{ "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": 6.460281512780675, "learning_rate": 3.2258064516129035e-07, "loss": 1.0413, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.466791060308555, "learning_rate": 6.451612903225807e-07, "loss": 1.0413, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.565133227174678, "learning_rate": 9.67741935483871e-07, "loss": 1.0603, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.224827344574061, "learning_rate": 1.2903225806451614e-06, "loss": 1.0374, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.046512561501461, "learning_rate": 1.6129032258064516e-06, "loss": 1.0288, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.779263160577111, "learning_rate": 1.935483870967742e-06, "loss": 1.013, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.541229108446014, "learning_rate": 2.2580645161290324e-06, "loss": 0.9917, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.237898036408897, "learning_rate": 2.580645161290323e-06, "loss": 0.995, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.7288759891983583, "learning_rate": 2.903225806451613e-06, "loss": 0.9524, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.5446345556670145, "learning_rate": 3.225806451612903e-06, "loss": 0.9649, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.475842251721532, "learning_rate": 3.548387096774194e-06, "loss": 0.9674, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.737989575720358, "learning_rate": 3.870967741935484e-06, "loss": 0.9473, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.0769848158428585, "learning_rate": 4.193548387096774e-06, "loss": 0.9389, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.9128431444115335, "learning_rate": 4.516129032258065e-06, "loss": 0.932, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.4822120899673648, "learning_rate": 4.838709677419355e-06, "loss": 0.9049, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.636667128499736, "learning_rate": 5.161290322580646e-06, "loss": 0.8665, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.5391345204239975, "learning_rate": 5.483870967741935e-06, "loss": 0.8955, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.069648774835288, "learning_rate": 5.806451612903226e-06, "loss": 0.8625, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.5744590766833744, "learning_rate": 6.129032258064517e-06, "loss": 0.8593, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.0972613978359071, "learning_rate": 6.451612903225806e-06, "loss": 0.8309, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 0.9910287050195916, "learning_rate": 6.774193548387097e-06, "loss": 0.8201, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.1665511392844539, "learning_rate": 7.096774193548388e-06, "loss": 0.8131, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.0384218402564456, "learning_rate": 7.4193548387096784e-06, "loss": 0.8091, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.9015268947671208, "learning_rate": 7.741935483870968e-06, "loss": 0.8009, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 0.8898398172388866, "learning_rate": 8.064516129032258e-06, "loss": 0.7682, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.795899027058141, "learning_rate": 8.387096774193549e-06, "loss": 0.784, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.7522380859801308, "learning_rate": 8.70967741935484e-06, "loss": 0.7769, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.7687106550565861, "learning_rate": 9.03225806451613e-06, "loss": 0.7744, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.7589942402402159, "learning_rate": 9.35483870967742e-06, "loss": 0.7644, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.6971213893418907, "learning_rate": 9.67741935483871e-06, "loss": 0.7431, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6166078768243743, "learning_rate": 1e-05, "loss": 0.7603, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.6305010341568069, "learning_rate": 1.0322580645161291e-05, "loss": 0.746, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6575646779080322, "learning_rate": 1.0645161290322582e-05, "loss": 0.7399, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.7264127723035677, "learning_rate": 1.096774193548387e-05, "loss": 0.7212, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.5567543466331926, "learning_rate": 1.1290322580645164e-05, "loss": 0.7309, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6317333091764326, "learning_rate": 1.1612903225806453e-05, "loss": 0.7376, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.655636963509697, "learning_rate": 1.1935483870967743e-05, "loss": 0.743, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.5379133491686702, "learning_rate": 1.2258064516129034e-05, "loss": 0.7182, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5948846918963232, "learning_rate": 1.2580645161290324e-05, "loss": 0.7148, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.6697068160308274, "learning_rate": 1.2903225806451613e-05, "loss": 0.7128, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.5765283182031973, "learning_rate": 1.3225806451612903e-05, "loss": 0.7323, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5066451773361726, "learning_rate": 1.3548387096774194e-05, "loss": 0.7167, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.6117379849130811, "learning_rate": 1.3870967741935486e-05, "loss": 0.7238, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6104584875065464, "learning_rate": 1.4193548387096776e-05, "loss": 0.7021, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.4373849313652711, "learning_rate": 1.4516129032258066e-05, "loss": 0.7149, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5881387530533388, "learning_rate": 1.4838709677419357e-05, "loss": 0.7099, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.45300710419017376, "learning_rate": 1.5161290322580646e-05, "loss": 0.7047, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.4615976799153108, "learning_rate": 1.5483870967741936e-05, "loss": 0.6937, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6377956778686389, "learning_rate": 1.5806451612903226e-05, "loss": 0.6966, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.4577905664037949, "learning_rate": 1.6129032258064517e-05, "loss": 0.6852, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.6569619144938285, "learning_rate": 1.6451612903225807e-05, "loss": 0.6891, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.602476999292113, "learning_rate": 1.6774193548387098e-05, "loss": 0.6847, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.49685538946727914, "learning_rate": 1.7096774193548388e-05, "loss": 0.7057, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.6989373217919814, "learning_rate": 1.741935483870968e-05, "loss": 0.6833, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.6022335549882298, "learning_rate": 1.774193548387097e-05, "loss": 0.691, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.5009880075226459, "learning_rate": 1.806451612903226e-05, "loss": 0.6756, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6192784195659286, "learning_rate": 1.838709677419355e-05, "loss": 0.6914, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.5919499081090954, "learning_rate": 1.870967741935484e-05, "loss": 0.6777, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5208288564225644, "learning_rate": 1.903225806451613e-05, "loss": 0.7053, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5590292308738402, "learning_rate": 1.935483870967742e-05, "loss": 0.6948, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.7442958212021001, "learning_rate": 1.967741935483871e-05, "loss": 0.6795, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.7264566006794605, "learning_rate": 2e-05, "loss": 0.6943, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5038860505110888, "learning_rate": 2.0322580645161292e-05, "loss": 0.6808, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.5032875600296112, "learning_rate": 2.0645161290322582e-05, "loss": 0.6702, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.539025945757303, "learning_rate": 2.0967741935483873e-05, "loss": 0.6787, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.6139664235037653, "learning_rate": 2.1290322580645163e-05, "loss": 0.6775, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.6010641180732336, "learning_rate": 2.161290322580645e-05, "loss": 0.6848, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.7916424483928622, "learning_rate": 2.193548387096774e-05, "loss": 0.6719, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 1.024241496922493, "learning_rate": 2.225806451612903e-05, "loss": 0.6668, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.901789247843836, "learning_rate": 2.2580645161290328e-05, "loss": 0.6681, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.8566886401555155, "learning_rate": 2.2903225806451615e-05, "loss": 0.67, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.9892684041990524, "learning_rate": 2.3225806451612906e-05, "loss": 0.6798, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 1.0795706750039207, "learning_rate": 2.3548387096774196e-05, "loss": 0.6599, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.7511608041239489, "learning_rate": 2.3870967741935486e-05, "loss": 0.6555, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.6845648301821255, "learning_rate": 2.4193548387096777e-05, "loss": 0.6628, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.8546004012789647, "learning_rate": 2.4516129032258067e-05, "loss": 0.6585, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.8903165634401248, "learning_rate": 2.4838709677419358e-05, "loss": 0.6618, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.8980526805224328, "learning_rate": 2.5161290322580648e-05, "loss": 0.6569, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.8695980275007712, "learning_rate": 2.548387096774194e-05, "loss": 0.6671, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.151178224002939, "learning_rate": 2.5806451612903226e-05, "loss": 0.6645, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.847707530967768, "learning_rate": 2.6129032258064516e-05, "loss": 0.6617, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.105815632042638, "learning_rate": 2.6451612903225806e-05, "loss": 0.6631, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 1.003218462362407, "learning_rate": 2.6774193548387097e-05, "loss": 0.6474, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.9344247410752562, "learning_rate": 2.7096774193548387e-05, "loss": 0.6521, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.1069183548582677, "learning_rate": 2.7419354838709678e-05, "loss": 0.658, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 0.7855066647810042, "learning_rate": 2.774193548387097e-05, "loss": 0.6353, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7899044254503745, "learning_rate": 2.8064516129032262e-05, "loss": 0.6633, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 0.805994427680937, "learning_rate": 2.8387096774193552e-05, "loss": 0.6509, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.7193911202843873, "learning_rate": 2.8709677419354843e-05, "loss": 0.6633, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.8017790868402029, "learning_rate": 2.9032258064516133e-05, "loss": 0.655, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.9489028782941111, "learning_rate": 2.9354838709677423e-05, "loss": 0.6407, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.8375277189231994, "learning_rate": 2.9677419354838714e-05, "loss": 0.6401, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.8463532892172373, "learning_rate": 3.0000000000000004e-05, "loss": 0.661, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.423668632451803, "learning_rate": 3.032258064516129e-05, "loss": 0.6644, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.7939098250643146, "learning_rate": 3.0645161290322585e-05, "loss": 0.6561, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.26159485283379, "learning_rate": 3.096774193548387e-05, "loss": 0.6599, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.2241182830584625, "learning_rate": 3.1290322580645166e-05, "loss": 0.6394, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.1214480451348288, "learning_rate": 3.161290322580645e-05, "loss": 0.6643, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.187761290692907, "learning_rate": 3.193548387096774e-05, "loss": 0.6374, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.294081023625737, "learning_rate": 3.2258064516129034e-05, "loss": 0.6607, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.7154793087961356, "learning_rate": 3.258064516129033e-05, "loss": 0.6473, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.7118359329821817, "learning_rate": 3.2903225806451614e-05, "loss": 0.6634, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.6976584617996157, "learning_rate": 3.322580645161291e-05, "loss": 0.6421, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.52064841323406, "learning_rate": 3.3548387096774195e-05, "loss": 0.647, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.8789557405814268, "learning_rate": 3.387096774193549e-05, "loss": 0.6379, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.324802083695205, "learning_rate": 3.4193548387096776e-05, "loss": 0.6536, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.9802651078881592, "learning_rate": 3.451612903225807e-05, "loss": 0.6497, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.9273191668338014, "learning_rate": 3.483870967741936e-05, "loss": 0.6314, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.4945901784171207, "learning_rate": 3.516129032258065e-05, "loss": 0.6432, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.6685879204772927, "learning_rate": 3.548387096774194e-05, "loss": 0.6418, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.3631486608493957, "learning_rate": 3.5806451612903225e-05, "loss": 0.6591, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.093352440955527, "learning_rate": 3.612903225806452e-05, "loss": 0.6533, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.456292558306633, "learning_rate": 3.6451612903225805e-05, "loss": 0.6395, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.0995450815307972, "learning_rate": 3.67741935483871e-05, "loss": 0.6412, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 0.9350423014158054, "learning_rate": 3.7096774193548386e-05, "loss": 0.6421, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.118580746518116, "learning_rate": 3.741935483870968e-05, "loss": 0.6354, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.2540812617524562, "learning_rate": 3.7741935483870974e-05, "loss": 0.6319, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.1651109366546035, "learning_rate": 3.806451612903226e-05, "loss": 0.6268, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.0943196823941301, "learning_rate": 3.8387096774193555e-05, "loss": 0.629, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.9350294921511624, "learning_rate": 3.870967741935484e-05, "loss": 0.6429, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.7565577944166387, "learning_rate": 3.9032258064516135e-05, "loss": 0.6399, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.7124299806213892, "learning_rate": 3.935483870967742e-05, "loss": 0.6399, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.8493459358722928, "learning_rate": 3.9677419354838716e-05, "loss": 0.6457, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.9778338779495157, "learning_rate": 4e-05, "loss": 0.6452, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.3546122949179034, "learning_rate": 3.9999920040266474e-05, "loss": 0.6533, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.9629330829291032, "learning_rate": 3.999968016170525e-05, "loss": 0.6498, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.049255407184481, "learning_rate": 3.9999280366234394e-05, "loss": 0.6558, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.2788335483019413, "learning_rate": 3.999872065705065e-05, "loss": 0.6319, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.9183258977900208, "learning_rate": 3.999800103862945e-05, "loss": 0.6386, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 1.032715011418926, "learning_rate": 3.9997121516724834e-05, "loss": 0.6373, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.032104830581706, "learning_rate": 3.999608209836944e-05, "loss": 0.6212, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.0243107566886003, "learning_rate": 3.999488279187443e-05, "loss": 0.636, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 0.8611750866241172, "learning_rate": 3.9993523606829425e-05, "loss": 0.6457, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.7171426432394724, "learning_rate": 3.9992004554102435e-05, "loss": 0.635, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 1.0404354837921046, "learning_rate": 3.999032564583976e-05, "loss": 0.6297, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.3051366461481744, "learning_rate": 3.998848689546591e-05, "loss": 0.647, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.916940030858699, "learning_rate": 3.9986488317683496e-05, "loss": 0.6406, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.70182117552418, "learning_rate": 3.9984329928473067e-05, "loss": 0.6399, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.8171260902901853, "learning_rate": 3.998201174509306e-05, "loss": 0.6211, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.8673519098534271, "learning_rate": 3.997953378607961e-05, "loss": 0.6306, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6190670352905996, "learning_rate": 3.9976896071246403e-05, "loss": 0.6264, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.9046848673511704, "learning_rate": 3.997409862168454e-05, "loss": 0.6347, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.8876382502114852, "learning_rate": 3.997114145976237e-05, "loss": 0.6303, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.7924088050442649, "learning_rate": 3.9968024609125245e-05, "loss": 0.6308, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.7581189289722325, "learning_rate": 3.996474809469545e-05, "loss": 0.6266, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.8385362525407055, "learning_rate": 3.996131194267189e-05, "loss": 0.6336, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.9530143205960375, "learning_rate": 3.995771618052995e-05, "loss": 0.6377, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.8545484556263601, "learning_rate": 3.9953960837021256e-05, "loss": 0.6189, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.8789122437107655, "learning_rate": 3.995004594217343e-05, "loss": 0.6167, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.8835572672798395, "learning_rate": 3.994597152728987e-05, "loss": 0.6401, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.7459339018110223, "learning_rate": 3.994173762494947e-05, "loss": 0.6332, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.7472754128910394, "learning_rate": 3.9937344269006424e-05, "loss": 0.6354, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.7336832259936671, "learning_rate": 3.993279149458988e-05, "loss": 0.6194, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.7982626592860528, "learning_rate": 3.9928079338103695e-05, "loss": 0.6365, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.660766338833895, "learning_rate": 3.992320783722616e-05, "loss": 0.6202, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.6108613553866319, "learning_rate": 3.991817703090965e-05, "loss": 0.6194, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.5856858060226331, "learning_rate": 3.991298695938038e-05, "loss": 0.6175, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.8095165403291474, "learning_rate": 3.9907637664138e-05, "loss": 0.6228, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.9541428318566139, "learning_rate": 3.990212918795534e-05, "loss": 0.632, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 1.1065878149334711, "learning_rate": 3.9896461574878036e-05, "loss": 0.6271, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.919056922847531, "learning_rate": 3.989063487022416e-05, "loss": 0.6304, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.773608440335062, "learning_rate": 3.9884649120583903e-05, "loss": 0.6322, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.7306957780040042, "learning_rate": 3.987850437381915e-05, "loss": 0.6218, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 1.062566235626997, "learning_rate": 3.987220067906313e-05, "loss": 0.6185, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 1.1440910111284721, "learning_rate": 3.986573808672002e-05, "loss": 0.6179, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.7619080902690288, "learning_rate": 3.9859116648464534e-05, "loss": 0.632, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5773129796815474, "learning_rate": 3.985233641724152e-05, "loss": 0.6081, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7448548479361786, "learning_rate": 3.984539744726554e-05, "loss": 0.6265, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.9209209089747589, "learning_rate": 3.983829979402038e-05, "loss": 0.6201, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.7507039050395495, "learning_rate": 3.983104351425871e-05, "loss": 0.6212, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6221283380032173, "learning_rate": 3.982362866600154e-05, "loss": 0.6117, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.7946799243905316, "learning_rate": 3.9816055308537806e-05, "loss": 0.617, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.8356343294408994, "learning_rate": 3.980832350242388e-05, "loss": 0.6229, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.6669492254515472, "learning_rate": 3.980043330948306e-05, "loss": 0.6244, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.6383528147114502, "learning_rate": 3.9792384792805124e-05, "loss": 0.6136, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.6565586454229619, "learning_rate": 3.978417801674579e-05, "loss": 0.6273, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.7358565125367605, "learning_rate": 3.9775813046926244e-05, "loss": 0.6151, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6771267382270145, "learning_rate": 3.976728995023254e-05, "loss": 0.616, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.5641312988623465, "learning_rate": 3.975860879481514e-05, "loss": 0.6293, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.630597119628644, "learning_rate": 3.974976965008833e-05, "loss": 0.6169, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.6176833648238066, "learning_rate": 3.9740772586729674e-05, "loss": 0.6185, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.557099947837819, "learning_rate": 3.973161767667946e-05, "loss": 0.6198, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6177526897196983, "learning_rate": 3.972230499314009e-05, "loss": 0.6098, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.6900988487783567, "learning_rate": 3.9712834610575545e-05, "loss": 0.6231, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.6000135683846065, "learning_rate": 3.9703206604710746e-05, "loss": 0.6004, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.7329070442597346, "learning_rate": 3.969342105253098e-05, "loss": 0.6025, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6589900241450817, "learning_rate": 3.9683478032281246e-05, "loss": 0.6156, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.545073840415887, "learning_rate": 3.967337762346568e-05, "loss": 0.6152, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.679152764823297, "learning_rate": 3.9663119906846885e-05, "loss": 0.6201, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.7086723785464338, "learning_rate": 3.965270496444528e-05, "loss": 0.6204, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.5907304389895561, "learning_rate": 3.9642132879538465e-05, "loss": 0.6154, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.7583453363386424, "learning_rate": 3.9631403736660566e-05, "loss": 0.606, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.7542708675575835, "learning_rate": 3.962051762160151e-05, "loss": 0.6091, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.5596342752811289, "learning_rate": 3.960947462140638e-05, "loss": 0.6087, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.6440951305194211, "learning_rate": 3.959827482437472e-05, "loss": 0.5817, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.8338415567165433, "learning_rate": 3.958691832005981e-05, "loss": 0.5956, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.5595183689159153, "learning_rate": 3.9575405199267944e-05, "loss": 0.5983, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.47275483898047566, "learning_rate": 3.956373555405774e-05, "loss": 0.6224, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.7106754777656409, "learning_rate": 3.955190947773937e-05, "loss": 0.6122, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.7029481510249941, "learning_rate": 3.9539927064873824e-05, "loss": 0.6162, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.45133010852247585, "learning_rate": 3.952778841127214e-05, "loss": 0.6174, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.6080974149462304, "learning_rate": 3.95154936139947e-05, "loss": 0.6235, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5867619273894914, "learning_rate": 3.950304277135034e-05, "loss": 0.5841, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.5119894250179496, "learning_rate": 3.94904359828957e-05, "loss": 0.6127, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.512792113259668, "learning_rate": 3.94776733494343e-05, "loss": 0.5993, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.8790081875616361, "learning_rate": 3.9464754973015826e-05, "loss": 0.5996, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.4906414008426151, "learning_rate": 3.9451680956935275e-05, "loss": 0.6128, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5401093068322907, "learning_rate": 3.943845140573213e-05, "loss": 0.613, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.5470944664791663, "learning_rate": 3.942506642518952e-05, "loss": 0.6007, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.556070412250651, "learning_rate": 3.9411526122333396e-05, "loss": 0.5898, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.5059553869799973, "learning_rate": 3.939783060543167e-05, "loss": 0.5957, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.41652323755532555, "learning_rate": 3.938397998399333e-05, "loss": 0.5914, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.574964255474185, "learning_rate": 3.936997436876756e-05, "loss": 0.6059, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.5584338126770658, "learning_rate": 3.935581387174289e-05, "loss": 0.6083, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5207306228209468, "learning_rate": 3.9341498606146295e-05, "loss": 0.6034, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.4687625864783287, "learning_rate": 3.932702868644224e-05, "loss": 0.6068, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5766481908608014, "learning_rate": 3.931240422833181e-05, "loss": 0.5999, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5001035056716104, "learning_rate": 3.9297625348751806e-05, "loss": 0.6165, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5993639806360099, "learning_rate": 3.9282692165873744e-05, "loss": 0.6075, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.6605781785409752, "learning_rate": 3.9267604799102945e-05, "loss": 0.6108, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.6184407307703538, "learning_rate": 3.9252363369077615e-05, "loss": 0.6161, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.662075148326909, "learning_rate": 3.9236967997667796e-05, "loss": 0.5996, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.5848209138145789, "learning_rate": 3.9221418807974496e-05, "loss": 0.6162, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.49662487662825017, "learning_rate": 3.92057159243286e-05, "loss": 0.6134, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.520913274841085, "learning_rate": 3.9189859472289956e-05, "loss": 0.6102, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.5674439132519554, "learning_rate": 3.9173849578646324e-05, "loss": 0.6087, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.5013137093914836, "learning_rate": 3.9157686371412395e-05, "loss": 0.6074, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5153799363644516, "learning_rate": 3.914136997982874e-05, "loss": 0.5924, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5313183561048377, "learning_rate": 3.912490053436079e-05, "loss": 0.601, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.45710544706471284, "learning_rate": 3.9108278166697805e-05, "loss": 0.5914, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5394570633815753, "learning_rate": 3.909150300975178e-05, "loss": 0.6151, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4269065481299578, "learning_rate": 3.907457519765642e-05, "loss": 0.5957, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5610106972256002, "learning_rate": 3.905749486576607e-05, "loss": 0.5985, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.4901602042802381, "learning_rate": 3.90402621506546e-05, "loss": 0.6108, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5611757952537471, "learning_rate": 3.902287719011435e-05, "loss": 0.5983, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.4378685557066265, "learning_rate": 3.900534012315499e-05, "loss": 0.5908, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5112617525478038, "learning_rate": 3.8987651090002454e-05, "loss": 0.6004, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.5764466575855177, "learning_rate": 3.896981023209777e-05, "loss": 0.6067, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.49691769367799066, "learning_rate": 3.8951817692095966e-05, "loss": 0.6069, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.4085173247788809, "learning_rate": 3.893367361386491e-05, "loss": 0.5868, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.4397797449052351, "learning_rate": 3.891537814248417e-05, "loss": 0.5847, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.45808787717640764, "learning_rate": 3.889693142424384e-05, "loss": 0.6158, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5867801488349661, "learning_rate": 3.8878333606643405e-05, "loss": 0.5976, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.6133110246505036, "learning_rate": 3.885958483839049e-05, "loss": 0.6011, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.4816794003691648, "learning_rate": 3.8840685269399786e-05, "loss": 0.5942, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.37707051234891475, "learning_rate": 3.882163505079171e-05, "loss": 0.5899, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.6078223413611321, "learning_rate": 3.880243433489132e-05, "loss": 0.5883, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.8034781688155699, "learning_rate": 3.878308327522702e-05, "loss": 0.5536, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.6141767908288025, "learning_rate": 3.876358202652936e-05, "loss": 0.5429, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.756087617999913, "learning_rate": 3.8743930744729835e-05, "loss": 0.564, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.7515954736003383, "learning_rate": 3.8724129586959535e-05, "loss": 0.5745, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5505002381439041, "learning_rate": 3.870417871154801e-05, "loss": 0.5539, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6051442177276707, "learning_rate": 3.868407827802192e-05, "loss": 0.5584, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.6692253401760527, "learning_rate": 3.8663828447103804e-05, "loss": 0.5472, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6188991846040914, "learning_rate": 3.8643429380710765e-05, "loss": 0.5431, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5461926294761101, "learning_rate": 3.862288124195319e-05, "loss": 0.5521, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.6831924741988284, "learning_rate": 3.8602184195133464e-05, "loss": 0.5572, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.7573156251599207, "learning_rate": 3.8581338405744604e-05, "loss": 0.5432, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.6906813677955971, "learning_rate": 3.8560344040468996e-05, "loss": 0.5542, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.43893712962600695, "learning_rate": 3.853920126717703e-05, "loss": 0.5544, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5257282996666941, "learning_rate": 3.851791025492574e-05, "loss": 0.5404, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.5809706511468297, "learning_rate": 3.8496471173957515e-05, "loss": 0.5385, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.3707332931151097, "learning_rate": 3.847488419569866e-05, "loss": 0.5514, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5603715559086029, "learning_rate": 3.8453149492758077e-05, "loss": 0.5599, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6040130861010227, "learning_rate": 3.8431267238925886e-05, "loss": 0.56, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.678645825650064, "learning_rate": 3.840923760917199e-05, "loss": 0.5539, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.8406039422699786, "learning_rate": 3.838706077964473e-05, "loss": 0.5475, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.649806424154655, "learning_rate": 3.836473692766944e-05, "loss": 0.5542, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.700211032728725, "learning_rate": 3.834226623174705e-05, "loss": 0.5638, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.6886023169128624, "learning_rate": 3.831964887155264e-05, "loss": 0.5572, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6574729994656875, "learning_rate": 3.829688502793403e-05, "loss": 0.5377, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5354344734348419, "learning_rate": 3.827397488291029e-05, "loss": 0.5507, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.4786569958095394, "learning_rate": 3.8250918619670343e-05, "loss": 0.5539, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5965621623689955, "learning_rate": 3.822771642257145e-05, "loss": 0.5519, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5877530354338283, "learning_rate": 3.820436847713776e-05, "loss": 0.5676, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.46597292629564774, "learning_rate": 3.8180874970058826e-05, "loss": 0.5423, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5197568892319975, "learning_rate": 3.8157236089188103e-05, "loss": 0.5505, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.5072894753098443, "learning_rate": 3.813345202354145e-05, "loss": 0.5623, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.42939785937864017, "learning_rate": 3.810952296329563e-05, "loss": 0.5629, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.5799934234783727, "learning_rate": 3.808544909978676e-05, "loss": 0.5566, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.6638985957195178, "learning_rate": 3.806123062550882e-05, "loss": 0.5471, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.46030158629365703, "learning_rate": 3.803686773411208e-05, "loss": 0.5446, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.6279654251523427, "learning_rate": 3.801236062040158e-05, "loss": 0.5481, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.7155223093634986, "learning_rate": 3.798770948033553e-05, "loss": 0.5604, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5683056670764356, "learning_rate": 3.796291451102381e-05, "loss": 0.5518, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5194969219644562, "learning_rate": 3.793797591072631e-05, "loss": 0.5521, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6496754516036727, "learning_rate": 3.791289387885144e-05, "loss": 0.5638, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.6231316886319518, "learning_rate": 3.788766861595443e-05, "loss": 0.5623, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.663215335413977, "learning_rate": 3.7862300323735835e-05, "loss": 0.5523, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.5901255901555483, "learning_rate": 3.783678920503983e-05, "loss": 0.5491, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.5932760880957302, "learning_rate": 3.781113546385265e-05, "loss": 0.5444, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.6433330937364736, "learning_rate": 3.7785339305300916e-05, "loss": 0.558, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6713145572777633, "learning_rate": 3.7759400935650025e-05, "loss": 0.5443, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.6411007340254692, "learning_rate": 3.77333205623025e-05, "loss": 0.5647, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.4417055407842242, "learning_rate": 3.7707098393796295e-05, "loss": 0.5546, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5917396891632769, "learning_rate": 3.7680734639803185e-05, "loss": 0.5604, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.6356285823360117, "learning_rate": 3.765422951112704e-05, "loss": 0.5652, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.4897452314330357, "learning_rate": 3.762758321970216e-05, "loss": 0.5541, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.4142800798362531, "learning_rate": 3.7600795978591584e-05, "loss": 0.5484, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.46268679044356015, "learning_rate": 3.757386800198538e-05, "loss": 0.5551, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.4790036746402262, "learning_rate": 3.7546799505198925e-05, "loss": 0.568, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.3646236523985694, "learning_rate": 3.7519590704671197e-05, "loss": 0.5428, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.3493027571268586, "learning_rate": 3.749224181796305e-05, "loss": 0.5397, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.3953864475141157, "learning_rate": 3.746475306375545e-05, "loss": 0.5599, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.49447562484816904, "learning_rate": 3.743712466184774e-05, "loss": 0.5575, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.35073806927131346, "learning_rate": 3.7409356833155885e-05, "loss": 0.5628, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.4480246271855326, "learning_rate": 3.73814497997107e-05, "loss": 0.5473, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.4736128522358814, "learning_rate": 3.7353403784656095e-05, "loss": 0.5411, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.4400690779482596, "learning_rate": 3.732521901224724e-05, "loss": 0.557, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.44864862708894204, "learning_rate": 3.7296895707848844e-05, "loss": 0.5526, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.4210471905490763, "learning_rate": 3.7268434097933275e-05, "loss": 0.5386, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.40599255037377363, "learning_rate": 3.723983441007882e-05, "loss": 0.5654, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.40017123196605714, "learning_rate": 3.721109687296781e-05, "loss": 0.5508, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.3709375944311697, "learning_rate": 3.718222171638484e-05, "loss": 0.5453, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.38652260351275014, "learning_rate": 3.715320917121488e-05, "loss": 0.5334, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.3819555439103628, "learning_rate": 3.712405946944149e-05, "loss": 0.5494, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.38616666657143056, "learning_rate": 3.709477284414488e-05, "loss": 0.5545, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.4159972064796836, "learning_rate": 3.7065349529500136e-05, "loss": 0.5477, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.3887720244528109, "learning_rate": 3.7035789760775305e-05, "loss": 0.5518, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.44218114950333975, "learning_rate": 3.70060937743295e-05, "loss": 0.5462, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.4922796131931344, "learning_rate": 3.6976261807611045e-05, "loss": 0.5582, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.4568553074736806, "learning_rate": 3.694629409915555e-05, "loss": 0.555, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.41200465322131996, "learning_rate": 3.691619088858401e-05, "loss": 0.5617, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.3999800204422049, "learning_rate": 3.68859524166009e-05, "loss": 0.5522, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.40748356939582886, "learning_rate": 3.6855578924992226e-05, "loss": 0.5572, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.43248248440770126, "learning_rate": 3.6825070656623626e-05, "loss": 0.5422, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.480915641945489, "learning_rate": 3.67944278554384e-05, "loss": 0.5662, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4810692295182732, "learning_rate": 3.676365076645557e-05, "loss": 0.5527, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4272271115100223, "learning_rate": 3.673273963576791e-05, "loss": 0.5449, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.4934661810875481, "learning_rate": 3.670169471054001e-05, "loss": 0.5398, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.5458157916054477, "learning_rate": 3.6670516239006254e-05, "loss": 0.5642, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4720748729626189, "learning_rate": 3.663920447046888e-05, "loss": 0.5408, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.3930357513357323, "learning_rate": 3.6607759655295954e-05, "loss": 0.5558, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.5227471735524906, "learning_rate": 3.657618204491937e-05, "loss": 0.5451, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.5543253058630732, "learning_rate": 3.6544471891832875e-05, "loss": 0.5584, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4357201727626802, "learning_rate": 3.6512629449589983e-05, "loss": 0.5595, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.48083447904621973, "learning_rate": 3.6480654972802045e-05, "loss": 0.5542, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.432148386230533, "learning_rate": 3.644854871713611e-05, "loss": 0.5617, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.44875605265823, "learning_rate": 3.6416310939312924e-05, "loss": 0.5531, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.4852683179940298, "learning_rate": 3.638394189710493e-05, "loss": 0.5438, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.32658702051339394, "learning_rate": 3.635144184933412e-05, "loss": 0.5409, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.4555321760975462, "learning_rate": 3.6318811055869994e-05, "loss": 0.5497, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.5470718853963118, "learning_rate": 3.628604977762752e-05, "loss": 0.5519, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.4487131369764289, "learning_rate": 3.6253158276565004e-05, "loss": 0.5635, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.3981959948138665, "learning_rate": 3.6220136815682016e-05, "loss": 0.5517, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.6319025653781897, "learning_rate": 3.618698565901727e-05, "loss": 0.5547, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.4410102460234565, "learning_rate": 3.615370507164654e-05, "loss": 0.5619, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5155903715971295, "learning_rate": 3.61202953196805e-05, "loss": 0.5439, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.41683385130627, "learning_rate": 3.6086756670262654e-05, "loss": 0.5465, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.42969022755705893, "learning_rate": 3.6053089391567135e-05, "loss": 0.558, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.3756165015241088, "learning_rate": 3.601929375279662e-05, "loss": 0.5436, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.33412255190790624, "learning_rate": 3.598537002418012e-05, "loss": 0.5463, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.3854613108061693, "learning_rate": 3.5951318476970885e-05, "loss": 0.5349, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5066153411534493, "learning_rate": 3.591713938344416e-05, "loss": 0.5395, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.49258086523040556, "learning_rate": 3.588283301689507e-05, "loss": 0.5443, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.41866193436534666, "learning_rate": 3.5848399651636424e-05, "loss": 0.5484, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.48978612117728176, "learning_rate": 3.5813839562996473e-05, "loss": 0.5608, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.4897573731221508, "learning_rate": 3.5779153027316775e-05, "loss": 0.5355, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.3801138554426809, "learning_rate": 3.574434032194994e-05, "loss": 0.5464, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.4966509483903841, "learning_rate": 3.5709401725257436e-05, "loss": 0.5546, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.537557173214491, "learning_rate": 3.5674337516607346e-05, "loss": 0.5509, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5075878971848541, "learning_rate": 3.563914797637216e-05, "loss": 0.5448, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.31928250788920465, "learning_rate": 3.560383338592649e-05, "loss": 0.5422, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.45187135979438653, "learning_rate": 3.556839402764487e-05, "loss": 0.5405, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.40066969640822514, "learning_rate": 3.553283018489946e-05, "loss": 0.5493, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.32840546835324874, "learning_rate": 3.54971421420578e-05, "loss": 0.5455, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.44255427745676784, "learning_rate": 3.5461330184480524e-05, "loss": 0.5576, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4433738724331908, "learning_rate": 3.54253945985191e-05, "loss": 0.5618, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.4594614224527193, "learning_rate": 3.5389335671513524e-05, "loss": 0.5398, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.496580461913869, "learning_rate": 3.5353153691789986e-05, "loss": 0.5485, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.3434809170207372, "learning_rate": 3.531684894865866e-05, "loss": 0.5499, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.5439745810909377, "learning_rate": 3.528042173241128e-05, "loss": 0.544, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.37986132504802433, "learning_rate": 3.524387233431892e-05, "loss": 0.5408, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.4157749590777627, "learning_rate": 3.520720104662958e-05, "loss": 0.5592, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.4117673553895597, "learning_rate": 3.5170408162565904e-05, "loss": 0.5496, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.32914338127684606, "learning_rate": 3.513349397632281e-05, "loss": 0.5476, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.41580098091598233, "learning_rate": 3.5096458783065145e-05, "loss": 0.5452, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.39776842851975075, "learning_rate": 3.505930287892533e-05, "loss": 0.5514, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.35582241056708225, "learning_rate": 3.502202656100099e-05, "loss": 0.5447, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.3677968045161884, "learning_rate": 3.498463012735256e-05, "loss": 0.5617, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.41334519676520387, "learning_rate": 3.494711387700094e-05, "loss": 0.5428, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.3401865116976949, "learning_rate": 3.490947810992505e-05, "loss": 0.5525, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.38252281887041506, "learning_rate": 3.48717231270595e-05, "loss": 0.5573, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.3869610236107179, "learning_rate": 3.483384923029211e-05, "loss": 0.5501, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.3528881740834739, "learning_rate": 3.479585672246156e-05, "loss": 0.546, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.40924564712838274, "learning_rate": 3.4757745907354924e-05, "loss": 0.5497, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.43351370273642237, "learning_rate": 3.471951708970527e-05, "loss": 0.5561, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.44195668516834985, "learning_rate": 3.468117057518921e-05, "loss": 0.5552, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.42468768194760875, "learning_rate": 3.4642706670424426e-05, "loss": 0.5416, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.41211011031135764, "learning_rate": 3.460412568296731e-05, "loss": 0.5573, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.39298754687561227, "learning_rate": 3.456542792131039e-05, "loss": 0.5435, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.37860378381558085, "learning_rate": 3.4526613694879936e-05, "loss": 0.5529, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.396542781608016, "learning_rate": 3.448768331403348e-05, "loss": 0.5383, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.3408702381799562, "learning_rate": 3.44486370900573e-05, "loss": 0.5498, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.42160517959613, "learning_rate": 3.440947533516396e-05, "loss": 0.5449, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.43397789060881453, "learning_rate": 3.4370198362489816e-05, "loss": 0.5543, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.32118246053673694, "learning_rate": 3.43308064860925e-05, "loss": 0.5523, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.42892475748082626, "learning_rate": 3.4291300020948393e-05, "loss": 0.5459, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.36432852319661674, "learning_rate": 3.425167928295015e-05, "loss": 0.5384, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.337267324028364, "learning_rate": 3.421194458890411e-05, "loss": 0.5436, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.35460145662164566, "learning_rate": 3.4172096256527865e-05, "loss": 0.5461, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.36290218574526056, "learning_rate": 3.4132134604447595e-05, "loss": 0.5389, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.35373647486549903, "learning_rate": 3.409205995219561e-05, "loss": 0.5406, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.31891460153203344, "learning_rate": 3.4051872620207765e-05, "loss": 0.5433, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.38629183314299975, "learning_rate": 3.40115729298209e-05, "loss": 0.5476, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.3436854155855686, "learning_rate": 3.397116120327025e-05, "loss": 0.5436, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.3661151230532352, "learning_rate": 3.3930637763686916e-05, "loss": 0.5431, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.3392377351558486, "learning_rate": 3.389000293509524e-05, "loss": 0.5331, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.33636785970867594, "learning_rate": 3.3849257042410225e-05, "loss": 0.5461, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.37779403603023, "learning_rate": 3.380840041143494e-05, "loss": 0.5566, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.3225291635725735, "learning_rate": 3.376743336885792e-05, "loss": 0.5432, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.3636885020358973, "learning_rate": 3.372635624225055e-05, "loss": 0.5391, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.45592733648631684, "learning_rate": 3.3685169360064445e-05, "loss": 0.5481, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.38111532876949433, "learning_rate": 3.3643873051628804e-05, "loss": 0.5518, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.3720151663686256, "learning_rate": 3.3602467647147814e-05, "loss": 0.5454, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.3833137791341534, "learning_rate": 3.356095347769799e-05, "loss": 0.5326, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.3498355312750512, "learning_rate": 3.351933087522552e-05, "loss": 0.5489, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.3735634207478597, "learning_rate": 3.3477600172543626e-05, "loss": 0.5431, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.31800168133418594, "learning_rate": 3.3435761703329894e-05, "loss": 0.5408, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.4514285507387777, "learning_rate": 3.3393815802123606e-05, "loss": 0.553, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.40779246231091976, "learning_rate": 3.335176280432308e-05, "loss": 0.5417, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.3540010005238643, "learning_rate": 3.330960304618295e-05, "loss": 0.5457, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4150852881565468, "learning_rate": 3.326733686481153e-05, "loss": 0.5478, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.3892244537006006, "learning_rate": 3.3224964598168084e-05, "loss": 0.5535, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.3440663161954791, "learning_rate": 3.318248658506012e-05, "loss": 0.5459, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.33796894458381616, "learning_rate": 3.313990316514069e-05, "loss": 0.5439, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.3407314419891414, "learning_rate": 3.309721467890571e-05, "loss": 0.5561, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.3454928979359742, "learning_rate": 3.305442146769115e-05, "loss": 0.5382, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.36410628734592176, "learning_rate": 3.30115238736704e-05, "loss": 0.5628, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.4084619840252625, "learning_rate": 3.296852223985148e-05, "loss": 0.5535, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.33680176149379804, "learning_rate": 3.2925416910074315e-05, "loss": 0.5582, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.30715140873351204, "learning_rate": 3.288220822900796e-05, "loss": 0.5505, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.3591506440201875, "learning_rate": 3.283889654214788e-05, "loss": 0.5339, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.32961786563655976, "learning_rate": 3.279548219581317e-05, "loss": 0.5524, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.33171076873195826, "learning_rate": 3.275196553714379e-05, "loss": 0.5371, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.32775437547651987, "learning_rate": 3.270834691409778e-05, "loss": 0.5408, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.3255657342595426, "learning_rate": 3.266462667544849e-05, "loss": 0.5274, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.3141236329339809, "learning_rate": 3.262080517078178e-05, "loss": 0.5474, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.32379695529681274, "learning_rate": 3.257688275049323e-05, "loss": 0.5416, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.3459590714310371, "learning_rate": 3.253285976578535e-05, "loss": 0.5369, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.3827554248874339, "learning_rate": 3.2488736568664756e-05, "loss": 0.551, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.34500863209979904, "learning_rate": 3.244451351193935e-05, "loss": 0.5345, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.37032727583216735, "learning_rate": 3.240019094921551e-05, "loss": 0.5497, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.35563210927620437, "learning_rate": 3.235576923489527e-05, "loss": 0.5385, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.3876253274419233, "learning_rate": 3.2311248724173476e-05, "loss": 0.5401, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.3426706840884502, "learning_rate": 3.226662977303494e-05, "loss": 0.5338, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.3789922197897341, "learning_rate": 3.2221912738251626e-05, "loss": 0.5636, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.36992892520982956, "learning_rate": 3.2177097977379736e-05, "loss": 0.5501, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.289562584357214, "learning_rate": 3.21321858487569e-05, "loss": 0.5342, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.397385088314687, "learning_rate": 3.208717671149931e-05, "loss": 0.5343, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.377738096191523, "learning_rate": 3.204207092549882e-05, "loss": 0.5423, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.3905666984898344, "learning_rate": 3.19968688514201e-05, "loss": 0.5409, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.3890696320104801, "learning_rate": 3.195157085069774e-05, "loss": 0.5566, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.44801518618630476, "learning_rate": 3.190617728553332e-05, "loss": 0.5445, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.38449488261178666, "learning_rate": 3.1860688518892606e-05, "loss": 0.5437, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4566059611702806, "learning_rate": 3.181510491450254e-05, "loss": 0.5487, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.3807260429500368, "learning_rate": 3.176942683684842e-05, "loss": 0.5526, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.4657354062752282, "learning_rate": 3.1723654651170934e-05, "loss": 0.5591, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4138793843344285, "learning_rate": 3.167778872346327e-05, "loss": 0.5441, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.2848862351723782, "learning_rate": 3.163182942046815e-05, "loss": 0.5394, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.33571940137229206, "learning_rate": 3.158577710967494e-05, "loss": 0.5376, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.35278116422732403, "learning_rate": 3.153963215931669e-05, "loss": 0.5358, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.39856996104471987, "learning_rate": 3.14933949383672e-05, "loss": 0.5364, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.33548402810853345, "learning_rate": 3.144706581653805e-05, "loss": 0.5392, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.429182337864315, "learning_rate": 3.140064516427566e-05, "loss": 0.5425, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.33349825614895545, "learning_rate": 3.135413335275833e-05, "loss": 0.5295, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.40213694777338516, "learning_rate": 3.130753075389327e-05, "loss": 0.5497, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.3269163388765448, "learning_rate": 3.1260837740313625e-05, "loss": 0.5382, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.39518732464273587, "learning_rate": 3.121405468537547e-05, "loss": 0.5398, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.346255823219799, "learning_rate": 3.116718196315488e-05, "loss": 0.5456, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.47021147003552866, "learning_rate": 3.1120219948444894e-05, "loss": 0.5477, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.3723563091781475, "learning_rate": 3.107316901675252e-05, "loss": 0.5436, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.39907919973189543, "learning_rate": 3.1026029544295745e-05, "loss": 0.5326, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.39392890725911167, "learning_rate": 3.097880190800057e-05, "loss": 0.5398, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.38456848075546923, "learning_rate": 3.093148648549788e-05, "loss": 0.5333, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.35491323308922595, "learning_rate": 3.088408365512055e-05, "loss": 0.5666, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.36171228995330407, "learning_rate": 3.083659379590034e-05, "loss": 0.5533, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.34963780904817715, "learning_rate": 3.0789017287564913e-05, "loss": 0.5353, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.31025919634928734, "learning_rate": 3.074135451053475e-05, "loss": 0.5542, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.3271964699582451, "learning_rate": 3.069360584592015e-05, "loss": 0.5482, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.37138829550707503, "learning_rate": 3.064577167551816e-05, "loss": 0.5155, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.4215568104251613, "learning_rate": 3.059785238180953e-05, "loss": 0.5348, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.4074088188525994, "learning_rate": 3.054984834795566e-05, "loss": 0.5472, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.46196743029817455, "learning_rate": 3.0501759957795537e-05, "loss": 0.5425, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.32945821265822445, "learning_rate": 3.0453587595842627e-05, "loss": 0.5318, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.3898531037877726, "learning_rate": 3.0405331647281856e-05, "loss": 0.5523, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.43104451365157975, "learning_rate": 3.0356992497966508e-05, "loss": 0.5412, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.32398487444665536, "learning_rate": 3.0308570534415137e-05, "loss": 0.5295, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.41744425238778576, "learning_rate": 3.0260066143808467e-05, "loss": 0.5436, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.3940883242696922, "learning_rate": 3.021147971398632e-05, "loss": 0.5415, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.3184087872042312, "learning_rate": 3.0162811633444478e-05, "loss": 0.5437, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.37722367847517924, "learning_rate": 3.0114062291331635e-05, "loss": 0.5271, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.40588130554322077, "learning_rate": 3.0065232077446217e-05, "loss": 0.5525, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.3698786036550318, "learning_rate": 3.001632138223332e-05, "loss": 0.5356, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.48971942971817023, "learning_rate": 2.9967330596781565e-05, "loss": 0.4869, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.3864353021738518, "learning_rate": 2.9918260112819952e-05, "loss": 0.475, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5434391629983896, "learning_rate": 2.9869110322714778e-05, "loss": 0.4804, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.4341561916317742, "learning_rate": 2.9819881619466447e-05, "loss": 0.4758, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.4978842862346423, "learning_rate": 2.9770574396706364e-05, "loss": 0.4782, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.4296308480665583, "learning_rate": 2.972118904869376e-05, "loss": 0.4873, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4481749910695149, "learning_rate": 2.9671725970312563e-05, "loss": 0.466, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.4974267976600344, "learning_rate": 2.9622185557068238e-05, "loss": 0.4753, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.45886176400209905, "learning_rate": 2.95725682050846e-05, "loss": 0.469, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.44007496484812886, "learning_rate": 2.9522874311100684e-05, "loss": 0.4792, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.39971265715608273, "learning_rate": 2.9473104272467526e-05, "loss": 0.476, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.4419856196196377, "learning_rate": 2.942325848714505e-05, "loss": 0.4697, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.4052517244250001, "learning_rate": 2.9373337353698804e-05, "loss": 0.4667, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4029421378233459, "learning_rate": 2.932334127129686e-05, "loss": 0.4882, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.4558092102857473, "learning_rate": 2.9273270639706547e-05, "loss": 0.4762, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.37028721987900154, "learning_rate": 2.922312585929131e-05, "loss": 0.4741, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.39252189061894205, "learning_rate": 2.9172907331007478e-05, "loss": 0.4864, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.4140357480734149, "learning_rate": 2.9122615456401053e-05, "loss": 0.4843, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.32375101747233637, "learning_rate": 2.9072250637604535e-05, "loss": 0.4745, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.40278566693925405, "learning_rate": 2.9021813277333667e-05, "loss": 0.4803, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.4222503120339647, "learning_rate": 2.8971303778884244e-05, "loss": 0.4757, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3786579717617521, "learning_rate": 2.8920722546128863e-05, "loss": 0.4879, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.34552018099100146, "learning_rate": 2.887006998351372e-05, "loss": 0.482, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4118539379825312, "learning_rate": 2.881934649605535e-05, "loss": 0.4858, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.4370407066341155, "learning_rate": 2.8768552489337408e-05, "loss": 0.4819, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.31755201476703016, "learning_rate": 2.8717688369507425e-05, "loss": 0.4694, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.42968821458536166, "learning_rate": 2.8666754543273535e-05, "loss": 0.4578, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.3707009444952269, "learning_rate": 2.8615751417901273e-05, "loss": 0.4782, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.4157140198937655, "learning_rate": 2.856467940121025e-05, "loss": 0.4817, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.3637891808099504, "learning_rate": 2.8513538901570964e-05, "loss": 0.4842, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.4235130726598351, "learning_rate": 2.846233032790149e-05, "loss": 0.476, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.35818248836343974, "learning_rate": 2.84110540896642e-05, "loss": 0.4792, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.4561684683068647, "learning_rate": 2.8359710596862555e-05, "loss": 0.4761, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.348083898379101, "learning_rate": 2.8308300260037734e-05, "loss": 0.4644, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.33533785588202536, "learning_rate": 2.8256823490265424e-05, "loss": 0.4677, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.33228801634907257, "learning_rate": 2.8205280699152515e-05, "loss": 0.4694, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.3054628959291482, "learning_rate": 2.8153672298833777e-05, "loss": 0.4776, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3541310628700886, "learning_rate": 2.8101998701968615e-05, "loss": 0.4809, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.33554293437966637, "learning_rate": 2.805026032173773e-05, "loss": 0.4645, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.44138428856721745, "learning_rate": 2.7998457571839832e-05, "loss": 0.473, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.37877620672984347, "learning_rate": 2.7946590866488322e-05, "loss": 0.4835, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.3528338363247591, "learning_rate": 2.7894660620408e-05, "loss": 0.4763, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.35964287657241123, "learning_rate": 2.784266724883173e-05, "loss": 0.4715, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3522714066944237, "learning_rate": 2.7790611167497128e-05, "loss": 0.4794, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.39119860608454426, "learning_rate": 2.7738492792643224e-05, "loss": 0.4818, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3422043348883192, "learning_rate": 2.768631254100716e-05, "loss": 0.4723, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3646369130103132, "learning_rate": 2.7634070829820836e-05, "loss": 0.4714, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.32854706736427014, "learning_rate": 2.7581768076807592e-05, "loss": 0.479, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.38636981254532116, "learning_rate": 2.7529404700178832e-05, "loss": 0.4742, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.32996977172316816, "learning_rate": 2.7476981118630735e-05, "loss": 0.4791, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.2953275441653384, "learning_rate": 2.742449775134085e-05, "loss": 0.4802, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.3117931766245555, "learning_rate": 2.7371955017964788e-05, "loss": 0.4914, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.36191841391159996, "learning_rate": 2.7319353338632845e-05, "loss": 0.4742, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3562187283818618, "learning_rate": 2.7266693133946645e-05, "loss": 0.4914, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.45543549581678616, "learning_rate": 2.7213974824975785e-05, "loss": 0.477, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.49254288790858647, "learning_rate": 2.7161198833254464e-05, "loss": 0.4861, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3603193549144612, "learning_rate": 2.7108365580778095e-05, "loss": 0.4801, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.412254229804841, "learning_rate": 2.705547548999996e-05, "loss": 0.4882, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.40828021115378355, "learning_rate": 2.7002528983827817e-05, "loss": 0.4861, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.38132218651958055, "learning_rate": 2.6949526485620517e-05, "loss": 0.4736, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3736264967491097, "learning_rate": 2.6896468419184623e-05, "loss": 0.4909, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.39934172532242207, "learning_rate": 2.6843355208771024e-05, "loss": 0.482, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3941726343137726, "learning_rate": 2.6790187279071536e-05, "loss": 0.4696, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.2927878059782222, "learning_rate": 2.67369650552155e-05, "loss": 0.4763, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.43851179198153556, "learning_rate": 2.6683688962766407e-05, "loss": 0.4748, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.3164588493504692, "learning_rate": 2.6630359427718468e-05, "loss": 0.477, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3238193272984263, "learning_rate": 2.6576976876493225e-05, "loss": 0.4728, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3031757951864985, "learning_rate": 2.652354173593614e-05, "loss": 0.484, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.361127865467333, "learning_rate": 2.647005443331317e-05, "loss": 0.498, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.31503313650211123, "learning_rate": 2.6416515396307354e-05, "loss": 0.4752, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3361500396219306, "learning_rate": 2.636292505301542e-05, "loss": 0.4889, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.30407536909744337, "learning_rate": 2.630928383194431e-05, "loss": 0.4855, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.29565241563495626, "learning_rate": 2.625559216200781e-05, "loss": 0.4737, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.34825213155890256, "learning_rate": 2.620185047252308e-05, "loss": 0.4716, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.31178633789496696, "learning_rate": 2.614805919320723e-05, "loss": 0.4847, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3494744858034561, "learning_rate": 2.6094218754173895e-05, "loss": 0.4696, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3392608726535771, "learning_rate": 2.60403295859298e-05, "loss": 0.4891, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.31365654669202214, "learning_rate": 2.5986392119371297e-05, "loss": 0.4876, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.3487788750267815, "learning_rate": 2.5932406785780928e-05, "loss": 0.482, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3984544958611732, "learning_rate": 2.5878374016823987e-05, "loss": 0.4778, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.3032976233971412, "learning_rate": 2.5824294244545045e-05, "loss": 0.4755, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.38417136700214916, "learning_rate": 2.577016790136453e-05, "loss": 0.4777, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.35264110510761115, "learning_rate": 2.5715995420075225e-05, "loss": 0.4733, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.29730346267782304, "learning_rate": 2.5661777233838864e-05, "loss": 0.481, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.33778042773305905, "learning_rate": 2.5607513776182616e-05, "loss": 0.467, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.4040977458251757, "learning_rate": 2.5553205480995633e-05, "loss": 0.4989, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.30631726313185137, "learning_rate": 2.5498852782525604e-05, "loss": 0.4843, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3370569119201179, "learning_rate": 2.5444456115375252e-05, "loss": 0.474, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.34316710812146445, "learning_rate": 2.539001591449889e-05, "loss": 0.4834, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.33835031467317334, "learning_rate": 2.53355326151989e-05, "loss": 0.4773, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3195459606861857, "learning_rate": 2.5281006653122288e-05, "loss": 0.4727, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3698661346840554, "learning_rate": 2.5226438464257217e-05, "loss": 0.4905, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.2949727628718433, "learning_rate": 2.5171828484929447e-05, "loss": 0.4926, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.39230538610813337, "learning_rate": 2.5117177151798934e-05, "loss": 0.4893, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.33136448507485533, "learning_rate": 2.506248490185627e-05, "loss": 0.4825, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.3069745698890718, "learning_rate": 2.500775217241923e-05, "loss": 0.4788, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3797996059902841, "learning_rate": 2.4952979401129266e-05, "loss": 0.4803, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.2957973857187961, "learning_rate": 2.4898167025948e-05, "loss": 0.4736, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.3791412972754394, "learning_rate": 2.4843315485153703e-05, "loss": 0.4845, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.35615552845773657, "learning_rate": 2.4788425217337856e-05, "loss": 0.4869, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.36807547388405815, "learning_rate": 2.4733496661401572e-05, "loss": 0.4865, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.48413167882384667, "learning_rate": 2.4678530256552114e-05, "loss": 0.4883, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.38476375287424136, "learning_rate": 2.46235264422994e-05, "loss": 0.4875, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.3079554673131378, "learning_rate": 2.4568485658452452e-05, "loss": 0.4876, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.3467198379702839, "learning_rate": 2.451340834511592e-05, "loss": 0.4874, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.3119891738917689, "learning_rate": 2.4458294942686528e-05, "loss": 0.4684, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.2999563304962877, "learning_rate": 2.440314589184958e-05, "loss": 0.4785, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.344994952543901, "learning_rate": 2.434796163357541e-05, "loss": 0.4847, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3279836987710585, "learning_rate": 2.429274260911588e-05, "loss": 0.4904, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.3728113267545704, "learning_rate": 2.423748926000084e-05, "loss": 0.4861, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.4025493136835467, "learning_rate": 2.418220202803459e-05, "loss": 0.4795, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3913380189685119, "learning_rate": 2.412688135529237e-05, "loss": 0.4952, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.34304911983206093, "learning_rate": 2.4071527684116807e-05, "loss": 0.4861, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.5012905637296432, "learning_rate": 2.4016141457114372e-05, "loss": 0.483, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.2787846770482309, "learning_rate": 2.396072311715187e-05, "loss": 0.4921, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.43119646290013147, "learning_rate": 2.3905273107352863e-05, "loss": 0.489, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.36123525284026425, "learning_rate": 2.3849791871094157e-05, "loss": 0.5023, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.3629574786413857, "learning_rate": 2.379427985200223e-05, "loss": 0.4908, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.446389297891404, "learning_rate": 2.373873749394972e-05, "loss": 0.4882, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.3224039310469981, "learning_rate": 2.3683165241051836e-05, "loss": 0.4879, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.41568550654257874, "learning_rate": 2.3627563537662823e-05, "loss": 0.4788, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.39186843445479175, "learning_rate": 2.3571932828372433e-05, "loss": 0.4655, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3430408661529002, "learning_rate": 2.351627355800233e-05, "loss": 0.4775, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.368693281442413, "learning_rate": 2.346058617160256e-05, "loss": 0.4829, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.33154581545472106, "learning_rate": 2.3404871114447976e-05, "loss": 0.47, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3508198908002298, "learning_rate": 2.334912883203469e-05, "loss": 0.4748, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.29778074815575606, "learning_rate": 2.3293359770076505e-05, "loss": 0.4708, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.37830232900157174, "learning_rate": 2.323756437450136e-05, "loss": 0.4871, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.3488407547932989, "learning_rate": 2.3181743091447754e-05, "loss": 0.4859, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.29428377984496845, "learning_rate": 2.3125896367261164e-05, "loss": 0.4748, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.31404604721697466, "learning_rate": 2.307002464849052e-05, "loss": 0.4845, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.27254350543002587, "learning_rate": 2.30141283818846e-05, "loss": 0.4632, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.32846851303766905, "learning_rate": 2.2958208014388462e-05, "loss": 0.4817, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.29580791679142565, "learning_rate": 2.2902263993139857e-05, "loss": 0.4898, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.29905522975791565, "learning_rate": 2.2846296765465708e-05, "loss": 0.4867, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3234855853067093, "learning_rate": 2.2790306778878465e-05, "loss": 0.4933, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.28126675699511694, "learning_rate": 2.273429448107257e-05, "loss": 0.478, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.2927533609284773, "learning_rate": 2.2678260319920868e-05, "loss": 0.4844, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.3018230436376904, "learning_rate": 2.262220474347102e-05, "loss": 0.4653, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3175233920084268, "learning_rate": 2.2566128199941918e-05, "loss": 0.4843, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.34238858304702574, "learning_rate": 2.2510031137720104e-05, "loss": 0.483, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.29391701707264706, "learning_rate": 2.2453914005356206e-05, "loss": 0.4775, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.2889947377820656, "learning_rate": 2.2397777251561302e-05, "loss": 0.4756, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.27009085341908806, "learning_rate": 2.2341621325203393e-05, "loss": 0.4723, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3185134939646456, "learning_rate": 2.2285446675303764e-05, "loss": 0.4872, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.31622189915045246, "learning_rate": 2.2229253751033423e-05, "loss": 0.487, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.295404576373028, "learning_rate": 2.2173043001709492e-05, "loss": 0.4979, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.31624272177680945, "learning_rate": 2.2116814876791627e-05, "loss": 0.4894, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.2825841349168955, "learning_rate": 2.2060569825878413e-05, "loss": 0.489, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.32923124104101587, "learning_rate": 2.2004308298703777e-05, "loss": 0.48, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.30192500001327616, "learning_rate": 2.1948030745133396e-05, "loss": 0.4881, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.27951773569597993, "learning_rate": 2.1891737615161083e-05, "loss": 0.4898, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.26177080905608674, "learning_rate": 2.1835429358905218e-05, "loss": 0.4862, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3078828093546271, "learning_rate": 2.17791064266051e-05, "loss": 0.4859, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.256790460824699, "learning_rate": 2.172276926861741e-05, "loss": 0.4827, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.2936663933447165, "learning_rate": 2.166641833541255e-05, "loss": 0.4761, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.2688143040225524, "learning_rate": 2.161005407757109e-05, "loss": 0.4786, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.306125243670988, "learning_rate": 2.155367694578013e-05, "loss": 0.4939, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.28037186763211114, "learning_rate": 2.1497287390829712e-05, "loss": 0.4804, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.29748619872932663, "learning_rate": 2.1440885863609208e-05, "loss": 0.4702, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.2936645563492996, "learning_rate": 2.1384472815103737e-05, "loss": 0.4915, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3475239322263207, "learning_rate": 2.1328048696390534e-05, "loss": 0.4738, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.2976423495533165, "learning_rate": 2.1271613958635342e-05, "loss": 0.4823, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.3670244815081606, "learning_rate": 2.1215169053088825e-05, "loss": 0.4631, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.2797609927856043, "learning_rate": 2.1158714431082937e-05, "loss": 0.4798, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3317795963332142, "learning_rate": 2.110225054402733e-05, "loss": 0.4847, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.27184304540783255, "learning_rate": 2.1045777843405747e-05, "loss": 0.4877, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.27114406917487155, "learning_rate": 2.09892967807724e-05, "loss": 0.4787, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.27913972009389737, "learning_rate": 2.093280780774835e-05, "loss": 0.4733, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.255601910229879, "learning_rate": 2.087631137601793e-05, "loss": 0.4691, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.2771294180738459, "learning_rate": 2.0819807937325104e-05, "loss": 0.4732, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.24505104613447687, "learning_rate": 2.0763297943469847e-05, "loss": 0.4802, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.2590771797515053, "learning_rate": 2.070678184630458e-05, "loss": 0.4646, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.29862204102478984, "learning_rate": 2.06502600977305e-05, "loss": 0.4834, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.26692349814056826, "learning_rate": 2.0593733149694008e-05, "loss": 0.474, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.30474624264924305, "learning_rate": 2.0537201454183074e-05, "loss": 0.4837, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.2866102879036461, "learning_rate": 2.0480665463223626e-05, "loss": 0.4703, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3147467537667422, "learning_rate": 2.042412562887594e-05, "loss": 0.4683, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.28074742708001144, "learning_rate": 2.0367582403231033e-05, "loss": 0.4767, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.31618472820611454, "learning_rate": 2.0311036238407023e-05, "loss": 0.4873, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.2751028276366503, "learning_rate": 2.0254487586545534e-05, "loss": 0.4674, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.28693954133438804, "learning_rate": 2.0197936899808088e-05, "loss": 0.4942, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.27682365411501986, "learning_rate": 2.0141384630372466e-05, "loss": 0.4873, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.2619097369277152, "learning_rate": 2.0084831230429106e-05, "loss": 0.4749, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.28634582661408137, "learning_rate": 2.0028277152177492e-05, "loss": 0.4815, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.27418117779206136, "learning_rate": 1.9971722847822518e-05, "loss": 0.4696, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.28403502616165627, "learning_rate": 1.99151687695709e-05, "loss": 0.4835, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.2660102349183622, "learning_rate": 1.9858615369627537e-05, "loss": 0.487, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.29049109317633426, "learning_rate": 1.9802063100191916e-05, "loss": 0.4802, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.274509502163027, "learning_rate": 1.974551241345447e-05, "loss": 0.4831, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.27011179634318616, "learning_rate": 1.9688963761592984e-05, "loss": 0.4865, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.2729100588093152, "learning_rate": 1.963241759676897e-05, "loss": 0.4915, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.28189879090349934, "learning_rate": 1.9575874371124066e-05, "loss": 0.4784, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.29827425365652455, "learning_rate": 1.951933453677638e-05, "loss": 0.4815, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.2715338862843642, "learning_rate": 1.9462798545816932e-05, "loss": 0.4638, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.27689442570764355, "learning_rate": 1.9406266850305996e-05, "loss": 0.4741, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.27628748504357326, "learning_rate": 1.9349739902269503e-05, "loss": 0.4844, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.2664773225051895, "learning_rate": 1.9293218153695425e-05, "loss": 0.4867, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2665055436399126, "learning_rate": 1.9236702056530153e-05, "loss": 0.4795, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.28206024553649406, "learning_rate": 1.9180192062674907e-05, "loss": 0.4811, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.24373956739878153, "learning_rate": 1.9123688623982076e-05, "loss": 0.4915, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3118090841914482, "learning_rate": 1.906719219225165e-05, "loss": 0.4744, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.2903681137832201, "learning_rate": 1.9010703219227603e-05, "loss": 0.4892, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.3137842785006115, "learning_rate": 1.8954222156594256e-05, "loss": 0.4815, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.2724405022862149, "learning_rate": 1.8897749455972673e-05, "loss": 0.4884, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.27009109118343383, "learning_rate": 1.884128556891707e-05, "loss": 0.4759, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.2820853873081445, "learning_rate": 1.878483094691119e-05, "loss": 0.48, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.30699338003136084, "learning_rate": 1.8728386041364664e-05, "loss": 0.4795, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.27821521164567853, "learning_rate": 1.867195130360947e-05, "loss": 0.4814, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.32533313053502066, "learning_rate": 1.8615527184896263e-05, "loss": 0.4842, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.27281750640191604, "learning_rate": 1.8559114136390795e-05, "loss": 0.489, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.31830490340357254, "learning_rate": 1.8502712609170298e-05, "loss": 0.485, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.25616335018969205, "learning_rate": 1.8446323054219876e-05, "loss": 0.4807, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.31532772513242435, "learning_rate": 1.838994592242891e-05, "loss": 0.4808, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.2502582168112442, "learning_rate": 1.8333581664587453e-05, "loss": 0.4735, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3078128064540932, "learning_rate": 1.8277230731382593e-05, "loss": 0.4712, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3172491591854999, "learning_rate": 1.82208935733949e-05, "loss": 0.4865, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.2983605154213146, "learning_rate": 1.8164570641094793e-05, "loss": 0.4915, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3221010264859756, "learning_rate": 1.810826238483892e-05, "loss": 0.4665, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.2856234129946649, "learning_rate": 1.8051969254866608e-05, "loss": 0.4788, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.35748686739083707, "learning_rate": 1.7995691701296226e-05, "loss": 0.4836, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.26317234674409967, "learning_rate": 1.7939430174121593e-05, "loss": 0.4855, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.3590223219289394, "learning_rate": 1.788318512320838e-05, "loss": 0.4714, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.259358021752294, "learning_rate": 1.782695699829051e-05, "loss": 0.4745, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.2943654423877561, "learning_rate": 1.7770746248966587e-05, "loss": 0.4616, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.31063876022678716, "learning_rate": 1.7714553324696243e-05, "loss": 0.4713, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.2738121569694387, "learning_rate": 1.7658378674796614e-05, "loss": 0.4915, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.2700939811278988, "learning_rate": 1.76022227484387e-05, "loss": 0.4942, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.2917618288831645, "learning_rate": 1.7546085994643807e-05, "loss": 0.4819, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.27926991501111503, "learning_rate": 1.7489968862279902e-05, "loss": 0.4854, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3061252028763524, "learning_rate": 1.743387180005809e-05, "loss": 0.4729, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.29539770504079643, "learning_rate": 1.737779525652899e-05, "loss": 0.4832, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.27173349934280927, "learning_rate": 1.732173968007914e-05, "loss": 0.48, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.24537101033796935, "learning_rate": 1.7265705518927437e-05, "loss": 0.4794, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.25911332512048824, "learning_rate": 1.7209693221121542e-05, "loss": 0.4766, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.2584859378161288, "learning_rate": 1.7153703234534302e-05, "loss": 0.4907, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.2647990286293501, "learning_rate": 1.709773600686015e-05, "loss": 0.4894, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.26658876955469896, "learning_rate": 1.7041791985611548e-05, "loss": 0.4801, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.2721239749966838, "learning_rate": 1.69858716181154e-05, "loss": 0.468, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.2520883042919042, "learning_rate": 1.692997535150948e-05, "loss": 0.4775, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.2571215753521519, "learning_rate": 1.687410363273884e-05, "loss": 0.4615, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.2609454558810596, "learning_rate": 1.6818256908552257e-05, "loss": 0.4847, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.24272670580769276, "learning_rate": 1.6762435625498646e-05, "loss": 0.4753, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.2720313541066754, "learning_rate": 1.67066402299235e-05, "loss": 0.4828, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.248194763975322, "learning_rate": 1.6650871167965313e-05, "loss": 0.4818, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.27695922529319283, "learning_rate": 1.6595128885552028e-05, "loss": 0.4797, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.26318567996845865, "learning_rate": 1.653941382839745e-05, "loss": 0.479, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.45650029590150565, "learning_rate": 1.6483726441997673e-05, "loss": 0.4154, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.4262093186591114, "learning_rate": 1.642806717162757e-05, "loss": 0.4301, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.47348998644413987, "learning_rate": 1.637243646233718e-05, "loss": 0.4214, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.4710549625900568, "learning_rate": 1.6316834758948174e-05, "loss": 0.4285, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.3966204543208905, "learning_rate": 1.6261262506050282e-05, "loss": 0.4346, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.4060357977234318, "learning_rate": 1.620572014799777e-05, "loss": 0.41, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.32142303837987907, "learning_rate": 1.6150208128905857e-05, "loss": 0.4142, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.46101242525111097, "learning_rate": 1.6094726892647147e-05, "loss": 0.4145, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.2586561503949867, "learning_rate": 1.6039276882848135e-05, "loss": 0.4165, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.4385478488919435, "learning_rate": 1.5983858542885635e-05, "loss": 0.4294, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3021584218699525, "learning_rate": 1.5928472315883203e-05, "loss": 0.4111, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.3976091064421034, "learning_rate": 1.5873118644707633e-05, "loss": 0.4167, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.31648785182747935, "learning_rate": 1.5817797971965413e-05, "loss": 0.4121, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.35758079099288903, "learning_rate": 1.576251073999917e-05, "loss": 0.4108, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.2863527229882479, "learning_rate": 1.5707257390884126e-05, "loss": 0.4142, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.3348926280824329, "learning_rate": 1.5652038366424595e-05, "loss": 0.3966, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.2862061016631119, "learning_rate": 1.5596854108150424e-05, "loss": 0.4104, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3416019894648696, "learning_rate": 1.5541705057313476e-05, "loss": 0.4151, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3157481475146905, "learning_rate": 1.5486591654884086e-05, "loss": 0.3997, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3087220315591873, "learning_rate": 1.543151434154755e-05, "loss": 0.4108, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.3467775068268298, "learning_rate": 1.5376473557700615e-05, "loss": 0.4178, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.27548842938341384, "learning_rate": 1.5321469743447893e-05, "loss": 0.4114, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.31982079019537524, "learning_rate": 1.5266503338598434e-05, "loss": 0.4275, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.2588921362891655, "learning_rate": 1.5211574782662149e-05, "loss": 0.4146, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.29070528056583866, "learning_rate": 1.5156684514846307e-05, "loss": 0.4112, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2781400599503536, "learning_rate": 1.5101832974052012e-05, "loss": 0.4256, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.28655883693613804, "learning_rate": 1.5047020598870737e-05, "loss": 0.4158, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.31365350130724545, "learning_rate": 1.4992247827580778e-05, "loss": 0.4126, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.31045332980100077, "learning_rate": 1.493751509814374e-05, "loss": 0.4343, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.28021282482293575, "learning_rate": 1.4882822848201073e-05, "loss": 0.4134, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.2730448498950505, "learning_rate": 1.4828171515070553e-05, "loss": 0.4107, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3343950496078222, "learning_rate": 1.4773561535742793e-05, "loss": 0.4131, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.26207541219021085, "learning_rate": 1.4718993346877715e-05, "loss": 0.407, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.34123803485712034, "learning_rate": 1.466446738480111e-05, "loss": 0.4051, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.2595717303990614, "learning_rate": 1.460998408550112e-05, "loss": 0.4114, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3013238127151438, "learning_rate": 1.4555543884624751e-05, "loss": 0.4133, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.3094707478157428, "learning_rate": 1.4501147217474402e-05, "loss": 0.4064, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.2400076790564963, "learning_rate": 1.444679451900437e-05, "loss": 0.4231, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.3164220810239345, "learning_rate": 1.4392486223817397e-05, "loss": 0.4376, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2791286089971318, "learning_rate": 1.4338222766161143e-05, "loss": 0.4189, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2642280709584568, "learning_rate": 1.4284004579924777e-05, "loss": 0.4118, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.30338545132963135, "learning_rate": 1.4229832098635479e-05, "loss": 0.4075, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.261069207331197, "learning_rate": 1.4175705755454963e-05, "loss": 0.4282, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.28910772504769805, "learning_rate": 1.412162598317602e-05, "loss": 0.4139, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.2910178436529231, "learning_rate": 1.406759321421907e-05, "loss": 0.416, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2713677354046252, "learning_rate": 1.401360788062871e-05, "loss": 0.4292, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.3125425870105007, "learning_rate": 1.3959670414070204e-05, "loss": 0.4277, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.24815661499348887, "learning_rate": 1.3905781245826108e-05, "loss": 0.4106, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.2936437697457016, "learning_rate": 1.3851940806792778e-05, "loss": 0.4273, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3050683765630299, "learning_rate": 1.379814952747693e-05, "loss": 0.4197, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.28515824224432507, "learning_rate": 1.3744407837992193e-05, "loss": 0.4176, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.3014795063037893, "learning_rate": 1.3690716168055692e-05, "loss": 0.4192, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.26217037938269233, "learning_rate": 1.363707494698459e-05, "loss": 0.4103, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.3246240964315619, "learning_rate": 1.358348460369265e-05, "loss": 0.422, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.25777148223205104, "learning_rate": 1.352994556668684e-05, "loss": 0.4129, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.28888292110344455, "learning_rate": 1.3476458264063865e-05, "loss": 0.4264, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.24685040052734697, "learning_rate": 1.342302312350678e-05, "loss": 0.4303, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.29359707152834474, "learning_rate": 1.3369640572281537e-05, "loss": 0.4185, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.26413100600492573, "learning_rate": 1.3316311037233596e-05, "loss": 0.4078, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2719944886495048, "learning_rate": 1.326303494478451e-05, "loss": 0.4208, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3043521034451551, "learning_rate": 1.3209812720928472e-05, "loss": 0.4309, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.23627939343731258, "learning_rate": 1.315664479122898e-05, "loss": 0.4193, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.30445856389426373, "learning_rate": 1.3103531580815378e-05, "loss": 0.4243, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.2507243409791743, "learning_rate": 1.3050473514379488e-05, "loss": 0.4083, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.2908137510310197, "learning_rate": 1.2997471016172188e-05, "loss": 0.4139, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2798349878933796, "learning_rate": 1.2944524510000042e-05, "loss": 0.4147, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.264152383542044, "learning_rate": 1.2891634419221908e-05, "loss": 0.4092, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.3130584825040094, "learning_rate": 1.2838801166745545e-05, "loss": 0.417, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.23708282885842955, "learning_rate": 1.2786025175024216e-05, "loss": 0.4266, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.30346556042689626, "learning_rate": 1.2733306866053357e-05, "loss": 0.4197, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2658252862558411, "learning_rate": 1.2680646661367163e-05, "loss": 0.3994, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.23965782448940953, "learning_rate": 1.2628044982035219e-05, "loss": 0.4082, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.2798326265175618, "learning_rate": 1.2575502248659155e-05, "loss": 0.4022, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.25553706627697537, "learning_rate": 1.2523018881369269e-05, "loss": 0.4121, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2487787376230602, "learning_rate": 1.2470595299821176e-05, "loss": 0.4344, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.2658487252543883, "learning_rate": 1.2418231923192416e-05, "loss": 0.4316, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.2592151042467478, "learning_rate": 1.2365929170179165e-05, "loss": 0.4222, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.23518103703647958, "learning_rate": 1.2313687458992848e-05, "loss": 0.4104, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.24608860457447207, "learning_rate": 1.2261507207356785e-05, "loss": 0.4307, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.24132102724348017, "learning_rate": 1.220938883250288e-05, "loss": 0.4312, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.24757588965750357, "learning_rate": 1.215733275116827e-05, "loss": 0.4251, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.23905163135478277, "learning_rate": 1.2105339379592005e-05, "loss": 0.4227, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.25778580920988897, "learning_rate": 1.2053409133511681e-05, "loss": 0.4186, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.2517884930715115, "learning_rate": 1.2001542428160173e-05, "loss": 0.4268, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.24322841414344315, "learning_rate": 1.1949739678262278e-05, "loss": 0.4181, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.22885867168548188, "learning_rate": 1.189800129803139e-05, "loss": 0.4111, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.24290819395364827, "learning_rate": 1.1846327701166228e-05, "loss": 0.4194, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.22080899917973895, "learning_rate": 1.1794719300847493e-05, "loss": 0.427, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2404505848444869, "learning_rate": 1.1743176509734582e-05, "loss": 0.4079, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.2378729360997712, "learning_rate": 1.1691699739962275e-05, "loss": 0.4201, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.2409935519578863, "learning_rate": 1.1640289403137456e-05, "loss": 0.4295, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.2440179111674402, "learning_rate": 1.1588945910335802e-05, "loss": 0.4227, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.2380274787886335, "learning_rate": 1.1537669672098517e-05, "loss": 0.4213, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.25675394942040003, "learning_rate": 1.1486461098429036e-05, "loss": 0.418, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.24155906405120334, "learning_rate": 1.1435320598789747e-05, "loss": 0.4209, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.25903000864610504, "learning_rate": 1.1384248582098736e-05, "loss": 0.4277, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.24275445074141913, "learning_rate": 1.1333245456726467e-05, "loss": 0.4217, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.2463643667313472, "learning_rate": 1.128231163049258e-05, "loss": 0.4174, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2495940582984584, "learning_rate": 1.123144751066259e-05, "loss": 0.427, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2371732288685553, "learning_rate": 1.1180653503944657e-05, "loss": 0.4021, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.27184803340634894, "learning_rate": 1.1129930016486287e-05, "loss": 0.4248, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.22716713938917305, "learning_rate": 1.107927745387114e-05, "loss": 0.4188, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.28932480207702227, "learning_rate": 1.1028696221115766e-05, "loss": 0.4154, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.23556280345191963, "learning_rate": 1.0978186722666341e-05, "loss": 0.4067, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.24791653639048042, "learning_rate": 1.0927749362395475e-05, "loss": 0.419, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.24198754753749832, "learning_rate": 1.0877384543598954e-05, "loss": 0.397, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.23937210259221314, "learning_rate": 1.0827092668992529e-05, "loss": 0.4234, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.24338653461015422, "learning_rate": 1.077687414070869e-05, "loss": 0.4106, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.2438635340352572, "learning_rate": 1.0726729360293451e-05, "loss": 0.4139, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.2559155279096328, "learning_rate": 1.0676658728703147e-05, "loss": 0.4174, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.23299032906591113, "learning_rate": 1.0626662646301198e-05, "loss": 0.4103, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2519566146997857, "learning_rate": 1.0576741512854958e-05, "loss": 0.3962, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.268172740479609, "learning_rate": 1.052689572753247e-05, "loss": 0.4095, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.25808849028015923, "learning_rate": 1.0477125688899328e-05, "loss": 0.409, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.23806659415211168, "learning_rate": 1.0427431794915406e-05, "loss": 0.4116, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2476720185709979, "learning_rate": 1.0377814442931769e-05, "loss": 0.4121, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.26355989292767634, "learning_rate": 1.0328274029687439e-05, "loss": 0.4207, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.24039160318801606, "learning_rate": 1.0278810951306253e-05, "loss": 0.4212, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.2612244111998821, "learning_rate": 1.0229425603293647e-05, "loss": 0.443, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.24275824312241626, "learning_rate": 1.0180118380533558e-05, "loss": 0.4201, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.24030917367742133, "learning_rate": 1.0130889677285225e-05, "loss": 0.4241, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.2560288131084518, "learning_rate": 1.008173988718005e-05, "loss": 0.413, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2388078527386156, "learning_rate": 1.0032669403218439e-05, "loss": 0.4125, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.23991215333499333, "learning_rate": 9.983678617766677e-06, "loss": 0.4091, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.24006484294823555, "learning_rate": 9.934767922553788e-06, "loss": 0.4166, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.24005929004756993, "learning_rate": 9.885937708668371e-06, "loss": 0.4162, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.22391746594370907, "learning_rate": 9.837188366555524e-06, "loss": 0.4236, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.2402330280663496, "learning_rate": 9.788520286013691e-06, "loss": 0.4293, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.23060482175184494, "learning_rate": 9.739933856191537e-06, "loss": 0.4146, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.24140306288623398, "learning_rate": 9.691429465584866e-06, "loss": 0.4215, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.24034778973647095, "learning_rate": 9.643007502033492e-06, "loss": 0.4127, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.24682071343006565, "learning_rate": 9.594668352718152e-06, "loss": 0.4034, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.21884037303938902, "learning_rate": 9.546412404157383e-06, "loss": 0.4147, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.23622348187298736, "learning_rate": 9.498240042204471e-06, "loss": 0.4177, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.2401198411863862, "learning_rate": 9.450151652044339e-06, "loss": 0.4301, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.24649415501364527, "learning_rate": 9.402147618190472e-06, "loss": 0.4303, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.22788556225248427, "learning_rate": 9.354228324481841e-06, "loss": 0.4175, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.22284958097266433, "learning_rate": 9.306394154079852e-06, "loss": 0.4194, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.2293440647274355, "learning_rate": 9.258645489465254e-06, "loss": 0.4279, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.21949268387456242, "learning_rate": 9.21098271243509e-06, "loss": 0.4159, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.2288339907523895, "learning_rate": 9.163406204099659e-06, "loss": 0.4109, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.21426182610710867, "learning_rate": 9.115916344879452e-06, "loss": 0.4151, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.22321325507052078, "learning_rate": 9.068513514502126e-06, "loss": 0.4147, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.22435937751130997, "learning_rate": 9.021198091999439e-06, "loss": 0.4185, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.23553241685828136, "learning_rate": 8.973970455704251e-06, "loss": 0.4146, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.3092427255785059, "learning_rate": 8.926830983247495e-06, "loss": 0.4185, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.22730153064698988, "learning_rate": 8.879780051555116e-06, "loss": 0.4183, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2287242390257417, "learning_rate": 8.83281803684512e-06, "loss": 0.4206, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.22294316315005405, "learning_rate": 8.785945314624532e-06, "loss": 0.4208, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.23359109964400723, "learning_rate": 8.739162259686385e-06, "loss": 0.4203, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.23465913560831095, "learning_rate": 8.692469246106734e-06, "loss": 0.4044, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.23719830975006842, "learning_rate": 8.645866647241677e-06, "loss": 0.4214, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2253688187182556, "learning_rate": 8.599354835724348e-06, "loss": 0.4172, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.23417061042319642, "learning_rate": 8.552934183461958e-06, "loss": 0.4176, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.22373446877513106, "learning_rate": 8.506605061632805e-06, "loss": 0.4228, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.2130963894330418, "learning_rate": 8.460367840683308e-06, "loss": 0.4276, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.24183905058152735, "learning_rate": 8.414222890325065e-06, "loss": 0.4159, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.23390998441480482, "learning_rate": 8.368170579531855e-06, "loss": 0.4224, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.21293275532702416, "learning_rate": 8.322211276536733e-06, "loss": 0.4274, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.2326790562825855, "learning_rate": 8.27634534882907e-06, "loss": 0.4139, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.22455412428773316, "learning_rate": 8.230573163151585e-06, "loss": 0.4145, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.23932350602696148, "learning_rate": 8.184895085497466e-06, "loss": 0.3963, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.2311690253856804, "learning_rate": 8.139311481107401e-06, "loss": 0.429, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.21926554958435707, "learning_rate": 8.093822714466686e-06, "loss": 0.4168, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.22419728712558698, "learning_rate": 8.048429149302271e-06, "loss": 0.4219, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.22786467275601516, "learning_rate": 8.003131148579902e-06, "loss": 0.4291, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2295018140958607, "learning_rate": 7.957929074501182e-06, "loss": 0.4234, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.22742340261765662, "learning_rate": 7.912823288500695e-06, "loss": 0.4192, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.23236851394084493, "learning_rate": 7.867814151243102e-06, "loss": 0.4261, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.22197538526521698, "learning_rate": 7.822902022620267e-06, "loss": 0.4216, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.24900771676566966, "learning_rate": 7.778087261748377e-06, "loss": 0.4138, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.22386416260480446, "learning_rate": 7.733370226965056e-06, "loss": 0.4085, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.22635486210018507, "learning_rate": 7.688751275826527e-06, "loss": 0.4143, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.25722106670993905, "learning_rate": 7.644230765104735e-06, "loss": 0.4168, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.22936029470837968, "learning_rate": 7.599809050784502e-06, "loss": 0.4258, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.23604079712085038, "learning_rate": 7.555486488060661e-06, "loss": 0.4106, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.23463130814832875, "learning_rate": 7.511263431335249e-06, "loss": 0.4198, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.20664027078173294, "learning_rate": 7.467140234214656e-06, "loss": 0.4135, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.23464545355994104, "learning_rate": 7.423117249506777e-06, "loss": 0.4277, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.23224558751755095, "learning_rate": 7.379194829218231e-06, "loss": 0.4404, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.2103735902400909, "learning_rate": 7.335373324551518e-06, "loss": 0.4039, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.22462105863913345, "learning_rate": 7.291653085902224e-06, "loss": 0.4077, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2264738875029294, "learning_rate": 7.248034462856213e-06, "loss": 0.441, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.23348633303587085, "learning_rate": 7.20451780418683e-06, "loss": 0.3979, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.22102429954654002, "learning_rate": 7.161103457852128e-06, "loss": 0.4199, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.25218650860920755, "learning_rate": 7.117791770992046e-06, "loss": 0.429, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.23301295454138582, "learning_rate": 7.074583089925688e-06, "loss": 0.4101, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.23220080190957476, "learning_rate": 7.0314777601485155e-06, "loss": 0.415, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.2240902424123142, "learning_rate": 6.988476126329604e-06, "loss": 0.4174, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.23477301923370744, "learning_rate": 6.945578532308857e-06, "loss": 0.4149, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.24465377802136237, "learning_rate": 6.902785321094301e-06, "loss": 0.4168, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.228223441165098, "learning_rate": 6.8600968348593115e-06, "loss": 0.4187, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.2230006641825921, "learning_rate": 6.817513414939892e-06, "loss": 0.415, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.22722341203253096, "learning_rate": 6.775035401831924e-06, "loss": 0.4145, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.20418669642832463, "learning_rate": 6.732663135188473e-06, "loss": 0.4272, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.22679609481043744, "learning_rate": 6.690396953817055e-06, "loss": 0.414, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.23002267726364714, "learning_rate": 6.648237195676927e-06, "loss": 0.4259, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.21564500598905895, "learning_rate": 6.606184197876395e-06, "loss": 0.4195, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.21521301268963142, "learning_rate": 6.564238296670109e-06, "loss": 0.402, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.220019369053253, "learning_rate": 6.52239982745638e-06, "loss": 0.4161, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.20246443262751765, "learning_rate": 6.480669124774484e-06, "loss": 0.421, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.2103176612662993, "learning_rate": 6.439046522302013e-06, "loss": 0.4256, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.21981954181934707, "learning_rate": 6.397532352852191e-06, "loss": 0.4202, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.2307550140706889, "learning_rate": 6.356126948371202e-06, "loss": 0.4164, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.2185401423314115, "learning_rate": 6.314830639935559e-06, "loss": 0.4088, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.20566783684889978, "learning_rate": 6.273643757749448e-06, "loss": 0.421, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.2200806613522291, "learning_rate": 6.2325666311420856e-06, "loss": 0.4173, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.23322282981026843, "learning_rate": 6.1915995885650675e-06, "loss": 0.4287, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.22137818966677072, "learning_rate": 6.150742957589784e-06, "loss": 0.4267, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.22080522440734013, "learning_rate": 6.109997064904774e-06, "loss": 0.4085, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.2129225715423571, "learning_rate": 6.069362236313092e-06, "loss": 0.4181, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.22458064553864915, "learning_rate": 6.0288387967297565e-06, "loss": 0.409, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2152449171566053, "learning_rate": 5.988427070179108e-06, "loss": 0.4262, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2032179127393196, "learning_rate": 5.948127379792234e-06, "loss": 0.4136, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.22940723872593236, "learning_rate": 5.90794004780439e-06, "loss": 0.4045, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.24576737787878328, "learning_rate": 5.867865395552405e-06, "loss": 0.4153, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.25721678412991117, "learning_rate": 5.8279037434721364e-06, "loss": 0.4083, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.22239429841005925, "learning_rate": 5.788055411095892e-06, "loss": 0.4216, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.245901119659113, "learning_rate": 5.7483207170498625e-06, "loss": 0.4268, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.23911966738293888, "learning_rate": 5.708699979051613e-06, "loss": 0.4336, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.206734131350416, "learning_rate": 5.66919351390751e-06, "loss": 0.4182, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.2503149515019083, "learning_rate": 5.629801637510188e-06, "loss": 0.4307, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.23581445906961915, "learning_rate": 5.590524664836043e-06, "loss": 0.4187, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.21396025036402821, "learning_rate": 5.551362909942708e-06, "loss": 0.4248, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2069857723259253, "learning_rate": 5.51231668596653e-06, "loss": 0.4248, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.22368084058696552, "learning_rate": 5.47338630512007e-06, "loss": 0.4153, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.22690434318560496, "learning_rate": 5.434572078689617e-06, "loss": 0.4086, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.2045245880194845, "learning_rate": 5.395874317032694e-06, "loss": 0.427, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.2077231834159897, "learning_rate": 5.357293329575573e-06, "loss": 0.408, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2151245310621232, "learning_rate": 5.318829424810797e-06, "loss": 0.4164, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.20345612864680512, "learning_rate": 5.280482910294728e-06, "loss": 0.4087, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.19819998734160735, "learning_rate": 5.242254092645078e-06, "loss": 0.4194, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.20464515057848112, "learning_rate": 5.2041432775384445e-06, "loss": 0.4173, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.20291216427130437, "learning_rate": 5.166150769707892e-06, "loss": 0.4062, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.21266137219122655, "learning_rate": 5.128276872940503e-06, "loss": 0.425, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.2168927594443113, "learning_rate": 5.090521890074953e-06, "loss": 0.4196, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.21171835182583226, "learning_rate": 5.0528861229990675e-06, "loss": 0.4086, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.20577744892305447, "learning_rate": 5.015369872647442e-06, "loss": 0.4178, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2194219059952537, "learning_rate": 4.9779734389990195e-06, "loss": 0.4316, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.22517766715485169, "learning_rate": 4.940697121074675e-06, "loss": 0.4189, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.21566650215387928, "learning_rate": 4.903541216934864e-06, "loss": 0.4122, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.197300260434329, "learning_rate": 4.8665060236772e-06, "loss": 0.4234, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.21779296454004607, "learning_rate": 4.829591837434102e-06, "loss": 0.4218, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.20195732614313494, "learning_rate": 4.792798953370424e-06, "loss": 0.415, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.21304334601678046, "learning_rate": 4.756127665681083e-06, "loss": 0.4316, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2105881062078211, "learning_rate": 4.719578267588725e-06, "loss": 0.427, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.2019137848443129, "learning_rate": 4.6831510513413525e-06, "loss": 0.4028, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3606966601102748, "learning_rate": 4.6468463082100176e-06, "loss": 0.3889, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.30444777392249933, "learning_rate": 4.610664328486485e-06, "loss": 0.3606, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.2886090757972497, "learning_rate": 4.5746054014809e-06, "loss": 0.3763, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.4415214139295201, "learning_rate": 4.5386698155194766e-06, "loss": 0.3667, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3040161374283923, "learning_rate": 4.502857857942204e-06, "loss": 0.3634, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.32663551115567263, "learning_rate": 4.467169815100549e-06, "loss": 0.3794, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.37001280267035214, "learning_rate": 4.431605972355137e-06, "loss": 0.3737, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.28327056964784114, "learning_rate": 4.396166614073516e-06, "loss": 0.3722, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.24373503363709442, "learning_rate": 4.360852023627846e-06, "loss": 0.3838, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.2757170681763288, "learning_rate": 4.325662483392656e-06, "loss": 0.3846, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.29087088801160343, "learning_rate": 4.29059827474257e-06, "loss": 0.3715, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.26118014295309466, "learning_rate": 4.255659678050063e-06, "loss": 0.3646, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.23672178656418913, "learning_rate": 4.22084697268323e-06, "loss": 0.3853, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.24856080193059704, "learning_rate": 4.186160437003535e-06, "loss": 0.3861, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.24621538881884206, "learning_rate": 4.151600348363582e-06, "loss": 0.3777, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.2514391668015992, "learning_rate": 4.11716698310493e-06, "loss": 0.3685, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.22165970393416684, "learning_rate": 4.082860616555848e-06, "loss": 0.3764, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.21665675483631508, "learning_rate": 4.048681523029125e-06, "loss": 0.3612, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.24833004714483586, "learning_rate": 4.014629975819882e-06, "loss": 0.3701, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.24499243267638643, "learning_rate": 3.9807062472033855e-06, "loss": 0.382, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.2312999471686835, "learning_rate": 3.94691060843287e-06, "loss": 0.374, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.2139566008027016, "learning_rate": 3.913243329737353e-06, "loss": 0.3857, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.2238813473581778, "learning_rate": 3.879704680319503e-06, "loss": 0.3868, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.23112182352757782, "learning_rate": 3.846294928353471e-06, "loss": 0.3817, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.222881570637751, "learning_rate": 3.8130143409827345e-06, "loss": 0.3727, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.21203198173066287, "learning_rate": 3.7798631843179887e-06, "loss": 0.3781, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2219740083586643, "learning_rate": 3.7468417234349973e-06, "loss": 0.3656, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.23005440151989726, "learning_rate": 3.7139502223724823e-06, "loss": 0.3593, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.21554142597110576, "learning_rate": 3.6811889441300095e-06, "loss": 0.3749, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.21777530577242182, "learning_rate": 3.648558150665886e-06, "loss": 0.3783, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.22115532832182194, "learning_rate": 3.616058102895075e-06, "loss": 0.3767, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2132038514173904, "learning_rate": 3.583689060687079e-06, "loss": 0.3825, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.207969872188024, "learning_rate": 3.5514512828639023e-06, "loss": 0.3686, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.19983454625159683, "learning_rate": 3.51934502719796e-06, "loss": 0.3801, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.2059805360070861, "learning_rate": 3.4873705504100185e-06, "loss": 0.3658, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.20065342506586528, "learning_rate": 3.4555281081671345e-06, "loss": 0.3765, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.20394123231666889, "learning_rate": 3.4238179550806326e-06, "loss": 0.3839, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.20652718582528556, "learning_rate": 3.3922403447040497e-06, "loss": 0.3776, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.20597940500196701, "learning_rate": 3.3607955295311247e-06, "loss": 0.3786, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2104456926272191, "learning_rate": 3.32948376099375e-06, "loss": 0.3743, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.21388088679118442, "learning_rate": 3.2983052894599976e-06, "loss": 0.3662, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.20960464600352108, "learning_rate": 3.2672603642320945e-06, "loss": 0.3744, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.20686638039039187, "learning_rate": 3.236349233544438e-06, "loss": 0.3898, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.19895194372740022, "learning_rate": 3.205572144561604e-06, "loss": 0.3778, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2174473636344013, "learning_rate": 3.174929343376374e-06, "loss": 0.3808, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.19738397745822092, "learning_rate": 3.1444210750077777e-06, "loss": 0.3907, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.20955449961685452, "learning_rate": 3.1140475833991046e-06, "loss": 0.3722, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.20276716506313877, "learning_rate": 3.0838091114159895e-06, "loss": 0.3692, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2074981434457121, "learning_rate": 3.0537059008444524e-06, "loss": 0.3549, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.20794168687533235, "learning_rate": 3.0237381923889563e-06, "loss": 0.3682, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.19907045246817484, "learning_rate": 2.9939062256704997e-06, "loss": 0.375, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.20369898859711705, "learning_rate": 2.964210239224696e-06, "loss": 0.3852, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.20855601508427266, "learning_rate": 2.934650470499869e-06, "loss": 0.3622, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2100628352877288, "learning_rate": 2.905227155855128e-06, "loss": 0.3592, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2249770662279609, "learning_rate": 2.875940530558519e-06, "loss": 0.3655, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.20255794251925102, "learning_rate": 2.8467908287851154e-06, "loss": 0.376, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.20384591030959195, "learning_rate": 2.8177782836151603e-06, "loss": 0.3776, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2100786180524005, "learning_rate": 2.7889031270321874e-06, "loss": 0.3635, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.20262531545672366, "learning_rate": 2.760165589921184e-06, "loss": 0.3821, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.2092307529052104, "learning_rate": 2.7315659020667305e-06, "loss": 0.3754, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2072760207395725, "learning_rate": 2.703104292151164e-06, "loss": 0.3715, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.2074695479334176, "learning_rate": 2.6747809877527607e-06, "loss": 0.3731, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.20586686583961927, "learning_rate": 2.6465962153439082e-06, "loss": 0.3762, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.20192008715680787, "learning_rate": 2.618550200289303e-06, "loss": 0.3871, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.20361050524370405, "learning_rate": 2.59064316684412e-06, "loss": 0.3764, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.20743110306634396, "learning_rate": 2.562875338152264e-06, "loss": 0.3538, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.21117576734701435, "learning_rate": 2.5352469362445552e-06, "loss": 0.3623, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2147946734670853, "learning_rate": 2.5077581820369523e-06, "loss": 0.3712, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.20076486210509964, "learning_rate": 2.480409295328803e-06, "loss": 0.3822, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.21224822470973903, "learning_rate": 2.45320049480108e-06, "loss": 0.3668, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.20271915841127153, "learning_rate": 2.4261319980146293e-06, "loss": 0.3647, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.2099783017855977, "learning_rate": 2.399204021408421e-06, "loss": 0.3772, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.20668996768050624, "learning_rate": 2.3724167802978395e-06, "loss": 0.3674, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.19845382925602473, "learning_rate": 2.3457704888729625e-06, "loss": 0.3704, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.2031758843704728, "learning_rate": 2.3192653601968162e-06, "loss": 0.3722, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.19977340344850308, "learning_rate": 2.2929016062037057e-06, "loss": 0.3795, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2152741974656386, "learning_rate": 2.2666794376975055e-06, "loss": 0.3768, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.21505708209982827, "learning_rate": 2.24059906434998e-06, "loss": 0.37, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.20543279799158579, "learning_rate": 2.214660694699091e-06, "loss": 0.3717, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.2116153711300222, "learning_rate": 2.188864536147355e-06, "loss": 0.3652, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.1997936295265869, "learning_rate": 2.1632107949601757e-06, "loss": 0.3813, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.20546581701240324, "learning_rate": 2.137699676264171e-06, "loss": 0.3715, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.2095354211398491, "learning_rate": 2.1123313840455738e-06, "loss": 0.3696, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.21846199599373142, "learning_rate": 2.08710612114857e-06, "loss": 0.3768, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2036359258568182, "learning_rate": 2.0620240892736953e-06, "loss": 0.3658, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.1985617993057767, "learning_rate": 2.0370854889762e-06, "loss": 0.3741, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.19800395640557567, "learning_rate": 2.0122905196644726e-06, "loss": 0.377, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.19887507808458926, "learning_rate": 1.987639379598427e-06, "loss": 0.3811, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.20258211005571958, "learning_rate": 1.963132265887919e-06, "loss": 0.3587, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20681908287606607, "learning_rate": 1.9387693744911784e-06, "loss": 0.3745, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.21211836746850427, "learning_rate": 1.9145509002132368e-06, "loss": 0.3647, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.20350119841636571, "learning_rate": 1.8904770367043723e-06, "loss": 0.3728, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.20753857168128045, "learning_rate": 1.8665479764585504e-06, "loss": 0.3851, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2041205450439026, "learning_rate": 1.8427639108118977e-06, "loss": 0.375, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.20529479375197732, "learning_rate": 1.8191250299411755e-06, "loss": 0.3715, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.19357962937949316, "learning_rate": 1.7956315228622446e-06, "loss": 0.3806, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.19993501020511087, "learning_rate": 1.7722835774285553e-06, "loss": 0.3747, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.19168025065203553, "learning_rate": 1.7490813803296624e-06, "loss": 0.3805, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.19752703987789572, "learning_rate": 1.726025117089718e-06, "loss": 0.3799, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.19306968365682095, "learning_rate": 1.70311497206598e-06, "loss": 0.388, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.1968276744105961, "learning_rate": 1.6803511284473638e-06, "loss": 0.3657, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.19376363669888388, "learning_rate": 1.6577337682529538e-06, "loss": 0.3713, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.1962374319992565, "learning_rate": 1.6352630723305617e-06, "loss": 0.3754, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.19724672909126523, "learning_rate": 1.612939220355272e-06, "loss": 0.3805, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.211119313512867, "learning_rate": 1.5907623908280112e-06, "loss": 0.3772, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.20195627506748076, "learning_rate": 1.568732761074121e-06, "loss": 0.3625, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.21367070026410165, "learning_rate": 1.5468505072419237e-06, "loss": 0.3714, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.19627430117959757, "learning_rate": 1.5251158043013448e-06, "loss": 0.3709, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2106599667290516, "learning_rate": 1.5035288260424885e-06, "loss": 0.3561, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.1999126771907028, "learning_rate": 1.4820897450742623e-06, "loss": 0.3743, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.21415511694717593, "learning_rate": 1.4607987328229767e-06, "loss": 0.362, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.2015157801439473, "learning_rate": 1.4396559595310056e-06, "loss": 0.3747, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.1980729941289169, "learning_rate": 1.4186615942553973e-06, "loss": 0.3714, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.18962670969509404, "learning_rate": 1.3978158048665424e-06, "loss": 0.3652, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2034339054595124, "learning_rate": 1.3771187580468115e-06, "loss": 0.3611, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.2060065602819576, "learning_rate": 1.3565706192892392e-06, "loss": 0.3794, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.19875656007799494, "learning_rate": 1.3361715528961993e-06, "loss": 0.3719, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.19951449648703903, "learning_rate": 1.3159217219780817e-06, "loss": 0.3819, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.19876854485977163, "learning_rate": 1.2958212884519949e-06, "loss": 0.3762, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.20048738308504188, "learning_rate": 1.2758704130404675e-06, "loss": 0.3655, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.19291937731746167, "learning_rate": 1.2560692552701738e-06, "loss": 0.3727, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.19053145884488695, "learning_rate": 1.2364179734706382e-06, "loss": 0.3882, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.1989154695287968, "learning_rate": 1.2169167247729852e-06, "loss": 0.3767, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.19302792152633091, "learning_rate": 1.1975656651086864e-06, "loss": 0.3796, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.19919382442374473, "learning_rate": 1.1783649492082926e-06, "loss": 0.3803, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.20572034755673316, "learning_rate": 1.1593147306002183e-06, "loss": 0.3626, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.19830256527003318, "learning_rate": 1.140415161609505e-06, "loss": 0.3828, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.19565452692109206, "learning_rate": 1.121666393356604e-06, "loss": 0.3746, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.19333310759542124, "learning_rate": 1.1030685757561632e-06, "loss": 0.3848, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.1957838425992772, "learning_rate": 1.0846218575158373e-06, "loss": 0.3766, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.19798237605085328, "learning_rate": 1.066326386135097e-06, "loss": 0.3698, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.21116151480174164, "learning_rate": 1.0481823079040398e-06, "loss": 0.3607, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.1978564445178577, "learning_rate": 1.0301897679022344e-06, "loss": 0.3794, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.19635493098881804, "learning_rate": 1.0123489099975491e-06, "loss": 0.3765, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.20516462093956853, "learning_rate": 9.9465987684501e-07, "loss": 0.3646, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.1975864599898427, "learning_rate": 9.771228098856534e-07, "loss": 0.3723, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.19128224968536234, "learning_rate": 9.597378493454013e-07, "loss": 0.3822, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.19222879114316507, "learning_rate": 9.425051342339353e-07, "loss": 0.3722, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.1958840493363243, "learning_rate": 9.254248023435864e-07, "loss": 0.3626, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.20100409637143454, "learning_rate": 9.084969902482288e-07, "loss": 0.357, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.20096826216675334, "learning_rate": 8.917218333021993e-07, "loss": 0.3642, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.19973218613215007, "learning_rate": 8.750994656392109e-07, "loss": 0.3704, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.20192380064385967, "learning_rate": 8.58630020171265e-07, "loss": 0.3794, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.20058581049037638, "learning_rate": 8.423136285876099e-07, "loss": 0.3662, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.20139335231541558, "learning_rate": 8.26150421353682e-07, "loss": 0.3705, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.20064252908863667, "learning_rate": 8.101405277100549e-07, "loss": 0.3694, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.1975106603438327, "learning_rate": 7.942840756714077e-07, "loss": 0.3837, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.19677199363655704, "learning_rate": 7.785811920255093e-07, "loss": 0.379, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.198077409341132, "learning_rate": 7.630320023322024e-07, "loss": 0.3593, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.19342225690071346, "learning_rate": 7.476366309223903e-07, "loss": 0.3689, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.1904331871414298, "learning_rate": 7.323952008970537e-07, "loss": 0.3768, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.19812242158445917, "learning_rate": 7.173078341262618e-07, "loss": 0.3698, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.19879314969546294, "learning_rate": 7.023746512481989e-07, "loss": 0.3607, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.19753540535085568, "learning_rate": 6.875957716681902e-07, "loss": 0.3769, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.19875487474678463, "learning_rate": 6.729713135577687e-07, "loss": 0.3606, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.1948222029607248, "learning_rate": 6.585013938537143e-07, "loss": 0.3687, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.1912179791913035, "learning_rate": 6.441861282571115e-07, "loss": 0.372, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.19950814421047103, "learning_rate": 6.300256312324471e-07, "loss": 0.37, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.19332157616341167, "learning_rate": 6.160200160066776e-07, "loss": 0.3862, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.19254542561828647, "learning_rate": 6.021693945683327e-07, "loss": 0.3704, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.20162645515579877, "learning_rate": 5.884738776666044e-07, "loss": 0.3644, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.18706296292996383, "learning_rate": 5.749335748104878e-07, "loss": 0.3828, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.19972652651869915, "learning_rate": 5.615485942678778e-07, "loss": 0.3718, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.1918256137537554, "learning_rate": 5.483190430647289e-07, "loss": 0.3871, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.19264527288548516, "learning_rate": 5.352450269841747e-07, "loss": 0.3772, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.19585772398851506, "learning_rate": 5.22326650565701e-07, "loss": 0.3649, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.195057681765119, "learning_rate": 5.095640171043048e-07, "loss": 0.3731, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.1975591297460501, "learning_rate": 4.969572286496594e-07, "loss": 0.3712, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.20391293046361852, "learning_rate": 4.845063860053079e-07, "loss": 0.3801, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.1909829290775936, "learning_rate": 4.7221158872785997e-07, "loss": 0.3637, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.20764829710327465, "learning_rate": 4.600729351261857e-07, "loss": 0.3647, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.19036083747431767, "learning_rate": 4.4809052226063355e-07, "loss": 0.3747, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.20367262807410472, "learning_rate": 4.3626444594226046e-07, "loss": 0.3705, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.1874460897631755, "learning_rate": 4.245948007320588e-07, "loss": 0.3701, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.1945823334716335, "learning_rate": 4.130816799401971e-07, "loss": 0.3773, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.1974390158330514, "learning_rate": 4.017251756252827e-07, "loss": 0.3753, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.20148818406877517, "learning_rate": 3.9052537859362473e-07, "loss": 0.3655, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.18991216483623288, "learning_rate": 3.7948237839849687e-07, "loss": 0.3837, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.19871843459442995, "learning_rate": 3.6859626333943797e-07, "loss": 0.3795, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.20077313087383514, "learning_rate": 3.578671204615347e-07, "loss": 0.3649, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.19658755344329984, "learning_rate": 3.472950355547267e-07, "loss": 0.3804, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.19794529726885787, "learning_rate": 3.3688009315312244e-07, "loss": 0.3579, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.18868652530974653, "learning_rate": 3.266223765343224e-07, "loss": 0.3717, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2013466537372202, "learning_rate": 3.16521967718757e-07, "loss": 0.3584, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.19286041962239495, "learning_rate": 3.0657894746902726e-07, "loss": 0.3818, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.196954962599738, "learning_rate": 2.9679339528925654e-07, "loss": 0.3747, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.18995378068578578, "learning_rate": 2.871653894244597e-07, "loss": 0.3737, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.19258706790998162, "learning_rate": 2.7769500685991266e-07, "loss": 0.3634, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.20816149952590607, "learning_rate": 2.683823233205485e-07, "loss": 0.3837, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.19263894660777875, "learning_rate": 2.592274132703287e-07, "loss": 0.3924, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.20020378459972554, "learning_rate": 2.502303499116754e-07, "loss": 0.3675, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.21652374019405474, "learning_rate": 2.413912051848666e-07, "loss": 0.3589, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.19316903218197096, "learning_rate": 2.3271004976746613e-07, "loss": 0.3763, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.19278814573943967, "learning_rate": 2.2418695307376393e-07, "loss": 0.3762, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.19072775749967363, "learning_rate": 2.1582198325420968e-07, "loss": 0.3847, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.19341612426505825, "learning_rate": 2.0761520719488447e-07, "loss": 0.3695, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.19451080691233286, "learning_rate": 1.9956669051694798e-07, "loss": 0.3767, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.19682937501531889, "learning_rate": 1.916764975761254e-07, "loss": 0.3663, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.18675622547585347, "learning_rate": 1.839446914621923e-07, "loss": 0.3779, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.1870039684754336, "learning_rate": 1.7637133399845962e-07, "loss": 0.3743, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.19526642592329088, "learning_rate": 1.6895648574129397e-07, "loss": 0.3712, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.19845401969912846, "learning_rate": 1.6170020597962465e-07, "loss": 0.3573, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.19473385703974996, "learning_rate": 1.5460255273447078e-07, "loss": 0.3788, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.19262008224912888, "learning_rate": 1.4766358275847715e-07, "loss": 0.3782, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.19299439425315987, "learning_rate": 1.4088335153546573e-07, "loss": 0.3628, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.1973700179507628, "learning_rate": 1.3426191327998496e-07, "loss": 0.379, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.1895505675934237, "learning_rate": 1.277993209368744e-07, "loss": 0.3746, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.20309278772304917, "learning_rate": 1.214956261808542e-07, "loss": 0.3681, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.19494717847937537, "learning_rate": 1.1535087941609846e-07, "loss": 0.3809, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.18732816078379536, "learning_rate": 1.0936512977583802e-07, "loss": 0.38, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.19113739957198767, "learning_rate": 1.0353842512196732e-07, "loss": 0.3676, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.19390503932805914, "learning_rate": 9.787081204466253e-08, "loss": 0.3844, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.19049350720864233, "learning_rate": 9.236233586200627e-08, "loss": 0.3641, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.19213958105019582, "learning_rate": 8.70130406196279e-08, "loss": 0.373, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.18867114255402778, "learning_rate": 8.182296909035047e-08, "loss": 0.3765, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.1882909200593606, "learning_rate": 7.679216277384439e-08, "loss": 0.3701, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.19025110449317717, "learning_rate": 7.19206618963053e-08, "loss": 0.3699, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.18789451728249046, "learning_rate": 6.720850541012347e-08, "loss": 0.3761, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.19200150170988636, "learning_rate": 6.265573099357714e-08, "loss": 0.3752, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.1943031955049009, "learning_rate": 5.826237505053067e-08, "loss": 0.3745, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.1907273052192125, "learning_rate": 5.4028472710137e-08, "loss": 0.3603, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.1930896637622411, "learning_rate": 4.9954057826571146e-08, "loss": 0.3745, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.1897868446464013, "learning_rate": 4.6039162978743776e-08, "loss": 0.3817, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.18506383317159605, "learning_rate": 4.228381947004812e-08, "loss": 0.3847, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.19072945087740845, "learning_rate": 3.868805732811343e-08, "loss": 0.3833, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.1898826212128884, "learning_rate": 3.525190530455636e-08, "loss": 0.3734, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.19515548805004815, "learning_rate": 3.197539087475887e-08, "loss": 0.3789, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.1927668948098283, "learning_rate": 2.8858540237641786e-08, "loss": 0.3783, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.19060628802054616, "learning_rate": 2.5901378315458247e-08, "loss": 0.3643, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.1893517893355939, "learning_rate": 2.3103928753598347e-08, "loss": 0.373, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.19782429608693977, "learning_rate": 2.0466213920393718e-08, "loss": 0.3659, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.19190190186353334, "learning_rate": 1.7988254906942115e-08, "loss": 0.3875, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.20215830642310123, "learning_rate": 1.5670071526936447e-08, "loss": 0.3772, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.18784450108943931, "learning_rate": 1.3511682316509344e-08, "loss": 0.3857, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.18576503241128428, "learning_rate": 1.1513104534086605e-08, "loss": 0.3785, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.18857292832366265, "learning_rate": 9.67435416023843e-09, "loss": 0.3655, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.18662788382714346, "learning_rate": 7.995445897566178e-09, "loss": 0.3715, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.19033697741123837, "learning_rate": 6.476393170578021e-09, "loss": 0.3804, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.19319594275883561, "learning_rate": 5.11720812557348e-09, "loss": 0.3664, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.19889498939203493, "learning_rate": 3.917901630563492e-09, "loss": 0.3738, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.19475493300847374, "learning_rate": 2.878483275170485e-09, "loss": 0.3684, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.18574878341788922, "learning_rate": 1.998961370555108e-09, "loss": 0.3761, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.2001810293543252, "learning_rate": 1.2793429493518361e-09, "loss": 0.354, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.1912642439520667, "learning_rate": 7.196337656112384e-10, "loss": 0.365, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.19072423732264815, "learning_rate": 3.198382947511292e-10, "loss": 0.3821, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.19145506747946664, "learning_rate": 7.995973352770137e-11, "loss": 0.3709, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19077781358375617, "learning_rate": 0.0, "loss": 0.3681, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 5.21680210452965e+18, "train_loss": 0.4983202329531372, "train_runtime": 29659.7722, "train_samples_per_second": 5.327, "train_steps_per_second": 0.042 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.21680210452965e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }