, "loss": 0.4994, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.765925423368321, "learning_rate": 3.5848399651636424e-05, "loss": 0.5149, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.6291983907008258, "learning_rate": 3.5813839562996473e-05, "loss": 0.4991, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.7214426567773777, "learning_rate": 3.5779153027316775e-05, "loss": 0.5176, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.7160810697922734, "learning_rate": 3.574434032194994e-05, "loss": 0.5027, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.6451479521555145, "learning_rate": 3.5709401725257436e-05, "loss": 0.5095, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.8110133556640089, "learning_rate": 3.5674337516607346e-05, "loss": 0.5048, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.6476236608517095, "learning_rate": 3.563914797637216e-05, "loss": 0.5014, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.7712709628781768, "learning_rate": 3.560383338592649e-05, "loss": 0.5209, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.7395315712118015, "learning_rate": 3.556839402764487e-05, "loss": 0.5052, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.701136844511446, "learning_rate": 3.553283018489946e-05, "loss": 0.5107, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.7294123907300668, "learning_rate": 3.54971421420578e-05, "loss": 0.5192, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.7169771934777687, "learning_rate": 3.5461330184480524e-05, "loss": 0.5066, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.766734795793749, "learning_rate": 3.54253945985191e-05, "loss": 0.5048, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.7587430830448129, "learning_rate": 3.5389335671513524e-05, "loss": 0.5207, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.7154531588560538, "learning_rate": 3.5353153691789986e-05, "loss": 0.5219, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.7725864838678139, "learning_rate": 3.531684894865866e-05, "loss": 0.5176, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.6709944295177942, "learning_rate": 3.528042173241128e-05, "loss": 0.491, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.7120163513264518, "learning_rate": 3.524387233431892e-05, "loss": 0.503, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.6400203920639718, "learning_rate": 3.520720104662958e-05, "loss": 0.5194, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.6142648555107427, "learning_rate": 3.5170408162565904e-05, "loss": 0.5019, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.7567267948687151, "learning_rate": 3.513349397632281e-05, "loss": 0.5122, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.5727042006124682, "learning_rate": 3.5096458783065145e-05, "loss": 0.5086, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.7561065002957736, "learning_rate": 3.505930287892533e-05, "loss": 0.4937, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.6777560896012663, "learning_rate": 3.502202656100099e-05, "loss": 0.4997, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.7908275765910658, "learning_rate": 3.498463012735256e-05, "loss": 0.5242, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.7257921569351039, "learning_rate": 3.494711387700094e-05, "loss": 0.4869, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.8265041580509188, "learning_rate": 3.490947810992505e-05, "loss": 0.5012, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.6860712132098231, "learning_rate": 3.48717231270595e-05, "loss": 0.5094, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.7722489281147833, "learning_rate": 3.483384923029211e-05, "loss": 0.5142, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.7116529390029164, "learning_rate": 3.479585672246156e-05, "loss": 0.4986, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.7514942998744033, "learning_rate": 3.4757745907354924e-05, "loss": 0.5142, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.798558350585866, "learning_rate": 3.471951708970527e-05, "loss": 0.5058, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.7008436031469284, "learning_rate": 3.468117057518921e-05, "loss": 0.5134, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.7733567825405905, "learning_rate": 3.4642706670424426e-05, "loss": 0.5003, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.6899718414424463, "learning_rate": 3.460412568296731e-05, "loss": 0.5139, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.7061700853970564, "learning_rate": 3.456542792131039e-05, "loss": 0.508, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.6813234579290132, "learning_rate": 3.4526613694879936e-05, "loss": 0.5076, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.6075924557166135, "learning_rate": 3.448768331403348e-05, "loss": 0.4925, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.675040622959714, "learning_rate": 3.44486370900573e-05, "loss": 0.502, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.7022125184337857, "learning_rate": 3.440947533516396e-05, "loss": 0.5065, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.6541277383740077, "learning_rate": 3.4370198362489816e-05, "loss": 0.5084, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.7512650419509327, "learning_rate": 3.43308064860925e-05, "loss": 0.5151, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.6705954509901076, "learning_rate": 3.4291300020948393e-05, "loss": 0.4956, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.6379488499355248, "learning_rate": 3.425167928295015e-05, "loss": 0.5065, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.7252597618222439, "learning_rate": 3.421194458890411e-05, "loss": 0.517, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.7098796374245604, "learning_rate": 3.4172096256527865e-05, "loss": 0.524, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.6262168454172714, "learning_rate": 3.4132134604447595e-05, "loss": 0.4898, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.7594523928315979, "learning_rate": 3.409205995219561e-05, "loss": 0.5232, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.62661142463114, "learning_rate": 3.4051872620207765e-05, "loss": 0.513, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.7924771780864053, "learning_rate": 3.40115729298209e-05, "loss": 0.5109, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.650604673416369, "learning_rate": 3.397116120327025e-05, "loss": 0.4853, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.6464289234009971, "learning_rate": 3.3930637763686916e-05, "loss": 0.4869, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.7342873811408203, "learning_rate": 3.389000293509524e-05, "loss": 0.5124, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.6171964737384268, "learning_rate": 3.3849257042410225e-05, "loss": 0.4977, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.6668498355724373, "learning_rate": 3.380840041143494e-05, "loss": 0.5139, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.6379973144539338, "learning_rate": 3.376743336885792e-05, "loss": 0.5016, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.6255755997528922, "learning_rate": 3.372635624225055e-05, "loss": 0.5031, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.6881241781508985, "learning_rate": 3.3685169360064445e-05, "loss": 0.496, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.6243433144421625, "learning_rate": 3.3643873051628804e-05, "loss": 0.5121, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.6106435105607648, "learning_rate": 3.3602467647147814e-05, "loss": 0.4886, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.6743112578534225, "learning_rate": 3.356095347769799e-05, "loss": 0.5072, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.5533694998484329, "learning_rate": 3.351933087522552e-05, "loss": 0.5028, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.7409343459897562, "learning_rate": 3.3477600172543626e-05, "loss": 0.4962, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.6556288477783744, "learning_rate": 3.3435761703329894e-05, "loss": 0.5107, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.5660898706373979, "learning_rate": 3.3393815802123606e-05, "loss": 0.5197, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.84016147972965, "learning_rate": 3.335176280432308e-05, "loss": 0.5157, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.6006866157699378, "learning_rate": 3.330960304618295e-05, "loss": 0.5026, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.6402434536355455, "learning_rate": 3.326733686481153e-05, "loss": 0.5047, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.6740395807402674, "learning_rate": 3.3224964598168084e-05, "loss": 0.5052, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.613018528734145, "learning_rate": 3.318248658506012e-05, "loss": 0.4788, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.6247290212611402, "learning_rate": 3.313990316514069e-05, "loss": 0.4945, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.6742106032910862, "learning_rate": 3.309721467890571e-05, "loss": 0.5015, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.5784077338775468, "learning_rate": 3.305442146769115e-05, "loss": 0.4897, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.6775631591458916, "learning_rate": 3.30115238736704e-05, "loss": 0.4889, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.6532553809309816, "learning_rate": 3.296852223985148e-05, "loss": 0.5092, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.663420359042472, "learning_rate": 3.2925416910074315e-05, "loss": 0.5044, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.7290334294180054, "learning_rate": 3.288220822900796e-05, "loss": 0.5049, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.6499791622984497, "learning_rate": 3.283889654214788e-05, "loss": 0.5033, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.6271442492778925, "learning_rate": 3.279548219581317e-05, "loss": 0.4934, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.7166143375816871, "learning_rate": 3.275196553714379e-05, "loss": 0.5051, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.691108297604648, "learning_rate": 3.270834691409778e-05, "loss": 0.5129, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.5704451815206003, "learning_rate": 3.266462667544849e-05, "loss": 0.5004, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.7553522582268496, "learning_rate": 3.262080517078178e-05, "loss": 0.515, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.6526204667448273, "learning_rate": 3.257688275049323e-05, "loss": 0.507, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.6181674493966699, "learning_rate": 3.253285976578535e-05, "loss": 0.5009, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.6961973633961789, "learning_rate": 3.2488736568664756e-05, "loss": 0.4915, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.6301639520351929, "learning_rate": 3.244451351193935e-05, "loss": 0.5103, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.7136568686023038, "learning_rate": 3.240019094921551e-05, "loss": 0.5079, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.6793387168939634, "learning_rate": 3.235576923489527e-05, "loss": 0.4878, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.64233948350445, "learning_rate": 3.2311248724173476e-05, "loss": 0.4971, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5877565416368784, "learning_rate": 3.226662977303494e-05, "loss": 0.5013, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.6699689270727811, "learning_rate": 3.2221912738251626e-05, "loss": 0.5161, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.6527843050330759, "learning_rate": 3.2177097977379736e-05, "loss": 0.4864, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.6542751085727732, "learning_rate": 3.21321858487569e-05, "loss": 0.5003, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.7699907763041003, "learning_rate": 3.208717671149931e-05, "loss": 0.5012, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.6865254931902653, "learning_rate": 3.204207092549882e-05, "loss": 0.5198, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.6987390841538995, "learning_rate": 3.19968688514201e-05, "loss": 0.5101, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.7166413175166679, "learning_rate": 3.195157085069774e-05, "loss": 0.4977, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.640600322944735, "learning_rate": 3.190617728553332e-05, "loss": 0.5032, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.7757638919286624, "learning_rate": 3.1860688518892606e-05, "loss": 0.4955, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.6376583034689963, "learning_rate": 3.181510491450254e-05, "loss": 0.5052, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.7162696435601492, "learning_rate": 3.176942683684842e-05, "loss": 0.5192, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.6137520840235002, "learning_rate": 3.1723654651170934e-05, "loss": 0.5148, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.5860008093573355, "learning_rate": 3.167778872346327e-05, "loss": 0.4996, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.6378470519391608, "learning_rate": 3.163182942046815e-05, "loss": 0.5076, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.5609762752459165, "learning_rate": 3.158577710967494e-05, "loss": 0.497, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.6580912884997667, "learning_rate": 3.153963215931669e-05, "loss": 0.5076, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.6094542199104481, "learning_rate": 3.14933949383672e-05, "loss": 0.5073, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.7207503663524532, "learning_rate": 3.144706581653805e-05, "loss": 0.5078, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.5652690159279754, "learning_rate": 3.140064516427566e-05, "loss": 0.4895, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.7220777771174518, "learning_rate": 3.135413335275833e-05, "loss": 0.5047, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.6307600767738635, "learning_rate": 3.130753075389327e-05, "loss": 0.4981, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.7236911088196227, "learning_rate": 3.1260837740313625e-05, "loss": 0.4952, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.7238209897285166, "learning_rate": 3.121405468537547e-05, "loss": 0.5063, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.8422830627363168, "learning_rate": 3.116718196315488e-05, "loss": 0.4972, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.6793027153442104, "learning_rate": 3.1120219948444894e-05, "loss": 0.4916, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.6237210945387671, "learning_rate": 3.107316901675252e-05, "loss": 0.5229, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.6340727829209798, "learning_rate": 3.1026029544295745e-05, "loss": 0.5048, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.7142286364948806, "learning_rate": 3.097880190800057e-05, "loss": 0.4846, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.5927042874835212, "learning_rate": 3.093148648549788e-05, "loss": 0.5085, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.6906247485877424, "learning_rate": 3.088408365512055e-05, "loss": 0.5013, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.6054222640256414, "learning_rate": 3.083659379590034e-05, "loss": 0.5123, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.7966258052646419, "learning_rate": 3.0789017287564913e-05, "loss": 0.4919, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.6517515891219524, "learning_rate": 3.074135451053475e-05, "loss": 0.4973, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.5635529745569277, "learning_rate": 3.069360584592015e-05, "loss": 0.5208, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.6761669927273513, "learning_rate": 3.064577167551816e-05, "loss": 0.4897, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.5741203019972658, "learning_rate": 3.059785238180953e-05, "loss": 0.4985, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.6263190465580449, "learning_rate": 3.054984834795566e-05, "loss": 0.5067, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.6051674202538629, "learning_rate": 3.0501759957795537e-05, "loss": 0.5105, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.6470581015776129, "learning_rate": 3.0453587595842627e-05, "loss": 0.5002, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.6474127157595476, "learning_rate": 3.0405331647281856e-05, "loss": 0.5185, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.6390167527043905, "learning_rate": 3.0356992497966508e-05, "loss": 0.5249, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.6323698119379176, "learning_rate": 3.0308570534415137e-05, "loss": 0.4899, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.6128826821718721, "learning_rate": 3.0260066143808467e-05, "loss": 0.4894, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.6164700685775517, "learning_rate": 3.021147971398632e-05, "loss": 0.5035, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.5613942074864914, "learning_rate": 3.0162811633444478e-05, "loss": 0.4932, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.643077136197598, "learning_rate": 3.0114062291331635e-05, "loss": 0.4935, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.5862133208732139, "learning_rate": 3.0065232077446217e-05, "loss": 0.4973, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.6268681697778087, "learning_rate": 3.001632138223332e-05, "loss": 0.4874, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.7497069502093034, "learning_rate": 2.9967330596781565e-05, "loss": 0.4333, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.5900497786643143, "learning_rate": 2.9918260112819952e-05, "loss": 0.4242, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.7001470568967737, "learning_rate": 2.9869110322714778e-05, "loss": 0.419, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.716404488186778, "learning_rate": 2.9819881619466447e-05, "loss": 0.4311, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.7526536016913539, "learning_rate": 2.9770574396706364e-05, "loss": 0.4205, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.6434584797979317, "learning_rate": 2.972118904869376e-05, "loss": 0.406, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.750387819392955, "learning_rate": 2.9671725970312563e-05, "loss": 0.4089, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.7267110350155764, "learning_rate": 2.9622185557068238e-05, "loss": 0.4199, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.8167864857954605, "learning_rate": 2.95725682050846e-05, "loss": 0.4066, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.6934637977192475, "learning_rate": 2.9522874311100684e-05, "loss": 0.4181, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.7065435554459357, "learning_rate": 2.9473104272467526e-05, "loss": 0.4087, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.6395179315957593, "learning_rate": 2.942325848714505e-05, "loss": 0.4032, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.6478365809005187, "learning_rate": 2.9373337353698804e-05, "loss": 0.4246, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.5896541560261942, "learning_rate": 2.932334127129686e-05, "loss": 0.4092, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.6169404765440214, "learning_rate": 2.9273270639706547e-05, "loss": 0.4124, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.6107213998159137, "learning_rate": 2.922312585929131e-05, "loss": 0.4139, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.6184797633316063, "learning_rate": 2.9172907331007478e-05, "loss": 0.4405, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.6489071189934782, "learning_rate": 2.9122615456401053e-05, "loss": 0.4158, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.6027071750118127, "learning_rate": 2.9072250637604535e-05, "loss": 0.4127, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.5969538797791464, "learning_rate": 2.9021813277333667e-05, "loss": 0.4117, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.5892108986410675, "learning_rate": 2.8971303778884244e-05, "loss": 0.4189, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.6338899124113089, "learning_rate": 2.8920722546128863e-05, "loss": 0.4103, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.5893569596827363, "learning_rate": 2.887006998351372e-05, "loss": 0.414, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.5738569017649005, "learning_rate": 2.881934649605535e-05, "loss": 0.4005, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.5794335112628964, "learning_rate": 2.8768552489337408e-05, "loss": 0.4036, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.568629441531512, "learning_rate": 2.8717688369507425e-05, "loss": 0.4107, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.5862510742404615, "learning_rate": 2.8666754543273535e-05, "loss": 0.4224, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.5579696917526445, "learning_rate": 2.8615751417901273e-05, "loss": 0.4084, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.5778613587511152, "learning_rate": 2.856467940121025e-05, "loss": 0.4008, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.5718414702725371, "learning_rate": 2.8513538901570964e-05, "loss": 0.4088, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.5940442853230871, "learning_rate": 2.846233032790149e-05, "loss": 0.4263, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.5314023044443185, "learning_rate": 2.84110540896642e-05, "loss": 0.3967, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.5692096969657218, "learning_rate": 2.8359710596862555e-05, "loss": 0.4212, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.5389815852773194, "learning_rate": 2.8308300260037734e-05, "loss": 0.4231, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.5302117093372141, "learning_rate": 2.8256823490265424e-05, "loss": 0.3949, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.579011931946701, "learning_rate": 2.8205280699152515e-05, "loss": 0.4204, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.6555639695113388, "learning_rate": 2.8153672298833777e-05, "loss": 0.4122, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.5918052148448211, "learning_rate": 2.8101998701968615e-05, "loss": 0.4043, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.6300713341841188, "learning_rate": 2.805026032173773e-05, "loss": 0.4204, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.6174126949702116, "learning_rate": 2.7998457571839832e-05, "loss": 0.4138, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.5418447493995489, "learning_rate": 2.7946590866488322e-05, "loss": 0.4104, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.6055847844334211, "learning_rate": 2.7894660620408e-05, "loss": 0.4261, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.5994670598361685, "learning_rate": 2.784266724883173e-05, "loss": 0.4076, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.5936938838961611, "learning_rate": 2.7790611167497128e-05, "loss": 0.4365, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.6543041015444495, "learning_rate": 2.7738492792643224e-05, "loss": 0.4311, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.5481671008017576, "learning_rate": 2.768631254100716e-05, "loss": 0.4207, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.6204029605192922, "learning_rate": 2.7634070829820836e-05, "loss": 0.4108, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.5991365682386872, "learning_rate": 2.7581768076807592e-05, "loss": 0.4022, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.5989914137351398, "learning_rate": 2.7529404700178832e-05, "loss": 0.4052, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.6768032069091938, "learning_rate": 2.7476981118630735e-05, "loss": 0.4096, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.6088034613432787, "learning_rate": 2.742449775134085e-05, "loss": 0.4328, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.6095352556204073, "learning_rate": 2.7371955017964788e-05, "loss": 0.4214, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.5808142524614093, "learning_rate": 2.7319353338632845e-05, "loss": 0.4201, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.5664974689146711, "learning_rate": 2.7266693133946645e-05, "loss": 0.4274, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.5520359030976045, "learning_rate": 2.7213974824975785e-05, "loss": 0.4178, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.5341487916251735, "learning_rate": 2.7161198833254464e-05, "loss": 0.4219, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.5256331227883997, "learning_rate": 2.7108365580778095e-05, "loss": 0.4046, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.541481956986803, "learning_rate": 2.705547548999996e-05, "loss": 0.3963, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.5866891950339389, "learning_rate": 2.7002528983827817e-05, "loss": 0.4202, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.592131675225489, "learning_rate": 2.6949526485620517e-05, "loss": 0.413, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.633064282999678, "learning_rate": 2.6896468419184623e-05, "loss": 0.4145, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.5707524209587914, "learning_rate": 2.6843355208771024e-05, "loss": 0.4227, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.6122462655206737, "learning_rate": 2.6790187279071536e-05, "loss": 0.3736, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.6130647929490455, "learning_rate": 2.67369650552155e-05, "loss": 0.4154, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.5632433613782609, "learning_rate": 2.6683688962766407e-05, "loss": 0.4031, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.5896955610971575, "learning_rate": 2.6630359427718468e-05, "loss": 0.4203, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.6745759044091892, "learning_rate": 2.6576976876493225e-05, "loss": 0.4184, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.6193844685295411, "learning_rate": 2.652354173593614e-05, "loss": 0.4167, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.6137150878436108, "learning_rate": 2.647005443331317e-05, "loss": 0.4171, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.5505712600048093, "learning_rate": 2.6416515396307354e-05, "loss": 0.4093, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.5693453127439181, "learning_rate": 2.636292505301542e-05, "loss": 0.4334, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.556377704104147, "learning_rate": 2.630928383194431e-05, "loss": 0.4079, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.589113788682908, "learning_rate": 2.625559216200781e-05, "loss": 0.4298, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5836727263067857, "learning_rate": 2.620185047252308e-05, "loss": 0.4235, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.557568758208206, "learning_rate": 2.614805919320723e-05, "loss": 0.4212, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.5595902073274098, "learning_rate": 2.6094218754173895e-05, "loss": 0.409, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.5400431959672334, "learning_rate": 2.60403295859298e-05, "loss": 0.4285, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.5921413348619464, "learning_rate": 2.5986392119371297e-05, "loss": 0.4153, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.5431701398260799, "learning_rate": 2.5932406785780928e-05, "loss": 0.4218, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.5591475921571304, "learning_rate": 2.5878374016823987e-05, "loss": 0.4063, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.5494355391137801, "learning_rate": 2.5824294244545045e-05, "loss": 0.4232, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.5969474479306144, "learning_rate": 2.577016790136453e-05, "loss": 0.4026, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.5702017877090036, "learning_rate": 2.5715995420075225e-05, "loss": 0.412, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.5444011614221886, "learning_rate": 2.5661777233838864e-05, "loss": 0.4399, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.553583937367057, "learning_rate": 2.5607513776182616e-05, "loss": 0.4192, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.49676175934679034, "learning_rate": 2.5553205480995633e-05, "loss": 0.425, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.6602540438018416, "learning_rate": 2.5498852782525604e-05, "loss": 0.4299, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.5601604149134055, "learning_rate": 2.5444456115375252e-05, "loss": 0.4097, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.5608093119668346, "learning_rate": 2.539001591449889e-05, "loss": 0.4074, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.5920172848280629, "learning_rate": 2.53355326151989e-05, "loss": 0.3988, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.6026205236620187, "learning_rate": 2.5281006653122288e-05, "loss": 0.4101, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.5807331491234109, "learning_rate": 2.5226438464257217e-05, "loss": 0.4217, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.5768433716344316, "learning_rate": 2.5171828484929447e-05, "loss": 0.4313, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.5600136663491666, "learning_rate": 2.5117177151798934e-05, "loss": 0.4183, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.537455249148678, "learning_rate": 2.506248490185627e-05, "loss": 0.4207, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.6019331278845441, "learning_rate": 2.500775217241923e-05, "loss": 0.4185, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.590287138621481, "learning_rate": 2.4952979401129266e-05, "loss": 0.4003, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.5354448430578264, "learning_rate": 2.4898167025948e-05, "loss": 0.4169, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.5272954283618005, "learning_rate": 2.4843315485153703e-05, "loss": 0.3896, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.5946346184177935, "learning_rate": 2.4788425217337856e-05, "loss": 0.4051, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.5537036285168639, "learning_rate": 2.4733496661401572e-05, "loss": 0.4247, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.5598903463734191, "learning_rate": 2.4678530256552114e-05, "loss": 0.4244, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.5712883511657461, "learning_rate": 2.46235264422994e-05, "loss": 0.4134, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.5186398315244376, "learning_rate": 2.4568485658452452e-05, "loss": 0.4207, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.5533839382699945, "learning_rate": 2.451340834511592e-05, "loss": 0.4305, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.5608537352453759, "learning_rate": 2.4458294942686528e-05, "loss": 0.4077, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.5528577810812866, "learning_rate": 2.440314589184958e-05, "loss": 0.4186, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.55551523249644, "learning_rate": 2.434796163357541e-05, "loss": 0.3967, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.5343441170555479, "learning_rate": 2.429274260911588e-05, "loss": 0.4045, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.5610789148552126, "learning_rate": 2.423748926000084e-05, "loss": 0.415, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.5262688273844893, "learning_rate": 2.418220202803459e-05, "loss": 0.4268, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.5289823214613582, "learning_rate": 2.412688135529237e-05, "loss": 0.4144, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.5596266193639103, "learning_rate": 2.4071527684116807e-05, "loss": 0.4158, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.5487815814895048, "learning_rate": 2.4016141457114372e-05, "loss": 0.4118, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.5262973986945957, "learning_rate": 2.396072311715187e-05, "loss": 0.4062, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.5229161038635902, "learning_rate": 2.3905273107352863e-05, "loss": 0.4136, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.5493739336392, "learning_rate": 2.3849791871094157e-05, "loss": 0.4092, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.5670457068216017, "learning_rate": 2.379427985200223e-05, "loss": 0.4095, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.5570392676930948, "learning_rate": 2.373873749394972e-05, "loss": 0.4101, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.6057422604812176, "learning_rate": 2.3683165241051836e-05, "loss": 0.3911, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.5345340060000118, "learning_rate": 2.3627563537662823e-05, "loss": 0.4054, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.5856710286456437, "learning_rate": 2.3571932828372433e-05, "loss": 0.41, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.5394643246882046, "learning_rate": 2.351627355800233e-05, "loss": 0.4055, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.5951247541881352, "learning_rate": 2.346058617160256e-05, "loss": 0.3916, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.5917936331423641, "learning_rate": 2.3404871114447976e-05, "loss": 0.4238, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.561108448448626, "learning_rate": 2.334912883203469e-05, "loss": 0.4041, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.6801339347268799, "learning_rate": 2.3293359770076505e-05, "loss": 0.419, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.5843298118719709, "learning_rate": 2.323756437450136e-05, "loss": 0.4112, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.509515369254357, "learning_rate": 2.3181743091447754e-05, "loss": 0.4048, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.558760435048231, "learning_rate": 2.3125896367261164e-05, "loss": 0.4253, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.6268994855534641, "learning_rate": 2.307002464849052e-05, "loss": 0.4182, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.5307721098665438, "learning_rate": 2.30141283818846e-05, "loss": 0.4126, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.5848832878473545, "learning_rate": 2.2958208014388462e-05, "loss": 0.4129, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.506920463580823, "learning_rate": 2.2902263993139857e-05, "loss": 0.4197, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.5137648813854789, "learning_rate": 2.2846296765465708e-05, "loss": 0.4171, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.567653379869534, "learning_rate": 2.2790306778878465e-05, "loss": 0.4288, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.5274656008284585, "learning_rate": 2.273429448107257e-05, "loss": 0.4106, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.5201583919913898, "learning_rate": 2.2678260319920868e-05, "loss": 0.4023, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.5551079430900269, "learning_rate": 2.262220474347102e-05, "loss": 0.4195, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.5149613363772927, "learning_rate": 2.2566128199941918e-05, "loss": 0.4131, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.5955643731855732, "learning_rate": 2.2510031137720104e-05, "loss": 0.4138, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.5384708780570234, "learning_rate": 2.2453914005356206e-05, "loss": 0.4154, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.6035217379618496, "learning_rate": 2.2397777251561302e-05, "loss": 0.4108, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.5476787386037436, "learning_rate": 2.2341621325203393e-05, "loss": 0.4063, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.5861995389921529, "learning_rate": 2.2285446675303764e-05, "loss": 0.4055, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.5611087747359339, "learning_rate": 2.2229253751033423e-05, "loss": 0.4276, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.5582171352732349, "learning_rate": 2.2173043001709492e-05, "loss": 0.4255, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.609400216573271, "learning_rate": 2.2116814876791627e-05, "loss": 0.4381, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.5634685905478931, "learning_rate": 2.2060569825878413e-05, "loss": 0.4084, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.5839750380315291, "learning_rate": 2.2004308298703777e-05, "loss": 0.4137, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.5556595055987807, "learning_rate": 2.1948030745133396e-05, "loss": 0.4119, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.5882788023877261, "learning_rate": 2.1891737615161083e-05, "loss": 0.4314, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.5905788911109571, "learning_rate": 2.1835429358905218e-05, "loss": 0.4041, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.5519657893976723, "learning_rate": 2.17791064266051e-05, "loss": 0.4074, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.5656131581827305, "learning_rate": 2.172276926861741e-05, "loss": 0.4212, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.5730139247198306, "learning_rate": 2.166641833541255e-05, "loss": 0.4219, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.5412600459582052, "learning_rate": 2.161005407757109e-05, "loss": 0.4254, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.5737288055228502, "learning_rate": 2.155367694578013e-05, "loss": 0.4263, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.6186070990894746, "learning_rate": 2.1497287390829712e-05, "loss": 0.4199, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.5134417136818318, "learning_rate": 2.1440885863609208e-05, "loss": 0.4075, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.5198945259916401, "learning_rate": 2.1384472815103737e-05, "loss": 0.4192, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.5869322516285377, "learning_rate": 2.1328048696390534e-05, "loss": 0.4028, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.502943555822258, "learning_rate": 2.1271613958635342e-05, "loss": 0.4433, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.5590986954339373, "learning_rate": 2.1215169053088825e-05, "loss": 0.4195, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.5639078212707936, "learning_rate": 2.1158714431082937e-05, "loss": 0.4064, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.5869958589976921, "learning_rate": 2.110225054402733e-05, "loss": 0.4175, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.5525734080312026, "learning_rate": 2.1045777843405747e-05, "loss": 0.4077, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.5168316481265892, "learning_rate": 2.09892967807724e-05, "loss": 0.4188, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.5679056350925079, "learning_rate": 2.093280780774835e-05, "loss": 0.4146, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.5673058141714944, "learning_rate": 2.087631137601793e-05, "loss": 0.4111, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.4999483754203047, "learning_rate": 2.0819807937325104e-05, "loss": 0.4343, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.544384342382126, "learning_rate": 2.0763297943469847e-05, "loss": 0.4093, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.5918783404939835, "learning_rate": 2.070678184630458e-05, "loss": 0.4109, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.5332658982694729, "learning_rate": 2.06502600977305e-05, "loss": 0.4245, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.6510863716873653, "learning_rate": 2.0593733149694008e-05, "loss": 0.3995, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.5468977032352059, "learning_rate": 2.0537201454183074e-05, "loss": 0.4096, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.5074652089702238, "learning_rate": 2.0480665463223626e-05, "loss": 0.4285, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.5620484224451531, "learning_rate": 2.042412562887594e-05, "loss": 0.3953, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.5239320198552895, "learning_rate": 2.0367582403231033e-05, "loss": 0.4074, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.5278614865207584, "learning_rate": 2.0311036238407023e-05, "loss": 0.4276, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.5114473434442811, "learning_rate": 2.0254487586545534e-05, "loss": 0.4037, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.5911374992326314, "learning_rate": 2.0197936899808088e-05, "loss": 0.4017, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.5673042766486305, "learning_rate": 2.0141384630372466e-05, "loss": 0.4044, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.5114930571291353, "learning_rate": 2.0084831230429106e-05, "loss": 0.4224, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.5395486852122666, "learning_rate": 2.0028277152177492e-05, "loss": 0.4251, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.5368961369331252, "learning_rate": 1.9971722847822518e-05, "loss": 0.4037, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.5669865008049103, "learning_rate": 1.99151687695709e-05, "loss": 0.4194, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.54591849664388, "learning_rate": 1.9858615369627537e-05, "loss": 0.3978, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.5233561245382318, "learning_rate": 1.9802063100191916e-05, "loss": 0.4031, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.5485001595353541, "learning_rate": 1.974551241345447e-05, "loss": 0.4057, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.5827996701826516, "learning_rate": 1.9688963761592984e-05, "loss": 0.41, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.4902576841529174, "learning_rate": 1.963241759676897e-05, "loss": 0.4277, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.5283599980642347, "learning_rate": 1.9575874371124066e-05, "loss": 0.4063, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.5497567609042602, "learning_rate": 1.951933453677638e-05, "loss": 0.404, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.525463714614561, "learning_rate": 1.9462798545816932e-05, "loss": 0.4089, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.5655129839844872, "learning_rate": 1.9406266850305996e-05, "loss": 0.4199, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.546038652143601, "learning_rate": 1.9349739902269503e-05, "loss": 0.415, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.555770836101547, "learning_rate": 1.9293218153695425e-05, "loss": 0.4048, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.4815117616909592, "learning_rate": 1.9236702056530153e-05, "loss": 0.429, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.5203522749616513, "learning_rate": 1.9180192062674907e-05, "loss": 0.4075, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.5262300365493923, "learning_rate": 1.9123688623982076e-05, "loss": 0.4404, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.49926032153211997, "learning_rate": 1.906719219225165e-05, "loss": 0.4132, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.5479123010732232, "learning_rate": 1.9010703219227603e-05, "loss": 0.4115, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.5258263848000991, "learning_rate": 1.8954222156594256e-05, "loss": 0.3968, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.5317355615340121, "learning_rate": 1.8897749455972673e-05, "loss": 0.4021, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.49346955829806183, "learning_rate": 1.884128556891707e-05, "loss": 0.4073, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.5213928315569472, "learning_rate": 1.878483094691119e-05, "loss": 0.4119, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.5158938408397538, "learning_rate": 1.8728386041364664e-05, "loss": 0.41, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.5014857158039502, "learning_rate": 1.867195130360947e-05, "loss": 0.4091, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.5557850499131507, "learning_rate": 1.8615527184896263e-05, "loss": 0.4052, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.5651783520321481, "learning_rate": 1.8559114136390795e-05, "loss": 0.3973, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.526420240945488, "learning_rate": 1.8502712609170298e-05, "loss": 0.405, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.560278093717058, "learning_rate": 1.8446323054219876e-05, "loss": 0.4078, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.6231409710563632, "learning_rate": 1.838994592242891e-05, "loss": 0.4211, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.5341040585328277, "learning_rate": 1.8333581664587453e-05, "loss": 0.3883, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.5205311526864347, "learning_rate": 1.8277230731382593e-05, "loss": 0.4188, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.5881752429530339, "learning_rate": 1.82208935733949e-05, "loss": 0.4009, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.5155906535772997, "learning_rate": 1.8164570641094793e-05, "loss": 0.4095, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.5443587470680606, "learning_rate": 1.810826238483892e-05, "loss": 0.4323, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.5510337603220051, "learning_rate": 1.8051969254866608e-05, "loss": 0.4126, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.5246780111763931, "learning_rate": 1.7995691701296226e-05, "loss": 0.4014, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.5031585946198803, "learning_rate": 1.7939430174121593e-05, "loss": 0.4139, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.4982242184895272, "learning_rate": 1.788318512320838e-05, "loss": 0.432, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.5169958295101019, "learning_rate": 1.782695699829051e-05, "loss": 0.4011, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.49325130426096253, "learning_rate": 1.7770746248966587e-05, "loss": 0.3933, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.4899056413768574, "learning_rate": 1.7714553324696243e-05, "loss": 0.4076, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.5130627875264557, "learning_rate": 1.7658378674796614e-05, "loss": 0.4213, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.48890791213722695, "learning_rate": 1.76022227484387e-05, "loss": 0.4104, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.5684223467713597, "learning_rate": 1.7546085994643807e-05, "loss": 0.4074, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.5211041722215548, "learning_rate": 1.7489968862279902e-05, "loss": 0.3999, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.5150700733866234, "learning_rate": 1.743387180005809e-05, "loss": 0.4207, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.5248579573734307, "learning_rate": 1.737779525652899e-05, "loss": 0.403, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.52337698395338, "learning_rate": 1.732173968007914e-05, "loss": 0.4121, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.5473776935400807, "learning_rate": 1.7265705518927437e-05, "loss": 0.4083, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.5091346502380989, "learning_rate": 1.7209693221121542e-05, "loss": 0.4019, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.528783506617042, "learning_rate": 1.7153703234534302e-05, "loss": 0.4029, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.5478144910451143, "learning_rate": 1.709773600686015e-05, "loss": 0.4045, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.5280376637639361, "learning_rate": 1.7041791985611548e-05, "loss": 0.408, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.5640845480484411, "learning_rate": 1.69858716181154e-05, "loss": 0.3962, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.5395742564102702, "learning_rate": 1.692997535150948e-05, "loss": 0.4254, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.598743240096158, "learning_rate": 1.687410363273884e-05, "loss": 0.3964, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.4952829804400032, "learning_rate": 1.6818256908552257e-05, "loss": 0.3964, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.5434020868854197, "learning_rate": 1.6762435625498646e-05, "loss": 0.4204, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.5471649951647867, "learning_rate": 1.67066402299235e-05, "loss": 0.4025, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.5334554726946669, "learning_rate": 1.6650871167965313e-05, "loss": 0.403, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.5332142160841491, "learning_rate": 1.6595128885552028e-05, "loss": 0.4121, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.48962848664949793, "learning_rate": 1.653941382839745e-05, "loss": 0.4047, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.6974384756241755, "learning_rate": 1.6483726441997673e-05, "loss": 0.3257, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.5987947601876378, "learning_rate": 1.642806717162757e-05, "loss": 0.3066, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.7072545254111899, "learning_rate": 1.637243646233718e-05, "loss": 0.3009, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.8602601600128725, "learning_rate": 1.6316834758948174e-05, "loss": 0.2969, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.5863451531423722, "learning_rate": 1.6261262506050282e-05, "loss": 0.292, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.6336792307239625, "learning_rate": 1.620572014799777e-05, "loss": 0.3083, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.6342892982390702, "learning_rate": 1.6150208128905857e-05, "loss": 0.3001, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.6104229617832063, "learning_rate": 1.6094726892647147e-05, "loss": 0.2959, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.5910032904211096, "learning_rate": 1.6039276882848135e-05, "loss": 0.2993, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.58816992219949, "learning_rate": 1.5983858542885635e-05, "loss": 0.308, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.6168737575554458, "learning_rate": 1.5928472315883203e-05, "loss": 0.3085, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.6075120188082367, "learning_rate": 1.5873118644707633e-05, "loss": 0.3051, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.5766111577004072, "learning_rate": 1.5817797971965413e-05, "loss": 0.3136, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.6210679274924986, "learning_rate": 1.576251073999917e-05, "loss": 0.3187, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.6091052169640913, "learning_rate": 1.5707257390884126e-05, "loss": 0.31, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.5960057180590114, "learning_rate": 1.5652038366424595e-05, "loss": 0.2999, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.5991848505464281, "learning_rate": 1.5596854108150424e-05, "loss": 0.2991, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.5919180555722081, "learning_rate": 1.5541705057313476e-05, "loss": 0.3093, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.5922628550293269, "learning_rate": 1.5486591654884086e-05, "loss": 0.2994, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.6037994032566213, "learning_rate": 1.543151434154755e-05, "loss": 0.3209, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.5722296035386683, "learning_rate": 1.5376473557700615e-05, "loss": 0.2995, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.5731211346972328, "learning_rate": 1.5321469743447893e-05, "loss": 0.2983, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.6001082934464049, "learning_rate": 1.5266503338598434e-05, "loss": 0.3081, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.5496883082083545, "learning_rate": 1.5211574782662149e-05, "loss": 0.3018, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.5762929044508638, "learning_rate": 1.5156684514846307e-05, "loss": 0.2997, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.5397453883211664, "learning_rate": 1.5101832974052012e-05, "loss": 0.3046, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.6099217578228914, "learning_rate": 1.5047020598870737e-05, "loss": 0.3035, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.5716625565707337, "learning_rate": 1.4992247827580778e-05, "loss": 0.3085, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.6260683925829237, "learning_rate": 1.493751509814374e-05, "loss": 0.2889, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.5343990802772826, "learning_rate": 1.4882822848201073e-05, "loss": 0.3186, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.5669734133507175, "learning_rate": 1.4828171515070553e-05, "loss": 0.3252, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.5796911579587739, "learning_rate": 1.4773561535742793e-05, "loss": 0.3193, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.5506471601776313, "learning_rate": 1.4718993346877715e-05, "loss": 0.3035, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.5868048758442775, "learning_rate": 1.466446738480111e-05, "loss": 0.3065, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.547934186430557, "learning_rate": 1.460998408550112e-05, "loss": 0.3007, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.5937500951338958, "learning_rate": 1.4555543884624751e-05, "loss": 0.2848, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.5705473314936076, "learning_rate": 1.4501147217474402e-05, "loss": 0.2829, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.5875889988835775, "learning_rate": 1.444679451900437e-05, "loss": 0.3005, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.5647130297636731, "learning_rate": 1.4392486223817397e-05, "loss": 0.3058, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.5417904211710995, "learning_rate": 1.4338222766161143e-05, "loss": 0.3148, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.5595098019241868, "learning_rate": 1.4284004579924777e-05, "loss": 0.3047, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.5598225257132502, "learning_rate": 1.4229832098635479e-05, "loss": 0.3219, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.5353511358419676, "learning_rate": 1.4175705755454963e-05, "loss": 0.3138, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.5617370876973737, "learning_rate": 1.412162598317602e-05, "loss": 0.3132, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.5807123741971694, "learning_rate": 1.406759321421907e-05, "loss": 0.3077, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.5351684816612219, "learning_rate": 1.401360788062871e-05, "loss": 0.3027, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.5594224068568302, "learning_rate": 1.3959670414070204e-05, "loss": 0.3103, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.5671751997492219, "learning_rate": 1.3905781245826108e-05, "loss": 0.2816, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.5530098717089519, "learning_rate": 1.3851940806792778e-05, "loss": 0.3054, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.5456110916361957, "learning_rate": 1.379814952747693e-05, "loss": 0.2882, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.5506183318890864, "learning_rate": 1.3744407837992193e-05, "loss": 0.3021, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.5595057368637794, "learning_rate": 1.3690716168055692e-05, "loss": 0.2986, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.5357093652993661, "learning_rate": 1.363707494698459e-05, "loss": 0.3164, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.6124168011369926, "learning_rate": 1.358348460369265e-05, "loss": 0.2956, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.5752290707833718, "learning_rate": 1.352994556668684e-05, "loss": 0.3034, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.5670954350334986, "learning_rate": 1.3476458264063865e-05, "loss": 0.2912, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.5973452616304806, "learning_rate": 1.342302312350678e-05, "loss": 0.3157, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.5550055898521284, "learning_rate": 1.3369640572281537e-05, "loss": 0.305, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.595865814855273, "learning_rate": 1.3316311037233596e-05, "loss": 0.2675, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.5686327153173651, "learning_rate": 1.326303494478451e-05, "loss": 0.3199, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.568800786415153, "learning_rate": 1.3209812720928472e-05, "loss": 0.2914, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.6041375146287484, "learning_rate": 1.315664479122898e-05, "loss": 0.2891, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.5827965524687604, "learning_rate": 1.3103531580815378e-05, "loss": 0.3056, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.5535826117765119, "learning_rate": 1.3050473514379488e-05, "loss": 0.2983, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.5703208954568653, "learning_rate": 1.2997471016172188e-05, "loss": 0.3052, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.5489147217444935, "learning_rate": 1.2944524510000042e-05, "loss": 0.3016, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.5624368659236274, "learning_rate": 1.2891634419221908e-05, "loss": 0.3009, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.591880584554651, "learning_rate": 1.2838801166745545e-05, "loss": 0.3073, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.5853790735856167, "learning_rate": 1.2786025175024216e-05, "loss": 0.2996, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.5504630502897792, "learning_rate": 1.2733306866053357e-05, "loss": 0.3258, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.5406169322501562, "learning_rate": 1.2680646661367163e-05, "loss": 0.3056, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.545574408275424, "learning_rate": 1.2628044982035219e-05, "loss": 0.301, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.5651087126561574, "learning_rate": 1.2575502248659155e-05, "loss": 0.2932, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.5400084278518505, "learning_rate": 1.2523018881369269e-05, "loss": 0.3048, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.5428166236926181, "learning_rate": 1.2470595299821176e-05, "loss": 0.3116, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.5933123264587016, "learning_rate": 1.2418231923192416e-05, "loss": 0.3094, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.5890999173007042, "learning_rate": 1.2365929170179165e-05, "loss": 0.2921, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.5305834765165256, "learning_rate": 1.2313687458992848e-05, "loss": 0.3026, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.6020122559073449, "learning_rate": 1.2261507207356785e-05, "loss": 0.3013, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.563002591839129, "learning_rate": 1.220938883250288e-05, "loss": 0.311, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.5310442232398886, "learning_rate": 1.215733275116827e-05, "loss": 0.3097, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.5737997537116202, "learning_rate": 1.2105339379592005e-05, "loss": 0.2869, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.6044801287785817, "learning_rate": 1.2053409133511681e-05, "loss": 0.307, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.5585140633129132, "learning_rate": 1.2001542428160173e-05, "loss": 0.2898, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.5467746690823339, "learning_rate": 1.1949739678262278e-05, "loss": 0.3056, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.5451286137883451, "learning_rate": 1.189800129803139e-05, "loss": 0.2918, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.5894237787548481, "learning_rate": 1.1846327701166228e-05, "loss": 0.2877, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.5485814275497823, "learning_rate": 1.1794719300847493e-05, "loss": 0.317, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.5732866404022354, "learning_rate": 1.1743176509734582e-05, "loss": 0.3172, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.5757481511322409, "learning_rate": 1.1691699739962275e-05, "loss": 0.3315, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.5596226417084674, "learning_rate": 1.1640289403137456e-05, "loss": 0.3139, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.5327432021320494, "learning_rate": 1.1588945910335802e-05, "loss": 0.3061, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.5871325401039846, "learning_rate": 1.1537669672098517e-05, "loss": 0.3017, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.566332736859938, "learning_rate": 1.1486461098429036e-05, "loss": 0.3001, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.5585333547755923, "learning_rate": 1.1435320598789747e-05, "loss": 0.3019, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.5757092566997708, "learning_rate": 1.1384248582098736e-05, "loss": 0.32, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.5629276496074497, "learning_rate": 1.1333245456726467e-05, "loss": 0.3064, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.5463226799093716, "learning_rate": 1.128231163049258e-05, "loss": 0.2956, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.5936698337006796, "learning_rate": 1.123144751066259e-05, "loss": 0.2854, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.5910519406238626, "learning_rate": 1.1180653503944657e-05, "loss": 0.2885, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.5499332485790606, "learning_rate": 1.1129930016486287e-05, "loss": 0.2855, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.5803102126985007, "learning_rate": 1.107927745387114e-05, "loss": 0.2864, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.5768284923037702, "learning_rate": 1.1028696221115766e-05, "loss": 0.3, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.5980356056229533, "learning_rate": 1.0978186722666341e-05, "loss": 0.3111, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.540226235439034, "learning_rate": 1.0927749362395475e-05, "loss": 0.2973, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.5727031322007046, "learning_rate": 1.0877384543598954e-05, "loss": 0.2996, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.5990044929115088, "learning_rate": 1.0827092668992529e-05, "loss": 0.3176, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.5559993729582065, "learning_rate": 1.077687414070869e-05, "loss": 0.3026, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.5246356972552049, "learning_rate": 1.0726729360293451e-05, "loss": 0.2983, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.5765981459411338, "learning_rate": 1.0676658728703147e-05, "loss": 0.3101, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.5682848954986895, "learning_rate": 1.0626662646301198e-05, "loss": 0.3061, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.5871036262859856, "learning_rate": 1.0576741512854958e-05, "loss": 0.3101, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.5360077006188831, "learning_rate": 1.052689572753247e-05, "loss": 0.299, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.5950286101122568, "learning_rate": 1.0477125688899328e-05, "loss": 0.2916, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.6031047254184843, "learning_rate": 1.0427431794915406e-05, "loss": 0.2834, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.5325434710738027, "learning_rate": 1.0377814442931769e-05, "loss": 0.2964, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.532007864358807, "learning_rate": 1.0328274029687439e-05, "loss": 0.298, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.5496796794772829, "learning_rate": 1.0278810951306253e-05, "loss": 0.308, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.5260728841881505, "learning_rate": 1.0229425603293647e-05, "loss": 0.3143, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.5686527102016571, "learning_rate": 1.0180118380533558e-05, "loss": 0.2928, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.5086657598412446, "learning_rate": 1.0130889677285225e-05, "loss": 0.3109, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.5376461062290866, "learning_rate": 1.008173988718005e-05, "loss": 0.2973, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.5226020930678482, "learning_rate": 1.0032669403218439e-05, "loss": 0.2925, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.5237004417984246, "learning_rate": 9.983678617766677e-06, "loss": 0.2866, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.5496884126914414, "learning_rate": 9.934767922553788e-06, "loss": 0.2994, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.5386925590206686, "learning_rate": 9.885937708668371e-06, "loss": 0.2948, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.5339628275108307, "learning_rate": 9.837188366555524e-06, "loss": 0.3135, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.5439299363299449, "learning_rate": 9.788520286013691e-06, "loss": 0.3064, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.5175488271880737, "learning_rate": 9.739933856191537e-06, "loss": 0.2953, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.537330007533394, "learning_rate": 9.691429465584866e-06, "loss": 0.2945, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.5491324868530012, "learning_rate": 9.643007502033492e-06, "loss": 0.2977, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.5252336092358194, "learning_rate": 9.594668352718152e-06, "loss": 0.3129, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.5240315561079973, "learning_rate": 9.546412404157383e-06, "loss": 0.2849, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.5588533762192751, "learning_rate": 9.498240042204471e-06, "loss": 0.3021, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.5444724663178453, "learning_rate": 9.450151652044339e-06, "loss": 0.3092, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.5435947383590659, "learning_rate": 9.402147618190472e-06, "loss": 0.3095, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.5333380292811543, "learning_rate": 9.354228324481841e-06, "loss": 0.2929, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.5580574467432348, "learning_rate": 9.306394154079852e-06, "loss": 0.3019, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.5382682873981546, "learning_rate": 9.258645489465254e-06, "loss": 0.3018, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.5691476356917451, "learning_rate": 9.21098271243509e-06, "loss": 0.2891, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.5168331543624157, "learning_rate": 9.163406204099659e-06, "loss": 0.293, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.5358675680079229, "learning_rate": 9.115916344879452e-06, "loss": 0.3064, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.5572654575509594, "learning_rate": 9.068513514502126e-06, "loss": 0.295, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.5182511760784784, "learning_rate": 9.021198091999439e-06, "loss": 0.3003, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.5494249091409579, "learning_rate": 8.973970455704251e-06, "loss": 0.3023, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.5386474135020246, "learning_rate": 8.926830983247495e-06, "loss": 0.2896, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.5485387217390991, "learning_rate": 8.879780051555116e-06, "loss": 0.3035, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.5402582420235919, "learning_rate": 8.83281803684512e-06, "loss": 0.2851, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.5230652432675661, "learning_rate": 8.785945314624532e-06, "loss": 0.3022, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.5644387286412308, "learning_rate": 8.739162259686385e-06, "loss": 0.2876, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.546039023885678, "learning_rate": 8.692469246106734e-06, "loss": 0.2992, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.5183027389537767, "learning_rate": 8.645866647241677e-06, "loss": 0.3011, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.5169657977133221, "learning_rate": 8.599354835724348e-06, "loss": 0.297, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.5489776034223502, "learning_rate": 8.552934183461958e-06, "loss": 0.2874, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.5367495640885236, "learning_rate": 8.506605061632805e-06, "loss": 0.2965, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.5207423530025892, "learning_rate": 8.460367840683308e-06, "loss": 0.3092, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.5328098062404052, "learning_rate": 8.414222890325065e-06, "loss": 0.3093, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.5468661931754479, "learning_rate": 8.368170579531855e-06, "loss": 0.3121, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.5493335092386947, "learning_rate": 8.322211276536733e-06, "loss": 0.2913, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.4947011903724158, "learning_rate": 8.27634534882907e-06, "loss": 0.3013, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.5864215078725943, "learning_rate": 8.230573163151585e-06, "loss": 0.274, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.5244080442834553, "learning_rate": 8.184895085497466e-06, "loss": 0.2975, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.5677122037726271, "learning_rate": 8.139311481107401e-06, "loss": 0.2905, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.5383613453111856, "learning_rate": 8.093822714466686e-06, "loss": 0.3066, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.5233994953343463, "learning_rate": 8.048429149302271e-06, "loss": 0.2993, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.5120193077654385, "learning_rate": 8.003131148579902e-06, "loss": 0.3187, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.5334378840995467, "learning_rate": 7.957929074501182e-06, "loss": 0.3161, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.5601909303842586, "learning_rate": 7.912823288500695e-06, "loss": 0.2818, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.5020930161680653, "learning_rate": 7.867814151243102e-06, "loss": 0.2907, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.5247409084248283, "learning_rate": 7.822902022620267e-06, "loss": 0.289, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.5212528281974577, "learning_rate": 7.778087261748377e-06, "loss": 0.3037, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.5076857578884841, "learning_rate": 7.733370226965056e-06, "loss": 0.2964, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.5108671377574414, "learning_rate": 7.688751275826527e-06, "loss": 0.3157, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.5440960240483932, "learning_rate": 7.644230765104735e-06, "loss": 0.2946, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.5115739000849975, "learning_rate": 7.599809050784502e-06, "loss": 0.3005, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.5244761150381089, "learning_rate": 7.555486488060661e-06, "loss": 0.2982, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.5198372049229264, "learning_rate": 7.511263431335249e-06, "loss": 0.3078, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.5456222961431827, "learning_rate": 7.467140234214656e-06, "loss": 0.2834, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.5231602430609625, "learning_rate": 7.423117249506777e-06, "loss": 0.2968, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.5112449566133133, "learning_rate": 7.379194829218231e-06, "loss": 0.2987, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.5371871380749774, "learning_rate": 7.335373324551518e-06, "loss": 0.2899, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.5361214671879568, "learning_rate": 7.291653085902224e-06, "loss": 0.2809, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.5460227684079999, "learning_rate": 7.248034462856213e-06, "loss": 0.2889, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.5331076226987133, "learning_rate": 7.20451780418683e-06, "loss": 0.3008, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.5373001984046409, "learning_rate": 7.161103457852128e-06, "loss": 0.2827, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.535073136237986, "learning_rate": 7.117791770992046e-06, "loss": 0.2793, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.49578493197046886, "learning_rate": 7.074583089925688e-06, "loss": 0.2992, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.5276505647398793, "learning_rate": 7.0314777601485155e-06, "loss": 0.2888, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.4906422946688334, "learning_rate": 6.988476126329604e-06, "loss": 0.294, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.551857934041659, "learning_rate": 6.945578532308857e-06, "loss": 0.2815, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.5305220408209458, "learning_rate": 6.902785321094301e-06, "loss": 0.3127, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.5108405191187335, "learning_rate": 6.8600968348593115e-06, "loss": 0.2878, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.5300394845988655, "learning_rate": 6.817513414939892e-06, "loss": 0.2977, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.505755124949392, "learning_rate": 6.775035401831924e-06, "loss": 0.3025, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.4900831590999215, "learning_rate": 6.732663135188473e-06, "loss": 0.3066, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.5505144020403886, "learning_rate": 6.690396953817055e-06, "loss": 0.2954, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.5206955199323959, "learning_rate": 6.648237195676927e-06, "loss": 0.2946, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.5388951357379934, "learning_rate": 6.606184197876395e-06, "loss": 0.2783, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.5127890503647589, "learning_rate": 6.564238296670109e-06, "loss": 0.289, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.5293788245807258, "learning_rate": 6.52239982745638e-06, "loss": 0.2965, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.5569064959838476, "learning_rate": 6.480669124774484e-06, "loss": 0.2852, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.5342064835881455, "learning_rate": 6.439046522302013e-06, "loss": 0.2799, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.5370506944003909, "learning_rate": 6.397532352852191e-06, "loss": 0.2936, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.5442237908182502, "learning_rate": 6.356126948371202e-06, "loss": 0.2878, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.5234355069770638, "learning_rate": 6.314830639935559e-06, "loss": 0.2816, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.5155555055083852, "learning_rate": 6.273643757749448e-06, "loss": 0.3119, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.530744173176552, "learning_rate": 6.2325666311420856e-06, "loss": 0.2708, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.5283545570469664, "learning_rate": 6.1915995885650675e-06, "loss": 0.2756, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.5151406040135152, "learning_rate": 6.150742957589784e-06, "loss": 0.2977, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.5213892149499424, "learning_rate": 6.109997064904774e-06, "loss": 0.2882, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.5104643201937172, "learning_rate": 6.069362236313092e-06, "loss": 0.2932, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.5302303587562306, "learning_rate": 6.0288387967297565e-06, "loss": 0.2903, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.5363218564121023, "learning_rate": 5.988427070179108e-06, "loss": 0.2911, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.5024090096559642, "learning_rate": 5.948127379792234e-06, "loss": 0.3105, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.5213779435030498, "learning_rate": 5.90794004780439e-06, "loss": 0.2772, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.5500127251568424, "learning_rate": 5.867865395552405e-06, "loss": 0.2859, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.5001763876885574, "learning_rate": 5.8279037434721364e-06, "loss": 0.3032, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.513646345753513, "learning_rate": 5.788055411095892e-06, "loss": 0.3017, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.5255017136964064, "learning_rate": 5.7483207170498625e-06, "loss": 0.2869, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.5159165935203409, "learning_rate": 5.708699979051613e-06, "loss": 0.2957, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.4861534411084183, "learning_rate": 5.66919351390751e-06, "loss": 0.3131, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.527924004418882, "learning_rate": 5.629801637510188e-06, "loss": 0.2949, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.4734949295295591, "learning_rate": 5.590524664836043e-06, "loss": 0.3061, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.521837089401299, "learning_rate": 5.551362909942708e-06, "loss": 0.2831, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.48396658882186927, "learning_rate": 5.51231668596653e-06, "loss": 0.3034, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.5084367762102245, "learning_rate": 5.47338630512007e-06, "loss": 0.2878, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.5411584577555474, "learning_rate": 5.434572078689617e-06, "loss": 0.2836, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.5199807733961808, "learning_rate": 5.395874317032694e-06, "loss": 0.294, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.5118561191046413, "learning_rate": 5.357293329575573e-06, "loss": 0.2849, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.5117323908755728, "learning_rate": 5.318829424810797e-06, "loss": 0.2934, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.5077858877338641, "learning_rate": 5.280482910294728e-06, "loss": 0.2906, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.49390867720388953, "learning_rate": 5.242254092645078e-06, "loss": 0.2883, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.6270028239567024, "learning_rate": 5.2041432775384445e-06, "loss": 0.306, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.5162903117060046, "learning_rate": 5.166150769707892e-06, "loss": 0.2843, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.5149520338502193, "learning_rate": 5.128276872940503e-06, "loss": 0.2819, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.5151041293505576, "learning_rate": 5.090521890074953e-06, "loss": 0.2896, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.5104851793669439, "learning_rate": 5.0528861229990675e-06, "loss": 0.2899, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.49992855259588326, "learning_rate": 5.015369872647442e-06, "loss": 0.2887, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.5274602594711753, "learning_rate": 4.9779734389990195e-06, "loss": 0.3267, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.5246331768879376, "learning_rate": 4.940697121074675e-06, "loss": 0.2744, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.49607243899702863, "learning_rate": 4.903541216934864e-06, "loss": 0.3073, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.5220720786171424, "learning_rate": 4.8665060236772e-06, "loss": 0.3029, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.49411523066375646, "learning_rate": 4.829591837434102e-06, "loss": 0.2986, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.5131168289116769, "learning_rate": 4.792798953370424e-06, "loss": 0.2802, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.48591323085346744, "learning_rate": 4.756127665681083e-06, "loss": 0.3075, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.5038788827358889, "learning_rate": 4.719578267588725e-06, "loss": 0.2874, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.5157667883879593, "learning_rate": 4.6831510513413525e-06, "loss": 0.2798, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.7358908642177457, "learning_rate": 4.6468463082100176e-06, "loss": 0.1873, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.5988991932099618, "learning_rate": 4.610664328486485e-06, "loss": 0.2024, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.5062641546255484, "learning_rate": 4.5746054014809e-06, "loss": 0.2225, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.5940630504989628, "learning_rate": 4.5386698155194766e-06, "loss": 0.1997, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.6816464860657734, "learning_rate": 4.502857857942204e-06, "loss": 0.1906, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.7661272991972101, "learning_rate": 4.467169815100549e-06, "loss": 0.1867, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.7358591909845994, "learning_rate": 4.431605972355137e-06, "loss": 0.197, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.6053267384937854, "learning_rate": 4.396166614073516e-06, "loss": 0.2032, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.615568637858542, "learning_rate": 4.360852023627846e-06, "loss": 0.1991, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.6229672828532007, "learning_rate": 4.325662483392656e-06, "loss": 0.2056, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.617659661684811, "learning_rate": 4.29059827474257e-06, "loss": 0.1725, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.6035906027678067, "learning_rate": 4.255659678050063e-06, "loss": 0.2166, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.5608019163990068, "learning_rate": 4.22084697268323e-06, "loss": 0.1996, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.5310526266961598, "learning_rate": 4.186160437003535e-06, "loss": 0.205, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.5494305917463015, "learning_rate": 4.151600348363582e-06, "loss": 0.2012, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.561306554433343, "learning_rate": 4.11716698310493e-06, "loss": 0.2096, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.5747654876411964, "learning_rate": 4.082860616555848e-06, "loss": 0.1884, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.5812004785173805, "learning_rate": 4.048681523029125e-06, "loss": 0.1878, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.5914208064603461, "learning_rate": 4.014629975819882e-06, "loss": 0.1913, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.5422720162762901, "learning_rate": 3.9807062472033855e-06, "loss": 0.2188, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.5463113459751971, "learning_rate": 3.94691060843287e-06, "loss": 0.2079, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.5299225749035101, "learning_rate": 3.913243329737353e-06, "loss": 0.1966, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.5300804904337789, "learning_rate": 3.879704680319503e-06, "loss": 0.1855, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.5435740552456323, "learning_rate": 3.846294928353471e-06, "loss": 0.199, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.5348940242642849, "learning_rate": 3.8130143409827345e-06, "loss": 0.1885, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.5610672611130444, "learning_rate": 3.7798631843179887e-06, "loss": 0.1828, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.5467816355371786, "learning_rate": 3.7468417234349973e-06, "loss": 0.2043, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.535876865620209, "learning_rate": 3.7139502223724823e-06, "loss": 0.1951, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.559960508825557, "learning_rate": 3.6811889441300095e-06, "loss": 0.216, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.564015142888622, "learning_rate": 3.648558150665886e-06, "loss": 0.209, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.5312207637065001, "learning_rate": 3.616058102895075e-06, "loss": 0.1934, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.541922057111471, "learning_rate": 3.583689060687079e-06, "loss": 0.2084, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.5200470513341865, "learning_rate": 3.5514512828639023e-06, "loss": 0.1712, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.5195598485917545, "learning_rate": 3.51934502719796e-06, "loss": 0.1971, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.511079187756824, "learning_rate": 3.4873705504100185e-06, "loss": 0.2069, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.5308891403339457, "learning_rate": 3.4555281081671345e-06, "loss": 0.2165, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.536456898577737, "learning_rate": 3.4238179550806326e-06, "loss": 0.2127, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.5200038904366858, "learning_rate": 3.3922403447040497e-06, "loss": 0.1963, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.5344643465579512, "learning_rate": 3.3607955295311247e-06, "loss": 0.1797, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.48700800959947543, "learning_rate": 3.32948376099375e-06, "loss": 0.215, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.5569414157195417, "learning_rate": 3.2983052894599976e-06, "loss": 0.1815, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.5597444804070619, "learning_rate": 3.2672603642320945e-06, "loss": 0.1802, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.520983176957298, "learning_rate": 3.236349233544438e-06, "loss": 0.2005, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.5201207537852804, "learning_rate": 3.205572144561604e-06, "loss": 0.1968, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.5210857192045772, "learning_rate": 3.174929343376374e-06, "loss": 0.1921, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.518167695190471, "learning_rate": 3.1444210750077777e-06, "loss": 0.2108, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.5224702730278847, "learning_rate": 3.1140475833991046e-06, "loss": 0.2004, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.5578246410886161, "learning_rate": 3.0838091114159895e-06, "loss": 0.1937, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.54645255211138, "learning_rate": 3.0537059008444524e-06, "loss": 0.2004, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.5123692636956289, "learning_rate": 3.0237381923889563e-06, "loss": 0.1945, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.5153149504787602, "learning_rate": 2.9939062256704997e-06, "loss": 0.2163, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.5148015750901104, "learning_rate": 2.964210239224696e-06, "loss": 0.2126, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.5380379244318864, "learning_rate": 2.934650470499869e-06, "loss": 0.1881, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.5431574455774913, "learning_rate": 2.905227155855128e-06, "loss": 0.198, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.5536682403899323, "learning_rate": 2.875940530558519e-06, "loss": 0.1877, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.5347790937725014, "learning_rate": 2.8467908287851154e-06, "loss": 0.1935, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.5712448363863464, "learning_rate": 2.8177782836151603e-06, "loss": 0.2025, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.5538568200444861, "learning_rate": 2.7889031270321874e-06, "loss": 0.1959, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.521901748479801, "learning_rate": 2.760165589921184e-06, "loss": 0.1938, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.5145134471578314, "learning_rate": 2.7315659020667305e-06, "loss": 0.2131, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.5275743260212382, "learning_rate": 2.703104292151164e-06, "loss": 0.2007, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.5343010707566469, "learning_rate": 2.6747809877527607e-06, "loss": 0.1847, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.5098976553529073, "learning_rate": 2.6465962153439082e-06, "loss": 0.1873, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.5094268965496342, "learning_rate": 2.618550200289303e-06, "loss": 0.2005, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.5352492065673793, "learning_rate": 2.59064316684412e-06, "loss": 0.1957, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.5478937288778366, "learning_rate": 2.562875338152264e-06, "loss": 0.1853, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.5170024594052954, "learning_rate": 2.5352469362445552e-06, "loss": 0.2006, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.5077328391491134, "learning_rate": 2.5077581820369523e-06, "loss": 0.1934, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.5548342872087795, "learning_rate": 2.480409295328803e-06, "loss": 0.1935, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.539359773077617, "learning_rate": 2.45320049480108e-06, "loss": 0.1986, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.5220821278821485, "learning_rate": 2.4261319980146293e-06, "loss": 0.1801, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.5333194855353087, "learning_rate": 2.399204021408421e-06, "loss": 0.2047, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.5374042536532134, "learning_rate": 2.3724167802978395e-06, "loss": 0.1874, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.5273324502585792, "learning_rate": 2.3457704888729625e-06, "loss": 0.1891, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.5141678498878423, "learning_rate": 2.3192653601968162e-06, "loss": 0.191, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.5379819409646915, "learning_rate": 2.2929016062037057e-06, "loss": 0.1955, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.5468953584789709, "learning_rate": 2.2666794376975055e-06, "loss": 0.2005, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.5885429109201585, "learning_rate": 2.24059906434998e-06, "loss": 0.1729, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.5115578390733684, "learning_rate": 2.214660694699091e-06, "loss": 0.2003, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.5372811064153706, "learning_rate": 2.188864536147355e-06, "loss": 0.1985, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.5209099561833018, "learning_rate": 2.1632107949601757e-06, "loss": 0.1972, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.512185399384256, "learning_rate": 2.137699676264171e-06, "loss": 0.2154, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.5166951391128699, "learning_rate": 2.1123313840455738e-06, "loss": 0.1909, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.5392829698421756, "learning_rate": 2.08710612114857e-06, "loss": 0.2043, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.5413274616364513, "learning_rate": 2.0620240892736953e-06, "loss": 0.2009, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.5291987451561984, "learning_rate": 2.0370854889762e-06, "loss": 0.1914, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.5219642585784041, "learning_rate": 2.0122905196644726e-06, "loss": 0.2011, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.5026907885219362, "learning_rate": 1.987639379598427e-06, "loss": 0.198, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.5307322232556256, "learning_rate": 1.963132265887919e-06, "loss": 0.1943, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.5206788457195886, "learning_rate": 1.9387693744911784e-06, "loss": 0.1989, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.5031919063626333, "learning_rate": 1.9145509002132368e-06, "loss": 0.1841, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.5083554542955797, "learning_rate": 1.8904770367043723e-06, "loss": 0.2189, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 1.695948180722877, "learning_rate": 1.8665479764585504e-06, "loss": 0.2147, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.51870858670738, "learning_rate": 1.8427639108118977e-06, "loss": 0.1747, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.5193095623412226, "learning_rate": 1.8191250299411755e-06, "loss": 0.2035, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.5152270467043659, "learning_rate": 1.7956315228622446e-06, "loss": 0.2165, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.5385695488825982, "learning_rate": 1.7722835774285553e-06, "loss": 0.1926, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.5073611601819851, "learning_rate": 1.7490813803296624e-06, "loss": 0.1924, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.5336604056785432, "learning_rate": 1.726025117089718e-06, "loss": 0.178, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.550148008408343, "learning_rate": 1.70311497206598e-06, "loss": 0.175, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.5132386820334816, "learning_rate": 1.6803511284473638e-06, "loss": 0.19, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.5104647787271329, "learning_rate": 1.6577337682529538e-06, "loss": 0.1892, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.5260221326913044, "learning_rate": 1.6352630723305617e-06, "loss": 0.1874, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.5396989776972649, "learning_rate": 1.612939220355272e-06, "loss": 0.1859, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.5628795417583453, "learning_rate": 1.5907623908280112e-06, "loss": 0.2064, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.5240600080360677, "learning_rate": 1.568732761074121e-06, "loss": 0.2082, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.531689905635302, "learning_rate": 1.5468505072419237e-06, "loss": 0.2233, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.5115826926007526, "learning_rate": 1.5251158043013448e-06, "loss": 0.1977, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.5245631076280565, "learning_rate": 1.5035288260424885e-06, "loss": 0.187, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.5331132699072215, "learning_rate": 1.4820897450742623e-06, "loss": 0.1806, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.5513591313190552, "learning_rate": 1.4607987328229767e-06, "loss": 0.1848, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.5264129672987775, "learning_rate": 1.4396559595310056e-06, "loss": 0.1983, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.49796920700639774, "learning_rate": 1.4186615942553973e-06, "loss": 0.1859, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.5084036987076319, "learning_rate": 1.3978158048665424e-06, "loss": 0.1843, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.5390889715000515, "learning_rate": 1.3771187580468115e-06, "loss": 0.1994, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.518566665634868, "learning_rate": 1.3565706192892392e-06, "loss": 0.1982, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.5300768431291877, "learning_rate": 1.3361715528961993e-06, "loss": 0.1918, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.5188515545959059, "learning_rate": 1.3159217219780817e-06, "loss": 0.1906, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.4950401851494459, "learning_rate": 1.2958212884519949e-06, "loss": 0.1989, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.5277932222121996, "learning_rate": 1.2758704130404675e-06, "loss": 0.1893, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.5192516446878147, "learning_rate": 1.2560692552701738e-06, "loss": 0.195, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.5105960663952002, "learning_rate": 1.2364179734706382e-06, "loss": 0.1912, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.5042758288065278, "learning_rate": 1.2169167247729852e-06, "loss": 0.2016, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.5046677293938447, "learning_rate": 1.1975656651086864e-06, "loss": 0.1966, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.5278083850813046, "learning_rate": 1.1783649492082926e-06, "loss": 0.1839, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.5577766986570938, "learning_rate": 1.1593147306002183e-06, "loss": 0.2092, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.531792697826876, "learning_rate": 1.140415161609505e-06, "loss": 0.2301, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.5088127540613223, "learning_rate": 1.121666393356604e-06, "loss": 0.202, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.5096280347957806, "learning_rate": 1.1030685757561632e-06, "loss": 0.1869, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.519774592936214, "learning_rate": 1.0846218575158373e-06, "loss": 0.1906, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.514441960558173, "learning_rate": 1.066326386135097e-06, "loss": 0.2008, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.5172712039599606, "learning_rate": 1.0481823079040398e-06, "loss": 0.1845, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.5180756161560008, "learning_rate": 1.0301897679022344e-06, "loss": 0.1954, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.5128111051144318, "learning_rate": 1.0123489099975491e-06, "loss": 0.1997, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.5193698847093124, "learning_rate": 9.9465987684501e-07, "loss": 0.1808, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.5229904912762385, "learning_rate": 9.771228098856534e-07, "loss": 0.1953, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.5203963752326755, "learning_rate": 9.597378493454013e-07, "loss": 0.1958, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.5261200811420512, "learning_rate": 9.425051342339353e-07, "loss": 0.2007, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.5150019464328301, "learning_rate": 9.254248023435864e-07, "loss": 0.1659, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.4977872480492143, "learning_rate": 9.084969902482288e-07, "loss": 0.212, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.5124947992682255, "learning_rate": 8.917218333021993e-07, "loss": 0.1856, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.5348018803379608, "learning_rate": 8.750994656392109e-07, "loss": 0.1907, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.5321938435808315, "learning_rate": 8.58630020171265e-07, "loss": 0.1886, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.5225686365472718, "learning_rate": 8.423136285876099e-07, "loss": 0.1876, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.5332572131453037, "learning_rate": 8.26150421353682e-07, "loss": 0.1817, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.5203293952605595, "learning_rate": 8.101405277100549e-07, "loss": 0.1841, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.5118891365303132, "learning_rate": 7.942840756714077e-07, "loss": 0.1929, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.5202134230872326, "learning_rate": 7.785811920255093e-07, "loss": 0.1909, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.5303146839422735, "learning_rate": 7.630320023322024e-07, "loss": 0.1839, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.5531175009909253, "learning_rate": 7.476366309223903e-07, "loss": 0.1981, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.512058608932492, "learning_rate": 7.323952008970537e-07, "loss": 0.1811, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.5351005635849085, "learning_rate": 7.173078341262618e-07, "loss": 0.1826, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.513052784989293, "learning_rate": 7.023746512481989e-07, "loss": 0.2009, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.5131919193354033, "learning_rate": 6.875957716681902e-07, "loss": 0.1898, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.5456014006695689, "learning_rate": 6.729713135577687e-07, "loss": 0.1952, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.510678340114214, "learning_rate": 6.585013938537143e-07, "loss": 0.1817, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.4924664628689196, "learning_rate": 6.441861282571115e-07, "loss": 0.2123, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.5039519381718811, "learning_rate": 6.300256312324471e-07, "loss": 0.1923, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.5245752251944019, "learning_rate": 6.160200160066776e-07, "loss": 0.1702, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.513267359428939, "learning_rate": 6.021693945683327e-07, "loss": 0.1925, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.5595119505567204, "learning_rate": 5.884738776666044e-07, "loss": 0.1819, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.5233295171938069, "learning_rate": 5.749335748104878e-07, "loss": 0.1929, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.5264458244213704, "learning_rate": 5.615485942678778e-07, "loss": 0.1964, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.544977429893308, "learning_rate": 5.483190430647289e-07, "loss": 0.2134, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.5229180479578797, "learning_rate": 5.352450269841747e-07, "loss": 0.1962, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.5317218968077394, "learning_rate": 5.22326650565701e-07, "loss": 0.1884, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.49124413494154995, "learning_rate": 5.095640171043048e-07, "loss": 0.1967, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.5209754008343703, "learning_rate": 4.969572286496594e-07, "loss": 0.1984, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.5129566984442578, "learning_rate": 4.845063860053079e-07, "loss": 0.2066, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.5320309733612444, "learning_rate": 4.7221158872785997e-07, "loss": 0.16, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.49628676049911624, "learning_rate": 4.600729351261857e-07, "loss": 0.1969, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.5147400549892907, "learning_rate": 4.4809052226063355e-07, "loss": 0.2086, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.5069712662915452, "learning_rate": 4.3626444594226046e-07, "loss": 0.1957, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.523605944454784, "learning_rate": 4.245948007320588e-07, "loss": 0.1841, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.49935964623838147, "learning_rate": 4.130816799401971e-07, "loss": 0.171, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.5203208561406366, "learning_rate": 4.017251756252827e-07, "loss": 0.2087, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.5292673945633066, "learning_rate": 3.9052537859362473e-07, "loss": 0.1835, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.5467471379887703, "learning_rate": 3.7948237839849687e-07, "loss": 0.1843, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.5100802224426266, "learning_rate": 3.6859626333943797e-07, "loss": 0.1923, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.5236883092721002, "learning_rate": 3.578671204615347e-07, "loss": 0.1921, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.5184080140782548, "learning_rate": 3.472950355547267e-07, "loss": 0.1877, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.5077041011173302, "learning_rate": 3.3688009315312244e-07, "loss": 0.1778, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.5117403164860711, "learning_rate": 3.266223765343224e-07, "loss": 0.1668, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.49485629331003095, "learning_rate": 3.16521967718757e-07, "loss": 0.1866, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.5116411966208975, "learning_rate": 3.0657894746902726e-07, "loss": 0.208, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.5399901750055959, "learning_rate": 2.9679339528925654e-07, "loss": 0.1912, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.5237504628547325, "learning_rate": 2.871653894244597e-07, "loss": 0.2081, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.5028143162666602, "learning_rate": 2.7769500685991266e-07, "loss": 0.1883, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.5103845568844794, "learning_rate": 2.683823233205485e-07, "loss": 0.1962, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.5015327080516153, "learning_rate": 2.592274132703287e-07, "loss": 0.1977, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.5080520163779695, "learning_rate": 2.502303499116754e-07, "loss": 0.1962, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.5079927632996626, "learning_rate": 2.413912051848666e-07, "loss": 0.2046, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.5382531853776301, "learning_rate": 2.3271004976746613e-07, "loss": 0.1949, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.5049852852783348, "learning_rate": 2.2418695307376393e-07, "loss": 0.1872, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.5299968428658428, "learning_rate": 2.1582198325420968e-07, "loss": 0.1688, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.5119643285073211, "learning_rate": 2.0761520719488447e-07, "loss": 0.1764, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.49639305634908215, "learning_rate": 1.9956669051694798e-07, "loss": 0.2006, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.5338099786604847, "learning_rate": 1.916764975761254e-07, "loss": 0.179, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.541860127915882, "learning_rate": 1.839446914621923e-07, "loss": 0.175, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.5186193282981165, "learning_rate": 1.7637133399845962e-07, "loss": 0.181, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.5211598884204867, "learning_rate": 1.6895648574129397e-07, "loss": 0.2038, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.5157224959265385, "learning_rate": 1.6170020597962465e-07, "loss": 0.1878, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.5381903895129485, "learning_rate": 1.5460255273447078e-07, "loss": 0.1679, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.5003822497021806, "learning_rate": 1.4766358275847715e-07, "loss": 0.1952, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.5172037345877769, "learning_rate": 1.4088335153546573e-07, "loss": 0.2003, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.5091522235164931, "learning_rate": 1.3426191327998496e-07, "loss": 0.2147, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.506045941969076, "learning_rate": 1.277993209368744e-07, "loss": 0.1854, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.5110270756753109, "learning_rate": 1.214956261808542e-07, "loss": 0.1805, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.5288328222705898, "learning_rate": 1.1535087941609846e-07, "loss": 0.209, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.5091857121138832, "learning_rate": 1.0936512977583802e-07, "loss": 0.202, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.5048264016704546, "learning_rate": 1.0353842512196732e-07, "loss": 0.2048, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.5076228893341783, "learning_rate": 9.787081204466253e-08, "loss": 0.2161, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.49473093808951774, "learning_rate": 9.236233586200627e-08, "loss": 0.1993, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.48529836448396574, "learning_rate": 8.70130406196279e-08, "loss": 0.2021, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.49273888852037584, "learning_rate": 8.182296909035047e-08, "loss": 0.205, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.5086518088659392, "learning_rate": 7.679216277384439e-08, "loss": 0.2019, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.5090315332562565, "learning_rate": 7.19206618963053e-08, "loss": 0.2169, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.5247807595447065, "learning_rate": 6.720850541012347e-08, "loss": 0.207, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.5150187144226345, "learning_rate": 6.265573099357714e-08, "loss": 0.1648, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.5214281109753391, "learning_rate": 5.826237505053067e-08, "loss": 0.1747, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.507546542333768, "learning_rate": 5.4028472710137e-08, "loss": 0.188, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.5218974290811411, "learning_rate": 4.9954057826571146e-08, "loss": 0.1906, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.5121816869284405, "learning_rate": 4.6039162978743776e-08, "loss": 0.1815, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.5222259297618159, "learning_rate": 4.228381947004812e-08, "loss": 0.1829, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.5157636421199493, "learning_rate": 3.868805732811343e-08, "loss": 0.1947, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.5049336995302601, "learning_rate": 3.525190530455636e-08, "loss": 0.2057, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.4958716866582017, "learning_rate": 3.197539087475887e-08, "loss": 0.2182, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.5008251711210492, "learning_rate": 2.8858540237641786e-08, "loss": 0.193, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.48520906669281166, "learning_rate": 2.5901378315458247e-08, "loss": 0.2069, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.5240631298106344, "learning_rate": 2.3103928753598347e-08, "loss": 0.1889, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.4948932699754954, "learning_rate": 2.0466213920393718e-08, "loss": 0.1953, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.509972574792855, "learning_rate": 1.7988254906942115e-08, "loss": 0.1917, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.5249683524344806, "learning_rate": 1.5670071526936447e-08, "loss": 0.1749, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.5196514369309825, "learning_rate": 1.3511682316509344e-08, "loss": 0.1977, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.4997578346894314, "learning_rate": 1.1513104534086605e-08, "loss": 0.1998, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.5220244920739097, "learning_rate": 9.67435416023843e-09, "loss": 0.1971, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.5012440776427266, "learning_rate": 7.995445897566178e-09, "loss": 0.2055, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.5183205766139027, "learning_rate": 6.476393170578021e-09, "loss": 0.1908, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.504535463537783, "learning_rate": 5.11720812557348e-09, "loss": 0.1875, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.5388091996988218, "learning_rate": 3.917901630563492e-09, "loss": 0.1965, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.4958462269447774, "learning_rate": 2.878483275170485e-09, "loss": 0.1884, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.48440663820135244, "learning_rate": 1.998961370555108e-09, "loss": 0.2172, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.5142030702100416, "learning_rate": 1.2793429493518361e-09, "loss": 0.206, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.533473202036406, "learning_rate": 7.196337656112384e-10, "loss": 0.1807, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.5116425112511473, "learning_rate": 3.198382947511292e-10, "loss": 0.1775, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.5174705563158587, "learning_rate": 7.995973352770137e-11, "loss": 0.173, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.4923639286849277, "learning_rate": 0.0, "loss": 0.1926, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 359959696654336.0, "train_loss": 0.414602139194002, "train_runtime": 6542.7065, "train_samples_per_second": 24.149, "train_steps_per_second": 0.189 } ], "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": 359959696654336.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }