{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 6.51673612776058, "learning_rate": 3.2258064516129035e-07, "loss": 1.068, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.7178794236047406, "learning_rate": 6.451612903225807e-07, "loss": 1.0948, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.63156840843939, "learning_rate": 9.67741935483871e-07, "loss": 1.0921, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.708537566565926, "learning_rate": 1.2903225806451614e-06, "loss": 1.0692, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.393954329648477, "learning_rate": 1.6129032258064516e-06, "loss": 1.0818, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.115997050001872, "learning_rate": 1.935483870967742e-06, "loss": 1.0789, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.913328174875689, "learning_rate": 2.2580645161290324e-06, "loss": 1.0457, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.464829852275024, "learning_rate": 2.580645161290323e-06, "loss": 1.0268, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.7091262259753224, "learning_rate": 2.903225806451613e-06, "loss": 0.9941, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.5954424444464164, "learning_rate": 3.225806451612903e-06, "loss": 0.9709, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.4881059862835633, "learning_rate": 3.548387096774194e-06, "loss": 0.9679, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.56422351571094, "learning_rate": 3.870967741935484e-06, "loss": 0.9345, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 3.8840451941318572, "learning_rate": 4.193548387096774e-06, "loss": 0.9576, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.5759365295581076, "learning_rate": 4.516129032258065e-06, "loss": 0.9479, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.4118451905414497, "learning_rate": 4.838709677419355e-06, "loss": 0.9112, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.47215820615736, "learning_rate": 5.161290322580646e-06, "loss": 0.8725, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.261686421423469, "learning_rate": 5.483870967741935e-06, "loss": 0.8592, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 1.974662376186147, "learning_rate": 5.806451612903226e-06, "loss": 0.8765, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.5494177006733763, "learning_rate": 6.129032258064517e-06, "loss": 0.8423, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.3005103545300627, "learning_rate": 6.451612903225806e-06, "loss": 0.8062, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.1596538971809196, "learning_rate": 6.774193548387097e-06, "loss": 0.8153, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.3107182059022888, "learning_rate": 7.096774193548388e-06, "loss": 0.7801, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.1810487184978047, "learning_rate": 7.4193548387096784e-06, "loss": 0.7862, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.9665240721203189, "learning_rate": 7.741935483870968e-06, "loss": 0.7774, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8231904308797178, "learning_rate": 8.064516129032258e-06, "loss": 0.7832, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.9910438267919923, "learning_rate": 8.387096774193549e-06, "loss": 0.7619, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.8533201242032654, "learning_rate": 8.70967741935484e-06, "loss": 0.7554, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.8115430994138391, "learning_rate": 9.03225806451613e-06, "loss": 0.7586, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7816211071158887, "learning_rate": 9.35483870967742e-06, "loss": 0.7386, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7625462137708804, "learning_rate": 9.67741935483871e-06, "loss": 0.731, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.7804277311330777, "learning_rate": 1e-05, "loss": 0.7327, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7883761867475888, "learning_rate": 1.0322580645161291e-05, "loss": 0.7464, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7475833139544376, "learning_rate": 1.0645161290322582e-05, "loss": 0.7279, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.6530228583717502, "learning_rate": 1.096774193548387e-05, "loss": 0.7261, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.6241807442896675, "learning_rate": 1.1290322580645164e-05, "loss": 0.7368, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6888963731736838, "learning_rate": 1.1612903225806453e-05, "loss": 0.7196, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.7097300452262809, "learning_rate": 1.1935483870967743e-05, "loss": 0.7381, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.6202761668570643, "learning_rate": 1.2258064516129034e-05, "loss": 0.7414, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.7199002861160231, "learning_rate": 1.2580645161290324e-05, "loss": 0.7288, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.5944961912312685, "learning_rate": 1.2903225806451613e-05, "loss": 0.7175, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7145718352845432, "learning_rate": 1.3225806451612903e-05, "loss": 0.6917, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6010454074680461, "learning_rate": 1.3548387096774194e-05, "loss": 0.7024, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.7418978754996275, "learning_rate": 1.3870967741935486e-05, "loss": 0.6983, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.5896851706859064, "learning_rate": 1.4193548387096776e-05, "loss": 0.7253, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6259019369303079, "learning_rate": 1.4516129032258066e-05, "loss": 0.6975, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.6517939674117661, "learning_rate": 1.4838709677419357e-05, "loss": 0.7018, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.5263728631236246, "learning_rate": 1.5161290322580646e-05, "loss": 0.6931, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5897771004385195, "learning_rate": 1.5483870967741936e-05, "loss": 0.6986, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6132965503849611, "learning_rate": 1.5806451612903226e-05, "loss": 0.6815, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.7679576451003134, "learning_rate": 1.6129032258064517e-05, "loss": 0.694, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.5817347539273946, "learning_rate": 1.6451612903225807e-05, "loss": 0.6869, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.6093353374932721, "learning_rate": 1.6774193548387098e-05, "loss": 0.6955, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.6420534591133933, "learning_rate": 1.7096774193548388e-05, "loss": 0.6996, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.6247143973026985, "learning_rate": 1.741935483870968e-05, "loss": 0.6856, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.7107813691417993, "learning_rate": 1.774193548387097e-05, "loss": 0.6707, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6042776745794393, "learning_rate": 1.806451612903226e-05, "loss": 0.691, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6763281747255037, "learning_rate": 1.838709677419355e-05, "loss": 0.6704, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6475051941997843, "learning_rate": 1.870967741935484e-05, "loss": 0.6788, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5588497916280976, "learning_rate": 1.903225806451613e-05, "loss": 0.6662, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.687326232641126, "learning_rate": 1.935483870967742e-05, "loss": 0.6866, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.557087742647539, "learning_rate": 1.967741935483871e-05, "loss": 0.6538, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.5370468008229901, "learning_rate": 2e-05, "loss": 0.6817, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.6345064663249672, "learning_rate": 2.0322580645161292e-05, "loss": 0.6812, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7105206017309365, "learning_rate": 2.0645161290322582e-05, "loss": 0.6882, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.83285614196591, "learning_rate": 2.0967741935483873e-05, "loss": 0.6665, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.750895221326107, "learning_rate": 2.1290322580645163e-05, "loss": 0.6629, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7442644082716043, "learning_rate": 2.161290322580645e-05, "loss": 0.6792, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.6808033367716091, "learning_rate": 2.193548387096774e-05, "loss": 0.665, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.7303290384986233, "learning_rate": 2.225806451612903e-05, "loss": 0.6669, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.6468789801475856, "learning_rate": 2.2580645161290328e-05, "loss": 0.6728, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.5906617211295803, "learning_rate": 2.2903225806451615e-05, "loss": 0.6916, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7249238700468954, "learning_rate": 2.3225806451612906e-05, "loss": 0.67, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.7006561440529655, "learning_rate": 2.3548387096774196e-05, "loss": 0.6381, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6231774853034144, "learning_rate": 2.3870967741935486e-05, "loss": 0.6619, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.6928920270627229, "learning_rate": 2.4193548387096777e-05, "loss": 0.6645, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.737846867446711, "learning_rate": 2.4516129032258067e-05, "loss": 0.684, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.8612484066153948, "learning_rate": 2.4838709677419358e-05, "loss": 0.6542, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.58877685620897, "learning_rate": 2.5161290322580648e-05, "loss": 0.6621, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7224294708374543, "learning_rate": 2.548387096774194e-05, "loss": 0.6783, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.8036021803522286, "learning_rate": 2.5806451612903226e-05, "loss": 0.6741, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.9084085824779596, "learning_rate": 2.6129032258064516e-05, "loss": 0.6566, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.356163497126968, "learning_rate": 2.6451612903225806e-05, "loss": 0.6744, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.7475732040461622, "learning_rate": 2.6774193548387097e-05, "loss": 0.6778, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.8920287892278013, "learning_rate": 2.7096774193548387e-05, "loss": 0.662, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.9557614305650197, "learning_rate": 2.7419354838709678e-05, "loss": 0.6701, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.9031336674215529, "learning_rate": 2.774193548387097e-05, "loss": 0.6576, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7862716174082159, "learning_rate": 2.8064516129032262e-05, "loss": 0.6685, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.0865071382511948, "learning_rate": 2.8387096774193552e-05, "loss": 0.661, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.0577292752716874, "learning_rate": 2.8709677419354843e-05, "loss": 0.6601, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.7470013009569076, "learning_rate": 2.9032258064516133e-05, "loss": 0.665, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.0156696779235208, "learning_rate": 2.9354838709677423e-05, "loss": 0.6583, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.9009553054511399, "learning_rate": 2.9677419354838714e-05, "loss": 0.6792, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.8254870161928765, "learning_rate": 3.0000000000000004e-05, "loss": 0.6547, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.7952405141996184, "learning_rate": 3.032258064516129e-05, "loss": 0.6589, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.097457148804237, "learning_rate": 3.0645161290322585e-05, "loss": 0.6595, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.6977549425508273, "learning_rate": 3.096774193548387e-05, "loss": 0.6669, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.9947416111878536, "learning_rate": 3.1290322580645166e-05, "loss": 0.6402, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.4722794735787332, "learning_rate": 3.161290322580645e-05, "loss": 0.66, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.8069718145963908, "learning_rate": 3.193548387096774e-05, "loss": 0.6701, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.403174968239727, "learning_rate": 3.2258064516129034e-05, "loss": 0.6586, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.8204539199303551, "learning_rate": 3.258064516129033e-05, "loss": 0.6588, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.4624408238547488, "learning_rate": 3.2903225806451614e-05, "loss": 0.6624, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.7973331276766294, "learning_rate": 3.322580645161291e-05, "loss": 0.6625, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.3073996521733684, "learning_rate": 3.3548387096774195e-05, "loss": 0.6662, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.8355841546874846, "learning_rate": 3.387096774193549e-05, "loss": 0.6573, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.2186202813991789, "learning_rate": 3.4193548387096776e-05, "loss": 0.658, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.8094108046169309, "learning_rate": 3.451612903225807e-05, "loss": 0.6658, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.0309068269824864, "learning_rate": 3.483870967741936e-05, "loss": 0.6577, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.9697912728720234, "learning_rate": 3.516129032258065e-05, "loss": 0.6628, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.4967224190254844, "learning_rate": 3.548387096774194e-05, "loss": 0.6525, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 0.9184742761414876, "learning_rate": 3.5806451612903225e-05, "loss": 0.642, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.7026162838056391, "learning_rate": 3.612903225806452e-05, "loss": 0.648, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.0151009375117592, "learning_rate": 3.6451612903225805e-05, "loss": 0.6684, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.5694113215263275, "learning_rate": 3.67741935483871e-05, "loss": 0.6603, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.1800828745089376, "learning_rate": 3.7096774193548386e-05, "loss": 0.6639, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.5105780101807547, "learning_rate": 3.741935483870968e-05, "loss": 0.6559, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.2741266114533258, "learning_rate": 3.7741935483870974e-05, "loss": 0.6696, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.150967835939801, "learning_rate": 3.806451612903226e-05, "loss": 0.651, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.0466833870761059, "learning_rate": 3.8387096774193555e-05, "loss": 0.6662, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.1362375097500832, "learning_rate": 3.870967741935484e-05, "loss": 0.6581, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.8928659651331434, "learning_rate": 3.9032258064516135e-05, "loss": 0.6645, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.0212424635269004, "learning_rate": 3.935483870967742e-05, "loss": 0.6615, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.9908435087398474, "learning_rate": 3.9677419354838716e-05, "loss": 0.6519, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.1029608432676012, "learning_rate": 4e-05, "loss": 0.6564, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.135980025612019, "learning_rate": 3.9999920040266474e-05, "loss": 0.6589, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.9431457343700058, "learning_rate": 3.999968016170525e-05, "loss": 0.6614, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.901246360762239, "learning_rate": 3.9999280366234394e-05, "loss": 0.6591, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.8407707910875913, "learning_rate": 3.999872065705065e-05, "loss": 0.6492, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.8427652937852096, "learning_rate": 3.999800103862945e-05, "loss": 0.6398, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 0.8003764205801056, "learning_rate": 3.9997121516724834e-05, "loss": 0.6526, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.7786863111852513, "learning_rate": 3.999608209836944e-05, "loss": 0.6424, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.8366799768210765, "learning_rate": 3.999488279187443e-05, "loss": 0.6493, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.8867788148674303, "learning_rate": 3.9993523606829425e-05, "loss": 0.6607, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7595083911801324, "learning_rate": 3.9992004554102435e-05, "loss": 0.6496, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.6969994222624021, "learning_rate": 3.999032564583976e-05, "loss": 0.6577, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.7331180668124145, "learning_rate": 3.998848689546591e-05, "loss": 0.6531, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7580765055642457, "learning_rate": 3.9986488317683496e-05, "loss": 0.6372, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.6708707322912881, "learning_rate": 3.9984329928473067e-05, "loss": 0.6382, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.6864120987164181, "learning_rate": 3.998201174509306e-05, "loss": 0.6395, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.7323413983891709, "learning_rate": 3.997953378607961e-05, "loss": 0.6446, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.7288304414555555, "learning_rate": 3.9976896071246403e-05, "loss": 0.6354, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.71945029655243, "learning_rate": 3.997409862168454e-05, "loss": 0.6536, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.0793860130859563, "learning_rate": 3.997114145976237e-05, "loss": 0.6416, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.6220237191836726, "learning_rate": 3.9968024609125245e-05, "loss": 0.6417, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 1.1125865283165588, "learning_rate": 3.996474809469545e-05, "loss": 0.6425, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.8467188039517863, "learning_rate": 3.996131194267189e-05, "loss": 0.6514, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.5876097412793783, "learning_rate": 3.995771618052995e-05, "loss": 0.6248, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.8394853855183323, "learning_rate": 3.9953960837021256e-05, "loss": 0.6609, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7590660170459015, "learning_rate": 3.995004594217343e-05, "loss": 0.6217, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6902329252273761, "learning_rate": 3.994597152728987e-05, "loss": 0.6382, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.5863663005123557, "learning_rate": 3.994173762494947e-05, "loss": 0.6339, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6702787279974756, "learning_rate": 3.9937344269006424e-05, "loss": 0.6217, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.5946957980909661, "learning_rate": 3.993279149458988e-05, "loss": 0.6452, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.6249330022235443, "learning_rate": 3.9928079338103695e-05, "loss": 0.6291, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.5913080088473593, "learning_rate": 3.992320783722616e-05, "loss": 0.6435, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.5672560250316826, "learning_rate": 3.991817703090965e-05, "loss": 0.6499, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.5798806417025991, "learning_rate": 3.991298695938038e-05, "loss": 0.643, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.7716075132146356, "learning_rate": 3.9907637664138e-05, "loss": 0.642, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.702178103248019, "learning_rate": 3.990212918795534e-05, "loss": 0.6355, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.7447562480075027, "learning_rate": 3.9896461574878036e-05, "loss": 0.6378, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.6615891584228508, "learning_rate": 3.989063487022416e-05, "loss": 0.6637, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.9464429115589319, "learning_rate": 3.9884649120583903e-05, "loss": 0.654, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.6906956863871103, "learning_rate": 3.987850437381915e-05, "loss": 0.6478, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.7546399854585522, "learning_rate": 3.987220067906313e-05, "loss": 0.6437, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.8832191003756034, "learning_rate": 3.986573808672002e-05, "loss": 0.6411, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.7289273529128291, "learning_rate": 3.9859116648464534e-05, "loss": 0.6577, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.7180820793454809, "learning_rate": 3.985233641724152e-05, "loss": 0.6498, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.8403709625685459, "learning_rate": 3.984539744726554e-05, "loss": 0.6507, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.8680004687810635, "learning_rate": 3.983829979402038e-05, "loss": 0.6383, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.976631729390332, "learning_rate": 3.983104351425871e-05, "loss": 0.6553, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.8292047557767757, "learning_rate": 3.982362866600154e-05, "loss": 0.6471, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.7814330420009099, "learning_rate": 3.9816055308537806e-05, "loss": 0.6528, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.936224575411586, "learning_rate": 3.980832350242388e-05, "loss": 0.6285, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.5726152119751687, "learning_rate": 3.980043330948306e-05, "loss": 0.6352, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.6236305595776562, "learning_rate": 3.9792384792805124e-05, "loss": 0.6213, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5905695046974128, "learning_rate": 3.978417801674579e-05, "loss": 0.6397, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.6410698170815919, "learning_rate": 3.9775813046926244e-05, "loss": 0.6403, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.4984738499334232, "learning_rate": 3.976728995023254e-05, "loss": 0.6365, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.552322908984422, "learning_rate": 3.975860879481514e-05, "loss": 0.6432, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.6763192832418506, "learning_rate": 3.974976965008833e-05, "loss": 0.6415, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5343213129188209, "learning_rate": 3.9740772586729674e-05, "loss": 0.6414, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.5732398947301411, "learning_rate": 3.973161767667946e-05, "loss": 0.6405, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.5578129989014867, "learning_rate": 3.972230499314009e-05, "loss": 0.6213, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.663290073837957, "learning_rate": 3.9712834610575545e-05, "loss": 0.6477, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5913380348242637, "learning_rate": 3.9703206604710746e-05, "loss": 0.648, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.6239365274093989, "learning_rate": 3.969342105253098e-05, "loss": 0.6354, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.4912275247885401, "learning_rate": 3.9683478032281246e-05, "loss": 0.6686, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.7960906208377153, "learning_rate": 3.967337762346568e-05, "loss": 0.6401, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.8473847465054533, "learning_rate": 3.9663119906846885e-05, "loss": 0.6348, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.6042896267239709, "learning_rate": 3.965270496444528e-05, "loss": 0.6504, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.7676456610612155, "learning_rate": 3.9642132879538465e-05, "loss": 0.6351, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.6274119680428183, "learning_rate": 3.9631403736660566e-05, "loss": 0.6404, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.7590968324228786, "learning_rate": 3.962051762160151e-05, "loss": 0.6346, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.6418833034780171, "learning_rate": 3.960947462140638e-05, "loss": 0.645, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5125972666919762, "learning_rate": 3.959827482437472e-05, "loss": 0.6366, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.7362636691370507, "learning_rate": 3.958691832005981e-05, "loss": 0.6241, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.7029555567548144, "learning_rate": 3.9575405199267944e-05, "loss": 0.6562, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.5124117078426231, "learning_rate": 3.956373555405774e-05, "loss": 0.6341, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.5808129967425455, "learning_rate": 3.955190947773937e-05, "loss": 0.66, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.7182561606293985, "learning_rate": 3.9539927064873824e-05, "loss": 0.6221, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.5433659984953711, "learning_rate": 3.952778841127214e-05, "loss": 0.6479, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.6078552713465516, "learning_rate": 3.95154936139947e-05, "loss": 0.6215, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.7482882244738415, "learning_rate": 3.950304277135034e-05, "loss": 0.6238, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.6326055774074878, "learning_rate": 3.94904359828957e-05, "loss": 0.6498, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.6754090090976783, "learning_rate": 3.94776733494343e-05, "loss": 0.6286, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.7945012596313549, "learning_rate": 3.9464754973015826e-05, "loss": 0.6272, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5531649867263083, "learning_rate": 3.9451680956935275e-05, "loss": 0.6291, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5949526620625962, "learning_rate": 3.943845140573213e-05, "loss": 0.6342, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.5289902319610763, "learning_rate": 3.942506642518952e-05, "loss": 0.6395, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.5782875872722676, "learning_rate": 3.9411526122333396e-05, "loss": 0.6363, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.607274103113457, "learning_rate": 3.939783060543167e-05, "loss": 0.6245, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5043483475764896, "learning_rate": 3.938397998399333e-05, "loss": 0.6368, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.6338780972573052, "learning_rate": 3.936997436876756e-05, "loss": 0.6492, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.7271428544686857, "learning_rate": 3.935581387174289e-05, "loss": 0.6302, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.47089171017244724, "learning_rate": 3.9341498606146295e-05, "loss": 0.6318, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.757938900120477, "learning_rate": 3.932702868644224e-05, "loss": 0.6174, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.6134212779631625, "learning_rate": 3.931240422833181e-05, "loss": 0.6308, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.7301191373059255, "learning_rate": 3.9297625348751806e-05, "loss": 0.6158, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.6246471007601954, "learning_rate": 3.9282692165873744e-05, "loss": 0.6171, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.5534110379826667, "learning_rate": 3.9267604799102945e-05, "loss": 0.6282, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.5346513125447954, "learning_rate": 3.9252363369077615e-05, "loss": 0.6311, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.46776755618194626, "learning_rate": 3.9236967997667796e-05, "loss": 0.6311, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.5036987282663655, "learning_rate": 3.9221418807974496e-05, "loss": 0.6298, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5640736117800568, "learning_rate": 3.92057159243286e-05, "loss": 0.6382, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.5241620914846078, "learning_rate": 3.9189859472289956e-05, "loss": 0.611, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.5176635431043708, "learning_rate": 3.9173849578646324e-05, "loss": 0.6328, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.4680164272736061, "learning_rate": 3.9157686371412395e-05, "loss": 0.6477, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.542391927261808, "learning_rate": 3.914136997982874e-05, "loss": 0.6399, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5947606175374746, "learning_rate": 3.912490053436079e-05, "loss": 0.632, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5255710271797088, "learning_rate": 3.9108278166697805e-05, "loss": 0.6054, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5142533492765093, "learning_rate": 3.909150300975178e-05, "loss": 0.6283, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.5526726962580545, "learning_rate": 3.907457519765642e-05, "loss": 0.626, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5770824303507432, "learning_rate": 3.905749486576607e-05, "loss": 0.6095, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.5547184169783682, "learning_rate": 3.90402621506546e-05, "loss": 0.6254, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.622655290818418, "learning_rate": 3.902287719011435e-05, "loss": 0.6288, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.611274921865302, "learning_rate": 3.900534012315499e-05, "loss": 0.6256, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.6280202704372857, "learning_rate": 3.8987651090002454e-05, "loss": 0.6634, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.5508529748375383, "learning_rate": 3.896981023209777e-05, "loss": 0.631, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.6301659186306474, "learning_rate": 3.8951817692095966e-05, "loss": 0.6322, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.7352015453945698, "learning_rate": 3.893367361386491e-05, "loss": 0.6322, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.49659649475622736, "learning_rate": 3.891537814248417e-05, "loss": 0.6377, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.7490254045213639, "learning_rate": 3.889693142424384e-05, "loss": 0.6203, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5579269029365989, "learning_rate": 3.8878333606643405e-05, "loss": 0.6346, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6735139398782849, "learning_rate": 3.885958483839049e-05, "loss": 0.619, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.7485158508487877, "learning_rate": 3.8840685269399786e-05, "loss": 0.6182, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.527443432703575, "learning_rate": 3.882163505079171e-05, "loss": 0.6278, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.7326492857245892, "learning_rate": 3.880243433489132e-05, "loss": 0.6269, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.5717499370373383, "learning_rate": 3.878308327522702e-05, "loss": 0.5702, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.7705964066920754, "learning_rate": 3.876358202652936e-05, "loss": 0.531, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5943130975709258, "learning_rate": 3.8743930744729835e-05, "loss": 0.5439, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6676827828322821, "learning_rate": 3.8724129586959535e-05, "loss": 0.5377, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5425891726783635, "learning_rate": 3.870417871154801e-05, "loss": 0.5396, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.5935902740432969, "learning_rate": 3.868407827802192e-05, "loss": 0.5399, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.6102603543029181, "learning_rate": 3.8663828447103804e-05, "loss": 0.5323, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.5609137594546934, "learning_rate": 3.8643429380710765e-05, "loss": 0.5231, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.6047752866400284, "learning_rate": 3.862288124195319e-05, "loss": 0.5359, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.642208845280121, "learning_rate": 3.8602184195133464e-05, "loss": 0.5583, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.6959598450410244, "learning_rate": 3.8581338405744604e-05, "loss": 0.5427, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.6868053640361811, "learning_rate": 3.8560344040468996e-05, "loss": 0.5666, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5165329383513736, "learning_rate": 3.853920126717703e-05, "loss": 0.5282, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6912440303436629, "learning_rate": 3.851791025492574e-05, "loss": 0.5722, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.5716766274756656, "learning_rate": 3.8496471173957515e-05, "loss": 0.5271, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.6541505108240165, "learning_rate": 3.847488419569866e-05, "loss": 0.5504, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.7840697977436674, "learning_rate": 3.8453149492758077e-05, "loss": 0.5392, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.5425710605748721, "learning_rate": 3.8431267238925886e-05, "loss": 0.5382, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.655683544241561, "learning_rate": 3.840923760917199e-05, "loss": 0.5408, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5914199541055299, "learning_rate": 3.838706077964473e-05, "loss": 0.5395, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.4912792604667177, "learning_rate": 3.836473692766944e-05, "loss": 0.5468, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5877487739240224, "learning_rate": 3.834226623174705e-05, "loss": 0.5318, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.5404218749910566, "learning_rate": 3.831964887155264e-05, "loss": 0.5586, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.5145905082187614, "learning_rate": 3.829688502793403e-05, "loss": 0.5246, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.6090155997923028, "learning_rate": 3.827397488291029e-05, "loss": 0.5551, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.6112241485861851, "learning_rate": 3.8250918619670343e-05, "loss": 0.5108, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.7880464899480089, "learning_rate": 3.822771642257145e-05, "loss": 0.5264, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.4757600138926665, "learning_rate": 3.820436847713776e-05, "loss": 0.5307, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.619816212675817, "learning_rate": 3.8180874970058826e-05, "loss": 0.5211, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.4584744680260032, "learning_rate": 3.8157236089188103e-05, "loss": 0.5274, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.600609462245879, "learning_rate": 3.813345202354145e-05, "loss": 0.5291, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.5099673798233969, "learning_rate": 3.810952296329563e-05, "loss": 0.5518, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.6024597833668714, "learning_rate": 3.808544909978676e-05, "loss": 0.5519, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.6891686343016958, "learning_rate": 3.806123062550882e-05, "loss": 0.5351, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.44913131079478164, "learning_rate": 3.803686773411208e-05, "loss": 0.5408, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.6617421872705908, "learning_rate": 3.801236062040158e-05, "loss": 0.5573, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5877898775808582, "learning_rate": 3.798770948033553e-05, "loss": 0.5362, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4581758196010779, "learning_rate": 3.796291451102381e-05, "loss": 0.5481, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6461031574980348, "learning_rate": 3.793797591072631e-05, "loss": 0.5226, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6120149686994928, "learning_rate": 3.791289387885144e-05, "loss": 0.5405, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.6250196176738368, "learning_rate": 3.788766861595443e-05, "loss": 0.5449, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5879719495651795, "learning_rate": 3.7862300323735835e-05, "loss": 0.5427, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5857626798459498, "learning_rate": 3.783678920503983e-05, "loss": 0.5456, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.6645204111811226, "learning_rate": 3.781113546385265e-05, "loss": 0.5478, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.5351440423795935, "learning_rate": 3.7785339305300916e-05, "loss": 0.5481, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6287707304226531, "learning_rate": 3.7759400935650025e-05, "loss": 0.5567, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5523445268889675, "learning_rate": 3.77333205623025e-05, "loss": 0.5263, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.44458699093507364, "learning_rate": 3.7707098393796295e-05, "loss": 0.5315, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5287548699213805, "learning_rate": 3.7680734639803185e-05, "loss": 0.54, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5150889329136311, "learning_rate": 3.765422951112704e-05, "loss": 0.5573, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.44429205907002156, "learning_rate": 3.762758321970216e-05, "loss": 0.5106, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.5076228818922588, "learning_rate": 3.7600795978591584e-05, "loss": 0.5598, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5076221593470481, "learning_rate": 3.757386800198538e-05, "loss": 0.5599, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.6306718719127316, "learning_rate": 3.7546799505198925e-05, "loss": 0.5475, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5101855976067492, "learning_rate": 3.7519590704671197e-05, "loss": 0.5344, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.6610909625823738, "learning_rate": 3.749224181796305e-05, "loss": 0.5472, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5031860609833824, "learning_rate": 3.746475306375545e-05, "loss": 0.5499, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.601918367190875, "learning_rate": 3.743712466184774e-05, "loss": 0.5478, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.5225180772973854, "learning_rate": 3.7409356833155885e-05, "loss": 0.5331, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.5031403637260804, "learning_rate": 3.73814497997107e-05, "loss": 0.5606, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.6642681857707, "learning_rate": 3.7353403784656095e-05, "loss": 0.5518, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5410858950320997, "learning_rate": 3.732521901224724e-05, "loss": 0.5453, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6105783096103186, "learning_rate": 3.7296895707848844e-05, "loss": 0.5508, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.58344957636947, "learning_rate": 3.7268434097933275e-05, "loss": 0.5543, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.5481858829798192, "learning_rate": 3.723983441007882e-05, "loss": 0.5254, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.6364257555125348, "learning_rate": 3.721109687296781e-05, "loss": 0.5443, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.5906562914776471, "learning_rate": 3.718222171638484e-05, "loss": 0.5518, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5470215617934658, "learning_rate": 3.715320917121488e-05, "loss": 0.5428, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.5818091810557239, "learning_rate": 3.712405946944149e-05, "loss": 0.5635, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6914072614970009, "learning_rate": 3.709477284414488e-05, "loss": 0.5441, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.519332084851258, "learning_rate": 3.7065349529500136e-05, "loss": 0.5155, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.5709521144434475, "learning_rate": 3.7035789760775305e-05, "loss": 0.5344, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.6115439047628624, "learning_rate": 3.70060937743295e-05, "loss": 0.5429, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.47250056933900864, "learning_rate": 3.6976261807611045e-05, "loss": 0.5417, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.5642204491783159, "learning_rate": 3.694629409915555e-05, "loss": 0.5683, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4794304925896376, "learning_rate": 3.691619088858401e-05, "loss": 0.5288, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5165426032523867, "learning_rate": 3.68859524166009e-05, "loss": 0.538, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.5892507525104899, "learning_rate": 3.6855578924992226e-05, "loss": 0.5605, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.520476448307042, "learning_rate": 3.6825070656623626e-05, "loss": 0.5581, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.5224797369301458, "learning_rate": 3.67944278554384e-05, "loss": 0.5507, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4485739634116467, "learning_rate": 3.676365076645557e-05, "loss": 0.5374, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.5452461552672948, "learning_rate": 3.673273963576791e-05, "loss": 0.5405, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.4790100833647731, "learning_rate": 3.670169471054001e-05, "loss": 0.5331, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.49065975217097335, "learning_rate": 3.6670516239006254e-05, "loss": 0.5375, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4873542247571918, "learning_rate": 3.663920447046888e-05, "loss": 0.5505, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.45036000177320196, "learning_rate": 3.6607759655295954e-05, "loss": 0.5284, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5613140565384446, "learning_rate": 3.657618204491937e-05, "loss": 0.5392, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.46685523602777473, "learning_rate": 3.6544471891832875e-05, "loss": 0.526, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4666116863139355, "learning_rate": 3.6512629449589983e-05, "loss": 0.5561, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.5144825111369038, "learning_rate": 3.6480654972802045e-05, "loss": 0.5564, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5240709161578784, "learning_rate": 3.644854871713611e-05, "loss": 0.5465, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.6224276994321107, "learning_rate": 3.6416310939312924e-05, "loss": 0.5494, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.4281464866047289, "learning_rate": 3.638394189710493e-05, "loss": 0.5367, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.5862297984252961, "learning_rate": 3.635144184933412e-05, "loss": 0.5407, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.512275906009396, "learning_rate": 3.6318811055869994e-05, "loss": 0.5513, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.5377103562842385, "learning_rate": 3.628604977762752e-05, "loss": 0.5271, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.45070334848584653, "learning_rate": 3.6253158276565004e-05, "loss": 0.5456, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.4989583536309349, "learning_rate": 3.6220136815682016e-05, "loss": 0.5584, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.4971193487573305, "learning_rate": 3.618698565901727e-05, "loss": 0.5643, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.436114871209885, "learning_rate": 3.615370507164654e-05, "loss": 0.5279, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.4338969279689383, "learning_rate": 3.61202953196805e-05, "loss": 0.5501, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.43486733264847893, "learning_rate": 3.6086756670262654e-05, "loss": 0.5349, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.44947663399579263, "learning_rate": 3.6053089391567135e-05, "loss": 0.549, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.4530427280218898, "learning_rate": 3.601929375279662e-05, "loss": 0.5565, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.5156323205101092, "learning_rate": 3.598537002418012e-05, "loss": 0.5569, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.4157210510272111, "learning_rate": 3.5951318476970885e-05, "loss": 0.544, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.4985100908026425, "learning_rate": 3.591713938344416e-05, "loss": 0.5245, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.48382078212413776, "learning_rate": 3.588283301689507e-05, "loss": 0.5407, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.48273035513287565, "learning_rate": 3.5848399651636424e-05, "loss": 0.5585, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.42891043913154164, "learning_rate": 3.5813839562996473e-05, "loss": 0.5231, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.5249123099635524, "learning_rate": 3.5779153027316775e-05, "loss": 0.5327, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.4589140045739978, "learning_rate": 3.574434032194994e-05, "loss": 0.5319, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.48431206512128544, "learning_rate": 3.5709401725257436e-05, "loss": 0.5459, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4376248844114752, "learning_rate": 3.5674337516607346e-05, "loss": 0.5452, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.4025561080409164, "learning_rate": 3.563914797637216e-05, "loss": 0.5301, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.4752840593939319, "learning_rate": 3.560383338592649e-05, "loss": 0.5389, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.4152372887836169, "learning_rate": 3.556839402764487e-05, "loss": 0.5189, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.49137504866119663, "learning_rate": 3.553283018489946e-05, "loss": 0.5298, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.4929613752288697, "learning_rate": 3.54971421420578e-05, "loss": 0.5428, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5302688834870111, "learning_rate": 3.5461330184480524e-05, "loss": 0.5544, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.47420382708293646, "learning_rate": 3.54253945985191e-05, "loss": 0.5428, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.5428676109834707, "learning_rate": 3.5389335671513524e-05, "loss": 0.5543, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.42774864996600537, "learning_rate": 3.5353153691789986e-05, "loss": 0.5629, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.4945042808526884, "learning_rate": 3.531684894865866e-05, "loss": 0.565, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4863574169200184, "learning_rate": 3.528042173241128e-05, "loss": 0.5332, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4533174854500543, "learning_rate": 3.524387233431892e-05, "loss": 0.5407, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.3927690185566775, "learning_rate": 3.520720104662958e-05, "loss": 0.5261, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.41197789433320703, "learning_rate": 3.5170408162565904e-05, "loss": 0.538, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.43221678974372807, "learning_rate": 3.513349397632281e-05, "loss": 0.5253, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.5237408668568735, "learning_rate": 3.5096458783065145e-05, "loss": 0.5404, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.4751167111962205, "learning_rate": 3.505930287892533e-05, "loss": 0.5228, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.4524134658400156, "learning_rate": 3.502202656100099e-05, "loss": 0.5476, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.5072437113775922, "learning_rate": 3.498463012735256e-05, "loss": 0.5517, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.4177052513791683, "learning_rate": 3.494711387700094e-05, "loss": 0.5448, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.5622305960167583, "learning_rate": 3.490947810992505e-05, "loss": 0.559, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.41267257294109744, "learning_rate": 3.48717231270595e-05, "loss": 0.5328, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.49128264417858875, "learning_rate": 3.483384923029211e-05, "loss": 0.5287, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.5063461346859975, "learning_rate": 3.479585672246156e-05, "loss": 0.5405, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.4946267327431368, "learning_rate": 3.4757745907354924e-05, "loss": 0.536, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.47196574243046285, "learning_rate": 3.471951708970527e-05, "loss": 0.5414, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4706582549814287, "learning_rate": 3.468117057518921e-05, "loss": 0.5333, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.4394833077075501, "learning_rate": 3.4642706670424426e-05, "loss": 0.5176, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.43592104342925814, "learning_rate": 3.460412568296731e-05, "loss": 0.54, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.4898101322863908, "learning_rate": 3.456542792131039e-05, "loss": 0.5239, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.4126484112490853, "learning_rate": 3.4526613694879936e-05, "loss": 0.5461, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.4641888063273763, "learning_rate": 3.448768331403348e-05, "loss": 0.5507, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.4106411523193953, "learning_rate": 3.44486370900573e-05, "loss": 0.5158, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.4622999431689633, "learning_rate": 3.440947533516396e-05, "loss": 0.5323, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.4344088316214562, "learning_rate": 3.4370198362489816e-05, "loss": 0.5627, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.45033161828821305, "learning_rate": 3.43308064860925e-05, "loss": 0.5512, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.4699392763773425, "learning_rate": 3.4291300020948393e-05, "loss": 0.5366, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.4521734766011855, "learning_rate": 3.425167928295015e-05, "loss": 0.5479, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.4836206485598086, "learning_rate": 3.421194458890411e-05, "loss": 0.5427, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.4938743644331027, "learning_rate": 3.4172096256527865e-05, "loss": 0.5358, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.50721141527443, "learning_rate": 3.4132134604447595e-05, "loss": 0.5308, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.47863117242616887, "learning_rate": 3.409205995219561e-05, "loss": 0.5361, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.4925326367187054, "learning_rate": 3.4051872620207765e-05, "loss": 0.5401, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.49516129152046157, "learning_rate": 3.40115729298209e-05, "loss": 0.5583, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.5053403034946515, "learning_rate": 3.397116120327025e-05, "loss": 0.5278, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.47360352177464893, "learning_rate": 3.3930637763686916e-05, "loss": 0.5384, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.40247848350164733, "learning_rate": 3.389000293509524e-05, "loss": 0.522, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.4654522085776853, "learning_rate": 3.3849257042410225e-05, "loss": 0.5285, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.45222455227453606, "learning_rate": 3.380840041143494e-05, "loss": 0.5518, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.42866606493559045, "learning_rate": 3.376743336885792e-05, "loss": 0.5483, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4370532561201772, "learning_rate": 3.372635624225055e-05, "loss": 0.5363, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.4531545543203661, "learning_rate": 3.3685169360064445e-05, "loss": 0.5495, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.5216445819405399, "learning_rate": 3.3643873051628804e-05, "loss": 0.5483, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4708718150756996, "learning_rate": 3.3602467647147814e-05, "loss": 0.5387, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.473956064295868, "learning_rate": 3.356095347769799e-05, "loss": 0.5414, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.43449693621186075, "learning_rate": 3.351933087522552e-05, "loss": 0.5235, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.5184223205248604, "learning_rate": 3.3477600172543626e-05, "loss": 0.5249, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.5431015510698907, "learning_rate": 3.3435761703329894e-05, "loss": 0.5551, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.5712818286505438, "learning_rate": 3.3393815802123606e-05, "loss": 0.5462, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.5403607003940298, "learning_rate": 3.335176280432308e-05, "loss": 0.5216, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.49970044384248813, "learning_rate": 3.330960304618295e-05, "loss": 0.5565, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.5694501870184657, "learning_rate": 3.326733686481153e-05, "loss": 0.5522, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.4336650523371355, "learning_rate": 3.3224964598168084e-05, "loss": 0.5341, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.5192368605163884, "learning_rate": 3.318248658506012e-05, "loss": 0.5553, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.4550531613849257, "learning_rate": 3.313990316514069e-05, "loss": 0.5446, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.49743390526165304, "learning_rate": 3.309721467890571e-05, "loss": 0.5349, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.44371838148491105, "learning_rate": 3.305442146769115e-05, "loss": 0.5374, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.43475872698459356, "learning_rate": 3.30115238736704e-05, "loss": 0.5296, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.4034768992259136, "learning_rate": 3.296852223985148e-05, "loss": 0.52, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4001018423850794, "learning_rate": 3.2925416910074315e-05, "loss": 0.5519, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.3800990315226268, "learning_rate": 3.288220822900796e-05, "loss": 0.5531, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.42523587965310555, "learning_rate": 3.283889654214788e-05, "loss": 0.5333, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.39462188737616566, "learning_rate": 3.279548219581317e-05, "loss": 0.5354, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.5057912094107899, "learning_rate": 3.275196553714379e-05, "loss": 0.5467, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.42681506239344796, "learning_rate": 3.270834691409778e-05, "loss": 0.5273, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.4341598444234669, "learning_rate": 3.266462667544849e-05, "loss": 0.5493, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.41370007104762563, "learning_rate": 3.262080517078178e-05, "loss": 0.5305, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.45126052318037974, "learning_rate": 3.257688275049323e-05, "loss": 0.5209, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.39525958566334596, "learning_rate": 3.253285976578535e-05, "loss": 0.516, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.4020982713706544, "learning_rate": 3.2488736568664756e-05, "loss": 0.5416, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.42900554492669707, "learning_rate": 3.244451351193935e-05, "loss": 0.5597, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.3789956995771035, "learning_rate": 3.240019094921551e-05, "loss": 0.5305, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.4768836973730779, "learning_rate": 3.235576923489527e-05, "loss": 0.5281, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.37795438973141937, "learning_rate": 3.2311248724173476e-05, "loss": 0.512, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.5029206204722503, "learning_rate": 3.226662977303494e-05, "loss": 0.5464, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4007756812662013, "learning_rate": 3.2221912738251626e-05, "loss": 0.5607, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.43402683596502445, "learning_rate": 3.2177097977379736e-05, "loss": 0.5521, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.43504804612003484, "learning_rate": 3.21321858487569e-05, "loss": 0.5455, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.41308837349830263, "learning_rate": 3.208717671149931e-05, "loss": 0.5346, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4274973426746321, "learning_rate": 3.204207092549882e-05, "loss": 0.5545, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.4952020670753913, "learning_rate": 3.19968688514201e-05, "loss": 0.5489, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.4291617561562027, "learning_rate": 3.195157085069774e-05, "loss": 0.5376, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.4722446862189365, "learning_rate": 3.190617728553332e-05, "loss": 0.5506, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.4376718286251849, "learning_rate": 3.1860688518892606e-05, "loss": 0.544, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.43222172268151465, "learning_rate": 3.181510491450254e-05, "loss": 0.5489, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.43891321325621974, "learning_rate": 3.176942683684842e-05, "loss": 0.5331, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.4159668621069411, "learning_rate": 3.1723654651170934e-05, "loss": 0.5362, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4056502779693788, "learning_rate": 3.167778872346327e-05, "loss": 0.5448, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.39268389026929296, "learning_rate": 3.163182942046815e-05, "loss": 0.5403, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.4560899684357969, "learning_rate": 3.158577710967494e-05, "loss": 0.5142, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.4016273652579926, "learning_rate": 3.153963215931669e-05, "loss": 0.5575, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.44053405710391164, "learning_rate": 3.14933949383672e-05, "loss": 0.5273, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.4513876327735859, "learning_rate": 3.144706581653805e-05, "loss": 0.5455, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.4445660729128112, "learning_rate": 3.140064516427566e-05, "loss": 0.531, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.44066687938354676, "learning_rate": 3.135413335275833e-05, "loss": 0.5453, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.41596670703869965, "learning_rate": 3.130753075389327e-05, "loss": 0.5347, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.5043403742419225, "learning_rate": 3.1260837740313625e-05, "loss": 0.5258, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.4010221063733586, "learning_rate": 3.121405468537547e-05, "loss": 0.5316, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.4914705662423459, "learning_rate": 3.116718196315488e-05, "loss": 0.5426, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4684277432406308, "learning_rate": 3.1120219948444894e-05, "loss": 0.5201, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.4272117582287086, "learning_rate": 3.107316901675252e-05, "loss": 0.5538, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.4545686187507757, "learning_rate": 3.1026029544295745e-05, "loss": 0.5455, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.4098738288722706, "learning_rate": 3.097880190800057e-05, "loss": 0.5389, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3923980816730232, "learning_rate": 3.093148648549788e-05, "loss": 0.5406, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4288005702662702, "learning_rate": 3.088408365512055e-05, "loss": 0.5236, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.39823479922572647, "learning_rate": 3.083659379590034e-05, "loss": 0.5545, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.46947602127723115, "learning_rate": 3.0789017287564913e-05, "loss": 0.5677, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.41336593146990025, "learning_rate": 3.074135451053475e-05, "loss": 0.5385, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.39303501214961356, "learning_rate": 3.069360584592015e-05, "loss": 0.5391, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.44038204439411943, "learning_rate": 3.064577167551816e-05, "loss": 0.5393, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.42472822149253975, "learning_rate": 3.059785238180953e-05, "loss": 0.5161, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.3842379760333588, "learning_rate": 3.054984834795566e-05, "loss": 0.5223, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.41222062192247794, "learning_rate": 3.0501759957795537e-05, "loss": 0.546, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.3633854946116158, "learning_rate": 3.0453587595842627e-05, "loss": 0.5133, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.41924600806447254, "learning_rate": 3.0405331647281856e-05, "loss": 0.5548, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.3907887019686506, "learning_rate": 3.0356992497966508e-05, "loss": 0.5258, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.4168972387338361, "learning_rate": 3.0308570534415137e-05, "loss": 0.5451, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.4076297341765684, "learning_rate": 3.0260066143808467e-05, "loss": 0.5388, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.3725416032850307, "learning_rate": 3.021147971398632e-05, "loss": 0.5245, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.38989750684105623, "learning_rate": 3.0162811633444478e-05, "loss": 0.5353, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.38054766484327096, "learning_rate": 3.0114062291331635e-05, "loss": 0.5522, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.46532707361445397, "learning_rate": 3.0065232077446217e-05, "loss": 0.5536, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.3825146202309846, "learning_rate": 3.001632138223332e-05, "loss": 0.5437, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.6729621077645546, "learning_rate": 2.9967330596781565e-05, "loss": 0.4471, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.6357519926204925, "learning_rate": 2.9918260112819952e-05, "loss": 0.4688, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.49742496522923624, "learning_rate": 2.9869110322714778e-05, "loss": 0.4401, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5729572675012902, "learning_rate": 2.9819881619466447e-05, "loss": 0.407, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.5219328004509503, "learning_rate": 2.9770574396706364e-05, "loss": 0.4497, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.4885345588601077, "learning_rate": 2.972118904869376e-05, "loss": 0.413, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.5288208766126837, "learning_rate": 2.9671725970312563e-05, "loss": 0.4376, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.451523817885433, "learning_rate": 2.9622185557068238e-05, "loss": 0.4149, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.496001790425184, "learning_rate": 2.95725682050846e-05, "loss": 0.4161, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.45402872650263837, "learning_rate": 2.9522874311100684e-05, "loss": 0.4417, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.5074772659430405, "learning_rate": 2.9473104272467526e-05, "loss": 0.4418, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.47252989699184805, "learning_rate": 2.942325848714505e-05, "loss": 0.4254, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.5140075208633182, "learning_rate": 2.9373337353698804e-05, "loss": 0.4654, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.5231102329389001, "learning_rate": 2.932334127129686e-05, "loss": 0.439, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.4551389931915876, "learning_rate": 2.9273270639706547e-05, "loss": 0.4252, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.55008850863246, "learning_rate": 2.922312585929131e-05, "loss": 0.4119, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.45430293858642823, "learning_rate": 2.9172907331007478e-05, "loss": 0.4431, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.5409920274169172, "learning_rate": 2.9122615456401053e-05, "loss": 0.4442, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.46746279525345397, "learning_rate": 2.9072250637604535e-05, "loss": 0.4074, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.4890747670654979, "learning_rate": 2.9021813277333667e-05, "loss": 0.4388, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.5630061103516046, "learning_rate": 2.8971303778884244e-05, "loss": 0.4385, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.39467011321238665, "learning_rate": 2.8920722546128863e-05, "loss": 0.4332, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.5445511700916427, "learning_rate": 2.887006998351372e-05, "loss": 0.4301, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.39758834436402374, "learning_rate": 2.881934649605535e-05, "loss": 0.4559, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.5301356070507672, "learning_rate": 2.8768552489337408e-05, "loss": 0.4406, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.43782187162720787, "learning_rate": 2.8717688369507425e-05, "loss": 0.4359, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.5349465390275551, "learning_rate": 2.8666754543273535e-05, "loss": 0.4294, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.4530719801836649, "learning_rate": 2.8615751417901273e-05, "loss": 0.4042, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.48415717650013923, "learning_rate": 2.856467940121025e-05, "loss": 0.438, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.49554437844196786, "learning_rate": 2.8513538901570964e-05, "loss": 0.4613, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.43783550038758956, "learning_rate": 2.846233032790149e-05, "loss": 0.419, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.3980356147825216, "learning_rate": 2.84110540896642e-05, "loss": 0.4199, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.42900003872953135, "learning_rate": 2.8359710596862555e-05, "loss": 0.4411, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.4226296322493978, "learning_rate": 2.8308300260037734e-05, "loss": 0.4466, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.43484515975755356, "learning_rate": 2.8256823490265424e-05, "loss": 0.4203, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.46211799462165426, "learning_rate": 2.8205280699152515e-05, "loss": 0.4392, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.43588445882987686, "learning_rate": 2.8153672298833777e-05, "loss": 0.4414, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.4359573182460058, "learning_rate": 2.8101998701968615e-05, "loss": 0.4242, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.4339817455221711, "learning_rate": 2.805026032173773e-05, "loss": 0.4384, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.42105658014062736, "learning_rate": 2.7998457571839832e-05, "loss": 0.4123, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.47910475018718635, "learning_rate": 2.7946590866488322e-05, "loss": 0.4298, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.4707543386320212, "learning_rate": 2.7894660620408e-05, "loss": 0.4294, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.5007442988302264, "learning_rate": 2.784266724883173e-05, "loss": 0.4292, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.46358136841091474, "learning_rate": 2.7790611167497128e-05, "loss": 0.4402, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.44361579221536296, "learning_rate": 2.7738492792643224e-05, "loss": 0.448, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.582863744677555, "learning_rate": 2.768631254100716e-05, "loss": 0.4516, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.43170026133920847, "learning_rate": 2.7634070829820836e-05, "loss": 0.4164, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.5656515778883333, "learning_rate": 2.7581768076807592e-05, "loss": 0.4222, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.41842626580829734, "learning_rate": 2.7529404700178832e-05, "loss": 0.4309, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.5714922030045507, "learning_rate": 2.7476981118630735e-05, "loss": 0.4326, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.489790829663918, "learning_rate": 2.742449775134085e-05, "loss": 0.446, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.46600411315072976, "learning_rate": 2.7371955017964788e-05, "loss": 0.4222, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.49670320489744363, "learning_rate": 2.7319353338632845e-05, "loss": 0.4288, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.38491611481400484, "learning_rate": 2.7266693133946645e-05, "loss": 0.4127, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.48013742300725, "learning_rate": 2.7213974824975785e-05, "loss": 0.4273, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.4269093381077101, "learning_rate": 2.7161198833254464e-05, "loss": 0.4606, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.49217665809413774, "learning_rate": 2.7108365580778095e-05, "loss": 0.4295, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.44536255749269793, "learning_rate": 2.705547548999996e-05, "loss": 0.4419, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.4748398697854764, "learning_rate": 2.7002528983827817e-05, "loss": 0.4221, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.4075721136634541, "learning_rate": 2.6949526485620517e-05, "loss": 0.4358, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.4244803033740132, "learning_rate": 2.6896468419184623e-05, "loss": 0.4396, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.4338466136504051, "learning_rate": 2.6843355208771024e-05, "loss": 0.4314, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.4031783707167606, "learning_rate": 2.6790187279071536e-05, "loss": 0.4397, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4570106354984998, "learning_rate": 2.67369650552155e-05, "loss": 0.4326, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.44555794682416516, "learning_rate": 2.6683688962766407e-05, "loss": 0.434, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.3845797309879818, "learning_rate": 2.6630359427718468e-05, "loss": 0.4433, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.43366785240628536, "learning_rate": 2.6576976876493225e-05, "loss": 0.4177, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.4328312262896802, "learning_rate": 2.652354173593614e-05, "loss": 0.4439, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.4623888782189375, "learning_rate": 2.647005443331317e-05, "loss": 0.4358, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.40720051217827835, "learning_rate": 2.6416515396307354e-05, "loss": 0.4351, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.4809665050920323, "learning_rate": 2.636292505301542e-05, "loss": 0.4218, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.41318168505518893, "learning_rate": 2.630928383194431e-05, "loss": 0.4324, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.45048486513764663, "learning_rate": 2.625559216200781e-05, "loss": 0.4222, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.5330202504607334, "learning_rate": 2.620185047252308e-05, "loss": 0.4398, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.41163650410093683, "learning_rate": 2.614805919320723e-05, "loss": 0.4592, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.4900210045150791, "learning_rate": 2.6094218754173895e-05, "loss": 0.4189, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.44234337626837217, "learning_rate": 2.60403295859298e-05, "loss": 0.4331, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.5075589290020899, "learning_rate": 2.5986392119371297e-05, "loss": 0.4363, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.4010293444062023, "learning_rate": 2.5932406785780928e-05, "loss": 0.4097, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.4491674531685835, "learning_rate": 2.5878374016823987e-05, "loss": 0.4465, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.4637813344298062, "learning_rate": 2.5824294244545045e-05, "loss": 0.4366, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.42679370848974857, "learning_rate": 2.577016790136453e-05, "loss": 0.4467, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.4454124545502148, "learning_rate": 2.5715995420075225e-05, "loss": 0.4393, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.3934745335832156, "learning_rate": 2.5661777233838864e-05, "loss": 0.4518, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.5185721190251783, "learning_rate": 2.5607513776182616e-05, "loss": 0.4187, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3892336286016316, "learning_rate": 2.5553205480995633e-05, "loss": 0.461, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.5380563429255518, "learning_rate": 2.5498852782525604e-05, "loss": 0.4472, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.39107073911194973, "learning_rate": 2.5444456115375252e-05, "loss": 0.4283, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.4847967338792219, "learning_rate": 2.539001591449889e-05, "loss": 0.4257, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.3927731248215943, "learning_rate": 2.53355326151989e-05, "loss": 0.4195, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.4491281040866904, "learning_rate": 2.5281006653122288e-05, "loss": 0.4224, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3929623443311021, "learning_rate": 2.5226438464257217e-05, "loss": 0.4163, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.4122204301230794, "learning_rate": 2.5171828484929447e-05, "loss": 0.4287, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.4037565870913012, "learning_rate": 2.5117177151798934e-05, "loss": 0.4275, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.425677003185945, "learning_rate": 2.506248490185627e-05, "loss": 0.4433, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.38279150622723973, "learning_rate": 2.500775217241923e-05, "loss": 0.4319, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.43327535732337386, "learning_rate": 2.4952979401129266e-05, "loss": 0.4446, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.3854834789257913, "learning_rate": 2.4898167025948e-05, "loss": 0.4225, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.44128014351001604, "learning_rate": 2.4843315485153703e-05, "loss": 0.4208, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.3653888788311031, "learning_rate": 2.4788425217337856e-05, "loss": 0.4325, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.42478391980327307, "learning_rate": 2.4733496661401572e-05, "loss": 0.4248, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.4119838620402723, "learning_rate": 2.4678530256552114e-05, "loss": 0.4256, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.3949325783685965, "learning_rate": 2.46235264422994e-05, "loss": 0.4447, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.39802381419827076, "learning_rate": 2.4568485658452452e-05, "loss": 0.4327, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.3949289144471177, "learning_rate": 2.451340834511592e-05, "loss": 0.457, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.41366995667820977, "learning_rate": 2.4458294942686528e-05, "loss": 0.4276, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.36129556581383504, "learning_rate": 2.440314589184958e-05, "loss": 0.4282, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.41099589488526017, "learning_rate": 2.434796163357541e-05, "loss": 0.4534, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3421545622986832, "learning_rate": 2.429274260911588e-05, "loss": 0.4396, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.3992631722047405, "learning_rate": 2.423748926000084e-05, "loss": 0.4185, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3641593522014568, "learning_rate": 2.418220202803459e-05, "loss": 0.4459, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3959859203741103, "learning_rate": 2.412688135529237e-05, "loss": 0.4477, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.3897679291918839, "learning_rate": 2.4071527684116807e-05, "loss": 0.4426, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.37468491732269876, "learning_rate": 2.4016141457114372e-05, "loss": 0.4346, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.36182990038884033, "learning_rate": 2.396072311715187e-05, "loss": 0.4246, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3711097704056697, "learning_rate": 2.3905273107352863e-05, "loss": 0.4283, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.37929990256692026, "learning_rate": 2.3849791871094157e-05, "loss": 0.4386, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.3948180631450716, "learning_rate": 2.379427985200223e-05, "loss": 0.4512, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.36584110631910555, "learning_rate": 2.373873749394972e-05, "loss": 0.408, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.3784293327878132, "learning_rate": 2.3683165241051836e-05, "loss": 0.4285, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.38754565566359817, "learning_rate": 2.3627563537662823e-05, "loss": 0.4365, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.39447090328820256, "learning_rate": 2.3571932828372433e-05, "loss": 0.4461, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.37686750061341984, "learning_rate": 2.351627355800233e-05, "loss": 0.4155, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.4833848610068439, "learning_rate": 2.346058617160256e-05, "loss": 0.4238, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.3707093243359014, "learning_rate": 2.3404871114447976e-05, "loss": 0.442, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.47630686597965055, "learning_rate": 2.334912883203469e-05, "loss": 0.4307, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.45043528224123236, "learning_rate": 2.3293359770076505e-05, "loss": 0.4328, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.47711449165999104, "learning_rate": 2.323756437450136e-05, "loss": 0.4261, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.39399519895988305, "learning_rate": 2.3181743091447754e-05, "loss": 0.4249, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.3542115884904491, "learning_rate": 2.3125896367261164e-05, "loss": 0.4497, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.41249423148919406, "learning_rate": 2.307002464849052e-05, "loss": 0.4626, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.3520238022940314, "learning_rate": 2.30141283818846e-05, "loss": 0.4416, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.4644082297334618, "learning_rate": 2.2958208014388462e-05, "loss": 0.4187, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.34705633223668453, "learning_rate": 2.2902263993139857e-05, "loss": 0.4347, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.46017435908731424, "learning_rate": 2.2846296765465708e-05, "loss": 0.4342, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.4025757632318471, "learning_rate": 2.2790306778878465e-05, "loss": 0.4506, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.4052036920395415, "learning_rate": 2.273429448107257e-05, "loss": 0.4356, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3943105974131594, "learning_rate": 2.2678260319920868e-05, "loss": 0.4178, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.3593341114215327, "learning_rate": 2.262220474347102e-05, "loss": 0.4348, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3823368573713626, "learning_rate": 2.2566128199941918e-05, "loss": 0.4249, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.38674414158510745, "learning_rate": 2.2510031137720104e-05, "loss": 0.4254, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.3647570576313808, "learning_rate": 2.2453914005356206e-05, "loss": 0.4219, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.38395483347100257, "learning_rate": 2.2397777251561302e-05, "loss": 0.442, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.37325699415345925, "learning_rate": 2.2341621325203393e-05, "loss": 0.4178, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3879086766758364, "learning_rate": 2.2285446675303764e-05, "loss": 0.4265, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.40677310372745573, "learning_rate": 2.2229253751033423e-05, "loss": 0.4408, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.37628280165880884, "learning_rate": 2.2173043001709492e-05, "loss": 0.4643, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.40479390340657406, "learning_rate": 2.2116814876791627e-05, "loss": 0.4526, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.40317933251954785, "learning_rate": 2.2060569825878413e-05, "loss": 0.4289, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.4184810930403859, "learning_rate": 2.2004308298703777e-05, "loss": 0.4148, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.39463373632801435, "learning_rate": 2.1948030745133396e-05, "loss": 0.4394, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.4324441106829139, "learning_rate": 2.1891737615161083e-05, "loss": 0.4485, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.36106562007606946, "learning_rate": 2.1835429358905218e-05, "loss": 0.4381, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3665130435511033, "learning_rate": 2.17791064266051e-05, "loss": 0.4339, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.4077800816928781, "learning_rate": 2.172276926861741e-05, "loss": 0.4235, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.39553396270416963, "learning_rate": 2.166641833541255e-05, "loss": 0.4404, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.39849268512049507, "learning_rate": 2.161005407757109e-05, "loss": 0.4166, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3690844440543086, "learning_rate": 2.155367694578013e-05, "loss": 0.4625, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.3834816040433844, "learning_rate": 2.1497287390829712e-05, "loss": 0.4397, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.39175199624633883, "learning_rate": 2.1440885863609208e-05, "loss": 0.4478, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.36684025858259967, "learning_rate": 2.1384472815103737e-05, "loss": 0.4253, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3780017167854875, "learning_rate": 2.1328048696390534e-05, "loss": 0.4343, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.3377707311339348, "learning_rate": 2.1271613958635342e-05, "loss": 0.4395, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.39567460379201713, "learning_rate": 2.1215169053088825e-05, "loss": 0.4381, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.36796881317579083, "learning_rate": 2.1158714431082937e-05, "loss": 0.4284, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.34482932875054, "learning_rate": 2.110225054402733e-05, "loss": 0.4436, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.39800021994430773, "learning_rate": 2.1045777843405747e-05, "loss": 0.4447, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.33517451170983714, "learning_rate": 2.09892967807724e-05, "loss": 0.4537, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.39200276317984306, "learning_rate": 2.093280780774835e-05, "loss": 0.4176, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.3558308642979411, "learning_rate": 2.087631137601793e-05, "loss": 0.4139, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.39484134968032314, "learning_rate": 2.0819807937325104e-05, "loss": 0.4216, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.3773452978801447, "learning_rate": 2.0763297943469847e-05, "loss": 0.4406, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.4047969073862156, "learning_rate": 2.070678184630458e-05, "loss": 0.4394, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.37365456591315566, "learning_rate": 2.06502600977305e-05, "loss": 0.4544, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3759722149735905, "learning_rate": 2.0593733149694008e-05, "loss": 0.4438, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3514450320847663, "learning_rate": 2.0537201454183074e-05, "loss": 0.4046, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.3319785158946259, "learning_rate": 2.0480665463223626e-05, "loss": 0.4156, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3340456989733811, "learning_rate": 2.042412562887594e-05, "loss": 0.4252, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.34572637821911084, "learning_rate": 2.0367582403231033e-05, "loss": 0.4194, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3504413260344169, "learning_rate": 2.0311036238407023e-05, "loss": 0.4, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.32890843612045295, "learning_rate": 2.0254487586545534e-05, "loss": 0.4267, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.33972062900987177, "learning_rate": 2.0197936899808088e-05, "loss": 0.4343, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3300334317752455, "learning_rate": 2.0141384630372466e-05, "loss": 0.4355, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.34941845209609274, "learning_rate": 2.0084831230429106e-05, "loss": 0.4293, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.3615518969683638, "learning_rate": 2.0028277152177492e-05, "loss": 0.4278, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.35871457465849077, "learning_rate": 1.9971722847822518e-05, "loss": 0.4123, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3533396224991382, "learning_rate": 1.99151687695709e-05, "loss": 0.4386, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.32043306668224303, "learning_rate": 1.9858615369627537e-05, "loss": 0.4322, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.3636007659646792, "learning_rate": 1.9802063100191916e-05, "loss": 0.4614, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.32838906488507946, "learning_rate": 1.974551241345447e-05, "loss": 0.429, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.3720299034873297, "learning_rate": 1.9688963761592984e-05, "loss": 0.4431, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.33998777821398085, "learning_rate": 1.963241759676897e-05, "loss": 0.435, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.3610345734162385, "learning_rate": 1.9575874371124066e-05, "loss": 0.4144, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.3537920622724643, "learning_rate": 1.951933453677638e-05, "loss": 0.4144, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.39047195645351807, "learning_rate": 1.9462798545816932e-05, "loss": 0.4441, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.3603075277853978, "learning_rate": 1.9406266850305996e-05, "loss": 0.431, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.3592111372318442, "learning_rate": 1.9349739902269503e-05, "loss": 0.4291, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3201822529856472, "learning_rate": 1.9293218153695425e-05, "loss": 0.4567, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.3647070474553045, "learning_rate": 1.9236702056530153e-05, "loss": 0.4302, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.3884569142679711, "learning_rate": 1.9180192062674907e-05, "loss": 0.4401, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.3379435495421954, "learning_rate": 1.9123688623982076e-05, "loss": 0.4146, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.37076879518546935, "learning_rate": 1.906719219225165e-05, "loss": 0.4493, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.34707601302359375, "learning_rate": 1.9010703219227603e-05, "loss": 0.4434, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.35451038008641655, "learning_rate": 1.8954222156594256e-05, "loss": 0.4236, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.36892057717158844, "learning_rate": 1.8897749455972673e-05, "loss": 0.4257, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.34987866685395436, "learning_rate": 1.884128556891707e-05, "loss": 0.4356, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.37647641651192054, "learning_rate": 1.878483094691119e-05, "loss": 0.4437, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.34830004923881264, "learning_rate": 1.8728386041364664e-05, "loss": 0.4478, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.3644821424281544, "learning_rate": 1.867195130360947e-05, "loss": 0.4293, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3651810736061893, "learning_rate": 1.8615527184896263e-05, "loss": 0.4248, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.355817443689133, "learning_rate": 1.8559114136390795e-05, "loss": 0.4547, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.33489865947186764, "learning_rate": 1.8502712609170298e-05, "loss": 0.4167, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.339388483486567, "learning_rate": 1.8446323054219876e-05, "loss": 0.4409, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.3650051637414312, "learning_rate": 1.838994592242891e-05, "loss": 0.4652, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.36760433907247797, "learning_rate": 1.8333581664587453e-05, "loss": 0.4255, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.379359750800627, "learning_rate": 1.8277230731382593e-05, "loss": 0.4506, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3493657092402995, "learning_rate": 1.82208935733949e-05, "loss": 0.4335, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.3224231151761662, "learning_rate": 1.8164570641094793e-05, "loss": 0.44, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3467604987105975, "learning_rate": 1.810826238483892e-05, "loss": 0.4416, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.34319708767022106, "learning_rate": 1.8051969254866608e-05, "loss": 0.4099, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.3464579743109789, "learning_rate": 1.7995691701296226e-05, "loss": 0.4189, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.35981406823741163, "learning_rate": 1.7939430174121593e-05, "loss": 0.4364, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.36734186739949376, "learning_rate": 1.788318512320838e-05, "loss": 0.4086, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3316368797209978, "learning_rate": 1.782695699829051e-05, "loss": 0.4379, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.36417083835349157, "learning_rate": 1.7770746248966587e-05, "loss": 0.4218, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.37631002942726227, "learning_rate": 1.7714553324696243e-05, "loss": 0.4317, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.35283128235080535, "learning_rate": 1.7658378674796614e-05, "loss": 0.4456, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.37337351718257894, "learning_rate": 1.76022227484387e-05, "loss": 0.4463, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.3903052929066931, "learning_rate": 1.7546085994643807e-05, "loss": 0.4319, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.3670660608481774, "learning_rate": 1.7489968862279902e-05, "loss": 0.4192, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3221217619168543, "learning_rate": 1.743387180005809e-05, "loss": 0.4433, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.3831210850227262, "learning_rate": 1.737779525652899e-05, "loss": 0.4498, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.33656885871755454, "learning_rate": 1.732173968007914e-05, "loss": 0.4138, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.391393419838225, "learning_rate": 1.7265705518927437e-05, "loss": 0.4392, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.3548793185120009, "learning_rate": 1.7209693221121542e-05, "loss": 0.4281, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.33406118542344143, "learning_rate": 1.7153703234534302e-05, "loss": 0.4282, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.3640963245873896, "learning_rate": 1.709773600686015e-05, "loss": 0.4346, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.3458432419182642, "learning_rate": 1.7041791985611548e-05, "loss": 0.4167, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.39480981302209217, "learning_rate": 1.69858716181154e-05, "loss": 0.4308, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.32351419818161925, "learning_rate": 1.692997535150948e-05, "loss": 0.4188, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.46263625574473083, "learning_rate": 1.687410363273884e-05, "loss": 0.4309, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3750042682244153, "learning_rate": 1.6818256908552257e-05, "loss": 0.4392, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.3542323895931522, "learning_rate": 1.6762435625498646e-05, "loss": 0.4333, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3876822204740183, "learning_rate": 1.67066402299235e-05, "loss": 0.4391, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.3150123313496533, "learning_rate": 1.6650871167965313e-05, "loss": 0.4316, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.36006500804849373, "learning_rate": 1.6595128885552028e-05, "loss": 0.431, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.3668868732439759, "learning_rate": 1.653941382839745e-05, "loss": 0.42, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.5243511331811983, "learning_rate": 1.6483726441997673e-05, "loss": 0.3696, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3845711096421284, "learning_rate": 1.642806717162757e-05, "loss": 0.3615, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.69156587805534, "learning_rate": 1.637243646233718e-05, "loss": 0.3633, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.3978683232483556, "learning_rate": 1.6316834758948174e-05, "loss": 0.3233, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.5480510154340127, "learning_rate": 1.6261262506050282e-05, "loss": 0.341, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4946805764842294, "learning_rate": 1.620572014799777e-05, "loss": 0.3398, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.3642648941705375, "learning_rate": 1.6150208128905857e-05, "loss": 0.3359, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.5350310316710383, "learning_rate": 1.6094726892647147e-05, "loss": 0.3786, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.4342035376540453, "learning_rate": 1.6039276882848135e-05, "loss": 0.3509, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.39407606946173485, "learning_rate": 1.5983858542885635e-05, "loss": 0.3314, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3930947257238725, "learning_rate": 1.5928472315883203e-05, "loss": 0.3279, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.4340403096160309, "learning_rate": 1.5873118644707633e-05, "loss": 0.3582, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.3682013584886686, "learning_rate": 1.5817797971965413e-05, "loss": 0.3511, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.3793417405861824, "learning_rate": 1.576251073999917e-05, "loss": 0.3306, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.4391134544431012, "learning_rate": 1.5707257390884126e-05, "loss": 0.3355, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.3811400821741092, "learning_rate": 1.5652038366424595e-05, "loss": 0.3481, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.38927337450400484, "learning_rate": 1.5596854108150424e-05, "loss": 0.3284, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3683615200827973, "learning_rate": 1.5541705057313476e-05, "loss": 0.3701, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3840965232826391, "learning_rate": 1.5486591654884086e-05, "loss": 0.3658, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.376440104065643, "learning_rate": 1.543151434154755e-05, "loss": 0.355, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.3581628573259911, "learning_rate": 1.5376473557700615e-05, "loss": 0.349, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.37527004147264376, "learning_rate": 1.5321469743447893e-05, "loss": 0.3577, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.36841970706079197, "learning_rate": 1.5266503338598434e-05, "loss": 0.3461, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.36250783413628895, "learning_rate": 1.5211574782662149e-05, "loss": 0.3506, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.42192915527638664, "learning_rate": 1.5156684514846307e-05, "loss": 0.3382, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.35339021900448025, "learning_rate": 1.5101832974052012e-05, "loss": 0.3345, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3261082303584934, "learning_rate": 1.5047020598870737e-05, "loss": 0.3248, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.4454937824271901, "learning_rate": 1.4992247827580778e-05, "loss": 0.3447, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.3598983330795707, "learning_rate": 1.493751509814374e-05, "loss": 0.3051, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.31097195242635134, "learning_rate": 1.4882822848201073e-05, "loss": 0.3677, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.4164037542125781, "learning_rate": 1.4828171515070553e-05, "loss": 0.3447, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3030772794118651, "learning_rate": 1.4773561535742793e-05, "loss": 0.3734, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.3383909694148308, "learning_rate": 1.4718993346877715e-05, "loss": 0.3811, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.4392653886165622, "learning_rate": 1.466446738480111e-05, "loss": 0.3487, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.32341796972863057, "learning_rate": 1.460998408550112e-05, "loss": 0.3508, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.31687015381616146, "learning_rate": 1.4555543884624751e-05, "loss": 0.3373, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.3643080718765697, "learning_rate": 1.4501147217474402e-05, "loss": 0.3474, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.31010555946779544, "learning_rate": 1.444679451900437e-05, "loss": 0.3446, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.3298020054040396, "learning_rate": 1.4392486223817397e-05, "loss": 0.3428, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3168997112760313, "learning_rate": 1.4338222766161143e-05, "loss": 0.3638, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.33467978812024074, "learning_rate": 1.4284004579924777e-05, "loss": 0.3506, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.3432523850238936, "learning_rate": 1.4229832098635479e-05, "loss": 0.3492, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.35382128014934294, "learning_rate": 1.4175705755454963e-05, "loss": 0.331, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.33007652520668307, "learning_rate": 1.412162598317602e-05, "loss": 0.3245, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.36034544951094205, "learning_rate": 1.406759321421907e-05, "loss": 0.3313, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.34090365716726256, "learning_rate": 1.401360788062871e-05, "loss": 0.3472, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.35459617542087357, "learning_rate": 1.3959670414070204e-05, "loss": 0.3262, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.3226705562804706, "learning_rate": 1.3905781245826108e-05, "loss": 0.3444, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.30832109528344714, "learning_rate": 1.3851940806792778e-05, "loss": 0.344, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.304703534709991, "learning_rate": 1.379814952747693e-05, "loss": 0.3359, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.3583420744716124, "learning_rate": 1.3744407837992193e-05, "loss": 0.3111, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.3081622578518997, "learning_rate": 1.3690716168055692e-05, "loss": 0.374, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.33041260892229174, "learning_rate": 1.363707494698459e-05, "loss": 0.3191, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.3057408831325129, "learning_rate": 1.358348460369265e-05, "loss": 0.3545, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.3070965415329181, "learning_rate": 1.352994556668684e-05, "loss": 0.3335, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3008362485381322, "learning_rate": 1.3476458264063865e-05, "loss": 0.3407, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.30596987625561756, "learning_rate": 1.342302312350678e-05, "loss": 0.3483, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3009371215896678, "learning_rate": 1.3369640572281537e-05, "loss": 0.3572, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.293733784547272, "learning_rate": 1.3316311037233596e-05, "loss": 0.3532, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.3014047130887242, "learning_rate": 1.326303494478451e-05, "loss": 0.3154, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.297346539339348, "learning_rate": 1.3209812720928472e-05, "loss": 0.3647, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.32410235840843676, "learning_rate": 1.315664479122898e-05, "loss": 0.3337, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.3033023105511427, "learning_rate": 1.3103531580815378e-05, "loss": 0.3462, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.2958137741013466, "learning_rate": 1.3050473514379488e-05, "loss": 0.3164, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.3132152617405624, "learning_rate": 1.2997471016172188e-05, "loss": 0.3608, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.29884059912970423, "learning_rate": 1.2944524510000042e-05, "loss": 0.3596, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.3155252176147482, "learning_rate": 1.2891634419221908e-05, "loss": 0.3274, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.32799013378705366, "learning_rate": 1.2838801166745545e-05, "loss": 0.3419, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.3317115978989365, "learning_rate": 1.2786025175024216e-05, "loss": 0.3306, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.31065802840760454, "learning_rate": 1.2733306866053357e-05, "loss": 0.3516, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.31596630084650285, "learning_rate": 1.2680646661367163e-05, "loss": 0.3501, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.33143885682710283, "learning_rate": 1.2628044982035219e-05, "loss": 0.338, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.3163875657984205, "learning_rate": 1.2575502248659155e-05, "loss": 0.3402, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.3500822806333854, "learning_rate": 1.2523018881369269e-05, "loss": 0.3441, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.3372856929821388, "learning_rate": 1.2470595299821176e-05, "loss": 0.3547, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.3224704125561126, "learning_rate": 1.2418231923192416e-05, "loss": 0.347, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.3214548346020048, "learning_rate": 1.2365929170179165e-05, "loss": 0.3465, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.329945896749683, "learning_rate": 1.2313687458992848e-05, "loss": 0.3609, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.3141142193155255, "learning_rate": 1.2261507207356785e-05, "loss": 0.3545, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.33099787799206476, "learning_rate": 1.220938883250288e-05, "loss": 0.3608, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.34056900742310914, "learning_rate": 1.215733275116827e-05, "loss": 0.346, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.31682640557786745, "learning_rate": 1.2105339379592005e-05, "loss": 0.3264, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.3208360046424932, "learning_rate": 1.2053409133511681e-05, "loss": 0.3455, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.3296629708173994, "learning_rate": 1.2001542428160173e-05, "loss": 0.3298, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.29727670897363495, "learning_rate": 1.1949739678262278e-05, "loss": 0.3288, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.3282859724891531, "learning_rate": 1.189800129803139e-05, "loss": 0.368, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.335129782949225, "learning_rate": 1.1846327701166228e-05, "loss": 0.3546, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.3266674390693627, "learning_rate": 1.1794719300847493e-05, "loss": 0.3348, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.3016095007874169, "learning_rate": 1.1743176509734582e-05, "loss": 0.3746, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.31161795235536793, "learning_rate": 1.1691699739962275e-05, "loss": 0.3259, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.32029741238328463, "learning_rate": 1.1640289403137456e-05, "loss": 0.3563, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.31616223767384194, "learning_rate": 1.1588945910335802e-05, "loss": 0.3524, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.30711375503550575, "learning_rate": 1.1537669672098517e-05, "loss": 0.3578, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.29593641771976187, "learning_rate": 1.1486461098429036e-05, "loss": 0.3432, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.3150436837260039, "learning_rate": 1.1435320598789747e-05, "loss": 0.3293, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.30329565165181144, "learning_rate": 1.1384248582098736e-05, "loss": 0.3455, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.3073598481400044, "learning_rate": 1.1333245456726467e-05, "loss": 0.3463, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.3172061497000428, "learning_rate": 1.128231163049258e-05, "loss": 0.3392, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.29999103002737615, "learning_rate": 1.123144751066259e-05, "loss": 0.3455, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.3039253184027857, "learning_rate": 1.1180653503944657e-05, "loss": 0.3657, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.3173428360286013, "learning_rate": 1.1129930016486287e-05, "loss": 0.3366, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2931220689151304, "learning_rate": 1.107927745387114e-05, "loss": 0.3772, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.29526102702984336, "learning_rate": 1.1028696221115766e-05, "loss": 0.3233, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.32241998527459403, "learning_rate": 1.0978186722666341e-05, "loss": 0.3295, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.3087763636361823, "learning_rate": 1.0927749362395475e-05, "loss": 0.3677, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.27598450791265283, "learning_rate": 1.0877384543598954e-05, "loss": 0.3561, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2973002833759415, "learning_rate": 1.0827092668992529e-05, "loss": 0.329, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.31048060953107814, "learning_rate": 1.077687414070869e-05, "loss": 0.3386, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.28581467420576223, "learning_rate": 1.0726729360293451e-05, "loss": 0.3601, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.29826345044317776, "learning_rate": 1.0676658728703147e-05, "loss": 0.3719, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.3067655851279488, "learning_rate": 1.0626662646301198e-05, "loss": 0.368, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.3077720902325854, "learning_rate": 1.0576741512854958e-05, "loss": 0.3317, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.2902641313672902, "learning_rate": 1.052689572753247e-05, "loss": 0.3517, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.29621502600456834, "learning_rate": 1.0477125688899328e-05, "loss": 0.3443, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.29396201214547907, "learning_rate": 1.0427431794915406e-05, "loss": 0.3229, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.31625832394591347, "learning_rate": 1.0377814442931769e-05, "loss": 0.3416, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.29410051661587483, "learning_rate": 1.0328274029687439e-05, "loss": 0.3394, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.3141556542431149, "learning_rate": 1.0278810951306253e-05, "loss": 0.3403, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.32320508442613005, "learning_rate": 1.0229425603293647e-05, "loss": 0.3372, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.30277244266111253, "learning_rate": 1.0180118380533558e-05, "loss": 0.3284, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2970902702142555, "learning_rate": 1.0130889677285225e-05, "loss": 0.343, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.29409015025366403, "learning_rate": 1.008173988718005e-05, "loss": 0.358, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2940093541243124, "learning_rate": 1.0032669403218439e-05, "loss": 0.333, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.32431531319496854, "learning_rate": 9.983678617766677e-06, "loss": 0.3399, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.283624244309531, "learning_rate": 9.934767922553788e-06, "loss": 0.3315, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2784384857281005, "learning_rate": 9.885937708668371e-06, "loss": 0.3601, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.30443574456425265, "learning_rate": 9.837188366555524e-06, "loss": 0.3429, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.27915135535214824, "learning_rate": 9.788520286013691e-06, "loss": 0.3571, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.29058559778745147, "learning_rate": 9.739933856191537e-06, "loss": 0.3322, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2928935295569154, "learning_rate": 9.691429465584866e-06, "loss": 0.3254, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.3073686219450123, "learning_rate": 9.643007502033492e-06, "loss": 0.3268, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.3016889895891988, "learning_rate": 9.594668352718152e-06, "loss": 0.3328, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.29359702735972115, "learning_rate": 9.546412404157383e-06, "loss": 0.356, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.27848148920169064, "learning_rate": 9.498240042204471e-06, "loss": 0.3644, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.28623989967516705, "learning_rate": 9.450151652044339e-06, "loss": 0.3277, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.32081370980017243, "learning_rate": 9.402147618190472e-06, "loss": 0.3515, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.3011162826382731, "learning_rate": 9.354228324481841e-06, "loss": 0.3534, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.2959365208544392, "learning_rate": 9.306394154079852e-06, "loss": 0.3592, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.29908363687045586, "learning_rate": 9.258645489465254e-06, "loss": 0.3397, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.2914590480552592, "learning_rate": 9.21098271243509e-06, "loss": 0.3446, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.2950696945630806, "learning_rate": 9.163406204099659e-06, "loss": 0.3611, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.28762578130419236, "learning_rate": 9.115916344879452e-06, "loss": 0.3471, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.2885565097579605, "learning_rate": 9.068513514502126e-06, "loss": 0.3429, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2775370603101277, "learning_rate": 9.021198091999439e-06, "loss": 0.3381, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.29984301684000947, "learning_rate": 8.973970455704251e-06, "loss": 0.3303, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.29081670748062144, "learning_rate": 8.926830983247495e-06, "loss": 0.3329, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.27268427008356066, "learning_rate": 8.879780051555116e-06, "loss": 0.37, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.28659498231678704, "learning_rate": 8.83281803684512e-06, "loss": 0.3353, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.28382529692039343, "learning_rate": 8.785945314624532e-06, "loss": 0.343, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.3070288727471501, "learning_rate": 8.739162259686385e-06, "loss": 0.3336, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.28581995065378996, "learning_rate": 8.692469246106734e-06, "loss": 0.3259, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.2571187916760253, "learning_rate": 8.645866647241677e-06, "loss": 0.3524, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.28156698417671955, "learning_rate": 8.599354835724348e-06, "loss": 0.3331, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.32058880621320923, "learning_rate": 8.552934183461958e-06, "loss": 0.3191, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2809165919278686, "learning_rate": 8.506605061632805e-06, "loss": 0.3429, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.28712581314569446, "learning_rate": 8.460367840683308e-06, "loss": 0.323, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.4538993469122704, "learning_rate": 8.414222890325065e-06, "loss": 0.3187, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2927258393592205, "learning_rate": 8.368170579531855e-06, "loss": 0.3417, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.3085082869346261, "learning_rate": 8.322211276536733e-06, "loss": 0.3407, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.29541479276753535, "learning_rate": 8.27634534882907e-06, "loss": 0.3372, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.2937121629986322, "learning_rate": 8.230573163151585e-06, "loss": 0.3625, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.28117718329247215, "learning_rate": 8.184895085497466e-06, "loss": 0.3491, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.3067209461992105, "learning_rate": 8.139311481107401e-06, "loss": 0.3417, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.29496343477969067, "learning_rate": 8.093822714466686e-06, "loss": 0.3184, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2994177411685386, "learning_rate": 8.048429149302271e-06, "loss": 0.3552, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2969913570212106, "learning_rate": 8.003131148579902e-06, "loss": 0.3383, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.29768196233644917, "learning_rate": 7.957929074501182e-06, "loss": 0.3394, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.28766791704053285, "learning_rate": 7.912823288500695e-06, "loss": 0.3412, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.31471996470592434, "learning_rate": 7.867814151243102e-06, "loss": 0.3659, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.30842709295288084, "learning_rate": 7.822902022620267e-06, "loss": 0.3385, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.2915569609746356, "learning_rate": 7.778087261748377e-06, "loss": 0.3276, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.3169120386201573, "learning_rate": 7.733370226965056e-06, "loss": 0.3181, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2925319434162726, "learning_rate": 7.688751275826527e-06, "loss": 0.349, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.3045572935469101, "learning_rate": 7.644230765104735e-06, "loss": 0.3834, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.315035024898235, "learning_rate": 7.599809050784502e-06, "loss": 0.3356, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.28134366858984633, "learning_rate": 7.555486488060661e-06, "loss": 0.3443, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2983286438638149, "learning_rate": 7.511263431335249e-06, "loss": 0.332, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.2761425832854257, "learning_rate": 7.467140234214656e-06, "loss": 0.3521, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.28289077708862387, "learning_rate": 7.423117249506777e-06, "loss": 0.3748, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.28949613636446847, "learning_rate": 7.379194829218231e-06, "loss": 0.353, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.27190057154796005, "learning_rate": 7.335373324551518e-06, "loss": 0.3694, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.28144656940131624, "learning_rate": 7.291653085902224e-06, "loss": 0.3317, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.27467109918927457, "learning_rate": 7.248034462856213e-06, "loss": 0.3747, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.30072377996228217, "learning_rate": 7.20451780418683e-06, "loss": 0.3576, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.2974203074078911, "learning_rate": 7.161103457852128e-06, "loss": 0.3451, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.2869441410550951, "learning_rate": 7.117791770992046e-06, "loss": 0.3516, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.28054595395555953, "learning_rate": 7.074583089925688e-06, "loss": 0.3449, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.2870531854930485, "learning_rate": 7.0314777601485155e-06, "loss": 0.3476, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.27964505874410067, "learning_rate": 6.988476126329604e-06, "loss": 0.3511, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.29140598958249186, "learning_rate": 6.945578532308857e-06, "loss": 0.3084, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.2883953160402072, "learning_rate": 6.902785321094301e-06, "loss": 0.3489, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.28779784077871395, "learning_rate": 6.8600968348593115e-06, "loss": 0.3586, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.30760894363949215, "learning_rate": 6.817513414939892e-06, "loss": 0.3502, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.28837688401598016, "learning_rate": 6.775035401831924e-06, "loss": 0.3365, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.2906546562387863, "learning_rate": 6.732663135188473e-06, "loss": 0.3319, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.3016568461926175, "learning_rate": 6.690396953817055e-06, "loss": 0.3223, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.28122910940700735, "learning_rate": 6.648237195676927e-06, "loss": 0.3605, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 1.9341487006931046, "learning_rate": 6.606184197876395e-06, "loss": 0.3256, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.2998338306284305, "learning_rate": 6.564238296670109e-06, "loss": 0.3258, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.28394904992213704, "learning_rate": 6.52239982745638e-06, "loss": 0.3453, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.30632877620009086, "learning_rate": 6.480669124774484e-06, "loss": 0.3585, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.2934864680894451, "learning_rate": 6.439046522302013e-06, "loss": 0.3453, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.28007945320243055, "learning_rate": 6.397532352852191e-06, "loss": 0.3276, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.30115617368033526, "learning_rate": 6.356126948371202e-06, "loss": 0.3282, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.30164140098693587, "learning_rate": 6.314830639935559e-06, "loss": 0.3334, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.28196267531903607, "learning_rate": 6.273643757749448e-06, "loss": 0.357, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.28099671900239787, "learning_rate": 6.2325666311420856e-06, "loss": 0.3367, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.2815744117645915, "learning_rate": 6.1915995885650675e-06, "loss": 0.3274, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.2878148026620032, "learning_rate": 6.150742957589784e-06, "loss": 0.3468, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2830158651879036, "learning_rate": 6.109997064904774e-06, "loss": 0.3408, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.29632432829525057, "learning_rate": 6.069362236313092e-06, "loss": 0.3389, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.293245684633204, "learning_rate": 6.0288387967297565e-06, "loss": 0.3651, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2834553315929654, "learning_rate": 5.988427070179108e-06, "loss": 0.3793, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.3043285767816467, "learning_rate": 5.948127379792234e-06, "loss": 0.3449, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.29728242812298455, "learning_rate": 5.90794004780439e-06, "loss": 0.3401, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.27578008647554453, "learning_rate": 5.867865395552405e-06, "loss": 0.3461, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.28610450185535585, "learning_rate": 5.8279037434721364e-06, "loss": 0.3365, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.27938210081352916, "learning_rate": 5.788055411095892e-06, "loss": 0.3248, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.27384461359414597, "learning_rate": 5.7483207170498625e-06, "loss": 0.3694, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.28522111532297273, "learning_rate": 5.708699979051613e-06, "loss": 0.3454, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2864764435765913, "learning_rate": 5.66919351390751e-06, "loss": 0.3599, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.28288162692029173, "learning_rate": 5.629801637510188e-06, "loss": 0.3621, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.3060026565051693, "learning_rate": 5.590524664836043e-06, "loss": 0.3556, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.29497431576660516, "learning_rate": 5.551362909942708e-06, "loss": 0.3474, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2935278614608358, "learning_rate": 5.51231668596653e-06, "loss": 0.3579, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.29549921520206945, "learning_rate": 5.47338630512007e-06, "loss": 0.3443, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.292703387496119, "learning_rate": 5.434572078689617e-06, "loss": 0.3498, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.30314567854568475, "learning_rate": 5.395874317032694e-06, "loss": 0.3671, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.2971160129765899, "learning_rate": 5.357293329575573e-06, "loss": 0.3645, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.3118909065808032, "learning_rate": 5.318829424810797e-06, "loss": 0.3063, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.27132851555891463, "learning_rate": 5.280482910294728e-06, "loss": 0.3455, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.28592727865584583, "learning_rate": 5.242254092645078e-06, "loss": 0.3336, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2938782535782394, "learning_rate": 5.2041432775384445e-06, "loss": 0.3642, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.2848573814184512, "learning_rate": 5.166150769707892e-06, "loss": 0.378, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.28858790012060526, "learning_rate": 5.128276872940503e-06, "loss": 0.3325, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.27990150595971536, "learning_rate": 5.090521890074953e-06, "loss": 0.3025, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.29552480262063585, "learning_rate": 5.0528861229990675e-06, "loss": 0.3078, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.2856939398838321, "learning_rate": 5.015369872647442e-06, "loss": 0.3402, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2790203923226061, "learning_rate": 4.9779734389990195e-06, "loss": 0.3656, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.30153400178948475, "learning_rate": 4.940697121074675e-06, "loss": 0.3423, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.27328087716093374, "learning_rate": 4.903541216934864e-06, "loss": 0.34, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.27348745446835226, "learning_rate": 4.8665060236772e-06, "loss": 0.3388, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.296472666635798, "learning_rate": 4.829591837434102e-06, "loss": 0.3349, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.29070366726827274, "learning_rate": 4.792798953370424e-06, "loss": 0.325, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.29663563067027227, "learning_rate": 4.756127665681083e-06, "loss": 0.3293, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2793752093020425, "learning_rate": 4.719578267588725e-06, "loss": 0.3477, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.30051780066978795, "learning_rate": 4.6831510513413525e-06, "loss": 0.3428, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.42622259916796795, "learning_rate": 4.6468463082100176e-06, "loss": 0.3051, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.33170784626357275, "learning_rate": 4.610664328486485e-06, "loss": 0.2862, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.2588598334291672, "learning_rate": 4.5746054014809e-06, "loss": 0.2922, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.35396469037249545, "learning_rate": 4.5386698155194766e-06, "loss": 0.288, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.40153754301947386, "learning_rate": 4.502857857942204e-06, "loss": 0.2731, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.4114523448720682, "learning_rate": 4.467169815100549e-06, "loss": 0.2925, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.299236734012728, "learning_rate": 4.431605972355137e-06, "loss": 0.301, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.3143739588704389, "learning_rate": 4.396166614073516e-06, "loss": 0.2679, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.34107886705418644, "learning_rate": 4.360852023627846e-06, "loss": 0.2999, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.341900891128967, "learning_rate": 4.325662483392656e-06, "loss": 0.2973, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.30077120104269434, "learning_rate": 4.29059827474257e-06, "loss": 0.3054, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.27506397088683254, "learning_rate": 4.255659678050063e-06, "loss": 0.3018, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.30299172782225553, "learning_rate": 4.22084697268323e-06, "loss": 0.2939, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.3152972986488083, "learning_rate": 4.186160437003535e-06, "loss": 0.3079, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.31855726812024016, "learning_rate": 4.151600348363582e-06, "loss": 0.2873, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.3425567239531563, "learning_rate": 4.11716698310493e-06, "loss": 0.3019, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.27599921745805767, "learning_rate": 4.082860616555848e-06, "loss": 0.2977, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.2681368612965345, "learning_rate": 4.048681523029125e-06, "loss": 0.2883, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.29884189567000724, "learning_rate": 4.014629975819882e-06, "loss": 0.2675, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.2844102569466409, "learning_rate": 3.9807062472033855e-06, "loss": 0.2912, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2727054847054293, "learning_rate": 3.94691060843287e-06, "loss": 0.3109, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.2599754014911471, "learning_rate": 3.913243329737353e-06, "loss": 0.2682, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.2694716496036917, "learning_rate": 3.879704680319503e-06, "loss": 0.3142, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.27235133056200667, "learning_rate": 3.846294928353471e-06, "loss": 0.2855, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.2726804588144115, "learning_rate": 3.8130143409827345e-06, "loss": 0.3042, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.24684059636488823, "learning_rate": 3.7798631843179887e-06, "loss": 0.2649, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2519371236118448, "learning_rate": 3.7468417234349973e-06, "loss": 0.2996, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.24513407493755218, "learning_rate": 3.7139502223724823e-06, "loss": 0.2948, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2330645478876944, "learning_rate": 3.6811889441300095e-06, "loss": 0.3115, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2602860511629226, "learning_rate": 3.648558150665886e-06, "loss": 0.3068, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.24324938267511514, "learning_rate": 3.616058102895075e-06, "loss": 0.2976, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.25130157816154663, "learning_rate": 3.583689060687079e-06, "loss": 0.2888, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.2607534625493829, "learning_rate": 3.5514512828639023e-06, "loss": 0.3056, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.25856357696763377, "learning_rate": 3.51934502719796e-06, "loss": 0.3035, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.25793217307126254, "learning_rate": 3.4873705504100185e-06, "loss": 0.2607, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.25738055487558226, "learning_rate": 3.4555281081671345e-06, "loss": 0.2721, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.23847678503633485, "learning_rate": 3.4238179550806326e-06, "loss": 0.2947, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.24816560038444999, "learning_rate": 3.3922403447040497e-06, "loss": 0.2897, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.258092594962533, "learning_rate": 3.3607955295311247e-06, "loss": 0.2516, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2573361892187611, "learning_rate": 3.32948376099375e-06, "loss": 0.3007, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.24285226038977856, "learning_rate": 3.2983052894599976e-06, "loss": 0.301, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.25454214265311437, "learning_rate": 3.2672603642320945e-06, "loss": 0.2883, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2580220378571504, "learning_rate": 3.236349233544438e-06, "loss": 0.2706, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.24967190191730765, "learning_rate": 3.205572144561604e-06, "loss": 0.2933, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.25201543578036095, "learning_rate": 3.174929343376374e-06, "loss": 0.2959, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.256633507799153, "learning_rate": 3.1444210750077777e-06, "loss": 0.3069, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2578167358049242, "learning_rate": 3.1140475833991046e-06, "loss": 0.2746, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.25894391298815167, "learning_rate": 3.0838091114159895e-06, "loss": 0.2534, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.23919964977363742, "learning_rate": 3.0537059008444524e-06, "loss": 0.2632, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2437535969880482, "learning_rate": 3.0237381923889563e-06, "loss": 0.2789, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.260574690833428, "learning_rate": 2.9939062256704997e-06, "loss": 0.2906, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.2373705010501919, "learning_rate": 2.964210239224696e-06, "loss": 0.2855, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.24989227066358968, "learning_rate": 2.934650470499869e-06, "loss": 0.2783, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.24442607431231234, "learning_rate": 2.905227155855128e-06, "loss": 0.2687, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.24584968375374763, "learning_rate": 2.875940530558519e-06, "loss": 0.2825, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2388941528993369, "learning_rate": 2.8467908287851154e-06, "loss": 0.2835, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.24078858522654437, "learning_rate": 2.8177782836151603e-06, "loss": 0.2661, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2535424213060705, "learning_rate": 2.7889031270321874e-06, "loss": 0.2526, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2547516513177257, "learning_rate": 2.760165589921184e-06, "loss": 0.2653, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.2617301214721082, "learning_rate": 2.7315659020667305e-06, "loss": 0.2751, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.22706007761512467, "learning_rate": 2.703104292151164e-06, "loss": 0.2849, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.24197221703761165, "learning_rate": 2.6747809877527607e-06, "loss": 0.2908, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.24498655332828248, "learning_rate": 2.6465962153439082e-06, "loss": 0.3056, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.23956326494354063, "learning_rate": 2.618550200289303e-06, "loss": 0.3007, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2575445877205495, "learning_rate": 2.59064316684412e-06, "loss": 0.2793, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.2467496065584509, "learning_rate": 2.562875338152264e-06, "loss": 0.2953, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.2595231037034403, "learning_rate": 2.5352469362445552e-06, "loss": 0.2934, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.250564728208201, "learning_rate": 2.5077581820369523e-06, "loss": 0.2945, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.23741367268922503, "learning_rate": 2.480409295328803e-06, "loss": 0.3104, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.23957436326320175, "learning_rate": 2.45320049480108e-06, "loss": 0.3209, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.23809537761973823, "learning_rate": 2.4261319980146293e-06, "loss": 0.3112, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.2507503217869511, "learning_rate": 2.399204021408421e-06, "loss": 0.2849, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.24121065491570676, "learning_rate": 2.3724167802978395e-06, "loss": 0.2817, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.23954626676789997, "learning_rate": 2.3457704888729625e-06, "loss": 0.3293, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.24172757072151488, "learning_rate": 2.3192653601968162e-06, "loss": 0.2968, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.23925324256946473, "learning_rate": 2.2929016062037057e-06, "loss": 0.2754, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.23440222371941336, "learning_rate": 2.2666794376975055e-06, "loss": 0.3007, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.23794237502200455, "learning_rate": 2.24059906434998e-06, "loss": 0.268, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.24523997157241975, "learning_rate": 2.214660694699091e-06, "loss": 0.2853, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.26410346525287476, "learning_rate": 2.188864536147355e-06, "loss": 0.3042, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2444882822662636, "learning_rate": 2.1632107949601757e-06, "loss": 0.2923, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.25403618938287065, "learning_rate": 2.137699676264171e-06, "loss": 0.2864, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.23837954291615593, "learning_rate": 2.1123313840455738e-06, "loss": 0.2954, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.24365920522233292, "learning_rate": 2.08710612114857e-06, "loss": 0.2851, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.244486745419509, "learning_rate": 2.0620240892736953e-06, "loss": 0.2869, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.23953069211594058, "learning_rate": 2.0370854889762e-06, "loss": 0.3288, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.23265946663895634, "learning_rate": 2.0122905196644726e-06, "loss": 0.3245, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.23649858258892775, "learning_rate": 1.987639379598427e-06, "loss": 0.2798, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.239788206237722, "learning_rate": 1.963132265887919e-06, "loss": 0.297, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.24200954431987537, "learning_rate": 1.9387693744911784e-06, "loss": 0.309, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.24442426288903926, "learning_rate": 1.9145509002132368e-06, "loss": 0.2959, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.24733854855993476, "learning_rate": 1.8904770367043723e-06, "loss": 0.2795, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.24094552568998212, "learning_rate": 1.8665479764585504e-06, "loss": 0.3014, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2394035654360483, "learning_rate": 1.8427639108118977e-06, "loss": 0.3066, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2302431768012655, "learning_rate": 1.8191250299411755e-06, "loss": 0.3095, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.23918689127547546, "learning_rate": 1.7956315228622446e-06, "loss": 0.2884, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2356170666921506, "learning_rate": 1.7722835774285553e-06, "loss": 0.301, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.24605382701743025, "learning_rate": 1.7490813803296624e-06, "loss": 0.293, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.23532917970935904, "learning_rate": 1.726025117089718e-06, "loss": 0.2919, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.23239444945642534, "learning_rate": 1.70311497206598e-06, "loss": 0.2891, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.23063068888791094, "learning_rate": 1.6803511284473638e-06, "loss": 0.3023, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.22799637431894273, "learning_rate": 1.6577337682529538e-06, "loss": 0.3105, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.23601630640953908, "learning_rate": 1.6352630723305617e-06, "loss": 0.3119, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.2381354389227765, "learning_rate": 1.612939220355272e-06, "loss": 0.295, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.24994845175009792, "learning_rate": 1.5907623908280112e-06, "loss": 0.3047, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.26399875790530236, "learning_rate": 1.568732761074121e-06, "loss": 0.2688, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.2546431687106848, "learning_rate": 1.5468505072419237e-06, "loss": 0.2688, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.24581425012956945, "learning_rate": 1.5251158043013448e-06, "loss": 0.2958, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.25173120619567907, "learning_rate": 1.5035288260424885e-06, "loss": 0.3029, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.23891932450901385, "learning_rate": 1.4820897450742623e-06, "loss": 0.3079, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2564717812483322, "learning_rate": 1.4607987328229767e-06, "loss": 0.2809, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.2508131482813402, "learning_rate": 1.4396559595310056e-06, "loss": 0.2837, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.23498852040215623, "learning_rate": 1.4186615942553973e-06, "loss": 0.2827, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2563837901067941, "learning_rate": 1.3978158048665424e-06, "loss": 0.2886, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.23297646452564078, "learning_rate": 1.3771187580468115e-06, "loss": 0.2764, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.23916911203317817, "learning_rate": 1.3565706192892392e-06, "loss": 0.2905, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.23454579809543272, "learning_rate": 1.3361715528961993e-06, "loss": 0.3107, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.23517034574464238, "learning_rate": 1.3159217219780817e-06, "loss": 0.267, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.2739808058718784, "learning_rate": 1.2958212884519949e-06, "loss": 0.2947, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.2307133957859913, "learning_rate": 1.2758704130404675e-06, "loss": 0.3018, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.23119541999241863, "learning_rate": 1.2560692552701738e-06, "loss": 0.2947, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.2422696657746169, "learning_rate": 1.2364179734706382e-06, "loss": 0.2901, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.2334759946876166, "learning_rate": 1.2169167247729852e-06, "loss": 0.3023, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.23856085061575955, "learning_rate": 1.1975656651086864e-06, "loss": 0.327, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.22108742214482713, "learning_rate": 1.1783649492082926e-06, "loss": 0.3076, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.25878998690780264, "learning_rate": 1.1593147306002183e-06, "loss": 0.2696, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2329555649931119, "learning_rate": 1.140415161609505e-06, "loss": 0.3034, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.2419308344343573, "learning_rate": 1.121666393356604e-06, "loss": 0.2806, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.22609052877531577, "learning_rate": 1.1030685757561632e-06, "loss": 0.3217, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.2307546802170943, "learning_rate": 1.0846218575158373e-06, "loss": 0.2962, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.22555294773584053, "learning_rate": 1.066326386135097e-06, "loss": 0.3075, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.23327495710726667, "learning_rate": 1.0481823079040398e-06, "loss": 0.2888, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.24755837788173612, "learning_rate": 1.0301897679022344e-06, "loss": 0.2409, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.2408210211561996, "learning_rate": 1.0123489099975491e-06, "loss": 0.2946, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.23639459745858057, "learning_rate": 9.9465987684501e-07, "loss": 0.2639, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.24190209641837288, "learning_rate": 9.771228098856534e-07, "loss": 0.3192, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.22767458767917118, "learning_rate": 9.597378493454013e-07, "loss": 0.278, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.23736043554484162, "learning_rate": 9.425051342339353e-07, "loss": 0.2992, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.2363398667303458, "learning_rate": 9.254248023435864e-07, "loss": 0.2899, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.24701413411118614, "learning_rate": 9.084969902482288e-07, "loss": 0.3062, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.23530081656181473, "learning_rate": 8.917218333021993e-07, "loss": 0.2897, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.24018273977427432, "learning_rate": 8.750994656392109e-07, "loss": 0.2873, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.24555634884787517, "learning_rate": 8.58630020171265e-07, "loss": 0.293, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.23882608493413032, "learning_rate": 8.423136285876099e-07, "loss": 0.2938, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.25240648379141817, "learning_rate": 8.26150421353682e-07, "loss": 0.2814, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.24595118819220324, "learning_rate": 8.101405277100549e-07, "loss": 0.2657, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.24163573020081927, "learning_rate": 7.942840756714077e-07, "loss": 0.3066, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.24037513906275781, "learning_rate": 7.785811920255093e-07, "loss": 0.3038, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.24162382100361066, "learning_rate": 7.630320023322024e-07, "loss": 0.2986, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.24698213752327325, "learning_rate": 7.476366309223903e-07, "loss": 0.2964, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.237469292705914, "learning_rate": 7.323952008970537e-07, "loss": 0.2709, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2514963954078106, "learning_rate": 7.173078341262618e-07, "loss": 0.2855, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2533989693982166, "learning_rate": 7.023746512481989e-07, "loss": 0.2742, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2315296634138559, "learning_rate": 6.875957716681902e-07, "loss": 0.2791, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.24109678822002145, "learning_rate": 6.729713135577687e-07, "loss": 0.3013, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.24094147667115529, "learning_rate": 6.585013938537143e-07, "loss": 0.2752, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.2547773380835246, "learning_rate": 6.441861282571115e-07, "loss": 0.3067, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.23976325685371117, "learning_rate": 6.300256312324471e-07, "loss": 0.2905, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2429833791296931, "learning_rate": 6.160200160066776e-07, "loss": 0.2996, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.22754432663174626, "learning_rate": 6.021693945683327e-07, "loss": 0.2766, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.23729248583580395, "learning_rate": 5.884738776666044e-07, "loss": 0.2829, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.24342055656050046, "learning_rate": 5.749335748104878e-07, "loss": 0.2913, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.23763496480351745, "learning_rate": 5.615485942678778e-07, "loss": 0.3007, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.24284475964029778, "learning_rate": 5.483190430647289e-07, "loss": 0.3111, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.2407261036980888, "learning_rate": 5.352450269841747e-07, "loss": 0.288, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.24734361876319166, "learning_rate": 5.22326650565701e-07, "loss": 0.2738, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.23186992212824076, "learning_rate": 5.095640171043048e-07, "loss": 0.2908, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.23254534183020698, "learning_rate": 4.969572286496594e-07, "loss": 0.2781, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.23498251201895334, "learning_rate": 4.845063860053079e-07, "loss": 0.2946, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.23531793198503884, "learning_rate": 4.7221158872785997e-07, "loss": 0.2895, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.23088317232752623, "learning_rate": 4.600729351261857e-07, "loss": 0.269, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.24993439702045556, "learning_rate": 4.4809052226063355e-07, "loss": 0.2771, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.23183128593032612, "learning_rate": 4.3626444594226046e-07, "loss": 0.291, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.238821175736498, "learning_rate": 4.245948007320588e-07, "loss": 0.2898, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.2440710238864394, "learning_rate": 4.130816799401971e-07, "loss": 0.2886, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.24456959464319278, "learning_rate": 4.017251756252827e-07, "loss": 0.2764, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.23647800838850383, "learning_rate": 3.9052537859362473e-07, "loss": 0.2792, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.24599026687365902, "learning_rate": 3.7948237839849687e-07, "loss": 0.2837, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.23589432247688116, "learning_rate": 3.6859626333943797e-07, "loss": 0.2973, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.2298992947945079, "learning_rate": 3.578671204615347e-07, "loss": 0.2851, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.23516865523078462, "learning_rate": 3.472950355547267e-07, "loss": 0.3259, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.24482260144349677, "learning_rate": 3.3688009315312244e-07, "loss": 0.2524, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.23630286660666602, "learning_rate": 3.266223765343224e-07, "loss": 0.2896, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.23330821370682253, "learning_rate": 3.16521967718757e-07, "loss": 0.2698, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.23699617096087866, "learning_rate": 3.0657894746902726e-07, "loss": 0.2832, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.2345508645847944, "learning_rate": 2.9679339528925654e-07, "loss": 0.2873, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.24141675111627575, "learning_rate": 2.871653894244597e-07, "loss": 0.3002, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2498548410421936, "learning_rate": 2.7769500685991266e-07, "loss": 0.2693, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.22962250612831567, "learning_rate": 2.683823233205485e-07, "loss": 0.2775, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.2562790448599486, "learning_rate": 2.592274132703287e-07, "loss": 0.2926, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.24031626330964453, "learning_rate": 2.502303499116754e-07, "loss": 0.2966, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.22710105390522625, "learning_rate": 2.413912051848666e-07, "loss": 0.2899, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.2294496559408616, "learning_rate": 2.3271004976746613e-07, "loss": 0.2871, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2393776767189861, "learning_rate": 2.2418695307376393e-07, "loss": 0.2794, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.234570220680637, "learning_rate": 2.1582198325420968e-07, "loss": 0.2813, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.22467938462994763, "learning_rate": 2.0761520719488447e-07, "loss": 0.3285, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.22932617699165966, "learning_rate": 1.9956669051694798e-07, "loss": 0.2757, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.24919567922751834, "learning_rate": 1.916764975761254e-07, "loss": 0.2914, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2528823244141749, "learning_rate": 1.839446914621923e-07, "loss": 0.2821, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.22563627523891028, "learning_rate": 1.7637133399845962e-07, "loss": 0.3072, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.24147758041150996, "learning_rate": 1.6895648574129397e-07, "loss": 0.2684, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.23446238154449217, "learning_rate": 1.6170020597962465e-07, "loss": 0.2779, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.23483302620685917, "learning_rate": 1.5460255273447078e-07, "loss": 0.2849, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.3027431041961462, "learning_rate": 1.4766358275847715e-07, "loss": 0.2849, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.23848601061458663, "learning_rate": 1.4088335153546573e-07, "loss": 0.3121, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.23772286522764755, "learning_rate": 1.3426191327998496e-07, "loss": 0.2809, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.23842724470943966, "learning_rate": 1.277993209368744e-07, "loss": 0.2872, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.23784984688240654, "learning_rate": 1.214956261808542e-07, "loss": 0.265, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.23706437540607925, "learning_rate": 1.1535087941609846e-07, "loss": 0.2845, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.24920702705514805, "learning_rate": 1.0936512977583802e-07, "loss": 0.2816, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.2400776759595583, "learning_rate": 1.0353842512196732e-07, "loss": 0.3004, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.24625287802606222, "learning_rate": 9.787081204466253e-08, "loss": 0.2986, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.22828316593954986, "learning_rate": 9.236233586200627e-08, "loss": 0.2912, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.25403507074974635, "learning_rate": 8.70130406196279e-08, "loss": 0.3008, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.25514627502199255, "learning_rate": 8.182296909035047e-08, "loss": 0.3027, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.23479148586678153, "learning_rate": 7.679216277384439e-08, "loss": 0.2877, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2273017789722254, "learning_rate": 7.19206618963053e-08, "loss": 0.278, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.24227344776244186, "learning_rate": 6.720850541012347e-08, "loss": 0.3168, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.23172794227069204, "learning_rate": 6.265573099357714e-08, "loss": 0.3063, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.23479652917823482, "learning_rate": 5.826237505053067e-08, "loss": 0.2838, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.23593520601536735, "learning_rate": 5.4028472710137e-08, "loss": 0.2939, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.24198368149353278, "learning_rate": 4.9954057826571146e-08, "loss": 0.2649, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2335754442553692, "learning_rate": 4.6039162978743776e-08, "loss": 0.2861, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.23487223767760215, "learning_rate": 4.228381947004812e-08, "loss": 0.2884, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.23833454328909398, "learning_rate": 3.868805732811343e-08, "loss": 0.2712, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.23120350018551356, "learning_rate": 3.525190530455636e-08, "loss": 0.2937, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.24047255553417785, "learning_rate": 3.197539087475887e-08, "loss": 0.3012, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2417554709411307, "learning_rate": 2.8858540237641786e-08, "loss": 0.2748, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.2218451791908883, "learning_rate": 2.5901378315458247e-08, "loss": 0.2871, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.22926514209471918, "learning_rate": 2.3103928753598347e-08, "loss": 0.2941, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.23723437876107878, "learning_rate": 2.0466213920393718e-08, "loss": 0.2887, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.24432284442051044, "learning_rate": 1.7988254906942115e-08, "loss": 0.3053, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.24670819607928177, "learning_rate": 1.5670071526936447e-08, "loss": 0.2825, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.23111561654765153, "learning_rate": 1.3511682316509344e-08, "loss": 0.3113, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.2314475735250837, "learning_rate": 1.1513104534086605e-08, "loss": 0.2974, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.2202647535880046, "learning_rate": 9.67435416023843e-09, "loss": 0.3037, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.23159635063525197, "learning_rate": 7.995445897566178e-09, "loss": 0.3286, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.22886047328567577, "learning_rate": 6.476393170578021e-09, "loss": 0.2819, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.24139445690963807, "learning_rate": 5.11720812557348e-09, "loss": 0.2765, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.2508565708958291, "learning_rate": 3.917901630563492e-09, "loss": 0.2854, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2239889852478667, "learning_rate": 2.878483275170485e-09, "loss": 0.3056, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.24051010891340874, "learning_rate": 1.998961370555108e-09, "loss": 0.2575, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.2422976277508279, "learning_rate": 1.2793429493518361e-09, "loss": 0.2984, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.22819213650702944, "learning_rate": 7.196337656112384e-10, "loss": 0.3162, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.23466147141388177, "learning_rate": 3.198382947511292e-10, "loss": 0.3034, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.22860331941397957, "learning_rate": 7.995973352770137e-11, "loss": 0.3282, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.2299908018165873, "learning_rate": 0.0, "loss": 0.291, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 3.0981921380100997e+18, "train_loss": 0.0, "train_runtime": 1.72, "train_samples_per_second": 91859.139, "train_steps_per_second": 718.013 } ], "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": 3.0981921380100997e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }